flashtext 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: d8ca3508b7355433ef41fc40eead394cdc2149d2
-  data.tar.gz: 3715210544ee9170cf9c559ab10193b016e63615
+  metadata.gz: 869b2bf065283da58b746046bc45317ca9a47526
+  data.tar.gz: 0111edfd1206e610a0a8727181fb98abd3bfc5c9
 SHA512:
-  metadata.gz: 2af1340ae2088f1327f689a0fc9c6036758f85571c3fbe6045b89593d2e5a45df8c5d2bcf705c51aa8fa69aad24504f71edd604454fd7cccfa485a31a605669f
-  data.tar.gz: 0daa3bc37c6820204950c02f6766d2e11ab3850ebfaca8abd75582aa0453a0a2f6df59d2bdf19bd83e4108597f48caec8cb7c224cfc4a5295a106a57c21ac735
+  metadata.gz: e66b94f29f8912987b4411953b33cb470163a4c6c9409778941b6f4f4722c8305eceb8fbef8b07dca0fcbf4c1f4a12dd767305a4b32b2cba2909815b7a994542
+  data.tar.gz: 62029dadbaca46ebc761596a7a683764dd0d8ff9b89f475787d3288785d86be8fb432eb4b2bb91b8966636c0947b335595169a25f05e1bad503283c8154f0978

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    flashtext (0.1.0)
+    flashtext (0.1.2)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -4,8 +4,7 @@
 
 This module can be used to replace keywords in sentences or extract keywords from sentences. It is based on the [FlashText algorithm](https://arxiv.org/abs/1711.00046)
 
-More about Flashtext algorithm can be found here.
-
+#### More about Flashtext algorithm.
 The original paper published on [FlashText algorithm](https://arxiv.org/abs/1711.00046>)
 
 The article published on [Medium freeCodeCamp](https://medium.freecodecamp.org/regex-was-taking-5-days-flashtext-does-it-in-15-minutes-55f04411025f)
@@ -22,6 +21,41 @@ API doc
 Documentation can be found at [FlashText Read the Docs](http://www.rubydoc.info/gems/flashtext/)
 
 ## Usage
+#### Extract keywords
+```ruby
+keyword_processor = Flashtext::KeywordProcessor.new
+# keyword_processor.add_keyword(<unclean name>, <standardised name>)
+keyword_processor.add_keyword('Big Apple', 'New York')
+keyword_processor.add_keyword('Bay Area')
+keywords_found = keyword_processor.extract_keywords('I love Big Apple and Bay Area.')
+keywords_found
+#=> ["New York", "Bay Area"]
+```
+
+#### Replace keywords
+```ruby
+keyword_processor.add_keyword('New Delhi', 'NCR region')
+new_sentence = keyword_processor.replace_keywords('I love Big Apple and new delhi.')
+new_sentence
+#=> "I love New York and NCR region."
+```
+
+#### Case Sensitive example
+```ruby
+keyword_processor = Flashtext::KeywordProcessor.new(case_sensitive = true)
+keyword_processor.add_keyword('Big Apple', 'New York')
+keyword_processor.add_keyword('Bay Area')
+keywords_found = keyword_processor.extract_keywords('I love big Apple and Bay Area.')
+keywords_found
+#=> ['Bay Area']
+```
+
+
+Test
+----------
+```ruby
+rspec spec
+```
 
 Contribute
 ----------
@@ -29,6 +63,13 @@ Contribute
 - Issue Tracker: https://github.com/imran3180/flashtext/issues
 - Source Code: https://github.com/imran3180/flashtext/issues
 
+Implementation in other languages
+---------------------------------
+
+- Python: https://github.com/vi3k6i5/flashtext (Core Project)
+- JavaScript: https://github.com/drenther/flashtext.js
+- Golang: https://github.com/sundy-li/flashtext
+
 
 ## License
 

data/lib/flashtext/keyword_processor.rb

@@ -130,5 +130,116 @@ module Flashtext
       end
       keywords_extracted
     end
+
+    def replace_keywords sentence
+      if sentence.nil? || sentence.empty?
+        return sentence
+      end
+      new_sentence = ""
+      original_sentence = sentence
+      sentence = sentence.downcase if not case_sensitive
+      current_word = ""
+      current_hash = keyword_trie_hash
+      current_white_space = ""
+      sequence_end_pos = 0
+      idx = 0
+      sentence_len = sentence.length
+
+      while idx < sentence_len
+        char = sentence[idx]
+        current_word += original_sentence[idx]
+
+        if not word_boundaries.member?(char)
+          current_white_space = char
+          if current_hash.has_key?(_keyword) or current_hash.has_key?(char)
+            # update longest sequence found
+            sequence_found = nil
+            longest_sequence_found = nil
+            is_longer_seq_found = false
+            if current_hash.has_key?(_keyword)
+              sequence_found = current_hash[_keyword]
+              longest_sequence_found = current_hash[_keyword]
+              sequence_end_pos = idx
+            end
+
+            # re look for longest_sequence from this position
+            if current_hash.has_key?(char)
+              current_hash_continued = current_hash[char]
+              current_word_continued = current_word
+              idy = idx + 1
+              while idy < sentence_len
+                inner_char = sentence[idy]
+                current_word_continued += original_sentence[idy]
+                if !word_boundaries.member?(inner_char) and current_hash_continued.has_key?(_keyword)
+                  # Update longest sequence found
+                  current_white_space = inner_char
+                  longest_sequence_found = current_hash_continued[_keyword]
+                  sequence_end_pos = idy
+                  is_longer_seq_found = true
+                end
+                if current_hash_continued.has_key?(inner_char)
+                  current_hash_continued = current_hash_continued[inner_char]
+                else
+                  break
+                end
+                idy += 1
+              end
+              if idy == sentence_len # end of sentence reached.
+                if current_hash_continued.member?(_keyword)
+                  # update longest sequence found
+                  current_white_space = ""
+                  longest_sequence_found = current_hash_continued[_keyword]
+                  sequence_end_pos = idy
+                  is_longer_seq_found = true
+                end
+              end
+              if is_longer_seq_found
+                idx = sequence_end_pos
+                current_word = current_word_continued
+              end
+            end
+            current_hash = keyword_trie_hash
+            if longest_sequence_found
+              new_sentence += (longest_sequence_found + current_white_space)
+              current_word = ''
+              current_white_space = ''
+            else
+              new_sentence += current_word
+              current_word = ''
+              current_white_space = ''
+            end
+          else
+            # we reset current_hash
+            current_hash = keyword_trie_hash
+            new_sentence += current_word
+            current_word = ''
+            current_white_space = ''
+          end
+        elsif current_hash.has_key?(char)
+          # we can continue from this char
+          current_hash = current_hash[char]
+        else
+          # reset current_hash
+          current_hash = keyword_trie_hash
+          idy = idx + 1
+          while idy < sentence_len
+            char = sentence[idy]
+            current_word += original_sentence[idy]
+            break if not word_boundaries.member?(char)
+            idy += 1
+          end
+          idx = idy
+          new_sentence += current_word
+          current_word = ""
+          current_white_space = ""
+        end
+        if idx + 1 >= sentence_len && current_hash.has_key?(_keyword)
+          sequence_found = current_hash[_keyword]
+          new_sentence += sequence_found
+        end
+        idx = idx + 1 # loop increment
+      end
+      return new_sentence
+    end
   end
 end

data/lib/flashtext/version.rb

@@ -1,3 +1,3 @@
 module Flashtext
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: flashtext
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Imran
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-11-18 00:00:00.000000000 Z
+date: 2018-01-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler