srx-polish 0.2.1 → 0.3.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: c1a5a585338642469bee4a679efc4f0d3f12228d
+  data.tar.gz: 5c5df57c6c78b5a89647e4f2ec21af5262dec6e8
+SHA512:
+  metadata.gz: 87d75afc302d0debe4aecf899184402eae26082925089d94f13c5a004beb3f3e7ac18b5bb9e8bc44689389165b2119432d27756e74dbace820ddd7b94cc7a7d7
+  data.tar.gz: 29a1b4c730e782b415bae8bb7b5f4d09fd9f126c01724916ce1a80b158ea5f087a608aa63d02f9d9bf831e802ef5e3d50ccb0b9ef281036123786f31ef86cea4

data/.gitignore

@@ -1,4 +1,5 @@
-.*.sw?
 *.gem
+.*.sw?
+Gemfile.lock
 pkg
 work

data/.ruby-version

@@ -0,0 +1 @@
+2.1

data/Gemfile

@@ -0,0 +1,2 @@
+source 'https://rubygems.org'
+gemspec

data/changelog.txt

@@ -1,3 +1,6 @@
+0.3.0
+- rule update (as of 07/2018)
+- all rules are in separate file to reduce code clutter
 0.2.1
 - fix extension of README (was md, should be rdoc)
 0.2.0

data/features/steps/sentence_splitter.rb

@@ -12,6 +12,6 @@ end
 
 Then /^the following sentences should be detected$/ do |table|
   table.hashes.zip(@splitter.to_a).each do |expected,returned|
-    returned.gsub(/\s*\n/," ").strip.should == expected[:sentence]
+    expect(returned.gsub(/\s*\n/," ").strip).to eq expected[:sentence]
   end
 end

data/features/steps/word_splitter.rb

@@ -12,15 +12,15 @@ end
 
 Then /^the following segments should be detected$/ do |table|
   table.hashes.zip(@splitter.to_a).each do |expected,returned|
-    returned[0].should == expected[:segment].gsub(/'/,"")
-    returned[1].should == expected[:type].to_sym
+    expect(returned[0]).to eq expected[:segment].gsub(/'/,"")
+    expect(returned[1]).to eq expected[:type].to_sym
   end
 end
 
 Then /^the following non-blank segments should be detected$/ do |table|
   segments = @splitter.select{|s| s[1] != :other}
   table.hashes.zip(segments).each do |expected,returned|
-    returned[0].should == expected[:segment].gsub(/'/,"")
-    returned[1].should == expected[:type].to_sym
+    expect(returned[0]).to eq expected[:segment].gsub(/'/,"")
+    expect(returned[1]).to eq expected[:type].to_sym
   end
 end

data/lib/srx/polish/polish-rules.rb

@@ -0,0 +1,114 @@
+module SRX
+  module Polish
+    module Rules
+      def rules
+        @@rules ||=
+[["(?:\\b[Aa]dw?\\.\\s)|(?:\\bafr\\.\\s)|(?:\\bakad\\.\\s)|(?:\\b[Aa]l\\.\\s)|(?:\\bam\\.\\s)|(?:\\bamer\\.\\s)|(?:\\barch\\.\\s)|(?:\\b[Aa]rt\\.\\s)|(?:\\bartyst\\.\\s)|(?:\\bastr\\.\\s)|(?:\\baustr\\.\\s)|(?:\\bbałt\\.\\s)|(?:\\bbdb\\.\\s)|(?:\\bbł\\.\\s)|(?:\\bbm\\.\\s)",
+  nil,
+  false],
+ ["(?:\\bbr\\.\\p{Pe}?\\s)", "[^\\p{Lu}]", false],
+ ["(?:\\bbry[gt]\\.\\s)|(?:\\bcentr\\.\\s)|(?:\\bces\\.\\s)|(?:\\bchem\\.\\s)|(?:\\bchiń\\.\\s)|(?:\\bchir\\.\\s)|(?:\\bc\\.k\\.\\s)|(?:\\bc\\.o\\.\\s)|(?:\\bcyg\\.\\s)|(?:\\bcyw\\.\\s)|(?:\\bcyt\\.\\s)|(?:\\bczes\\.\\s)|(?:\\bczw?\\.\\s)|(?:\\b[Cc]d\\.\\s)|(?:\\bczyt\\.\\s)|(?:\\bćw\\.\\s)|(?:\\bćwicz\\.\\s)|(?:\\bdaw\\.\\s)|(?:\\bdcn\\.\\s)|(?:\\bdekl\\.\\s)|(?:\\bdemokr\\.\\s)|(?:\\bdet\\.\\s)|(?:\\bdiec\\.\\s)|(?:\\bdł\\.\\s)|(?:\\bdn\\.\\s)",
+  nil,
+  false],
+ ["(?:\\bdo[tlp]\\.\\s)", "[^\\p{Lu}]", false],
+ ["(?:\\bdost\\.\\s)|(?:\\bdosł\\.\\s)|(?:\\bh\\.c\\.\\s)|(?:\\bds\\.\\s)|(?:\\bdst\\.\\s)|(?:\\bduszp\\.\\s)|(?:\\bdypl\\.\\s)|(?:\\begz\\.\\s)|(?:\\bekol\\.\\s)|(?:\\bekon\\.\\s)|(?:\\belektr\\.\\s)|(?:\\bem\\.\\s)|(?:\\bew\\.\\s)|(?:\\bfab\\.\\s)|(?:\\bfarm\\.\\s)|(?:\\bfot\\.\\s)|(?:\\bfr\\.\\s)|(?:\\bgat\\.\\s)|(?:\\bgastr\\.\\s)|(?:\\bgeogr\\.\\s)|(?:\\bgeol\\.\\s)|(?:\\bgimn\\.\\s)|(?:\\bgłęb\\.\\s)|(?:\\bgm\\.\\s)|(?:\\bgodz\\.\\s)|(?:\\bgórn\\.\\s)|(?:\\bgosp\\.\\s)|(?:\\bgr\\.\\s)|(?:\\bgram\\.\\s)|(?:\\bhist\\.\\s)|(?:\\bhiszp\\.\\s)|(?:\\b[Hh]r\\.\\s)|(?:\\bhot\\.\\s)|(?:\\bid\\.\\s)|(?:\\bin\\.\\s)|(?:\\bim\\.\\s)|(?:\\biron\\.\\s)|(?:\\bjn\\.\\s)|(?:\\bkard\\.\\s)|(?:\\bkat\\.\\s)|(?:\\bkatol\\.\\s)|(?:\\bk\\.k\\.\\s)|(?:\\bkk\\.\\s)|(?:\\bko?l\\.\\s)|(?:\\bk\\.p\\.a\\.\\s)|(?:\\bkpc\\.\\s)|(?:\\bk\\.p\\.c\\.\\s)|(?:\\bkpt\\.\\s)|(?:\\bkr\\.\\s)|(?:\\bk\\.r\\.\\s)|(?:\\bkrak\\.\\s)|(?:\\bk\\.r\\.o\\.\\s)|(?:\\bkryt\\.\\s)|(?:\\bkult\\.\\s)|(?:\\blaic\\.\\s)|(?:\\błac\\.\\s)|(?:\\bniem\\.\\s)|(?:\\bwoj\\.\\s)|(?:\\b[Nn][bp]\\.\\s)|(?:\\bpo[lw]\\.\\s)|(?:\\bm\\.in\\.\\s)|(?:\\b[Pp][ts]\\.\\s)|(?:\\bcdn\\.\\s)|(?:\\bjw\\.\\s)|(?:\\b[Rr]y[cs]\\.\\s)|(?:\\btj\\.\\s)|(?:\\b[Tt]zw\\.\\s)|(?:\\btzn\\.\\s)|(?:\\b[Zz]ob\\.\\s)|(?:\\bsłow\\.\\s)",
+  nil,
+  false],
+ ["(?:[^s]\\.pl\\.\\s)", "\\p{Lu}\\p{Ll}+", true],
+ ["(?:\\bp[wnl]\\.\\s)|(?:\\bang\\.\\s)|(?:\\bu[lb]\\.\\s?)|(?:\\bal\\.\\s)|(?:\\bk\\.\\s)|(?:\\bn\\.\\s)",
+  nil,
+  false],
+ ["(?:\\b[Oo]k\\.\\s)", "[\\p{Ll}\\d]", false],
+ ["(?:\\b[\\d,\\.]*ty[sś]\\.\\p{Pe}?\\s)", "[\\p{Ll}\\d]+", false],
+ ["(?:\\b[Nn]r\\.\\s)", "\\d", false],
+ ["(?:\\bw[wł]\\.\\s)|(?:\\bur\\.\\s)|(?:\\bzm\\.\\s)|(?:\\bżyd\\.\\s)|(?:\\bżarg\\.\\s)|(?:\\bżyw\\.\\s)|(?:\\bwy[łdm]\\.\\s)|(?:\\b[bu]p\\.\\s)|(?:\\bwyst\\.\\s)",
+  nil,
+  false],
+ ["(?:\\b(?i)mazeł\\stow\\.\\s)", nil, true],
+ ["(?:\\b[Tt]ow\\.\\s)|(?:\\bo\\.\\s)|(?:\\b(?:[sS]p|st|[Ss]półdz|społ|spółgł|[Ss]to[łw])\\.\\s)|(?:\\bzn\\.\\s)|(?:\\bzew\\.\\s)|(?:\\bzewn\\.\\s)|(?:\\bzdr\\.\\s)|(?:\\bzazw\\.\\s)|(?:\\bzast\\.\\s)|(?:\\bzaw\\.\\s)|(?:\\bzał\\.\\s)|(?:\\bzal\\.\\s)|(?:\\bzam\\.\\s)|(?:\\bzak\\.\\s)|(?:\\bzakł\\.\\s)|(?:\\bzagr\\.\\s)|(?:\\bzach\\.\\s)|(?:\\b[Aa]dw\\.\\s)|(?:\\b[Ll]ek\\.\\s)|(?:\\bmed\\.\\s)|(?:\\b[Mm]ec\\.\\s)|(?:\\b[Dd]oc\\.\\s)|(?:\\b[Dd]y[wr]\\.\\s)|(?:\\b[Ii]nż\\.\\s)|(?:\\b(?i)mgr\\.\\s)|(?:\\b[dD][hr]\\.\\s)",
+  nil,
+  false],
+ ["(?:\\b[pP]\\.\\s)", "\\p{Lu}\\p{Ll}+", false],
+ ["(?:\\b[Rr]ed\\.\\)?\\s)|(?:\\b(?i)pro[fk]\\.\\s)|(?:\\bhab\\.\\s)|(?:\\b[Pp]łk\\.\\s)|(?:\\b(?:[Nn]a|[Pp]o)dkom\\.\\s)|(?:\\b[kK]s\\.\\s)|(?:\\b(?i)gen\\.\\s)|(?:\\b(?i)por\\.\\s)|(?:\\b[Rr]eż\\.\\s)|(?:\\b[Pp]rzyp\\.\\s)|(?:\\bp\\.n\\.e\\.\\s)|(?:\\bdyr\\.\\smuz\\.\\s)|(?:\\b[śŚ][pwW]\\.\\s)",
+  nil,
+  false],
+ ["(?:\\bII?\\społ\\.\\s)", "[IVX]+", false],
+ ["(?:\\betc\\.\\s)", "\\p{Ll}", false],
+ ["(?:\\bit[dp]\\.\\s)", "[„”\"]?\\p{Ll}", false],
+ ["(?:\\bproc\\.\\)?\\s)", "\\p{Ll}|\\p{Lu}\\p{Lu}+", false],
+ ["(?:\\b[rwn]\\.\\s)|(?:\\bit[dp]\\.\\s)|(?:\\bcdn\\.\\s)", "\\p{Ll}", false],
+ ["(?:\\b[Ss]zer\\.\\s)", nil, false],
+ ["(?:\\bjw\\.\\s)|(?:\\bn\\.e\\.\\s)|(?:\\bw\\.\\s)|(?:\\bn[tn]\\.\\s)|(?:\\b[dm]l\\.\\s)|(?:\\bdag\\.\\s)|(?:\\b[cd]?m\\.\\s)|(?:\\b[Zz][Łł]\\.\\s)|(?:\\b[Gg][rR]\\.\\s)|(?:\\b[d]?kg\\.\\s)|(?:\\bml[nd]\\.\\s)|(?:\\bnpl\\.\\s)",
+  "\\p{Ll}",
+  false],
+ ["(?:\\bpkt\\.\\s)|(?:\\bstr\\.\\s)|(?:\\b[Tt]ab\\.\\s)",
+  "[\\p{Ll}\\d]",
+  false],
+ ["(?:\\btel\\.\\s)", nil, false],
+ ["(?:\\b[ptw]g\\.\\s)|(?:\\bcos\\.\\s)|(?:\\bcosec\\.\\s)|(?:\\bsec\\.\\s)|(?:\\bsin\\.\\s)|(?:\\brkm\\.\\s)",
+  "\\p{Ll}",
+  false],
+ ["(?:\\bust\\.\\s)|(?:\\bpar\\.\\s)", "\\d", false],
+ ["(?:\\blit\\.\\s)", "\\p{Ll}\\p{Pe}?\\p{P}?\\s", false],
