srx-languagetool 0.12.0 → 0.14.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b095dc51541d60d446b063cdff16940d7840e7d51891e1f5201117d42089b0da
-  data.tar.gz: 5376dce7bda3c17a142477a3b19f629e65527c4fb96d540bfa1a853f0ed394f8
+  metadata.gz: a71886af9137758228b7fdbb92b1e0c9e8f64c1b3456597660186b43379bf098
+  data.tar.gz: 621f91e2be6bc34a564259f61953b56e02cb57aeaa7c68fdea2770f39ee2631a
 SHA512:
-  metadata.gz: eb9f0aac7af1e2345842bdaf21917556429d8c887d356430c4c707b18b82d0a54cc46a5b6344247de27113f3ad0730f0d3fa37012f4a7c5c7cf4987dcedcf271
-  data.tar.gz: 3370f8761982aa574c862f32d9a2702451cb992fa35dd0f842a4116224d448c7a2dd247be0ac2c61cace69f72364963c9072bd72e3fc2c46a3bc948996c8fc61
+  metadata.gz: 2dd8b533adbd82f274f492b1243330554a35a8e98d88af8a7790d2aaef6b2ebb85c0a3f0fc4bb87964b9a0135a5efd65554dbdae0ab8569e0838dbb2e5f504ef
+  data.tar.gz: d5270d27a3dba9622b84ebfb1a6874c5eaeb655cdc933e61001ae9827fbfd0158bd7ebe7da4491145d8acc1273501aa7aee2c687438f957026a3c16c5273c2a3

data/.github/workflows/main.yml

@@ -6,14 +6,14 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: 2.7.7
+        ruby-version: 3.2.3
     - name: Install
       run: |
-        gem install bundler -v 2.4.10
+        gem install bundler -v 2.5.7
         bundle install
     - name: Type check
       run: bundle exec solargraph typecheck --level typed

data/.ruby-version

@@ -1 +1 @@
-2.7.7
+3.2.3

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 ## [Unreleased]
 
+## [0.14.0] - 2024-09-27
+
+- Update rules to LanguageTool 6.5
+
+## [0.13.0] - 2024-03-29
+
+- Update rules to LanguageTool 6.4
+
 ## [0.12.0] - 2023-10-07
 
 - Update rules to LanguageTool 6.3

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    srx-languagetool (0.12.0)
+    srx-languagetool (0.14.0)
       srx (< 1.0)
 
 GEM
@@ -9,74 +9,77 @@ GEM
   specs:
     ast (2.4.2)
     backport (1.2.0)
-    benchmark (0.2.1)
+    benchmark (0.3.0)
     byebug (11.1.3)
-    diff-lcs (1.5.0)
+    diff-lcs (1.5.1)
     e2mmap (0.1.0)
-    jaro_winkler (1.5.4)
-    json (2.6.3)
+    jaro_winkler (1.6.0)
+    json (2.7.2)
     kramdown (2.4.0)
       rexml
     kramdown-parser-gfm (1.1.0)
       kramdown (~> 2.0)
-    minitest (5.18.0)
-    nokogiri (1.14.2-x86_64-darwin)
+    language_server-protocol (3.17.0.3)
+    minitest (5.25.1)
+    nokogiri (1.16.7-x86_64-darwin)
       racc (~> 1.4)
-    parallel (1.22.1)
-    parser (3.2.1.1)
+    parallel (1.26.3)
+    parser (3.3.5.0)
       ast (~> 2.4.1)
-    racc (1.6.2)
+      racc
+    racc (1.8.1)
     rainbow (3.1.1)
-    rake (13.0.6)
-    regexp_parser (2.7.0)
+    rake (13.2.1)
+    rbs (2.8.4)
+    regexp_parser (2.9.2)
     reverse_markdown (2.1.1)
       nokogiri
-    rexml (3.2.5)
-    rspec-expectations (3.12.2)
+    rexml (3.3.7)
+    rspec-expectations (3.13.3)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-support (3.12.0)
-    rubocop (1.48.1)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.1)
+    rubocop (1.66.1)
       json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.0.0)
+      parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
-      regexp_parser (>= 1.8, < 3.0)
-      rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.26.0, < 2.0)
+      regexp_parser (>= 2.4, < 3.0)
+      rubocop-ast (>= 1.32.2, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.28.0)
-      parser (>= 3.2.1.0)
+    rubocop-ast (1.32.3)
+      parser (>= 3.3.1.0)
     ruby-progressbar (1.13.0)
-    solargraph (0.48.0)
+    solargraph (0.50.0)
       backport (~> 1.2)
       benchmark
-      bundler (>= 1.17.2)
+      bundler (~> 2.0)
       diff-lcs (~> 1.4)
       e2mmap
       jaro_winkler (~> 1.5)
       kramdown (~> 2.3)
       kramdown-parser-gfm (~> 1.1)
       parser (~> 3.0)
-      reverse_markdown (>= 1.0.5, < 3)
-      rubocop (>= 0.52)
+      rbs (~> 2.0)
+      reverse_markdown (~> 2.0)
+      rubocop (~> 1.38)
       thor (~> 1.0)
       tilt (~> 2.0)
       yard (~> 0.9, >= 0.9.24)
     srx (0.6.0)
       nokogiri (~> 1.11)
-    thor (1.2.1)
-    tilt (2.1.0)
-    unicode-display_width (2.4.2)
-    webrick (1.7.0)
-    yard (0.9.28)
-      webrick (~> 1.7.0)
+    thor (1.3.2)
+    tilt (2.4.0)
+    unicode-display_width (2.6.0)
+    yard (0.9.37)
 
 PLATFORMS
   x86_64-darwin-20
   x86_64-darwin-21
   x86_64-darwin-22
+  x86_64-darwin-23
 
 DEPENDENCIES
   byebug
@@ -88,4 +91,4 @@ DEPENDENCIES
   srx-languagetool!
 
 BUNDLED WITH
-   2.4.10
+   2.5.7

data/lib/srx/languagetool/version.rb

@@ -2,6 +2,6 @@
 
 module Srx
   module Languagetool
-    VERSION = '0.12.0'
+    VERSION = '0.14.0'
   end
 end

data/lib/srx/segment.srx

@@ -5,7 +5,7 @@
 <formathandle type="end" include="yes"></formathandle>
 <formathandle type="isolated" include="no"></formathandle>
 <okpsrx:options oneSegmentIncludesAll="no" trimLeadingWhitespaces="no" trimTrailingWhitespaces="no" useJavaRegex="yes" useIcu4JBreakRules="no" treatIsolatedCodesAsWhitespace="no"></okpsrx:options>
-<okpsrx:sample language="nl" useMappedRules="yes">Wat God buiten Christus is. 2.</okpsrx:sample>
+<okpsrx:sample language="nl" useMappedRules="yes"> ON! is een omroep.</okpsrx:sample>
 <okpsrx:rangeRule></okpsrx:rangeRule>
 </header>
 <body>
@@ -1107,6 +1107,14 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="English">
+<rule break="no"><!-- https://www.seven.one/ -->
+<beforebreak>\b[Se]even\.</beforebreak>
+<afterbreak>[Oo]ne\b</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b[1-9]\.[\s\u00A0]</beforebreak>
+<afterbreak>[a-z]</afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>[\u00A0\s]</beforebreak>
 <afterbreak>\n</afterbreak>
@@ -1164,7 +1172,7 @@
 <afterbreak>D\.?</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b([Aa]vg|[Ee]d|pp|[Vv]iz|i\.?[\s\u00A0]*e|[Vvol]|[Rr]col|maj|Lt|[Ff]ig|[Ff]igs|[Vv]iz|[Vv]ols|[Aa]pprox|[Aa]cq|[Ii]ncl?|[Aa]cc|Pres|[Cc]orp|[Ee]x|[Cc]onn|[Dd]ept|[Ll]tda|[Mm]in|[Mm]ax|[Gg]ovt|[Rr]etd|Ing|lb|lbf|ft|c\.?[\s\u00A0]*f|vs|dia|lbs|\d+-(:?oz|kc|in|h[rp]|ml)|M?sec)\.[\s\u00A0]</beforebreak>
+<beforebreak>\b([Aa]vg|[Ee]d|pp|[Vv]iz|i\.?[\s\u00A0]*e|[Vvol]|[Rr]col|maj|Lt|[Ff]ig|[Ee]xt|[Ff]igs|[Vv]iz|[Vv]ols|[Aa]pprox|[Aa]cq|[Ii]ncl?|[Ee]xcl|[Aa]cc|Pres|[Cc]orp|[Ee]x|[Cc]onn|[Dd]ept|[Ll]tda|[Mm]in|[Mm]ax|[Gg]ovt|[Rr]etd|Ing|lb|lbf|ft|c\.?[\s\u00A0]*f|vs|dia|lbs|\d+-(:?oz|kc|in|h[rp]|ml)|M?sec)\.[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{Lu}]|I</afterbreak>
 </rule>
 <rule break="no">
@@ -1273,7 +1281,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\bLL\.[\s\u00A0]?[BM]\.[\s\u00A0]</beforebreak>
+<beforebreak>\bLL\.[\s\u00A0]?[BMD]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1282,7 +1290,7 @@
 </rule>
 <rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?</beforebreak>
-<afterbreak>[BM]\.?</afterbreak>
+<afterbreak>[BMD]\.?</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
@@ -1329,7 +1337,11 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\bCorp\.[\s\u00A0]</beforebreak>
