pragmatic_tokenizer 1.0.1 → 1.0.2

Sign up to get free protection for your applications and to get access to all the features.
Files changed (5) hide show
  1. checksums.yaml +4 -4
  2. data/lib/pragmatic_tokenizer/languages/common.rb +3 -3
  3. data/lib/pragmatic_tokenizer/tokenizer.rb +1 -1
  4. data/lib/pragmatic_tokenizer/version.rb +1 -1
  5. metadata +1 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 8cba2ce060ad1d9ffc74953a9e3a9504b1c8ed13
4
- data.tar.gz: 3d96486358f974ce30165199381b27c3e01f7625
3
+ metadata.gz: 1d89939b4aa11fc9918019838c4877e3c2ed4d4f
4
+ data.tar.gz: 012586a964ee04adb2762d7152853ba7d56e7cd4
5
5
  SHA512:
6
- metadata.gz: 8cc83be7dc5d9db9dd03d8895ea0a0d7bb1856b0f7b82698362dfb97f8e6cd32c3cbaccbb320ce04cb193594c765ae4cbbce5cb24634f3fe0aced37298ce75c5
7
- data.tar.gz: f7edb187f8cc2f60aad58d79eac454b556dec53d77aa86a90d55d054d009783be8b4619da22550a79a01ac91540a7b1e3d5ea509e4c482821e32517f976c6208
6
+ metadata.gz: 0fe3e08af8e3a4b3fb1f8ddc69b743904d8949af2ce26d1388e4e10376d0c906b30a1e6434ede092078096f77b2cbc9dbca5292c1fe95fb1f95d8533da10ea49
7
+ data.tar.gz: b96e03429866b9cc26e4c2227535650d967748ffc686a1c0d83959f65f105f98b36a274a4b3b66493f55128640bdcad3ed9cd19c56076cf40da3ee7f8fd007a7
data/lib/pragmatic_tokenizer/languages/common.rb CHANGED
@@ -9,9 +9,9 @@ module PragmaticTokenizer
9
9
  ABBREVIATIONS = [].freeze
10
10
  STOP_WORDS = [].freeze
11
11
  CONTRACTIONS = {}.freeze
12
- EMOJI_REGEX = /[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}]/
13
- PREFIX_EMOJI_REGEX = /(?<=\S)(?=[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}])/
14
- POSTFIX_EMOJI_REGEX = /(?<=[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}])(?=\S)/
12
+ EMOJI_REGEX = /[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}\u{1F914}\u{1F644}]/
13
+ PREFIX_EMOJI_REGEX = /(?<=\S)(?=[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}\u{1F914}\u{1F644}])/
14
+ POSTFIX_EMOJI_REGEX = /(?<=[\u{203C}\u{2049}\u{20E3}\u{2122}\u{2139}\u{2194}-\u{2199}\u{21A9}-\u{21AA}\u{231A}-\u{231B}\u{23E9}-\u{23EC}\u{23F0}\u{23F3}\u{24C2}\u{25AA}-\u{25AB}\u{25B6}\u{25C0}\u{25FB}-\u{25FE}\u{2600}-\u{2601}\u{260E}\u{2611}\u{2614}-\u{2615}\u{261D}\u{263A}\u{2648}-\u{2653}\u{2660}\u{2663}\u{2665}-\u{2666}\u{2668}\u{267B}\u{267F}\u{2693}\u{26A0}-\u{26A1}\u{26AA}-\u{26AB}\u{26BD}-\u{26BE}\u{26C4}-\u{26C5}\u{26CE}\u{26D4}\u{26EA}\u{26F2}-\u{26F3}\u{26F5}\u{26FA}\u{26FD}\u{2702}\u{2705}\u{2708}-\u{270C}\u{270F}\u{2712}\u{2714}\u{2716}\u{2728}\u{2733}-\u{2734}\u{2744}\u{2747}\u{274C}\u{274E}\u{2753}-\u{2755}\u{2757}\u{2764}\u{2795}-\u{2797}\u{27A1}\u{27B0}\u{2934}-\u{2935}\u{2B05}-\u{2B07}\u{2B1B}-\u{2B1C}\u{2B50}\u{2B55}\u{3030}\u{303D}\u{3297}\u{3299}\u{1F004}\u{1F0CF}\u{1F170}-\u{1F171}\u{1F17E}-\u{1F17F}\u{1F18E}\u{1F191}-\u{1F19A}\u{1F1E7}-\u{1F1EC}\u{1F1EE}-\u{1F1F0}\u{1F1F3}\u{1F1F5}\u{1F1F7}-\u{1F1FA}\u{1F201}-\u{1F202}\u{1F21A}\u{1F22F}\u{1F232}-\u{1F23A}\u{1F250}-\u{1F251}\u{1F300}-\u{1F320}\u{1F330}-\u{1F335}\u{1F337}-\u{1F37C}\u{1F380}-\u{1F393}\u{1F3A0}-\u{1F3C4}\u{1F3C6}-\u{1F3CA}\u{1F3E0}-\u{1F3F0}\u{1F400}-\u{1F43E}\u{1F440}\u{1F442}-\u{1F4F7}\u{1F4F9}-\u{1F4FC}\u{1F500}-\u{1F507}\u{1F509}-\u{1F53D}\u{1F550}-\u{1F567}\u{1F5FB}-\u{1F640}\u{1F645}-\u{1F64F}\u{1F680}-\u{1F68A}\u{1F914}\u{1F644}])(?=\S)/
15
15
  EMOTICON_REGEX = /(?::|;|=)(?:-)?(?:\)|D|P)/
16
16
 
17
17
  class SingleQuotes
data/lib/pragmatic_tokenizer/tokenizer.rb CHANGED
@@ -175,7 +175,7 @@ module PragmaticTokenizer
175
175
  end
176
176
 
177
177
  def classic_filter!
178
- @tokens.map! { |t| abbreviations.include?(t.chomp(".")) ? t.gsub('.', '').chomp("'s").chomp("’s").chomp("`s") : t.chomp("'s").chomp("’s").chomp("`s") }
178
+ @tokens.map! { |t| abbreviations.include?(t.chomp(".")) ? t.gsub('.', '').chomp("'s").chomp("’s").chomp("`s").chomp("́s") : t.chomp("'s").chomp("’s").chomp("`s").chomp("́s") }
179
179
  end
180
180
 
181
181
  def process_numbers!
data/lib/pragmatic_tokenizer/version.rb CHANGED
@@ -1,3 +1,3 @@
1
1
  module PragmaticTokenizer
2
- VERSION = "1.0.1"
2
+ VERSION = "1.0.2"
3
3
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: pragmatic_tokenizer
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.1
4
+ version: 1.0.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Kevin S. Dias