From c74994eb14c4d1e34f5f5e7ff630c2c7f5f19ad2 Mon Sep 17 00:00:00 2001
From: akshayaurora <akshayaurora@gmail.com>
Date: Sat, 10 Dec 2016 04:08:27 +0530
Subject: [PATCH 1/2] fix pkgresources recipe
---
recipes/pkgresources/__init__.py | 2 +-
recipes/pkgresources/{ => pkgr}/pkg_resources.py | 0
2 files changed, 1 insertion(+), 1 deletion(-)
rename recipes/pkgresources/{ => pkgr}/pkg_resources.py (100%)
diff --git a/recipes/pkgresources/__init__.py b/recipes/pkgresources/__init__.py
index a46869f..8924556 100644
--- a/recipes/pkgresources/__init__.py
+++ b/recipes/pkgresources/__init__.py
@@ -7,7 +7,7 @@ import os
class pkg_resources(Recipe):
depends = ["hostpython", "python"]
archs = ['i386']
- url = ""
+ url = "pkgr"
def prebuild_arch(self, arch):
sh.cp("pkg_resources.py", join(self.ctx.dist_dir, "root", "python", "lib", "python2.7", "site-packages", "pkg_resources.py"))
diff --git a/recipes/pkgresources/pkg_resources.py b/recipes/pkgresources/pkgr/pkg_resources.py
similarity index 100%
rename from recipes/pkgresources/pkg_resources.py
rename to recipes/pkgresources/pkgr/pkg_resources.py
From 8655bf279b8edb47d3920ffca2095880b4420053 Mon Sep 17 00:00:00 2001
From: akshayaurora <akshayaurora@gmail.com>
Date: Mon, 26 Dec 2016 21:07:38 +0530
Subject: [PATCH 2/2] Update PIL and Libffi recipes to latest versions
---
recipes/host_setuptools/__init__.py | 27 +-
recipes/hostlibffi/__init__.py | 3 +-
recipes/pil/__init__.py | 10 +-
recipes/pil/pil_setup.patch | 128 +-
recipes/pkgresources/__init__.py | 7 +-
.../pkgr/{pkg_resources.py => __init__.py} | 1448 +++--
recipes/pkgresources/pkgr/_vendor/__init__.py | 0
recipes/pkgresources/pkgr/_vendor/appdirs.py | 552 ++
.../pkgr/_vendor/packaging/__about__.py | 21 +
.../pkgr/_vendor/packaging/__init__.py | 14 +
.../pkgr/_vendor/packaging/_compat.py | 30 +
.../pkgr/_vendor/packaging/_structures.py | 68 +
.../pkgr/_vendor/packaging/markers.py | 301 +
.../pkgr/_vendor/packaging/requirements.py | 127 +
.../pkgr/_vendor/packaging/specifiers.py | 774 +++
.../pkgr/_vendor/packaging/utils.py | 14 +
.../pkgr/_vendor/packaging/version.py | 393 ++
.../pkgresources/pkgr/_vendor/pyparsing.py | 5696 +++++++++++++++++
recipes/pkgresources/pkgr/_vendor/six.py | 868 +++
recipes/pkgresources/pkgr/extern/__init__.py | 73 +
20 files changed, 9849 insertions(+), 705 deletions(-)
rename recipes/pkgresources/pkgr/{pkg_resources.py => __init__.py} (75%)
create mode 100644 recipes/pkgresources/pkgr/_vendor/__init__.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/appdirs.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/__about__.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/__init__.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/_compat.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/_structures.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/markers.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/requirements.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/specifiers.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/utils.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/packaging/version.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/pyparsing.py
create mode 100644 recipes/pkgresources/pkgr/_vendor/six.py
create mode 100644 recipes/pkgresources/pkgr/extern/__init__.py
diff --git a/recipes/host_setuptools/__init__.py b/recipes/host_setuptools/__init__.py
index 5ee6056..53f6a7f 100644
--- a/recipes/host_setuptools/__init__.py
+++ b/recipes/host_setuptools/__init__.py
@@ -11,10 +11,27 @@ class HostSetuptools(Recipe):
archs = ["x86_64"]
url = "setuptools"
+ def get_stt_env(self, arch):
+ build_env = arch.get_env()
+ build_env["IOSROOT"] = self.ctx.root_dir
+ build_env["IOSSDKROOT"] = arch.sysroot
+ build_env["LDSHARED"] = join(self.ctx.root_dir, "tools", "liblink")
+ build_env["ARM_LD"] = build_env["LD"]
+ build_env["ARCH"] = arch.arch
+ build_env["C_INCLUDE_PATH"] = join(arch.sysroot, "usr", "include")
+ build_env["LIBRARY_PATH"] = join(arch.sysroot, "usr", "lib")
+ build_env["CFLAGS"] = " ".join([
+ "-I{}".format(join(self.ctx.dist_dir, "include", arch.arch, "freetype")) +
+ " -I{}".format(join(self.ctx.dist_dir, "include", arch.arch, "libjpeg")) +
+ " -arch {}".format(arch.arch)
+ ])
+ return build_env
+
+
def prebuild_arch(self, arch):
hostpython = sh.Command(self.ctx.hostpython)
sh.curl("-O", "https://bootstrap.pypa.io/ez_setup.py")
- shprint(hostpython, "./ez_setup.py")
+ shprint(hostpython, "./ez_setup.py", _env=self.get_stt_env(arch))
# Extract setuptools egg and remove .pth files. Otherwise subsequent
# python package installations using setuptools will raise exceptions.
# Setuptools version 28.3.0
@@ -26,9 +43,9 @@ class HostSetuptools(Recipe):
setuptools_egg_path = f.read().strip('./').strip('\n')
unzip = sh.Command('unzip')
shprint(unzip, setuptools_egg_path)
- os.remove(setuptools_egg_path)
- os.remove('setuptools.pth')
- os.remove('easy-install.pth')
- shutil.rmtree('EGG-INFO')
+ #os.remove(setuptools_egg_path)
+ #os.remove('setuptools.pth')
+ #os.remove('easy-install.pth')
+ #shutil.rmtree('EGG-INFO')
recipe = HostSetuptools()
diff --git a/recipes/hostlibffi/__init__.py b/recipes/hostlibffi/__init__.py
index 7d64efa..a0a0ada 100644
--- a/recipes/hostlibffi/__init__.py
+++ b/recipes/hostlibffi/__init__.py
@@ -4,7 +4,8 @@ import sh
class LibffiRecipe(Recipe):
version = "3.2.1"
- url = "ftp://sourceware.org/pub/libffi/libffi-{version}.tar.gz"
+ #url = "ftp://sourceware.org/pub/libffi/libffi-{version}.tar.gz"
+ url = "https://www.mirrorservice.org/sites/sourceware.org/pub/libffi/libffi-{version}.tar.gz"
library = "build/Release-{arch.sdk}/libffi.a"
include_per_arch = True
include_dir = "build_{arch.sdk}-{arch.arch}/include"
diff --git a/recipes/pil/__init__.py b/recipes/pil/__init__.py
index f2e159c..f4bee01 100644
--- a/recipes/pil/__init__.py
+++ b/recipes/pil/__init__.py
@@ -6,9 +6,9 @@ import fnmatch
class PillowRecipe(Recipe):
- version = "2.8.2"
- url = "https://pypi.python.org/packages/source/P/Pillow/Pillow-{version}.tar.gz"
- #url = "https://github.com/python-pillow/Pillow/archive/{version}.tar.gz"
+ version = "3.4.2"
+ #url = "https://pypi.python.org/packages/source/P/Pillow/Pillow-{version}.tar.gz"
+ url = "https://github.com/python-pillow/Pillow/archive/{version}.tar.gz"
library = "libpil.a"
depends = ["hostpython", "host_setuptools", "pkgresources", "freetype", "libjpeg", "python", "ios"]
pbx_libraries = ["libz", "libbz2"]
@@ -49,7 +49,9 @@ class PillowRecipe(Recipe):
build_env = self.get_pil_env(arch)
dest_dir = join(self.ctx.dist_dir, "root", "python")
build_env['PYTHONPATH'] = join(dest_dir, 'lib', 'python2.7', 'site-packages')
- shprint(hostpython, "-m", "easy_install",
+ es = self.ctx.dist_dir + '/hostpython/bin/easy_install'
+ easy_install = sh.Command(es)
+ shprint(easy_install,
"--prefix", dest_dir, "-Z", "./",
_env=build_env)
diff --git a/recipes/pil/pil_setup.patch b/recipes/pil/pil_setup.patch
index 7b54193..571d6b5 100644
--- a/recipes/pil/pil_setup.patch
+++ b/recipes/pil/pil_setup.patch
@@ -1,60 +1,94 @@
---- Pillow-2.7.0/setup.py 2014-12-31 20:42:56.000000000 +0530
-+++ Pillow-2.7.0/setup.py 2015-02-26 19:38:59.000000000 +0530
-@@ -20,7 +20,6 @@
-
+--- Pillow-3.4.2/setup.py 2016-12-19 19:10:30.000000000 +0530
++++ Pillow-2.4.2/setup.py 2016-12-19 23:07:15.000000000 +0530
+@@ -6,7 +6,9 @@
+ # Final rating: 10/10
+ # Your cheese is so fresh most people think it's a cream: Mascarpone
+ # ------------------------------
++
+ from __future__ import print_function
++BUILD_IOS = True
+ import glob
+ import os
+ import platform as plat
+@@ -21,7 +23,8 @@
+
# monkey patch import hook. Even though flake8 says it's not used, it is.
# comment this out to disable multi threaded builds.
-import mp_compile
-
- _IMAGING = (
- "decode", "encode", "map", "display", "outline", "path")
-@@ -83,7 +82,7 @@
++if not BUILD_IOS:
++ import mp_compile
+
+ _IMAGING = ("decode", "encode", "map", "display", "outline", "path")
+
+@@ -103,11 +106,13 @@
return open(file, 'rb').read()
-
- try:
+
+
+-try:
- import _tkinter
-+ _tkinter = None
- except (ImportError, OSError):
- # pypy emits an oserror
- _tkinter = None
-@@ -186,7 +185,7 @@
- for d in os.environ[k].split(os.path.pathsep):
+-except (ImportError, OSError):
+- # pypy emits an oserror
+- _tkinter = None
++_tkinter = None
++if not BUILD_IOS:
++ try:
++ import _tkinter
++ except (ImportError, OSError):
++ # pypy emits an oserror
++ pass
+
+ NAME = 'Pillow'
+ PILLOW_VERSION = '3.4.2'
+@@ -216,7 +221,7 @@
_add_directory(library_dirs, d)
-
-- prefix = sysconfig.get_config_var("prefix")
-+ prefix = False
- if prefix:
+
+ prefix = sysconfig.get_config_var("prefix")
+- if prefix:
++ if not BUILD_IOS and prefix:
_add_directory(library_dirs, os.path.join(prefix, "lib"))
_add_directory(include_dirs, os.path.join(prefix, "include"))
-@@ -199,7 +198,9 @@
- _add_directory(library_dirs, os.path.join(
- "/usr/lib", "python%s" % sys.version[:3], "config"))
-
+
+@@ -232,7 +237,7 @@
+ os.path.join("/usr/lib", "python%s" %
+ sys.version[:3], "config"))
+
- elif sys.platform == "darwin":
-+ elif True:
-+ pass
-+ if False:
++ elif not BUILD_IOS and sys.platform == "darwin":
# attempt to make sure we pick freetype2 over other versions
_add_directory(include_dirs, "/sw/include/freetype2")
_add_directory(include_dirs, "/sw/lib/freetype2/include")
-@@ -346,11 +347,7 @@
- _add_directory(include_dirs, tcl_dir)
-
+@@ -346,7 +351,7 @@
+ # FIXME: check /opt/stuff directories here?
+
# standard locations
-- _add_directory(library_dirs, "/usr/local/lib")
-- _add_directory(include_dirs, "/usr/local/include")
-
-- _add_directory(library_dirs, "/usr/lib")
-- _add_directory(include_dirs, "/usr/include")
-
- # on Windows, look for the OpenJPEG libraries in the location that
- # the official installer puts them
-@@ -575,7 +572,7 @@
- exts.append(Extension(
- "PIL._webp", ["_webp.c"], libraries=libs, define_macros=defs))
-
-- if sys.platform == "darwin":
-+ if False:
- # locate Tcl/Tk frameworks
- frameworks = []
- framework_roots = [
+- if not self.disable_platform_guessing:
++ if not BUILD_IOS and not self.disable_platform_guessing:
+ _add_directory(library_dirs, "/usr/local/lib")
+ _add_directory(include_dirs, "/usr/local/include")
+
+@@ -389,7 +394,9 @@
+
+ if feature.want('zlib'):
+ _dbg('Looking for zlib')
+- if _find_include_file(self, "zlib.h"):
++ if BUILD_IOS:
++ feature.zlib = 'z'
++ elif _find_include_file(self, "zlib.h"):
+ if _find_library_file(self, "z"):
+ feature.zlib = "z"
+ elif (sys.platform == "win32" and
+@@ -592,10 +599,10 @@
+ define_macros=defs))
+
+ tk_libs = ['psapi'] if sys.platform == 'win32' else []
+- exts.append(Extension("PIL._imagingtk",
+- ["_imagingtk.c", "Tk/tkImaging.c"],
+- include_dirs=['Tk'],
+- libraries=tk_libs))
++# exts.append(Extension("PIL._imagingtk",
++# ["_imagingtk.c", "Tk/tkImaging.c"],
++# include_dirs=['Tk'],
++# libraries=tk_libs))
+
+ exts.append(Extension("PIL._imagingmath", ["_imagingmath.c"]))
+ exts.append(Extension("PIL._imagingmorph", ["_imagingmorph.c"]))
diff --git a/recipes/pkgresources/__init__.py b/recipes/pkgresources/__init__.py
index 8924556..cc723b5 100644
--- a/recipes/pkgresources/__init__.py
+++ b/recipes/pkgresources/__init__.py
@@ -10,7 +10,12 @@ class pkg_resources(Recipe):
url = "pkgr"
def prebuild_arch(self, arch):
- sh.cp("pkg_resources.py", join(self.ctx.dist_dir, "root", "python", "lib", "python2.7", "site-packages", "pkg_resources.py"))
+ pkgdir = join(self.ctx.dist_dir, "root", "python", "lib", "python2.7", "site-packages", "pkg_resources")
+ if not os.path.exists(pkgdir):
+ sh.mkdir(pkgdir)
+ sh.cp("-a", "./", pkgdir)
+ #sh.pip('install', '-t', join(self.ctx.dist_dir, "root", "python", "lib", "python2.7", "site-packages"))
+
recipe = pkg_resources()
diff --git a/recipes/pkgresources/pkgr/pkg_resources.py b/recipes/pkgresources/pkgr/__init__.py
similarity index 75%
rename from recipes/pkgresources/pkgr/pkg_resources.py
rename to recipes/pkgresources/pkgr/__init__.py
index 511068a..9250328 100644
--- a/recipes/pkgresources/pkgr/pkg_resources.py
+++ b/recipes/pkgresources/pkgr/__init__.py
@@ -1,3 +1,4 @@
+# coding: utf-8
"""
Package resource API
--------------------
@@ -14,41 +15,38 @@ The package resource API is designed to work with normal filesystem packages,
method.
"""
+from __future__ import absolute_import
+
import sys
import os
import io
import time
import re
-import imp
+import types
import zipfile
import zipimport
import warnings
import stat
import functools
import pkgutil
-import token
-import symbol
import operator
import platform
import collections
import plistlib
import email.parser
import tempfile
+import textwrap
+import itertools
from pkgutil import get_importer
-PY3 = sys.version_info > (3,)
-PY2 = not PY3
+try:
+ import _imp
+except ImportError:
+ # Python 3.2 compatibility
+ import imp as _imp
-if PY3:
- from urllib.parse import urlparse, urlunparse
-
-if PY2:
- from urlparse import urlparse, urlunparse
-
-if PY3:
- string_types = str,
-else:
- string_types = str, eval('unicode')
+from pkg_resources.extern import six
+from pkg_resources.extern.six.moves import urllib, map, filter
# capture these to bypass sandboxing
from os import utime
@@ -62,50 +60,190 @@ except ImportError:
from os import open as os_open
from os.path import isdir, split
-# Avoid try/except due to potential problems with delayed import mechanisms.
-if sys.version_info >= (3, 3) and sys.implementation.name == "cpython":
- import importlib._bootstrap as importlib_bootstrap
-else:
- importlib_bootstrap = None
-
try:
- import parser
+ import importlib.machinery as importlib_machinery
+ # access attribute to force import under delayed import mechanisms.
+ importlib_machinery.__name__
except ImportError:
+ importlib_machinery = None
+
+from pkg_resources.extern import appdirs
+from pkg_resources.extern import packaging
+__import__('pkg_resources.extern.packaging.version')
+__import__('pkg_resources.extern.packaging.specifiers')
+__import__('pkg_resources.extern.packaging.requirements')
+__import__('pkg_resources.extern.packaging.markers')
+
+if (3, 0) < sys.version_info < (3, 3):
+ raise RuntimeError("Python 3.3 or later is required")
+
+# declare some globals that will be defined later to
+# satisfy the linters.
+require = None
+working_set = None
+
+
+class PEP440Warning(RuntimeWarning):
+ """
+ Used when there is an issue with a version or specifier not complying with
+ PEP 440.
+ """
+
+
+class _SetuptoolsVersionMixin(object):
+ def __hash__(self):
+ return super(_SetuptoolsVersionMixin, self).__hash__()
+
+ def __lt__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) < other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__lt__(other)
+
+ def __le__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) <= other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__le__(other)
+
+ def __eq__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) == other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__eq__(other)
+
+ def __ge__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) >= other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__ge__(other)
+
+ def __gt__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) > other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__gt__(other)
+
+ def __ne__(self, other):
+ if isinstance(other, tuple):
+ return tuple(self) != other
+ else:
+ return super(_SetuptoolsVersionMixin, self).__ne__(other)
+
+ def __getitem__(self, key):
+ return tuple(self)[key]
+
+ def __iter__(self):
+ component_re = re.compile(r'(\d+ | [a-z]+ | \.| -)', re.VERBOSE)
+ replace = {
+ 'pre': 'c',
+ 'preview': 'c',
+ '-': 'final-',
+ 'rc': 'c',
+ 'dev': '@',
+ }.get
+
+ def _parse_version_parts(s):
+ for part in component_re.split(s):
+ part = replace(part, part)
+ if not part or part == '.':
+ continue
+ if part[:1] in '0123456789':
+ # pad for numeric comparison
+ yield part.zfill(8)
+ else:
+ yield '*' + part
+
+ # ensure that alpha/beta/candidate are before final
+ yield '*final'
+
+ def old_parse_version(s):
+ parts = []
+ for part in _parse_version_parts(s.lower()):
+ if part.startswith('*'):
+ # remove '-' before a prerelease tag
+ if part < '*final':
+ while parts and parts[-1] == '*final-':
+ parts.pop()
+ # remove trailing zeros from each series of numeric parts
+ while parts and parts[-1] == '00000000':
+ parts.pop()
+ parts.append(part)
+ return tuple(parts)
+
+ # Warn for use of this function
+ warnings.warn(
+ "You have iterated over the result of "
+ "pkg_resources.parse_version. This is a legacy behavior which is "
+ "inconsistent with the new version class introduced in setuptools "
+ "8.0. In most cases, conversion to a tuple is unnecessary. For "
+ "comparison of versions, sort the Version instances directly. If "
+ "you have another use case requiring the tuple, please file a "
+ "bug with the setuptools project describing that need.",
+ RuntimeWarning,
+ stacklevel=1,
+ )
+
+ for part in old_parse_version(str(self)):
+ yield part
+
+
+class SetuptoolsVersion(_SetuptoolsVersionMixin, packaging.version.Version):
pass
+class SetuptoolsLegacyVersion(_SetuptoolsVersionMixin,
+ packaging.version.LegacyVersion):
+ pass
+
+
+def parse_version(v):
+ try:
+ return SetuptoolsVersion(v)
+ except packaging.version.InvalidVersion:
+ return SetuptoolsLegacyVersion(v)
+
+
_state_vars = {}
+
def _declare_state(vartype, **kw):
globals().update(kw)
_state_vars.update(dict.fromkeys(kw, vartype))
+
def __getstate__():
state = {}
g = globals()
for k, v in _state_vars.items():
- state[k] = g['_sget_'+v](g[k])
+ state[k] = g['_sget_' + v](g[k])
return state
+
def __setstate__(state):
g = globals()
for k, v in state.items():
- g['_sset_'+_state_vars[k]](k, g[k], v)
+ g['_sset_' + _state_vars[k]](k, g[k], v)
return state
+
def _sget_dict(val):
return val.copy()
+
def _sset_dict(key, ob, state):
ob.clear()
ob.update(state)
+
def _sget_object(val):
return val.__getstate__()
+
def _sset_object(key, ob, state):
ob.__setstate__(state)
+
_sget_none = _sset_none = lambda *args: None
@@ -132,9 +270,10 @@ def get_supported_platform():
pass
return plat
+
__all__ = [
# Basic resource access and distribution/entry point discovery
- 'require', 'run_script', 'get_provider', 'get_distribution',
+ 'require', 'run_script', 'get_provider', 'get_distribution',
'load_entry_point', 'get_entry_map', 'get_entry_info',
'iter_entry_points',
'resource_string', 'resource_stream', 'resource_filename',
@@ -153,6 +292,9 @@ __all__ = [
'ResolutionError', 'VersionConflict', 'DistributionNotFound',
'UnknownExtra', 'ExtractionError',
+ # Warnings
+ 'PEP440Warning',
+
# Parsing functions and string utilities
'parse_requirements', 'parse_version', 'safe_name', 'safe_version',
'get_platform', 'compatible_platforms', 'yield_lines', 'split_sections',
@@ -175,19 +317,90 @@ __all__ = [
'run_main', 'AvailableDistributions',
]
+
class ResolutionError(Exception):
"""Abstract base for dependency resolution errors"""
+
def __repr__(self):
- return self.__class__.__name__+repr(self.args)
+ return self.__class__.__name__ + repr(self.args)
+
class VersionConflict(ResolutionError):
- """An already-installed version conflicts with the requested version"""
+ """
+ An already-installed version conflicts with the requested version.
+
+ Should be initialized with the installed Distribution and the requested
+ Requirement.
+ """
+
+ _template = "{self.dist} is installed but {self.req} is required"
+
+ @property
+ def dist(self):
+ return self.args[0]
+
+ @property
+ def req(self):
+ return self.args[1]
+
+ def report(self):
+ return self._template.format(**locals())
+
+ def with_context(self, required_by):
+ """
+ If required_by is non-empty, return a version of self that is a
+ ContextualVersionConflict.
+ """
+ if not required_by:
+ return self
+ args = self.args + (required_by,)
+ return ContextualVersionConflict(*args)
+
+
+class ContextualVersionConflict(VersionConflict):
+ """
+ A VersionConflict that accepts a third parameter, the set of the
+ requirements that required the installed Distribution.
+ """
+
+ _template = VersionConflict._template + ' by {self.required_by}'
+
+ @property
+ def required_by(self):
+ return self.args[2]
+
class DistributionNotFound(ResolutionError):
"""A requested distribution was not found"""
+ _template = ("The '{self.req}' distribution was not found "
+ "and is required by {self.requirers_str}")
+
+ @property
+ def req(self):
+ return self.args[0]
+
+ @property
+ def requirers(self):
+ return self.args[1]
+
+ @property
+ def requirers_str(self):
+ if not self.requirers:
+ return 'the application'
+ return ', '.join(self.requirers)
+
+ def report(self):
+ return self._template.format(**locals())
+
+ def __str__(self):
+ return self.report()
+
+
class UnknownExtra(ResolutionError):
"""Distribution doesn't have an "extra feature" of the given name"""
+
+
_provider_factories = {}
PY_MAJOR = sys.version[:3]
@@ -197,6 +410,7 @@ SOURCE_DIST = 1
CHECKOUT_DIST = 0
DEVELOP_DIST = -1
+
def register_loader_type(loader_type, provider_factory):
"""Register `provider_factory` to make providers for `loader_type`
@@ -206,6 +420,7 @@ def register_loader_type(loader_type, provider_factory):
"""
_provider_factories[loader_type] = provider_factory
+
def get_provider(moduleOrReq):
"""Return an IResourceProvider for the named module or requirement"""
if isinstance(moduleOrReq, Requirement):
@@ -218,6 +433,7 @@ def get_provider(moduleOrReq):
loader = getattr(module, '__loader__', None)
return _find_adapter(_provider_factories, loader)(module)
+
def _macosx_vers(_cache=[]):
if not _cache:
version = platform.mac_ver()[0]
@@ -233,9 +449,11 @@ def _macosx_vers(_cache=[]):
_cache.append(version.split('.'))
return _cache[0]
+
def _macosx_arch(machine):
return {'PowerPC': 'ppc', 'Power_Macintosh': 'ppc'}.get(machine, machine)
+
def get_build_platform():
"""Return this platform's string for platform-specific distributions
@@ -261,6 +479,7 @@ def get_build_platform():
pass
return plat
+
macosVersionString = re.compile(r"macosx-(\d+)\.(\d+)-(.*)")
darwinVersionString = re.compile(r"darwin-(\d+)\.(\d+)\.(\d+)-(.*)")
# XXX backward compat
@@ -274,7 +493,7 @@ def compatible_platforms(provided, required):
XXX Needs compatibility checks for Linux and other unixy OSes.
"""
- if provided is None or required is None or provided==required:
+ if provided is None or required is None or provided == required:
# easy case
return True
@@ -321,12 +540,14 @@ def run_script(dist_spec, script_name):
ns['__name__'] = name
require(dist_spec)[0].run_script(script_name, ns)
+
# backward compatibility
run_main = run_script
+
def get_distribution(dist):
"""Return a current distribution object for a Requirement or string"""
- if isinstance(dist, string_types):
+ if isinstance(dist, six.string_types):
dist = Requirement.parse(dist)
if isinstance(dist, Requirement):
dist = get_provider(dist)
@@ -334,21 +555,23 @@ def get_distribution(dist):
raise TypeError("Expected string, Requirement, or Distribution", dist)
return dist
+
def load_entry_point(dist, group, name):
"""Return `name` entry point of `group` for `dist` or raise ImportError"""
return get_distribution(dist).load_entry_point(group, name)
+
def get_entry_map(dist, group=None):
"""Return the entry point map for `group`, or the full entry map"""
return get_distribution(dist).get_entry_map(group)
+
def get_entry_info(dist, group, name):
"""Return the EntryPoint object for `group`+`name`, or ``None``"""
return get_distribution(dist).get_entry_info(group, name)
class IMetadataProvider:
-
def has_metadata(name):
"""Does the package's distribution contain the named metadata?"""
@@ -490,8 +713,7 @@ class WorkingSet(object):
if dist is not None and dist not in req:
# XXX add more info
raise VersionConflict(dist, req)
- else:
- return dist
+ return dist
def iter_entry_points(self, group, name=None):
"""Yield entry point objects from `group` matching `name`
@@ -530,7 +752,7 @@ class WorkingSet(object):
for key in self.entry_keys[item]:
if key not in seen:
- seen[key]=1
+ seen[key] = 1
yield self.by_key[key]
def add(self, dist, entry=None, insert=True, replace=False):
@@ -546,12 +768,12 @@ class WorkingSet(object):
will be called.
"""
if insert:
- dist.insert_on(self.entries, entry)
+ dist.insert_on(self.entries, entry, replace=replace)
if entry is None:
entry = dist.location
- keys = self.entry_keys.setdefault(entry,[])
- keys2 = self.entry_keys.setdefault(dist.location,[])
+ keys = self.entry_keys.setdefault(entry, [])
+ keys2 = self.entry_keys.setdefault(dist.location, [])
if not replace and dist.key in self.by_key:
# ignore hidden distros
return
@@ -590,6 +812,8 @@ class WorkingSet(object):
best = {}
to_activate = []
+ req_extras = _ReqExtras()
+
# Mapping of requirement to set of distributions that required it;
# useful for reporting info about conflicts.
required_by = collections.defaultdict(set)
@@ -600,6 +824,10 @@ class WorkingSet(object):
if req in processed:
# Ignore cyclic or redundant dependencies
continue
+
+ if not req_extras.markers_pass(req):
+ continue
+
dist = best.get(req.key)
if dist is None:
# Find the best distribution and add it to the map
@@ -617,19 +845,13 @@ class WorkingSet(object):
ws = WorkingSet([])
dist = best[req.key] = env.best_match(req, ws, installer)
if dist is None:
- #msg = ("The '%s' distribution was not found on this "
- # "system, and is required by this application.")
- #raise DistributionNotFound(msg % req)
-
- # unfortunately, zc.buildout uses a str(err)
- # to get the name of the distribution here..
- raise DistributionNotFound(req)
+ requirers = required_by.get(req, None)
+ raise DistributionNotFound(req, requirers)
to_activate.append(dist)
if dist not in req:
# Oops, the "best" so far conflicts with a dependency
- tmpl = "%s is installed but %s is required by %s"
- args = dist, req, list(required_by.get(req, []))
- raise VersionConflict(tmpl % args)
+ dependent_req = required_by[req]
+ raise VersionConflict(dist, req).with_context(dependent_req)
# push the new requirements onto the stack
new_requirements = dist.requires(req.extras)[::-1]
@@ -638,6 +860,7 @@ class WorkingSet(object):
# Register the new requirements needed by req
for new_requirement in new_requirements:
required_by[new_requirement].add(req.project_name)
+ req_extras[new_requirement] = req.extras
processed[req] = True
@@ -706,8 +929,7 @@ class WorkingSet(object):
try:
resolvees = shadow_set.resolve(req, env, installer)
- except ResolutionError:
- v = sys.exc_info()[1]
+ except ResolutionError as v:
# save error info
error_info[dist] = v
if fallback:
@@ -745,11 +967,17 @@ class WorkingSet(object):
return needed
- def subscribe(self, callback):
- """Invoke `callback` for all distributions (including existing ones)"""
+ def subscribe(self, callback, existing=True):
+ """Invoke `callback` for all distributions
+
+ If `existing=True` (default),
+ call on all existing ones, as well.
+ """
if callback in self.callbacks:
return
self.callbacks.append(callback)
+ if not existing:
+ return
for dist in self:
callback(dist)
@@ -771,6 +999,26 @@ class WorkingSet(object):
self.callbacks = callbacks[:]
+class _ReqExtras(dict):
+ """
+ Map each requirement to the extras that demanded it.
+ """
+
+ def markers_pass(self, req):
+ """
+ Evaluate markers for req against each extra that
+ demanded it.
+
+ Return False if the req has a marker and fails
+ evaluation. Otherwise, return True.
+ """
+ extra_evals = (
+ req.marker.evaluate({'extra': extra})
+ for extra in self.get(req, ()) + (None,)
+ )
+ return not req.marker or any(extra_evals)
+
+
class Environment(object):
"""Searchable snapshot of distributions on a search path"""
@@ -805,7 +1053,7 @@ class Environment(object):
is returned.
"""
return (self.python is None or dist.py_version is None
- or dist.py_version==self.python) \
+ or dist.py_version == self.python) \
and compatible_platforms(dist.platform, self.platform)
def remove(self, dist):
@@ -974,22 +1222,23 @@ class ResourceManager:
old_exc = sys.exc_info()[1]
cache_path = self.extraction_path or get_default_cache()
- err = ExtractionError("""Can't extract file(s) to egg cache
+ tmpl = textwrap.dedent("""
+ Can't extract file(s) to egg cache
-The following error occurred while trying to extract file(s) to the Python egg
-cache:
+ The following error occurred while trying to extract file(s) to the Python egg
+ cache:
- %s
+ {old_exc}
-The Python egg cache directory is currently set to:
+ The Python egg cache directory is currently set to:
- %s
+ {cache_path}
-Perhaps your account does not have write access to this directory? You can
-change the cache directory by setting the PYTHON_EGG_CACHE environment
-variable to point to an accessible directory.
-""" % (old_exc, cache_path)
- )
+ Perhaps your account does not have write access to this directory? You can
+ change the cache directory by setting the PYTHON_EGG_CACHE environment
+ variable to point to an accessible directory.
+ """).lstrip()
+ err = ExtractionError(tmpl.format(**locals()))
err.manager = self
err.cache_path = cache_path
err.original_error = old_exc
@@ -1009,7 +1258,7 @@ variable to point to an accessible directory.
extract, as it tracks the generated names for possible cleanup later.
"""
extract_path = self.extraction_path or get_default_cache()
- target_path = os.path.join(extract_path, archive_name+'-tmp', *names)
+ target_path = os.path.join(extract_path, archive_name + '-tmp', *names)
try:
_bypass_ensure_directory(target_path)
except:
@@ -1103,49 +1352,18 @@ variable to point to an accessible directory.
"""
# XXX
+
def get_default_cache():
- """Determine the default cache location
-
- This returns the ``PYTHON_EGG_CACHE`` environment variable, if set.
- Otherwise, on Windows, it returns a "Python-Eggs" subdirectory of the
- "Application Data" directory. On all other systems, it's "~/.python-eggs".
"""
- try:
- return os.environ['PYTHON_EGG_CACHE']
- except KeyError:
- pass
+ Return the ``PYTHON_EGG_CACHE`` environment variable
+ or a platform-relevant user cache dir for an app
+ named "Python-Eggs".
+ """
+ return (
+ os.environ.get('PYTHON_EGG_CACHE')
+ or appdirs.user_cache_dir(appname='Python-Eggs')
+ )
- if os.name!='nt':
- return os.path.expanduser('~/.python-eggs')
-
- # XXX this may be locale-specific!
- app_data = 'Application Data'
- app_homes = [
- # best option, should be locale-safe
- (('APPDATA',), None),
- (('USERPROFILE',), app_data),
- (('HOMEDRIVE','HOMEPATH'), app_data),
- (('HOMEPATH',), app_data),
- (('HOME',), None),
- # 95/98/ME
- (('WINDIR',), app_data),
- ]
-
- for keys, subdir in app_homes:
- dirname = ''
- for key in keys:
- if key in os.environ:
- dirname = os.path.join(dirname, os.environ[key])
- else:
- break
- else:
- if subdir:
- dirname = os.path.join(dirname, subdir)
- return os.path.join(dirname, 'Python-Eggs')
- else:
- raise RuntimeError(
- "Please set the PYTHON_EGG_CACHE enviroment variable"
- )
def safe_name(name):
"""Convert an arbitrary string to a standard distribution name
@@ -1156,13 +1374,15 @@ def safe_name(name):
def safe_version(version):
- """Convert an arbitrary string to a standard version string
-
- Spaces become dots, and all other non-alphanumeric characters become
- dashes, with runs of multiple dashes condensed to a single dash.
"""
- version = version.replace(' ','.')
- return re.sub('[^A-Za-z0-9.]+', '-', version)
+ Convert an arbitrary string to a standard version string
+ """
+ try:
+ # normalize the version
+ return str(packaging.version.Version(version))
+ except packaging.version.InvalidVersion:
+ version = version.replace(' ', '.')
+ return re.sub('[^A-Za-z0-9.]+', '-', version)
def safe_extra(extra):
@@ -1171,7 +1391,7 @@ def safe_extra(extra):
Any runs of non-alphanumeric characters are replaced with a single '_',
and the result is always lowercased.
"""
- return re.sub('[^A-Za-z0-9.]+', '_', extra).lower()
+ return re.sub('[^A-Za-z0-9.-]+', '_', extra).lower()
def to_filename(name):
@@ -1179,194 +1399,37 @@ def to_filename(name):
Any '-' characters are currently replaced with '_'.
"""
- return name.replace('-','_')
+ return name.replace('-', '_')
-class MarkerEvaluation(object):
- values = {
- 'os_name': lambda: os.name,
- 'sys_platform': lambda: sys.platform,
- 'python_full_version': platform.python_version,
- 'python_version': lambda: platform.python_version()[:3],
- 'platform_version': platform.version,
- 'platform_machine': platform.machine,
- 'python_implementation': platform.python_implementation,
- }
+def invalid_marker(text):
+ """
+ Validate text as a PEP 508 environment marker; return an exception
+ if invalid or False otherwise.
+ """
+ try:
+ evaluate_marker(text)
+ except SyntaxError as e:
+ e.filename = None
+ e.lineno = None
+ return e
+ return False
- @classmethod
- def is_invalid_marker(cls, text):
- """
- Validate text as a PEP 426 environment marker; return an exception
- if invalid or False otherwise.
- """
- try:
- cls.evaluate_marker(text)
- except SyntaxError:
- return cls.normalize_exception(sys.exc_info()[1])
- return False
- @staticmethod
- def normalize_exception(exc):
- """
- Given a SyntaxError from a marker evaluation, normalize the error
- message:
- - Remove indications of filename and line number.
- - Replace platform-specific error messages with standard error
- messages.
- """
- subs = {
- 'unexpected EOF while parsing': 'invalid syntax',
- 'parenthesis is never closed': 'invalid syntax',
- }
- exc.filename = None
- exc.lineno = None
- exc.msg = subs.get(exc.msg, exc.msg)
- return exc
+def evaluate_marker(text, extra=None):
+ """
+ Evaluate a PEP 508 environment marker.
+ Return a boolean indicating the marker result in this environment.
+ Raise SyntaxError if marker is invalid.
- @classmethod
- def and_test(cls, nodelist):
- # MUST NOT short-circuit evaluation, or invalid syntax can be skipped!
- items = [
- cls.interpret(nodelist[i])
- for i in range(1, len(nodelist), 2)
- ]
- return functools.reduce(operator.and_, items)
+ This implementation uses the 'pyparsing' module.
+ """
+ try:
+ marker = packaging.markers.Marker(text)
+ return marker.evaluate()
+ except packaging.markers.InvalidMarker as e:
+ raise SyntaxError(e)
- @classmethod
- def test(cls, nodelist):
- # MUST NOT short-circuit evaluation, or invalid syntax can be skipped!
- items = [
- cls.interpret(nodelist[i])
- for i in range(1, len(nodelist), 2)
- ]
- return functools.reduce(operator.or_, items)
-
- @classmethod
- def atom(cls, nodelist):
- t = nodelist[1][0]
- if t == token.LPAR:
- if nodelist[2][0] == token.RPAR:
- raise SyntaxError("Empty parentheses")
- return cls.interpret(nodelist[2])
- msg = "Language feature not supported in environment markers"
- raise SyntaxError(msg)
-
- @classmethod
- def comparison(cls, nodelist):
- if len(nodelist) > 4:
- msg = "Chained comparison not allowed in environment markers"
- raise SyntaxError(msg)
- comp = nodelist[2][1]
- cop = comp[1]
- if comp[0] == token.NAME:
- if len(nodelist[2]) == 3:
- if cop == 'not':
- cop = 'not in'
- else:
- cop = 'is not'
- try:
- cop = cls.get_op(cop)
- except KeyError:
- msg = repr(cop) + " operator not allowed in environment markers"
- raise SyntaxError(msg)
- return cop(cls.evaluate(nodelist[1]), cls.evaluate(nodelist[3]))
-
- @classmethod
- def get_op(cls, op):
- ops = {
- symbol.test: cls.test,
- symbol.and_test: cls.and_test,
- symbol.atom: cls.atom,
- symbol.comparison: cls.comparison,
- 'not in': lambda x, y: x not in y,
- 'in': lambda x, y: x in y,
- '==': operator.eq,
- '!=': operator.ne,
- }
- if hasattr(symbol, 'or_test'):
- ops[symbol.or_test] = cls.test
- return ops[op]
-
- @classmethod
- def evaluate_marker(cls, text, extra=None):
- """
- Evaluate a PEP 426 environment marker on CPython 2.4+.
- Return a boolean indicating the marker result in this environment.
- Raise SyntaxError if marker is invalid.
-
- This implementation uses the 'parser' module, which is not implemented
- on
- Jython and has been superseded by the 'ast' module in Python 2.6 and
- later.
- """
- return cls.interpret(parser.expr(text).totuple(1)[1])
-
- @classmethod
- def _markerlib_evaluate(cls, text):
- """
- Evaluate a PEP 426 environment marker using markerlib.
- Return a boolean indicating the marker result in this environment.
- Raise SyntaxError if marker is invalid.
- """
- import _markerlib
- # markerlib implements Metadata 1.2 (PEP 345) environment markers.
- # Translate the variables to Metadata 2.0 (PEP 426).
- env = _markerlib.default_environment()
- for key in env.keys():
- new_key = key.replace('.', '_')
- env[new_key] = env.pop(key)
- try:
- result = _markerlib.interpret(text, env)
- except NameError:
- e = sys.exc_info()[1]
- raise SyntaxError(e.args[0])
- return result
-
- if 'parser' not in globals():
- # Fall back to less-complete _markerlib implementation if 'parser' module
- # is not available.
- evaluate_marker = _markerlib_evaluate
-
- @classmethod
- def interpret(cls, nodelist):
- while len(nodelist)==2: nodelist = nodelist[1]
- try:
- op = cls.get_op(nodelist[0])
- except KeyError:
- raise SyntaxError("Comparison or logical expression expected")
- return op(nodelist)
-
- @classmethod
- def evaluate(cls, nodelist):
- while len(nodelist)==2: nodelist = nodelist[1]
- kind = nodelist[0]
- name = nodelist[1]
- if kind==token.NAME:
- try:
- op = cls.values[name]
- except KeyError:
- raise SyntaxError("Unknown name %r" % name)
- return op()
- if kind==token.STRING:
- s = nodelist[1]
- if not cls._safe_string(s):
- raise SyntaxError(
- "Only plain strings allowed in environment markers")
- return s[1:-1]
- msg = "Language feature not supported in environment markers"
- raise SyntaxError(msg)
-
- @staticmethod
- def _safe_string(cand):
- return (
- cand[:1] in "'\"" and
- not cand.startswith('"""') and
- not cand.startswith("'''") and
- '\\' not in cand
- )
-
-invalid_marker = MarkerEvaluation.is_invalid_marker
-evaluate_marker = MarkerEvaluation.evaluate_marker
class NullProvider:
"""Try to implement resources and metadata for arbitrary PEP 302 loaders"""
@@ -1394,16 +1457,11 @@ class NullProvider:
def has_metadata(self, name):
return self.egg_info and self._has(self._fn(self.egg_info, name))
- if sys.version_info <= (3,):
- def get_metadata(self, name):
- if not self.egg_info:
- return ""
- return self._get(self._fn(self.egg_info, name))
- else:
- def get_metadata(self, name):
- if not self.egg_info:
- return ""
- return self._get(self._fn(self.egg_info, name)).decode("utf-8")
+ def get_metadata(self, name):
+ if not self.egg_info:
+ return ""
+ value = self._get(self._fn(self.egg_info, name))
+ return value.decode('utf-8') if six.PY3 else value
def get_metadata_lines(self, name):
return yield_lines(self.get_metadata(name))
@@ -1423,7 +1481,7 @@ class NullProvider:
return []
def run_script(self, script_name, namespace):
- script = 'scripts/'+script_name
+ script = 'scripts/' + script_name
if not self.has_metadata(script):
raise ResolutionError("No script named %r" % script_name)
script_text = self.get_metadata(script).replace('\r\n', '\n')
@@ -1439,7 +1497,7 @@ class NullProvider:
cache[script_filename] = (
len(script_text), 0, script_text.split('\n'), script_filename
)
- script_code = compile(script_text, script_filename,'exec')
+ script_code = compile(script_text, script_filename, 'exec')
exec(script_code, namespace, namespace)
def _has(self, path):
@@ -1469,6 +1527,7 @@ class NullProvider:
"Can't perform this operation for loaders without 'get_data()'"
)
+
register_loader_type(object, NullProvider)
@@ -1484,8 +1543,8 @@ class EggProvider(NullProvider):
# of multiple eggs; that's why we use module_path instead of .archive
path = self.module_path
old = None
- while path!=old:
- if path.lower().endswith('.egg'):
+ while path != old:
+ if _is_unpacked_egg(path):
self.egg_name = os.path.basename(path)
self.egg_info = os.path.join(path, 'EGG-INFO')
self.egg_root = path
@@ -1493,6 +1552,7 @@ class EggProvider(NullProvider):
old = path
path, base = os.path.split(path)
+
class DefaultProvider(EggProvider):
"""Provides access to package resources in the filesystem"""
@@ -1512,10 +1572,14 @@ class DefaultProvider(EggProvider):
with open(path, 'rb') as stream:
return stream.read()
-register_loader_type(type(None), DefaultProvider)
+ @classmethod
+ def _register(cls):
+ loader_cls = getattr(importlib_machinery, 'SourceFileLoader',
+ type(None))
+ register_loader_type(loader_cls, cls)
-if importlib_bootstrap is not None:
- register_loader_type(importlib_bootstrap.SourceFileLoader, DefaultProvider)
+
+DefaultProvider._register()
class EmptyProvider(NullProvider):
@@ -1529,6 +1593,7 @@ class EmptyProvider(NullProvider):
def __init__(self):
pass
+
empty_provider = EmptyProvider()
@@ -1607,7 +1672,7 @@ class ZipProvider(EggProvider):
def __init__(self, module):
EggProvider.__init__(self, module)
- self.zip_pre = self.loader.archive+os.sep
+ self.zip_pre = self.loader.archive + os.sep
def _zipinfo_name(self, fspath):
# Convert a virtual filename (full path to file) into a zipfile subpath
@@ -1621,9 +1686,9 @@ class ZipProvider(EggProvider):
def _parts(self, zip_path):
# Convert a zipfile subpath into an egg-relative path part list.
# pseudo-fs path
- fspath = self.zip_pre+zip_path
- if fspath.startswith(self.egg_root+os.sep):
- return fspath[len(self.egg_root)+1:].split(os.sep)
+ fspath = self.zip_pre + zip_path
+ if fspath.startswith(self.egg_root + os.sep):
+ return fspath[len(self.egg_root) + 1:].split(os.sep)
raise AssertionError(
"%s is not a subpath of %s" % (fspath, self.egg_root)
)
@@ -1694,7 +1759,7 @@ class ZipProvider(EggProvider):
# so proceed.
return real_path
# Windows, del old file and retry
- elif os.name=='nt':
+ elif os.name == 'nt':
unlink(real_path)
rename(tmpnam, real_path)
return real_path
@@ -1714,7 +1779,7 @@ class ZipProvider(EggProvider):
if not os.path.isfile(file_path):
return False
stat = os.stat(file_path)
- if stat.st_size!=size or stat.st_mtime!=timestamp:
+ if stat.st_size != size or stat.st_mtime != timestamp:
return False
# check that the contents match
zip_contents = self.loader.get_data(zip_path)
@@ -1764,6 +1829,7 @@ class ZipProvider(EggProvider):
def _resource_to_zip(self, resource_name):
return self._zipinfo_name(self._fn(self.module_path, resource_name))
+
register_loader_type(zipimport.zipimporter, ZipProvider)
@@ -1783,14 +1849,24 @@ class FileMetadata(EmptyProvider):
self.path = path
def has_metadata(self, name):
- return name=='PKG-INFO'
+ return name == 'PKG-INFO' and os.path.isfile(self.path)
def get_metadata(self, name):
- if name=='PKG-INFO':
- with open(self.path,'rU') as f:
- metadata = f.read()
- return metadata
- raise KeyError("No metadata except PKG-INFO is available")
+ if name != 'PKG-INFO':
+ raise KeyError("No metadata except PKG-INFO is available")
+
+ with io.open(self.path, encoding='utf-8', errors="replace") as f:
+ metadata = f.read()
+ self._warn_on_replacement(metadata)
+ return metadata
+
+ def _warn_on_replacement(self, metadata):
+ # Python 2.6 and 3.2 compat for: replacement_char = '�'
+ replacement_char = b'\xef\xbf\xbd'.decode('utf-8')
+ if replacement_char in metadata:
+ tmpl = "{self.path} could not be properly decoded in UTF-8"
+ msg = tmpl.format(**locals())
+ warnings.warn(msg)
def get_metadata_lines(self, name):
return yield_lines(self.get_metadata(name))
@@ -1827,7 +1903,7 @@ class EggMetadata(ZipProvider):
def __init__(self, importer):
"""Create a metadata provider from a zipimporter"""
- self.zip_pre = importer.archive+os.sep
+ self.zip_pre = importer.archive + os.sep
self.loader = importer
if importer.prefix:
self.module_path = os.path.join(importer.archive, importer.prefix)
@@ -1835,7 +1911,9 @@ class EggMetadata(ZipProvider):
self.module_path = importer.archive
self._setup_prefix()
-_declare_state('dict', _distribution_finders = {})
+
+_declare_state('dict', _distribution_finders={})
+
def register_finder(importer_type, distribution_finder):
"""Register `distribution_finder` to find distributions in sys.path items
@@ -1853,6 +1931,7 @@ def find_distributions(path_item, only=False):
finder = _find_adapter(_distribution_finders, importer)
return finder(importer, path_item, only)
+
def find_eggs_in_zip(importer, path_item, only=False):
"""
Find eggs in zip files; possibly multiple nested eggs.
