pragmatic_segmenter 0.3.12 → 0.3.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4e6a6df4ee1ee432fdf8c5a480db27f05c79b169
-  data.tar.gz: c041b6b02d37dc873e9b99df10579fd6b4cda651
+  metadata.gz: c313d610281828819a76463bd3b42590927307e2
+  data.tar.gz: 3c9f340a197450a6dffac38f4a3c0b378f3b8edf
 SHA512:
-  metadata.gz: 1c15ba49df9d8b9c176f2e89ceba0c4d89390dee86db73d7bc1a3b076e2e9811e9308d1bfe59075faf41342699c9fd7c9bec0555d57c28cefedc1462479348bc
-  data.tar.gz: 94ae2baac22caef699c8251405fa7b44403b16fb7365b26af257ecb163714be1815ef93ab9a47de5babf16e79e5203a6912a2a6beec34f2e4ca266a026df8ad7
+  metadata.gz: d8756402fcb03f456f27d8359b4e8adfd970fed42a89bdfebab9b7a75b25d83dd9b4db19b1f7982b71214c573500b519cbc1920b6a54fa2632a3521dabee9a68
+  data.tar.gz: 911a665d2609086e20aff601161e63ce22410e18c0d169fc9d8032cef029062aa7a3cdafa082c55db1ab78ae6f2e5f7a1f302246c716f5393a815ed9aec890dc

data/.gitignore

@@ -12,3 +12,4 @@
 *.o
 *.a
 mkmf.log
+.DS_Store

data/NEWS

@@ -1,3 +1,7 @@
+0.3.13 (2017-01-17):
+
+* Bug Fix: Unexpected sentence break between abbreviation and hyphen
+
 0.3.12 (2016-12-12):
 
 * Bug Fix: Issue with words with leading apostrophes

data/README.md

@@ -847,6 +847,9 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.3.12**  
 * Fix issue involving words with leading apostrophes
 
+**Version 0.3.13**  
+* Fix issue involving unexpected sentence break between abbreviation and hyphen
+
 ## Contributing
 
 If you find a text that is incorrectly segmented using this gem, please submit an issue.

data/lib/pragmatic_segmenter/abbreviation_replacer.rb

@@ -113,7 +113,7 @@ 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

@@ -1,3 +1,3 @@
 module PragmaticSegmenter
-  VERSION = "0.3.12"
+  VERSION = "0.3.13"
 end

data/spec/pragmatic_segmenter/languages/english_spec.rb

@@ -1359,5 +1359,15 @@ RSpec.describe PragmaticSegmenter::Languages::English, "(en)" do
       ps = PragmaticSegmenter::Segmenter.new(text: "I wrote this in the ’nineties.  It has four sentences.  This is the third, isn't it?  And this is the last")
       expect(ps.segment).to eq(["I wrote this in the ’nineties.", "It has four sentences.", "This is the third, isn't it?", "And this is the last"])
     end
+
+    it "correctly segments text #109" do
+      ps = PragmaticSegmenter::Segmenter.new(text: "He has Ph.D.-level training", clean: false)
+      expect(ps.segment).to eq(["He has Ph.D.-level training"])
+    end
+
+    it "correctly segments text #110" do
+      ps = PragmaticSegmenter::Segmenter.new(text: "He has Ph.D. level training", clean: false)
+      expect(ps.segment).to eq(["He has Ph.D. level training"])
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.3.12
+  version: 0.3.13
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-12-13 00:00:00.000000000 Z
+date: 2017-01-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode
@@ -178,7 +178,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.2
+rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
 summary: A rule-based sentence boundary detection gem that works out-of-the-box across