summaryrefslogtreecommitdiff
path: root/lib/bundler/similarity_detector.rb
diff options
context:
space:
mode:
authorhsbt <hsbt@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2018-11-02 23:07:56 +0000
committerhsbt <hsbt@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>2018-11-02 23:07:56 +0000
commit59c8d50653480bef3f24517296e6ddf937fdf6bc (patch)
treedf10aaf4f3307837fe3d1d129d66f6c0c7586bc5 /lib/bundler/similarity_detector.rb
parent7deb37777a230837e865e0a11fb8d7c1dc6d03ce (diff)
Added bundler as default gems. Revisit [Feature #12733]
* bin/*, lib/bundler/*, lib/bundler.rb, spec/bundler, man/*: Merge from latest stable branch of bundler/bundler repository and added workaround patches. I will backport them into upstream. * common.mk, defs/gmake.mk: Added `test-bundler` task for test suite of bundler. * tool/sync_default_gems.rb: Added sync task for bundler. git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@65509 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
Diffstat (limited to 'lib/bundler/similarity_detector.rb')
-rw-r--r--lib/bundler/similarity_detector.rb63
1 files changed, 63 insertions, 0 deletions
diff --git a/lib/bundler/similarity_detector.rb b/lib/bundler/similarity_detector.rb
new file mode 100644
index 0000000000..b7f3ee7afa
--- /dev/null
+++ b/lib/bundler/similarity_detector.rb
@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+
+module Bundler
+ class SimilarityDetector
+ SimilarityScore = Struct.new(:string, :distance)
+
+ # initialize with an array of words to be matched against
+ def initialize(corpus)
+ @corpus = corpus
+ end
+
+ # return an array of words similar to 'word' from the corpus
+ def similar_words(word, limit = 3)
+ words_by_similarity = @corpus.map {|w| SimilarityScore.new(w, levenshtein_distance(word, w)) }
+ words_by_similarity.select {|s| s.distance <= limit }.sort_by(&:distance).map(&:string)
+ end
+
+ # return the result of 'similar_words', concatenated into a list
+ # (eg "a, b, or c")
+ def similar_word_list(word, limit = 3)
+ words = similar_words(word, limit)
+ if words.length == 1
+ words[0]
+ elsif words.length > 1
+ [words[0..-2].join(", "), words[-1]].join(" or ")
+ end
+ end
+
+ protected
+
+ # http://www.informit.com/articles/article.aspx?p=683059&seqNum=36
+ def levenshtein_distance(this, that, ins = 2, del = 2, sub = 1)
+ # ins, del, sub are weighted costs
+ return nil if this.nil?
+ return nil if that.nil?
+ dm = [] # distance matrix
+
+ # Initialize first row values
+ dm[0] = (0..this.length).collect {|i| i * ins }
+ fill = [0] * (this.length - 1)
+
+ # Initialize first column values
+ (1..that.length).each do |i|
+ dm[i] = [i * del, fill.flatten]
+ end
+
+ # populate matrix
+ (1..that.length).each do |i|
+ (1..this.length).each do |j|
+ # critical comparison
+ dm[i][j] = [
+ dm[i - 1][j - 1] + (this[j - 1] == that[i - 1] ? 0 : sub),
+ dm[i][j - 1] + ins,
+ dm[i - 1][j] + del
+ ].min
+ end
+ end
+
+ # The last value in matrix is the Levenshtein distance between the strings
+ dm[that.length][this.length]
+ end
+ end
+end