pragmatic_segmenter 0.3.18 → 0.3.19

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3bb581e56e988521adc41dbb94bc7281ee7dfa95
-  data.tar.gz: 0c3b6fe877a5d39d36053b7ed68a860b5d17779b
+  metadata.gz: 3f03709232bf5b433b73de74a04b254228bc3ce6
+  data.tar.gz: 087860da234619d431849de1f85614b876e6d31a
 SHA512:
-  metadata.gz: 1b1dd64b5a382e8bb7ed5d79fbb9264565d71088f234ba4a9bd7cae47184e1c64f78b32a72f39326aa31936c6c6742aa2ff75cd75cd1b328987a6061a4d2534b
-  data.tar.gz: c150b178c93b7183300559e89c117cf8f9f93adf6ef33790a3ce0b292c66588fe6461c724210f7f93e078d2d08a10e995d7234bad963f8d5aa1c52c378effe5e
+  metadata.gz: 6d2759f5a302f6acf40b34990df8fd20d352b0aef5dfdd1799e5f7303d065466964566c068c505460837e838a8fa296754031084ef42715aab709f5d7a2f882c
+  data.tar.gz: 0ad1c988cff72e818fe9fdd4de77831e792e20834f27c6a40b34f594e8ef5a9927fdf1da259cdcd7a7d990b592c53f09bba11c59432b74d3b6a6f46615186378

data/NEWS

@@ -1,3 +1,7 @@
+0.3.19 (2018-07-19):
+
+* Bug Fix: A parenthetical following an abbreviation is now included as part of the same segment. Example: "The parties to this Agreement are PragmaticSegmenterExampleCompanyA Inc. (“Company A”), and PragmaticSegmenterExampleCompanyB Inc. (“Company B”)." is now treated as one segment.
+
 0.3.18 (2018-03-27):
 
 * Improvement: Performance optimizations

data/README.md

@@ -865,6 +865,9 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.3.18**
 * Performance optimizations
 
+**Version 0.3.19**
+* Treat a parenthetical following an abbreviation as part of the same segment
+
 ## Contributing
 
 If you find a text that is incorrectly segmented using this gem, please submit an issue.

data/lib/pragmatic_segmenter/abbreviation_replacer.rb

@@ -108,7 +108,7 @@ module PragmaticSegmenter
     end
 
     def replace_period_of_abbr(txt, abbr)
-      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=((\.|\:|-|\?)|(\s([a-z]|I\s|I'm|I'll|\d))))|(?<=^#{abbr.strip})\.(?=((\.|\:|\?)|(\s([a-z]|I\s|I'm|I'll|\d))))/, '∯')
+      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=((\.|\:|-|\?)|(\s([a-z]|I\s|I'm|I'll|\d|\())))|(?<=^#{abbr.strip})\.(?=((\.|\:|\?)|(\s([a-z]|I\s|I'm|I'll|\d))))/, '∯')
       txt.gsub!(/(?<=\s#{abbr.strip})\.(?=,)|(?<=^#{abbr.strip})\.(?=,)/, '∯')
       txt
     end

data/lib/pragmatic_segmenter/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PragmaticSegmenter
-  VERSION = "0.3.18"
+  VERSION = "0.3.19"
 end

data/spec/pragmatic_segmenter/languages/danish_spec.rb

@@ -507,7 +507,7 @@ RSpec.describe PragmaticSegmenter::Languages::Danish, "(da)" do
 
     it 'correctly segments text #048' do
       ps = PragmaticSegmenter::Segmenter.new(text: "CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co. (cited from WSJ 05/29/1987)", language: 'en')
-      expect(ps.segment).to eq(["CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co.", "(cited from WSJ 05/29/1987)"])
+      expect(ps.segment).to eq(["CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co. (cited from WSJ 05/29/1987)"])
     end
 
     it 'correctly segments text #049' do

data/spec/pragmatic_segmenter/languages/english_spec.rb

@@ -512,7 +512,7 @@ RSpec.describe PragmaticSegmenter::Languages::English, "(en)" do
 
     it 'correctly segments text #048' do
       ps = PragmaticSegmenter::Segmenter.new(text: "CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co. (cited from WSJ 05/29/1987)", language: 'en')
-      expect(ps.segment).to eq(["CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co.", "(cited from WSJ 05/29/1987)"])
+      expect(ps.segment).to eq(["CELLULAR COMMUNICATIONS INC. sold 1,550,000 common shares at $21.75 each yesterday, according to lead underwriter L.F. Rothschild & Co. (cited from WSJ 05/29/1987)"])
     end
 
     it 'correctly segments text #049' do
@@ -1406,5 +1406,10 @@ RSpec.describe PragmaticSegmenter::Languages::English, "(en)" do
       expect(ps.segment).to eq(["In placebo-controlled studies of all uses of Tracleer, marked decreases in hemoglobin (>15% decrease from baseline resulting in values <11 g/ dL) were observed in 6% of Tracleer-treated patients and 3% of placebo-treated patients.", "Bosentan is highly bound (>98%) to plasma proteins, mainly albumin."])
     end
 
+    it 'correctly segments text #118' do
+      text = "The parties to this Agreement are PragmaticSegmenterExampleCompanyA Inc. (“Company A”), and PragmaticSegmenterExampleCompanyB Inc. (“Company B”)."
+      ps = PragmaticSegmenter::Segmenter.new(text: text, clean: false)
+      expect(ps.segment).to eq(["The parties to this Agreement are PragmaticSegmenterExampleCompanyA Inc. (“Company A”), and PragmaticSegmenterExampleCompanyB Inc. (“Company B”)."])
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.3.18
+  version: 0.3.19
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-03-27 00:00:00.000000000 Z
+date: 2018-07-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode
@@ -180,7 +180,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.1
+rubygems_version: 2.6.14
 signing_key: 
 specification_version: 4
 summary: A rule-based sentence boundary detection gem that works out-of-the-box across