@@ -1868,44 +1947,78 @@ def find_eggs_in_zip(importer, path_item, only=False):
# don't yield nested distros
return
for subitem in metadata.resource_listdir('/'):
- if subitem.endswith('.egg'):
+ if _is_unpacked_egg(subitem):
subpath = os.path.join(path_item, subitem)
for dist in find_eggs_in_zip(zipimport.zipimporter(subpath), subpath):
yield dist
+
register_finder(zipimport.zipimporter, find_eggs_in_zip)
+
def find_nothing(importer, path_item, only=False):
return ()
+
+
register_finder(object, find_nothing)
+
+def _by_version_descending(names):
+ """
+ Given a list of filenames, return them in descending order
+ by version number.
+
+ >>> names = 'bar', 'foo', 'Python-2.7.10.egg', 'Python-2.7.2.egg'
+ >>> _by_version_descending(names)
+ ['Python-2.7.10.egg', 'Python-2.7.2.egg', 'foo', 'bar']
+ >>> names = 'Setuptools-1.2.3b1.egg', 'Setuptools-1.2.3.egg'
+ >>> _by_version_descending(names)
+ ['Setuptools-1.2.3.egg', 'Setuptools-1.2.3b1.egg']
+ >>> names = 'Setuptools-1.2.3b1.egg', 'Setuptools-1.2.3.post1.egg'
+ >>> _by_version_descending(names)
+ ['Setuptools-1.2.3.post1.egg', 'Setuptools-1.2.3b1.egg']
+ """
+ def _by_version(name):
+ """
+ Parse each component of the filename
+ """
+ name, ext = os.path.splitext(name)
+ parts = itertools.chain(name.split('-'), [ext])
+ return [packaging.version.parse(part) for part in parts]
+
+ return sorted(names, key=_by_version, reverse=True)
+
+
def find_on_path(importer, path_item, only=False):
"""Yield distributions accessible on a sys.path directory"""
path_item = _normalize_cached(path_item)
if os.path.isdir(path_item) and os.access(path_item, os.R_OK):
- if path_item.lower().endswith('.egg'):
- # unpacked egg
+ if _is_unpacked_egg(path_item):
yield Distribution.from_filename(
path_item, metadata=PathMetadata(
- path_item, os.path.join(path_item,'EGG-INFO')
+ path_item, os.path.join(path_item, 'EGG-INFO')
)
)
else:
# scan for .egg and .egg-info in directory
- for entry in os.listdir(path_item):
+ path_item_entries = _by_version_descending(os.listdir(path_item))
+ for entry in path_item_entries:
lower = entry.lower()
if lower.endswith('.egg-info') or lower.endswith('.dist-info'):
fullpath = os.path.join(path_item, entry)
if os.path.isdir(fullpath):
# egg-info directory, allow getting metadata
+ if len(os.listdir(fullpath)) == 0:
+ # Empty egg directory, skip.
+ continue
metadata = PathMetadata(path_item, fullpath)
else:
metadata = FileMetadata(fullpath)
yield Distribution.from_location(
path_item, entry, metadata, precedence=DEVELOP_DIST
)
- elif not only and lower.endswith('.egg'):
+ elif not only and _is_unpacked_egg(entry):
dists = find_distributions(os.path.join(path_item, entry))
for dist in dists:
yield dist
@@ -1920,10 +2033,12 @@ def find_on_path(importer, path_item, only=False):
for item in dists:
yield item
break
+
+
register_finder(pkgutil.ImpImporter, find_on_path)
-if importlib_bootstrap is not None:
- register_finder(importlib_bootstrap.FileFinder, find_on_path)
+if hasattr(importlib_machinery, 'FileFinder'):
+ register_finder(importlib_machinery.FileFinder, find_on_path)
_declare_state('dict', _namespace_handlers={})
_declare_state('dict', _namespace_packages={})
@@ -1946,6 +2061,7 @@ def register_namespace_handler(importer_type, namespace_handler):
"""
_namespace_handlers[importer_type] = namespace_handler
+
def _handle_ns(packageName, path_item):
"""Ensure that named package includes a subpath of path_item (if needed)"""
@@ -1957,10 +2073,10 @@ def _handle_ns(packageName, path_item):
return None
module = sys.modules.get(packageName)
if module is None:
- module = sys.modules[packageName] = imp.new_module(packageName)
+ module = sys.modules[packageName] = types.ModuleType(packageName)
module.__path__ = []
_set_parent_ns(packageName)
- elif not hasattr(module,'__path__'):
+ elif not hasattr(module, '__path__'):
raise TypeError("Not a package:", packageName)
handler = _find_adapter(_namespace_handlers, importer)
subpath = handler(importer, path_item, packageName, module)
@@ -1968,15 +2084,43 @@ def _handle_ns(packageName, path_item):
path = module.__path__
path.append(subpath)
loader.load_module(packageName)
- for path_item in path:
- if path_item not in module.__path__:
- module.__path__.append(path_item)
+ _rebuild_mod_path(path, packageName, module)
return subpath
+
+def _rebuild_mod_path(orig_path, package_name, module):
+ """
+ Rebuild module.__path__ ensuring that all entries are ordered
+ corresponding to their sys.path order
+ """
+ sys_path = [_normalize_cached(p) for p in sys.path]
+
+ def safe_sys_path_index(entry):
+ """
+ Workaround for #520 and #513.
+ """
+ try:
+ return sys_path.index(entry)
+ except ValueError:
+ return float('inf')
+
+ def position_in_sys_path(path):
+ """
+ Return the ordinal of the path based on its position in sys.path
+ """
+ path_parts = path.split(os.sep)
+ module_parts = package_name.count('.') + 1
+ parts = path_parts[:-module_parts]
+ return safe_sys_path_index(_normalize_cached(os.sep.join(parts)))
+
+ orig_path.sort(key=position_in_sys_path)
+ module.__path__[:] = [_normalize_cached(p) for p in orig_path]
+
+
def declare_namespace(packageName):
"""Declare that package 'packageName' is a namespace package"""
- imp.acquire_lock()
+ _imp.acquire_lock()
try:
if packageName in _namespace_packages:
return
@@ -1994,8 +2138,8 @@ def declare_namespace(packageName):
# Track what packages are namespaces, so when new path items are added,
# they can be updated
- _namespace_packages.setdefault(parent,[]).append(packageName)
- _namespace_packages.setdefault(packageName,[])
+ _namespace_packages.setdefault(parent, []).append(packageName)
+ _namespace_packages.setdefault(packageName, [])
for path_item in path:
# Ensure all the parent's path items are reflected in the child,
@@ -2003,18 +2147,20 @@ def declare_namespace(packageName):
_handle_ns(packageName, path_item)
finally:
- imp.release_lock()
+ _imp.release_lock()
+
def fixup_namespace_packages(path_item, parent=None):
"""Ensure that previously-declared namespace packages include path_item"""
- imp.acquire_lock()
+ _imp.acquire_lock()
try:
- for package in _namespace_packages.get(parent,()):
+ for package in _namespace_packages.get(parent, ()):
subpath = _handle_ns(package, path_item)
if subpath:
fixup_namespace_packages(subpath, package)
finally:
- imp.release_lock()
+ _imp.release_lock()
+
def file_ns_handler(importer, path_item, packageName, module):
"""Compute an ns-package subpath for a filesystem or zipfile importer"""
@@ -2022,22 +2168,24 @@ def file_ns_handler(importer, path_item, packageName, module):
subpath = os.path.join(path_item, packageName.split('.')[-1])
normalized = _normalize_cached(subpath)
for item in module.__path__:
- if _normalize_cached(item)==normalized:
+ if _normalize_cached(item) == normalized:
break
else:
# Only return the path if it's not already there
return subpath
+
register_namespace_handler(pkgutil.ImpImporter, file_ns_handler)
register_namespace_handler(zipimport.zipimporter, file_ns_handler)
-if importlib_bootstrap is not None:
- register_namespace_handler(importlib_bootstrap.FileFinder, file_ns_handler)
+if hasattr(importlib_machinery, 'FileFinder'):
+ register_namespace_handler(importlib_machinery.FileFinder, file_ns_handler)
def null_ns_handler(importer, path_item, packageName, module):
return None
+
register_namespace_handler(object, null_ns_handler)
@@ -2045,6 +2193,7 @@ def normalize_path(filename):
"""Normalize a file/dir name for comparison purposes"""
return os.path.normcase(os.path.realpath(filename))
+
def _normalize_cached(filename, _cache={}):
try:
return _cache[filename]
@@ -2052,6 +2201,16 @@ def _normalize_cached(filename, _cache={}):
_cache[filename] = result = normalize_path(filename)
return result
+
+def _is_unpacked_egg(path):
+ """
+ Determine if given path appears to be an unpacked egg.
+ """
+ return (
+ path.lower().endswith('.egg')
+ )
+
+
def _set_parent_ns(packageName):
parts = packageName.split('.')
name = parts.pop()
@@ -2062,7 +2221,7 @@ def _set_parent_ns(packageName):
def yield_lines(strs):
"""Yield non-empty/non-comment lines of a string or sequence"""
- if isinstance(strs, string_types):
+ if isinstance(strs, six.string_types):
for s in strs.splitlines():
s = s.strip()
# skip blank lines/comments
@@ -2073,86 +2232,21 @@ def yield_lines(strs):
for s in yield_lines(ss):
yield s
-# whitespace and comment
-LINE_END = re.compile(r"\s*(#.*)?$").match
-# line continuation
-CONTINUE = re.compile(r"\s*\\\s*(#.*)?$").match
-# Distribution or extra
-DISTRO = re.compile(r"\s*((\w|[-.])+)").match
-# ver. info
-VERSION = re.compile(r"\s*(<=?|>=?|==|!=)\s*((\w|[-.])+)").match
-# comma between items
-COMMA = re.compile(r"\s*,").match
-OBRACKET = re.compile(r"\s*\[").match
-CBRACKET = re.compile(r"\s*\]").match
+
MODULE = re.compile(r"\w+(\.\w+)*$").match
EGG_NAME = re.compile(
- r"(?P<name>[^-]+)"
- r"( -(?P<ver>[^-]+) (-py(?P<pyver>[^-]+) (-(?P<plat>.+))? )? )?",
- re.VERBOSE | re.IGNORECASE
+ r"""
+ (?P<name>[^-]+) (
+ -(?P<ver>[^-]+) (
+ -py(?P<pyver>[^-]+) (
+ -(?P<plat>.+)
+ )?
+ )?
+ )?
+ """,
+ re.VERBOSE | re.IGNORECASE,
).match
-component_re = re.compile(r'(\d+ | [a-z]+ | \.| -)', re.VERBOSE)
-replace = {'pre':'c', 'preview':'c','-':'final-','rc':'c','dev':'@'}.get
-
-def _parse_version_parts(s):
- for part in component_re.split(s):
- part = replace(part, part)
- if not part or part=='.':
- continue
- if part[:1] in '0123456789':
- # pad for numeric comparison
- yield part.zfill(8)
- else:
- yield '*'+part
-
- # ensure that alpha/beta/candidate are before final
- yield '*final'
-
-def parse_version(s):
- """Convert a version string to a chronologically-sortable key
-
- This is a rough cross between distutils' StrictVersion and LooseVersion;
- if you give it versions that would work with StrictVersion, then it behaves
- the same; otherwise it acts like a slightly-smarter LooseVersion. It is
- *possible* to create pathological version coding schemes that will fool
- this parser, but they should be very rare in practice.
-
- The returned value will be a tuple of strings. Numeric portions of the
- version are padded to 8 digits so they will compare numerically, but
- without relying on how numbers compare relative to strings. Dots are
- dropped, but dashes are retained. Trailing zeros between alpha segments
- or dashes are suppressed, so that e.g. "2.4.0" is considered the same as
- "2.4". Alphanumeric parts are lower-cased.
-
- The algorithm assumes that strings like "-" and any alpha string that
- alphabetically follows "final" represents a "patch level". So, "2.4-1"
- is assumed to be a branch or patch of "2.4", and therefore "2.4.1" is
- considered newer than "2.4-1", which in turn is newer than "2.4".
-
- Strings like "a", "b", "c", "alpha", "beta", "candidate" and so on (that
- come before "final" alphabetically) are assumed to be pre-release versions,
- so that the version "2.4" is considered newer than "2.4a1".
-
- Finally, to handle miscellaneous cases, the strings "pre", "preview", and
- "rc" are treated as if they were "c", i.e. as though they were release
- candidates, and therefore are not as new as a version string that does not
- contain them, and "dev" is replaced with an '@' so that it sorts lower than
- than any other pre-release tag.
- """
- parts = []
- for part in _parse_version_parts(s.lower()):
- if part.startswith('*'):
- # remove '-' before a prerelease tag
- if part < '*final':
- while parts and parts[-1] == '*final-':
- parts.pop()
- # remove trailing zeros from each series of numeric parts
- while parts and parts[-1]=='00000000':
- parts.pop()
- parts.append(part)
- return tuple(parts)
-
class EntryPoint(object):
"""Object representing an advertised importable object"""
@@ -2177,17 +2271,30 @@ class EntryPoint(object):
def __repr__(self):
return "EntryPoint.parse(%r)" % str(self)
- def load(self, require=True, env=None, installer=None):
+ def load(self, require=True, *args, **kwargs):
+ """
+ Require packages for this EntryPoint, then resolve it.
+ """
+ if not require or args or kwargs:
+ warnings.warn(
+ "Parameters to load are deprecated. Call .resolve and "
+ ".require separately.",
+ DeprecationWarning,
+ stacklevel=2,
+ )
if require:
- self.require(env, installer)
- entry = __import__(self.module_name, globals(), globals(),
- ['__name__'])
- for attr in self.attrs:
- try:
- entry = getattr(entry, attr)
- except AttributeError:
- raise ImportError("%r has no %r attribute" % (entry, attr))
- return entry
+ self.require(*args, **kwargs)
+ return self.resolve()
+
+ def resolve(self):
+ """
+ Resolve the entry point from its module and attrs.
+ """
+ module = __import__(self.module_name, fromlist=['__name__'], level=0)
+ try:
+ return functools.reduce(getattr, self.attrs, module)
+ except AttributeError as exc:
+ raise ImportError(str(exc))
def require(self, env=None, installer=None):
if self.extras and not self.dist:
@@ -2196,6 +2303,15 @@ class EntryPoint(object):
items = working_set.resolve(reqs, env, installer)
list(map(working_set.add, items))
+ pattern = re.compile(
+ r'\s*'
+ r'(?P<name>.+?)\s*'
+ r'=\s*'
+ r'(?P<module>[\w.]+)\s*'
+ r'(:\s*(?P<attr>[\w.]+))?\s*'
+ r'(?P<extras>\[.*\])?\s*$'
+ )
+
@classmethod
def parse(cls, src, dist=None):
"""Parse a single entry point from string `src`
@@ -2207,25 +2323,23 @@ class EntryPoint(object):
The entry name and module name are required, but the ``:attrs`` and
``[extras]`` parts are optional
"""
- try:
- attrs = extras = ()
- name, value = src.split('=', 1)
- if '[' in value:
- value, extras = value.split('[', 1)
- req = Requirement.parse("x[" + extras)
- if req.specs:
- raise ValueError
- extras = req.extras
- if ':' in value:
- value, attrs = value.split(':', 1)
- if not MODULE(attrs.rstrip()):
- raise ValueError
- attrs = attrs.rstrip().split('.')
- except ValueError:
+ m = cls.pattern.match(src)
+ if not m:
msg = "EntryPoint must be in 'name=module:attrs [extras]' format"
raise ValueError(msg, src)
- else:
- return cls(name.strip(), value.strip(), attrs, extras, dist)
+ res = m.groupdict()
+ extras = cls._parse_extras(res['extras'])
+ attrs = res['attr'].split('.') if res['attr'] else ()
+ return cls(res['name'], res['module'], attrs, extras, dist)
+
+ @classmethod
+ def _parse_extras(cls, extras_spec):
+ if not extras_spec:
+ return ()
+ req = Requirement.parse('x' + extras_spec)
+ if req.specs:
+ raise ValueError()
+ return req.extras
@classmethod
def parse_group(cls, group, lines, dist=None):
@@ -2237,7 +2351,7 @@ class EntryPoint(object):
ep = cls.parse(line, dist)
if ep.name in this:
raise ValueError("Duplicate entry point", group, ep.name)
- this[ep.name]=ep
+ this[ep.name] = ep
return this
@classmethod
@@ -2263,12 +2377,24 @@ class EntryPoint(object):
def _remove_md5_fragment(location):
if not location:
return ''
- parsed = urlparse(location)
+ parsed = urllib.parse.urlparse(location)
if parsed[-1].startswith('md5='):
- return urlunparse(parsed[:-1] + ('',))
+ return urllib.parse.urlunparse(parsed[:-1] + ('',))
return location
+def _version_from_file(lines):
+ """
+ Given an iterable of lines from a Metadata file, return
+ the value of the Version field, if present, or None otherwise.
+ """
+ is_version_line = lambda line: line.lower().startswith('version:')
+ version_lines = filter(is_version_line, lines)
+ line = next(iter(version_lines), '')
+ _, _, value = line.partition(':')
+ return safe_version(value.strip()) or None
+
+
class Distribution(object):
"""Wrap an actual or potential sys.path entry w/metadata"""
PKG_INFO = 'PKG-INFO'
@@ -2286,31 +2412,34 @@ class Distribution(object):
self._provider = metadata or empty_provider
@classmethod
- def from_location(cls, location, basename, metadata=None,**kw):
- project_name, version, py_version, platform = [None]*4
+ def from_location(cls, location, basename, metadata=None, **kw):
+ project_name, version, py_version, platform = [None] * 4
basename, ext = os.path.splitext(basename)
if ext.lower() in _distributionImpl:
- # .dist-info gets much metadata differently
+ cls = _distributionImpl[ext.lower()]
+
match = EGG_NAME(basename)
if match:
project_name, version, py_version, platform = match.group(
- 'name','ver','pyver','plat'
+ 'name', 'ver', 'pyver', 'plat'
)
- cls = _distributionImpl[ext.lower()]
return cls(
location, metadata, project_name=project_name, version=version,
py_version=py_version, platform=platform, **kw
- )
+ )._reload_version()
+
+ def _reload_version(self):
+ return self
@property
def hashcmp(self):
return (
- getattr(self, 'parsed_version', ()),
+ self.parsed_version,
self.precedence,
self.key,
_remove_md5_fragment(self.location),
- self.py_version,
- self.platform,
+ self.py_version or '',
+ self.platform or '',
)
def __hash__(self):
@@ -2351,24 +2480,47 @@ class Distribution(object):
@property
def parsed_version(self):
- try:
- return self._parsed_version
- except AttributeError:
- self._parsed_version = pv = parse_version(self.version)
- return pv
+ if not hasattr(self, "_parsed_version"):
+ self._parsed_version = parse_version(self.version)
+
+ return self._parsed_version
+
+ def _warn_legacy_version(self):
+ LV = packaging.version.LegacyVersion
+ is_legacy = isinstance(self._parsed_version, LV)
+ if not is_legacy:
+ return
+
+ # While an empty version is technically a legacy version and
+ # is not a valid PEP 440 version, it's also unlikely to
+ # actually come from someone and instead it is more likely that
+ # it comes from setuptools attempting to parse a filename and
+ # including it in the list. So for that we'll gate this warning
+ # on if the version is anything at all or not.
+ if not self.version:
+ return
+
+ tmpl = textwrap.dedent("""
+ '{project_name} ({version})' is being parsed as a legacy,
+ non PEP 440,
+ version. You may find odd behavior and sort order.
+ In particular it will be sorted as less than 0.0. It
+ is recommended to migrate to PEP 440 compatible
+ versions.
+ """).strip().replace('\n', ' ')
+
+ warnings.warn(tmpl.format(**vars(self)), PEP440Warning)
@property
def version(self):
try:
return self._version
except AttributeError:
- for line in self._get_metadata(self.PKG_INFO):
- if line.lower().startswith('version:'):
- self._version = safe_version(line.split(':',1)[1].strip())
- return self._version
- else:
+ version = _version_from_file(self._get_metadata(self.PKG_INFO))
+ if version is None:
tmpl = "Missing 'Version:' header and/or %s file"
raise ValueError(tmpl % self.PKG_INFO, self)
+ return version
@property
def _dep_map(self):
@@ -2383,11 +2535,11 @@ class Distribution(object):
extra, marker = extra.split(':', 1)
if invalid_marker(marker):
# XXX warn
- reqs=[]
+ reqs = []
elif not evaluate_marker(marker):
- reqs=[]
+ reqs = []
extra = safe_extra(extra) or None
- dm.setdefault(extra,[]).extend(parse_requirements(reqs))
+ dm.setdefault(extra, []).extend(parse_requirements(reqs))
return dm
def requires(self, extras=()):
@@ -2409,11 +2561,11 @@ class Distribution(object):
for line in self.get_metadata_lines(name):
yield line
- def activate(self, path=None):
+ def activate(self, path=None, replace=False):
"""Ensure distribution is importable on `path` (default=sys.path)"""
if path is None:
path = sys.path
- self.insert_on(path)
+ self.insert_on(path, replace=replace)
if path is sys.path:
fixup_namespace_packages(self.location)
for pkg in self._get_metadata('namespace_packages.txt'):
@@ -2460,7 +2612,12 @@ class Distribution(object):
def as_requirement(self):
"""Return a ``Requirement`` that matches this distribution exactly"""
- return Requirement.parse('%s==%s' % (self.project_name, self.version))
+ if isinstance(self.parsed_version, packaging.version.Version):
+ spec = "%s==%s" % (self.project_name, self.parsed_version)
+ else:
+ spec = "%s===%s" % (self.project_name, self.parsed_version)
+
+ return Requirement.parse(spec)
def load_entry_point(self, group, name):
"""Return the `name` entry point of `group` or raise ImportError"""
@@ -2478,15 +2635,32 @@ class Distribution(object):
self._get_metadata('entry_points.txt'), self
)
if group is not None:
- return ep_map.get(group,{})
+ return ep_map.get(group, {})
return ep_map
def get_entry_info(self, group, name):
"""Return the EntryPoint object for `group`+`name`, or ``None``"""
return self.get_entry_map(group).get(name)
- def insert_on(self, path, loc = None):
- """Insert self.location in path before its nearest parent directory"""
+ def insert_on(self, path, loc=None, replace=False):
+ """Ensure self.location is on path
+
+ If replace=False (default):
+ - If location is already in path anywhere, do nothing.
+ - Else:
+ - If it's an egg and its parent directory is on path,
+ insert just ahead of the parent.
+ - Else: add to the end of path.
+ If replace=True:
+ - If location is already on path anywhere (not eggs)
+ or higher priority than its parent (eggs)
+ do nothing.
+ - Else:
+ - If it's an egg and its parent directory is on path,
+ insert just ahead of the parent,
+ removing any lower-priority entries.
+ - Else: add it to the front of path.
+ """
loc = loc or self.location
if not loc:
@@ -2494,13 +2668,20 @@ class Distribution(object):
nloc = _normalize_cached(loc)
bdir = os.path.dirname(nloc)
- npath= [(p and _normalize_cached(p) or p) for p in path]
+ npath = [(p and _normalize_cached(p) or p) for p in path]
for p, item in enumerate(npath):
if item == nloc:
- break
+ if replace:
+ break
+ else:
+ # don't modify path (even removing duplicates) if found and not replace
+ return
elif item == bdir and self.precedence == EGG_DIST:
# if it's an .egg, give it precedence over its directory
+ # UNLESS it's already been added to sys.path and replace=False
+ if (not replace) and nloc in npath[p:]:
+ return
if path is sys.path:
self.check_version_conflict()
path.insert(p, loc)
@@ -2509,13 +2690,16 @@ class Distribution(object):
else:
if path is sys.path:
self.check_version_conflict()
- path.append(loc)
+ if replace:
+ path.insert(0, loc)
+ else:
+ path.append(loc)
return
# p is the spot where we found or inserted loc; now remove duplicates
while True:
try:
- np = npath.index(nloc, p+1)
+ np = npath.index(nloc, p + 1)
except ValueError:
break
else:
@@ -2555,7 +2739,7 @@ class Distribution(object):
return False
return True
- def clone(self,**kw):
+ def clone(self, **kw):
"""Copy this distribution, substituting in any changed keyword args"""
names = 'project_name version py_version platform location precedence'
for attr in names.split():
@@ -2568,6 +2752,25 @@ class Distribution(object):
return [dep for dep in self._dep_map if dep]
+class EggInfoDistribution(Distribution):
+ def _reload_version(self):
+ """
+ Packages installed by distutils (e.g. numpy or scipy),
+ which uses an old safe_version, and so
+ their version numbers can get mangled when
+ converted to filenames (e.g., 1.11.0.dev0+2329eae to
+ 1.11.0.dev0_2329eae). These distributions will not be
+ parsed properly
+ downstream by Distribution and safe_version, so
+ take an extra step and try to get the version number from
+ the metadata file itself instead of the filename.
+ """
+ md_version = _version_from_file(self._get_metadata(self.PKG_INFO))
+ if md_version:
+ self._version = md_version
+ return self
+
+
class DistInfoDistribution(Distribution):
"""Wrap an actual or potential sys.path entry w/metadata, .dist-info style"""
PKG_INFO = 'METADATA'
@@ -2591,54 +2794,38 @@ class DistInfoDistribution(Distribution):
self.__dep_map = self._compute_dependencies()
return self.__dep_map
- def _preparse_requirement(self, requires_dist):
- """Convert 'Foobar (1); baz' to ('Foobar ==1', 'baz')
- Split environment marker, add == prefix to version specifiers as
- necessary, and remove parenthesis.
- """
- parts = requires_dist.split(';', 1) + ['']
- distvers = parts[0].strip()
- mark = parts[1].strip()
- distvers = re.sub(self.EQEQ, r"\1==\2\3", distvers)
- distvers = distvers.replace('(', '').replace(')', '')
- return (distvers, mark)
-
def _compute_dependencies(self):
"""Recompute this distribution's dependencies."""
- from _markerlib import compile as compile_marker
dm = self.__dep_map = {None: []}
reqs = []
# Including any condition expressions
for req in self._parsed_pkg_info.get_all('Requires-Dist') or []:
- distvers, mark = self._preparse_requirement(req)
- parsed = next(parse_requirements(distvers))
- parsed.marker_fn = compile_marker(mark)
- reqs.append(parsed)
+ reqs.extend(parse_requirements(req))
def reqs_for_extra(extra):
for req in reqs:
- if req.marker_fn(override={'extra':extra}):
+ if not req.marker or req.marker.evaluate({'extra': extra}):
yield req
common = frozenset(reqs_for_extra(None))
dm[None].extend(common)
for extra in self._parsed_pkg_info.get_all('Provides-Extra') or []:
- extra = safe_extra(extra.strip())
- dm[extra] = list(frozenset(reqs_for_extra(extra)) - common)
+ s_extra = safe_extra(extra.strip())
+ dm[s_extra] = list(frozenset(reqs_for_extra(extra)) - common)
return dm
_distributionImpl = {
'.egg': Distribution,
- '.egg-info': Distribution,
+ '.egg-info': EggInfoDistribution,
'.dist-info': DistInfoDistribution,
}
-def issue_warning(*args,**kw):
+def issue_warning(*args, **kw):
level = 1
g = globals()
try:
@@ -2651,6 +2838,11 @@ def issue_warning(*args,**kw):
warnings.warn(stacklevel=level + 1, *args, **kw)
+class RequirementParseError(ValueError):
+ def __str__(self):
+ return ' '.join(self.args)
+
+
def parse_requirements(strs):
"""Yield ``Requirement`` objects for each specification in `strs`
@@ -2659,122 +2851,58 @@ def parse_requirements(strs):
# create a steppable iterator, so we can handle \-continuations
lines = iter(yield_lines(strs))
- def scan_list(ITEM, TERMINATOR, line, p, groups, item_name):
-
- items = []
-
- while not TERMINATOR(line, p):
- if CONTINUE(line, p):
- try:
- line = next(lines)
- p = 0
- except StopIteration:
- raise ValueError(
- "\\ must not appear on the last nonblank line"
- )
-
- match = ITEM(line, p)
- if not match:
- msg = "Expected " + item_name + " in"
- raise ValueError(msg, line, "at", line[p:])
-
- items.append(match.group(*groups))
- p = match.end()
-
- match = COMMA(line, p)
- if match:
- # skip the comma
- p = match.end()
- elif not TERMINATOR(line, p):
- msg = "Expected ',' or end-of-list in"
- raise ValueError(msg, line, "at", line[p:])
-
- match = TERMINATOR(line, p)
- # skip the terminator, if any
- if match:
- p = match.end()
- return line, p, items
-
for line in lines:
- match = DISTRO(line)
- if not match:
- raise ValueError("Missing distribution spec", line)
- project_name = match.group(1)
- p = match.end()
- extras = []
-
- match = OBRACKET(line, p)
- if match:
- p = match.end()
- line, p, extras = scan_list(
- DISTRO, CBRACKET, line, p, (1,), "'extra' name"
- )
-
- line, p, specs = scan_list(VERSION, LINE_END, line, p, (1, 2),
- "version spec")
- specs = [(op, safe_version(val)) for op, val in specs]
- yield Requirement(project_name, specs, extras)
+ # Drop comments -- a hash without a space may be in a URL.
+ if ' #' in line:
+ line = line[:line.find(' #')]
+ # If there is a line continuation, drop it, and append the next line.
+ if line.endswith('\\'):
+ line = line[:-2].strip()
+ line += next(lines)
+ yield Requirement(line)
-class Requirement:
- def __init__(self, project_name, specs, extras):
+class Requirement(packaging.requirements.Requirement):
+ def __init__(self, requirement_string):
"""DO NOT CALL THIS UNDOCUMENTED METHOD; use Requirement.parse()!"""
- self.unsafe_name, project_name = project_name, safe_name(project_name)
+ try:
+ super(Requirement, self).__init__(requirement_string)
+ except packaging.requirements.InvalidRequirement as e:
+ raise RequirementParseError(str(e))
+ self.unsafe_name = self.name
+ project_name = safe_name(self.name)
self.project_name, self.key = project_name, project_name.lower()
- index = [
- (parse_version(v), state_machine[op], op, v)
- for op, v in specs
- ]
- index.sort()
- self.specs = [(op, ver) for parsed, trans, op, ver in index]
- self.index, self.extras = index, tuple(map(safe_extra, extras))
+ self.specs = [
+ (spec.operator, spec.version) for spec in self.specifier]
+ self.extras = tuple(map(safe_extra, self.extras))
self.hashCmp = (
self.key,
- tuple((op, parsed) for parsed, trans, op, ver in index),
+ self.specifier,
frozenset(self.extras),
+ str(self.marker) if self.marker else None,
)
self.__hash = hash(self.hashCmp)
- def __str__(self):
- specs = ','.join([''.join(s) for s in self.specs])
- extras = ','.join(self.extras)
- if extras:
- extras = '[%s]' % extras
- return '%s%s%s' % (self.project_name, extras, specs)
-
def __eq__(self, other):
return (
isinstance(other, Requirement) and
self.hashCmp == other.hashCmp
)
+ def __ne__(self, other):
+ return not self == other
+
def __contains__(self, item):
if isinstance(item, Distribution):
if item.key != self.key:
return False
- # only get if we need it
- if self.index:
- item = item.parsed_version
- elif isinstance(item, string_types):
- item = parse_version(item)
- last = None
- # -1, 0, 1
- compare = lambda a, b: (a > b) - (a < b)
- for parsed, trans, op, ver in self.index:
- # Indexing: 0, 1, -1
- action = trans[compare(item, parsed)]
- if action == 'F':
- return False
- elif action == 'T':
- return True
- elif action == '+':
- last = True
- elif action == '-' or last is None:
- last = False
- # no rules encountered
- if last is None:
- last = True
- return last
+
+ item = item.version
+
+ # Allow prereleases always in order to match the previous behavior of
+ # this method. In the future this should be smarter and follow PEP 440
+ # more accurately.
+ return self.specifier.contains(item, prereleases=True)
def __hash__(self):
return self.__hash
@@ -2783,31 +2911,21 @@ class Requirement:
@staticmethod
def parse(s):
- reqs = list(parse_requirements(s))
- if reqs:
- if len(reqs) == 1:
- return reqs[0]
- raise ValueError("Expected only one requirement", s)
- raise ValueError("No requirements found", s)
-
-state_machine = {
- # =><
- '<': '--T',
- '<=': 'T-T',
- '>': 'F+F',
- '>=': 'T+F',
- '==': 'T..',
- '!=': 'F++',
-}
+ req, = parse_requirements(s)
+ return req
def _get_mro(cls):
"""Get an mro for a type or classic class"""
if not isinstance(cls, type):
- class cls(cls, object): pass
+
+ class cls(cls, object):
+ pass
+
return cls.__mro__[1:]
return cls.__mro__
+
def _find_adapter(registry, ob):
"""Return an adapter factory for `ob` from `registry`"""
for t in _get_mro(getattr(ob, '__class__', type(ob))):
@@ -2822,14 +2940,14 @@ def ensure_directory(path):
os.makedirs(dirname)
-def _bypass_ensure_directory(path, mode=0o777):
+def _bypass_ensure_directory(path):
"""Sandbox-bypassing version of ensure_directory()"""
if not WRITE_SUPPORT:
raise IOError('"os.mkdir" not supported on this platform.')
dirname, filename = split(path)
if dirname and filename and not isdir(dirname):
_bypass_ensure_directory(dirname)
- mkdir(dirname, mode)
+ mkdir(dirname, 0o755)
def split_sections(s):
@@ -2857,39 +2975,75 @@ def split_sections(s):
# wrap up last segment
yield section, content
-def _mkstemp(*args,**kw):
+
+def _mkstemp(*args, **kw):
old_open = os.open
try:
# temporarily bypass sandboxing
os.open = os_open
- return tempfile.mkstemp(*args,**kw)
+ return tempfile.mkstemp(*args, **kw)
finally:
# and then put it back
os.open = old_open
-# Set up global resource manager (deliberately not state-saved)
-_manager = ResourceManager()
-def _initialize(g):
- for name in dir(_manager):
- if not name.startswith('_'):
- g[name] = getattr(_manager, name)
-_initialize(globals())
+# Silence the PEP440Warning by default, so that end users don't get hit by it
+# randomly just because they use pkg_resources. We want to append the rule
+# because we want earlier uses of filterwarnings to take precedence over this
+# one.
+warnings.filterwarnings("ignore", category=PEP440Warning, append=True)
-# Prepare the master working set and make the ``require()`` API available
-working_set = WorkingSet._build_master()
-_declare_state('object', working_set=working_set)
-require = working_set.require
-iter_entry_points = working_set.iter_entry_points
-add_activation_listener = working_set.subscribe
-run_script = working_set.run_script
-# backward compatibility
-run_main = run_script
-# Activate all distributions already on sys.path, and ensure that
-# all distributions added to the working set in the future (e.g. by
-# calling ``require()``) will get activated as well.
-add_activation_listener(lambda dist: dist.activate())
-working_set.entries=[]
-# match order
-list(map(working_set.add_entry, sys.path))
+# from jaraco.functools 1.3
+def _call_aside(f, *args, **kwargs):
+ f(*args, **kwargs)
+ return f
+
+
+@_call_aside
+def _initialize(g=globals()):
+ "Set up global resource manager (deliberately not state-saved)"
+ manager = ResourceManager()
+ g['_manager'] = manager
+ g.update(
+ (name, getattr(manager, name))
+ for name in dir(manager)
+ if not name.startswith('_')
+ )
+
+
+@_call_aside
+def _initialize_master_working_set():
+ """
+ Prepare the master working set and make the ``require()``
+ API available.
+
+ This function has explicit effects on the global state
+ of pkg_resources. It is intended to be invoked once at
+ the initialization of this module.
+
+ Invocation by other packages is unsupported and done
+ at their own risk.
+ """
+ working_set = WorkingSet._build_master()
+ _declare_state('object', working_set=working_set)
+
+ require = working_set.require
+ iter_entry_points = working_set.iter_entry_points
+ add_activation_listener = working_set.subscribe
+ run_script = working_set.run_script
+ # backward compatibility
+ run_main = run_script
+ # Activate all distributions already on sys.path with replace=False and
+ # ensure that all distributions added to the working set in the future
+ # (e.g. by calling ``require()``) will get activated as well,
+ # with higher priority (replace=True).
+ tuple(
+ dist.activate(replace=False)
+ for dist in working_set
+ )
+ add_activation_listener(lambda dist: dist.activate(replace=True), existing=False)
+ working_set.entries = []
+ # match order
+ list(map(working_set.add_entry, sys.path))
+ globals().update(locals())
diff --git a/recipes/pkgresources/pkgr/_vendor/__init__.py b/recipes/pkgresources/pkgr/_vendor/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/recipes/pkgresources/pkgr/_vendor/appdirs.py b/recipes/pkgresources/pkgr/_vendor/appdirs.py
new file mode 100644
index 0000000..f4dba09
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/appdirs.py
@@ -0,0 +1,552 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright (c) 2005-2010 ActiveState Software Inc.
+# Copyright (c) 2013 Eddy Petrișor
+
+"""Utilities for determining application-specific dirs.
+
+See <http://github.com/ActiveState/appdirs> for details and usage.
+"""
+# Dev Notes:
+# - MSDN on where to store app data files:
+# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120
+# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html
+# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html
+
+__version_info__ = (1, 4, 0)
+__version__ = '.'.join(map(str, __version_info__))
+
+
+import sys
+import os
+
+PY3 = sys.version_info[0] == 3
+
+if PY3:
+ unicode = str
+
+if sys.platform.startswith('java'):
+ import platform
+ os_name = platform.java_ver()[3][0]
+ if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc.
+ system = 'win32'
+ elif os_name.startswith('Mac'): # "Mac OS X", etc.
+ system = 'darwin'
+ else: # "Linux", "SunOS", "FreeBSD", etc.
+ # Setting this to "linux2" is not ideal, but only Windows or Mac
+ # are actually checked for and the rest of the module expects
+ # *sys.platform* style strings.
+ system = 'linux2'
+else:
+ system = sys.platform
+
+
+
+def user_data_dir(appname=None, appauthor=None, version=None, roaming=False):
+ r"""Return full path to the user-specific data dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "roaming" (boolean, default False) can be set True to use the Windows
+ roaming appdata directory. That means that for users on a Windows
+ network setup for roaming profiles, this user data will be
+ sync'd on login. See
+ <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
+ for a discussion of issues.
+
+ Typical user data directories are:
+ Mac OS X: ~/Library/Application Support/<AppName>
+ Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined
+ Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName>
+ Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>
+ Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>
+ Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName>
+
+ For Unix, we follow the XDG spec and support $XDG_DATA_HOME.
+ That means, by default "~/.local/share/<AppName>".
+ """
+ if system == "win32":
+ if appauthor is None:
+ appauthor = appname
+ const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA"
+ path = os.path.normpath(_get_win_folder(const))
+ if appname:
+ if appauthor is not False:
+ path = os.path.join(path, appauthor, appname)
+ else:
+ path = os.path.join(path, appname)
+ elif system == 'darwin':
+ path = os.path.expanduser('~/Library/Application Support/')
+ if appname:
+ path = os.path.join(path, appname)
+ else:
+ path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share"))
+ if appname:
+ path = os.path.join(path, appname)
+ if appname and version:
+ path = os.path.join(path, version)
+ return path
+
+
+def site_data_dir(appname=None, appauthor=None, version=None, multipath=False):
+ """Return full path to the user-shared data dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "multipath" is an optional parameter only applicable to *nix
+ which indicates that the entire list of data dirs should be
+ returned. By default, the first item from XDG_DATA_DIRS is
+ returned, or '/usr/local/share/<AppName>',
+ if XDG_DATA_DIRS is not set
+
+ Typical user data directories are:
+ Mac OS X: /Library/Application Support/<AppName>
+ Unix: /usr/local/share/<AppName> or /usr/share/<AppName>
+ Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName>
+ Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
+ Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7.
+
+ For Unix, this is using the $XDG_DATA_DIRS[0] default.
+
+ WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
+ """
+ if system == "win32":
+ if appauthor is None:
+ appauthor = appname
+ path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA"))
+ if appname:
+ if appauthor is not False:
+ path = os.path.join(path, appauthor, appname)
+ else:
+ path = os.path.join(path, appname)
+ elif system == 'darwin':
+ path = os.path.expanduser('/Library/Application Support')
+ if appname:
+ path = os.path.join(path, appname)
+ else:
+ # XDG default for $XDG_DATA_DIRS
+ # only first, if multipath is False
+ path = os.getenv('XDG_DATA_DIRS',
+ os.pathsep.join(['/usr/local/share', '/usr/share']))
+ pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)]
+ if appname:
+ if version:
+ appname = os.path.join(appname, version)
+ pathlist = [os.sep.join([x, appname]) for x in pathlist]
+
+ if multipath:
+ path = os.pathsep.join(pathlist)
+ else:
+ path = pathlist[0]
+ return path
+
+ if appname and version:
+ path = os.path.join(path, version)
+ return path
+
+
+def user_config_dir(appname=None, appauthor=None, version=None, roaming=False):
+ r"""Return full path to the user-specific config dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "roaming" (boolean, default False) can be set True to use the Windows
+ roaming appdata directory. That means that for users on a Windows
+ network setup for roaming profiles, this user data will be
+ sync'd on login. See
+ <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx>
+ for a discussion of issues.
+
+ Typical user data directories are:
+ Mac OS X: same as user_data_dir
+ Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined
+ Win *: same as user_data_dir
+
+ For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME.
+ That means, by deafult "~/.config/<AppName>".
+ """
+ if system in ["win32", "darwin"]:
+ path = user_data_dir(appname, appauthor, None, roaming)
+ else:
+ path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config"))
+ if appname:
+ path = os.path.join(path, appname)
+ if appname and version:
+ path = os.path.join(path, version)
+ return path
+
+
+def site_config_dir(appname=None, appauthor=None, version=None, multipath=False):
+ """Return full path to the user-shared data dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "multipath" is an optional parameter only applicable to *nix
+ which indicates that the entire list of config dirs should be
+ returned. By default, the first item from XDG_CONFIG_DIRS is
+ returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set
+
+ Typical user data directories are:
+ Mac OS X: same as site_data_dir
+ Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in
+ $XDG_CONFIG_DIRS
+ Win *: same as site_data_dir
+ Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.)
+
+ For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False
+
+ WARNING: Do not use this on Windows. See the Vista-Fail note above for why.