+<beforebreak>\b[cC]orp\.[\s\u00A0]</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b[Rr]eg\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1540,6 +1552,15 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="Dutch">
+<rule break="no">
+<beforebreak>\sart\.\s</beforebreak>
+<afterbreak>[IVX]+[ .]</afterbreak>
+</rule>
+<!--Do not break after abbreviation of type a.b.c.-->
+<rule break="no">
+<beforebreak>\s([a-z]\.){2,10}\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
 <rule break="yes">
 <beforebreak>[ ]is[.][ ]</beforebreak>
 <afterbreak>[0-9]\.($|[ ])</afterbreak>
@@ -1582,7 +1603,7 @@
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="yes">
-<beforebreak>\s(la|do|del)\sMar\.\s</beforebreak>
+<beforebreak>\s(la|do|del?)\sMar\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1641,6 +1662,14 @@
 <beforebreak>\b(geb|[Gg]em|get|gld|id|[Ii]ncl|ind|inf|ing|intern|[Ss]ec|inz|ir|jhr|jkvr)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<rule break="yes">
+<beforebreak>\s(tel|red|min)\.\s</beforebreak>
+<afterbreak>[A-Z]</afterbreak>
+</rule>
+<rule break="yes">
+<beforebreak>\.(nl|be|com)\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>\b(jl|jr|kr|kt|lic|ll|lt|lw|max|[Mm]evr|mi|[Mm]in|mld)\.\s</beforebreak>
 <afterbreak></afterbreak>
@@ -1662,6 +1691,10 @@
 <afterbreak>[A-Z]</afterbreak>
 </rule>
 <rule break="yes">
+<beforebreak>\svitamine [A-Z]\.\s</beforebreak>
+<afterbreak>[A-Z]</afterbreak>
+</rule>
+<rule break="yes">
 <beforebreak>°C\.\s</beforebreak>
 <afterbreak>[A-Z][a-z]</afterbreak>
 </rule>
@@ -1714,6 +1747,34 @@
 <afterbreak>\p{L}\.\s</afterbreak>
 </rule>
 <rule break="no">
+<beforebreak>\set al\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<!--pa. as (wrong) abbrev for pag.-->
+<rule break="no">
+<beforebreak>\spa\.\s</beforebreak>
+<afterbreak>[0-9]</afterbreak>
+</rule>
+<!--op. as abbrev for opus-->
+<rule break="no">
+<beforebreak>\sop\.\s</beforebreak>
+<afterbreak>[0-9]|cit\.</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\soa\.\s</beforebreak>
+<afterbreak>[a-z]</afterbreak>
+</rule>
+<!--al. as abbrev for alinea-->
+<rule break="no">
+<beforebreak>\sal\.\s</beforebreak>
+<afterbreak>[0-9]</afterbreak>
+</rule>
+<!--Break also when the next sentence has no capital-->
+<rule break="yes">
+<beforebreak>\s((is|op|in|af|ik|ze|om|me|je|na|nu|al|ja|VS|EU|er|we|tv|he|ga|hè|hé|TV|as|ei|SP|pc|wc|PC|IS|NS|ok|AD|OK|at|OM|cd|VN|it|EK|In|pa|AZ|up|IT|FM|VI|ui|la|CD|CV|pr|ie|cv|WW|GB|Jo|Aa|UK|HD|oa|VU))\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
 <beforebreak>\b\p{L}\.</beforebreak>
 <afterbreak>\p{L}\.</afterbreak>
 </rule>
@@ -1737,6 +1798,10 @@
 <beforebreak>\b\p{Lu}\.\p{Lu}\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<rule break="yes">
+<beforebreak>\s(op)\sX\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>[^\.]\s[A-Z]\.\s</beforebreak>