+ ["(?:\\b[Pp]on\\.\\s)|(?:\\b[Ss]ob\\.\\s)|(?:\\bba!\\s)", "\\p{Ll}", false],
+ ["(?:\\bpo[zk]\\.\\s)", nil, false],
+ ["(?:\\bop\\.\\s)", "cit\\.", false],
+ ["(?:\\b[Oo][Oo]\\.\\s)", nil, false],
+ ["(?:\\b(?:[CDSR]z|Ch)\\.\\s)", "\\p{Ll}", false],
+ ["(?:\\b[rls]\\.\\s)", "[1-9]+", false],
+ ["(?:\\((?:od|do|w)\\s[1-9]\\d*\\sr\\.\\s)", nil, false],
+ ["(?:\\d+\\sr\\.\\s)|(?:\\bn\\.e\\.\\s)", "[^\\p{Lu}]", false],
+ ["(?:\\bt\\.\\s)", "\\d+", false],
+ ["(?:\\b[,uoi]\\ss\\.\\s)|(?:\\b[Nn]ajśw\\.\\s)|(?:\\b[Nn]a\\sos\\.\\s)",
+  nil,
+  false],
+ ["(?:\\bT\\.)", "Love\\b", false],
+ ["(?:\\bpl\\.)", "Open[oO]ffice", false],
+ ["(?:\\bha\\.\\s)", "[\\p{Ll}]", false],
+ ["(?:\\bmin\\.\\s)", "[\\p{Ll}\\d]", false],
+ ["(?:\\bW\\s\\d{4}\\sr\\.\\s)", "[\\p{Lu}–—„\"-]", false],
+ ["(?:\\b\\d+\\.\\s)", "\\p{Ll}|\\p{Lu}{2,}", false],
+ ["(?:\\b\\p{L}\\.\\s)", "\\p{L}\\.\\s", false],
+ ["(?:\\b\\p{L}\\.)", "\\p{L}\\.", false],
+ ["(?:\\.\\p{L}+\\.\\s)", "\\p{Ll}", false],
+ ["(?:[\\s\\(\\[][\\p{L}&&[^rwn]]\\.\\s+)",
+  "\\p{Ll}\\p{Ll}|\\p{Lu}[\\p{Punct}\\p{Lu}]",
+  false],
+ ["(?:['\"„][\\.!?…]['\"”]\\s)", nil, false],
+ ["(?:[\"”']\\s*)", "\\s*\\p{Ll}", false],
+ ["(?:[!?]+\\p{Pe} )", "\\p{Ll}", false],
+ ["(?:[\\p{Ps}][!?]+[\\p{Pe}] )", nil, false],
+ ["(?:[\\[\\(]*\\.\\.\\.[\\]\\)]* )|(?:[\\[\\(]*…[\\]\\)]* )",
+  "\\p{Ll}",
+  false],
+ ["(?:\\b\\p{Lu}\\.\\s\\p{Lu}\\.\\s)|(?:\\b\\p{Lu}\\.\\p{Lu}\\.\\s)",
+  nil,
+  false],
+ ["(?:\\b\\p{Lu}\\p{Ll}\\.\\s?)|(?:\\.\\p{Lu}\\p{Ll}\\.\\s?)",
+  "\\p{Lu}[^\\p{Lu}]",
+  false],
+ ["(?:\\s(?<!\\.)[„\"\\p{Ps}]?[A-Z]\\.\\s)|(?:^[„\"]?[A-ZŚĆŻŹ]\\.\\s)",
+  "\\p{Ll}|\\p{Lu}\\p{Ll}\\p{Ll}+",
+  false],
+ ["(?:\\(\\p{Lu}?\\p{Ll}+\\.\\s)", nil, false],
+ ["(?:\\s[A-Z]\\.\\s)", "\\(\\d", false],
+ ["(?:\\bDz\\.\\s?U\\.\\s)", nil, false],
+ ["(?:[\\p{Ll}&&[^aeouiyęąó]][\\p{Ll}&&[^aeouiyęąó]]+\\.\\s)",
+  "\\p{Ll}+",
+  false],
+ ["(?:[\\.!?…]+['\"\\p{Pe}\\u00BB\\u2019\\u201D\\u203A\\u0002]*\\s)",
+  "[\\p{Ps}–—-]\\s?\\p{Ll}",
+  false],
+ ["(?:[\\.!?…]['\"\\u00BB\\u2019\\u201D\\u203A\\u0002]*\\p{Pe}\\s)",
+  "\\p{Ll}",
+  false],
+ ["(?:[\\.!?…]['\"\\p{Pe}\\u00BB\\u2019\\u201D\\u203A\\u0002¹²³]*\\s)",
+  nil,
+  true],
+ ["(?:[\\.!?…]['»\"”\\p{Pe}]*)", "\\p{Lu}[^\\p{Lu}\\.]", true],
+ ["(?:\\s\\p{L}[\\.!?…]\\s)", "\\p{Lu}\\p{Ll}", true],
+ ["(?:: )", "[—\\-–] \\p{Lu}", true]]
+      end
+    end
+  end
+end