+ """
+ if system in ["win32", "darwin"]:
+ path = site_data_dir(appname, appauthor)
+ if appname and version:
+ path = os.path.join(path, version)
+ else:
+ # XDG default for $XDG_CONFIG_DIRS
+ # only first, if multipath is False
+ path = os.getenv('XDG_CONFIG_DIRS', '/etc/xdg')
+ pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)]
+ if appname:
+ if version:
+ appname = os.path.join(appname, version)
+ pathlist = [os.sep.join([x, appname]) for x in pathlist]
+
+ if multipath:
+ path = os.pathsep.join(pathlist)
+ else:
+ path = pathlist[0]
+ return path
+
+
+def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True):
+ r"""Return full path to the user-specific cache dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "opinion" (boolean) can be False to disable the appending of
+ "Cache" to the base app data dir for Windows. See
+ discussion below.
+
+ Typical user cache directories are:
+ Mac OS X: ~/Library/Caches/<AppName>
+ Unix: ~/.cache/<AppName> (XDG default)
+ Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache
+ Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache
+
+ On Windows the only suggestion in the MSDN docs is that local settings go in
+ the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming
+ app data dir (the default returned by `user_data_dir` above). Apps typically
+ put cache data somewhere *under* the given dir here. Some examples:
+ ...\Mozilla\Firefox\Profiles\<ProfileName>\Cache
+ ...\Acme\SuperApp\Cache\1.0
+ OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value.
+ This can be disabled with the `opinion=False` option.
+ """
+ if system == "win32":
+ if appauthor is None:
+ appauthor = appname
+ path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA"))
+ if appname:
+ if appauthor is not False:
+ path = os.path.join(path, appauthor, appname)
+ else:
+ path = os.path.join(path, appname)
+ if opinion:
+ path = os.path.join(path, "Cache")
+ elif system == 'darwin':
+ path = os.path.expanduser('~/Library/Caches')
+ if appname:
+ path = os.path.join(path, appname)
+ else:
+ path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache'))
+ if appname:
+ path = os.path.join(path, appname)
+ if appname and version:
+ path = os.path.join(path, version)
+ return path
+
+
+def user_log_dir(appname=None, appauthor=None, version=None, opinion=True):
+ r"""Return full path to the user-specific log dir for this application.
+
+ "appname" is the name of application.
+ If None, just the system directory is returned.
+ "appauthor" (only used on Windows) is the name of the
+ appauthor or distributing body for this application. Typically
+ it is the owning company name. This falls back to appname. You may
+ pass False to disable it.
+ "version" is an optional version path element to append to the
+ path. You might want to use this if you want multiple versions
+ of your app to be able to run independently. If used, this
+ would typically be "<major>.<minor>".
+ Only applied when appname is present.
+ "opinion" (boolean) can be False to disable the appending of
+ "Logs" to the base app data dir for Windows, and "log" to the
+ base cache dir for Unix. See discussion below.
+
+ Typical user cache directories are:
+ Mac OS X: ~/Library/Logs/<AppName>
+ Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined
+ Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs
+ Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs
+
+ On Windows the only suggestion in the MSDN docs is that local settings
+ go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in
+ examples of what some windows apps use for a logs dir.)
+
+ OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA`
+ value for Windows and appends "log" to the user cache dir for Unix.
+ This can be disabled with the `opinion=False` option.
+ """
+ if system == "darwin":
+ path = os.path.join(
+ os.path.expanduser('~/Library/Logs'),
+ appname)
+ elif system == "win32":
+ path = user_data_dir(appname, appauthor, version)
+ version = False
+ if opinion:
+ path = os.path.join(path, "Logs")
+ else:
+ path = user_cache_dir(appname, appauthor, version)
+ version = False
+ if opinion:
+ path = os.path.join(path, "log")
+ if appname and version:
+ path = os.path.join(path, version)
+ return path
+
+
+class AppDirs(object):
+ """Convenience wrapper for getting application dirs."""
+ def __init__(self, appname, appauthor=None, version=None, roaming=False,
+ multipath=False):
+ self.appname = appname
+ self.appauthor = appauthor
+ self.version = version
+ self.roaming = roaming
+ self.multipath = multipath
+
+ @property
+ def user_data_dir(self):
+ return user_data_dir(self.appname, self.appauthor,
+ version=self.version, roaming=self.roaming)
+
+ @property
+ def site_data_dir(self):
+ return site_data_dir(self.appname, self.appauthor,
+ version=self.version, multipath=self.multipath)
+
+ @property
+ def user_config_dir(self):
+ return user_config_dir(self.appname, self.appauthor,
+ version=self.version, roaming=self.roaming)
+
+ @property
+ def site_config_dir(self):
+ return site_config_dir(self.appname, self.appauthor,
+ version=self.version, multipath=self.multipath)
+
+ @property
+ def user_cache_dir(self):
+ return user_cache_dir(self.appname, self.appauthor,
+ version=self.version)
+
+ @property
+ def user_log_dir(self):
+ return user_log_dir(self.appname, self.appauthor,
+ version=self.version)
+
+
+#---- internal support stuff
+
+def _get_win_folder_from_registry(csidl_name):
+ """This is a fallback technique at best. I'm not sure if using the
+ registry for this guarantees us the correct answer for all CSIDL_*
+ names.
+ """
+ import _winreg
+
+ shell_folder_name = {
+ "CSIDL_APPDATA": "AppData",
+ "CSIDL_COMMON_APPDATA": "Common AppData",
+ "CSIDL_LOCAL_APPDATA": "Local AppData",
+ }[csidl_name]
+
+ key = _winreg.OpenKey(
+ _winreg.HKEY_CURRENT_USER,
+ r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders"
+ )
+ dir, type = _winreg.QueryValueEx(key, shell_folder_name)
+ return dir
+
+
+def _get_win_folder_with_pywin32(csidl_name):
+ from win32com.shell import shellcon, shell
+ dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0)
+ # Try to make this a unicode path because SHGetFolderPath does
+ # not return unicode strings when there is unicode data in the
+ # path.
+ try:
+ dir = unicode(dir)
+
+ # Downgrade to short path name if have highbit chars. See
+ # <http://bugs.activestate.com/show_bug.cgi?id=85099>.
+ has_high_char = False
+ for c in dir:
+ if ord(c) > 255:
+ has_high_char = True
+ break
+ if has_high_char:
+ try:
+ import win32api
+ dir = win32api.GetShortPathName(dir)
+ except ImportError:
+ pass
+ except UnicodeError:
+ pass
+ return dir
+
+
+def _get_win_folder_with_ctypes(csidl_name):
+ import ctypes
+
+ csidl_const = {
+ "CSIDL_APPDATA": 26,
+ "CSIDL_COMMON_APPDATA": 35,
+ "CSIDL_LOCAL_APPDATA": 28,
+ }[csidl_name]
+
+ buf = ctypes.create_unicode_buffer(1024)
+ ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf)
+
+ # Downgrade to short path name if have highbit chars. See
+ # <http://bugs.activestate.com/show_bug.cgi?id=85099>.
+ has_high_char = False
+ for c in buf:
+ if ord(c) > 255:
+ has_high_char = True
+ break
+ if has_high_char:
+ buf2 = ctypes.create_unicode_buffer(1024)
+ if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024):
+ buf = buf2
+
+ return buf.value
+
+def _get_win_folder_with_jna(csidl_name):
+ import array
+ from com.sun import jna
+ from com.sun.jna.platform import win32
+
+ buf_size = win32.WinDef.MAX_PATH * 2
+ buf = array.zeros('c', buf_size)
+ shell = win32.Shell32.INSTANCE
+ shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf)
+ dir = jna.Native.toString(buf.tostring()).rstrip("\0")
+
+ # Downgrade to short path name if have highbit chars. See
+ # <http://bugs.activestate.com/show_bug.cgi?id=85099>.
+ has_high_char = False
+ for c in dir:
+ if ord(c) > 255:
+ has_high_char = True
+ break
+ if has_high_char:
+ buf = array.zeros('c', buf_size)
+ kernel = win32.Kernel32.INSTANCE
+ if kernal.GetShortPathName(dir, buf, buf_size):
+ dir = jna.Native.toString(buf.tostring()).rstrip("\0")
+
+ return dir
+
+if system == "win32":
+ try:
+ import win32com.shell
+ _get_win_folder = _get_win_folder_with_pywin32
+ except ImportError:
+ try:
+ from ctypes import windll
+ _get_win_folder = _get_win_folder_with_ctypes
+ except ImportError:
+ try:
+ import com.sun.jna
+ _get_win_folder = _get_win_folder_with_jna
+ except ImportError:
+ _get_win_folder = _get_win_folder_from_registry
+
+
+#---- self test code
+
+if __name__ == "__main__":
+ appname = "MyApp"
+ appauthor = "MyCompany"
+
+ props = ("user_data_dir", "site_data_dir",
+ "user_config_dir", "site_config_dir",
+ "user_cache_dir", "user_log_dir")
+
+ print("-- app dirs (with optional 'version')")
+ dirs = AppDirs(appname, appauthor, version="1.0")
+ for prop in props:
+ print("%s: %s" % (prop, getattr(dirs, prop)))
+
+ print("\n-- app dirs (without optional 'version')")
+ dirs = AppDirs(appname, appauthor)
+ for prop in props:
+ print("%s: %s" % (prop, getattr(dirs, prop)))
+
+ print("\n-- app dirs (without optional 'appauthor')")
+ dirs = AppDirs(appname)
+ for prop in props:
+ print("%s: %s" % (prop, getattr(dirs, prop)))
+
+ print("\n-- app dirs (with disabled 'appauthor')")
+ dirs = AppDirs(appname, appauthor=False)
+ for prop in props:
+ print("%s: %s" % (prop, getattr(dirs, prop)))
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/__about__.py b/recipes/pkgresources/pkgr/_vendor/packaging/__about__.py
new file mode 100644
index 0000000..95d330e
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/__about__.py
@@ -0,0 +1,21 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+__all__ = [
+ "__title__", "__summary__", "__uri__", "__version__", "__author__",
+ "__email__", "__license__", "__copyright__",
+]
+
+__title__ = "packaging"
+__summary__ = "Core utilities for Python packages"
+__uri__ = "https://github.com/pypa/packaging"
+
+__version__ = "16.8"
+
+__author__ = "Donald Stufft and individual contributors"
+__email__ = "donald@stufft.io"
+
+__license__ = "BSD or Apache License, Version 2.0"
+__copyright__ = "Copyright 2014-2016 %s" % __author__
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/__init__.py b/recipes/pkgresources/pkgr/_vendor/packaging/__init__.py
new file mode 100644
index 0000000..5ee6220
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/__init__.py
@@ -0,0 +1,14 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+from .__about__ import (
+ __author__, __copyright__, __email__, __license__, __summary__, __title__,
+ __uri__, __version__
+)
+
+__all__ = [
+ "__title__", "__summary__", "__uri__", "__version__", "__author__",
+ "__email__", "__license__", "__copyright__",
+]
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/_compat.py b/recipes/pkgresources/pkgr/_vendor/packaging/_compat.py
new file mode 100644
index 0000000..210bb80
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/_compat.py
@@ -0,0 +1,30 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import sys
+
+
+PY2 = sys.version_info[0] == 2
+PY3 = sys.version_info[0] == 3
+
+# flake8: noqa
+
+if PY3:
+ string_types = str,
+else:
+ string_types = basestring,
+
+
+def with_metaclass(meta, *bases):
+ """
+ Create a base class with a metaclass.
+ """
+ # This requires a bit of explanation: the basic idea is to make a dummy
+ # metaclass for one level of class instantiation that replaces itself with
+ # the actual metaclass.
+ class metaclass(meta):
+ def __new__(cls, name, this_bases, d):
+ return meta(name, bases, d)
+ return type.__new__(metaclass, 'temporary_class', (), {})
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/_structures.py b/recipes/pkgresources/pkgr/_vendor/packaging/_structures.py
new file mode 100644
index 0000000..ccc2786
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/_structures.py
@@ -0,0 +1,68 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+
+class Infinity(object):
+
+ def __repr__(self):
+ return "Infinity"
+
+ def __hash__(self):
+ return hash(repr(self))
+
+ def __lt__(self, other):
+ return False
+
+ def __le__(self, other):
+ return False
+
+ def __eq__(self, other):
+ return isinstance(other, self.__class__)
+
+ def __ne__(self, other):
+ return not isinstance(other, self.__class__)
+
+ def __gt__(self, other):
+ return True
+
+ def __ge__(self, other):
+ return True
+
+ def __neg__(self):
+ return NegativeInfinity
+
+Infinity = Infinity()
+
+
+class NegativeInfinity(object):
+
+ def __repr__(self):
+ return "-Infinity"
+
+ def __hash__(self):
+ return hash(repr(self))
+
+ def __lt__(self, other):
+ return True
+
+ def __le__(self, other):
+ return True
+
+ def __eq__(self, other):
+ return isinstance(other, self.__class__)
+
+ def __ne__(self, other):
+ return not isinstance(other, self.__class__)
+
+ def __gt__(self, other):
+ return False
+
+ def __ge__(self, other):
+ return False
+
+ def __neg__(self):
+ return Infinity
+
+NegativeInfinity = NegativeInfinity()
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/markers.py b/recipes/pkgresources/pkgr/_vendor/packaging/markers.py
new file mode 100644
index 0000000..892e578
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/markers.py
@@ -0,0 +1,301 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import operator
+import os
+import platform
+import sys
+
+from pkg_resources.extern.pyparsing import ParseException, ParseResults, stringStart, stringEnd
+from pkg_resources.extern.pyparsing import ZeroOrMore, Group, Forward, QuotedString
+from pkg_resources.extern.pyparsing import Literal as L # noqa
+
+from ._compat import string_types
+from .specifiers import Specifier, InvalidSpecifier
+
+
+__all__ = [
+ "InvalidMarker", "UndefinedComparison", "UndefinedEnvironmentName",
+ "Marker", "default_environment",
+]
+
+
+class InvalidMarker(ValueError):
+ """
+ An invalid marker was found, users should refer to PEP 508.
+ """
+
+
+class UndefinedComparison(ValueError):
+ """
+ An invalid operation was attempted on a value that doesn't support it.
+ """
+
+
+class UndefinedEnvironmentName(ValueError):
+ """
+ A name was attempted to be used that does not exist inside of the
+ environment.
+ """
+
+
+class Node(object):
+
+ def __init__(self, value):
+ self.value = value
+
+ def __str__(self):
+ return str(self.value)
+
+ def __repr__(self):
+ return "<{0}({1!r})>".format(self.__class__.__name__, str(self))
+
+ def serialize(self):
+ raise NotImplementedError
+
+
+class Variable(Node):
+
+ def serialize(self):
+ return str(self)
+
+
+class Value(Node):
+
+ def serialize(self):
+ return '"{0}"'.format(self)
+
+
+class Op(Node):
+
+ def serialize(self):
+ return str(self)
+
+
+VARIABLE = (
+ L("implementation_version") |
+ L("platform_python_implementation") |
+ L("implementation_name") |
+ L("python_full_version") |
+ L("platform_release") |
+ L("platform_version") |
+ L("platform_machine") |
+ L("platform_system") |
+ L("python_version") |
+ L("sys_platform") |
+ L("os_name") |
+ L("os.name") | # PEP-345
+ L("sys.platform") | # PEP-345
+ L("platform.version") | # PEP-345
+ L("platform.machine") | # PEP-345
+ L("platform.python_implementation") | # PEP-345
+ L("python_implementation") | # undocumented setuptools legacy
+ L("extra")
+)
+ALIASES = {
+ 'os.name': 'os_name',
+ 'sys.platform': 'sys_platform',
+ 'platform.version': 'platform_version',
+ 'platform.machine': 'platform_machine',
+ 'platform.python_implementation': 'platform_python_implementation',
+ 'python_implementation': 'platform_python_implementation'
+}
+VARIABLE.setParseAction(lambda s, l, t: Variable(ALIASES.get(t[0], t[0])))
+
+VERSION_CMP = (
+ L("===") |
+ L("==") |
+ L(">=") |
+ L("<=") |
+ L("!=") |
+ L("~=") |
+ L(">") |
+ L("<")
+)
+
+MARKER_OP = VERSION_CMP | L("not in") | L("in")
+MARKER_OP.setParseAction(lambda s, l, t: Op(t[0]))
+
+MARKER_VALUE = QuotedString("'") | QuotedString('"')
+MARKER_VALUE.setParseAction(lambda s, l, t: Value(t[0]))
+
+BOOLOP = L("and") | L("or")
+
+MARKER_VAR = VARIABLE | MARKER_VALUE
+
+MARKER_ITEM = Group(MARKER_VAR + MARKER_OP + MARKER_VAR)
+MARKER_ITEM.setParseAction(lambda s, l, t: tuple(t[0]))
+
+LPAREN = L("(").suppress()
+RPAREN = L(")").suppress()
+
+MARKER_EXPR = Forward()
+MARKER_ATOM = MARKER_ITEM | Group(LPAREN + MARKER_EXPR + RPAREN)
+MARKER_EXPR << MARKER_ATOM + ZeroOrMore(BOOLOP + MARKER_EXPR)
+
+MARKER = stringStart + MARKER_EXPR + stringEnd
+
+
+def _coerce_parse_result(results):
+ if isinstance(results, ParseResults):
+ return [_coerce_parse_result(i) for i in results]
+ else:
+ return results
+
+
+def _format_marker(marker, first=True):
+ assert isinstance(marker, (list, tuple, string_types))
+
+ # Sometimes we have a structure like [[...]] which is a single item list
+ # where the single item is itself it's own list. In that case we want skip
+ # the rest of this function so that we don't get extraneous () on the
+ # outside.
+ if (isinstance(marker, list) and len(marker) == 1 and
+ isinstance(marker[0], (list, tuple))):
+ return _format_marker(marker[0])
+
+ if isinstance(marker, list):
+ inner = (_format_marker(m, first=False) for m in marker)
+ if first:
+ return " ".join(inner)
+ else:
+ return "(" + " ".join(inner) + ")"
+ elif isinstance(marker, tuple):
+ return " ".join([m.serialize() for m in marker])
+ else:
+ return marker
+
+
+_operators = {
+ "in": lambda lhs, rhs: lhs in rhs,
+ "not in": lambda lhs, rhs: lhs not in rhs,
+ "<": operator.lt,
+ "<=": operator.le,
+ "==": operator.eq,
+ "!=": operator.ne,
+ ">=": operator.ge,
+ ">": operator.gt,
+}
+
+
+def _eval_op(lhs, op, rhs):
+ try:
+ spec = Specifier("".join([op.serialize(), rhs]))
+ except InvalidSpecifier:
+ pass
+ else:
+ return spec.contains(lhs)
+
+ oper = _operators.get(op.serialize())
+ if oper is None:
+ raise UndefinedComparison(
+ "Undefined {0!r} on {1!r} and {2!r}.".format(op, lhs, rhs)
+ )
+
+ return oper(lhs, rhs)
+
+
+_undefined = object()
+
+
+def _get_env(environment, name):
+ value = environment.get(name, _undefined)
+
+ if value is _undefined:
+ raise UndefinedEnvironmentName(
+ "{0!r} does not exist in evaluation environment.".format(name)
+ )
+
+ return value
+
+
+def _evaluate_markers(markers, environment):
+ groups = [[]]
+
+ for marker in markers:
+ assert isinstance(marker, (list, tuple, string_types))
+
+ if isinstance(marker, list):
+ groups[-1].append(_evaluate_markers(marker, environment))
+ elif isinstance(marker, tuple):
+ lhs, op, rhs = marker
+
+ if isinstance(lhs, Variable):
+ lhs_value = _get_env(environment, lhs.value)
+ rhs_value = rhs.value
+ else:
+ lhs_value = lhs.value
+ rhs_value = _get_env(environment, rhs.value)
+
+ groups[-1].append(_eval_op(lhs_value, op, rhs_value))
+ else:
+ assert marker in ["and", "or"]
+ if marker == "or":
+ groups.append([])
+
+ return any(all(item) for item in groups)
+
+
+def format_full_version(info):
+ version = '{0.major}.{0.minor}.{0.micro}'.format(info)
+ kind = info.releaselevel
+ if kind != 'final':
+ version += kind[0] + str(info.serial)
+ return version
+
+
+def default_environment():
+ if hasattr(sys, 'implementation'):
+ iver = format_full_version(sys.implementation.version)
+ implementation_name = sys.implementation.name
+ else:
+ iver = '0'
+ implementation_name = ''
+
+ return {
+ "implementation_name": implementation_name,
+ "implementation_version": iver,
+ "os_name": os.name,
+ "platform_machine": platform.machine(),
+ "platform_release": platform.release(),
+ "platform_system": platform.system(),
+ "platform_version": platform.version(),
+ "python_full_version": platform.python_version(),
+ "platform_python_implementation": platform.python_implementation(),
+ "python_version": platform.python_version()[:3],
+ "sys_platform": sys.platform,
+ }
+
+
+class Marker(object):
+
+ def __init__(self, marker):
+ try:
+ self._markers = _coerce_parse_result(MARKER.parseString(marker))
+ except ParseException as e:
+ err_str = "Invalid marker: {0!r}, parse error at {1!r}".format(
+ marker, marker[e.loc:e.loc + 8])
+ raise InvalidMarker(err_str)
+
+ def __str__(self):
+ return _format_marker(self._markers)
+
+ def __repr__(self):
+ return "<Marker({0!r})>".format(str(self))
+
+ def evaluate(self, environment=None):
+ """Evaluate a marker.
+
+ Return the boolean from evaluating the given marker against the
+ environment. environment is an optional argument to override all or
+ part of the determined environment.
+
+ The environment is determined from the current Python process.
+ """
+ current_environment = default_environment()
+ if environment is not None:
+ current_environment.update(environment)
+
+ return _evaluate_markers(self._markers, current_environment)
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/requirements.py b/recipes/pkgresources/pkgr/_vendor/packaging/requirements.py
new file mode 100644
index 0000000..0c8c4a3
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/requirements.py
@@ -0,0 +1,127 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import string
+import re
+
+from pkg_resources.extern.pyparsing import stringStart, stringEnd, originalTextFor, ParseException
+from pkg_resources.extern.pyparsing import ZeroOrMore, Word, Optional, Regex, Combine
+from pkg_resources.extern.pyparsing import Literal as L # noqa
+from pkg_resources.extern.six.moves.urllib import parse as urlparse
+
+from .markers import MARKER_EXPR, Marker
+from .specifiers import LegacySpecifier, Specifier, SpecifierSet
+
+
+class InvalidRequirement(ValueError):
+ """
+ An invalid requirement was found, users should refer to PEP 508.
+ """
+
+
+ALPHANUM = Word(string.ascii_letters + string.digits)
+
+LBRACKET = L("[").suppress()
+RBRACKET = L("]").suppress()
+LPAREN = L("(").suppress()
+RPAREN = L(")").suppress()
+COMMA = L(",").suppress()
+SEMICOLON = L(";").suppress()
+AT = L("@").suppress()
+
+PUNCTUATION = Word("-_.")
+IDENTIFIER_END = ALPHANUM | (ZeroOrMore(PUNCTUATION) + ALPHANUM)
+IDENTIFIER = Combine(ALPHANUM + ZeroOrMore(IDENTIFIER_END))
+
+NAME = IDENTIFIER("name")
+EXTRA = IDENTIFIER
+
+URI = Regex(r'[^ ]+')("url")
+URL = (AT + URI)
+
+EXTRAS_LIST = EXTRA + ZeroOrMore(COMMA + EXTRA)
+EXTRAS = (LBRACKET + Optional(EXTRAS_LIST) + RBRACKET)("extras")
+
+VERSION_PEP440 = Regex(Specifier._regex_str, re.VERBOSE | re.IGNORECASE)
+VERSION_LEGACY = Regex(LegacySpecifier._regex_str, re.VERBOSE | re.IGNORECASE)
+
+VERSION_ONE = VERSION_PEP440 ^ VERSION_LEGACY
+VERSION_MANY = Combine(VERSION_ONE + ZeroOrMore(COMMA + VERSION_ONE),
+ joinString=",", adjacent=False)("_raw_spec")
+_VERSION_SPEC = Optional(((LPAREN + VERSION_MANY + RPAREN) | VERSION_MANY))
+_VERSION_SPEC.setParseAction(lambda s, l, t: t._raw_spec or '')
+
+VERSION_SPEC = originalTextFor(_VERSION_SPEC)("specifier")
+VERSION_SPEC.setParseAction(lambda s, l, t: t[1])
+
+MARKER_EXPR = originalTextFor(MARKER_EXPR())("marker")
+MARKER_EXPR.setParseAction(
+ lambda s, l, t: Marker(s[t._original_start:t._original_end])
+)
+MARKER_SEPERATOR = SEMICOLON
+MARKER = MARKER_SEPERATOR + MARKER_EXPR
+
+VERSION_AND_MARKER = VERSION_SPEC + Optional(MARKER)
+URL_AND_MARKER = URL + Optional(MARKER)
+
+NAMED_REQUIREMENT = \
+ NAME + Optional(EXTRAS) + (URL_AND_MARKER | VERSION_AND_MARKER)
+
+REQUIREMENT = stringStart + NAMED_REQUIREMENT + stringEnd
+
+
+class Requirement(object):
+ """Parse a requirement.
+
+ Parse a given requirement string into its parts, such as name, specifier,
+ URL, and extras. Raises InvalidRequirement on a badly-formed requirement
+ string.
+ """
+
+ # TODO: Can we test whether something is contained within a requirement?
+ # If so how do we do that? Do we need to test against the _name_ of
+ # the thing as well as the version? What about the markers?
+ # TODO: Can we normalize the name and extra name?
+
+ def __init__(self, requirement_string):
+ try:
+ req = REQUIREMENT.parseString(requirement_string)
+ except ParseException as e:
+ raise InvalidRequirement(
+ "Invalid requirement, parse error at \"{0!r}\"".format(
+ requirement_string[e.loc:e.loc + 8]))
+
+ self.name = req.name
+ if req.url:
+ parsed_url = urlparse.urlparse(req.url)
+ if not (parsed_url.scheme and parsed_url.netloc) or (
+ not parsed_url.scheme and not parsed_url.netloc):
+ raise InvalidRequirement("Invalid URL given")
+ self.url = req.url
+ else:
+ self.url = None
+ self.extras = set(req.extras.asList() if req.extras else [])
+ self.specifier = SpecifierSet(req.specifier)
+ self.marker = req.marker if req.marker else None
+
+ def __str__(self):
+ parts = [self.name]
+
+ if self.extras:
+ parts.append("[{0}]".format(",".join(sorted(self.extras))))
+
+ if self.specifier:
+ parts.append(str(self.specifier))
+
+ if self.url:
+ parts.append("@ {0}".format(self.url))
+
+ if self.marker:
+ parts.append("; {0}".format(self.marker))
+
+ return "".join(parts)
+
+ def __repr__(self):
+ return "<Requirement({0!r})>".format(str(self))
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/specifiers.py b/recipes/pkgresources/pkgr/_vendor/packaging/specifiers.py
new file mode 100644
index 0000000..7f5a76c
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/specifiers.py
@@ -0,0 +1,774 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import abc
+import functools
+import itertools
+import re
+
+from ._compat import string_types, with_metaclass
+from .version import Version, LegacyVersion, parse
+
+
+class InvalidSpecifier(ValueError):
+ """
+ An invalid specifier was found, users should refer to PEP 440.
+ """
+
+
+class BaseSpecifier(with_metaclass(abc.ABCMeta, object)):
+
+ @abc.abstractmethod
+ def __str__(self):
+ """
+ Returns the str representation of this Specifier like object. This
+ should be representative of the Specifier itself.
+ """
+
+ @abc.abstractmethod
+ def __hash__(self):
+ """
+ Returns a hash value for this Specifier like object.
+ """
+
+ @abc.abstractmethod
+ def __eq__(self, other):
+ """
+ Returns a boolean representing whether or not the two Specifier like
+ objects are equal.
+ """
+
+ @abc.abstractmethod
+ def __ne__(self, other):
+ """
+ Returns a boolean representing whether or not the two Specifier like
+ objects are not equal.
+ """
+
+ @abc.abstractproperty
+ def prereleases(self):
+ """
+ Returns whether or not pre-releases as a whole are allowed by this
+ specifier.
+ """
+
+ @prereleases.setter
+ def prereleases(self, value):
+ """
+ Sets whether or not pre-releases as a whole are allowed by this
+ specifier.
+ """
+
+ @abc.abstractmethod
+ def contains(self, item, prereleases=None):
+ """
+ Determines if the given item is contained within this specifier.
+ """
+
+ @abc.abstractmethod
+ def filter(self, iterable, prereleases=None):
+ """
+ Takes an iterable of items and filters them so that only items which
+ are contained within this specifier are allowed in it.
+ """
+
+
+class _IndividualSpecifier(BaseSpecifier):
+
+ _operators = {}
+
+ def __init__(self, spec="", prereleases=None):
+ match = self._regex.search(spec)
+ if not match:
+ raise InvalidSpecifier("Invalid specifier: '{0}'".format(spec))
+
+ self._spec = (
+ match.group("operator").strip(),
+ match.group("version").strip(),
+ )
+
+ # Store whether or not this Specifier should accept prereleases
+ self._prereleases = prereleases
+
+ def __repr__(self):
+ pre = (
+ ", prereleases={0!r}".format(self.prereleases)
+ if self._prereleases is not None
+ else ""
+ )
+
+ return "<{0}({1!r}{2})>".format(
+ self.__class__.__name__,
+ str(self),
+ pre,
+ )
+
+ def __str__(self):
+ return "{0}{1}".format(*self._spec)
+
+ def __hash__(self):
+ return hash(self._spec)
+
+ def __eq__(self, other):
+ if isinstance(other, string_types):
+ try:
+ other = self.__class__(other)
+ except InvalidSpecifier:
+ return NotImplemented
+ elif not isinstance(other, self.__class__):
+ return NotImplemented
+
+ return self._spec == other._spec
+
+ def __ne__(self, other):
+ if isinstance(other, string_types):
+ try:
+ other = self.__class__(other)
+ except InvalidSpecifier:
+ return NotImplemented
+ elif not isinstance(other, self.__class__):
+ return NotImplemented
+
+ return self._spec != other._spec
+
+ def _get_operator(self, op):
+ return getattr(self, "_compare_{0}".format(self._operators[op]))
+
+ def _coerce_version(self, version):
+ if not isinstance(version, (LegacyVersion, Version)):
+ version = parse(version)
+ return version
+
+ @property
+ def operator(self):
+ return self._spec[0]
+
+ @property
+ def version(self):
+ return self._spec[1]
+
+ @property
+ def prereleases(self):
+ return self._prereleases
+
+ @prereleases.setter
+ def prereleases(self, value):
+ self._prereleases = value
+
+ def __contains__(self, item):
+ return self.contains(item)
+
+ def contains(self, item, prereleases=None):
+ # Determine if prereleases are to be allowed or not.
+ if prereleases is None:
+ prereleases = self.prereleases
+
+ # Normalize item to a Version or LegacyVersion, this allows us to have
+ # a shortcut for ``"2.0" in Specifier(">=2")
+ item = self._coerce_version(item)
+
+ # Determine if we should be supporting prereleases in this specifier
+ # or not, if we do not support prereleases than we can short circuit
+ # logic if this version is a prereleases.
+ if item.is_prerelease and not prereleases:
+ return False
+
+ # Actually do the comparison to determine if this item is contained
+ # within this Specifier or not.
+ return self._get_operator(self.operator)(item, self.version)
+
+ def filter(self, iterable, prereleases=None):
+ yielded = False
+ found_prereleases = []
+
+ kw = {"prereleases": prereleases if prereleases is not None else True}
+
+ # Attempt to iterate over all the values in the iterable and if any of
+ # them match, yield them.
+ for version in iterable:
+ parsed_version = self._coerce_version(version)
+
+ if self.contains(parsed_version, **kw):
+ # If our version is a prerelease, and we were not set to allow
+ # prereleases, then we'll store it for later incase nothing
+ # else matches this specifier.
+ if (parsed_version.is_prerelease and not
+ (prereleases or self.prereleases)):
+ found_prereleases.append(version)
+ # Either this is not a prerelease, or we should have been
+ # accepting prereleases from the begining.
+ else:
+ yielded = True
+ yield version
+
+ # Now that we've iterated over everything, determine if we've yielded
+ # any values, and if we have not and we have any prereleases stored up
+ # then we will go ahead and yield the prereleases.
+ if not yielded and found_prereleases:
+ for version in found_prereleases:
+ yield version
+
+
+class LegacySpecifier(_IndividualSpecifier):
+
+ _regex_str = (
+ r"""
+ (?P<operator>(==|!=|<=|>=|<|>))
+ \s*
+ (?P<version>
+ [^,;\s)]* # Since this is a "legacy" specifier, and the version
+ # string can be just about anything, we match everything
+ # except for whitespace, a semi-colon for marker support,
+ # a closing paren since versions can be enclosed in
+ # them, and a comma since it's a version separator.
+ )
+ """
+ )
+
+ _regex = re.compile(
+ r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE)
+
+ _operators = {
+ "==": "equal",
+ "!=": "not_equal",
+ "<=": "less_than_equal",
+ ">=": "greater_than_equal",
+ "<": "less_than",
+ ">": "greater_than",
+ }
+
+ def _coerce_version(self, version):
+ if not isinstance(version, LegacyVersion):
+ version = LegacyVersion(str(version))
+ return version
+
+ def _compare_equal(self, prospective, spec):
+ return prospective == self._coerce_version(spec)
+
+ def _compare_not_equal(self, prospective, spec):
+ return prospective != self._coerce_version(spec)
+
+ def _compare_less_than_equal(self, prospective, spec):
+ return prospective <= self._coerce_version(spec)
+
+ def _compare_greater_than_equal(self, prospective, spec):
+ return prospective >= self._coerce_version(spec)
+
+ def _compare_less_than(self, prospective, spec):
+ return prospective < self._coerce_version(spec)
+
+ def _compare_greater_than(self, prospective, spec):
+ return prospective > self._coerce_version(spec)
+
+
+def _require_version_compare(fn):
+ @functools.wraps(fn)
+ def wrapped(self, prospective, spec):
+ if not isinstance(prospective, Version):
+ return False
+ return fn(self, prospective, spec)
+ return wrapped
+
+
+class Specifier(_IndividualSpecifier):
+
+ _regex_str = (
+ r"""
+ (?P<operator>(~=|==|!=|<=|>=|<|>|===))
+ (?P<version>
+ (?:
+ # The identity operators allow for an escape hatch that will
+ # do an exact string match of the version you wish to install.
+ # This will not be parsed by PEP 440 and we cannot determine
+ # any semantic meaning from it. This operator is discouraged
+ # but included entirely as an escape hatch.
+ (?<====) # Only match for the identity operator
+ \s*
+ [^\s]* # We just match everything, except for whitespace
+ # since we are only testing for strict identity.
+ )
+ |
+ (?:
+ # The (non)equality operators allow for wild card and local
+ # versions to be specified so we have to define these two
+ # operators separately to enable that.
+ (?<===|!=) # Only match for equals and not equals
+
+ \s*
+ v?
+ (?:[0-9]+!)? # epoch
+ [0-9]+(?:\.[0-9]+)* # release
+ (?: # pre release
+ [-_\.]?
+ (a|b|c|rc|alpha|beta|pre|preview)
+ [-_\.]?
+ [0-9]*
+ )?
+ (?: # post release
+ (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*)
+ )?
+
+ # You cannot use a wild card and a dev or local version
+ # together so group them with a | and make them optional.
+ (?:
+ (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release
+ (?:\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*)? # local
+ |
+ \.\* # Wild card syntax of .*
+ )?
+ )
+ |
+ (?:
+ # The compatible operator requires at least two digits in the
+ # release segment.
+ (?<=~=) # Only match for the compatible operator
+
+ \s*
+ v?
+ (?:[0-9]+!)? # epoch
+ [0-9]+(?:\.[0-9]+)+ # release (We have a + instead of a *)
+ (?: # pre release
+ [-_\.]?
+ (a|b|c|rc|alpha|beta|pre|preview)
+ [-_\.]?
+ [0-9]*
+ )?
+ (?: # post release
+ (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*)
+ )?
+ (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release
+ )
+ |
+ (?:
+ # All other operators only allow a sub set of what the
+ # (non)equality operators do. Specifically they do not allow
+ # local versions to be specified nor do they allow the prefix
+ # matching wild cards.
+ (?<!==|!=|~=) # We have special cases for these
+ # operators so we want to make sure they
+ # don't match here.
+
+ \s*
+ v?
+ (?:[0-9]+!)? # epoch
+ [0-9]+(?:\.[0-9]+)* # release
+ (?: # pre release
+ [-_\.]?
+ (a|b|c|rc|alpha|beta|pre|preview)
+ [-_\.]?
+ [0-9]*
+ )?
+ (?: # post release
+ (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*)
+ )?
+ (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release
+ )
+ )
+ """
+ )
+
+ _regex = re.compile(
+ r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE)
+
+ _operators = {
+ "~=": "compatible",
+ "==": "equal",
+ "!=": "not_equal",
+ "<=": "less_than_equal",
+ ">=": "greater_than_equal",
+ "<": "less_than",
+ ">": "greater_than",
+ "===": "arbitrary",
+ }
+
+ @_require_version_compare
+ def _compare_compatible(self, prospective, spec):
+ # Compatible releases have an equivalent combination of >= and ==. That
+ # is that ~=2.2 is equivalent to >=2.2,==2.*. This allows us to
+ # implement this in terms of the other specifiers instead of
+ # implementing it ourselves. The only thing we need to do is construct
+ # the other specifiers.
+
+ # We want everything but the last item in the version, but we want to
+ # ignore post and dev releases and we want to treat the pre-release as
+ # it's own separate segment.
+ prefix = ".".join(
+ list(
+ itertools.takewhile(
+ lambda x: (not x.startswith("post") and not
+ x.startswith("dev")),
+ _version_split(spec),
+ )
+ )[:-1]
+ )
+
+ # Add the prefix notation to the end of our string
+ prefix += ".*"
+
+ return (self._get_operator(">=")(prospective, spec) and
+ self._get_operator("==")(prospective, prefix))
+
+ @_require_version_compare
+ def _compare_equal(self, prospective, spec):
+ # We need special logic to handle prefix matching
+ if spec.endswith(".*"):
+ # In the case of prefix matching we want to ignore local segment.
+ prospective = Version(prospective.public)
+ # Split the spec out by dots, and pretend that there is an implicit
+ # dot in between a release segment and a pre-release segment.
+ spec = _version_split(spec[:-2]) # Remove the trailing .*
+
+ # Split the prospective version out by dots, and pretend that there
+ # is an implicit dot in between a release segment and a pre-release
+ # segment.
+ prospective = _version_split(str(prospective))
+
+ # Shorten the prospective version to be the same length as the spec
+ # so that we can determine if the specifier is a prefix of the
+ # prospective version or not.
+ prospective = prospective[:len(spec)]
+
+ # Pad out our two sides with zeros so that they both equal the same
+ # length.
+ spec, prospective = _pad_version(spec, prospective)
+ else:
+ # Convert our spec string into a Version
+ spec = Version(spec)
+
+ # If the specifier does not have a local segment, then we want to
+ # act as if the prospective version also does not have a local
+ # segment.
+ if not spec.local:
+ prospective = Version(prospective.public)
+
+ return prospective == spec
+
+ @_require_version_compare
+ def _compare_not_equal(self, prospective, spec):
+ return not self._compare_equal(prospective, spec)
+
+ @_require_version_compare
+ def _compare_less_than_equal(self, prospective, spec):
+ return prospective <= Version(spec)
+
+ @_require_version_compare
+ def _compare_greater_than_equal(self, prospective, spec):
+ return prospective >= Version(spec)
+
+ @_require_version_compare
+ def _compare_less_than(self, prospective, spec):
+ # Convert our spec to a Version instance, since we'll want to work with
+ # it as a version.
+ spec = Version(spec)
+
+ # Check to see if the prospective version is less than the spec
+ # version. If it's not we can short circuit and just return False now
+ # instead of doing extra unneeded work.
+ if not prospective < spec:
+ return False
+
+ # This special case is here so that, unless the specifier itself
+ # includes is a pre-release version, that we do not accept pre-release
+ # versions for the version mentioned in the specifier (e.g. <3.1 should
+ # not match 3.1.dev0, but should match 3.0.dev0).
+ if not spec.is_prerelease and prospective.is_prerelease:
+ if Version(prospective.base_version) == Version(spec.base_version):
+ return False
+
+ # If we've gotten to here, it means that prospective version is both
+ # less than the spec version *and* it's not a pre-release of the same
+ # version in the spec.
+ return True
+
+ @_require_version_compare
+ def _compare_greater_than(self, prospective, spec):
+ # Convert our spec to a Version instance, since we'll want to work with
+ # it as a version.
+ spec = Version(spec)
+
+ # Check to see if the prospective version is greater than the spec
+ # version. If it's not we can short circuit and just return False now
+ # instead of doing extra unneeded work.
+ if not prospective > spec:
+ return False
+
+ # This special case is here so that, unless the specifier itself
+ # includes is a post-release version, that we do not accept
+ # post-release versions for the version mentioned in the specifier
+ # (e.g. >3.1 should not match 3.0.post0, but should match 3.2.post0).
+ if not spec.is_postrelease and prospective.is_postrelease:
+ if Version(prospective.base_version) == Version(spec.base_version):
+ return False
+
+ # Ensure that we do not allow a local version of the version mentioned
+ # in the specifier, which is techincally greater than, to match.
+ if prospective.local is not None:
+ if Version(prospective.base_version) == Version(spec.base_version):
+ return False
+
+ # If we've gotten to here, it means that prospective version is both
+ # greater than the spec version *and* it's not a pre-release of the
+ # same version in the spec.
+ return True
+
+ def _compare_arbitrary(self, prospective, spec):
+ return str(prospective).lower() == str(spec).lower()
+
+ @property
+ def prereleases(self):
+ # If there is an explicit prereleases set for this, then we'll just
+ # blindly use that.
+ if self._prereleases is not None:
+ return self._prereleases
+
+ # Look at all of our specifiers and determine if they are inclusive
+ # operators, and if they are if they are including an explicit
+ # prerelease.
+ operator, version = self._spec
+ if operator in ["==", ">=", "<=", "~=", "==="]:
+ # The == specifier can include a trailing .*, if it does we
+ # want to remove before parsing.
+ if operator == "==" and version.endswith(".*"):
+ version = version[:-2]
+
+ # Parse the version, and if it is a pre-release than this
+ # specifier allows pre-releases.
+ if parse(version).is_prerelease:
+ return True
+
+ return False
+
+ @prereleases.setter
+ def prereleases(self, value):
+ self._prereleases = value
+
+
+_prefix_regex = re.compile(r"^([0-9]+)((?:a|b|c|rc)[0-9]+)$")
+
+
+def _version_split(version):
+ result = []
+ for item in version.split("."):
+ match = _prefix_regex.search(item)
+ if match:
+ result.extend(match.groups())
+ else:
+ result.append(item)
+ return result
+
+
+def _pad_version(left, right):
+ left_split, right_split = [], []
+
+ # Get the release segment of our versions
+ left_split.append(list(itertools.takewhile(lambda x: x.isdigit(), left)))
+ right_split.append(list(itertools.takewhile(lambda x: x.isdigit(), right)))
+
+ # Get the rest of our versions
+ left_split.append(left[len(left_split[0]):])
+ right_split.append(right[len(right_split[0]):])
+
+ # Insert our padding
+ left_split.insert(
+ 1,
+ ["0"] * max(0, len(right_split[0]) - len(left_split[0])),
+ )
+ right_split.insert(
+ 1,
+ ["0"] * max(0, len(left_split[0]) - len(right_split[0])),
+ )
+
+ return (
+ list(itertools.chain(*left_split)),
+ list(itertools.chain(*right_split)),
+ )
+
+
+class SpecifierSet(BaseSpecifier):
+
+ def __init__(self, specifiers="", prereleases=None):
+ # Split on , to break each indidivual specifier into it's own item, and
+ # strip each item to remove leading/trailing whitespace.
+ specifiers = [s.strip() for s in specifiers.split(",") if s.strip()]
+
+ # Parsed each individual specifier, attempting first to make it a
+ # Specifier and falling back to a LegacySpecifier.
+ parsed = set()
+ for specifier in specifiers:
+ try:
+ parsed.add(Specifier(specifier))
+ except InvalidSpecifier:
+ parsed.add(LegacySpecifier(specifier))
+
+ # Turn our parsed specifiers into a frozen set and save them for later.
+ self._specs = frozenset(parsed)
+
+ # Store our prereleases value so we can use it later to determine if
+ # we accept prereleases or not.
+ self._prereleases = prereleases
+
+ def __repr__(self):
+ pre = (
+ ", prereleases={0!r}".format(self.prereleases)
+ if self._prereleases is not None
+ else ""
+ )
+
+ return "<SpecifierSet({0!r}{1})>".format(str(self), pre)
+
+ def __str__(self):
+ return ",".join(sorted(str(s) for s in self._specs))
+
+ def __hash__(self):
+ return hash(self._specs)
+
+ def __and__(self, other):
+ if isinstance(other, string_types):
+ other = SpecifierSet(other)
+ elif not isinstance(other, SpecifierSet):
+ return NotImplemented
+
+ specifier = SpecifierSet()
+ specifier._specs = frozenset(self._specs | other._specs)
+
+ if self._prereleases is None and other._prereleases is not None:
+ specifier._prereleases = other._prereleases
+ elif self._prereleases is not None and other._prereleases is None:
+ specifier._prereleases = self._prereleases
+ elif self._prereleases == other._prereleases:
+ specifier._prereleases = self._prereleases
+ else:
+ raise ValueError(
+ "Cannot combine SpecifierSets with True and False prerelease "
+ "overrides."