 <afterbreak></afterbreak>
@@ -1771,10 +1836,18 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\s[A-Z].+!\s</beforebreak>
+<beforebreak>(^|\s)[A-Z].+!\s</beforebreak>
 <afterbreak>[a-z]</afterbreak>
 </rule>
 <rule break="no">
+<beforebreak>\s[A-Z].+z\.\s</beforebreak>
+<afterbreak>[a-z]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\sart\.\s</beforebreak>
+<afterbreak>[0-9]</afterbreak>
+</rule>
+<rule break="no">
 <beforebreak>\b(jan|mrt|mar|jun|jul|aug|sept|okt|sep|spt|nov|dec|.*opp)\.\s</beforebreak>
 <afterbreak>[a-z]</afterbreak>
 </rule>
@@ -4688,6 +4761,19 @@
 <beforebreak>\.\[\d+\][\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<!-- unknown abbreviations inside parentheses -->
+<rule break="no">
+<beforebreak>\([^\)]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\)\r\n]*\)</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\[[^\]]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\]\r\n]*\]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\{[^\}]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\}\r\n]*\}</afterbreak>
+</rule>
 <!-- initials: A. C. Jones. Problem: [...] d'Alfons I. Ell era [...] -->
 <rule break="no">
 <beforebreak>\b[A-ZÀÉÈÍÓÒÚ]\.[\s\u00A0]</beforebreak>
@@ -4695,7 +4781,7 @@
 </rule>
 <!-- Abbreviations that cannot finish sentences-->
 <rule break="no">
-<beforebreak>\b(dc|(?iu)(n|Mr|C|Dr|Dra|Dra\. Ma|Sta\. Ma|E|Emm|Emma|Excm|Excma|Hble|I|Il·lm|Il·lma|Il·ltre|Im|Ima|Mgfc|Mgfca|Mn|R|Rev|Sr|Sra|Sres|Srs|St|Sta|a|abr|abs|acad|add|adj|adm|admdor|admdora|admtiu|admtiva|adv|ag|agl|agr|agron|agròn|aj|ajud|al|alim|amb|ampl|ant|ap|apmt|apnt|apr|aprox|apt|arm|arq|arqueol|arquit|assign|assoc|atm|aut|aux|av|b|batx|bda|bibl|bl|bnc|butll|bxs|c|calef|cartogr|cat|catedr|catol|cf|cia|cin|cint|circul|cit|climat|col|col·l|compt|cons|constr|cont|contr|conv|corp|corr|cpl|cpt|cró|ct|cte|ctra|cts|d|dept|derog|des|desp|dg|dip|disp|distr|div|dj|dl|doc|drec|ds|dt|dta|dte|dupl|dv|e|econ|ed|ef|entl|esc|esp|espf|esq|ex|exc|exp|exped|ext|f|fac|fca|febr|fig|figs|fra|gen|gov|gral|i|imp|impr|impt|inc|insp|inst|int|inv|j|jul|jur|jurispr|leg|llic|loc|ltda|làm|merc|mil·l|màx|mín|neg|nov|nre|núm|o|oct|op|p|pàg|pàgs|paq|par|pda|pg|pl|pobl|pol|ppda|ppt|pral|prev|prof|progr|prov|pta|ptes|ptge|pvt|pàg|quadr|quint|r|rbla|ref|reg|rev|secr|serv|sgt|sotsp|subsp|supl|supt|t|tel|telegr|tit|trad|trans|transcr|transf|trav|tripl|trv|tt|tèc|univ|urb|v|var|veg|venc|vid|vig|vocab|vs|x|àt|íd))\.[\s\u00A0]</beforebreak>