data/lib/srx/polish/sentence_splitter.rb

@@ -1,58 +1,13 @@
 #encoding: utf-8
 require 'stringio'
 require 'term/ansicolor'
+require_relative 'polish-rules'
 module SRX
   module Polish
-    RULES =
-[["(?:\\b[Aa]l\\.\\s)|(?:\\b[Aa]rt\\.\\s)|(?:\\b[Cc]d\\.\\s)|(?:\\b[Hh]r\\.\\s)|(?:\\b[Nn][bp]\\.\\s)|(?:\\b[Pp][ts]\\.\\s)|(?:\\b[Rr]y[cs]\\.\\s)|(?:\\b[Tt]zw\\.\\s)|(?:\\b[\\d,\\.]*ty[sś]\\.\\p{Pe}?\\s)|(?:\\b[bu]p\\.\\s)|(?:\\badw\\.\\s)|(?:\\bafr\\.\\s)|(?:\\bakad\\.\\s)|(?:\\bal\\.\\s)|(?:\\bam\\.\\s)|(?:\\bamer\\.\\s)|(?:\\bang\\.\\s)|(?:\\barch\\.\\s)|(?:\\bartyst\\.\\s)|(?:\\bastr\\.\\s)|(?:\\baustr\\.\\s)|(?:\\bbałt\\.\\s)|(?:\\bbdb\\.\\s)|(?:\\bbm\\.\\s)|(?:\\bbr\\.\\p{Pe}?\\s)|(?:\\bbry[gt]\\.\\s)|(?:\\bbł\\.\\s)|(?:\\bc\\.k\\.\\s)|(?:\\bc\\.o\\.\\s)|(?:\\bcdn\\.\\s)|(?:\\bcentr\\.\\s)|(?:\\bces\\.\\s)|(?:\\bchem\\.\\s)|(?:\\bchir\\.\\s)|(?:\\bchiń\\.\\s)|(?:\\bcyg\\.\\s)|(?:\\bcyt\\.\\s)|(?:\\bcyw\\.\\s)|(?:\\bczes\\.\\s)|(?:\\bczw\\.\\s)|(?:\\bczyt\\.\\s)|(?:\\bdaw\\.\\s)|(?:\\bdcn\\.\\s)|(?:\\bdekl\\.\\s)|(?:\\bdemokr\\.\\s)|(?:\\bdet\\.\\s)|(?:\\bdiec\\.\\s)|(?:\\bdn\\.\\s)|(?:\\bdo[tlp]\\.\\s)|(?:\\bdost\\.\\s)|(?:\\bdosł\\.\\s)|(?:\\bds\\.\\s)|(?:\\bdst\\.\\s)|(?:\\bduszp\\.\\s)|(?:\\bdypl\\.\\s)|(?:\\bdł\\.\\s)|(?:\\begz\\.\\s)|(?:\\bekol\\.\\s)|(?:\\bekon\\.\\s)|(?:\\belektr\\.\\s)|(?:\\bem\\.\\s)|(?:\\bew\\.\\s)|(?:\\bfab\\.\\s)|(?:\\bfarm\\.\\s)|(?:\\bfot\\.\\s)|(?:\\bfr\\.\\s)|(?:\\bgastr\\.\\s)|(?:\\bgat\\.\\s)|(?:\\bgeogr\\.\\s)|(?:\\bgeol\\.\\s)|(?:\\bgimn\\.\\s)|(?:\\bgm\\.\\s)|(?:\\bgodz\\.\\s)|(?:\\bgosp\\.\\s)|(?:\\bgr\\.\\s)|(?:\\bgram\\.\\s)|(?:\\bgórn\\.\\s)|(?:\\bgłęb\\.\\s)|(?:\\bh\\.c\\.\\s)|(?:\\bhist\\.\\s)|(?:\\bhiszp\\.\\s)|(?:\\bhot\\.\\s)|(?:\\bid\\.\\s)|(?:\\bim\\.\\s)|(?:\\bin\\.\\s)|(?:\\biron\\.\\s)|(?:\\bjn\\.\\s)|(?:\\bjw\\.\\s)|(?:\\bk\\.\\s)|(?:\\bk\\.k\\.\\s)|(?:\\bk\\.p\\.a\\.\\s)|(?:\\bk\\.p\\.c\\.\\s)|(?:\\bk\\.r\\.\\s)|(?:\\bk\\.r\\.o\\.\\s)|(?:\\bkard\\.\\s)|(?:\\bkat\\.\\s)|(?:\\bkatol\\.\\s)|(?:\\bkk\\.\\s)|(?:\\bko?l\\.\\s)|(?:\\bkpc\\.\\s)|(?:\\bkpt\\.\\s)|(?:\\bkr\\.\\s)|(?:\\bkrak\\.