+ )
+
+ return specifier
+
+ def __eq__(self, other):
+ if isinstance(other, string_types):
+ other = SpecifierSet(other)
+ elif isinstance(other, _IndividualSpecifier):
+ other = SpecifierSet(str(other))
+ elif not isinstance(other, SpecifierSet):
+ return NotImplemented
+
+ return self._specs == other._specs
+
+ def __ne__(self, other):
+ if isinstance(other, string_types):
+ other = SpecifierSet(other)
+ elif isinstance(other, _IndividualSpecifier):
+ other = SpecifierSet(str(other))
+ elif not isinstance(other, SpecifierSet):
+ return NotImplemented
+
+ return self._specs != other._specs
+
+ def __len__(self):
+ return len(self._specs)
+
+ def __iter__(self):
+ return iter(self._specs)
+
+ @property
+ def prereleases(self):
+ # If we have been given an explicit prerelease modifier, then we'll
+ # pass that through here.
+ if self._prereleases is not None:
+ return self._prereleases
+
+ # If we don't have any specifiers, and we don't have a forced value,
+ # then we'll just return None since we don't know if this should have
+ # pre-releases or not.
+ if not self._specs:
+ return None
+
+ # Otherwise we'll see if any of the given specifiers accept
+ # prereleases, if any of them do we'll return True, otherwise False.
+ return any(s.prereleases for s in self._specs)
+
+ @prereleases.setter
+ def prereleases(self, value):
+ self._prereleases = value
+
+ def __contains__(self, item):
+ return self.contains(item)
+
+ def contains(self, item, prereleases=None):
+ # Ensure that our item is a Version or LegacyVersion instance.
+ if not isinstance(item, (LegacyVersion, Version)):
+ item = parse(item)
+
+ # Determine if we're forcing a prerelease or not, if we're not forcing
+ # one for this particular filter call, then we'll use whatever the
+ # SpecifierSet thinks for whether or not we should support prereleases.
+ if prereleases is None:
+ prereleases = self.prereleases
+
+ # We can determine if we're going to allow pre-releases by looking to
+ # see if any of the underlying items supports them. If none of them do
+ # and this item is a pre-release then we do not allow it and we can
+ # short circuit that here.
+ # Note: This means that 1.0.dev1 would not be contained in something
+ # like >=1.0.devabc however it would be in >=1.0.debabc,>0.0.dev0
+ if not prereleases and item.is_prerelease:
+ return False
+
+ # We simply dispatch to the underlying specs here to make sure that the
+ # given version is contained within all of them.
+ # Note: This use of all() here means that an empty set of specifiers
+ # will always return True, this is an explicit design decision.
+ return all(
+ s.contains(item, prereleases=prereleases)
+ for s in self._specs
+ )
+
+ def filter(self, iterable, prereleases=None):
+ # Determine if we're forcing a prerelease or not, if we're not forcing
+ # one for this particular filter call, then we'll use whatever the
+ # SpecifierSet thinks for whether or not we should support prereleases.
+ if prereleases is None:
+ prereleases = self.prereleases
+
+ # If we have any specifiers, then we want to wrap our iterable in the
+ # filter method for each one, this will act as a logical AND amongst
+ # each specifier.
+ if self._specs:
+ for spec in self._specs:
+ iterable = spec.filter(iterable, prereleases=bool(prereleases))
+ return iterable
+ # If we do not have any specifiers, then we need to have a rough filter
+ # which will filter out any pre-releases, unless there are no final
+ # releases, and which will filter out LegacyVersion in general.
+ else:
+ filtered = []
+ found_prereleases = []
+
+ for item in iterable:
+ # Ensure that we some kind of Version class for this item.
+ if not isinstance(item, (LegacyVersion, Version)):
+ parsed_version = parse(item)
+ else:
+ parsed_version = item
+
+ # Filter out any item which is parsed as a LegacyVersion
+ if isinstance(parsed_version, LegacyVersion):
+ continue
+
+ # Store any item which is a pre-release for later unless we've
+ # already found a final version or we are accepting prereleases
+ if parsed_version.is_prerelease and not prereleases:
+ if not filtered:
+ found_prereleases.append(item)
+ else:
+ filtered.append(item)
+
+ # If we've found no items except for pre-releases, then we'll go
+ # ahead and use the pre-releases
+ if not filtered and found_prereleases and prereleases is None:
+ return found_prereleases
+
+ return filtered
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/utils.py b/recipes/pkgresources/pkgr/_vendor/packaging/utils.py
new file mode 100644
index 0000000..942387c
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/utils.py
@@ -0,0 +1,14 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import re
+
+
+_canonicalize_regex = re.compile(r"[-_.]+")
+
+
+def canonicalize_name(name):
+ # This is taken from PEP 503.
+ return _canonicalize_regex.sub("-", name).lower()
diff --git a/recipes/pkgresources/pkgr/_vendor/packaging/version.py b/recipes/pkgresources/pkgr/_vendor/packaging/version.py
new file mode 100644
index 0000000..83b5ee8
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/packaging/version.py
@@ -0,0 +1,393 @@
+# This file is dual licensed under the terms of the Apache License, Version
+# 2.0, and the BSD License. See the LICENSE file in the root of this repository
+# for complete details.
+from __future__ import absolute_import, division, print_function
+
+import collections
+import itertools
+import re
+
+from ._structures import Infinity
+
+
+__all__ = [
+ "parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN"
+]
+
+
+_Version = collections.namedtuple(
+ "_Version",
+ ["epoch", "release", "dev", "pre", "post", "local"],
+)
+
+
+def parse(version):
+ """
+ Parse the given version string and return either a :class:`Version` object
+ or a :class:`LegacyVersion` object depending on if the given version is
+ a valid PEP 440 version or a legacy version.
+ """
+ try:
+ return Version(version)
+ except InvalidVersion:
+ return LegacyVersion(version)
+
+
+class InvalidVersion(ValueError):
+ """
+ An invalid version was found, users should refer to PEP 440.
+ """
+
+
+class _BaseVersion(object):
+
+ def __hash__(self):
+ return hash(self._key)
+
+ def __lt__(self, other):
+ return self._compare(other, lambda s, o: s < o)
+
+ def __le__(self, other):
+ return self._compare(other, lambda s, o: s <= o)
+
+ def __eq__(self, other):
+ return self._compare(other, lambda s, o: s == o)
+
+ def __ge__(self, other):
+ return self._compare(other, lambda s, o: s >= o)
+
+ def __gt__(self, other):
+ return self._compare(other, lambda s, o: s > o)
+
+ def __ne__(self, other):
+ return self._compare(other, lambda s, o: s != o)
+
+ def _compare(self, other, method):
+ if not isinstance(other, _BaseVersion):
+ return NotImplemented
+
+ return method(self._key, other._key)
+
+
+class LegacyVersion(_BaseVersion):
+
+ def __init__(self, version):
+ self._version = str(version)
+ self._key = _legacy_cmpkey(self._version)
+
+ def __str__(self):
+ return self._version
+
+ def __repr__(self):
+ return "<LegacyVersion({0})>".format(repr(str(self)))
+
+ @property
+ def public(self):
+ return self._version
+
+ @property
+ def base_version(self):
+ return self._version
+
+ @property
+ def local(self):
+ return None
+
+ @property
+ def is_prerelease(self):
+ return False
+
+ @property
+ def is_postrelease(self):
+ return False
+
+
+_legacy_version_component_re = re.compile(
+ r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE,
+)
+
+_legacy_version_replacement_map = {
+ "pre": "c", "preview": "c", "-": "final-", "rc": "c", "dev": "@",
+}
+
+
+def _parse_version_parts(s):
+ for part in _legacy_version_component_re.split(s):
+ part = _legacy_version_replacement_map.get(part, part)
+
+ if not part or part == ".":
+ continue
+
+ if part[:1] in "0123456789":
+ # pad for numeric comparison
+ yield part.zfill(8)
+ else:
+ yield "*" + part
+
+ # ensure that alpha/beta/candidate are before final
+ yield "*final"
+
+
+def _legacy_cmpkey(version):
+ # We hardcode an epoch of -1 here. A PEP 440 version can only have a epoch
+ # greater than or equal to 0. This will effectively put the LegacyVersion,
+ # which uses the defacto standard originally implemented by setuptools,
+ # as before all PEP 440 versions.
+ epoch = -1
+
+ # This scheme is taken from pkg_resources.parse_version setuptools prior to
+ # it's adoption of the packaging library.
+ parts = []
+ for part in _parse_version_parts(version.lower()):
+ if part.startswith("*"):
+ # remove "-" before a prerelease tag
+ if part < "*final":
+ while parts and parts[-1] == "*final-":
+ parts.pop()
+
+ # remove trailing zeros from each series of numeric parts
+ while parts and parts[-1] == "00000000":
+ parts.pop()
+
+ parts.append(part)
+ parts = tuple(parts)
+
+ return epoch, parts
+
+# Deliberately not anchored to the start and end of the string, to make it
+# easier for 3rd party code to reuse
+VERSION_PATTERN = r"""
+ v?
+ (?:
+ (?:(?P<epoch>[0-9]+)!)? # epoch
+ (?P<release>[0-9]+(?:\.[0-9]+)*) # release segment
+ (?P<pre> # pre-release
+ [-_\.]?
+ (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
+ [-_\.]?
+ (?P<pre_n>[0-9]+)?
+ )?
+ (?P<post> # post release
+ (?:-(?P<post_n1>[0-9]+))
+ |
+ (?:
+ [-_\.]?
+ (?P<post_l>post|rev|r)
+ [-_\.]?
+ (?P<post_n2>[0-9]+)?
+ )
+ )?
+ (?P<dev> # dev release
+ [-_\.]?
+ (?P<dev_l>dev)
+ [-_\.]?
+ (?P<dev_n>[0-9]+)?
+ )?
+ )
+ (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))? # local version
+"""
+
+
+class Version(_BaseVersion):
+
+ _regex = re.compile(
+ r"^\s*" + VERSION_PATTERN + r"\s*$",
+ re.VERBOSE | re.IGNORECASE,
+ )
+
+ def __init__(self, version):
+ # Validate the version and parse it into pieces
+ match = self._regex.search(version)
+ if not match:
+ raise InvalidVersion("Invalid version: '{0}'".format(version))
+
+ # Store the parsed out pieces of the version
+ self._version = _Version(
+ epoch=int(match.group("epoch")) if match.group("epoch") else 0,
+ release=tuple(int(i) for i in match.group("release").split(".")),
+ pre=_parse_letter_version(
+ match.group("pre_l"),
+ match.group("pre_n"),
+ ),
+ post=_parse_letter_version(
+ match.group("post_l"),
+ match.group("post_n1") or match.group("post_n2"),
+ ),
+ dev=_parse_letter_version(
+ match.group("dev_l"),
+ match.group("dev_n"),
+ ),
+ local=_parse_local_version(match.group("local")),
+ )
+
+ # Generate a key which will be used for sorting
+ self._key = _cmpkey(
+ self._version.epoch,
+ self._version.release,
+ self._version.pre,
+ self._version.post,
+ self._version.dev,
+ self._version.local,
+ )
+
+ def __repr__(self):
+ return "<Version({0})>".format(repr(str(self)))
+
+ def __str__(self):
+ parts = []
+
+ # Epoch
+ if self._version.epoch != 0:
+ parts.append("{0}!".format(self._version.epoch))
+
+ # Release segment
+ parts.append(".".join(str(x) for x in self._version.release))
+
+ # Pre-release
+ if self._version.pre is not None:
+ parts.append("".join(str(x) for x in self._version.pre))
+
+ # Post-release
+ if self._version.post is not None:
+ parts.append(".post{0}".format(self._version.post[1]))
+
+ # Development release
+ if self._version.dev is not None:
+ parts.append(".dev{0}".format(self._version.dev[1]))
+
+ # Local version segment
+ if self._version.local is not None:
+ parts.append(
+ "+{0}".format(".".join(str(x) for x in self._version.local))
+ )
+
+ return "".join(parts)
+
+ @property
+ def public(self):
+ return str(self).split("+", 1)[0]
+
+ @property
+ def base_version(self):
+ parts = []
+
+ # Epoch
+ if self._version.epoch != 0:
+ parts.append("{0}!".format(self._version.epoch))
+
+ # Release segment
+ parts.append(".".join(str(x) for x in self._version.release))
+
+ return "".join(parts)
+
+ @property
+ def local(self):
+ version_string = str(self)
+ if "+" in version_string:
+ return version_string.split("+", 1)[1]
+
+ @property
+ def is_prerelease(self):
+ return bool(self._version.dev or self._version.pre)
+
+ @property
+ def is_postrelease(self):
+ return bool(self._version.post)
+
+
+def _parse_letter_version(letter, number):
+ if letter:
+ # We consider there to be an implicit 0 in a pre-release if there is
+ # not a numeral associated with it.
+ if number is None:
+ number = 0
+
+ # We normalize any letters to their lower case form
+ letter = letter.lower()
+
+ # We consider some words to be alternate spellings of other words and
+ # in those cases we want to normalize the spellings to our preferred
+ # spelling.
+ if letter == "alpha":
+ letter = "a"
+ elif letter == "beta":
+ letter = "b"
+ elif letter in ["c", "pre", "preview"]:
+ letter = "rc"
+ elif letter in ["rev", "r"]:
+ letter = "post"
+
+ return letter, int(number)
+ if not letter and number:
+ # We assume if we are given a number, but we are not given a letter
+ # then this is using the implicit post release syntax (e.g. 1.0-1)
+ letter = "post"
+
+ return letter, int(number)
+
+
+_local_version_seperators = re.compile(r"[\._-]")
+
+
+def _parse_local_version(local):
+ """
+ Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
+ """
+ if local is not None:
+ return tuple(
+ part.lower() if not part.isdigit() else int(part)
+ for part in _local_version_seperators.split(local)
+ )
+
+
+def _cmpkey(epoch, release, pre, post, dev, local):
+ # When we compare a release version, we want to compare it with all of the
+ # trailing zeros removed. So we'll use a reverse the list, drop all the now
+ # leading zeros until we come to something non zero, then take the rest
+ # re-reverse it back into the correct order and make it a tuple and use
+ # that for our sorting key.
+ release = tuple(
+ reversed(list(
+ itertools.dropwhile(
+ lambda x: x == 0,
+ reversed(release),
+ )
+ ))
+ )
+
+ # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0.
+ # We'll do this by abusing the pre segment, but we _only_ want to do this
+ # if there is not a pre or a post segment. If we have one of those then
+ # the normal sorting rules will handle this case correctly.
+ if pre is None and post is None and dev is not None:
+ pre = -Infinity
+ # Versions without a pre-release (except as noted above) should sort after
+ # those with one.
+ elif pre is None:
+ pre = Infinity
+
+ # Versions without a post segment should sort before those with one.
+ if post is None:
+ post = -Infinity
+
+ # Versions without a development segment should sort after those with one.
+ if dev is None:
+ dev = Infinity
+
+ if local is None:
+ # Versions without a local segment should sort before those with one.
+ local = -Infinity
+ else:
+ # Versions with a local segment need that segment parsed to implement
+ # the sorting rules in PEP440.
+ # - Alpha numeric segments sort before numeric segments
+ # - Alpha numeric segments sort lexicographically
+ # - Numeric segments sort numerically
+ # - Shorter versions sort before longer versions when the prefixes
+ # match exactly
+ local = tuple(
+ (i, "") if isinstance(i, int) else (-Infinity, i)
+ for i in local
+ )
+
+ return epoch, release, pre, post, dev, local
diff --git a/recipes/pkgresources/pkgr/_vendor/pyparsing.py b/recipes/pkgresources/pkgr/_vendor/pyparsing.py
new file mode 100644
index 0000000..a212243
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/pyparsing.py
@@ -0,0 +1,5696 @@
+# module pyparsing.py
+#
+# Copyright (c) 2003-2016 Paul T. McGuire
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+#
+
+__doc__ = \
+"""
+pyparsing module - Classes and methods to define and execute parsing grammars
+
+The pyparsing module is an alternative approach to creating and executing simple grammars,
+vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you
+don't need to learn a new syntax for defining grammars or matching expressions - the parsing module
+provides a library of classes that you use to construct the grammar directly in Python.
+
+Here is a program to parse "Hello, World!" (or any greeting of the form
+C{"<salutation>, <addressee>!"}), built up using L{Word}, L{Literal}, and L{And} elements
+(L{'+'<ParserElement.__add__>} operator gives L{And} expressions, strings are auto-converted to
+L{Literal} expressions)::
+
+ from pyparsing import Word, alphas
+
+ # define grammar of a greeting
+ greet = Word(alphas) + "," + Word(alphas) + "!"
+
+ hello = "Hello, World!"
+ print (hello, "->", greet.parseString(hello))
+
+The program outputs the following::
+
+ Hello, World! -> ['Hello', ',', 'World', '!']
+
+The Python representation of the grammar is quite readable, owing to the self-explanatory
+class names, and the use of '+', '|' and '^' operators.
+
+The L{ParseResults} object returned from L{ParserElement.parseString<ParserElement.parseString>} can be accessed as a nested list, a dictionary, or an
+object with named attributes.
+
+The pyparsing module handles some of the problems that are typically vexing when writing text parsers:
+ - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.)
+ - quoted strings
+ - embedded comments
+"""
+
+__version__ = "2.1.10"
+__versionTime__ = "07 Oct 2016 01:31 UTC"
+__author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"
+
+import string
+from weakref import ref as wkref
+import copy
+import sys
+import warnings
+import re
+import sre_constants
+import collections
+import pprint
+import traceback
+import types
+from datetime import datetime
+
+try:
+ from _thread import RLock
+except ImportError:
+ from threading import RLock
+
+try:
+ from collections import OrderedDict as _OrderedDict
+except ImportError:
+ try:
+ from ordereddict import OrderedDict as _OrderedDict
+ except ImportError:
+ _OrderedDict = None
+
+#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )
+
+__all__ = [
+'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty',
+'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal',
+'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or',
+'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException',
+'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException',
+'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter',
+'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
+'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
+'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
+'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
+'htmlComment', 'javaStyleComment', 'line', 'lineEnd', 'lineStart', 'lineno',
+'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral',
+'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables',
+'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity',
+'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd',
+'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute',
+'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation','locatedExpr', 'withClass',
+'CloseMatch', 'tokenMap', 'pyparsing_common',
+]
+
+system_version = tuple(sys.version_info)[:3]
+PY_3 = system_version[0] == 3
+if PY_3:
+ _MAX_INT = sys.maxsize
+ basestring = str
+ unichr = chr
+ _ustr = str
+
+ # build list of single arg builtins, that can be used as parse actions
+ singleArgBuiltins = [sum, len, sorted, reversed, list, tuple, set, any, all, min, max]
+
+else:
+ _MAX_INT = sys.maxint
+ range = xrange
+
+ def _ustr(obj):
+ """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries
+ str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It
+ then < returns the unicode object | encodes it with the default encoding | ... >.
+ """
+ if isinstance(obj,unicode):
+ return obj
+
+ try:
+ # If this works, then _ustr(obj) has the same behaviour as str(obj), so
+ # it won't break any existing code.
+ return str(obj)
+
+ except UnicodeEncodeError:
+ # Else encode it
+ ret = unicode(obj).encode(sys.getdefaultencoding(), 'xmlcharrefreplace')
+ xmlcharref = Regex('&#\d+;')
+ xmlcharref.setParseAction(lambda t: '\\u' + hex(int(t[0][2:-1]))[2:])
+ return xmlcharref.transformString(ret)
+
+ # build list of single arg builtins, tolerant of Python version, that can be used as parse actions
+ singleArgBuiltins = []
+ import __builtin__
+ for fname in "sum len sorted reversed list tuple set any all min max".split():
+ try:
+ singleArgBuiltins.append(getattr(__builtin__,fname))
+ except AttributeError:
+ continue
+
+_generatorType = type((y for y in range(1)))
+
+def _xml_escape(data):
+ """Escape &, <, >, ", ', etc. in a string of data."""
+
+ # ampersand must be replaced first
+ from_symbols = '&><"\''
+ to_symbols = ('&'+s+';' for s in "amp gt lt quot apos".split())
+ for from_,to_ in zip(from_symbols, to_symbols):
+ data = data.replace(from_, to_)
+ return data
+
+class _Constants(object):
+ pass
+
+alphas = string.ascii_uppercase + string.ascii_lowercase
+nums = "0123456789"
+hexnums = nums + "ABCDEFabcdef"
+alphanums = alphas + nums
+_bslash = chr(92)
+printables = "".join(c for c in string.printable if c not in string.whitespace)
+
+class ParseBaseException(Exception):
+ """base exception class for all parsing runtime exceptions"""
+ # Performance tuning: we construct a *lot* of these, so keep this
+ # constructor as small and fast as possible
+ def __init__( self, pstr, loc=0, msg=None, elem=None ):
+ self.loc = loc
+ if msg is None:
+ self.msg = pstr
+ self.pstr = ""
+ else:
+ self.msg = msg
+ self.pstr = pstr
+ self.parserElement = elem
+ self.args = (pstr, loc, msg)
+
+ @classmethod
+ def _from_exception(cls, pe):
+ """
+ internal factory method to simplify creating one type of ParseException
+ from another - avoids having __init__ signature conflicts among subclasses
+ """
+ return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement)
+
+ def __getattr__( self, aname ):
+ """supported attributes by name are:
+ - lineno - returns the line number of the exception text
+ - col - returns the column number of the exception text
+ - line - returns the line containing the exception text
+ """
+ if( aname == "lineno" ):
+ return lineno( self.loc, self.pstr )
+ elif( aname in ("col", "column") ):
+ return col( self.loc, self.pstr )
+ elif( aname == "line" ):
+ return line( self.loc, self.pstr )
+ else:
+ raise AttributeError(aname)
+
+ def __str__( self ):
+ return "%s (at char %d), (line:%d, col:%d)" % \
+ ( self.msg, self.loc, self.lineno, self.column )
+ def __repr__( self ):
+ return _ustr(self)
+ def markInputline( self, markerString = ">!<" ):
+ """Extracts the exception line from the input string, and marks
+ the location of the exception with a special symbol.
+ """
+ line_str = self.line
+ line_column = self.column - 1
+ if markerString:
+ line_str = "".join((line_str[:line_column],
+ markerString, line_str[line_column:]))
+ return line_str.strip()
+ def __dir__(self):
+ return "lineno col line".split() + dir(type(self))
+
+class ParseException(ParseBaseException):
+ """
+ Exception thrown when parse expressions don't match class;
+ supported attributes by name are:
+ - lineno - returns the line number of the exception text
+ - col - returns the column number of the exception text
+ - line - returns the line containing the exception text
+
+ Example::
+ try:
+ Word(nums).setName("integer").parseString("ABC")
+ except ParseException as pe:
+ print(pe)
+ print("column: {}".format(pe.col))
+
+ prints::
+ Expected integer (at char 0), (line:1, col:1)
+ column: 1
+ """
+ pass
+
+class ParseFatalException(ParseBaseException):
+ """user-throwable exception thrown when inconsistent parse content
+ is found; stops all parsing immediately"""
+ pass
+
+class ParseSyntaxException(ParseFatalException):
+ """just like L{ParseFatalException}, but thrown internally when an
+ L{ErrorStop<And._ErrorStop>} ('-' operator) indicates that parsing is to stop
+ immediately because an unbacktrackable syntax error has been found"""
+ pass
+
+#~ class ReparseException(ParseBaseException):
+ #~ """Experimental class - parse actions can raise this exception to cause
+ #~ pyparsing to reparse the input string:
+ #~ - with a modified input string, and/or
+ #~ - with a modified start location
+ #~ Set the values of the ReparseException in the constructor, and raise the
+ #~ exception in a parse action to cause pyparsing to use the new string/location.
+ #~ Setting the values as None causes no change to be made.
+ #~ """
+ #~ def __init_( self, newstring, restartLoc ):
+ #~ self.newParseText = newstring
+ #~ self.reparseLoc = restartLoc
+
+class RecursiveGrammarException(Exception):
+ """exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive"""
+ def __init__( self, parseElementList ):
+ self.parseElementTrace = parseElementList
+
+ def __str__( self ):
+ return "RecursiveGrammarException: %s" % self.parseElementTrace
+
+class _ParseResultsWithOffset(object):
+ def __init__(self,p1,p2):
+ self.tup = (p1,p2)
+ def __getitem__(self,i):
+ return self.tup[i]
+ def __repr__(self):
+ return repr(self.tup[0])
+ def setOffset(self,i):
+ self.tup = (self.tup[0],i)
+
+class ParseResults(object):
+ """
+ Structured parse results, to provide multiple means of access to the parsed data:
+ - as a list (C{len(results)})
+ - by list index (C{results[0], results[1]}, etc.)
+ - by attribute (C{results.<resultsName>} - see L{ParserElement.setResultsName})
+
+ Example::
+ integer = Word(nums)
+ date_str = (integer.setResultsName("year") + '/'
+ + integer.setResultsName("month") + '/'
+ + integer.setResultsName("day"))
+ # equivalent form:
+ # date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ # parseString returns a ParseResults object
+ result = date_str.parseString("1999/12/31")
+
+ def test(s, fn=repr):
+ print("%s -> %s" % (s, fn(eval(s))))
+ test("list(result)")
+ test("result[0]")
+ test("result['month']")
+ test("result.day")
+ test("'month' in result")
+ test("'minutes' in result")
+ test("result.dump()", str)
+ prints::
+ list(result) -> ['1999', '/', '12', '/', '31']
+ result[0] -> '1999'
+ result['month'] -> '12'
+ result.day -> '31'
+ 'month' in result -> True
+ 'minutes' in result -> False
+ result.dump() -> ['1999', '/', '12', '/', '31']
+ - day: 31
+ - month: 12
+ - year: 1999
+ """
+ def __new__(cls, toklist=None, name=None, asList=True, modal=True ):
+ if isinstance(toklist, cls):
+ return toklist
+ retobj = object.__new__(cls)
+ retobj.__doinit = True
+ return retobj
+
+ # Performance tuning: we construct a *lot* of these, so keep this
+ # constructor as small and fast as possible
+ def __init__( self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance ):
+ if self.__doinit:
+ self.__doinit = False
+ self.__name = None
+ self.__parent = None
+ self.__accumNames = {}
+ self.__asList = asList
+ self.__modal = modal
+ if toklist is None:
+ toklist = []
+ if isinstance(toklist, list):
+ self.__toklist = toklist[:]
+ elif isinstance(toklist, _generatorType):
+ self.__toklist = list(toklist)
+ else:
+ self.__toklist = [toklist]
+ self.__tokdict = dict()
+
+ if name is not None and name:
+ if not modal:
+ self.__accumNames[name] = 0
+ if isinstance(name,int):
+ name = _ustr(name) # will always return a str, but use _ustr for consistency
+ self.__name = name
+ if not (isinstance(toklist, (type(None), basestring, list)) and toklist in (None,'',[])):
+ if isinstance(toklist,basestring):
+ toklist = [ toklist ]
+ if asList:
+ if isinstance(toklist,ParseResults):
+ self[name] = _ParseResultsWithOffset(toklist.copy(),0)
+ else:
+ self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0)
+ self[name].__name = name
+ else:
+ try:
+ self[name] = toklist[0]
+ except (KeyError,TypeError,IndexError):
+ self[name] = toklist
+
+ def __getitem__( self, i ):
+ if isinstance( i, (int,slice) ):
+ return self.__toklist[i]
+ else:
+ if i not in self.__accumNames:
+ return self.__tokdict[i][-1][0]
+ else:
+ return ParseResults([ v[0] for v in self.__tokdict[i] ])
+
+ def __setitem__( self, k, v, isinstance=isinstance ):
+ if isinstance(v,_ParseResultsWithOffset):
+ self.__tokdict[k] = self.__tokdict.get(k,list()) + [v]
+ sub = v[0]
+ elif isinstance(k,(int,slice)):
+ self.__toklist[k] = v
+ sub = v
+ else:
+ self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)]
+ sub = v
+ if isinstance(sub,ParseResults):
+ sub.__parent = wkref(self)
+
+ def __delitem__( self, i ):
+ if isinstance(i,(int,slice)):
+ mylen = len( self.__toklist )
+ del self.__toklist[i]
+
+ # convert int to slice
+ if isinstance(i, int):
+ if i < 0:
+ i += mylen
+ i = slice(i, i+1)
+ # get removed indices
+ removed = list(range(*i.indices(mylen)))
+ removed.reverse()
+ # fixup indices in token dictionary
+ for name,occurrences in self.__tokdict.items():
+ for j in removed:
+ for k, (value, position) in enumerate(occurrences):
+ occurrences[k] = _ParseResultsWithOffset(value, position - (position > j))
+ else:
+ del self.__tokdict[i]
+
+ def __contains__( self, k ):
+ return k in self.__tokdict
+
+ def __len__( self ): return len( self.__toklist )
+ def __bool__(self): return ( not not self.__toklist )
+ __nonzero__ = __bool__
+ def __iter__( self ): return iter( self.__toklist )
+ def __reversed__( self ): return iter( self.__toklist[::-1] )
+ def _iterkeys( self ):
+ if hasattr(self.__tokdict, "iterkeys"):
+ return self.__tokdict.iterkeys()
+ else:
+ return iter(self.__tokdict)
+
+ def _itervalues( self ):
+ return (self[k] for k in self._iterkeys())
+
+ def _iteritems( self ):
+ return ((k, self[k]) for k in self._iterkeys())
+
+ if PY_3:
+ keys = _iterkeys
+ """Returns an iterator of all named result keys (Python 3.x only)."""
+
+ values = _itervalues
+ """Returns an iterator of all named result values (Python 3.x only)."""
+
+ items = _iteritems
+ """Returns an iterator of all named result key-value tuples (Python 3.x only)."""
+
+ else:
+ iterkeys = _iterkeys
+ """Returns an iterator of all named result keys (Python 2.x only)."""
+
+ itervalues = _itervalues
+ """Returns an iterator of all named result values (Python 2.x only)."""
+
+ iteritems = _iteritems
+ """Returns an iterator of all named result key-value tuples (Python 2.x only)."""
+
+ def keys( self ):
+ """Returns all named result keys (as a list in Python 2.x, as an iterator in Python 3.x)."""
+ return list(self.iterkeys())
+
+ def values( self ):
+ """Returns all named result values (as a list in Python 2.x, as an iterator in Python 3.x)."""
+ return list(self.itervalues())
+
+ def items( self ):
+ """Returns all named result key-values (as a list of tuples in Python 2.x, as an iterator in Python 3.x)."""
+ return list(self.iteritems())
+
+ def haskeys( self ):
+ """Since keys() returns an iterator, this method is helpful in bypassing
+ code that looks for the existence of any defined results names."""
+ return bool(self.__tokdict)
+
+ def pop( self, *args, **kwargs):
+ """
+ Removes and returns item at specified index (default=C{last}).
+ Supports both C{list} and C{dict} semantics for C{pop()}. If passed no
+ argument or an integer argument, it will use C{list} semantics
+ and pop tokens from the list of parsed tokens. If passed a
+ non-integer argument (most likely a string), it will use C{dict}
+ semantics and pop the corresponding value from any defined
+ results names. A second default return value argument is
+ supported, just as in C{dict.pop()}.
+
+ Example::
+ def remove_first(tokens):
+ tokens.pop(0)
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+ print(OneOrMore(Word(nums)).addParseAction(remove_first).parseString("0 123 321")) # -> ['123', '321']
+
+ label = Word(alphas)
+ patt = label("LABEL") + OneOrMore(Word(nums))
+ print(patt.parseString("AAB 123 321").dump())
+
+ # Use pop() in a parse action to remove named result (note that corresponding value is not
+ # removed from list form of results)
+ def remove_LABEL(tokens):
+ tokens.pop("LABEL")
+ return tokens
+ patt.addParseAction(remove_LABEL)
+ print(patt.parseString("AAB 123 321").dump())
+ prints::
+ ['AAB', '123', '321']
+ - LABEL: AAB
+
+ ['AAB', '123', '321']
+ """
+ if not args:
+ args = [-1]
+ for k,v in kwargs.items():
+ if k == 'default':
+ args = (args[0], v)
+ else:
+ raise TypeError("pop() got an unexpected keyword argument '%s'" % k)
+ if (isinstance(args[0], int) or
+ len(args) == 1 or
+ args[0] in self):
+ index = args[0]
+ ret = self[index]
+ del self[index]
+ return ret
+ else:
+ defaultvalue = args[1]
+ return defaultvalue
+
+ def get(self, key, defaultValue=None):
+ """
+ Returns named result matching the given key, or if there is no
+ such name, then returns the given C{defaultValue} or C{None} if no
+ C{defaultValue} is specified.
+
+ Similar to C{dict.get()}.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString("1999/12/31")
+ print(result.get("year")) # -> '1999'
+ print(result.get("hour", "not specified")) # -> 'not specified'
+ print(result.get("hour")) # -> None
+ """
+ if key in self:
+ return self[key]
+ else:
+ return defaultValue
+
+ def insert( self, index, insStr ):
+ """
+ Inserts new element at location index in the list of parsed tokens.
+
+ Similar to C{list.insert()}.
+
+ Example::
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+
+ # use a parse action to insert the parse location in the front of the parsed results
+ def insert_locn(locn, tokens):
+ tokens.insert(0, locn)
+ print(OneOrMore(Word(nums)).addParseAction(insert_locn).parseString("0 123 321")) # -> [0, '0', '123', '321']
+ """
+ self.__toklist.insert(index, insStr)
+ # fixup indices in token dictionary
+ for name,occurrences in self.__tokdict.items():
+ for k, (value, position) in enumerate(occurrences):
+ occurrences[k] = _ParseResultsWithOffset(value, position + (position > index))
+
+ def append( self, item ):
+ """
+ Add single element to end of ParseResults list of elements.
+
+ Example::
+ print(OneOrMore(Word(nums)).parseString("0 123 321")) # -> ['0', '123', '321']
+
+ # use a parse action to compute the sum of the parsed integers, and add it to the end
+ def append_sum(tokens):
+ tokens.append(sum(map(int, tokens)))
+ print(OneOrMore(Word(nums)).addParseAction(append_sum).parseString("0 123 321")) # -> ['0', '123', '321', 444]
+ """
+ self.__toklist.append(item)
+
+ def extend( self, itemseq ):
+ """
+ Add sequence of elements to end of ParseResults list of elements.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+
+ # use a parse action to append the reverse of the matched strings, to make a palindrome
+ def make_palindrome(tokens):
+ tokens.extend(reversed([t[::-1] for t in tokens]))
+ return ''.join(tokens)
+ print(patt.addParseAction(make_palindrome).parseString("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl'
+ """
+ if isinstance(itemseq, ParseResults):
+ self += itemseq
+ else:
+ self.__toklist.extend(itemseq)
+
+ def clear( self ):
+ """
+ Clear all elements and results names.
+ """
+ del self.__toklist[:]
+ self.__tokdict.clear()
+
+ def __getattr__( self, name ):
+ try:
+ return self[name]
+ except KeyError:
+ return ""
+
+ if name in self.__tokdict:
+ if name not in self.__accumNames:
+ return self.__tokdict[name][-1][0]
+ else:
+ return ParseResults([ v[0] for v in self.__tokdict[name] ])
+ else:
+ return ""
+
+ def __add__( self, other ):
+ ret = self.copy()
+ ret += other
+ return ret
+
+ def __iadd__( self, other ):
+ if other.__tokdict:
+ offset = len(self.__toklist)
+ addoffset = lambda a: offset if a<0 else a+offset
+ otheritems = other.__tokdict.items()
+ otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) )
+ for (k,vlist) in otheritems for v in vlist]
+ for k,v in otherdictitems:
+ self[k] = v
+ if isinstance(v[0],ParseResults):
+ v[0].__parent = wkref(self)
+
+ self.__toklist += other.__toklist
+ self.__accumNames.update( other.__accumNames )
+ return self
+
+ def __radd__(self, other):
+ if isinstance(other,int) and other == 0:
+ # useful for merging many ParseResults using sum() builtin
+ return self.copy()
+ else:
+ # this may raise a TypeError - so be it
+ return other + self
+
+ def __repr__( self ):
+ return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) )
+
+ def __str__( self ):
+ return '[' + ', '.join(_ustr(i) if isinstance(i, ParseResults) else repr(i) for i in self.__toklist) + ']'
+
+ def _asStringList( self, sep='' ):
+ out = []
+ for item in self.__toklist:
+ if out and sep:
+ out.append(sep)
+ if isinstance( item, ParseResults ):
+ out += item._asStringList()
+ else:
+ out.append( _ustr(item) )
+ return out
+
+ def asList( self ):
+ """
+ Returns the parse results as a nested list of matching tokens, all converted to strings.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+ result = patt.parseString("sldkj lsdkj sldkj")
+ # even though the result prints in string-like form, it is actually a pyparsing ParseResults
+ print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj']
+
+ # Use asList() to create an actual list
+ result_list = result.asList()
+ print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj']
+ """
+ return [res.asList() if isinstance(res,ParseResults) else res for res in self.__toklist]
+
+ def asDict( self ):
+ """
+ Returns the named parse results as a nested dictionary.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString('12/31/1999')
+ print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]})
+
+ result_dict = result.asDict()
+ print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'}
+
+ # even though a ParseResults supports dict-like access, sometime you just need to have a dict
+ import json
+ print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable
+ print(json.dumps(result.asDict())) # -> {"month": "31", "day": "1999", "year": "12"}
+ """
+ if PY_3:
+ item_fn = self.items
+ else:
+ item_fn = self.iteritems
+
+ def toItem(obj):
+ if isinstance(obj, ParseResults):
+ if obj.haskeys():
+ return obj.asDict()
+ else:
+ return [toItem(v) for v in obj]
+ else:
+ return obj
+
+ return dict((k,toItem(v)) for k,v in item_fn())
+
+ def copy( self ):
+ """
+ Returns a new copy of a C{ParseResults} object.
+ """
+ ret = ParseResults( self.__toklist )
+ ret.__tokdict = self.__tokdict.copy()
+ ret.__parent = self.__parent
+ ret.__accumNames.update( self.__accumNames )
+ ret.__name = self.__name
+ return ret
+
+ def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ):
+ """
+ (Deprecated) Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.
+ """
+ nl = "\n"
+ out = []
+ namedItems = dict((v[1],k) for (k,vlist) in self.__tokdict.items()
+ for v in vlist)
+ nextLevelIndent = indent + " "
+
+ # collapse out indents if formatting is not desired
+ if not formatted:
+ indent = ""
+ nextLevelIndent = ""
+ nl = ""
+
+ selfTag = None
+ if doctag is not None:
+ selfTag = doctag
+ else:
+ if self.__name:
+ selfTag = self.__name
+
+ if not selfTag:
+ if namedItemsOnly:
+ return ""
+ else:
+ selfTag = "ITEM"
+
+ out += [ nl, indent, "<", selfTag, ">" ]
+
+ for i,res in enumerate(self.__toklist):
+ if isinstance(res,ParseResults):
+ if i in namedItems:
+ out += [ res.asXML(namedItems[i],
+ namedItemsOnly and doctag is None,
+ nextLevelIndent,
+ formatted)]
+ else:
+ out += [ res.asXML(None,
+ namedItemsOnly and doctag is None,
+ nextLevelIndent,
+ formatted)]
+ else:
+ # individual token, see if there is a name for it
+ resTag = None
+ if i in namedItems:
+ resTag = namedItems[i]
+ if not resTag:
+ if namedItemsOnly:
+ continue
+ else:
+ resTag = "ITEM"
+ xmlBodyText = _xml_escape(_ustr(res))
+ out += [ nl, nextLevelIndent, "<", resTag, ">",
+ xmlBodyText,
+ "</", resTag, ">" ]
+
+ out += [ nl, indent, "</", selfTag, ">" ]
+ return "".join(out)
+
+ def __lookup(self,sub):
+ for k,vlist in self.__tokdict.items():
+ for v,loc in vlist:
+ if sub is v:
+ return k
+ return None
+
+ def getName(self):
+ """
+ Returns the results name for this token expression. Useful when several
+ different expressions might match at a particular location.
+
+ Example::
+ integer = Word(nums)
+ ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d")
+ house_number_expr = Suppress('#') + Word(nums, alphanums)
+ user_data = (Group(house_number_expr)("house_number")
+ | Group(ssn_expr)("ssn")
+ | Group(integer)("age"))
+ user_info = OneOrMore(user_data)
+
+ result = user_info.parseString("22 111-22-3333 #221B")
+ for item in result:
+ print(item.getName(), ':', item[0])
+ prints::
+ age : 22
+ ssn : 111-22-3333
+ house_number : 221B
+ """
+ if self.__name:
+ return self.__name
+ elif self.__parent:
+ par = self.__parent()
+ if par:
+ return par.__lookup(self)
+ else:
+ return None
+ elif (len(self) == 1 and
+ len(self.__tokdict) == 1 and
+ next(iter(self.__tokdict.values()))[0][1] in (0,-1)):
+ return next(iter(self.__tokdict.keys()))
+ else:
+ return None
+
+ def dump(self, indent='', depth=0, full=True):
+ """
+ Diagnostic method for listing out the contents of a C{ParseResults}.
+ Accepts an optional C{indent} argument so that this string can be embedded
+ in a nested display of other data.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ result = date_str.parseString('12/31/1999')
+ print(result.dump())
+ prints::
+ ['12', '/', '31', '/', '1999']
+ - day: 1999
+ - month: 31
+ - year: 12
+ """
+ out = []
+ NL = '\n'
+ out.append( indent+_ustr(self.asList()) )
+ if full:
+ if self.haskeys():
+ items = sorted((str(k), v) for k,v in self.items())
+ for k,v in items:
+ if out:
+ out.append(NL)
+ out.append( "%s%s- %s: " % (indent,(' '*depth), k) )
+ if isinstance(v,ParseResults):
+ if v:
+ out.append( v.dump(indent,depth+1) )
+ else:
+ out.append(_ustr(v))
+ else:
+ out.append(repr(v))
+ elif any(isinstance(vv,ParseResults) for vv in self):
+ v = self
+ for i,vv in enumerate(v):
+ if isinstance(vv,ParseResults):
+ out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),vv.dump(indent,depth+1) ))
+ else:
+ out.append("\n%s%s[%d]:\n%s%s%s" % (indent,(' '*(depth)),i,indent,(' '*(depth+1)),_ustr(vv)))
+
+ return "".join(out)
+
+ def pprint(self, *args, **kwargs):
+ """
+ Pretty-printer for parsed results as a list, using the C{pprint} module.
+ Accepts additional positional or keyword args as defined for the
+ C{pprint.pprint} method. (U{http://docs.python.org/3/library/pprint.html#pprint.pprint})
+
+ Example::
+ ident = Word(alphas, alphanums)
+ num = Word(nums)
+ func = Forward()
+ term = ident | num | Group('(' + func + ')')
+ func <<= ident + Group(Optional(delimitedList(term)))
+ result = func.parseString("fna a,b,(fnb c,d,200),100")
+ result.pprint(width=40)
+ prints::
+ ['fna',
+ ['a',
+ 'b',
+ ['(', 'fnb', ['c', 'd', '200'], ')'],
+ '100']]
+ """
+ pprint.pprint(self.asList(), *args, **kwargs)
+
+ # add support for pickle protocol
+ def __getstate__(self):
+ return ( self.__toklist,
+ ( self.__tokdict.copy(),
+ self.__parent is not None and self.__parent() or None,
+ self.__accumNames,
+ self.__name ) )
+
+ def __setstate__(self,state):
+ self.__toklist = state[0]
+ (self.__tokdict,
+ par,
+ inAccumNames,
+ self.__name) = state[1]
+ self.__accumNames = {}
+ self.__accumNames.update(inAccumNames)
+ if par is not None:
+ self.__parent = wkref(par)
+ else:
+ self.__parent = None
+
+ def __getnewargs__(self):
+ return self.__toklist, self.__name, self.__asList, self.__modal
+
+ def __dir__(self):
+ return (dir(type(self)) + list(self.keys()))
+
+collections.MutableMapping.register(ParseResults)
+
+def col (loc,strg):
+ """Returns current column within a string, counting newlines as line separators.
+ The first column is number 1.
+
+ Note: the default parsing behavior is to expand tabs in the input string
+ before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
+ on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
+ consistent view of the parsed string, the parse location, and line and column
+ positions within the parsed string.
+ """
+ s = strg
+ return 1 if 0<loc<len(s) and s[loc-1] == '\n' else loc - s.rfind("\n", 0, loc)
+
+def lineno(loc,strg):
+ """Returns current line number within a string, counting newlines as line separators.
+ The first line is number 1.
+
+ Note: the default parsing behavior is to expand tabs in the input string
+ before starting the parsing process. See L{I{ParserElement.parseString}<ParserElement.parseString>} for more information
+ on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
+ consistent view of the parsed string, the parse location, and line and column
+ positions within the parsed string.
+ """
+ return strg.count("\n",0,loc) + 1
+
+def line( loc, strg ):
+ """Returns the line of text containing loc within a string, counting newlines as line separators.
+ """
+ lastCR = strg.rfind("\n", 0, loc)
+ nextCR = strg.find("\n", loc)
+ if nextCR >= 0:
+ return strg[lastCR+1:nextCR]
+ else:
+ return strg[lastCR+1:]
+
+def _defaultStartDebugAction( instring, loc, expr ):
+ print (("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )))
+
+def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ):
+ print ("Matched " + _ustr(expr) + " -> " + str(toks.asList()))
+
+def _defaultExceptionDebugAction( instring, loc, expr, exc ):
+ print ("Exception raised:" + _ustr(exc))
+
+def nullDebugAction(*args):
+ """'Do-nothing' debug action, to suppress debugging output during parsing."""
