pragmatic_segmenter 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 518ed98b0c60605da21ddd818f5cc8b5fef7fc99
-  data.tar.gz: 2531a0cb86b3790cbad5ef8a79b7abdbffe09403
+  metadata.gz: a2951fa2242e1eb7ce0898862d41fd5239d871f8
+  data.tar.gz: 01d84b2637e84598907ef08e59ec64e90855c2ec
 SHA512:
-  metadata.gz: 721b451df7243ff5fe334abc7d43d8b143ac33fa0aff33aa88d6af2a1b6dda34a92f1c1c0ee7bb8bf2cae85830f0aa4af05acdcecb16f9e0a0f58c773bc21ba4
-  data.tar.gz: 7eb98fdb49c723b37e23fe5d36fd28510b789feec731c30abb8387d24f7c9415aba1fafad304671fab3a105d5a1348cdd3348fe889d941360ad328714142818b
+  metadata.gz: 25ec02bc41c649a57b1bc993848bed546514568c74e2e0ec5b6a2242fbbb579e61e199210f8ea4349ceadee5a06ad0fa76c7c60196762903cab984bbad3c2286
+  data.tar.gz: 925a24d8c131813ddb4f80a8865697baa0efe05ef781cabfc13dfb9b1efc878c2e6e276a46a9f1301049a99b2f64a558b6a9911e0a2f5f8f4c17622df3fd0b2a

data/README.md

@@ -760,6 +760,9 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.1.4**  
 * Fix missing abbreviations  
 
+**Version 0.1.5**  
+* Fix comma at end of quoatation bug  
+
 ## Contributing
 
 If you find a text that is incorrectly segmented using this gem, please submit an issue.

data/lib/pragmatic_segmenter/sentence_boundary_punctuation.rb

@@ -3,7 +3,7 @@
 module PragmaticSegmenter
   # This class splits text at sentence boundary punctuation marks
   class SentenceBoundaryPunctuation
-    SENTENCE_BOUNDARY_REGEX = /\u{ff08}(?:[^\u{ff09}])*\u{ff09}(?=\s?[A-Z])|\u{300c}(?:[^\u{300d}])*\u{300d}(?=\s[A-Z])|\((?:[^\)]){2,}\)(?=\s[A-Z])|'(?:[^'])*'(?=\s[A-Z])|"(?:[^"])*"(?=\s[A-Z])|“(?:[^”])*”(?=\s[A-Z])|\S.*?[。．.！!?？ȸȹ☉☈☇☄]/
+    SENTENCE_BOUNDARY_REGEX = /\u{ff08}(?:[^\u{ff09}])*\u{ff09}(?=\s?[A-Z])|\u{300c}(?:[^\u{300d}])*\u{300d}(?=\s[A-Z])|\((?:[^\)]){2,}\)(?=\s[A-Z])|'(?:[^'])*[^,]'(?=\s[A-Z])|"(?:[^"])*[^,]"(?=\s[A-Z])|“(?:[^”])*[^,]”(?=\s[A-Z])|\S.*?[。．.！!?？ȸȹ☉☈☇☄]/
 
     attr_reader :text
     def initialize(text:)

data/lib/pragmatic_segmenter/version.rb

@@ -1,3 +1,3 @@
 module PragmaticSegmenter
-  VERSION = "0.1.4"
+  VERSION = "0.1.5"
 end

data/spec/pragmatic_segmenter_spec.rb

@@ -928,6 +928,11 @@ RSpec.describe PragmaticSegmenter::Segmenter do
         ps = PragmaticSegmenter::Segmenter.new(text: "[15:  12:32]  [16:  firma? 13:28]")
         expect(ps.segment).to eq(["[15:  12:32]  [16:  firma? 13:28]"])
       end
+
+      it "correctly segments text #092" do
+        ps = PragmaticSegmenter::Segmenter.new(text: "\"It's a good thing that the water is really calm,\" I answered ironically.")
+        expect(ps.segment).to eq(["\"It's a good thing that the water is really calm,\" I answered ironically."])
+      end
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Kevin S. Dias