+<beforebreak>\b(dc|inst|(?iu)(n|Mr|C|Dr|Dra|Dra\. Ma|Sta\. Ma|E|Emm|Emma|Excm|Excma|Hble|I|Il·lm|Il·lma|Il·ltre|Im|Ima|Mgfc|Mgfca|Mn|R|Rev|Sr|Sra|Sres|Srs|St|Sta|a|abr|abs|acad|add|adj|adm|admdor|admdora|admtiu|admtiva|adv|ag|agl|agr|agron|agròn|aj|ajud|al|alim|amb|ampl|ant|ap|apmt|apnt|apr|aprox|apt|arm|arq|arqueol|arquit|assign|assoc|atm|aut|aux|av|b|batx|bda|bibl|bl|bnc|butll|bxs|c|calef|cartogr|cat|catedr|catol|cf|cia|cin|cint|circul|cit|climat|col|col·l|compt|cons|constr|cont|contr|conv|corp|corr|cpl|cpt|cró|ct|cte|ctra|cts|d|dept|derog|des|desp|dg|dip|disp|distr|div|dj|dl|doc|drec|ds|dt|dta|dte|dupl|dv|e|econ|ed|ef|entl|esc|esp|espf|esq|ex|exc|exp|exped|ext|f|fac|fca|febr|fig|figs|fra|gen|gov|gral|i|imp|impr|impt|inc|insp|inst|int|inv|j|jul|jur|jurispr|leg|llic|loc|ltda|làm|merc|mil·l|màx|mín|neg|nov|nre|núm|o|oct|op|p|pàg|pàgs|paq|par|pda|pg|pl|pobl|pol|ppda|ppt|pral|prev|prof|progr|prov|pta|ptes|ptge|pvt|pàg|quadr|quint|r|rbla|ref|reg|rev|secr|serv|sgt|sotsp|subsp|supl|supt|t|tel|telegr|tit|trad|trans|transcr|transf|trav|tripl|trv|tt|tèc|univ|urb|v|var|veg|venc|vid|vig|vocab|vs|x|àt|íd))\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- Abbreviations that can finish sentences -->
@@ -4750,12 +4836,12 @@
 </rule>
 <!-- Ellipsis: ... lowercase -->
 <rule break="no">
-<beforebreak>[^\s\u00A0](\Q...\E|…)[\s\u00A0]</beforebreak>
+<beforebreak>[^\s\u00A0](\.\.\.|…)[\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- (enum...) -->
 <rule break="no">
-<beforebreak>\b(\Q...\E|…)[\p{Pe}»"’”][\s\u00A0]</beforebreak>
+<beforebreak>\b(\.\.\.|…)[\p{Pe}»"’”][\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- pero ¡ah! no estaba
@@ -4779,6 +4865,19 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="Spanish">
+<!-- unknown abbreviations inside parentheses -->
+<rule break="no">
+<beforebreak>\([^\)]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\)\r\n]*\)</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\[[^\]]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\]\r\n]*\]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\{[^\}]*\.[\s\u00A0]</beforebreak>
+<afterbreak>[^\}\r\n]*\}</afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>¿[^?]+:[\s\u00A0]</beforebreak>
 <afterbreak>.</afterbreak>
@@ -4802,12 +4901,12 @@
 </rule>
 <!-- Ellipsis: ... lowercase -->
 <rule break="no">
-<beforebreak>[^\s\u00A0](\Q...\E|…)[\s\u00A0]</beforebreak>
+<beforebreak>[^\s\u00A0](\.\.\.|…)[\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- (enum...) -->
 <rule break="no">
-<beforebreak>\b(\Q...\E|…)[\p{Pe}»"’”][\s\u00A0]</beforebreak>
+<beforebreak>\b(\.\.\.|…)[\p{Pe}»"’”][\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- Abbreviations that can finish sentences -->
@@ -4917,6 +5016,10 @@
 <beforebreak>\b(https?|ftp|file|chrome|chromium|android|(chrome|moz)\-extension):///?[A-Za-z0-9\-]+\.</beforebreak>
 <afterbreak>[A-Za-z0-9\-]+(\.|\b)</afterbreak>
 </rule>
+<rule break="no"><!-- https://www.seven.one/ -->
+<beforebreak>\b[Se]even\.</beforebreak>