+ pass
+
+# Only works on Python 3.x - nonlocal is toxic to Python 2 installs
+#~ 'decorator to trim function calls to match the arity of the target'
+#~ def _trim_arity(func, maxargs=3):
+ #~ if func in singleArgBuiltins:
+ #~ return lambda s,l,t: func(t)
+ #~ limit = 0
+ #~ foundArity = False
+ #~ def wrapper(*args):
+ #~ nonlocal limit,foundArity
+ #~ while 1:
+ #~ try:
+ #~ ret = func(*args[limit:])
+ #~ foundArity = True
+ #~ return ret
+ #~ except TypeError:
+ #~ if limit == maxargs or foundArity:
+ #~ raise
+ #~ limit += 1
+ #~ continue
+ #~ return wrapper
+
+# this version is Python 2.x-3.x cross-compatible
+'decorator to trim function calls to match the arity of the target'
+def _trim_arity(func, maxargs=2):
+ if func in singleArgBuiltins:
+ return lambda s,l,t: func(t)
+ limit = [0]
+ foundArity = [False]
+
+ # traceback return data structure changed in Py3.5 - normalize back to plain tuples
+ if system_version[:2] >= (3,5):
+ def extract_stack(limit=0):
+ # special handling for Python 3.5.0 - extra deep call stack by 1
+ offset = -3 if system_version == (3,5,0) else -2
+ frame_summary = traceback.extract_stack(limit=-offset+limit-1)[offset]
+ return [(frame_summary.filename, frame_summary.lineno)]
+ def extract_tb(tb, limit=0):
+ frames = traceback.extract_tb(tb, limit=limit)
+ frame_summary = frames[-1]
+ return [(frame_summary.filename, frame_summary.lineno)]
+ else:
+ extract_stack = traceback.extract_stack
+ extract_tb = traceback.extract_tb
+
+ # synthesize what would be returned by traceback.extract_stack at the call to
+ # user's parse action 'func', so that we don't incur call penalty at parse time
+
+ LINE_DIFF = 6
+ # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND
+ # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!!
+ this_line = extract_stack(limit=2)[-1]
+ pa_call_line_synth = (this_line[0], this_line[1]+LINE_DIFF)
+
+ def wrapper(*args):
+ while 1:
+ try:
+ ret = func(*args[limit[0]:])
+ foundArity[0] = True
+ return ret
+ except TypeError:
+ # re-raise TypeErrors if they did not come from our arity testing
+ if foundArity[0]:
+ raise
+ else:
+ try:
+ tb = sys.exc_info()[-1]
+ if not extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth:
+ raise
+ finally:
+ del tb
+
+ if limit[0] <= maxargs:
+ limit[0] += 1
+ continue
+ raise
+
+ # copy func name to wrapper for sensible debug output
+ func_name = "<parse action>"
+ try:
+ func_name = getattr(func, '__name__',
+ getattr(func, '__class__').__name__)
+ except Exception:
+ func_name = str(func)
+ wrapper.__name__ = func_name
+
+ return wrapper
+
+class ParserElement(object):
+ """Abstract base level parser element class."""
+ DEFAULT_WHITE_CHARS = " \n\t\r"
+ verbose_stacktrace = False
+
+ @staticmethod
+ def setDefaultWhitespaceChars( chars ):
+ r"""
+ Overrides the default whitespace chars
+
+ Example::
+ # default whitespace chars are space, <TAB> and newline
+ OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl']
+
+ # change to just treat newline as significant
+ ParserElement.setDefaultWhitespaceChars(" \t")
+ OneOrMore(Word(alphas)).parseString("abc def\nghi jkl") # -> ['abc', 'def']
+ """
+ ParserElement.DEFAULT_WHITE_CHARS = chars
+
+ @staticmethod
+ def inlineLiteralsUsing(cls):
+ """
+ Set class to be used for inclusion of string literals into a parser.
+
+ Example::
+ # default literal class used is Literal
+ integer = Word(nums)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
+
+
+ # change to Suppress
+ ParserElement.inlineLiteralsUsing(Suppress)
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+
+ date_str.parseString("1999/12/31") # -> ['1999', '12', '31']
+ """
+ ParserElement._literalStringClass = cls
+
+ def __init__( self, savelist=False ):
+ self.parseAction = list()
+ self.failAction = None
+ #~ self.name = "<unknown>" # don't define self.name, let subclasses try/except upcall
+ self.strRepr = None
+ self.resultsName = None
+ self.saveAsList = savelist
+ self.skipWhitespace = True
+ self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
+ self.copyDefaultWhiteChars = True
+ self.mayReturnEmpty = False # used when checking for left-recursion
+ self.keepTabs = False
+ self.ignoreExprs = list()
+ self.debug = False
+ self.streamlined = False
+ self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index
+ self.errmsg = ""
+ self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all)
+ self.debugActions = ( None, None, None ) #custom debug actions
+ self.re = None
+ self.callPreparse = True # used to avoid redundant calls to preParse
+ self.callDuringTry = False
+
+ def copy( self ):
+ """
+ Make a copy of this C{ParserElement}. Useful for defining different parse actions
+ for the same parsing pattern, using copies of the original parse element.
+
+ Example::
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ integerK = integer.copy().addParseAction(lambda toks: toks[0]*1024) + Suppress("K")
+ integerM = integer.copy().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
+
+ print(OneOrMore(integerK | integerM | integer).parseString("5K 100 640K 256M"))
+ prints::
+ [5120, 100, 655360, 268435456]
+ Equivalent form of C{expr.copy()} is just C{expr()}::
+ integerM = integer().addParseAction(lambda toks: toks[0]*1024*1024) + Suppress("M")
+ """
+ cpy = copy.copy( self )
+ cpy.parseAction = self.parseAction[:]
+ cpy.ignoreExprs = self.ignoreExprs[:]
+ if self.copyDefaultWhiteChars:
+ cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS
+ return cpy
+
+ def setName( self, name ):
+ """
+ Define name for this expression, makes debugging and exception messages clearer.
+
+ Example::
+ Word(nums).parseString("ABC") # -> Exception: Expected W:(0123...) (at char 0), (line:1, col:1)
+ Word(nums).setName("integer").parseString("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1)
+ """
+ self.name = name
+ self.errmsg = "Expected " + self.name
+ if hasattr(self,"exception"):
+ self.exception.msg = self.errmsg
+ return self
+
+ def setResultsName( self, name, listAllMatches=False ):
+ """
+ Define name for referencing matching tokens as a nested attribute
+ of the returned parse results.
+ NOTE: this returns a *copy* of the original C{ParserElement} object;
+ this is so that the client can define a basic element, such as an
+ integer, and reference it in multiple places with different names.
+
+ You can also set results names using the abbreviated syntax,
+ C{expr("name")} in place of C{expr.setResultsName("name")} -
+ see L{I{__call__}<__call__>}.
+
+ Example::
+ date_str = (integer.setResultsName("year") + '/'
+ + integer.setResultsName("month") + '/'
+ + integer.setResultsName("day"))
+
+ # equivalent form:
+ date_str = integer("year") + '/' + integer("month") + '/' + integer("day")
+ """
+ newself = self.copy()
+ if name.endswith("*"):
+ name = name[:-1]
+ listAllMatches=True
+ newself.resultsName = name
+ newself.modalResults = not listAllMatches
+ return newself
+
+ def setBreak(self,breakFlag = True):
+ """Method to invoke the Python pdb debugger when this element is
+ about to be parsed. Set C{breakFlag} to True to enable, False to
+ disable.
+ """
+ if breakFlag:
+ _parseMethod = self._parse
+ def breaker(instring, loc, doActions=True, callPreParse=True):
+ import pdb
+ pdb.set_trace()
+ return _parseMethod( instring, loc, doActions, callPreParse )
+ breaker._originalParseMethod = _parseMethod
+ self._parse = breaker
+ else:
+ if hasattr(self._parse,"_originalParseMethod"):
+ self._parse = self._parse._originalParseMethod
+ return self
+
+ def setParseAction( self, *fns, **kwargs ):
+ """
+ Define action to perform when successfully matching parse element definition.
+ Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)},
+ C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where:
+ - s = the original string being parsed (see note below)
+ - loc = the location of the matching substring
+ - toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object
+ If the functions in fns modify the tokens, they can return them as the return
+ value from fn, and the modified list of tokens will replace the original.
+ Otherwise, fn does not need to return any value.
+
+ Optional keyword arguments:
+ - callDuringTry = (default=C{False}) indicate if parse action should be run during lookaheads and alternate testing
+
+ Note: the default parsing behavior is to expand tabs in the input string
+ before starting the parsing process. See L{I{parseString}<parseString>} for more information
+ on parsing strings containing C{<TAB>}s, and suggested methods to maintain a
+ consistent view of the parsed string, the parse location, and line and column
+ positions within the parsed string.
+
+ Example::
+ integer = Word(nums)
+ date_str = integer + '/' + integer + '/' + integer
+
+ date_str.parseString("1999/12/31") # -> ['1999', '/', '12', '/', '31']
+
+ # use parse action to convert to ints at parse time
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ date_str = integer + '/' + integer + '/' + integer
+
+ # note that integer fields are now ints, not strings
+ date_str.parseString("1999/12/31") # -> [1999, '/', 12, '/', 31]
+ """
+ self.parseAction = list(map(_trim_arity, list(fns)))
+ self.callDuringTry = kwargs.get("callDuringTry", False)
+ return self
+
+ def addParseAction( self, *fns, **kwargs ):
+ """
+ Add parse action to expression's list of parse actions. See L{I{setParseAction}<setParseAction>}.
+
+ See examples in L{I{copy}<copy>}.
+ """
+ self.parseAction += list(map(_trim_arity, list(fns)))
+ self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
+ return self
+
+ def addCondition(self, *fns, **kwargs):
+ """Add a boolean predicate function to expression's list of parse actions. See
+ L{I{setParseAction}<setParseAction>} for function call signatures. Unlike C{setParseAction},
+ functions passed to C{addCondition} need to return boolean success/fail of the condition.
+
+ Optional keyword arguments:
+ - message = define a custom message to be used in the raised exception
+ - fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise ParseException
+
+ Example::
+ integer = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ year_int = integer.copy()
+ year_int.addCondition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later")
+ date_str = year_int + '/' + integer + '/' + integer
+
+ result = date_str.parseString("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), (line:1, col:1)
+ """
+ msg = kwargs.get("message", "failed user-defined condition")
+ exc_type = ParseFatalException if kwargs.get("fatal", False) else ParseException
+ for fn in fns:
+ def pa(s,l,t):
+ if not bool(_trim_arity(fn)(s,l,t)):
+ raise exc_type(s,l,msg)
+ self.parseAction.append(pa)
+ self.callDuringTry = self.callDuringTry or kwargs.get("callDuringTry", False)
+ return self
+
+ def setFailAction( self, fn ):
+ """Define action to perform if parsing fails at this expression.
+ Fail acton fn is a callable function that takes the arguments
+ C{fn(s,loc,expr,err)} where:
+ - s = string being parsed
+ - loc = location where expression match was attempted and failed
+ - expr = the parse expression that failed
+ - err = the exception thrown
+ The function returns no value. It may throw C{L{ParseFatalException}}
+ if it is desired to stop parsing immediately."""
+ self.failAction = fn
+ return self
+
+ def _skipIgnorables( self, instring, loc ):
+ exprsFound = True
+ while exprsFound:
+ exprsFound = False
+ for e in self.ignoreExprs:
+ try:
+ while 1:
+ loc,dummy = e._parse( instring, loc )
+ exprsFound = True
+ except ParseException:
+ pass
+ return loc
+
+ def preParse( self, instring, loc ):
+ if self.ignoreExprs:
+ loc = self._skipIgnorables( instring, loc )
+
+ if self.skipWhitespace:
+ wt = self.whiteChars
+ instrlen = len(instring)
+ while loc < instrlen and instring[loc] in wt:
+ loc += 1
+
+ return loc
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ return loc, []
+
+ def postParse( self, instring, loc, tokenlist ):
+ return tokenlist
+
+ #~ @profile
+ def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ):
+ debugging = ( self.debug ) #and doActions )
+
+ if debugging or self.failAction:
+ #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) ))
+ if (self.debugActions[0] ):
+ self.debugActions[0]( instring, loc, self )
+ if callPreParse and self.callPreparse:
+ preloc = self.preParse( instring, loc )
+ else:
+ preloc = loc
+ tokensStart = preloc
+ try:
+ try:
+ loc,tokens = self.parseImpl( instring, preloc, doActions )
+ except IndexError:
+ raise ParseException( instring, len(instring), self.errmsg, self )
+ except ParseBaseException as err:
+ #~ print ("Exception raised:", err)
+ if self.debugActions[2]:
+ self.debugActions[2]( instring, tokensStart, self, err )
+ if self.failAction:
+ self.failAction( instring, tokensStart, self, err )
+ raise
+ else:
+ if callPreParse and self.callPreparse:
+ preloc = self.preParse( instring, loc )
+ else:
+ preloc = loc
+ tokensStart = preloc
+ if self.mayIndexError or loc >= len(instring):
+ try:
+ loc,tokens = self.parseImpl( instring, preloc, doActions )
+ except IndexError:
+ raise ParseException( instring, len(instring), self.errmsg, self )
+ else:
+ loc,tokens = self.parseImpl( instring, preloc, doActions )
+
+ tokens = self.postParse( instring, loc, tokens )
+
+ retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults )
+ if self.parseAction and (doActions or self.callDuringTry):
+ if debugging:
+ try:
+ for fn in self.parseAction:
+ tokens = fn( instring, tokensStart, retTokens )
+ if tokens is not None:
+ retTokens = ParseResults( tokens,
+ self.resultsName,
+ asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
+ modal=self.modalResults )
+ except ParseBaseException as err:
+ #~ print "Exception raised in user parse action:", err
+ if (self.debugActions[2] ):
+ self.debugActions[2]( instring, tokensStart, self, err )
+ raise
+ else:
+ for fn in self.parseAction:
+ tokens = fn( instring, tokensStart, retTokens )
+ if tokens is not None:
+ retTokens = ParseResults( tokens,
+ self.resultsName,
+ asList=self.saveAsList and isinstance(tokens,(ParseResults,list)),
+ modal=self.modalResults )
+
+ if debugging:
+ #~ print ("Matched",self,"->",retTokens.asList())
+ if (self.debugActions[1] ):
+ self.debugActions[1]( instring, tokensStart, loc, self, retTokens )
+
+ return loc, retTokens
+
+ def tryParse( self, instring, loc ):
+ try:
+ return self._parse( instring, loc, doActions=False )[0]
+ except ParseFatalException:
+ raise ParseException( instring, loc, self.errmsg, self)
+
+ def canParseNext(self, instring, loc):
+ try:
+ self.tryParse(instring, loc)
+ except (ParseException, IndexError):
+ return False
+ else:
+ return True
+
+ class _UnboundedCache(object):
+ def __init__(self):
+ cache = {}
+ self.not_in_cache = not_in_cache = object()
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+
+ def clear(self):
+ cache.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ if _OrderedDict is not None:
+ class _FifoCache(object):
+ def __init__(self, size):
+ self.not_in_cache = not_in_cache = object()
+
+ cache = _OrderedDict()
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+ if len(cache) > size:
+ cache.popitem(False)
+
+ def clear(self):
+ cache.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ else:
+ class _FifoCache(object):
+ def __init__(self, size):
+ self.not_in_cache = not_in_cache = object()
+
+ cache = {}
+ key_fifo = collections.deque([], size)
+
+ def get(self, key):
+ return cache.get(key, not_in_cache)
+
+ def set(self, key, value):
+ cache[key] = value
+ if len(cache) > size:
+ cache.pop(key_fifo.popleft(), None)
+ key_fifo.append(key)
+
+ def clear(self):
+ cache.clear()
+ key_fifo.clear()
+
+ self.get = types.MethodType(get, self)
+ self.set = types.MethodType(set, self)
+ self.clear = types.MethodType(clear, self)
+
+ # argument cache for optimizing repeated calls when backtracking through recursive expressions
+ packrat_cache = {} # this is set later by enabledPackrat(); this is here so that resetCache() doesn't fail
+ packrat_cache_lock = RLock()
+ packrat_cache_stats = [0, 0]
+
+ # this method gets repeatedly called during backtracking with the same arguments -
+ # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression
+ def _parseCache( self, instring, loc, doActions=True, callPreParse=True ):
+ HIT, MISS = 0, 1
+ lookup = (self, instring, loc, callPreParse, doActions)
+ with ParserElement.packrat_cache_lock:
+ cache = ParserElement.packrat_cache
+ value = cache.get(lookup)
+ if value is cache.not_in_cache:
+ ParserElement.packrat_cache_stats[MISS] += 1
+ try:
+ value = self._parseNoCache(instring, loc, doActions, callPreParse)
+ except ParseBaseException as pe:
+ # cache a copy of the exception, without the traceback
+ cache.set(lookup, pe.__class__(*pe.args))
+ raise
+ else:
+ cache.set(lookup, (value[0], value[1].copy()))
+ return value
+ else:
+ ParserElement.packrat_cache_stats[HIT] += 1
+ if isinstance(value, Exception):
+ raise value
+ return (value[0], value[1].copy())
+
+ _parse = _parseNoCache
+
+ @staticmethod
+ def resetCache():
+ ParserElement.packrat_cache.clear()
+ ParserElement.packrat_cache_stats[:] = [0] * len(ParserElement.packrat_cache_stats)
+
+ _packratEnabled = False
+ @staticmethod
+ def enablePackrat(cache_size_limit=128):
+ """Enables "packrat" parsing, which adds memoizing to the parsing logic.
+ Repeated parse attempts at the same string location (which happens
+ often in many complex grammars) can immediately return a cached value,
+ instead of re-executing parsing/validating code. Memoizing is done of
+ both valid results and parsing exceptions.
+
+ Parameters:
+ - cache_size_limit - (default=C{128}) - if an integer value is provided
+ will limit the size of the packrat cache; if None is passed, then
+ the cache size will be unbounded; if 0 is passed, the cache will
+ be effectively disabled.
+
+ This speedup may break existing programs that use parse actions that
+ have side-effects. For this reason, packrat parsing is disabled when
+ you first import pyparsing. To activate the packrat feature, your
+ program must call the class method C{ParserElement.enablePackrat()}. If
+ your program uses C{psyco} to "compile as you go", you must call
+ C{enablePackrat} before calling C{psyco.full()}. If you do not do this,
+ Python will crash. For best results, call C{enablePackrat()} immediately
+ after importing pyparsing.
+
+ Example::
+ import pyparsing
+ pyparsing.ParserElement.enablePackrat()
+ """
+ if not ParserElement._packratEnabled:
+ ParserElement._packratEnabled = True
+ if cache_size_limit is None:
+ ParserElement.packrat_cache = ParserElement._UnboundedCache()
+ else:
+ ParserElement.packrat_cache = ParserElement._FifoCache(cache_size_limit)
+ ParserElement._parse = ParserElement._parseCache
+
+ def parseString( self, instring, parseAll=False ):
+ """
+ Execute the parse expression with the given string.
+ This is the main interface to the client code, once the complete
+ expression has been built.
+
+ If you want the grammar to require that the entire input string be
+ successfully parsed, then set C{parseAll} to True (equivalent to ending
+ the grammar with C{L{StringEnd()}}).
+
+ Note: C{parseString} implicitly calls C{expandtabs()} on the input string,
+ in order to report proper column numbers in parse actions.
+ If the input string contains tabs and
+ the grammar uses parse actions that use the C{loc} argument to index into the
+ string being parsed, you can ensure you have a consistent view of the input
+ string by:
+ - calling C{parseWithTabs} on your grammar before calling C{parseString}
+ (see L{I{parseWithTabs}<parseWithTabs>})
+ - define your parse action using the full C{(s,loc,toks)} signature, and
+ reference the input string using the parse action's C{s} argument
+ - explictly expand the tabs in your input string before calling
+ C{parseString}
+
+ Example::
+ Word('a').parseString('aaaaabaaa') # -> ['aaaaa']
+ Word('a').parseString('aaaaabaaa', parseAll=True) # -> Exception: Expected end of text
+ """
+ ParserElement.resetCache()
+ if not self.streamlined:
+ self.streamline()
+ #~ self.saveAsList = True
+ for e in self.ignoreExprs:
+ e.streamline()
+ if not self.keepTabs:
+ instring = instring.expandtabs()
+ try:
+ loc, tokens = self._parse( instring, 0 )
+ if parseAll:
+ loc = self.preParse( instring, loc )
+ se = Empty() + StringEnd()
+ se._parse( instring, loc )
+ except ParseBaseException as exc:
+ if ParserElement.verbose_stacktrace:
+ raise
+ else:
+ # catch and re-raise exception from here, clears out pyparsing internal stack trace
+ raise exc
+ else:
+ return tokens
+
+ def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ):
+ """
+ Scan the input string for expression matches. Each match will return the
+ matching tokens, start location, and end location. May be called with optional
+ C{maxMatches} argument, to clip scanning after 'n' matches are found. If
+ C{overlap} is specified, then overlapping matches will be reported.
+
+ Note that the start and end locations are reported relative to the string
+ being parsed. See L{I{parseString}<parseString>} for more information on parsing
+ strings with embedded tabs.
+
+ Example::
+ source = "sldjf123lsdjjkf345sldkjf879lkjsfd987"
+ print(source)
+ for tokens,start,end in Word(alphas).scanString(source):
+ print(' '*start + '^'*(end-start))
+ print(' '*start + tokens[0])
+
+ prints::
+
+ sldjf123lsdjjkf345sldkjf879lkjsfd987
+ ^^^^^
+ sldjf
+ ^^^^^^^
+ lsdjjkf
+ ^^^^^^
+ sldkjf
+ ^^^^^^
+ lkjsfd
+ """
+ if not self.streamlined:
+ self.streamline()
+ for e in self.ignoreExprs:
+ e.streamline()
+
+ if not self.keepTabs:
+ instring = _ustr(instring).expandtabs()
+ instrlen = len(instring)
+ loc = 0
+ preparseFn = self.preParse
+ parseFn = self._parse
+ ParserElement.resetCache()
+ matches = 0
+ try:
+ while loc <= instrlen and matches < maxMatches:
+ try:
+ preloc = preparseFn( instring, loc )
+ nextLoc,tokens = parseFn( instring, preloc, callPreParse=False )
+ except ParseException:
+ loc = preloc+1
+ else:
+ if nextLoc > loc:
+ matches += 1
+ yield tokens, preloc, nextLoc
+ if overlap:
+ nextloc = preparseFn( instring, loc )
+ if nextloc > loc:
+ loc = nextLoc
+ else:
+ loc += 1
+ else:
+ loc = nextLoc
+ else:
+ loc = preloc+1
+ except ParseBaseException as exc:
+ if ParserElement.verbose_stacktrace:
+ raise
+ else:
+ # catch and re-raise exception from here, clears out pyparsing internal stack trace
+ raise exc
+
+ def transformString( self, instring ):
+ """
+ Extension to C{L{scanString}}, to modify matching text with modified tokens that may
+ be returned from a parse action. To use C{transformString}, define a grammar and
+ attach a parse action to it that modifies the returned token list.
+ Invoking C{transformString()} on a target string will then scan for matches,
+ and replace the matched text patterns according to the logic in the parse
+ action. C{transformString()} returns the resulting transformed string.
+
+ Example::
+ wd = Word(alphas)
+ wd.setParseAction(lambda toks: toks[0].title())
+
+ print(wd.transformString("now is the winter of our discontent made glorious summer by this sun of york."))
+ Prints::
+ Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York.
+ """
+ out = []
+ lastE = 0
+ # force preservation of <TAB>s, to minimize unwanted transformation of string, and to
+ # keep string locs straight between transformString and scanString
+ self.keepTabs = True
+ try:
+ for t,s,e in self.scanString( instring ):
+ out.append( instring[lastE:s] )
+ if t:
+ if isinstance(t,ParseResults):
+ out += t.asList()
+ elif isinstance(t,list):
+ out += t
+ else:
+ out.append(t)
+ lastE = e
+ out.append(instring[lastE:])
+ out = [o for o in out if o]
+ return "".join(map(_ustr,_flatten(out)))
+ except ParseBaseException as exc:
+ if ParserElement.verbose_stacktrace:
+ raise
+ else:
+ # catch and re-raise exception from here, clears out pyparsing internal stack trace
+ raise exc
+
+ def searchString( self, instring, maxMatches=_MAX_INT ):
+ """
+ Another extension to C{L{scanString}}, simplifying the access to the tokens found
+ to match the given parse expression. May be called with optional
+ C{maxMatches} argument, to clip searching after 'n' matches are found.
+
+ Example::
+ # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters
+ cap_word = Word(alphas.upper(), alphas.lower())
+
+ print(cap_word.searchString("More than Iron, more than Lead, more than Gold I need Electricity"))
+ prints::
+ ['More', 'Iron', 'Lead', 'Gold', 'I']
+ """
+ try:
+ return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ])
+ except ParseBaseException as exc:
+ if ParserElement.verbose_stacktrace:
+ raise
+ else:
+ # catch and re-raise exception from here, clears out pyparsing internal stack trace
+ raise exc
+
+ def split(self, instring, maxsplit=_MAX_INT, includeSeparators=False):
+ """
+ Generator method to split a string using the given expression as a separator.
+ May be called with optional C{maxsplit} argument, to limit the number of splits;
+ and the optional C{includeSeparators} argument (default=C{False}), if the separating
+ matching text should be included in the split results.
+
+ Example::
+ punc = oneOf(list(".,;:/-!?"))
+ print(list(punc.split("This, this?, this sentence, is badly punctuated!")))
+ prints::
+ ['This', ' this', '', ' this sentence', ' is badly punctuated', '']
+ """
+ splits = 0
+ last = 0
+ for t,s,e in self.scanString(instring, maxMatches=maxsplit):
+ yield instring[last:s]
+ if includeSeparators:
+ yield t[0]
+ last = e
+ yield instring[last:]
+
+ def __add__(self, other ):
+ """
+ Implementation of + operator - returns C{L{And}}. Adding strings to a ParserElement
+ converts them to L{Literal}s by default.
+
+ Example::
+ greet = Word(alphas) + "," + Word(alphas) + "!"
+ hello = "Hello, World!"
+ print (hello, "->", greet.parseString(hello))
+ Prints::
+ Hello, World! -> ['Hello', ',', 'World', '!']
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return And( [ self, other ] )
+
+ def __radd__(self, other ):
+ """
+ Implementation of + operator when left operand is not a C{L{ParserElement}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return other + self
+
+ def __sub__(self, other):
+ """
+ Implementation of - operator, returns C{L{And}} with error stop
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return And( [ self, And._ErrorStop(), other ] )
+
+ def __rsub__(self, other ):
+ """
+ Implementation of - operator when left operand is not a C{L{ParserElement}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return other - self
+
+ def __mul__(self,other):
+ """
+ Implementation of * operator, allows use of C{expr * 3} in place of
+ C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer
+ tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples
+ may also include C{None} as in:
+ - C{expr*(n,None)} or C{expr*(n,)} is equivalent
+ to C{expr*n + L{ZeroOrMore}(expr)}
+ (read as "at least n instances of C{expr}")
+ - C{expr*(None,n)} is equivalent to C{expr*(0,n)}
+ (read as "0 to n instances of C{expr}")
+ - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)}
+ - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)}
+
+ Note that C{expr*(None,n)} does not raise an exception if
+ more than n exprs exist in the input stream; that is,
+ C{expr*(None,n)} does not enforce a maximum number of expr
+ occurrences. If this behavior is desired, then write
+ C{expr*(None,n) + ~expr}
+ """
+ if isinstance(other,int):
+ minElements, optElements = other,0
+ elif isinstance(other,tuple):
+ other = (other + (None, None))[:2]
+ if other[0] is None:
+ other = (0, other[1])
+ if isinstance(other[0],int) and other[1] is None:
+ if other[0] == 0:
+ return ZeroOrMore(self)
+ if other[0] == 1:
+ return OneOrMore(self)
+ else:
+ return self*other[0] + ZeroOrMore(self)
+ elif isinstance(other[0],int) and isinstance(other[1],int):
+ minElements, optElements = other
+ optElements -= minElements
+ else:
+ raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1]))
+ else:
+ raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other))
+
+ if minElements < 0:
+ raise ValueError("cannot multiply ParserElement by negative value")
+ if optElements < 0:
+ raise ValueError("second tuple value must be greater or equal to first tuple value")
+ if minElements == optElements == 0:
+ raise ValueError("cannot multiply ParserElement by 0 or (0,0)")
+
+ if (optElements):
+ def makeOptionalList(n):
+ if n>1:
+ return Optional(self + makeOptionalList(n-1))
+ else:
+ return Optional(self)
+ if minElements:
+ if minElements == 1:
+ ret = self + makeOptionalList(optElements)
+ else:
+ ret = And([self]*minElements) + makeOptionalList(optElements)
+ else:
+ ret = makeOptionalList(optElements)
+ else:
+ if minElements == 1:
+ ret = self
+ else:
+ ret = And([self]*minElements)
+ return ret
+
+ def __rmul__(self, other):
+ return self.__mul__(other)
+
+ def __or__(self, other ):
+ """
+ Implementation of | operator - returns C{L{MatchFirst}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return MatchFirst( [ self, other ] )
+
+ def __ror__(self, other ):
+ """
+ Implementation of | operator when left operand is not a C{L{ParserElement}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return other | self
+
+ def __xor__(self, other ):
+ """
+ Implementation of ^ operator - returns C{L{Or}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return Or( [ self, other ] )
+
+ def __rxor__(self, other ):
+ """
+ Implementation of ^ operator when left operand is not a C{L{ParserElement}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return other ^ self
+
+ def __and__(self, other ):
+ """
+ Implementation of & operator - returns C{L{Each}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return Each( [ self, other ] )
+
+ def __rand__(self, other ):
+ """
+ Implementation of & operator when left operand is not a C{L{ParserElement}}
+ """
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ if not isinstance( other, ParserElement ):
+ warnings.warn("Cannot combine element of type %s with ParserElement" % type(other),
+ SyntaxWarning, stacklevel=2)
+ return None
+ return other & self
+
+ def __invert__( self ):
+ """
+ Implementation of ~ operator - returns C{L{NotAny}}
+ """
+ return NotAny( self )
+
+ def __call__(self, name=None):
+ """
+ Shortcut for C{L{setResultsName}}, with C{listAllMatches=False}.
+
+ If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be
+ passed as C{True}.
+
+ If C{name} is omitted, same as calling C{L{copy}}.
+
+ Example::
+ # these are equivalent
+ userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno")
+ userdata = Word(alphas)("name") + Word(nums+"-")("socsecno")
+ """
+ if name is not None:
+ return self.setResultsName(name)
+ else:
+ return self.copy()
+
+ def suppress( self ):
+ """
+ Suppresses the output of this C{ParserElement}; useful to keep punctuation from
+ cluttering up returned output.
+ """
+ return Suppress( self )
+
+ def leaveWhitespace( self ):
+ """
+ Disables the skipping of whitespace before matching the characters in the
+ C{ParserElement}'s defined pattern. This is normally only used internally by
+ the pyparsing module, but may be needed in some whitespace-sensitive grammars.
+ """
+ self.skipWhitespace = False
+ return self
+
+ def setWhitespaceChars( self, chars ):
+ """
+ Overrides the default whitespace chars
+ """
+ self.skipWhitespace = True
+ self.whiteChars = chars
+ self.copyDefaultWhiteChars = False
+ return self
+
+ def parseWithTabs( self ):
+ """
+ Overrides default behavior to expand C{<TAB>}s to spaces before parsing the input string.
+ Must be called before C{parseString} when the input grammar contains elements that
+ match C{<TAB>} characters.
+ """
+ self.keepTabs = True
+ return self
+
+ def ignore( self, other ):
+ """
+ Define expression to be ignored (e.g., comments) while doing pattern
+ matching; may be called repeatedly, to define multiple comment or other
+ ignorable patterns.
+
+ Example::
+ patt = OneOrMore(Word(alphas))
+ patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj']
+
+ patt.ignore(cStyleComment)
+ patt.parseString('ablaj /* comment */ lskjd') # -> ['ablaj', 'lskjd']
+ """
+ if isinstance(other, basestring):
+ other = Suppress(other)
+
+ if isinstance( other, Suppress ):
+ if other not in self.ignoreExprs:
+ self.ignoreExprs.append(other)
+ else:
+ self.ignoreExprs.append( Suppress( other.copy() ) )
+ return self
+
+ def setDebugActions( self, startAction, successAction, exceptionAction ):
+ """
+ Enable display of debugging messages while doing pattern matching.
+ """
+ self.debugActions = (startAction or _defaultStartDebugAction,
+ successAction or _defaultSuccessDebugAction,
+ exceptionAction or _defaultExceptionDebugAction)
+ self.debug = True
+ return self
+
+ def setDebug( self, flag=True ):
+ """
+ Enable display of debugging messages while doing pattern matching.
+ Set C{flag} to True to enable, False to disable.
+
+ Example::
+ wd = Word(alphas).setName("alphaword")
+ integer = Word(nums).setName("numword")
+ term = wd | integer
+
+ # turn on debugging for wd
+ wd.setDebug()
+
+ OneOrMore(term).parseString("abc 123 xyz 890")
+
+ prints::
+ Match alphaword at loc 0(1,1)
+ Matched alphaword -> ['abc']
+ Match alphaword at loc 3(1,4)
+ Exception raised:Expected alphaword (at char 4), (line:1, col:5)
+ Match alphaword at loc 7(1,8)
+ Matched alphaword -> ['xyz']
+ Match alphaword at loc 11(1,12)
+ Exception raised:Expected alphaword (at char 12), (line:1, col:13)
+ Match alphaword at loc 15(1,16)
+ Exception raised:Expected alphaword (at char 15), (line:1, col:16)
+
+ The output shown is that produced by the default debug actions - custom debug actions can be
+ specified using L{setDebugActions}. Prior to attempting
+ to match the C{wd} expression, the debugging message C{"Match <exprname> at loc <n>(<line>,<col>)"}
+ is shown. Then if the parse succeeds, a C{"Matched"} message is shown, or an C{"Exception raised"}
+ message is shown. Also note the use of L{setName} to assign a human-readable name to the expression,
+ which makes debugging and exception messages easier to understand - for instance, the default
+ name created for the C{Word} expression without calling C{setName} is C{"W:(ABCD...)"}.
+ """
+ if flag:
+ self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction )
+ else:
+ self.debug = False
+ return self
+
+ def __str__( self ):
+ return self.name
+
+ def __repr__( self ):
+ return _ustr(self)
+
+ def streamline( self ):
+ self.streamlined = True
+ self.strRepr = None
+ return self
+
+ def checkRecursion( self, parseElementList ):
+ pass
+
+ def validate( self, validateTrace=[] ):
+ """
+ Check defined expressions for valid structure, check for infinite recursive definitions.
+ """
+ self.checkRecursion( [] )
+
+ def parseFile( self, file_or_filename, parseAll=False ):
+ """
+ Execute the parse expression on the given file or filename.
+ If a filename is specified (instead of a file object),
+ the entire file is opened, read, and closed before parsing.
+ """
+ try:
+ file_contents = file_or_filename.read()
+ except AttributeError:
+ with open(file_or_filename, "r") as f:
+ file_contents = f.read()
+ try:
+ return self.parseString(file_contents, parseAll)
+ except ParseBaseException as exc:
+ if ParserElement.verbose_stacktrace:
+ raise
+ else:
+ # catch and re-raise exception from here, clears out pyparsing internal stack trace
+ raise exc
+
+ def __eq__(self,other):
+ if isinstance(other, ParserElement):
+ return self is other or vars(self) == vars(other)
+ elif isinstance(other, basestring):
+ return self.matches(other)
+ else:
+ return super(ParserElement,self)==other
+
+ def __ne__(self,other):
+ return not (self == other)
+
+ def __hash__(self):
+ return hash(id(self))
+
+ def __req__(self,other):
+ return self == other
+
+ def __rne__(self,other):
+ return not (self == other)
+
+ def matches(self, testString, parseAll=True):
+ """
+ Method for quick testing of a parser against a test string. Good for simple
+ inline microtests of sub expressions while building up larger parser.
+
+ Parameters:
+ - testString - to test against this expression for a match
+ - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
+
+ Example::
+ expr = Word(nums)
+ assert expr.matches("100")
+ """
+ try:
+ self.parseString(_ustr(testString), parseAll=parseAll)
+ return True
+ except ParseBaseException:
+ return False
+
+ def runTests(self, tests, parseAll=True, comment='#', fullDump=True, printResults=True, failureTests=False):
+ """
+ Execute the parse expression on a series of test strings, showing each
+ test, the parsed results or where the parse failed. Quick and easy way to
+ run a parse expression against a list of sample strings.
+
+ Parameters:
+ - tests - a list of separate test strings, or a multiline string of test strings
+ - parseAll - (default=C{True}) - flag to pass to C{L{parseString}} when running tests
+ - comment - (default=C{'#'}) - expression for indicating embedded comments in the test
+ string; pass None to disable comment filtering
+ - fullDump - (default=C{True}) - dump results as list followed by results names in nested outline;
+ if False, only dump nested list
+ - printResults - (default=C{True}) prints test output to stdout
+ - failureTests - (default=C{False}) indicates if these tests are expected to fail parsing
+
+ Returns: a (success, results) tuple, where success indicates that all tests succeeded
+ (or failed if C{failureTests} is True), and the results contain a list of lines of each
+ test's output
+
+ Example::
+ number_expr = pyparsing_common.number.copy()
+
+ result = number_expr.runTests('''
+ # unsigned integer
+ 100
+ # negative integer
+ -100
+ # float with scientific notation
+ 6.02e23
+ # integer with scientific notation
+ 1e-12
+ ''')
+ print("Success" if result[0] else "Failed!")
+
+ result = number_expr.runTests('''
+ # stray character
+ 100Z
+ # missing leading digit before '.'
+ -.100
+ # too many '.'
+ 3.14.159
+ ''', failureTests=True)
+ print("Success" if result[0] else "Failed!")
+ prints::
+ # unsigned integer
+ 100
+ [100]
+
+ # negative integer
+ -100
+ [-100]
+
+ # float with scientific notation
+ 6.02e23
+ [6.02e+23]
+
+ # integer with scientific notation
+ 1e-12
+ [1e-12]
+
+ Success
+
+ # stray character
+ 100Z
+ ^
+ FAIL: Expected end of text (at char 3), (line:1, col:4)
+
+ # missing leading digit before '.'
+ -.100
+ ^
+ FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1)
+
+ # too many '.'
+ 3.14.159
+ ^
+ FAIL: Expected end of text (at char 4), (line:1, col:5)
+
+ Success
+
+ Each test string must be on a single line. If you want to test a string that spans multiple
+ lines, create a test like this::
+
+ expr.runTest(r"this is a test\\n of strings that spans \\n 3 lines")
+
+ (Note that this is a raw string literal, you must include the leading 'r'.)
+ """
+ if isinstance(tests, basestring):
+ tests = list(map(str.strip, tests.rstrip().splitlines()))
+ if isinstance(comment, basestring):
+ comment = Literal(comment)
+ allResults = []
+ comments = []
+ success = True
+ for t in tests:
+ if comment is not None and comment.matches(t, False) or comments and not t:
+ comments.append(t)
+ continue
+ if not t:
+ continue
+ out = ['\n'.join(comments), t]
+ comments = []
+ try:
+ t = t.replace(r'\n','\n')
+ result = self.parseString(t, parseAll=parseAll)
+ out.append(result.dump(full=fullDump))
+ success = success and not failureTests
+ except ParseBaseException as pe:
+ fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else ""
+ if '\n' in t:
+ out.append(line(pe.loc, t))
+ out.append(' '*(col(pe.loc,t)-1) + '^' + fatal)
+ else:
+ out.append(' '*pe.loc + '^' + fatal)
+ out.append("FAIL: " + str(pe))
+ success = success and failureTests
+ result = pe
+ except Exception as exc:
+ out.append("FAIL-EXCEPTION: " + str(exc))
+ success = success and failureTests
+ result = exc
+
+ if printResults:
+ if fullDump:
+ out.append('')
+ print('\n'.join(out))
+
+ allResults.append((t, result))
+
+ return success, allResults
+
+
+class Token(ParserElement):
+ """
+ Abstract C{ParserElement} subclass, for defining atomic matching patterns.
+ """
+ def __init__( self ):
+ super(Token,self).__init__( savelist=False )
+
+
+class Empty(Token):
+ """
+ An empty token, will always match.
+ """
+ def __init__( self ):
+ super(Empty,self).__init__()
+ self.name = "Empty"
+ self.mayReturnEmpty = True
+ self.mayIndexError = False
+
+
+class NoMatch(Token):
+ """
+ A token that will never match.
+ """
+ def __init__( self ):
+ super(NoMatch,self).__init__()
+ self.name = "NoMatch"
+ self.mayReturnEmpty = True
+ self.mayIndexError = False
+ self.errmsg = "Unmatchable token"
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ raise ParseException(instring, loc, self.errmsg, self)
+
+
+class Literal(Token):
+ """
+ Token to exactly match a specified string.
+
+ Example::
+ Literal('blah').parseString('blah') # -> ['blah']
+ Literal('blah').parseString('blahfooblah') # -> ['blah']
+ Literal('blah').parseString('bla') # -> Exception: Expected "blah"
+
+ For case-insensitive matching, use L{CaselessLiteral}.
+
+ For keyword matching (force word break before and after the matched string),
+ use L{Keyword} or L{CaselessKeyword}.
+ """
+ def __init__( self, matchString ):
+ super(Literal,self).__init__()
+ self.match = matchString
+ self.matchLen = len(matchString)
+ try:
+ self.firstMatchChar = matchString[0]
+ except IndexError:
+ warnings.warn("null string passed to Literal; use Empty() instead",
+ SyntaxWarning, stacklevel=2)
+ self.__class__ = Empty
+ self.name = '"%s"' % _ustr(self.match)
+ self.errmsg = "Expected " + self.name
+ self.mayReturnEmpty = False
+ self.mayIndexError = False
+
+ # Performance tuning: this routine gets called a *lot*
+ # if this is a single character match string and the first character matches,
+ # short-circuit as quickly as possible, and avoid calling startswith
+ #~ @profile
+ def parseImpl( self, instring, loc, doActions=True ):
+ if (instring[loc] == self.firstMatchChar and
+ (self.matchLen==1 or instring.startswith(self.match,loc)) ):
+ return loc+self.matchLen, self.match
+ raise ParseException(instring, loc, self.errmsg, self)
+_L = Literal
+ParserElement._literalStringClass = Literal
+
+class Keyword(Token):
+ """
+ Token to exactly match a specified string as a keyword, that is, it must be
+ immediately followed by a non-keyword character. Compare with C{L{Literal}}:
+ - C{Literal("if")} will match the leading C{'if'} in C{'ifAndOnlyIf'}.
+ - C{Keyword("if")} will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'}
+ Accepts two optional constructor arguments in addition to the keyword string:
+ - C{identChars} is a string of characters that would be valid identifier characters,
+ defaulting to all alphanumerics + "_" and "$"
+ - C{caseless} allows case-insensitive matching, default is C{False}.
+
+ Example::
+ Keyword("start").parseString("start") # -> ['start']
+ Keyword("start").parseString("starting") # -> Exception
+
+ For case-insensitive matching, use L{CaselessKeyword}.
+ """
+ DEFAULT_KEYWORD_CHARS = alphanums+"_$"
+
+ def __init__( self, matchString, identChars=None, caseless=False ):
+ super(Keyword,self).__init__()
+ if identChars is None:
+ identChars = Keyword.DEFAULT_KEYWORD_CHARS
+ self.match = matchString
+ self.matchLen = len(matchString)
+ try:
+ self.firstMatchChar = matchString[0]
+ except IndexError:
+ warnings.warn("null string passed to Keyword; use Empty() instead",
+ SyntaxWarning, stacklevel=2)
+ self.name = '"%s"' % self.match
+ self.errmsg = "Expected " + self.name
+ self.mayReturnEmpty = False
+ self.mayIndexError = False
+ self.caseless = caseless
+ if caseless:
+ self.caselessmatch = matchString.upper()
+ identChars = identChars.upper()
+ self.identChars = set(identChars)
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if self.caseless:
+ if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
+ (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and
+ (loc == 0 or instring[loc-1].upper() not in self.identChars) ):
+ return loc+self.matchLen, self.match
+ else:
+ if (instring[loc] == self.firstMatchChar and
+ (self.matchLen==1 or instring.startswith(self.match,loc)) and
+ (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and
+ (loc == 0 or instring[loc-1] not in self.identChars) ):
+ return loc+self.matchLen, self.match
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ def copy(self):
+ c = super(Keyword,self).copy()
+ c.identChars = Keyword.DEFAULT_KEYWORD_CHARS
+ return c
+
+ @staticmethod
+ def setDefaultKeywordChars( chars ):
+ """Overrides the default Keyword chars
+ """
+ Keyword.DEFAULT_KEYWORD_CHARS = chars
+
+class CaselessLiteral(Literal):
+ """
+ Token to match a specified string, ignoring case of letters.
+ Note: the matched results will always be in the case of the given
+ match string, NOT the case of the input text.
+
+ Example::
+ OneOrMore(CaselessLiteral("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD', 'CMD']
+
+ (Contrast with example for L{CaselessKeyword}.)
+ """
+ def __init__( self, matchString ):
+ super(CaselessLiteral,self).__init__( matchString.upper() )
+ # Preserve the defining literal.
+ self.returnString = matchString
+ self.name = "'%s'" % self.returnString
+ self.errmsg = "Expected " + self.name
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if instring[ loc:loc+self.matchLen ].upper() == self.match:
+ return loc+self.matchLen, self.returnString
+ raise ParseException(instring, loc, self.errmsg, self)
+
+class CaselessKeyword(Keyword):
+ """
+ Caseless version of L{Keyword}.