\\s)|(?:\\bkryt\\.\\s)|(?:\\bkult\\.\\s)|(?:\\blaic\\.\\s)|(?:\\bm\\.in\\.\\s)|(?:\\bn\\.\\s)|(?:\\bniem\\.\\s)|(?:\\bp[wnl]\\.\\s)|(?:\\bpo[lw]\\.\\s)|(?:\\btj\\.\\s)|(?:\\btzn\\.\\s)|(?:\\bu[lb]\\.\\s?)|(?:\\bur\\.\\s)|(?:\\bw[wł]\\.\\s)|(?:\\bwoj\\.\\s)|(?:\\bwyst\\.\\s)|(?:\\bwył\\.\\s)|(?:\\bzm\\.\\s)|(?:\\bzob\\.\\s)|(?:\\bćw\\.\\s)|(?:\\bćwicz\\.\\s)|(?:\\błac\\.\\s)|(?:\\bżarg\\.\\s)|(?:\\bżyd\\.\\s)|(?:\\bżyw\\.\\s)",
-  nil,
-  false],
- ["(?:\\b[Oo]k\\.\\s)", "[\\p{Ll}\\d]", false],
- ["(?:\\b[Nn]r\\.\\s)", "\\d", false],
- ["(?:\\b(?i)mazeł\\stow\\.\\s)", nil, true],
- ["(?:['\"„][\\.!?…]['\"”]\\s)|(?:[\\p{Ps}][!?]+[\\p{Pe}] )|(?:\\b(?:[Nn]a|[Pp]o)dkom\\.\\s)|(?:\\b(?:[sS]p|st|[Ss]półdz|społ|spółgł|[Ss]to[łw])\\.\\s)|(?:\\b(?i)gen\\.\\s)|(?:\\b(?i)mgr\\.\\s)|(?:\\b(?i)por\\.\\s)|(?:\\b(?i)pro[fk]\\.\\s)|(?:\\bDz\\.\\s?U\\.\\s)|(?:\\b[,uoi]\\ss\\.\\s)|(?:\\b[Aa]dw\\.\\s)|(?:\\b[Dd]oc\\.\\s)|(?:\\b[Dd]y[wr]\\.\\s)|(?:\\b[Ii]nż\\.\\s)|(?:\\b[Ll]ek\\.\\s)|(?:\\b[Mm]ec\\.\\s)|(?:\\b[Nn]a\\sos\\.\\s)|(?:\\b[Nn]ajśw\\.\\s)|(?:\\b[Oo][Oo]\\.\\s)|(?:\\b[Pp]rzyp\\.\\s)|(?:\\b[Pp]łk\\.\\s)|(?:\\b[Rr]ed\\.\\)?\\s)|(?:\\b[Rr]eż\\.\\s)|(?:\\b[Ss]zer\\.\\s)|(?:\\b[Tt]ow\\.\\s)|(?:\\b[dD][hr]\\.\\s)|(?:\\b[kK]s\\.\\s)|(?:\\b[śŚ][pwW]\\.\\s)|(?:\\b\\p{Lu}\\.\\p{Lu}\\.\\s)|(?:\\b\\p{Lu}\\.\\s\\p{Lu}\\.\\s)|(?:\\bhab\\.\\s)|(?:\\bmed\\.\\s)|(?:\\bo\\.\\s)|(?:\\bpo[zk]\\.\\s)|(?:\\btel\\.\\s)|(?:\\bzach\\.\\s)|(?:\\bzagr\\.\\s)|(?:\\bzak\\.\\s)|(?:\\bzakł\\.\\s)|(?:\\bzal\\.\\s)|(?:\\bzam\\.\\s)|(?:\\bzast\\.\\s)|(?:\\bzaw\\.\\s)|(?:\\bzazw\\.\\s)|(?:\\bzał\\.\\s)|(?:\\bzdr\\.\\s)|(?:\\bzew\\.\\s)|(?:\\bzewn\\.\\s)|(?:\\bzn\\.\\s)",
-  nil,
-  false],
- ["(?:\\b[rls]\\.\\s)", "[1-9]+", false],
- ["(?:\\b[Tt]ab\\.\\s)|(?:\\bmin\\.\\s)|(?:\\bpkt\\.\\s)|(?:\\bstr\\.\\s)",
-  "[\\p{Ll}\\d]",
-  false],
- ["(?:\\bW\\s\\d{4}\\sr\\.\\s)", "[\\p{Lu}–—„\"-]", false],
- ["(?:[\\.!?…]+['\"\\p{Pe}\\u00BB\\u2019\\u201D\\u203A\\u0002]*\\s)",
-  "[\\p{Ps}–—-]\\s?\\p{Ll}",
-  false],
- ["(?:\\bit[dp]\\.\\s)", "[„”\"]?\\p{Ll}", false],
- ["(?:\\s[A-Z]\\.\\s)", "\\(\\d", false],
