From af4329b9e7501de9e744fed047a0bc44d0892779 Mon Sep 17 00:00:00 2001 From: Mark Beamer Jr Date: Mon, 12 Nov 2018 21:33:18 -0500 Subject: [PATCH 1/3] Added multi character splits to split by `&`, ` `, and `$` --- server/controllers/lighthouse.js | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/server/controllers/lighthouse.js b/server/controllers/lighthouse.js index b715c5a..81bd4ae 100644 --- a/server/controllers/lighthouse.js +++ b/server/controllers/lighthouse.js @@ -318,8 +318,10 @@ function getStatus () { function getWashedQuery (query) { // compress multiple white spaces to 1 query = query.toLowerCase().replace(/ +/g, ' '); + let splitBy = ['&', '$', ' ']; + let regex = new RegExp(splitBy.join('|'), 'gi'); let badWords = [ 'from', 'with', 'not', 'can', 'all', 'are', 'for', 'but', 'and', 'the' ]; - let words = query.split(' '); + let words = query.split(regex); let sentence = []; words.forEach(w => { if (!badWords.includes(w)) { sentence.push(w) } From 5081e1bff92635164a0c703790fa7f00bbbb81e8 Mon Sep 17 00:00:00 2001 From: Mark Beamer Jr Date: Mon, 12 Nov 2018 21:52:18 -0500 Subject: [PATCH 2/3] added removal from query `lbry://` ( lbry urls ) --- server/controllers/lighthouse.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/controllers/lighthouse.js b/server/controllers/lighthouse.js index 81bd4ae..cc441a8 100644 --- a/server/controllers/lighthouse.js +++ b/server/controllers/lighthouse.js @@ -317,7 +317,7 @@ function getStatus () { function getWashedQuery (query) { // compress multiple white spaces to 1 - query = query.toLowerCase().replace(/ +/g, ' '); + query = query.toLowerCase().replace(/ +/g, ' ').replace('lbry://', ''); let splitBy = ['&', '$', ' ']; let regex = new RegExp(splitBy.join('|'), 'gi'); let badWords = [ 'from', 'with', 'not', 'can', 'all', 'are', 'for', 'but', 'and', 'the' ]; From 423176da3f27a21b08f2f1de0172a7c5085a131f Mon Sep 17 00:00:00 2001 From: Thomas Zarebczan Date: Tue, 13 Nov 2018 13:23:01 -0500 Subject: [PATCH 3/3] Update lighthouse.js decrease effective factor one more decimal to compare related content results while we work on proper query washing. --- server/controllers/lighthouse.js | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/server/controllers/lighthouse.js b/server/controllers/lighthouse.js index cc441a8..6eb8578 100644 --- a/server/controllers/lighthouse.js +++ b/server/controllers/lighthouse.js @@ -40,7 +40,7 @@ function getResults (input) { let trimmedQuery = input.s.trim(); let escapedQuery = getWashedQuery(getEscapedQuery(trimmedQuery)); let washedQuery = getWashedQuery(trimmedQuery); - let effectiveFactor = '0.0000000001'; + let effectiveFactor = '0.00000000001'; // Search is split up into different parts, all search parts goes under this line. let channelSearch; if (input.channel !== undefined) { // If we got a channel argument, lets filter out only that channel