+
+ Example::
+ OneOrMore(CaselessKeyword("CMD")).parseString("cmd CMD Cmd10") # -> ['CMD', 'CMD']
+
+ (Contrast with example for L{CaselessLiteral}.)
+ """
+ def __init__( self, matchString, identChars=None ):
+ super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True )
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and
+ (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ):
+ return loc+self.matchLen, self.match
+ raise ParseException(instring, loc, self.errmsg, self)
+
+class CloseMatch(Token):
+ """
+ A variation on L{Literal} which matches "close" matches, that is,
+ strings with at most 'n' mismatching characters. C{CloseMatch} takes parameters:
+ - C{match_string} - string to be matched
+ - C{maxMismatches} - (C{default=1}) maximum number of mismatches allowed to count as a match
+
+ The results from a successful parse will contain the matched text from the input string and the following named results:
+ - C{mismatches} - a list of the positions within the match_string where mismatches were found
+ - C{original} - the original match_string used to compare against the input string
+
+ If C{mismatches} is an empty list, then the match was an exact match.
+
+ Example::
+ patt = CloseMatch("ATCATCGAATGGA")
+ patt.parseString("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']})
+ patt.parseString("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1)
+
+ # exact match
+ patt.parseString("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']})
+
+ # close match allowing up to 2 mismatches
+ patt = CloseMatch("ATCATCGAATGGA", maxMismatches=2)
+ patt.parseString("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']})
+ """
+ def __init__(self, match_string, maxMismatches=1):
+ super(CloseMatch,self).__init__()
+ self.name = match_string
+ self.match_string = match_string
+ self.maxMismatches = maxMismatches
+ self.errmsg = "Expected %r (with up to %d mismatches)" % (self.match_string, self.maxMismatches)
+ self.mayIndexError = False
+ self.mayReturnEmpty = False
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ start = loc
+ instrlen = len(instring)
+ maxloc = start + len(self.match_string)
+
+ if maxloc <= instrlen:
+ match_string = self.match_string
+ match_stringloc = 0
+ mismatches = []
+ maxMismatches = self.maxMismatches
+
+ for match_stringloc,s_m in enumerate(zip(instring[loc:maxloc], self.match_string)):
+ src,mat = s_m
+ if src != mat:
+ mismatches.append(match_stringloc)
+ if len(mismatches) > maxMismatches:
+ break
+ else:
+ loc = match_stringloc + 1
+ results = ParseResults([instring[start:loc]])
+ results['original'] = self.match_string
+ results['mismatches'] = mismatches
+ return loc, results
+
+ raise ParseException(instring, loc, self.errmsg, self)
+
+
+class Word(Token):
+ """
+ Token for matching words composed of allowed character sets.
+ Defined with string containing all allowed initial characters,
+ an optional string containing allowed body characters (if omitted,
+ defaults to the initial character set), and an optional minimum,
+ maximum, and/or exact length. The default value for C{min} is 1 (a
+ minimum value < 1 is not valid); the default values for C{max} and C{exact}
+ are 0, meaning no maximum or exact length restriction. An optional
+ C{excludeChars} parameter can list characters that might be found in
+ the input C{bodyChars} string; useful to define a word of all printables
+ except for one or two characters, for instance.
+
+ L{srange} is useful for defining custom character set strings for defining
+ C{Word} expressions, using range notation from regular expression character sets.
+
+ A common mistake is to use C{Word} to match a specific literal string, as in
+ C{Word("Address")}. Remember that C{Word} uses the string argument to define
+ I{sets} of matchable characters. This expression would match "Add", "AAA",
+ "dAred", or any other word made up of the characters 'A', 'd', 'r', 'e', and 's'.
+ To match an exact literal string, use L{Literal} or L{Keyword}.
+
+ pyparsing includes helper strings for building Words:
+ - L{alphas}
+ - L{nums}
+ - L{alphanums}
+ - L{hexnums}
+ - L{alphas8bit} (alphabetic characters in ASCII range 128-255 - accented, tilded, umlauted, etc.)
+ - L{punc8bit} (non-alphabetic characters in ASCII range 128-255 - currency, symbols, superscripts, diacriticals, etc.)
+ - L{printables} (any non-whitespace character)
+
+ Example::
+ # a word composed of digits
+ integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9"))
+
+ # a word with a leading capital, and zero or more lowercase
+ capital_word = Word(alphas.upper(), alphas.lower())
+
+ # hostnames are alphanumeric, with leading alpha, and '-'
+ hostname = Word(alphas, alphanums+'-')
+
+ # roman numeral (not a strict parser, accepts invalid mix of characters)
+ roman = Word("IVXLCDM")
+
+ # any string of non-whitespace characters, except for ','
+ csv_value = Word(printables, excludeChars=",")
+ """
+ def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ):
+ super(Word,self).__init__()
+ if excludeChars:
+ initChars = ''.join(c for c in initChars if c not in excludeChars)
+ if bodyChars:
+ bodyChars = ''.join(c for c in bodyChars if c not in excludeChars)
+ self.initCharsOrig = initChars
+ self.initChars = set(initChars)
+ if bodyChars :
+ self.bodyCharsOrig = bodyChars
+ self.bodyChars = set(bodyChars)
+ else:
+ self.bodyCharsOrig = initChars
+ self.bodyChars = set(initChars)
+
+ self.maxSpecified = max > 0
+
+ if min < 1:
+ raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted")
+
+ self.minLen = min
+
+ if max > 0:
+ self.maxLen = max
+ else:
+ self.maxLen = _MAX_INT
+
+ if exact > 0:
+ self.maxLen = exact
+ self.minLen = exact
+
+ self.name = _ustr(self)
+ self.errmsg = "Expected " + self.name
+ self.mayIndexError = False
+ self.asKeyword = asKeyword
+
+ if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0):
+ if self.bodyCharsOrig == self.initCharsOrig:
+ self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig)
+ elif len(self.initCharsOrig) == 1:
+ self.reString = "%s[%s]*" % \
+ (re.escape(self.initCharsOrig),
+ _escapeRegexRangeChars(self.bodyCharsOrig),)
+ else:
+ self.reString = "[%s][%s]*" % \
+ (_escapeRegexRangeChars(self.initCharsOrig),
+ _escapeRegexRangeChars(self.bodyCharsOrig),)
+ if self.asKeyword:
+ self.reString = r"\b"+self.reString+r"\b"
+ try:
+ self.re = re.compile( self.reString )
+ except Exception:
+ self.re = None
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if self.re:
+ result = self.re.match(instring,loc)
+ if not result:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ loc = result.end()
+ return loc, result.group()
+
+ if not(instring[ loc ] in self.initChars):
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ start = loc
+ loc += 1
+ instrlen = len(instring)
+ bodychars = self.bodyChars
+ maxloc = start + self.maxLen
+ maxloc = min( maxloc, instrlen )
+ while loc < maxloc and instring[loc] in bodychars:
+ loc += 1
+
+ throwException = False
+ if loc - start < self.minLen:
+ throwException = True
+ if self.maxSpecified and loc < instrlen and instring[loc] in bodychars:
+ throwException = True
+ if self.asKeyword:
+ if (start>0 and instring[start-1] in bodychars) or (loc<instrlen and instring[loc] in bodychars):
+ throwException = True
+
+ if throwException:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ return loc, instring[start:loc]
+
+ def __str__( self ):
+ try:
+ return super(Word,self).__str__()
+ except Exception:
+ pass
+
+
+ if self.strRepr is None:
+
+ def charsAsStr(s):
+ if len(s)>4:
+ return s[:4]+"..."
+ else:
+ return s
+
+ if ( self.initCharsOrig != self.bodyCharsOrig ):
+ self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) )
+ else:
+ self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig)
+
+ return self.strRepr
+
+
+class Regex(Token):
+ """
+ Token for matching strings that match a given regular expression.
+ Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module.
+ If the given regex contains named groups (defined using C{(?P<name>...)}), these will be preserved as
+ named parse results.
+
+ Example::
+ realnum = Regex(r"[+-]?\d+\.\d*")
+ date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)')
+ # ref: http://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression
+ roman = Regex(r"M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})")
+ """
+ compiledREtype = type(re.compile("[A-Z]"))
+ def __init__( self, pattern, flags=0):
+ """The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags."""
+ super(Regex,self).__init__()
+
+ if isinstance(pattern, basestring):
+ if not pattern:
+ warnings.warn("null string passed to Regex; use Empty() instead",
+ SyntaxWarning, stacklevel=2)
+
+ self.pattern = pattern
+ self.flags = flags
+
+ try:
+ self.re = re.compile(self.pattern, self.flags)
+ self.reString = self.pattern
+ except sre_constants.error:
+ warnings.warn("invalid pattern (%s) passed to Regex" % pattern,
+ SyntaxWarning, stacklevel=2)
+ raise
+
+ elif isinstance(pattern, Regex.compiledREtype):
+ self.re = pattern
+ self.pattern = \
+ self.reString = str(pattern)
+ self.flags = flags
+
+ else:
+ raise ValueError("Regex may only be constructed with a string or a compiled RE object")
+
+ self.name = _ustr(self)
+ self.errmsg = "Expected " + self.name
+ self.mayIndexError = False
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ result = self.re.match(instring,loc)
+ if not result:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ loc = result.end()
+ d = result.groupdict()
+ ret = ParseResults(result.group())
+ if d:
+ for k in d:
+ ret[k] = d[k]
+ return loc,ret
+
+ def __str__( self ):
+ try:
+ return super(Regex,self).__str__()
+ except Exception:
+ pass
+
+ if self.strRepr is None:
+ self.strRepr = "Re:(%s)" % repr(self.pattern)
+
+ return self.strRepr
+
+
+class QuotedString(Token):
+ r"""
+ Token for matching strings that are delimited by quoting characters.
+
+ Defined with the following parameters:
+ - quoteChar - string of one or more characters defining the quote delimiting string
+ - escChar - character to escape quotes, typically backslash (default=C{None})
+ - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=C{None})
+ - multiline - boolean indicating whether quotes can span multiple lines (default=C{False})
+ - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True})
+ - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar)
+ - convertWhitespaceEscapes - convert escaped whitespace (C{'\t'}, C{'\n'}, etc.) to actual whitespace (default=C{True})
+
+ Example::
+ qs = QuotedString('"')
+ print(qs.searchString('lsjdf "This is the quote" sldjf'))
+ complex_qs = QuotedString('{{', endQuoteChar='}}')
+ print(complex_qs.searchString('lsjdf {{This is the "quote"}} sldjf'))
+ sql_qs = QuotedString('"', escQuote='""')
+ print(sql_qs.searchString('lsjdf "This is the quote with ""embedded"" quotes" sldjf'))
+ prints::
+ [['This is the quote']]
+ [['This is the "quote"']]
+ [['This is the quote with "embedded" quotes']]
+ """
+ def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None, convertWhitespaceEscapes=True):
+ super(QuotedString,self).__init__()
+
+ # remove white space from quote chars - wont work anyway
+ quoteChar = quoteChar.strip()
+ if not quoteChar:
+ warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
+ raise SyntaxError()
+
+ if endQuoteChar is None:
+ endQuoteChar = quoteChar
+ else:
+ endQuoteChar = endQuoteChar.strip()
+ if not endQuoteChar:
+ warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2)
+ raise SyntaxError()
+
+ self.quoteChar = quoteChar
+ self.quoteCharLen = len(quoteChar)
+ self.firstQuoteChar = quoteChar[0]
+ self.endQuoteChar = endQuoteChar
+ self.endQuoteCharLen = len(endQuoteChar)
+ self.escChar = escChar
+ self.escQuote = escQuote
+ self.unquoteResults = unquoteResults
+ self.convertWhitespaceEscapes = convertWhitespaceEscapes
+
+ if multiline:
+ self.flags = re.MULTILINE | re.DOTALL
+ self.pattern = r'%s(?:[^%s%s]' % \
+ ( re.escape(self.quoteChar),
+ _escapeRegexRangeChars(self.endQuoteChar[0]),
+ (escChar is not None and _escapeRegexRangeChars(escChar) or '') )
+ else:
+ self.flags = 0
+ self.pattern = r'%s(?:[^%s\n\r%s]' % \
+ ( re.escape(self.quoteChar),
+ _escapeRegexRangeChars(self.endQuoteChar[0]),
+ (escChar is not None and _escapeRegexRangeChars(escChar) or '') )
+ if len(self.endQuoteChar) > 1:
+ self.pattern += (
+ '|(?:' + ')|(?:'.join("%s[^%s]" % (re.escape(self.endQuoteChar[:i]),
+ _escapeRegexRangeChars(self.endQuoteChar[i]))
+ for i in range(len(self.endQuoteChar)-1,0,-1)) + ')'
+ )
+ if escQuote:
+ self.pattern += (r'|(?:%s)' % re.escape(escQuote))
+ if escChar:
+ self.pattern += (r'|(?:%s.)' % re.escape(escChar))
+ self.escCharReplacePattern = re.escape(self.escChar)+"(.)"
+ self.pattern += (r')*%s' % re.escape(self.endQuoteChar))
+
+ try:
+ self.re = re.compile(self.pattern, self.flags)
+ self.reString = self.pattern
+ except sre_constants.error:
+ warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern,
+ SyntaxWarning, stacklevel=2)
+ raise
+
+ self.name = _ustr(self)
+ self.errmsg = "Expected " + self.name
+ self.mayIndexError = False
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None
+ if not result:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ loc = result.end()
+ ret = result.group()
+
+ if self.unquoteResults:
+
+ # strip off quotes
+ ret = ret[self.quoteCharLen:-self.endQuoteCharLen]
+
+ if isinstance(ret,basestring):
+ # replace escaped whitespace
+ if '\\' in ret and self.convertWhitespaceEscapes:
+ ws_map = {
+ r'\t' : '\t',
+ r'\n' : '\n',
+ r'\f' : '\f',
+ r'\r' : '\r',
+ }
+ for wslit,wschar in ws_map.items():
+ ret = ret.replace(wslit, wschar)
+
+ # replace escaped characters
+ if self.escChar:
+ ret = re.sub(self.escCharReplacePattern,"\g<1>",ret)
+
+ # replace escaped quotes
+ if self.escQuote:
+ ret = ret.replace(self.escQuote, self.endQuoteChar)
+
+ return loc, ret
+
+ def __str__( self ):
+ try:
+ return super(QuotedString,self).__str__()
+ except Exception:
+ pass
+
+ if self.strRepr is None:
+ self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar)
+
+ return self.strRepr
+
+
+class CharsNotIn(Token):
+ """
+ Token for matching words composed of characters I{not} in a given set (will
+ include whitespace in matched characters if not listed in the provided exclusion set - see example).
+ Defined with string containing all disallowed characters, and an optional
+ minimum, maximum, and/or exact length. The default value for C{min} is 1 (a
+ minimum value < 1 is not valid); the default values for C{max} and C{exact}
+ are 0, meaning no maximum or exact length restriction.
+
+ Example::
+ # define a comma-separated-value as anything that is not a ','
+ csv_value = CharsNotIn(',')
+ print(delimitedList(csv_value).parseString("dkls,lsdkjf,s12 34,@!#,213"))
+ prints::
+ ['dkls', 'lsdkjf', 's12 34', '@!#', '213']
+ """
+ def __init__( self, notChars, min=1, max=0, exact=0 ):
+ super(CharsNotIn,self).__init__()
+ self.skipWhitespace = False
+ self.notChars = notChars
+
+ if min < 1:
+ raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted")
+
+ self.minLen = min
+
+ if max > 0:
+ self.maxLen = max
+ else:
+ self.maxLen = _MAX_INT
+
+ if exact > 0:
+ self.maxLen = exact
+ self.minLen = exact
+
+ self.name = _ustr(self)
+ self.errmsg = "Expected " + self.name
+ self.mayReturnEmpty = ( self.minLen == 0 )
+ self.mayIndexError = False
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if instring[loc] in self.notChars:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ start = loc
+ loc += 1
+ notchars = self.notChars
+ maxlen = min( start+self.maxLen, len(instring) )
+ while loc < maxlen and \
+ (instring[loc] not in notchars):
+ loc += 1
+
+ if loc - start < self.minLen:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ return loc, instring[start:loc]
+
+ def __str__( self ):
+ try:
+ return super(CharsNotIn, self).__str__()
+ except Exception:
+ pass
+
+ if self.strRepr is None:
+ if len(self.notChars) > 4:
+ self.strRepr = "!W:(%s...)" % self.notChars[:4]
+ else:
+ self.strRepr = "!W:(%s)" % self.notChars
+
+ return self.strRepr
+
+class White(Token):
+ """
+ Special matching class for matching whitespace. Normally, whitespace is ignored
+ by pyparsing grammars. This class is included when some whitespace structures
+ are significant. Define with a string containing the whitespace characters to be
+ matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments,
+ as defined for the C{L{Word}} class.
+ """
+ whiteStrs = {
+ " " : "<SPC>",
+ "\t": "<TAB>",
+ "\n": "<LF>",
+ "\r": "<CR>",
+ "\f": "<FF>",
+ }
+ def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0):
+ super(White,self).__init__()
+ self.matchWhite = ws
+ self.setWhitespaceChars( "".join(c for c in self.whiteChars if c not in self.matchWhite) )
+ #~ self.leaveWhitespace()
+ self.name = ("".join(White.whiteStrs[c] for c in self.matchWhite))
+ self.mayReturnEmpty = True
+ self.errmsg = "Expected " + self.name
+
+ self.minLen = min
+
+ if max > 0:
+ self.maxLen = max
+ else:
+ self.maxLen = _MAX_INT
+
+ if exact > 0:
+ self.maxLen = exact
+ self.minLen = exact
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if not(instring[ loc ] in self.matchWhite):
+ raise ParseException(instring, loc, self.errmsg, self)
+ start = loc
+ loc += 1
+ maxloc = start + self.maxLen
+ maxloc = min( maxloc, len(instring) )
+ while loc < maxloc and instring[loc] in self.matchWhite:
+ loc += 1
+
+ if loc - start < self.minLen:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ return loc, instring[start:loc]
+
+
+class _PositionToken(Token):
+ def __init__( self ):
+ super(_PositionToken,self).__init__()
+ self.name=self.__class__.__name__
+ self.mayReturnEmpty = True
+ self.mayIndexError = False
+
+class GoToColumn(_PositionToken):
+ """
+ Token to advance to a specific column of input text; useful for tabular report scraping.
+ """
+ def __init__( self, colno ):
+ super(GoToColumn,self).__init__()
+ self.col = colno
+
+ def preParse( self, instring, loc ):
+ if col(loc,instring) != self.col:
+ instrlen = len(instring)
+ if self.ignoreExprs:
+ loc = self._skipIgnorables( instring, loc )
+ while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col :
+ loc += 1
+ return loc
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ thiscol = col( loc, instring )
+ if thiscol > self.col:
+ raise ParseException( instring, loc, "Text not in expected column", self )
+ newloc = loc + self.col - thiscol
+ ret = instring[ loc: newloc ]
+ return newloc, ret
+
+
+class LineStart(_PositionToken):
+ """
+ Matches if current position is at the beginning of a line within the parse string
+
+ Example::
+
+ test = '''\
+ AAA this line
+ AAA and this line
+ AAA but not this one
+ B AAA and definitely not this one
+ '''
+
+ for t in (LineStart() + 'AAA' + restOfLine).searchString(test):
+ print(t)
+
+ Prints::
+ ['AAA', ' this line']
+ ['AAA', ' and this line']
+
+ """
+ def __init__( self ):
+ super(LineStart,self).__init__()
+ self.errmsg = "Expected start of line"
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if col(loc, instring) == 1:
+ return loc, []
+ raise ParseException(instring, loc, self.errmsg, self)
+
+class LineEnd(_PositionToken):
+ """
+ Matches if current position is at the end of a line within the parse string
+ """
+ def __init__( self ):
+ super(LineEnd,self).__init__()
+ self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") )
+ self.errmsg = "Expected end of line"
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if loc<len(instring):
+ if instring[loc] == "\n":
+ return loc+1, "\n"
+ else:
+ raise ParseException(instring, loc, self.errmsg, self)
+ elif loc == len(instring):
+ return loc+1, []
+ else:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+class StringStart(_PositionToken):
+ """
+ Matches if current position is at the beginning of the parse string
+ """
+ def __init__( self ):
+ super(StringStart,self).__init__()
+ self.errmsg = "Expected start of text"
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if loc != 0:
+ # see if entire string up to here is just whitespace and ignoreables
+ if loc != self.preParse( instring, 0 ):
+ raise ParseException(instring, loc, self.errmsg, self)
+ return loc, []
+
+class StringEnd(_PositionToken):
+ """
+ Matches if current position is at the end of the parse string
+ """
+ def __init__( self ):
+ super(StringEnd,self).__init__()
+ self.errmsg = "Expected end of text"
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if loc < len(instring):
+ raise ParseException(instring, loc, self.errmsg, self)
+ elif loc == len(instring):
+ return loc+1, []
+ elif loc > len(instring):
+ return loc, []
+ else:
+ raise ParseException(instring, loc, self.errmsg, self)
+
+class WordStart(_PositionToken):
+ """
+ Matches if the current position is at the beginning of a Word, and
+ is not preceded by any character in a given set of C{wordChars}
+ (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
+ use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of
+ the string being parsed, or at the beginning of a line.
+ """
+ def __init__(self, wordChars = printables):
+ super(WordStart,self).__init__()
+ self.wordChars = set(wordChars)
+ self.errmsg = "Not at the start of a word"
+
+ def parseImpl(self, instring, loc, doActions=True ):
+ if loc != 0:
+ if (instring[loc-1] in self.wordChars or
+ instring[loc] not in self.wordChars):
+ raise ParseException(instring, loc, self.errmsg, self)
+ return loc, []
+
+class WordEnd(_PositionToken):
+ """
+ Matches if the current position is at the end of a Word, and
+ is not followed by any character in a given set of C{wordChars}
+ (default=C{printables}). To emulate the C{\b} behavior of regular expressions,
+ use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of
+ the string being parsed, or at the end of a line.
+ """
+ def __init__(self, wordChars = printables):
+ super(WordEnd,self).__init__()
+ self.wordChars = set(wordChars)
+ self.skipWhitespace = False
+ self.errmsg = "Not at the end of a word"
+
+ def parseImpl(self, instring, loc, doActions=True ):
+ instrlen = len(instring)
+ if instrlen>0 and loc<instrlen:
+ if (instring[loc] in self.wordChars or
+ instring[loc-1] not in self.wordChars):
+ raise ParseException(instring, loc, self.errmsg, self)
+ return loc, []
+
+
+class ParseExpression(ParserElement):
+ """
+ Abstract subclass of ParserElement, for combining and post-processing parsed tokens.
+ """
+ def __init__( self, exprs, savelist = False ):
+ super(ParseExpression,self).__init__(savelist)
+ if isinstance( exprs, _generatorType ):
+ exprs = list(exprs)
+
+ if isinstance( exprs, basestring ):
+ self.exprs = [ ParserElement._literalStringClass( exprs ) ]
+ elif isinstance( exprs, collections.Iterable ):
+ exprs = list(exprs)
+ # if sequence of strings provided, wrap with Literal
+ if all(isinstance(expr, basestring) for expr in exprs):
+ exprs = map(ParserElement._literalStringClass, exprs)
+ self.exprs = list(exprs)
+ else:
+ try:
+ self.exprs = list( exprs )
+ except TypeError:
+ self.exprs = [ exprs ]
+ self.callPreparse = False
+
+ def __getitem__( self, i ):
+ return self.exprs[i]
+
+ def append( self, other ):
+ self.exprs.append( other )
+ self.strRepr = None
+ return self
+
+ def leaveWhitespace( self ):
+ """Extends C{leaveWhitespace} defined in base class, and also invokes C{leaveWhitespace} on
+ all contained expressions."""
+ self.skipWhitespace = False
+ self.exprs = [ e.copy() for e in self.exprs ]
+ for e in self.exprs:
+ e.leaveWhitespace()
+ return self
+
+ def ignore( self, other ):
+ if isinstance( other, Suppress ):
+ if other not in self.ignoreExprs:
+ super( ParseExpression, self).ignore( other )
+ for e in self.exprs:
+ e.ignore( self.ignoreExprs[-1] )
+ else:
+ super( ParseExpression, self).ignore( other )
+ for e in self.exprs:
+ e.ignore( self.ignoreExprs[-1] )
+ return self
+
+ def __str__( self ):
+ try:
+ return super(ParseExpression,self).__str__()
+ except Exception:
+ pass
+
+ if self.strRepr is None:
+ self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.exprs) )
+ return self.strRepr
+
+ def streamline( self ):
+ super(ParseExpression,self).streamline()
+
+ for e in self.exprs:
+ e.streamline()
+
+ # collapse nested And's of the form And( And( And( a,b), c), d) to And( a,b,c,d )
+ # but only if there are no parse actions or resultsNames on the nested And's
+ # (likewise for Or's and MatchFirst's)
+ if ( len(self.exprs) == 2 ):
+ other = self.exprs[0]
+ if ( isinstance( other, self.__class__ ) and
+ not(other.parseAction) and
+ other.resultsName is None and
+ not other.debug ):
+ self.exprs = other.exprs[:] + [ self.exprs[1] ]
+ self.strRepr = None
+ self.mayReturnEmpty |= other.mayReturnEmpty
+ self.mayIndexError |= other.mayIndexError
+
+ other = self.exprs[-1]
+ if ( isinstance( other, self.__class__ ) and
+ not(other.parseAction) and
+ other.resultsName is None and
+ not other.debug ):
+ self.exprs = self.exprs[:-1] + other.exprs[:]
+ self.strRepr = None
+ self.mayReturnEmpty |= other.mayReturnEmpty
+ self.mayIndexError |= other.mayIndexError
+
+ self.errmsg = "Expected " + _ustr(self)
+
+ return self
+
+ def setResultsName( self, name, listAllMatches=False ):
+ ret = super(ParseExpression,self).setResultsName(name,listAllMatches)
+ return ret
+
+ def validate( self, validateTrace=[] ):
+ tmp = validateTrace[:]+[self]
+ for e in self.exprs:
+ e.validate(tmp)
+ self.checkRecursion( [] )
+
+ def copy(self):
+ ret = super(ParseExpression,self).copy()
+ ret.exprs = [e.copy() for e in self.exprs]
+ return ret
+
+class And(ParseExpression):
+ """
+ Requires all given C{ParseExpression}s to be found in the given order.
+ Expressions may be separated by whitespace.
+ May be constructed using the C{'+'} operator.
+ May also be constructed using the C{'-'} operator, which will suppress backtracking.
+
+ Example::
+ integer = Word(nums)
+ name_expr = OneOrMore(Word(alphas))
+
+ expr = And([integer("id"),name_expr("name"),integer("age")])
+ # more easily written as:
+ expr = integer("id") + name_expr("name") + integer("age")
+ """
+
+ class _ErrorStop(Empty):
+ def __init__(self, *args, **kwargs):
+ super(And._ErrorStop,self).__init__(*args, **kwargs)
+ self.name = '-'
+ self.leaveWhitespace()
+
+ def __init__( self, exprs, savelist = True ):
+ super(And,self).__init__(exprs, savelist)
+ self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
+ self.setWhitespaceChars( self.exprs[0].whiteChars )
+ self.skipWhitespace = self.exprs[0].skipWhitespace
+ self.callPreparse = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ # pass False as last arg to _parse for first element, since we already
+ # pre-parsed the string as part of our And pre-parsing
+ loc, resultlist = self.exprs[0]._parse( instring, loc, doActions, callPreParse=False )
+ errorStop = False
+ for e in self.exprs[1:]:
+ if isinstance(e, And._ErrorStop):
+ errorStop = True
+ continue
+ if errorStop:
+ try:
+ loc, exprtokens = e._parse( instring, loc, doActions )
+ except ParseSyntaxException:
+ raise
+ except ParseBaseException as pe:
+ pe.__traceback__ = None
+ raise ParseSyntaxException._from_exception(pe)
+ except IndexError:
+ raise ParseSyntaxException(instring, len(instring), self.errmsg, self)
+ else:
+ loc, exprtokens = e._parse( instring, loc, doActions )
+ if exprtokens or exprtokens.haskeys():
+ resultlist += exprtokens
+ return loc, resultlist
+
+ def __iadd__(self, other ):
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ return self.append( other ) #And( [ self, other ] )
+
+ def checkRecursion( self, parseElementList ):
+ subRecCheckList = parseElementList[:] + [ self ]
+ for e in self.exprs:
+ e.checkRecursion( subRecCheckList )
+ if not e.mayReturnEmpty:
+ break
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "{" + " ".join(_ustr(e) for e in self.exprs) + "}"
+
+ return self.strRepr
+
+
+class Or(ParseExpression):
+ """
+ Requires that at least one C{ParseExpression} is found.
+ If two expressions match, the expression that matches the longest string will be used.
+ May be constructed using the C{'^'} operator.
+
+ Example::
+ # construct Or using '^' operator
+
+ number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums))
+ print(number.searchString("123 3.1416 789"))
+ prints::
+ [['123'], ['3.1416'], ['789']]
+ """
+ def __init__( self, exprs, savelist = False ):
+ super(Or,self).__init__(exprs, savelist)
+ if self.exprs:
+ self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
+ else:
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ maxExcLoc = -1
+ maxException = None
+ matches = []
+ for e in self.exprs:
+ try:
+ loc2 = e.tryParse( instring, loc )
+ except ParseException as err:
+ err.__traceback__ = None
+ if err.loc > maxExcLoc:
+ maxException = err
+ maxExcLoc = err.loc
+ except IndexError:
+ if len(instring) > maxExcLoc:
+ maxException = ParseException(instring,len(instring),e.errmsg,self)
+ maxExcLoc = len(instring)
+ else:
+ # save match among all matches, to retry longest to shortest
+ matches.append((loc2, e))
+
+ if matches:
+ matches.sort(key=lambda x: -x[0])
+ for _,e in matches:
+ try:
+ return e._parse( instring, loc, doActions )
+ except ParseException as err:
+ err.__traceback__ = None
+ if err.loc > maxExcLoc:
+ maxException = err
+ maxExcLoc = err.loc
+
+ if maxException is not None:
+ maxException.msg = self.errmsg
+ raise maxException
+ else:
+ raise ParseException(instring, loc, "no defined alternatives to match", self)
+
+
+ def __ixor__(self, other ):
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ return self.append( other ) #Or( [ self, other ] )
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "{" + " ^ ".join(_ustr(e) for e in self.exprs) + "}"
+
+ return self.strRepr
+
+ def checkRecursion( self, parseElementList ):
+ subRecCheckList = parseElementList[:] + [ self ]
+ for e in self.exprs:
+ e.checkRecursion( subRecCheckList )
+
+
+class MatchFirst(ParseExpression):
+ """
+ Requires that at least one C{ParseExpression} is found.
+ If two expressions match, the first one listed is the one that will match.
+ May be constructed using the C{'|'} operator.
+
+ Example::
+ # construct MatchFirst using '|' operator
+
+ # watch the order of expressions to match
+ number = Word(nums) | Combine(Word(nums) + '.' + Word(nums))
+ print(number.searchString("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']]
+
+ # put more selective expression first
+ number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums)
+ print(number.searchString("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']]
+ """
+ def __init__( self, exprs, savelist = False ):
+ super(MatchFirst,self).__init__(exprs, savelist)
+ if self.exprs:
+ self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs)
+ else:
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ maxExcLoc = -1
+ maxException = None
+ for e in self.exprs:
+ try:
+ ret = e._parse( instring, loc, doActions )
+ return ret
+ except ParseException as err:
+ if err.loc > maxExcLoc:
+ maxException = err
+ maxExcLoc = err.loc
+ except IndexError:
+ if len(instring) > maxExcLoc:
+ maxException = ParseException(instring,len(instring),e.errmsg,self)
+ maxExcLoc = len(instring)
+
+ # only got here if no expression matched, raise exception for match that made it the furthest
+ else:
+ if maxException is not None:
+ maxException.msg = self.errmsg
+ raise maxException
+ else:
+ raise ParseException(instring, loc, "no defined alternatives to match", self)
+
+ def __ior__(self, other ):
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass( other )
+ return self.append( other ) #MatchFirst( [ self, other ] )
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "{" + " | ".join(_ustr(e) for e in self.exprs) + "}"
+
+ return self.strRepr
+
+ def checkRecursion( self, parseElementList ):
+ subRecCheckList = parseElementList[:] + [ self ]
+ for e in self.exprs:
+ e.checkRecursion( subRecCheckList )
+
+
+class Each(ParseExpression):
+ """
+ Requires all given C{ParseExpression}s to be found, but in any order.
+ Expressions may be separated by whitespace.
+ May be constructed using the C{'&'} operator.
+
+ Example::
+ color = oneOf("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN")
+ shape_type = oneOf("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON")
+ integer = Word(nums)
+ shape_attr = "shape:" + shape_type("shape")
+ posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn")
+ color_attr = "color:" + color("color")
+ size_attr = "size:" + integer("size")
+
+ # use Each (using operator '&') to accept attributes in any order
+ # (shape and posn are required, color and size are optional)
+ shape_spec = shape_attr & posn_attr & Optional(color_attr) & Optional(size_attr)
+
+ shape_spec.runTests('''
+ shape: SQUARE color: BLACK posn: 100, 120
+ shape: CIRCLE size: 50 color: BLUE posn: 50,80
+ color:GREEN size:20 shape:TRIANGLE posn:20,40
+ '''
+ )
+ prints::
+ shape: SQUARE color: BLACK posn: 100, 120
+ ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']]
+ - color: BLACK
+ - posn: ['100', ',', '120']
+ - x: 100
+ - y: 120
+ - shape: SQUARE
+
+
+ shape: CIRCLE size: 50 color: BLUE posn: 50,80
+ ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']]
+ - color: BLUE
+ - posn: ['50', ',', '80']
+ - x: 50
+ - y: 80
+ - shape: CIRCLE
+ - size: 50
+
+
+ color: GREEN size: 20 shape: TRIANGLE posn: 20,40
+ ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']]
+ - color: GREEN
+ - posn: ['20', ',', '40']
+ - x: 20
+ - y: 40
+ - shape: TRIANGLE
+ - size: 20
+ """
+ def __init__( self, exprs, savelist = True ):
+ super(Each,self).__init__(exprs, savelist)
+ self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs)
+ self.skipWhitespace = True
+ self.initExprGroups = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if self.initExprGroups:
+ self.opt1map = dict((id(e.expr),e) for e in self.exprs if isinstance(e,Optional))
+ opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ]
+ opt2 = [ e for e in self.exprs if e.mayReturnEmpty and not isinstance(e,Optional)]
+ self.optionals = opt1 + opt2
+ self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ]
+ self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ]
+ self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ]
+ self.required += self.multirequired
+ self.initExprGroups = False
+ tmpLoc = loc
+ tmpReqd = self.required[:]
+ tmpOpt = self.optionals[:]
+ matchOrder = []
+
+ keepMatching = True
+ while keepMatching:
+ tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired
+ failed = []
+ for e in tmpExprs:
+ try:
+ tmpLoc = e.tryParse( instring, tmpLoc )
+ except ParseException:
+ failed.append(e)
+ else:
+ matchOrder.append(self.opt1map.get(id(e),e))
+ if e in tmpReqd:
+ tmpReqd.remove(e)
+ elif e in tmpOpt:
+ tmpOpt.remove(e)
+ if len(failed) == len(tmpExprs):
+ keepMatching = False
+
+ if tmpReqd:
+ missing = ", ".join(_ustr(e) for e in tmpReqd)
+ raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing )
+
+ # add any unmatched Optionals, in case they have default values defined
+ matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt]
+
+ resultlist = []
+ for e in matchOrder:
+ loc,results = e._parse(instring,loc,doActions)
+ resultlist.append(results)
+
+ finalResults = sum(resultlist, ParseResults([]))
+ return loc, finalResults
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "{" + " & ".join(_ustr(e) for e in self.exprs) + "}"
+
+ return self.strRepr
+
+ def checkRecursion( self, parseElementList ):
+ subRecCheckList = parseElementList[:] + [ self ]
+ for e in self.exprs:
+ e.checkRecursion( subRecCheckList )
+
+
+class ParseElementEnhance(ParserElement):
+ """
+ Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.
+ """
+ def __init__( self, expr, savelist=False ):
+ super(ParseElementEnhance,self).__init__(savelist)
+ if isinstance( expr, basestring ):
+ if issubclass(ParserElement._literalStringClass, Token):
+ expr = ParserElement._literalStringClass(expr)
+ else:
+ expr = ParserElement._literalStringClass(Literal(expr))
+ self.expr = expr
+ self.strRepr = None
+ if expr is not None:
+ self.mayIndexError = expr.mayIndexError
+ self.mayReturnEmpty = expr.mayReturnEmpty
+ self.setWhitespaceChars( expr.whiteChars )
+ self.skipWhitespace = expr.skipWhitespace
+ self.saveAsList = expr.saveAsList
+ self.callPreparse = expr.callPreparse
+ self.ignoreExprs.extend(expr.ignoreExprs)
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if self.expr is not None:
+ return self.expr._parse( instring, loc, doActions, callPreParse=False )
+ else:
+ raise ParseException("",loc,self.errmsg,self)
+
+ def leaveWhitespace( self ):
+ self.skipWhitespace = False
+ self.expr = self.expr.copy()
+ if self.expr is not None:
+ self.expr.leaveWhitespace()
+ return self
+
+ def ignore( self, other ):
+ if isinstance( other, Suppress ):
+ if other not in self.ignoreExprs:
+ super( ParseElementEnhance, self).ignore( other )
+ if self.expr is not None:
+ self.expr.ignore( self.ignoreExprs[-1] )
+ else:
+ super( ParseElementEnhance, self).ignore( other )
+ if self.expr is not None:
+ self.expr.ignore( self.ignoreExprs[-1] )
+ return self
+
+ def streamline( self ):
+ super(ParseElementEnhance,self).streamline()
+ if self.expr is not None:
+ self.expr.streamline()
+ return self
+
+ def checkRecursion( self, parseElementList ):
+ if self in parseElementList:
+ raise RecursiveGrammarException( parseElementList+[self] )
+ subRecCheckList = parseElementList[:] + [ self ]
+ if self.expr is not None:
+ self.expr.checkRecursion( subRecCheckList )
+
+ def validate( self, validateTrace=[] ):
+ tmp = validateTrace[:]+[self]
+ if self.expr is not None:
+ self.expr.validate(tmp)
+ self.checkRecursion( [] )
+
+ def __str__( self ):
+ try:
+ return super(ParseElementEnhance,self).__str__()
+ except Exception:
+ pass
+
+ if self.strRepr is None and self.expr is not None:
+ self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) )
+ return self.strRepr
+
+
+class FollowedBy(ParseElementEnhance):
+ """
+ Lookahead matching of the given parse expression. C{FollowedBy}
+ does I{not} advance the parsing position within the input string, it only
+ verifies that the specified parse expression matches at the current
+ position. C{FollowedBy} always returns a null token list.
+
+ Example::
+ # use FollowedBy to match a label only if it is followed by a ':'
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+
+ OneOrMore(attr_expr).parseString("shape: SQUARE color: BLACK posn: upper left").pprint()
+ prints::
+ [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']]
+ """
+ def __init__( self, expr ):
+ super(FollowedBy,self).__init__(expr)
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ self.expr.tryParse( instring, loc )
+ return loc, []
+
+
+class NotAny(ParseElementEnhance):
+ """
+ Lookahead to disallow matching with the given parse expression. C{NotAny}
+ does I{not} advance the parsing position within the input string, it only
+ verifies that the specified parse expression does I{not} match at the current
+ position. Also, C{NotAny} does I{not} skip over leading whitespace. C{NotAny}
+ always returns a null token list. May be constructed using the '~' operator.
+
+ Example::
+
+ """
+ def __init__( self, expr ):
+ super(NotAny,self).__init__(expr)
+ #~ self.leaveWhitespace()
+ self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs
+ self.mayReturnEmpty = True
+ self.errmsg = "Found unwanted token, "+_ustr(self.expr)
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ if self.expr.canParseNext(instring, loc):
+ raise ParseException(instring, loc, self.errmsg, self)
+ return loc, []
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "~{" + _ustr(self.expr) + "}"
+
+ return self.strRepr
+
+class _MultipleMatch(ParseElementEnhance):
+ def __init__( self, expr, stopOn=None):
+ super(_MultipleMatch, self).__init__(expr)
+ self.saveAsList = True
+ ender = stopOn
+ if isinstance(ender, basestring):
+ ender = ParserElement._literalStringClass(ender)
+ self.not_ender = ~ender if ender is not None else None
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ self_expr_parse = self.expr._parse
+ self_skip_ignorables = self._skipIgnorables
+ check_ender = self.not_ender is not None
+ if check_ender:
+ try_not_ender = self.not_ender.tryParse
+
+ # must be at least one (but first see if we are the stopOn sentinel;
+ # if so, fail)
+ if check_ender:
+ try_not_ender(instring, loc)
+ loc, tokens = self_expr_parse( instring, loc, doActions, callPreParse=False )
+ try:
+ hasIgnoreExprs = (not not self.ignoreExprs)
+ while 1:
+ if check_ender:
+ try_not_ender(instring, loc)
+ if hasIgnoreExprs:
+ preloc = self_skip_ignorables( instring, loc )
+ else:
+ preloc = loc
+ loc, tmptokens = self_expr_parse( instring, preloc, doActions )
+ if tmptokens or tmptokens.haskeys():
+ tokens += tmptokens
+ except (ParseException,IndexError):
+ pass
+
+ return loc, tokens
+
+class OneOrMore(_MultipleMatch):
+ """
+ Repetition of one or more of the given expression.
+
+ Parameters:
+ - expr - expression that must match one or more times
+ - stopOn - (default=C{None}) - expression for a terminating sentinel
+ (only required if the sentinel would ordinarily match the repetition
+ expression)
+
+ Example::
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
+
+ text = "shape: SQUARE posn: upper left color: BLACK"
+ OneOrMore(attr_expr).parseString(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']]
+
+ # use stopOn attribute for OneOrMore to avoid reading label string as part of the data
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+ OneOrMore(attr_expr).parseString(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']]
+
+ # could also be written as
+ (attr_expr * (1,)).parseString(text).pprint()
+ """
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "{" + _ustr(self.expr) + "}..."
+
+ return self.strRepr
+
+class ZeroOrMore(_MultipleMatch):
+ """
+ Optional repetition of zero or more of the given expression.
+
+ Parameters:
+ - expr - expression that must match zero or more times
+ - stopOn - (default=C{None}) - expression for a terminating sentinel
+ (only required if the sentinel would ordinarily match the repetition
+ expression)
+
+ Example: similar to L{OneOrMore}
+ """
+ def __init__( self, expr, stopOn=None):
+ super(ZeroOrMore,self).__init__(expr, stopOn=stopOn)
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ try:
+ return super(ZeroOrMore, self).parseImpl(instring, loc, doActions)
+ except (ParseException,IndexError):
+ return loc, []
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "[" + _ustr(self.expr) + "]..."
+
+ return self.strRepr
+
+class _NullToken(object):
+ def __bool__(self):
+ return False
+ __nonzero__ = __bool__
+ def __str__(self):
+ return ""
+
+_optionalNotMatched = _NullToken()
+class Optional(ParseElementEnhance):
+ """
+ Optional matching of the given expression.
+
+ Parameters:
+ - expr - expression that must match zero or more times
+ - default (optional) - value to be returned if the optional expression is not found.
+
+ Example::
+ # US postal code can be a 5-digit zip, plus optional 4-digit qualifier
+ zip = Combine(Word(nums, exact=5) + Optional('-' + Word(nums, exact=4)))
+ zip.runTests('''
+ # traditional ZIP code
+ 12345
+
+ # ZIP+4 form
+ 12101-0001
+
+ # invalid ZIP
+ 98765-
+ ''')
+ prints::
+ # traditional ZIP code
+ 12345
+ ['12345']
+
+ # ZIP+4 form
+ 12101-0001
+ ['12101-0001']
+
+ # invalid ZIP
+ 98765-
+ ^
+ FAIL: Expected end of text (at char 5), (line:1, col:6)
+ """
+ def __init__( self, expr, default=_optionalNotMatched ):
+ super(Optional,self).__init__( expr, savelist=False )
+ self.saveAsList = self.expr.saveAsList
+ self.defaultValue = default
+ self.mayReturnEmpty = True
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ try:
+ loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False )
+ except (ParseException,IndexError):
+ if self.defaultValue is not _optionalNotMatched:
+ if self.expr.resultsName:
+ tokens = ParseResults([ self.defaultValue ])
+ tokens[self.expr.resultsName] = self.defaultValue
+ else:
+ tokens = [ self.defaultValue ]
+ else:
+ tokens = []
+ return loc, tokens
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+
+ if self.strRepr is None:
+ self.strRepr = "[" + _ustr(self.expr) + "]"
+
+ return self.strRepr
+
+class SkipTo(ParseElementEnhance):
+ """
+ Token for skipping over all undefined text until the matched expression is found.
+
+ Parameters:
+ - expr - target expression marking the end of the data to be skipped
+ - include - (default=C{False}) if True, the target expression is also parsed
+ (the skipped text and target expression are returned as a 2-element list).