- ["(?:\\bpar\\.\\s)|(?:\\bust\\.\\s)", "\\d", false],
- ["(?:[!?]+\\p{Pe} )|(?:[\\.!?…]['\"\\u00BB\\u2019\\u201D\\u203A\\u0002]*\\p{Pe}\\s)|(?:[\\[\\(]*\\.\\.\\.[\\]\\)]* )|(?:[\\[\\(]*…[\\]\\)]* )|(?:\\.\\p{L}+\\.\\s)|(?:\\b(?:[CDSR]z|Ch)\\.\\s)|(?:\\b[Gg][rR]\\.\\s)|(?:\\b[Pp]on\\.\\s)|(?:\\b[Ss]ob\\.\\s)|(?:\\b[Zz][Łł]\\.\\s)|(?:\\b[cd]?m\\.\\s)|(?:\\b[d]?kg\\.\\s)|(?:\\b[dm]l\\.\\s)|(?:\\b[ptw]g\\.\\s)|(?:\\b[rwn]\\.\\s)|(?:\\bba!\\s)|(?:\\bcdn\\.\\s)|(?:\\bcos\\.\\s)|(?:\\bcosec\\.\\s)|(?:\\bdag\\.\\s)|(?:\\betc\\.\\s)|(?:\\bit[dp]\\.\\s)|(?:\\bjw\\.\\s)|(?:\\bml[nd]\\.\\s)|(?:\\bn[tn]\\.\\s)|(?:\\bn\\.e\\.\\s)|(?:\\bnpl\\.\\s)|(?:\\brkm\\.\\s)|(?:\\bsec\\.\\s)|(?:\\bsin\\.\\s)|(?:\\bw\\.\\s)",
-  "\\p{Ll}",
-  false],
- ["(?:[\\p{Ll}&&[^aeouiyęąó]][\\p{Ll}&&[^aeouiyęąó]]+\\.\\s)",
-  "\\p{Ll}+",
-  false],
- ["(?:[\\s\\(\\[][\\p{L}&&[^rwn]]\\.\\s+)",
-  "\\p{Ll}\\p{Ll}|\\p{Lu}[\\p{Punct}\\p{Lu}]",
-  false],
- ["(?:\\blit\\.\\s)", "\\p{Ll}\\p{Pe}?\\p{P}?\\s", false],
- ["(?:\\s(?<!\\.)[„\"\\p{Ps}]?[A-Z]\\.\\s)|(?:^[„\"]?[A-ZŚĆŻŹ]\\.\\s)",
-  "\\p{Ll}|\\p{Lu}\\p{Ll}\\p{Ll}+",
-  false],
- ["(?:\\bproc\\.\\)?\\s)", "\\p{Ll}|\\p{Lu}\\p{Lu}+", false],
- ["(?:\\b\\d+\\.\\s)", "\\p{Ll}|\\p{Lu}{2,}", false],
- ["(?:\\.\\p{Lu}\\p{Ll}\\.\\s?)|(?:\\b\\p{Lu}\\p{Ll}\\.\\s?)",
-  "\\p{Lu}[^\\p{Lu}]",
-  false],
- ["(?:\\b[pP]\\.\\s)", "\\p{Lu}\\p{Ll}+", false],
- ["(?:\\b\\p{L}\\.)", "\\p{L}\\.", false],
- ["(?:\\b\\p{L}\\.\\s)", "\\p{L}\\.\\s", false],
- ["(?:[\"”']\\s*)", "\\s*\\p{Ll}", false],
- ["(?:[\\.!?…]['\"\\p{Pe}\\u00BB\\u2019\\u201D\\u203A\\u0002]*\\s)|(?:\\r?\\n\\s*\\r?\\n[\\t]*)",
-  nil,
-  true],
- ["(?:[\\.!?…]['»\"”\\p{Pe}]*)", "\\p{Lu}[^\\p{Lu}\\.]", true],
- ["(?:\\s\\p{L}[\\.!?…]\\s)", "\\p{Lu}\\p{Ll}", true]]
-    BEFORE_RE = /(?:#{RULES.map{|s,e,v| "(#{s})"}.join("|")})\Z/m
-    REGEXPS = RULES.map{|s,e,v| [/(#{s})\Z/m,/\A(#{e})/m,v] }
+    extend Rules
+
+    BEFORE_RE = /(?:#{self.rules.map{|s,e,v| "(#{s})"}.join("|")})\Z/m
+    REGEXPS = self.rules.map{|s,e,v| [/(#{s})\Z/m,/\A(#{e})/m,v] }
     FIRST_CHAR = /\A./m
 
