pragmatic_segmenter 0.0.9 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c54f1c34c1f0bd34858cbd9c3915ec47f8a4d807
-  data.tar.gz: 19a936bfd8fb6c0046f06a20f50319fb5a2c0ed7
+  metadata.gz: 96aa232b769e566aad1de6ace0fa6d8591e3859c
+  data.tar.gz: 2ed0518fb7c236821b0986795e7bc1ce5e19e1a8
 SHA512:
-  metadata.gz: 824392373d56549289ae89de98976d53afdf74ccde45f3b6069164d8882fbeef7ae04e2fec1261af2baf43223246b4f1f90ebab12b97fa0c22e0d81d6caa56fa
-  data.tar.gz: 4f43e20c69be0515d81c9d98e33b7ed2aadf05d5110ddd7acae3f971745c8406c03763fdc275afa3b14de3d5aa8846a85638845d90cc4c9fd34f4cf9e120d1d3
+  metadata.gz: fef9536b2c2dc9896aedcb363f89bc10af37c09d66c034d8814ccb784619a9ea82fa3d20e9e69316dfcef06d7013183d9dcbd564430dc7ce2303a7cfbe32ba87
+  data.tar.gz: 813a64e15c83b9dab5a2fe29c0bebba638fba0663c3debb26442cd42f060fa87e927846309355ec15953ca0a45c90d764fae796533f7d054282bdf8b5bcb06d4

data/README.md

@@ -744,6 +744,9 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.0.9**  
 * Improve handling of alphabetical and roman numeral lists  
 
+**Version 0.1.0**  
+* Add Kommanditgesellschaft Rule  
+
 ## Contributing
 
 If you find a text that is incorrectly segmented using this gem, please submit an issue.

data/lib/pragmatic_segmenter/abbreviation_replacer.rb

@@ -9,6 +9,9 @@ module PragmaticSegmenter
     # Rubular: http://rubular.com/r/yqa4Rit8EY
     PossessiveAbbreviationRule = Rule.new(/\.(?='s\s)|\.(?='s$)|\.(?='s\z)/, '∯')
 
+    # Rubular: http://rubular.com/r/NEv265G2X2
+    KommanditgesellschaftRule = Rule.new(/(?<=Co)\.(?=\sKG)/, '∯')
+
     # Rubular: http://rubular.com/r/xDkpFZ0EgH
     MULTI_PERIOD_ABBREVIATION_REGEX = /\b[a-z](?:\.[a-z])+[.]/i
 
@@ -37,6 +40,7 @@ module PragmaticSegmenter
 
     def replace
       @reformatted_text = text.apply(PossessiveAbbreviationRule)
+      @reformatted_text = text.apply(KommanditgesellschaftRule)
       @reformatted_text = PragmaticSegmenter::SingleLetterAbbreviation.new(text: @reformatted_text).replace
       @reformatted_text = search_for_abbreviations_in_string(@reformatted_text, abbreviations)
       @reformatted_text = replace_multi_period_abbreviations(@reformatted_text)

data/lib/pragmatic_segmenter/version.rb

@@ -1,3 +1,3 @@
 module PragmaticSegmenter
-  VERSION = "0.0.9"
+  VERSION = "0.1.0"
 end

data/spec/pragmatic_segmenter_spec.rb

@@ -913,6 +913,11 @@ RSpec.describe PragmaticSegmenter::Segmenter do
         ps = PragmaticSegmenter::Segmenter.new(text: "A) Hello world. \nB) Hello world.\nC) Hello world.\nD) Hello world.\nE) Hello world.\nF) Hello world.", language: "en")
         expect(ps.segment).to eq(["A) Hello world.", "B) Hello world.", "C) Hello world.", "D) Hello world.", "E) Hello world.", "F) Hello world."])
       end
+
+      it "correctly segments text #089" do
+        ps = PragmaticSegmenter::Segmenter.new(text: "The GmbH & Co. KG is a limited partnership with, typically, the sole general partner being a limited liability company.")
+        expect(ps.segment).to eq(["The GmbH & Co. KG is a limited partnership with, typically, the sole general partner being a limited liability company."])
+      end
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.0.9
+  version: 0.1.0
 platform: ruby
 authors:
 - Kevin S. Dias