+ - ignore - (default=C{None}) used to define grammars (typically quoted strings and
+ comments) that might contain false matches to the target expression
+ - failOn - (default=C{None}) define expressions that are not allowed to be
+ included in the skipped test; if found before the target expression is found,
+ the SkipTo is not a match
+
+ Example::
+ report = '''
+ Outstanding Issues Report - 1 Jan 2000
+
+ # | Severity | Description | Days Open
+ -----+----------+-------------------------------------------+-----------
+ 101 | Critical | Intermittent system crash | 6
+ 94 | Cosmetic | Spelling error on Login ('log|n') | 14
+ 79 | Minor | System slow when running too many reports | 47
+ '''
+ integer = Word(nums)
+ SEP = Suppress('|')
+ # use SkipTo to simply match everything up until the next SEP
+ # - ignore quoted strings, so that a '|' character inside a quoted string does not match
+ # - parse action will call token.strip() for each matched token, i.e., the description body
+ string_data = SkipTo(SEP, ignore=quotedString)
+ string_data.setParseAction(tokenMap(str.strip))
+ ticket_expr = (integer("issue_num") + SEP
+ + string_data("sev") + SEP
+ + string_data("desc") + SEP
+ + integer("days_open"))
+
+ for tkt in ticket_expr.searchString(report):
+ print tkt.dump()
+ prints::
+ ['101', 'Critical', 'Intermittent system crash', '6']
+ - days_open: 6
+ - desc: Intermittent system crash
+ - issue_num: 101
+ - sev: Critical
+ ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14']
+ - days_open: 14
+ - desc: Spelling error on Login ('log|n')
+ - issue_num: 94
+ - sev: Cosmetic
+ ['79', 'Minor', 'System slow when running too many reports', '47']
+ - days_open: 47
+ - desc: System slow when running too many reports
+ - issue_num: 79
+ - sev: Minor
+ """
+ def __init__( self, other, include=False, ignore=None, failOn=None ):
+ super( SkipTo, self ).__init__( other )
+ self.ignoreExpr = ignore
+ self.mayReturnEmpty = True
+ self.mayIndexError = False
+ self.includeMatch = include
+ self.asList = False
+ if isinstance(failOn, basestring):
+ self.failOn = ParserElement._literalStringClass(failOn)
+ else:
+ self.failOn = failOn
+ self.errmsg = "No match found for "+_ustr(self.expr)
+
+ def parseImpl( self, instring, loc, doActions=True ):
+ startloc = loc
+ instrlen = len(instring)
+ expr = self.expr
+ expr_parse = self.expr._parse
+ self_failOn_canParseNext = self.failOn.canParseNext if self.failOn is not None else None
+ self_ignoreExpr_tryParse = self.ignoreExpr.tryParse if self.ignoreExpr is not None else None
+
+ tmploc = loc
+ while tmploc <= instrlen:
+ if self_failOn_canParseNext is not None:
+ # break if failOn expression matches
+ if self_failOn_canParseNext(instring, tmploc):
+ break
+
+ if self_ignoreExpr_tryParse is not None:
+ # advance past ignore expressions
+ while 1:
+ try:
+ tmploc = self_ignoreExpr_tryParse(instring, tmploc)
+ except ParseBaseException:
+ break
+
+ try:
+ expr_parse(instring, tmploc, doActions=False, callPreParse=False)
+ except (ParseException, IndexError):
+ # no match, advance loc in string
+ tmploc += 1
+ else:
+ # matched skipto expr, done
+ break
+
+ else:
+ # ran off the end of the input string without matching skipto expr, fail
+ raise ParseException(instring, loc, self.errmsg, self)
+
+ # build up return values
+ loc = tmploc
+ skiptext = instring[startloc:loc]
+ skipresult = ParseResults(skiptext)
+
+ if self.includeMatch:
+ loc, mat = expr_parse(instring,loc,doActions,callPreParse=False)
+ skipresult += mat
+
+ return loc, skipresult
+
+class Forward(ParseElementEnhance):
+ """
+ Forward declaration of an expression to be defined later -
+ used for recursive grammars, such as algebraic infix notation.
+ When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator.
+
+ Note: take care when assigning to C{Forward} not to overlook precedence of operators.
+ Specifically, '|' has a lower precedence than '<<', so that::
+ fwdExpr << a | b | c
+ will actually be evaluated as::
+ (fwdExpr << a) | b | c
+ thereby leaving b and c out as parseable alternatives. It is recommended that you
+ explicitly group the values inserted into the C{Forward}::
+ fwdExpr << (a | b | c)
+ Converting to use the '<<=' operator instead will avoid this problem.
+
+ See L{ParseResults.pprint} for an example of a recursive parser created using
+ C{Forward}.
+ """
+ def __init__( self, other=None ):
+ super(Forward,self).__init__( other, savelist=False )
+
+ def __lshift__( self, other ):
+ if isinstance( other, basestring ):
+ other = ParserElement._literalStringClass(other)
+ self.expr = other
+ self.strRepr = None
+ self.mayIndexError = self.expr.mayIndexError
+ self.mayReturnEmpty = self.expr.mayReturnEmpty
+ self.setWhitespaceChars( self.expr.whiteChars )
+ self.skipWhitespace = self.expr.skipWhitespace
+ self.saveAsList = self.expr.saveAsList
+ self.ignoreExprs.extend(self.expr.ignoreExprs)
+ return self
+
+ def __ilshift__(self, other):
+ return self << other
+
+ def leaveWhitespace( self ):
+ self.skipWhitespace = False
+ return self
+
+ def streamline( self ):
+ if not self.streamlined:
+ self.streamlined = True
+ if self.expr is not None:
+ self.expr.streamline()
+ return self
+
+ def validate( self, validateTrace=[] ):
+ if self not in validateTrace:
+ tmp = validateTrace[:]+[self]
+ if self.expr is not None:
+ self.expr.validate(tmp)
+ self.checkRecursion([])
+
+ def __str__( self ):
+ if hasattr(self,"name"):
+ return self.name
+ return self.__class__.__name__ + ": ..."
+
+ # stubbed out for now - creates awful memory and perf issues
+ self._revertClass = self.__class__
+ self.__class__ = _ForwardNoRecurse
+ try:
+ if self.expr is not None:
+ retString = _ustr(self.expr)
+ else:
+ retString = "None"
+ finally:
+ self.__class__ = self._revertClass
+ return self.__class__.__name__ + ": " + retString
+
+ def copy(self):
+ if self.expr is not None:
+ return super(Forward,self).copy()
+ else:
+ ret = Forward()
+ ret <<= self
+ return ret
+
+class _ForwardNoRecurse(Forward):
+ def __str__( self ):
+ return "..."
+
+class TokenConverter(ParseElementEnhance):
+ """
+ Abstract subclass of C{ParseExpression}, for converting parsed results.
+ """
+ def __init__( self, expr, savelist=False ):
+ super(TokenConverter,self).__init__( expr )#, savelist )
+ self.saveAsList = False
+
+class Combine(TokenConverter):
+ """
+ Converter to concatenate all matching tokens to a single string.
+ By default, the matching patterns must also be contiguous in the input string;
+ this can be disabled by specifying C{'adjacent=False'} in the constructor.
+
+ Example::
+ real = Word(nums) + '.' + Word(nums)
+ print(real.parseString('3.1416')) # -> ['3', '.', '1416']
+ # will also erroneously match the following
+ print(real.parseString('3. 1416')) # -> ['3', '.', '1416']
+
+ real = Combine(Word(nums) + '.' + Word(nums))
+ print(real.parseString('3.1416')) # -> ['3.1416']
+ # no match when there are internal spaces
+ print(real.parseString('3. 1416')) # -> Exception: Expected W:(0123...)
+ """
+ def __init__( self, expr, joinString="", adjacent=True ):
+ super(Combine,self).__init__( expr )
+ # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself
+ if adjacent:
+ self.leaveWhitespace()
+ self.adjacent = adjacent
+ self.skipWhitespace = True
+ self.joinString = joinString
+ self.callPreparse = True
+
+ def ignore( self, other ):
+ if self.adjacent:
+ ParserElement.ignore(self, other)
+ else:
+ super( Combine, self).ignore( other )
+ return self
+
+ def postParse( self, instring, loc, tokenlist ):
+ retToks = tokenlist.copy()
+ del retToks[:]
+ retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults)
+
+ if self.resultsName and retToks.haskeys():
+ return [ retToks ]
+ else:
+ return retToks
+
+class Group(TokenConverter):
+ """
+ Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.
+
+ Example::
+ ident = Word(alphas)
+ num = Word(nums)
+ term = ident | num
+ func = ident + Optional(delimitedList(term))
+ print(func.parseString("fn a,b,100")) # -> ['fn', 'a', 'b', '100']
+
+ func = ident + Group(Optional(delimitedList(term)))
+ print(func.parseString("fn a,b,100")) # -> ['fn', ['a', 'b', '100']]
+ """
+ def __init__( self, expr ):
+ super(Group,self).__init__( expr )
+ self.saveAsList = True
+
+ def postParse( self, instring, loc, tokenlist ):
+ return [ tokenlist ]
+
+class Dict(TokenConverter):
+ """
+ Converter to return a repetitive expression as a list, but also as a dictionary.
+ Each element can also be referenced using the first token in the expression as its key.
+ Useful for tabular report scraping when the first column can be used as a item key.
+
+ Example::
+ data_word = Word(alphas)
+ label = data_word + FollowedBy(':')
+ attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).setParseAction(' '.join))
+
+ text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
+ attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+
+ # print attributes as plain groups
+ print(OneOrMore(attr_expr).parseString(text).dump())
+
+ # instead of OneOrMore(expr), parse using Dict(OneOrMore(Group(expr))) - Dict will auto-assign names
+ result = Dict(OneOrMore(Group(attr_expr))).parseString(text)
+ print(result.dump())
+
+ # access named fields as dict entries, or output as dict
+ print(result['shape'])
+ print(result.asDict())
+ prints::
+ ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap']
+
+ [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
+ - color: light blue
+ - posn: upper left
+ - shape: SQUARE
+ - texture: burlap
+ SQUARE
+ {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'}
+ See more examples at L{ParseResults} of accessing fields by results name.
+ """
+ def __init__( self, expr ):
+ super(Dict,self).__init__( expr )
+ self.saveAsList = True
+
+ def postParse( self, instring, loc, tokenlist ):
+ for i,tok in enumerate(tokenlist):
+ if len(tok) == 0:
+ continue
+ ikey = tok[0]
+ if isinstance(ikey,int):
+ ikey = _ustr(tok[0]).strip()
+ if len(tok)==1:
+ tokenlist[ikey] = _ParseResultsWithOffset("",i)
+ elif len(tok)==2 and not isinstance(tok[1],ParseResults):
+ tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i)
+ else:
+ dictvalue = tok.copy() #ParseResults(i)
+ del dictvalue[0]
+ if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.haskeys()):
+ tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i)
+ else:
+ tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i)
+
+ if self.resultsName:
+ return [ tokenlist ]
+ else:
+ return tokenlist
+
+
+class Suppress(TokenConverter):
+ """
+ Converter for ignoring the results of a parsed expression.
+
+ Example::
+ source = "a, b, c,d"
+ wd = Word(alphas)
+ wd_list1 = wd + ZeroOrMore(',' + wd)
+ print(wd_list1.parseString(source))
+
+ # often, delimiters that are useful during parsing are just in the
+ # way afterward - use Suppress to keep them out of the parsed output
+ wd_list2 = wd + ZeroOrMore(Suppress(',') + wd)
+ print(wd_list2.parseString(source))
+ prints::
+ ['a', ',', 'b', ',', 'c', ',', 'd']
+ ['a', 'b', 'c', 'd']
+ (See also L{delimitedList}.)
+ """
+ def postParse( self, instring, loc, tokenlist ):
+ return []
+
+ def suppress( self ):
+ return self
+
+
+class OnlyOnce(object):
+ """
+ Wrapper for parse actions, to ensure they are only called once.
+ """
+ def __init__(self, methodCall):
+ self.callable = _trim_arity(methodCall)
+ self.called = False
+ def __call__(self,s,l,t):
+ if not self.called:
+ results = self.callable(s,l,t)
+ self.called = True
+ return results
+ raise ParseException(s,l,"")
+ def reset(self):
+ self.called = False
+
+def traceParseAction(f):
+ """
+ Decorator for debugging parse actions.
+
+ When the parse action is called, this decorator will print C{">> entering I{method-name}(line:I{current_source_line}, I{parse_location}, I{matched_tokens})".}
+ When the parse action completes, the decorator will print C{"<<"} followed by the returned value, or any exception that the parse action raised.
+
+ Example::
+ wd = Word(alphas)
+
+ @traceParseAction
+ def remove_duplicate_chars(tokens):
+ return ''.join(sorted(set(''.join(tokens)))
+
+ wds = OneOrMore(wd).setParseAction(remove_duplicate_chars)
+ print(wds.parseString("slkdjs sld sldd sdlf sdljf"))
+ prints::
+ >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {}))
+ <<leaving remove_duplicate_chars (ret: 'dfjkls')
+ ['dfjkls']
+ """
+ f = _trim_arity(f)
+ def z(*paArgs):
+ thisFunc = f.__name__
+ s,l,t = paArgs[-3:]
+ if len(paArgs)>3:
+ thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc
+ sys.stderr.write( ">>entering %s(line: '%s', %d, %r)\n" % (thisFunc,line(l,s),l,t) )
+ try:
+ ret = f(*paArgs)
+ except Exception as exc:
+ sys.stderr.write( "<<leaving %s (exception: %s)\n" % (thisFunc,exc) )
+ raise
+ sys.stderr.write( "<<leaving %s (ret: %r)\n" % (thisFunc,ret) )
+ return ret
+ try:
+ z.__name__ = f.__name__
+ except AttributeError:
+ pass
+ return z
+
+#
+# global helpers
+#
+def delimitedList( expr, delim=",", combine=False ):
+ """
+ Helper to define a delimited list of expressions - the delimiter defaults to ','.
+ By default, the list elements and delimiters can have intervening whitespace, and
+ comments, but this can be overridden by passing C{combine=True} in the constructor.
+ If C{combine} is set to C{True}, the matching tokens are returned as a single token
+ string, with the delimiters included; otherwise, the matching tokens are returned
+ as a list of tokens, with the delimiters suppressed.
+
+ Example::
+ delimitedList(Word(alphas)).parseString("aa,bb,cc") # -> ['aa', 'bb', 'cc']
+ delimitedList(Word(hexnums), delim=':', combine=True).parseString("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE']
+ """
+ dlName = _ustr(expr)+" ["+_ustr(delim)+" "+_ustr(expr)+"]..."
+ if combine:
+ return Combine( expr + ZeroOrMore( delim + expr ) ).setName(dlName)
+ else:
+ return ( expr + ZeroOrMore( Suppress( delim ) + expr ) ).setName(dlName)
+
+def countedArray( expr, intExpr=None ):
+ """
+ Helper to define a counted list of expressions.
+ This helper defines a pattern of the form::
+ integer expr expr expr...
+ where the leading integer tells how many expr expressions follow.
+ The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed.
+
+ If C{intExpr} is specified, it should be a pyparsing expression that produces an integer value.
+
+ Example::
+ countedArray(Word(alphas)).parseString('2 ab cd ef') # -> ['ab', 'cd']
+
+ # in this parser, the leading integer value is given in binary,
+ # '10' indicating that 2 values are in the array
+ binaryConstant = Word('01').setParseAction(lambda t: int(t[0], 2))
+ countedArray(Word(alphas), intExpr=binaryConstant).parseString('10 ab cd ef') # -> ['ab', 'cd']
+ """
+ arrayExpr = Forward()
+ def countFieldParseAction(s,l,t):
+ n = t[0]
+ arrayExpr << (n and Group(And([expr]*n)) or Group(empty))
+ return []
+ if intExpr is None:
+ intExpr = Word(nums).setParseAction(lambda t:int(t[0]))
+ else:
+ intExpr = intExpr.copy()
+ intExpr.setName("arrayLen")
+ intExpr.addParseAction(countFieldParseAction, callDuringTry=True)
+ return ( intExpr + arrayExpr ).setName('(len) ' + _ustr(expr) + '...')
+
+def _flatten(L):
+ ret = []
+ for i in L:
+ if isinstance(i,list):
+ ret.extend(_flatten(i))
+ else:
+ ret.append(i)
+ return ret
+
+def matchPreviousLiteral(expr):
+ """
+ Helper to define an expression that is indirectly defined from
+ the tokens matched in a previous expression, that is, it looks
+ for a 'repeat' of a previous expression. For example::
+ first = Word(nums)
+ second = matchPreviousLiteral(first)
+ matchExpr = first + ":" + second
+ will match C{"1:1"}, but not C{"1:2"}. Because this matches a
+ previous literal, will also match the leading C{"1:1"} in C{"1:10"}.
+ If this is not desired, use C{matchPreviousExpr}.
+ Do I{not} use with packrat parsing enabled.
+ """
+ rep = Forward()
+ def copyTokenToRepeater(s,l,t):
+ if t:
+ if len(t) == 1:
+ rep << t[0]
+ else:
+ # flatten t tokens
+ tflat = _flatten(t.asList())
+ rep << And(Literal(tt) for tt in tflat)
+ else:
+ rep << Empty()
+ expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
+ rep.setName('(prev) ' + _ustr(expr))
+ return rep
+
+def matchPreviousExpr(expr):
+ """
+ Helper to define an expression that is indirectly defined from
+ the tokens matched in a previous expression, that is, it looks
+ for a 'repeat' of a previous expression. For example::
+ first = Word(nums)
+ second = matchPreviousExpr(first)
+ matchExpr = first + ":" + second
+ will match C{"1:1"}, but not C{"1:2"}. Because this matches by
+ expressions, will I{not} match the leading C{"1:1"} in C{"1:10"};
+ the expressions are evaluated first, and then compared, so
+ C{"1"} is compared with C{"10"}.
+ Do I{not} use with packrat parsing enabled.
+ """
+ rep = Forward()
+ e2 = expr.copy()
+ rep <<= e2
+ def copyTokenToRepeater(s,l,t):
+ matchTokens = _flatten(t.asList())
+ def mustMatchTheseTokens(s,l,t):
+ theseTokens = _flatten(t.asList())
+ if theseTokens != matchTokens:
+ raise ParseException("",0,"")
+ rep.setParseAction( mustMatchTheseTokens, callDuringTry=True )
+ expr.addParseAction(copyTokenToRepeater, callDuringTry=True)
+ rep.setName('(prev) ' + _ustr(expr))
+ return rep
+
+def _escapeRegexRangeChars(s):
+ #~ escape these chars: ^-]
+ for c in r"\^-]":
+ s = s.replace(c,_bslash+c)
+ s = s.replace("\n",r"\n")
+ s = s.replace("\t",r"\t")
+ return _ustr(s)
+
+def oneOf( strs, caseless=False, useRegex=True ):
+ """
+ Helper to quickly define a set of alternative Literals, and makes sure to do
+ longest-first testing when there is a conflict, regardless of the input order,
+ but returns a C{L{MatchFirst}} for best performance.
+
+ Parameters:
+ - strs - a string of space-delimited literals, or a collection of string literals
+ - caseless - (default=C{False}) - treat all literals as caseless
+ - useRegex - (default=C{True}) - as an optimization, will generate a Regex
+ object; otherwise, will generate a C{MatchFirst} object (if C{caseless=True}, or
+ if creating a C{Regex} raises an exception)
+
+ Example::
+ comp_oper = oneOf("< = > <= >= !=")
+ var = Word(alphas)
+ number = Word(nums)
+ term = var | number
+ comparison_expr = term + comp_oper + term
+ print(comparison_expr.searchString("B = 12 AA=23 B<=AA AA>12"))
+ prints::
+ [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']]
+ """
+ if caseless:
+ isequal = ( lambda a,b: a.upper() == b.upper() )
+ masks = ( lambda a,b: b.upper().startswith(a.upper()) )
+ parseElementClass = CaselessLiteral
+ else:
+ isequal = ( lambda a,b: a == b )
+ masks = ( lambda a,b: b.startswith(a) )
+ parseElementClass = Literal
+
+ symbols = []
+ if isinstance(strs,basestring):
+ symbols = strs.split()
+ elif isinstance(strs, collections.Iterable):
+ symbols = list(strs)
+ else:
+ warnings.warn("Invalid argument to oneOf, expected string or iterable",
+ SyntaxWarning, stacklevel=2)
+ if not symbols:
+ return NoMatch()
+
+ i = 0
+ while i < len(symbols)-1:
+ cur = symbols[i]
+ for j,other in enumerate(symbols[i+1:]):
+ if ( isequal(other, cur) ):
+ del symbols[i+j+1]
+ break
+ elif ( masks(cur, other) ):
+ del symbols[i+j+1]
+ symbols.insert(i,other)
+ cur = other
+ break
+ else:
+ i += 1
+
+ if not caseless and useRegex:
+ #~ print (strs,"->", "|".join( [ _escapeRegexChars(sym) for sym in symbols] ))
+ try:
+ if len(symbols)==len("".join(symbols)):
+ return Regex( "[%s]" % "".join(_escapeRegexRangeChars(sym) for sym in symbols) ).setName(' | '.join(symbols))
+ else:
+ return Regex( "|".join(re.escape(sym) for sym in symbols) ).setName(' | '.join(symbols))
+ except Exception:
+ warnings.warn("Exception creating Regex for oneOf, building MatchFirst",
+ SyntaxWarning, stacklevel=2)
+
+
+ # last resort, just use MatchFirst
+ return MatchFirst(parseElementClass(sym) for sym in symbols).setName(' | '.join(symbols))
+
+def dictOf( key, value ):
+ """
+ Helper to easily and clearly define a dictionary by specifying the respective patterns
+ for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens
+ in the proper order. The key pattern can include delimiting markers or punctuation,
+ as long as they are suppressed, thereby leaving the significant key text. The value
+ pattern can include named results, so that the C{Dict} results can include named token
+ fields.
+
+ Example::
+ text = "shape: SQUARE posn: upper left color: light blue texture: burlap"
+ attr_expr = (label + Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join))
+ print(OneOrMore(attr_expr).parseString(text).dump())
+
+ attr_label = label
+ attr_value = Suppress(':') + OneOrMore(data_word, stopOn=label).setParseAction(' '.join)
+
+ # similar to Dict, but simpler call format
+ result = dictOf(attr_label, attr_value).parseString(text)
+ print(result.dump())
+ print(result['shape'])
+ print(result.shape) # object attribute access works too
+ print(result.asDict())
+ prints::
+ [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']]
+ - color: light blue
+ - posn: upper left
+ - shape: SQUARE
+ - texture: burlap
+ SQUARE
+ SQUARE
+ {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'}
+ """
+ return Dict( ZeroOrMore( Group ( key + value ) ) )
+
+def originalTextFor(expr, asString=True):
+ """
+ Helper to return the original, untokenized text for a given expression. Useful to
+ restore the parsed fields of an HTML start tag into the raw tag text itself, or to
+ revert separate tokens with intervening whitespace back to the original matching
+ input text. By default, returns astring containing the original parsed text.
+
+ If the optional C{asString} argument is passed as C{False}, then the return value is a
+ C{L{ParseResults}} containing any results names that were originally matched, and a
+ single token containing the original matched text from the input string. So if
+ the expression passed to C{L{originalTextFor}} contains expressions with defined
+ results names, you must set C{asString} to C{False} if you want to preserve those
+ results name values.
+
+ Example::
+ src = "this is test <b> bold <i>text</i> </b> normal text "
+ for tag in ("b","i"):
+ opener,closer = makeHTMLTags(tag)
+ patt = originalTextFor(opener + SkipTo(closer) + closer)
+ print(patt.searchString(src)[0])
+ prints::
+ ['<b> bold <i>text</i> </b>']
+ ['<i>text</i>']
+ """
+ locMarker = Empty().setParseAction(lambda s,loc,t: loc)
+ endlocMarker = locMarker.copy()
+ endlocMarker.callPreparse = False
+ matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end")
+ if asString:
+ extractText = lambda s,l,t: s[t._original_start:t._original_end]
+ else:
+ def extractText(s,l,t):
+ t[:] = [s[t.pop('_original_start'):t.pop('_original_end')]]
+ matchExpr.setParseAction(extractText)
+ matchExpr.ignoreExprs = expr.ignoreExprs
+ return matchExpr
+
+def ungroup(expr):
+ """
+ Helper to undo pyparsing's default grouping of And expressions, even
+ if all but one are non-empty.
+ """
+ return TokenConverter(expr).setParseAction(lambda t:t[0])
+
+def locatedExpr(expr):
+ """
+ Helper to decorate a returned token with its starting and ending locations in the input string.
+ This helper adds the following results names:
+ - locn_start = location where matched expression begins
+ - locn_end = location where matched expression ends
+ - value = the actual parsed results
+
+ Be careful if the input text contains C{<TAB>} characters, you may want to call
+ C{L{ParserElement.parseWithTabs}}
+
+ Example::
+ wd = Word(alphas)
+ for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"):
+ print(match)
+ prints::
+ [[0, 'ljsdf', 5]]
+ [[8, 'lksdjjf', 15]]
+ [[18, 'lkkjj', 23]]
+ """
+ locator = Empty().setParseAction(lambda s,l,t: l)
+ return Group(locator("locn_start") + expr("value") + locator.copy().leaveWhitespace()("locn_end"))
+
+
+# convenience constants for positional expressions
+empty = Empty().setName("empty")
+lineStart = LineStart().setName("lineStart")
+lineEnd = LineEnd().setName("lineEnd")
+stringStart = StringStart().setName("stringStart")
+stringEnd = StringEnd().setName("stringEnd")
+
+_escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1])
+_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16)))
+_escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8)))
+_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(printables, excludeChars=r'\]', exact=1) | Regex(r"\w", re.UNICODE)
+_charRange = Group(_singleChar + Suppress("-") + _singleChar)
+_reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]"
+
+def srange(s):
+ r"""
+ Helper to easily define string ranges for use in Word construction. Borrows
+ syntax from regexp '[]' string range definitions::
+ srange("[0-9]") -> "0123456789"
+ srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz"
+ srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_"
+ The input string must be enclosed in []'s, and the returned string is the expanded
+ character set joined into a single string.
+ The values enclosed in the []'s may be:
+ - a single character
+ - an escaped character with a leading backslash (such as C{\-} or C{\]})
+ - an escaped hex character with a leading C{'\x'} (C{\x21}, which is a C{'!'} character)
+ (C{\0x##} is also supported for backwards compatibility)
+ - an escaped octal character with a leading C{'\0'} (C{\041}, which is a C{'!'} character)
+ - a range of any of the above, separated by a dash (C{'a-z'}, etc.)
+ - any combination of the above (C{'aeiouy'}, C{'a-zA-Z0-9_$'}, etc.)
+ """
+ _expanded = lambda p: p if not isinstance(p,ParseResults) else ''.join(unichr(c) for c in range(ord(p[0]),ord(p[1])+1))
+ try:
+ return "".join(_expanded(part) for part in _reBracketExpr.parseString(s).body)
+ except Exception:
+ return ""
+
+def matchOnlyAtCol(n):
+ """
+ Helper method for defining parse actions that require matching at a specific
+ column in the input text.
+ """
+ def verifyCol(strg,locn,toks):
+ if col(locn,strg) != n:
+ raise ParseException(strg,locn,"matched token not at column %d" % n)
+ return verifyCol
+
+def replaceWith(replStr):
+ """
+ Helper method for common parse actions that simply return a literal value. Especially
+ useful when used with C{L{transformString<ParserElement.transformString>}()}.
+
+ Example::
+ num = Word(nums).setParseAction(lambda toks: int(toks[0]))
+ na = oneOf("N/A NA").setParseAction(replaceWith(math.nan))
+ term = na | num
+
+ OneOrMore(term).parseString("324 234 N/A 234") # -> [324, 234, nan, 234]
+ """
+ return lambda s,l,t: [replStr]
+
+def removeQuotes(s,l,t):
+ """
+ Helper parse action for removing quotation marks from parsed quoted strings.
+
+ Example::
+ # by default, quotation marks are included in parsed results
+ quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"]
+
+ # use removeQuotes to strip quotation marks from parsed results
+ quotedString.setParseAction(removeQuotes)
+ quotedString.parseString("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"]
+ """
+ return t[0][1:-1]
+
+def tokenMap(func, *args):
+ """
+ Helper to define a parse action by mapping a function to all elements of a ParseResults list.If any additional
+ args are passed, they are forwarded to the given function as additional arguments after
+ the token, as in C{hex_integer = Word(hexnums).setParseAction(tokenMap(int, 16))}, which will convert the
+ parsed data to an integer using base 16.
+
+ Example (compare the last to example in L{ParserElement.transformString}::
+ hex_ints = OneOrMore(Word(hexnums)).setParseAction(tokenMap(int, 16))
+ hex_ints.runTests('''
+ 00 11 22 aa FF 0a 0d 1a
+ ''')
+
+ upperword = Word(alphas).setParseAction(tokenMap(str.upper))
+ OneOrMore(upperword).runTests('''
+ my kingdom for a horse
+ ''')
+
+ wd = Word(alphas).setParseAction(tokenMap(str.title))
+ OneOrMore(wd).setParseAction(' '.join).runTests('''
+ now is the winter of our discontent made glorious summer by this sun of york
+ ''')
+ prints::
+ 00 11 22 aa FF 0a 0d 1a
+ [0, 17, 34, 170, 255, 10, 13, 26]
+
+ my kingdom for a horse
+ ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE']
+
+ now is the winter of our discontent made glorious summer by this sun of york
+ ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York']
+ """
+ def pa(s,l,t):
+ return [func(tokn, *args) for tokn in t]
+
+ try:
+ func_name = getattr(func, '__name__',
+ getattr(func, '__class__').__name__)
+ except Exception:
+ func_name = str(func)
+ pa.__name__ = func_name
+
+ return pa
+
+upcaseTokens = tokenMap(lambda t: _ustr(t).upper())
+"""(Deprecated) Helper parse action to convert tokens to upper case. Deprecated in favor of L{pyparsing_common.upcaseTokens}"""
+
+downcaseTokens = tokenMap(lambda t: _ustr(t).lower())
+"""(Deprecated) Helper parse action to convert tokens to lower case. Deprecated in favor of L{pyparsing_common.downcaseTokens}"""
+
+def _makeTags(tagStr, xml):
+ """Internal helper to construct opening and closing tag expressions, given a tag name"""
+ if isinstance(tagStr,basestring):
+ resname = tagStr
+ tagStr = Keyword(tagStr, caseless=not xml)
+ else:
+ resname = tagStr.name
+
+ tagAttrName = Word(alphas,alphanums+"_-:")
+ if (xml):
+ tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes )
+ openTag = Suppress("<") + tagStr("tag") + \
+ Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \
+ Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
+ else:
+ printablesLessRAbrack = "".join(c for c in printables if c not in ">")
+ tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack)
+ openTag = Suppress("<") + tagStr("tag") + \
+ Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \
+ Optional( Suppress("=") + tagAttrValue ) ))) + \
+ Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">")
+ closeTag = Combine(_L("</") + tagStr + ">")
+
+ openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % resname)
+ closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("</%s>" % resname)
+ openTag.tag = resname
+ closeTag.tag = resname
+ return openTag, closeTag
+
+def makeHTMLTags(tagStr):
+ """
+ Helper to construct opening and closing tag expressions for HTML, given a tag name. Matches
+ tags in either upper or lower case, attributes with namespaces and with quoted or unquoted values.
+
+ Example::
+ text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
+ # makeHTMLTags returns pyparsing expressions for the opening and closing tags as a 2-tuple
+ a,a_end = makeHTMLTags("A")
+ link_expr = a + SkipTo(a_end)("link_text") + a_end
+
+ for link in link_expr.searchString(text):
+ # attributes in the <A> tag (like "href" shown here) are also accessible as named results
+ print(link.link_text, '->', link.href)
+ prints::
+ pyparsing -> http://pyparsing.wikispaces.com
+ """
+ return _makeTags( tagStr, False )
+
+def makeXMLTags(tagStr):
+ """
+ Helper to construct opening and closing tag expressions for XML, given a tag name. Matches
+ tags only in the given upper/lower case.
+
+ Example: similar to L{makeHTMLTags}
+ """
+ return _makeTags( tagStr, True )
+
+def withAttribute(*args,**attrDict):
+ """
+ Helper to create a validating parse action to be used with start tags created
+ with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag
+ with a required attribute value, to avoid false matches on common tags such as
+ C{<TD>} or C{<DIV>}.
+
+ Call C{withAttribute} with a series of attribute names and values. Specify the list
+ of filter attributes names and values as:
+ - keyword arguments, as in C{(align="right")}, or
+ - as an explicit dict with C{**} operator, when an attribute name is also a Python
+ reserved word, as in C{**{"class":"Customer", "align":"right"}}
+ - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") )
+ For attribute names with a namespace prefix, you must use the second form. Attribute
+ names are matched insensitive to upper/lower case.
+
+ If just testing for C{class} (with or without a namespace), use C{L{withClass}}.
+
+ To verify that the attribute exists, but without specifying a value, pass
+ C{withAttribute.ANY_VALUE} as the value.
+
+ Example::
+ html = '''
+ <div>
+ Some text
+ <div type="grid">1 4 0 1 0</div>
+ <div type="graph">1,3 2,3 1,1</div>
+ <div>this has no type</div>
+ </div>
+
+ '''
+ div,div_end = makeHTMLTags("div")
+
+ # only match div tag having a type attribute with value "grid"
+ div_grid = div().setParseAction(withAttribute(type="grid"))
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ # construct a match with any div tag having a type attribute, regardless of the value
+ div_any_type = div().setParseAction(withAttribute(type=withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+ prints::
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
+ if args:
+ attrs = args[:]
+ else:
+ attrs = attrDict.items()
+ attrs = [(k,v) for k,v in attrs]
+ def pa(s,l,tokens):
+ for attrName,attrValue in attrs:
+ if attrName not in tokens:
+ raise ParseException(s,l,"no matching attribute " + attrName)
+ if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue:
+ raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" %
+ (attrName, tokens[attrName], attrValue))
+ return pa
+withAttribute.ANY_VALUE = object()
+
+def withClass(classname, namespace=''):
+ """
+ Simplified version of C{L{withAttribute}} when matching on a div class - made
+ difficult because C{class} is a reserved word in Python.
+
+ Example::
+ html = '''
+ <div>
+ Some text
+ <div class="grid">1 4 0 1 0</div>
+ <div class="graph">1,3 2,3 1,1</div>
+ <div>this <div> has no class</div>
+ </div>
+
+ '''
+ div,div_end = makeHTMLTags("div")
+ div_grid = div().setParseAction(withClass("grid"))
+
+ grid_expr = div_grid + SkipTo(div | div_end)("body")
+ for grid_header in grid_expr.searchString(html):
+ print(grid_header.body)
+
+ div_any_type = div().setParseAction(withClass(withAttribute.ANY_VALUE))
+ div_expr = div_any_type + SkipTo(div | div_end)("body")
+ for div_header in div_expr.searchString(html):
+ print(div_header.body)
+ prints::
+ 1 4 0 1 0
+
+ 1 4 0 1 0
+ 1,3 2,3 1,1
+ """
+ classattr = "%s:class" % namespace if namespace else "class"
+ return withAttribute(**{classattr : classname})
+
+opAssoc = _Constants()
+opAssoc.LEFT = object()
+opAssoc.RIGHT = object()
+
+def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ):
+ """
+ Helper method for constructing grammars of expressions made up of
+ operators working in a precedence hierarchy. Operators may be unary or
+ binary, left- or right-associative. Parse actions can also be attached
+ to operator expressions. The generated parser will also recognize the use
+ of parentheses to override operator precedences (see example below).
+
+ Note: if you define a deep operator list, you may see performance issues
+ when using infixNotation. See L{ParserElement.enablePackrat} for a
+ mechanism to potentially improve your parser performance.
+
+ Parameters:
+ - baseExpr - expression representing the most basic element for the nested
+ - opList - list of tuples, one for each operator precedence level in the
+ expression grammar; each tuple is of the form
+ (opExpr, numTerms, rightLeftAssoc, parseAction), where:
+ - opExpr is the pyparsing expression for the operator;
+ may also be a string, which will be converted to a Literal;
+ if numTerms is 3, opExpr is a tuple of two expressions, for the
+ two operators separating the 3 terms
+ - numTerms is the number of terms for this operator (must
+ be 1, 2, or 3)
+ - rightLeftAssoc is the indicator whether the operator is
+ right or left associative, using the pyparsing-defined
+ constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}.
+ - parseAction is the parse action to be associated with
+ expressions matching this operator expression (the
+ parse action tuple member may be omitted)
+ - lpar - expression for matching left-parentheses (default=C{Suppress('(')})
+ - rpar - expression for matching right-parentheses (default=C{Suppress(')')})
+
+ Example::
+ # simple example of four-function arithmetic with ints and variable names
+ integer = pyparsing_common.signed_integer
+ varname = pyparsing_common.identifier
+
+ arith_expr = infixNotation(integer | varname,
+ [
+ ('-', 1, opAssoc.RIGHT),
+ (oneOf('* /'), 2, opAssoc.LEFT),
+ (oneOf('+ -'), 2, opAssoc.LEFT),
+ ])
+
+ arith_expr.runTests('''
+ 5+3*6
+ (5+3)*6
+ -2--11
+ ''', fullDump=False)
+ prints::
+ 5+3*6
+ [[5, '+', [3, '*', 6]]]
+
+ (5+3)*6
+ [[[5, '+', 3], '*', 6]]
+
+ -2--11
+ [[['-', 2], '-', ['-', 11]]]
+ """
+ ret = Forward()
+ lastExpr = baseExpr | ( lpar + ret + rpar )
+ for i,operDef in enumerate(opList):
+ opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4]
+ termName = "%s term" % opExpr if arity < 3 else "%s%s term" % opExpr
+ if arity == 3:
+ if opExpr is None or len(opExpr) != 2:
+ raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions")
+ opExpr1, opExpr2 = opExpr
+ thisExpr = Forward().setName(termName)
+ if rightLeftAssoc == opAssoc.LEFT:
+ if arity == 1:
+ matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) )
+ elif arity == 2:
+ if opExpr is not None:
+ matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) )
+ else:
+ matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) )
+ elif arity == 3:
+ matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \
+ Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr )
+ else:
+ raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
+ elif rightLeftAssoc == opAssoc.RIGHT:
+ if arity == 1:
+ # try to avoid LR with this extra test
+ if not isinstance(opExpr, Optional):
+ opExpr = Optional(opExpr)
+ matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr )
+ elif arity == 2:
+ if opExpr is not None:
+ matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) )
+ else:
+ matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) )
+ elif arity == 3:
+ matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \
+ Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr )
+ else:
+ raise ValueError("operator must be unary (1), binary (2), or ternary (3)")
+ else:
+ raise ValueError("operator must indicate right or left associativity")
+ if pa:
+ matchExpr.setParseAction( pa )
+ thisExpr <<= ( matchExpr.setName(termName) | lastExpr )
+ lastExpr = thisExpr
+ ret <<= lastExpr
+ return ret
+
+operatorPrecedence = infixNotation
+"""(Deprecated) Former name of C{L{infixNotation}}, will be dropped in a future release."""
+
+dblQuotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"').setName("string enclosed in double quotes")
+sglQuotedString = Combine(Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("string enclosed in single quotes")
+quotedString = Combine(Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*')+'"'|
+ Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*")+"'").setName("quotedString using single or double quotes")
+unicodeString = Combine(_L('u') + quotedString.copy()).setName("unicode string literal")
+
+def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
+ """
+ Helper method for defining nested lists enclosed in opening and closing
+ delimiters ("(" and ")" are the default).
+
+ Parameters:
+ - opener - opening character for a nested list (default=C{"("}); can also be a pyparsing expression
+ - closer - closing character for a nested list (default=C{")"}); can also be a pyparsing expression
+ - content - expression for items within the nested lists (default=C{None})
+ - ignoreExpr - expression for ignoring opening and closing delimiters (default=C{quotedString})
+
+ If an expression is not provided for the content argument, the nested
+ expression will capture all whitespace-delimited content between delimiters
+ as a list of separate values.
+
+ Use the C{ignoreExpr} argument to define expressions that may contain
+ opening or closing characters that should not be treated as opening
+ or closing characters for nesting, such as quotedString or a comment
+ expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}.
+ The default is L{quotedString}, but if no expressions are to be ignored,
+ then pass C{None} for this argument.
+
+ Example::
+ data_type = oneOf("void int short long char float double")
+ decl_data_type = Combine(data_type + Optional(Word('*')))
+ ident = Word(alphas+'_', alphanums+'_')
+ number = pyparsing_common.number
+ arg = Group(decl_data_type + ident)
+ LPAR,RPAR = map(Suppress, "()")
+
+ code_body = nestedExpr('{', '}', ignoreExpr=(quotedString | cStyleComment))
+
+ c_function = (decl_data_type("type")
+ + ident("name")
+ + LPAR + Optional(delimitedList(arg), [])("args") + RPAR
+ + code_body("body"))
+ c_function.ignore(cStyleComment)
+
+ source_code = '''
+ int is_odd(int x) {
+ return (x%2);
+ }
+
+ int dec_to_hex(char hchar) {
+ if (hchar >= '0' && hchar <= '9') {
+ return (ord(hchar)-ord('0'));
+ } else {
+ return (10+ord(hchar)-ord('A'));
+ }
+ }
+ '''
+ for func in c_function.searchString(source_code):
+ print("%(name)s (%(type)s) args: %(args)s" % func)
+
+ prints::
+ is_odd (int) args: [['int', 'x']]
+ dec_to_hex (int) args: [['char', 'hchar']]
+ """
+ if opener == closer:
+ raise ValueError("opening and closing strings cannot be the same")
+ if content is None:
+ if isinstance(opener,basestring) and isinstance(closer,basestring):
+ if len(opener) == 1 and len(closer)==1:
+ if ignoreExpr is not None:
+ content = (Combine(OneOrMore(~ignoreExpr +
+ CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1))
+ ).setParseAction(lambda t:t[0].strip()))
+ else:
+ content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS
+ ).setParseAction(lambda t:t[0].strip()))
+ else:
+ if ignoreExpr is not None:
+ content = (Combine(OneOrMore(~ignoreExpr +
+ ~Literal(opener) + ~Literal(closer) +
+ CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
+ ).setParseAction(lambda t:t[0].strip()))
+ else:
+ content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) +
+ CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
+ ).setParseAction(lambda t:t[0].strip()))
+ else:
+ raise ValueError("opening and closing arguments must be strings if no content expression is given")
+ ret = Forward()
+ if ignoreExpr is not None:
+ ret <<= Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) )
+ else:
+ ret <<= Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) )
+ ret.setName('nested %s%s expression' % (opener,closer))
+ return ret
+
+def indentedBlock(blockStatementExpr, indentStack, indent=True):
+ """
+ Helper method for defining space-delimited indentation blocks, such as
+ those used to define block statements in Python source code.
+
+ Parameters:
+ - blockStatementExpr - expression defining syntax of statement that
+ is repeated within the indented block
+ - indentStack - list created by caller to manage indentation stack
+ (multiple statementWithIndentedBlock expressions within a single grammar
+ should share a common indentStack)
+ - indent - boolean indicating whether block must be indented beyond the
+ the current level; set to False for block of left-most statements
+ (default=C{True})
+
+ A valid block must contain at least one C{blockStatement}.
+
+ Example::
+ data = '''
+ def A(z):
+ A1
+ B = 100
+ G = A2
+ A2
+ A3
+ B
+ def BB(a,b,c):
+ BB1
+ def BBA():
+ bba1
+ bba2
+ bba3
+ C
+ D
+ def spam(x,y):
+ def eggs(z):
+ pass
+ '''
+
+
+ indentStack = [1]
+ stmt = Forward()
+
+ identifier = Word(alphas, alphanums)
+ funcDecl = ("def" + identifier + Group( "(" + Optional( delimitedList(identifier) ) + ")" ) + ":")
+ func_body = indentedBlock(stmt, indentStack)
+ funcDef = Group( funcDecl + func_body )
+
+ rvalue = Forward()
+ funcCall = Group(identifier + "(" + Optional(delimitedList(rvalue)) + ")")
+ rvalue << (funcCall | identifier | Word(nums))
+ assignment = Group(identifier + "=" + rvalue)
+ stmt << ( funcDef | assignment | identifier )
+
+ module_body = OneOrMore(stmt)
+
+ parseTree = module_body.parseString(data)
+ parseTree.pprint()
+ prints::
+ [['def',
+ 'A',
+ ['(', 'z', ')'],
+ ':',
+ [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]],
+ 'B',
+ ['def',
+ 'BB',
+ ['(', 'a', 'b', 'c', ')'],
+ ':',
+ [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]],
+ 'C',
+ 'D',
+ ['def',
+ 'spam',
+ ['(', 'x', 'y', ')'],
+ ':',
+ [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]]
+ """
+ def checkPeerIndent(s,l,t):
+ if l >= len(s): return
+ curCol = col(l,s)
+ if curCol != indentStack[-1]:
+ if curCol > indentStack[-1]:
+ raise ParseFatalException(s,l,"illegal nesting")
+ raise ParseException(s,l,"not a peer entry")
+
+ def checkSubIndent(s,l,t):
+ curCol = col(l,s)
+ if curCol > indentStack[-1]:
+ indentStack.append( curCol )
+ else:
+ raise ParseException(s,l,"not a subentry")
+
+ def checkUnindent(s,l,t):
+ if l >= len(s): return
+ curCol = col(l,s)
+ if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]):
+ raise ParseException(s,l,"not an unindent")
+ indentStack.pop()
+
+ NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress())
+ INDENT = (Empty() + Empty().setParseAction(checkSubIndent)).setName('INDENT')
+ PEER = Empty().setParseAction(checkPeerIndent).setName('')
+ UNDENT = Empty().setParseAction(checkUnindent).setName('UNINDENT')
+ if indent:
+ smExpr = Group( Optional(NL) +
+ #~ FollowedBy(blockStatementExpr) +
+ INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT)
+ else:
+ smExpr = Group( Optional(NL) +
+ (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) )
+ blockStatementExpr.ignore(_bslash + LineEnd())
+ return smExpr.setName('indented block')
+
+alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]")
+punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]")
+
+anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:").setName('any tag'))
+_htmlEntityMap = dict(zip("gt lt amp nbsp quot apos".split(),'><& "\''))
+commonHTMLEntity = Regex('&(?P<entity>' + '|'.join(_htmlEntityMap.keys()) +");").setName("common HTML entity")
+def replaceHTMLEntity(t):
+ """Helper parser action to replace common HTML entities with their special characters"""
+ return _htmlEntityMap.get(t.entity)
+
+# it's easy to get these comment structures wrong - they're very common, so may as well make them available
+cStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/').setName("C style comment")
+"Comment of the form C{/* ... */}"
+
+htmlComment = Regex(r"<!--[\s\S]*?-->").setName("HTML comment")
+"Comment of the form C{<!-- ... -->}"
+
+restOfLine = Regex(r".*").leaveWhitespace().setName("rest of line")
+dblSlashComment = Regex(r"//(?:\\\n|[^\n])*").setName("// comment")
+"Comment of the form C{// ... (to end of line)}"
+
+cppStyleComment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + '*/'| dblSlashComment).setName("C++ style comment")
+"Comment of either form C{L{cStyleComment}} or C{L{dblSlashComment}}"
+
+javaStyleComment = cppStyleComment
+"Same as C{L{cppStyleComment}}"
+
+pythonStyleComment = Regex(r"#.*").setName("Python style comment")
+"Comment of the form C{# ... (to end of line)}"
+
+_commasepitem = Combine(OneOrMore(Word(printables, excludeChars=',') +
+ Optional( Word(" \t") +
+ ~Literal(",") + ~LineEnd() ) ) ).streamline().setName("commaItem")
+commaSeparatedList = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("commaSeparatedList")
+"""(Deprecated) Predefined expression of 1 or more printable words or quoted strings, separated by commas.