     class SentenceSplitter
@@ -67,50 +22,54 @@ module SRX
         else
           @input = text
         end
+        @debug = false
       end
 
       def each
-        raise "Invalid argument - text is nil" if @input.nil?
-        buffer_length = 10
-        sentence = ""
-        before_buffer = ""
-        @input.pos = 0
-        after_buffer = buffer_length.times.map{|i| @input.readchar}.join("")
-        matched_rule = nil
-        while(!@input.eof?) do
-          matched_before = BEFORE_RE.match(before_buffer)
-          break_detected = false
-          if matched_before
-            start_index = (matched_before.size - 1).times.find do |index|
-              matched_before[index+1]
-            end
-            if @debug
-              puts "#{before_buffer}|#{after_buffer.gsub(/\n/,"\\n")}"
-            end
-            REGEXPS.each do |before_re,after_re,value|
-              # skip the whole match
-              if before_re.match(before_buffer) && after_re.match(after_buffer)
-                break_detected = true
-                color = value ? :red : :green
-                if @debug
-                  sentence << Term::ANSIColor.send(color,"<#{before_re}:#{after_re}>")
-                end
-                if value
-                  yield sentence
-                  sentence = ""
+        if block_given?
+          raise "Invalid argument - text is nil" if @input.nil?
+          buffer_length = 10
+          sentence = ""
+          before_buffer = ""
+          @input.pos = 0
+          after_buffer = buffer_length.times.map{|i| @input.readchar }.join("")
+          while(!@input.eof?) do
+            matched_before = BEFORE_RE.match(before_buffer)
+            break_detected = false
+            if matched_before
+              (matched_before.size - 1).times.find do |index|
+                matched_before[index+1]
+              end
+              if @debug
+                puts "#{before_buffer}|#{after_buffer.gsub(/\n/,"\\n")}"
+              end
+              REGEXPS.each do |before_re,after_re,value|
+                # skip the whole match
+                if before_re.match(before_buffer) && after_re.match(after_buffer)
+                  break_detected = true
+                  if @debug
+                    color = value ? :red : :green
+                    sentence << Term::ANSIColor.send(color,"<#{before_re}:#{after_re}>")
+                  end
+                  if value
+                    yield sentence
+                    sentence = ""
+                  end
+                  break
                 end
-                break
               end
             end
+            next_after = @input.readchar
+            before_buffer.sub!(FIRST_CHAR,"") if before_buffer.size >= buffer_length
+            after_buffer.sub!(FIRST_CHAR,"")
+            before_buffer << $&
+              sentence << $&
+              after_buffer << next_after
           end
-          next_after = @input.readchar
-          before_buffer.sub!(FIRST_CHAR,"") if before_buffer.size >= buffer_length
-          after_buffer.sub!(FIRST_CHAR,"")
-          before_buffer << $&
-          sentence << $&
-          after_buffer << next_after
+          yield sentence + after_buffer unless sentence.empty? || after_buffer.empty?
+        else
+          enum_for(:each)
         end
-        yield sentence + after_buffer unless sentence.empty? || after_buffer.empty?
       end
     end
   end

data/srx-polish.gemspec

@@ -3,9 +3,9 @@ $:.push File.expand_path("../lib", __FILE__)
 
 Gem::Specification.new do |s|
   s.name        = "srx-polish"
-  s.version     = "0.2.1"
+  s.version     = "0.3.0"
   s.platform    = Gem::Platform::RUBY
-  s.authors     = ["Aleksander Pohl"]
+  s.authors     = ["Aleksander Smywiński-Pohl"]
   s.email       = ["apohllo@o2.pl"]
   s.homepage    = "http://github.com/apohllo/srx2ruby"
   s.summary     = %q{Polish sentence and word segmentation rules.}
@@ -19,5 +19,5 @@ Gem::Specification.new do |s|
   s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
   s.require_paths = ["lib"]
 
-  s.add_dependency("term-ansicolor", ["~> 1.0.5"])
+  s.add_dependency 'term-ansicolor', '~> 1.0', '>= 1.0.5'
 end

metadata

@@ -1,77 +1,77 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: srx-polish
-version: !ruby/object:Gem::Version 
-  prerelease: 
-  version: 0.2.1
+version: !ruby/object:Gem::Version
+  version: 0.3.0
 platform: ruby
-authors: 
-- Aleksander Pohl
+authors:
+- Aleksander Smywiński-Pohl
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-10-14 00:00:00 Z
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2018-07-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: term-ansicolor
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
-    - - ~>
-      - !ruby/object:Gem::Version 
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
         version: 1.0.5
   type: :runtime
-  version_requirements: *id001
-description: "Polish sentence and word segmentation rules. The sentence segmentation rules are based on Marcin Mi\xC5\x82kowski's SRX rules."
-email: 
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.0.5
+description: Polish sentence and word segmentation rules. The sentence segmentation
+  rules are based on Marcin Miłkowski's SRX rules.
+email:
 - apohllo@o2.pl
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
-- .gitignore
+files:
+- ".gitignore"
+- ".ruby-version"
+- Gemfile
 - README.rdoc
 - changelog.txt
 - features/sentence_splitter.feature
 - features/steps/sentence_splitter.rb
 - features/steps/word_splitter.rb
 - features/word_splitter.feature
+- lib/srx/polish/polish-rules.rb
 - lib/srx/polish/sentence_splitter.rb
 - lib/srx/polish/word_splitter.rb
 - srx-polish.gemspec
 homepage: http://github.com/apohllo/srx2ruby
 licenses: []
-
+metadata: {}
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: srx-polish
-rubygems_version: 1.8.5
+rubygems_version: 2.6.14
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Polish sentence and word segmentation rules.
-test_files: 
-- features/sentence_splitter.feature
-- features/steps/sentence_splitter.rb
-- features/steps/word_splitter.rb
-- features/word_splitter.feature
+test_files: []