Merge pull request #1700 from lbryio/mimetypes

improve contentType detection

lbrynet/extras/daemon/Daemon.py

@@ -1,5 +1,4 @@
 import logging.handlers
-import mimetypes
 import os
 import requests
 import urllib
@@ -29,6 +28,7 @@ from lbrynet.extras.daemon.ComponentManager import RequiredCondition
 from lbrynet.extras.daemon.Downloader import GetStream
 from lbrynet.extras.daemon.Publisher import Publisher
 from lbrynet.extras.daemon.auth.server import AuthJSONRPCServer
+from lbrynet.extras.daemon.mime_types import guess_mime_type
 from lbrynet.extras.wallet import LbryWalletManager
 from lbrynet.extras.wallet.account import Account as LBCAccount
 from lbrynet.extras.wallet.dewies import dewies_to_lbc, lbc_to_dewies
@@ -535,7 +535,7 @@ class Daemon(AuthJSONRPCServer):
     def _get_lbry_file_dict(self, lbry_file):
         key = hexlify(lbry_file.key) if lbry_file.key else None
         full_path = os.path.join(lbry_file.download_directory, lbry_file.file_name)
-        mime_type = mimetypes.guess_type(full_path)[0]
+        mime_type = guess_mime_type(lbry_file.file_name)
         if os.path.isfile(full_path):
             with open(full_path) as written_file:
                 written_file.seek(0, os.SEEK_END)

lbrynet/extras/daemon/Publisher.py

@@ -1,9 +1,9 @@
 import asyncio
 import logging
-import mimetypes
 import os
 
 from lbrynet.blob.EncryptedFileCreator import create_lbry_file
+from lbrynet.extras.daemon.mime_types import guess_mime_type
 
 log = logging.getLogger(__name__)
 
@@ -43,7 +43,7 @@ class Publisher:
             claim_dict['stream']['source'] = {}
         claim_dict['stream']['source']['source'] = self.lbry_file.sd_hash
         claim_dict['stream']['source']['sourceType'] = 'lbry_sd_hash'
-        claim_dict['stream']['source']['contentType'] = get_content_type(file_path)
+        claim_dict['stream']['source']['contentType'] = guess_mime_type(file_path)
         claim_dict['stream']['source']['version'] = "_0_0_1"  # need current version here
         tx = await self.wallet.claim_name(
             self.account, name, bid, claim_dict, self.certificate, holding_address
@@ -75,7 +75,3 @@ class Publisher:
             ))
             self.lbry_file = [f for f in self.lbry_file_manager.lbry_files if f.stream_hash == stream_hash][0]
         return tx
-
-
-def get_content_type(filename):
-    return mimetypes.guess_type(filename)[0] or 'application/octet-stream'