+<afterbreak>[Oo]nes?\b</afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>\b[A-Za-z0-9\-]+\.</beforebreak>
 <afterbreak>[A-Za-z0-9\-]+\.(com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)</afterbreak>
@@ -5026,7 +5129,7 @@
 </rule>
 <!-- don't split at cases like "Friedrich II. wird auch..." -->
 <rule break="no">
-<beforebreak>[\u00A0\s ][IVX]+\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>[\u00A0\s ][IVX]+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>[^\p{Lu}]+</afterbreak>
 </rule>
 <!-- don't split at cases like "im 13. oder 14. Jahrhundert" -->
@@ -5066,11 +5169,11 @@
 </rule>
 <!-- German abbreviations -->
 <rule break="no">
-<beforebreak>\b(betr|Geb|Stk|ggü|Mag|mtl|[Pp]arl|Bsp|versch|[Dd]iesbzgl|[Dd]bzgl[Ss]tellv|d|Übers|usw|[Bb]zw|Ab[hkst]|[Aa]bzü?gl|\d+-tlg|tlg|ggfls|[Ll]tda|[Ee]inschl|[Vv]mtl|Ev|bezgl|lit|Abzw|[Vv]sl|ahd|Akk|aktual|[Öö]ffentl|prof|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|[Aa]utom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|Bez|Bhf|Blvd|[Bb]spw|btto|bw|Dtl|[Gg]esetzl|Dez|[Jj]gdfr|[Ee]ff)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(betr|Geb|Stk|ggü|Mag|mtl|Flgh?|[Pp]arl|Bsp|versch|[Dd]iesbzgl|[Zz]ykl|[Dd]bzgl[Ss]tellv|d|Übers|usw|[Bb]zw|Ab[hkst]|[Ee]ig|[Aa]bzü?gl|\d+-tlg|tlg|[Gg]gfls|[Ff]achspr|[Ll]tda|[Ee]inschl|[Vv]mtl|[Ss]tellv|Ev|[Bb]ezgl|lit|Abzw|[Vv]sl|ahd|Akk|aktual|[Öö]ffentl|prof|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|[Aa]utom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|wsl|vsl|Bez|Bhf|Blvd|[Bb]spw|btto|bw|Dtl|[Gg]esetzl|Dez|[Jj]gdfr|[Ee]ff)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(cts?|[Cc]a|chem|chin|Chr|cresc|[Dd]at|desgl|ders|dgl|Dipl|Dir?|Doz?|durchg|durchges|Dr|dt|ebd|Ed|[Ee]igt?l|akt|[Ee]ngl|Erg|al|et[cw]|Etw|ev|[Ee]vtl?|[Ee]xkl|Expl|Exz)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(cts?|[Cc]a|chem|chin|Chr|cresc|[Dd]at|desgl|ders|dgl|Dipl|Dir?|Doz?|durchg|durchges|Dr|[Dd]t|ebd|Ed|[Ee]igt?l|akt|[Ee]ngl|Erg|al|et[cw]|Etw|ev|[Ee]vtl?|[Ee]xkl|Expl|Exz)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5094,7 +5197,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Part|Per[fs]|Pfd|Pl(ur)?|pl|Plusq|Pos|pp|Prä[ps]|Prät|Pro[vf]|rd|reg|resp|Rhld|rit|Sa|südl|Br|se[ln]|Sept|Sing|sign|So|sog|Sp|Std?|stacc|Str|stud|Subst|sva|svw|sZ)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(Part|Per[fs]|Pfd|Pl(ur)?|pl|Plusq|Pos|pp|Prä[ps]|Prät|Pro[vf]|rd|reg|resp|Rhld|rit|Sa|südl|Br|se[ln]|Sept|Sing|sign|So|sog|Sp|[Ss]td?|stacc|Str|stud|Subst|sva|svw|sZ)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5227,7 +5330,7 @@
 </rule>
 <rule break="no">
 <beforebreak>\bLL\.\s?</beforebreak>
-<afterbreak>[BM]\.?</afterbreak>
+<afterbreak>[BMD]\.?</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b[BM]\.\s?</beforebreak>