+ This expression is deprecated in favor of L{pyparsing_common.comma_separated_list}."""
+
+# some other useful expressions - using lower-case class name since we are really using this as a namespace
+class pyparsing_common:
+ """
+ Here are some common low-level expressions that may be useful in jump-starting parser development:
+ - numeric forms (L{integers<integer>}, L{reals<real>}, L{scientific notation<sci_real>})
+ - common L{programming identifiers<identifier>}
+ - network addresses (L{MAC<mac_address>}, L{IPv4<ipv4_address>}, L{IPv6<ipv6_address>})
+ - ISO8601 L{dates<iso8601_date>} and L{datetime<iso8601_datetime>}
+ - L{UUID<uuid>}
+ - L{comma-separated list<comma_separated_list>}
+ Parse actions:
+ - C{L{convertToInteger}}
+ - C{L{convertToFloat}}
+ - C{L{convertToDate}}
+ - C{L{convertToDatetime}}
+ - C{L{stripHTMLTags}}
+ - C{L{upcaseTokens}}
+ - C{L{downcaseTokens}}
+
+ Example::
+ pyparsing_common.number.runTests('''
+ # any int or real number, returned as the appropriate type
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.fnumber.runTests('''
+ # any int or real number, returned as float
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ ''')
+
+ pyparsing_common.hex_integer.runTests('''
+ # hex numbers
+ 100
+ FF
+ ''')
+
+ pyparsing_common.fraction.runTests('''
+ # fractions
+ 1/2
+ -3/4
+ ''')
+
+ pyparsing_common.mixed_integer.runTests('''
+ # mixed fractions
+ 1
+ 1/2
+ -3/4
+ 1-3/4
+ ''')
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests('''
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ ''')
+ prints::
+ # any int or real number, returned as the appropriate type
+ 100
+ [100]
+
+ -100
+ [-100]
+
+ +100
+ [100]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # any int or real number, returned as float
+ 100
+ [100.0]
+
+ -100
+ [-100.0]
+
+ +100
+ [100.0]
+
+ 3.14159
+ [3.14159]
+
+ 6.02e23
+ [6.02e+23]
+
+ 1e-12
+ [1e-12]
+
+ # hex numbers
+ 100
+ [256]
+
+ FF
+ [255]
+
+ # fractions
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ # mixed fractions
+ 1
+ [1]
+
+ 1/2
+ [0.5]
+
+ -3/4
+ [-0.75]
+
+ 1-3/4
+ [1.75]
+
+ # uuid
+ 12345678-1234-5678-1234-567812345678
+ [UUID('12345678-1234-5678-1234-567812345678')]
+ """
+
+ convertToInteger = tokenMap(int)
+ """
+ Parse action for converting parsed integers to Python int
+ """
+
+ convertToFloat = tokenMap(float)
+ """
+ Parse action for converting parsed numbers to Python float
+ """
+
+ integer = Word(nums).setName("integer").setParseAction(convertToInteger)
+ """expression that parses an unsigned integer, returns an int"""
+
+ hex_integer = Word(hexnums).setName("hex integer").setParseAction(tokenMap(int,16))
+ """expression that parses a hexadecimal integer, returns an int"""
+
+ signed_integer = Regex(r'[+-]?\d+').setName("signed integer").setParseAction(convertToInteger)
+ """expression that parses an integer with optional leading sign, returns an int"""
+
+ fraction = (signed_integer().setParseAction(convertToFloat) + '/' + signed_integer().setParseAction(convertToFloat)).setName("fraction")
+ """fractional expression of an integer divided by an integer, returns a float"""
+ fraction.addParseAction(lambda t: t[0]/t[-1])
+
+ mixed_integer = (fraction | signed_integer + Optional(Optional('-').suppress() + fraction)).setName("fraction or mixed integer-fraction")
+ """mixed integer of the form 'integer - fraction', with optional leading integer, returns float"""
+ mixed_integer.addParseAction(sum)
+
+ real = Regex(r'[+-]?\d+\.\d*').setName("real number").setParseAction(convertToFloat)
+ """expression that parses a floating point number and returns a float"""
+
+ sci_real = Regex(r'[+-]?\d+([eE][+-]?\d+|\.\d*([eE][+-]?\d+)?)').setName("real number with scientific notation").setParseAction(convertToFloat)
+ """expression that parses a floating point number with optional scientific notation and returns a float"""
+
+ # streamlining this expression makes the docs nicer-looking
+ number = (sci_real | real | signed_integer).streamline()
+ """any numeric expression, returns the corresponding Python type"""
+
+ fnumber = Regex(r'[+-]?\d+\.?\d*([eE][+-]?\d+)?').setName("fnumber").setParseAction(convertToFloat)
+ """any int or real number, returned as float"""
+
+ identifier = Word(alphas+'_', alphanums+'_').setName("identifier")
+ """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')"""
+
+ ipv4_address = Regex(r'(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}').setName("IPv4 address")
+ "IPv4 address (C{0.0.0.0 - 255.255.255.255})"
+
+ _ipv6_part = Regex(r'[0-9a-fA-F]{1,4}').setName("hex_integer")
+ _full_ipv6_address = (_ipv6_part + (':' + _ipv6_part)*7).setName("full IPv6 address")
+ _short_ipv6_address = (Optional(_ipv6_part + (':' + _ipv6_part)*(0,6)) + "::" + Optional(_ipv6_part + (':' + _ipv6_part)*(0,6))).setName("short IPv6 address")
+ _short_ipv6_address.addCondition(lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8)
+ _mixed_ipv6_address = ("::ffff:" + ipv4_address).setName("mixed IPv6 address")
+ ipv6_address = Combine((_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).setName("IPv6 address")).setName("IPv6 address")
+ "IPv6 address (long, short, or mixed form)"
+
+ mac_address = Regex(r'[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}').setName("MAC address")
+ "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)"
+
+ @staticmethod
+ def convertToDate(fmt="%Y-%m-%d"):
+ """
+ Helper to create a parse action for converting parsed date string to Python datetime.date
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%d"})
+
+ Example::
+ date_expr = pyparsing_common.iso8601_date.copy()
+ date_expr.setParseAction(pyparsing_common.convertToDate())
+ print(date_expr.parseString("1999-12-31"))
+ prints::
+ [datetime.date(1999, 12, 31)]
+ """
+ def cvt_fn(s,l,t):
+ try:
+ return datetime.strptime(t[0], fmt).date()
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ @staticmethod
+ def convertToDatetime(fmt="%Y-%m-%dT%H:%M:%S.%f"):
+ """
+ Helper to create a parse action for converting parsed datetime string to Python datetime.datetime
+
+ Params -
+ - fmt - format to be passed to datetime.strptime (default=C{"%Y-%m-%dT%H:%M:%S.%f"})
+
+ Example::
+ dt_expr = pyparsing_common.iso8601_datetime.copy()
+ dt_expr.setParseAction(pyparsing_common.convertToDatetime())
+ print(dt_expr.parseString("1999-12-31T23:59:59.999"))
+ prints::
+ [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)]
+ """
+ def cvt_fn(s,l,t):
+ try:
+ return datetime.strptime(t[0], fmt)
+ except ValueError as ve:
+ raise ParseException(s, l, str(ve))
+ return cvt_fn
+
+ iso8601_date = Regex(r'(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?').setName("ISO8601 date")
+ "ISO8601 date (C{yyyy-mm-dd})"
+
+ iso8601_datetime = Regex(r'(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?').setName("ISO8601 datetime")
+ "ISO8601 datetime (C{yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)}) - trailing seconds, milliseconds, and timezone optional; accepts separating C{'T'} or C{' '}"
+
+ uuid = Regex(r'[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}').setName("UUID")
+ "UUID (C{xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx})"
+
+ _html_stripper = anyOpenTag.suppress() | anyCloseTag.suppress()
+ @staticmethod
+ def stripHTMLTags(s, l, tokens):
+ """
+ Parse action to remove HTML tags from web page HTML source
+
+ Example::
+ # strip HTML links from normal text
+ text = '<td>More info at the <a href="http://pyparsing.wikispaces.com">pyparsing</a> wiki page</td>'
+ td,td_end = makeHTMLTags("TD")
+ table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end
+
+ print(table_text.parseString(text).body) # -> 'More info at the pyparsing wiki page'
+ """
+ return pyparsing_common._html_stripper.transformString(tokens[0])
+
+ _commasepitem = Combine(OneOrMore(~Literal(",") + ~LineEnd() + Word(printables, excludeChars=',')
+ + Optional( White(" \t") ) ) ).streamline().setName("commaItem")
+ comma_separated_list = delimitedList( Optional( quotedString.copy() | _commasepitem, default="") ).setName("comma separated list")
+ """Predefined expression of 1 or more printable words or quoted strings, separated by commas."""
+
+ upcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).upper()))
+ """Parse action to convert tokens to upper case."""
+
+ downcaseTokens = staticmethod(tokenMap(lambda t: _ustr(t).lower()))
+ """Parse action to convert tokens to lower case."""
+
+
+if __name__ == "__main__":
+
+ selectToken = CaselessLiteral("select")
+ fromToken = CaselessLiteral("from")
+
+ ident = Word(alphas, alphanums + "_$")
+
+ columnName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ columnNameList = Group(delimitedList(columnName)).setName("columns")
+ columnSpec = ('*' | columnNameList)
+
+ tableName = delimitedList(ident, ".", combine=True).setParseAction(upcaseTokens)
+ tableNameList = Group(delimitedList(tableName)).setName("tables")
+
+ simpleSQL = selectToken("command") + columnSpec("columns") + fromToken + tableNameList("tables")
+
+ # demo runTests method, including embedded comments in test string
+ simpleSQL.runTests("""
+ # '*' as column list and dotted table name
+ select * from SYS.XYZZY
+
+ # caseless match on "SELECT", and casts back to "select"
+ SELECT * from XYZZY, ABC
+
+ # list of column names, and mixed case SELECT keyword
+ Select AA,BB,CC from Sys.dual
+
+ # multiple tables
+ Select A, B, C from Sys.dual, Table2
+
+ # invalid SELECT keyword - should fail
+ Xelect A, B, C from Sys.dual
+
+ # incomplete command - should fail
+ Select
+
+ # invalid column name - should fail
+ Select ^^^ frox Sys.dual
+
+ """)
+
+ pyparsing_common.number.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ # any int or real number, returned as float
+ pyparsing_common.fnumber.runTests("""
+ 100
+ -100
+ +100
+ 3.14159
+ 6.02e23
+ 1e-12
+ """)
+
+ pyparsing_common.hex_integer.runTests("""
+ 100
+ FF
+ """)
+
+ import uuid
+ pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID))
+ pyparsing_common.uuid.runTests("""
+ 12345678-1234-5678-1234-567812345678
+ """)
diff --git a/recipes/pkgresources/pkgr/_vendor/six.py b/recipes/pkgresources/pkgr/_vendor/six.py
new file mode 100644
index 0000000..190c023
--- /dev/null
+++ b/recipes/pkgresources/pkgr/_vendor/six.py
@@ -0,0 +1,868 @@
+"""Utilities for writing code that runs on Python 2 and 3"""
+
+# Copyright (c) 2010-2015 Benjamin Peterson
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+from __future__ import absolute_import
+
+import functools
+import itertools
+import operator
+import sys
+import types
+
+__author__ = "Benjamin Peterson <benjamin@python.org>"
+__version__ = "1.10.0"
+
+
+# Useful for very coarse version differentiation.
+PY2 = sys.version_info[0] == 2
+PY3 = sys.version_info[0] == 3
+PY34 = sys.version_info[0:2] >= (3, 4)
+
+if PY3:
+ string_types = str,
+ integer_types = int,
+ class_types = type,
+ text_type = str
+ binary_type = bytes
+
+ MAXSIZE = sys.maxsize
+else:
+ string_types = basestring,
+ integer_types = (int, long)
+ class_types = (type, types.ClassType)
+ text_type = unicode
+ binary_type = str
+
+ if sys.platform.startswith("java"):
+ # Jython always uses 32 bits.
+ MAXSIZE = int((1 << 31) - 1)
+ else:
+ # It's possible to have sizeof(long) != sizeof(Py_ssize_t).
+ class X(object):
+
+ def __len__(self):
+ return 1 << 31
+ try:
+ len(X())
+ except OverflowError:
+ # 32-bit
+ MAXSIZE = int((1 << 31) - 1)
+ else:
+ # 64-bit
+ MAXSIZE = int((1 << 63) - 1)
+ del X
+
+
+def _add_doc(func, doc):
+ """Add documentation to a function."""
+ func.__doc__ = doc
+
+
+def _import_module(name):
+ """Import module, returning the module after the last dot."""
+ __import__(name)
+ return sys.modules[name]
+
+
+class _LazyDescr(object):
+
+ def __init__(self, name):
+ self.name = name
+
+ def __get__(self, obj, tp):
+ result = self._resolve()
+ setattr(obj, self.name, result) # Invokes __set__.
+ try:
+ # This is a bit ugly, but it avoids running this again by
+ # removing this descriptor.
+ delattr(obj.__class__, self.name)
+ except AttributeError:
+ pass
+ return result
+
+
+class MovedModule(_LazyDescr):
+
+ def __init__(self, name, old, new=None):
+ super(MovedModule, self).__init__(name)
+ if PY3:
+ if new is None:
+ new = name
+ self.mod = new
+ else:
+ self.mod = old
+
+ def _resolve(self):
+ return _import_module(self.mod)
+
+ def __getattr__(self, attr):
+ _module = self._resolve()
+ value = getattr(_module, attr)
+ setattr(self, attr, value)
+ return value
+
+
+class _LazyModule(types.ModuleType):
+
+ def __init__(self, name):
+ super(_LazyModule, self).__init__(name)
+ self.__doc__ = self.__class__.__doc__
+
+ def __dir__(self):
+ attrs = ["__doc__", "__name__"]
+ attrs += [attr.name for attr in self._moved_attributes]
+ return attrs
+
+ # Subclasses should override this
+ _moved_attributes = []
+
+
+class MovedAttribute(_LazyDescr):
+
+ def __init__(self, name, old_mod, new_mod, old_attr=None, new_attr=None):
+ super(MovedAttribute, self).__init__(name)
+ if PY3:
+ if new_mod is None:
+ new_mod = name
+ self.mod = new_mod
+ if new_attr is None:
+ if old_attr is None:
+ new_attr = name
+ else:
+ new_attr = old_attr
+ self.attr = new_attr
+ else:
+ self.mod = old_mod
+ if old_attr is None:
+ old_attr = name
+ self.attr = old_attr
+
+ def _resolve(self):
+ module = _import_module(self.mod)
+ return getattr(module, self.attr)
+
+
+class _SixMetaPathImporter(object):
+
+ """
+ A meta path importer to import six.moves and its submodules.
+
+ This class implements a PEP302 finder and loader. It should be compatible
+ with Python 2.5 and all existing versions of Python3
+ """
+
+ def __init__(self, six_module_name):
+ self.name = six_module_name
+ self.known_modules = {}
+
+ def _add_module(self, mod, *fullnames):
+ for fullname in fullnames:
+ self.known_modules[self.name + "." + fullname] = mod
+
+ def _get_module(self, fullname):
+ return self.known_modules[self.name + "." + fullname]
+
+ def find_module(self, fullname, path=None):
+ if fullname in self.known_modules:
+ return self
+ return None
+
+ def __get_module(self, fullname):
+ try:
+ return self.known_modules[fullname]
+ except KeyError:
+ raise ImportError("This loader does not know module " + fullname)
+
+ def load_module(self, fullname):
+ try:
+ # in case of a reload
+ return sys.modules[fullname]
+ except KeyError:
+ pass
+ mod = self.__get_module(fullname)
+ if isinstance(mod, MovedModule):
+ mod = mod._resolve()
+ else:
+ mod.__loader__ = self
+ sys.modules[fullname] = mod
+ return mod
+
+ def is_package(self, fullname):
+ """
+ Return true, if the named module is a package.
+
+ We need this method to get correct spec objects with
+ Python 3.4 (see PEP451)
+ """
+ return hasattr(self.__get_module(fullname), "__path__")
+
+ def get_code(self, fullname):
+ """Return None
+
+ Required, if is_package is implemented"""
+ self.__get_module(fullname) # eventually raises ImportError
+ return None
+ get_source = get_code # same as get_code
+
+_importer = _SixMetaPathImporter(__name__)
+
+
+class _MovedItems(_LazyModule):
+
+ """Lazy loading of moved objects"""
+ __path__ = [] # mark as package
+
+
+_moved_attributes = [
+ MovedAttribute("cStringIO", "cStringIO", "io", "StringIO"),
+ MovedAttribute("filter", "itertools", "builtins", "ifilter", "filter"),
+ MovedAttribute("filterfalse", "itertools", "itertools", "ifilterfalse", "filterfalse"),
+ MovedAttribute("input", "__builtin__", "builtins", "raw_input", "input"),
+ MovedAttribute("intern", "__builtin__", "sys"),
+ MovedAttribute("map", "itertools", "builtins", "imap", "map"),
+ MovedAttribute("getcwd", "os", "os", "getcwdu", "getcwd"),
+ MovedAttribute("getcwdb", "os", "os", "getcwd", "getcwdb"),
+ MovedAttribute("range", "__builtin__", "builtins", "xrange", "range"),
+ MovedAttribute("reload_module", "__builtin__", "importlib" if PY34 else "imp", "reload"),
+ MovedAttribute("reduce", "__builtin__", "functools"),
+ MovedAttribute("shlex_quote", "pipes", "shlex", "quote"),
+ MovedAttribute("StringIO", "StringIO", "io"),
+ MovedAttribute("UserDict", "UserDict", "collections"),
+ MovedAttribute("UserList", "UserList", "collections"),
+ MovedAttribute("UserString", "UserString", "collections"),
+ MovedAttribute("xrange", "__builtin__", "builtins", "xrange", "range"),
+ MovedAttribute("zip", "itertools", "builtins", "izip", "zip"),
+ MovedAttribute("zip_longest", "itertools", "itertools", "izip_longest", "zip_longest"),
+ MovedModule("builtins", "__builtin__"),
+ MovedModule("configparser", "ConfigParser"),
+ MovedModule("copyreg", "copy_reg"),
+ MovedModule("dbm_gnu", "gdbm", "dbm.gnu"),
+ MovedModule("_dummy_thread", "dummy_thread", "_dummy_thread"),
+ MovedModule("http_cookiejar", "cookielib", "http.cookiejar"),
+ MovedModule("http_cookies", "Cookie", "http.cookies"),
+ MovedModule("html_entities", "htmlentitydefs", "html.entities"),
+ MovedModule("html_parser", "HTMLParser", "html.parser"),
+ MovedModule("http_client", "httplib", "http.client"),
+ MovedModule("email_mime_multipart", "email.MIMEMultipart", "email.mime.multipart"),
+ MovedModule("email_mime_nonmultipart", "email.MIMENonMultipart", "email.mime.nonmultipart"),
+ MovedModule("email_mime_text", "email.MIMEText", "email.mime.text"),
+ MovedModule("email_mime_base", "email.MIMEBase", "email.mime.base"),
+ MovedModule("BaseHTTPServer", "BaseHTTPServer", "http.server"),
+ MovedModule("CGIHTTPServer", "CGIHTTPServer", "http.server"),
+ MovedModule("SimpleHTTPServer", "SimpleHTTPServer", "http.server"),
+ MovedModule("cPickle", "cPickle", "pickle"),
+ MovedModule("queue", "Queue"),
+ MovedModule("reprlib", "repr"),
+ MovedModule("socketserver", "SocketServer"),
+ MovedModule("_thread", "thread", "_thread"),
+ MovedModule("tkinter", "Tkinter"),
+ MovedModule("tkinter_dialog", "Dialog", "tkinter.dialog"),
+ MovedModule("tkinter_filedialog", "FileDialog", "tkinter.filedialog"),
+ MovedModule("tkinter_scrolledtext", "ScrolledText", "tkinter.scrolledtext"),
+ MovedModule("tkinter_simpledialog", "SimpleDialog", "tkinter.simpledialog"),
+ MovedModule("tkinter_tix", "Tix", "tkinter.tix"),
+ MovedModule("tkinter_ttk", "ttk", "tkinter.ttk"),
+ MovedModule("tkinter_constants", "Tkconstants", "tkinter.constants"),
+ MovedModule("tkinter_dnd", "Tkdnd", "tkinter.dnd"),
+ MovedModule("tkinter_colorchooser", "tkColorChooser",
+ "tkinter.colorchooser"),
+ MovedModule("tkinter_commondialog", "tkCommonDialog",
+ "tkinter.commondialog"),
+ MovedModule("tkinter_tkfiledialog", "tkFileDialog", "tkinter.filedialog"),
+ MovedModule("tkinter_font", "tkFont", "tkinter.font"),
+ MovedModule("tkinter_messagebox", "tkMessageBox", "tkinter.messagebox"),
+ MovedModule("tkinter_tksimpledialog", "tkSimpleDialog",
+ "tkinter.simpledialog"),
+ MovedModule("urllib_parse", __name__ + ".moves.urllib_parse", "urllib.parse"),
+ MovedModule("urllib_error", __name__ + ".moves.urllib_error", "urllib.error"),
+ MovedModule("urllib", __name__ + ".moves.urllib", __name__ + ".moves.urllib"),
+ MovedModule("urllib_robotparser", "robotparser", "urllib.robotparser"),
+ MovedModule("xmlrpc_client", "xmlrpclib", "xmlrpc.client"),
+ MovedModule("xmlrpc_server", "SimpleXMLRPCServer", "xmlrpc.server"),
+]
+# Add windows specific modules.
+if sys.platform == "win32":
+ _moved_attributes += [
+ MovedModule("winreg", "_winreg"),
+ ]
+
+for attr in _moved_attributes:
+ setattr(_MovedItems, attr.name, attr)
+ if isinstance(attr, MovedModule):
+ _importer._add_module(attr, "moves." + attr.name)
+del attr
+
+_MovedItems._moved_attributes = _moved_attributes
+
+moves = _MovedItems(__name__ + ".moves")
+_importer._add_module(moves, "moves")
+
+
+class Module_six_moves_urllib_parse(_LazyModule):
+
+ """Lazy loading of moved objects in six.moves.urllib_parse"""
+
+
+_urllib_parse_moved_attributes = [
+ MovedAttribute("ParseResult", "urlparse", "urllib.parse"),
+ MovedAttribute("SplitResult", "urlparse", "urllib.parse"),
+ MovedAttribute("parse_qs", "urlparse", "urllib.parse"),
+ MovedAttribute("parse_qsl", "urlparse", "urllib.parse"),
+ MovedAttribute("urldefrag", "urlparse", "urllib.parse"),
+ MovedAttribute("urljoin", "urlparse", "urllib.parse"),
+ MovedAttribute("urlparse", "urlparse", "urllib.parse"),
+ MovedAttribute("urlsplit", "urlparse", "urllib.parse"),
+ MovedAttribute("urlunparse", "urlparse", "urllib.parse"),
+ MovedAttribute("urlunsplit", "urlparse", "urllib.parse"),
+ MovedAttribute("quote", "urllib", "urllib.parse"),
+ MovedAttribute("quote_plus", "urllib", "urllib.parse"),
+ MovedAttribute("unquote", "urllib", "urllib.parse"),
+ MovedAttribute("unquote_plus", "urllib", "urllib.parse"),
+ MovedAttribute("urlencode", "urllib", "urllib.parse"),
+ MovedAttribute("splitquery", "urllib", "urllib.parse"),
+ MovedAttribute("splittag", "urllib", "urllib.parse"),
+ MovedAttribute("splituser", "urllib", "urllib.parse"),
+ MovedAttribute("uses_fragment", "urlparse", "urllib.parse"),
+ MovedAttribute("uses_netloc", "urlparse", "urllib.parse"),
+ MovedAttribute("uses_params", "urlparse", "urllib.parse"),
+ MovedAttribute("uses_query", "urlparse", "urllib.parse"),
+ MovedAttribute("uses_relative", "urlparse", "urllib.parse"),
+]
+for attr in _urllib_parse_moved_attributes:
+ setattr(Module_six_moves_urllib_parse, attr.name, attr)
+del attr
+
+Module_six_moves_urllib_parse._moved_attributes = _urllib_parse_moved_attributes
+
+_importer._add_module(Module_six_moves_urllib_parse(__name__ + ".moves.urllib_parse"),
+ "moves.urllib_parse", "moves.urllib.parse")
+
+
+class Module_six_moves_urllib_error(_LazyModule):
+
+ """Lazy loading of moved objects in six.moves.urllib_error"""
+
+
+_urllib_error_moved_attributes = [
+ MovedAttribute("URLError", "urllib2", "urllib.error"),
+ MovedAttribute("HTTPError", "urllib2", "urllib.error"),
+ MovedAttribute("ContentTooShortError", "urllib", "urllib.error"),
+]
+for attr in _urllib_error_moved_attributes:
+ setattr(Module_six_moves_urllib_error, attr.name, attr)
+del attr
+
+Module_six_moves_urllib_error._moved_attributes = _urllib_error_moved_attributes
+
+_importer._add_module(Module_six_moves_urllib_error(__name__ + ".moves.urllib.error"),
+ "moves.urllib_error", "moves.urllib.error")
+
+
+class Module_six_moves_urllib_request(_LazyModule):
+
+ """Lazy loading of moved objects in six.moves.urllib_request"""
+
+
+_urllib_request_moved_attributes = [
+ MovedAttribute("urlopen", "urllib2", "urllib.request"),
+ MovedAttribute("install_opener", "urllib2", "urllib.request"),
+ MovedAttribute("build_opener", "urllib2", "urllib.request"),
+ MovedAttribute("pathname2url", "urllib", "urllib.request"),
+ MovedAttribute("url2pathname", "urllib", "urllib.request"),
+ MovedAttribute("getproxies", "urllib", "urllib.request"),
+ MovedAttribute("Request", "urllib2", "urllib.request"),
+ MovedAttribute("OpenerDirector", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPDefaultErrorHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPRedirectHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPCookieProcessor", "urllib2", "urllib.request"),
+ MovedAttribute("ProxyHandler", "urllib2", "urllib.request"),
+ MovedAttribute("BaseHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPPasswordMgr", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPPasswordMgrWithDefaultRealm", "urllib2", "urllib.request"),
+ MovedAttribute("AbstractBasicAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPBasicAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("ProxyBasicAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("AbstractDigestAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPDigestAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("ProxyDigestAuthHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPSHandler", "urllib2", "urllib.request"),
+ MovedAttribute("FileHandler", "urllib2", "urllib.request"),
+ MovedAttribute("FTPHandler", "urllib2", "urllib.request"),
+ MovedAttribute("CacheFTPHandler", "urllib2", "urllib.request"),
+ MovedAttribute("UnknownHandler", "urllib2", "urllib.request"),
+ MovedAttribute("HTTPErrorProcessor", "urllib2", "urllib.request"),
+ MovedAttribute("urlretrieve", "urllib", "urllib.request"),
+ MovedAttribute("urlcleanup", "urllib", "urllib.request"),
+ MovedAttribute("URLopener", "urllib", "urllib.request"),
+ MovedAttribute("FancyURLopener", "urllib", "urllib.request"),
+ MovedAttribute("proxy_bypass", "urllib", "urllib.request"),
+]
+for attr in _urllib_request_moved_attributes:
+ setattr(Module_six_moves_urllib_request, attr.name, attr)
+del attr
+
+Module_six_moves_urllib_request._moved_attributes = _urllib_request_moved_attributes
+
+_importer._add_module(Module_six_moves_urllib_request(__name__ + ".moves.urllib.request"),
+ "moves.urllib_request", "moves.urllib.request")
+
+
+class Module_six_moves_urllib_response(_LazyModule):
+
+ """Lazy loading of moved objects in six.moves.urllib_response"""
+
+
+_urllib_response_moved_attributes = [
+ MovedAttribute("addbase", "urllib", "urllib.response"),
+ MovedAttribute("addclosehook", "urllib", "urllib.response"),
+ MovedAttribute("addinfo", "urllib", "urllib.response"),
+ MovedAttribute("addinfourl", "urllib", "urllib.response"),
+]
+for attr in _urllib_response_moved_attributes:
+ setattr(Module_six_moves_urllib_response, attr.name, attr)
+del attr
+
+Module_six_moves_urllib_response._moved_attributes = _urllib_response_moved_attributes
+
+_importer._add_module(Module_six_moves_urllib_response(__name__ + ".moves.urllib.response"),
+ "moves.urllib_response", "moves.urllib.response")
+
+
+class Module_six_moves_urllib_robotparser(_LazyModule):
+
+ """Lazy loading of moved objects in six.moves.urllib_robotparser"""
+
+
+_urllib_robotparser_moved_attributes = [
+ MovedAttribute("RobotFileParser", "robotparser", "urllib.robotparser"),
+]
+for attr in _urllib_robotparser_moved_attributes:
+ setattr(Module_six_moves_urllib_robotparser, attr.name, attr)
+del attr
+
+Module_six_moves_urllib_robotparser._moved_attributes = _urllib_robotparser_moved_attributes
+
+_importer._add_module(Module_six_moves_urllib_robotparser(__name__ + ".moves.urllib.robotparser"),
+ "moves.urllib_robotparser", "moves.urllib.robotparser")
+
+
+class Module_six_moves_urllib(types.ModuleType):
+
+ """Create a six.moves.urllib namespace that resembles the Python 3 namespace"""
+ __path__ = [] # mark as package
+ parse = _importer._get_module("moves.urllib_parse")
+ error = _importer._get_module("moves.urllib_error")
+ request = _importer._get_module("moves.urllib_request")
+ response = _importer._get_module("moves.urllib_response")
+ robotparser = _importer._get_module("moves.urllib_robotparser")
+
+ def __dir__(self):
+ return ['parse', 'error', 'request', 'response', 'robotparser']
+
+_importer._add_module(Module_six_moves_urllib(__name__ + ".moves.urllib"),
+ "moves.urllib")
+
+
+def add_move(move):
+ """Add an item to six.moves."""
+ setattr(_MovedItems, move.name, move)
+
+
+def remove_move(name):
+ """Remove item from six.moves."""
+ try:
+ delattr(_MovedItems, name)
+ except AttributeError:
+ try:
+ del moves.__dict__[name]
+ except KeyError:
+ raise AttributeError("no such move, %r" % (name,))
+
+
+if PY3:
+ _meth_func = "__func__"
+ _meth_self = "__self__"
+
+ _func_closure = "__closure__"
+ _func_code = "__code__"
+ _func_defaults = "__defaults__"
+ _func_globals = "__globals__"
+else:
+ _meth_func = "im_func"
+ _meth_self = "im_self"
+
+ _func_closure = "func_closure"
+ _func_code = "func_code"
+ _func_defaults = "func_defaults"
+ _func_globals = "func_globals"
+
+
+try:
+ advance_iterator = next
+except NameError:
+ def advance_iterator(it):
+ return it.next()
+next = advance_iterator
+
+
+try:
+ callable = callable
+except NameError:
+ def callable(obj):
+ return any("__call__" in klass.__dict__ for klass in type(obj).__mro__)
+
+
+if PY3:
+ def get_unbound_function(unbound):
+ return unbound
+
+ create_bound_method = types.MethodType
+
+ def create_unbound_method(func, cls):
+ return func
+
+ Iterator = object
+else:
+ def get_unbound_function(unbound):
+ return unbound.im_func
+
+ def create_bound_method(func, obj):
+ return types.MethodType(func, obj, obj.__class__)
+
+ def create_unbound_method(func, cls):
+ return types.MethodType(func, None, cls)
+
+ class Iterator(object):
+
+ def next(self):
+ return type(self).__next__(self)
+
+ callable = callable
+_add_doc(get_unbound_function,
+ """Get the function out of a possibly unbound function""")
+
+
+get_method_function = operator.attrgetter(_meth_func)
+get_method_self = operator.attrgetter(_meth_self)
+get_function_closure = operator.attrgetter(_func_closure)
+get_function_code = operator.attrgetter(_func_code)
+get_function_defaults = operator.attrgetter(_func_defaults)
+get_function_globals = operator.attrgetter(_func_globals)
+
+
+if PY3:
+ def iterkeys(d, **kw):
+ return iter(d.keys(**kw))
+
+ def itervalues(d, **kw):
+ return iter(d.values(**kw))
+
+ def iteritems(d, **kw):
+ return iter(d.items(**kw))
+
+ def iterlists(d, **kw):
+ return iter(d.lists(**kw))
+
+ viewkeys = operator.methodcaller("keys")
+
+ viewvalues = operator.methodcaller("values")
+
+ viewitems = operator.methodcaller("items")
+else:
+ def iterkeys(d, **kw):
+ return d.iterkeys(**kw)
+
+ def itervalues(d, **kw):
+ return d.itervalues(**kw)
+
+ def iteritems(d, **kw):
+ return d.iteritems(**kw)
+
+ def iterlists(d, **kw):
+ return d.iterlists(**kw)
+
+ viewkeys = operator.methodcaller("viewkeys")
+
+ viewvalues = operator.methodcaller("viewvalues")
+
+ viewitems = operator.methodcaller("viewitems")
+
+_add_doc(iterkeys, "Return an iterator over the keys of a dictionary.")
+_add_doc(itervalues, "Return an iterator over the values of a dictionary.")
+_add_doc(iteritems,
+ "Return an iterator over the (key, value) pairs of a dictionary.")
+_add_doc(iterlists,
+ "Return an iterator over the (key, [values]) pairs of a dictionary.")
+
+
+if PY3:
+ def b(s):
+ return s.encode("latin-1")
+
+ def u(s):
+ return s
+ unichr = chr
+ import struct
+ int2byte = struct.Struct(">B").pack
+ del struct
+ byte2int = operator.itemgetter(0)
+ indexbytes = operator.getitem
+ iterbytes = iter
+ import io
+ StringIO = io.StringIO
+ BytesIO = io.BytesIO
+ _assertCountEqual = "assertCountEqual"
+ if sys.version_info[1] <= 1:
+ _assertRaisesRegex = "assertRaisesRegexp"
+ _assertRegex = "assertRegexpMatches"
+ else:
+ _assertRaisesRegex = "assertRaisesRegex"
+ _assertRegex = "assertRegex"
+else:
+ def b(s):
+ return s
+ # Workaround for standalone backslash
+
+ def u(s):
+ return unicode(s.replace(r'\\', r'\\\\'), "unicode_escape")
+ unichr = unichr
+ int2byte = chr
+
+ def byte2int(bs):
+ return ord(bs[0])
+
+ def indexbytes(buf, i):
+ return ord(buf[i])
+ iterbytes = functools.partial(itertools.imap, ord)
+ import StringIO
+ StringIO = BytesIO = StringIO.StringIO
+ _assertCountEqual = "assertItemsEqual"
+ _assertRaisesRegex = "assertRaisesRegexp"
+ _assertRegex = "assertRegexpMatches"
+_add_doc(b, """Byte literal""")
+_add_doc(u, """Text literal""")
+
+
+def assertCountEqual(self, *args, **kwargs):
+ return getattr(self, _assertCountEqual)(*args, **kwargs)
+
+
+def assertRaisesRegex(self, *args, **kwargs):
+ return getattr(self, _assertRaisesRegex)(*args, **kwargs)
+
+
+def assertRegex(self, *args, **kwargs):
+ return getattr(self, _assertRegex)(*args, **kwargs)
+
+
+if PY3:
+ exec_ = getattr(moves.builtins, "exec")
+
+ def reraise(tp, value, tb=None):
+ if value is None:
+ value = tp()
+ if value.__traceback__ is not tb:
+ raise value.with_traceback(tb)
+ raise value
+
+else:
+ def exec_(_code_, _globs_=None, _locs_=None):
+ """Execute code in a namespace."""
+ if _globs_ is None:
+ frame = sys._getframe(1)
+ _globs_ = frame.f_globals
+ if _locs_ is None:
+ _locs_ = frame.f_locals
+ del frame
+ elif _locs_ is None:
+ _locs_ = _globs_
+ exec("""exec _code_ in _globs_, _locs_""")
+
+ exec_("""def reraise(tp, value, tb=None):
+ raise tp, value, tb
+""")
+
+
+if sys.version_info[:2] == (3, 2):
+ exec_("""def raise_from(value, from_value):
+ if from_value is None:
+ raise value
+ raise value from from_value
+""")
+elif sys.version_info[:2] > (3, 2):
+ exec_("""def raise_from(value, from_value):
+ raise value from from_value
+""")
+else:
+ def raise_from(value, from_value):
+ raise value
+
+
+print_ = getattr(moves.builtins, "print", None)
+if print_ is None:
+ def print_(*args, **kwargs):
+ """The new-style print function for Python 2.4 and 2.5."""
+ fp = kwargs.pop("file", sys.stdout)
+ if fp is None:
+ return
+
+ def write(data):
+ if not isinstance(data, basestring):
+ data = str(data)
+ # If the file has an encoding, encode unicode with it.
+ if (isinstance(fp, file) and
+ isinstance(data, unicode) and
+ fp.encoding is not None):
+ errors = getattr(fp, "errors", None)
+ if errors is None:
+ errors = "strict"
+ data = data.encode(fp.encoding, errors)
+ fp.write(data)
+ want_unicode = False
+ sep = kwargs.pop("sep", None)
+ if sep is not None:
+ if isinstance(sep, unicode):
+ want_unicode = True
+ elif not isinstance(sep, str):
+ raise TypeError("sep must be None or a string")
+ end = kwargs.pop("end", None)
+ if end is not None:
+ if isinstance(end, unicode):
+ want_unicode = True
+ elif not isinstance(end, str):
+ raise TypeError("end must be None or a string")
+ if kwargs:
+ raise TypeError("invalid keyword arguments to print()")
+ if not want_unicode:
+ for arg in args:
+ if isinstance(arg, unicode):
+ want_unicode = True
+ break
+ if want_unicode:
+ newline = unicode("\n")
+ space = unicode(" ")
+ else:
+ newline = "\n"
+ space = " "
+ if sep is None:
+ sep = space
+ if end is None:
+ end = newline
+ for i, arg in enumerate(args):
+ if i:
+ write(sep)
+ write(arg)
+ write(end)
+if sys.version_info[:2] < (3, 3):
+ _print = print_
+
+ def print_(*args, **kwargs):
+ fp = kwargs.get("file", sys.stdout)
+ flush = kwargs.pop("flush", False)
+ _print(*args, **kwargs)
+ if flush and fp is not None:
+ fp.flush()
+
+_add_doc(reraise, """Reraise an exception.""")
+
+if sys.version_info[0:2] < (3, 4):
+ def wraps(wrapped, assigned=functools.WRAPPER_ASSIGNMENTS,
+ updated=functools.WRAPPER_UPDATES):
+ def wrapper(f):
+ f = functools.wraps(wrapped, assigned, updated)(f)
+ f.__wrapped__ = wrapped
+ return f
+ return wrapper
+else:
+ wraps = functools.wraps
+
+
+def with_metaclass(meta, *bases):
+ """Create a base class with a metaclass."""
+ # This requires a bit of explanation: the basic idea is to make a dummy
+ # metaclass for one level of class instantiation that replaces itself with
+ # the actual metaclass.
+ class metaclass(meta):
+
+ def __new__(cls, name, this_bases, d):
+ return meta(name, bases, d)
+ return type.__new__(metaclass, 'temporary_class', (), {})
+
+
+def add_metaclass(metaclass):
+ """Class decorator for creating a class with a metaclass."""
+ def wrapper(cls):
+ orig_vars = cls.__dict__.copy()
+ slots = orig_vars.get('__slots__')
+ if slots is not None:
+ if isinstance(slots, str):
+ slots = [slots]
+ for slots_var in slots:
+ orig_vars.pop(slots_var)
+ orig_vars.pop('__dict__', None)
+ orig_vars.pop('__weakref__', None)
+ return metaclass(cls.__name__, cls.__bases__, orig_vars)
+ return wrapper
+
+
+def python_2_unicode_compatible(klass):
+ """
+ A decorator that defines __unicode__ and __str__ methods under Python 2.
+ Under Python 3 it does nothing.
+
+ To support Python 2 and 3 with a single code base, define a __str__ method
+ returning text and apply this decorator to the class.
+ """
+ if PY2:
+ if '__str__' not in klass.__dict__:
+ raise ValueError("@python_2_unicode_compatible cannot be applied "
+ "to %s because it doesn't define __str__()." %
+ klass.__name__)
+ klass.__unicode__ = klass.__str__
+ klass.__str__ = lambda self: self.__unicode__().encode('utf-8')
+ return klass
+
+
+# Complete the moves implementation.
+# This code is at the end of this module to speed up module loading.
+# Turn this module into a package.
+__path__ = [] # required for PEP 302 and PEP 451
+__package__ = __name__ # see PEP 366 @ReservedAssignment
+if globals().get("__spec__") is not None:
+ __spec__.submodule_search_locations = [] # PEP 451 @UndefinedVariable
+# Remove other six meta path importers, since they cause problems. This can
+# happen if six is removed from sys.modules and then reloaded. (Setuptools does
+# this for some reason.)
+if sys.meta_path:
+ for i, importer in enumerate(sys.meta_path):
+ # Here's some real nastiness: Another "instance" of the six module might
+ # be floating around. Therefore, we can't use isinstance() to check for
+ # the six meta path importer, since the other six instance will have
+ # inserted an importer with different class.
+ if (type(importer).__name__ == "_SixMetaPathImporter" and
+ importer.name == __name__):
+ del sys.meta_path[i]
+ break
+ del i, importer
+# Finally, add the importer to the meta path import hook.
+sys.meta_path.append(_importer)
diff --git a/recipes/pkgresources/pkgr/extern/__init__.py b/recipes/pkgresources/pkgr/extern/__init__.py
new file mode 100644
index 0000000..b4156fe
--- /dev/null
+++ b/recipes/pkgresources/pkgr/extern/__init__.py
@@ -0,0 +1,73 @@
+import sys
+
+
+class VendorImporter:
+ """
+ A PEP 302 meta path importer for finding optionally-vendored
+ or otherwise naturally-installed packages from root_name.
+ """
+
+ def __init__(self, root_name, vendored_names=(), vendor_pkg=None):
+ self.root_name = root_name
+ self.vendored_names = set(vendored_names)
+ self.vendor_pkg = vendor_pkg or root_name.replace('extern', '_vendor')
+
+ @property
+ def search_path(self):
+ """
+ Search first the vendor package then as a natural package.
+ """
+ yield self.vendor_pkg + '.'
+ yield ''
+
+ def find_module(self, fullname, path=None):
+ """
+ Return self when fullname starts with root_name and the
+ target module is one vendored through this importer.
+ """
+ root, base, target = fullname.partition(self.root_name + '.')
+ if root:
+ return
+ if not any(map(target.startswith, self.vendored_names)):
+ return
+ return self
+
+ def load_module(self, fullname):
+ """
+ Iterate over the search path to locate and load fullname.
+ """
+ root, base, target = fullname.partition(self.root_name + '.')
+ for prefix in self.search_path:
+ try:
+ extant = prefix + target
+ __import__(extant)
+ mod = sys.modules[extant]
+ sys.modules[fullname] = mod
+ # mysterious hack:
+ # Remove the reference to the extant package/module
+ # on later Python versions to cause relative imports
+ # in the vendor package to resolve the same modules
+ # as those going through this importer.
+ if sys.version_info > (3, 3):
+ del sys.modules[extant]
+ return mod
+ except ImportError:
+ pass
+ else:
+ raise ImportError(
+ "The '{target}' package is required; "
+ "normally this is bundled with this package so if you get "
+ "this warning, consult the packager of your "
+ "distribution.".format(**locals())
+ )
+
+ def install(self):
+ """
+ Install this importer into sys.meta_path if not already present.
+ """
+ if self not in sys.meta_path:
+ sys.meta_path.append(self)
+
+
+names = 'packaging', 'pyparsing', 'six', 'appdirs'
+VendorImporter(__name__, names).install()