lbrynet/extras/daemon/mime_types.py

@@ -0,0 +1,154 @@
+import os
+
+
+types_map = {
+    # http://www.iana.org/assignments/media-types
+    '.a': 'application/octet-stream',
+    '.ai': 'application/postscript',
+    '.aif': 'audio/x-aiff',
+    '.aifc': 'audio/x-aiff',
+    '.aiff': 'audio/x-aiff',
+    '.au': 'audio/basic',
+    '.avi': 'video/x-msvideo',
+    '.bat': 'text/plain',
+    '.bcpio': 'application/x-bcpio',
+    '.bin': 'application/octet-stream',
+    '.bmp': 'image/bmp',
+    '.c': 'text/plain',
+    '.cdf': 'application/x-netcdf',
+    '.cpio': 'application/x-cpio',
+    '.csh': 'application/x-csh',
+    '.css': 'text/css',
+    '.csv': 'text/csv',
+    '.dll': 'application/octet-stream',
+    '.doc': 'application/msword',
+    '.dot': 'application/msword',
+    '.dvi': 'application/x-dvi',
+    '.eml': 'message/rfc822',
+    '.eps': 'application/postscript',
+    '.etx': 'text/x-setext',
+    '.exe': 'application/octet-stream',
+    '.gif': 'image/gif',
+    '.gtar': 'application/x-gtar',
+    '.h': 'text/plain',
+    '.hdf': 'application/x-hdf',
+    '.htm': 'text/html',
+    '.html': 'text/html',
+    '.ico': 'image/vnd.microsoft.icon',
+    '.ief': 'image/ief',
+    '.iges': 'model/iges',
+    '.jpe': 'image/jpeg',
+    '.jpeg': 'image/jpeg',
+    '.jpg': 'image/jpeg',
+    '.js': 'application/javascript',
+    '.json': 'application/json',
+    '.ksh': 'text/plain',
+    '.latex': 'application/x-latex',
+    '.m1v': 'video/mpeg',
+    '.m3u': 'application/vnd.apple.mpegurl',
+    '.m3u8': 'application/vnd.apple.mpegurl',
+    '.man': 'application/x-troff-man',
+    '.markdown': 'text/markdown',
+    '.md': 'text/markdown',
+    '.me': 'application/x-troff-me',
+    '.mht': 'message/rfc822',
+    '.mhtml': 'message/rfc822',
+    '.mif': 'application/x-mif',
+    '.mov': 'video/quicktime',
+    '.movie': 'video/x-sgi-movie',
+    '.mp2': 'audio/mpeg',
+    '.mp3': 'audio/mpeg',
+    '.mp4': 'video/mp4',
+    '.mpa': 'video/mpeg',
+    '.mpe': 'video/mpeg',
+    '.mpeg': 'video/mpeg',
+    '.mpg': 'video/mpeg',
+    '.ms': 'application/x-troff-ms',
+    '.nc': 'application/x-netcdf',
+    '.nws': 'message/rfc822',
+    '.o': 'application/octet-stream',
+    '.obj': 'application/octet-stream',
+    '.oda': 'application/oda',
+    '.p12': 'application/x-pkcs12',
+    '.p7c': 'application/pkcs7-mime',
+    '.pbm': 'image/x-portable-bitmap',
+    '.pdf': 'application/pdf',
+    '.pfx': 'application/x-pkcs12',
+    '.pgm': 'image/x-portable-graymap',
+    '.pl': 'text/plain',
+    '.png': 'image/png',
+    '.pnm': 'image/x-portable-anymap',
+    '.pot': 'application/vnd.ms-powerpoint',
+    '.ppa': 'application/vnd.ms-powerpoint',
+    '.ppm': 'image/x-portable-pixmap',
+    '.pps': 'application/vnd.ms-powerpoint',
+    '.ppt': 'application/vnd.ms-powerpoint',
+    '.ps': 'application/postscript',
+    '.pwz': 'application/vnd.ms-powerpoint',
+    '.py': 'text/x-python',
+    '.pyc': 'application/x-python-code',
+    '.pyo': 'application/x-python-code',
+    '.qt': 'video/quicktime',
+    '.ra': 'audio/x-pn-realaudio',
+    '.ram': 'application/x-pn-realaudio',
+    '.ras': 'image/x-cmu-raster',
+    '.rdf': 'application/xml',
+    '.rgb': 'image/x-rgb',
+    '.roff': 'application/x-troff',
+    '.rtx': 'text/richtext',
+    '.sgm': 'text/x-sgml',
+    '.sgml': 'text/x-sgml',
+    '.sh': 'application/x-sh',
+    '.shar': 'application/x-shar',
+    '.snd': 'audio/basic',
+    '.so': 'application/octet-stream',
+    '.src': 'application/x-wais-source',
+    '.stl': 'model/stl',
+    '.sv4cpio': 'application/x-sv4cpio',
+    '.sv4crc': 'application/x-sv4crc',
+    '.svg': 'image/svg+xml',
+    '.swf': 'application/x-shockwave-flash',
+    '.t': 'application/x-troff',
+    '.tar': 'application/x-tar',
+    '.tcl': 'application/x-tcl',
+    '.tex': 'application/x-tex',
+    '.texi': 'application/x-texinfo',
+    '.texinfo': 'application/x-texinfo',
+    '.tif': 'image/tiff',
+    '.tiff': 'image/tiff',
+    '.tr': 'application/x-troff',
+    '.tsv': 'text/tab-separated-values',
+    '.txt': 'text/plain',
+    '.ustar': 'application/x-ustar',
+    '.vcf': 'text/x-vcard',
+    '.wav': 'audio/x-wav',
+    '.webm': 'video/webm',
+    '.wiz': 'application/msword',
+    '.wsdl': 'application/xml',
+    '.xbm': 'image/x-xbitmap',
+    '.xlb': 'application/vnd.ms-excel',
+    '.xls': 'application/vnd.ms-excel',
+    '.xml': 'text/xml',
+    '.xpdl': 'application/xml',
+    '.xpm': 'image/x-xpixmap',
+    '.xsl': 'application/xml',
+    '.xwd': 'image/x-xwindowdump',
+    '.zip': 'application/zip',
+
+    # These are non-standard types, commonly found in the wild.
+    '.mid': 'audio/midi',
+    '.midi': 'audio/midi',
+    '.pct': 'image/pict',
+    '.pic': 'image/pict',
+    '.pict': 'image/pict',
+    '.rtf': 'application/rtf',
+    '.xul': 'text/xul'
+}
+
+
+fallback_mime_type = 'application/octet-stream'
+
+
+def guess_mime_type(path):
+    _, ext = os.path.splitext(path)
+    return types_map.get(ext, fallback_mime_type)