KevinMidboe/linguist
1
0
Fork 0
mirror of https://github.com/KevinMidboe/linguist.git synced 2025-12-08 20:38:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use heuristics earlier to inform the rest of the classification process

Browse Source
This commit is contained in:
Arfon Smith
2014-11-06 14:09:19 -06:00
parent f4c7661cc6
commit 1831390429
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
lib/linguist/language.rb
View File

@@ -125,6 +125,11 @@ module Linguist
if possible_languages.length > 1 if possible_languages.length > 1
data = blob.data data = blob.data
possible_language_names = possible_languages.map(&:name) possible_language_names = possible_languages.map(&:name)
heuristic_languages = Heuristics.find_by_heuristics(data, possible_language_names)
if heuristic_languages.size > 1
possible_language_names = heuristic_languages.map(&:name)
end
# Don't bother with binary contents or an empty file # Don't bother with binary contents or an empty file
if data.nil? || data == "" if data.nil? || data == ""
@@ -133,8 +138,8 @@ module Linguist
elsif (result = find_by_shebang(data)) && !result.empty? elsif (result = find_by_shebang(data)) && !result.empty?
result.first result.first
# No shebang. Still more work to do. Try to find it with our heuristics. # No shebang. Still more work to do. Try to find it with our heuristics.
elsif (determined = Heuristics.find_by_heuristics(data, possible_language_names)) && !determined.empty? elsif heuristic_languages.size == 1
determined.first heuristic_languages.first
# Lastly, fall back to the probabilistic classifier. # Lastly, fall back to the probabilistic classifier.
elsif classified = Classifier.classify(Samples.cache, data, possible_language_names).first elsif classified = Classifier.classify(Samples.cache, data, possible_language_names).first
# Return the actual Language object based of the string language name (i.e., first element of `#classify`) # Return the actual Language object based of the string language name (i.e., first element of `#classify`)