pragmatic_segmenter 0.3.23 → 0.3.24

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2c66c757c1b4bd8d090e88d7db6c627720f58f6f26e6fab9916a20e8bc15471c
-  data.tar.gz: da3a9088f72c90ddde6f0deda67d3e3b4ea3bed317970416deef794e0f594d89
+  metadata.gz: 51ae71a6650fcd15671ac767d26ebe1315a9ea655d8fbf6e29ef9e4fa668fc93
+  data.tar.gz: 786246dc9e80872b423013fed2d69e0cba48cc7a7d5a693a3165b4cdf61fe00d
 SHA512:
-  metadata.gz: 503c52965b2f98eebbc24e1215204c45307958a0279d56834e0c929d18625e81ac8c5c78779efb1a5946b5fdda5d8496b54a72b009ad6b2a597a70c4ba0fff66
-  data.tar.gz: f23773139a3a6d9f45cecaacabb363a7fb825a21eb76b40514abf4d0407191ed3b1afa887a5bc5328626abe2dbac5864895add62a1da036234036984d19a3454
+  metadata.gz: a830c5787a3818bc274b69aabd82bf5f837ba76c43921970c26a59f229d69bb24b698ff27389056ed6c536216edefdf4fa12338affbe883929b492065554af4c
+  data.tar.gz: f86cd6a66eaeb1890b5ddb2316d5ede734061b78212a490f8092bd20845cdb4dd47fac374972244785170ae266af21c566cbf59dd1a5667151ccd651269b72d8

data/NEWS

@@ -1,4 +1,9 @@
-0.3.22 (2021-05-03):
+0.3.24 (2024-08-12):
+
+* Bug Fix: Catastrophic backtracking in regular expression for numerical references
+* Improvement: Remove unicode dependency
+
+0.3.23 (2021-05-03):
 
 * Improvement: Refactor for Ruby 3.0 compatibility
 

data/README.md

@@ -890,6 +890,10 @@ To test the relative performance of different segmentation tools and libraries I
 **Version 0.3.23**
 * Refactor for Ruby 3.0 compatibility
 
+**Version 0.3.24**
+* Fix catastrophic backtracking in regular expression for numerical references
+* Remove unicode dependency
+
 ## Contributing
 
 If you find a text that is incorrectly segmented using this gem, please submit an issue.

data/lib/pragmatic_segmenter/languages/common/numbers.rb

@@ -47,7 +47,7 @@ module PragmaticSegmenter
       # Rubular: http://rubular.com/r/mQ8Es9bxtk
       CONTINUOUS_PUNCTUATION_REGEX = /(?<=\S)(!|\?){3,}(?=(\s|\z|$))/
 
-      NUMBERED_REFERENCE_REGEX = /(?<=[^\d\s])(\.|∯)((\[(\d{1,3},?\s?-?\s?)*\b\d{1,3}\])+|((\d{1,3}\s?)*\d{1,3}))(\s)(?=[A-Z])/
+      NUMBERED_REFERENCE_REGEX = /(?<=[^\d\s])(\.|∯)((\[(\d{1,3},?\s?-?\s?)?\b\d{1,3}\])+|((\d{1,3}\s?){0,3}\d{1,3}))(\s)(?=[A-Z])/
 
       # Rubular: http://rubular.com/r/yqa4Rit8EY
       PossessiveAbbreviationRule = Rule.new(/\.(?='s\s)|\.(?='s$)|\.(?='s\z)/, '∯')

data/lib/pragmatic_segmenter/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PragmaticSegmenter
-  VERSION = "0.3.23"
+  VERSION = "0.3.24"
 end

data/lib/unicode.rb

@@ -0,0 +1,5 @@
+module Unicode
+  def self.downcase(text)
+    text.downcase
+  end
+end

data/pragmatic_segmenter.gemspec

@@ -18,7 +18,6 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ["lib"]
 
-  spec.add_runtime_dependency "unicode"
   spec.add_development_dependency "bundler", ">= 1.7"
   spec.add_development_dependency "rake", ">= 12.3.3"
   spec.add_development_dependency "rspec"

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: pragmatic_segmenter
 version: !ruby/object:Gem::Version
-  version: 0.3.23
+  version: 0.3.24
 platform: ruby
 authors:
 - Kevin S. Dias
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-05-02 00:00:00.000000000 Z
+date: 2024-08-11 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: unicode
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -136,6 +122,7 @@ files:
 - lib/pragmatic_segmenter/segmenter.rb
 - lib/pragmatic_segmenter/types.rb
 - lib/pragmatic_segmenter/version.rb
+- lib/unicode.rb
 - pragmatic_segmenter.gemspec
 - spec/performance_spec.rb
 - spec/pragmatic_segmenter/languages/amharic_spec.rb
@@ -181,8 +168,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project:
-rubygems_version: 2.7.6
+rubygems_version: 3.3.26
 signing_key:
 specification_version: 4
 summary: A rule-based sentence boundary detection gem that works out-of-the-box across