@@ -5526,7 +5629,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\bLL\.[\s\u00A0]?[BM]\.[\s\u00A0]</beforebreak>
+<beforebreak>\bLL\.[\s\u00A0]?[BMD]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5535,7 +5638,7 @@
 </rule>
 <rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?</beforebreak>
-<afterbreak>[BM]\.?</afterbreak>
+<afterbreak>[BMD]\.?</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
@@ -5591,6 +5694,14 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
+
+<languagerule languagerulename="Crimean Tatar">
+<rule break="no">
+<beforebreak>\b[0-9]+(\.|:)[0-9][0-9][\s\u00A0\u202F]</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+</languagerule>
+
 <languagerule languagerulename="Ukrainian">
 <!-- when sentence starts with ellipsis: ...Мазій і Юхим теж. -->
 <rule break="no">
@@ -5651,7 +5762,7 @@
 </rule>
 <!-- Ів. Франко (але Ів Бутільє) -->
 <rule break="no">
-<beforebreak>(^|[\h\v])(Ів|Дж)\.[\h\v]+</beforebreak>
+<beforebreak>(^|[\h\v])(Ів|Дж|Ол)\.[\h\v]+</beforebreak>
 <afterbreak>[А-ЯІЇЄҐA-Z]</afterbreak>
 </rule>
 <!-- Year: 2000 р.:
@@ -5742,7 +5853,7 @@
 </rule>
 <!-- abbreviation with proper noun: проф. Грицько, о. Лісове -->
 <rule break="no">
-<beforebreak>\b(ап|[Аа]кад|[Пп]роф|[Дд]оц|[Аа]сист|[Рр]еж|[Аа]рх|[Сс]вв?|о|оз|ім|інж|дир|тов|упоряд|тт|чл\.-кор|[Пп]реп)\.[\h\v]*</beforebreak>
+<beforebreak>\b(ап|[Аа]кад|[Пп]роф|[Дд]оц|[Аа]сист|[Рр]еж|[Аа]рх|[Сс]вв?|о|оз|ім|інж|дир|тов|упоряд|тт|чл\.-кор|[Пп]реп|[сС]вт)\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*[А-ЯІЇЄҐA-Z]</afterbreak>
 </rule>
 <rule break="no">
@@ -5760,8 +5871,8 @@
 </rule>
 <!-- TODO: арт. - артист -->
 <rule break="no">
-<beforebreak>\b([Аа]рт|[Мм]ал|[Рр]ис)\.[\h\v]*</beforebreak>
-<afterbreak>[\h\v]*[0-9]</afterbreak>
+<beforebreak>\b([Аа]рт|[Мм]ал|[Рр]ис|[Сс]пр)\.[\h\v]*</beforebreak>
+<afterbreak>[\h\v]*(№[\h\v]*)?[0-9]</afterbreak>
 </rule>
 <!-- ХІІ р., 3-6 арт., 2-3 тт. -->
 <rule break="no">
@@ -5791,7 +5902,11 @@
 <!-- статус правових держав. — Авт.). -->
 <rule break="no">
 <beforebreak></beforebreak>
-<afterbreak>[\h\v]*[‐-―-][\h\v]*([Рр]ед|[Аа]вт)[\h\v]*\.[\)\]]</afterbreak>
+<afterbreak>[\h\v]*[‐-―-][\h\v]*([Рр]ед|[Аа]вт)\.[\h\v]*[\)\]]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b([Рр]ед)\.[\h\v]*</beforebreak>
+<afterbreak>[А-ЯІЇЄҐ]</afterbreak>
 </rule>
 <!-- Цензор.НЕТ -->
 <rule break="no">
@@ -6282,7 +6397,7 @@
 </rule>
 <!-- Not break for ellipses (...) -->
 <rule break="no">
-<beforebreak>[^\s](\Q...\E|…)\s</beforebreak>
+<beforebreak>[^\s](\.\.\.|…)\s</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- z.B. "bla (...) blubb" -> without ending sentence -->
@@ -6503,7 +6618,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>[^\.]\s[ضصثقفغعهخحجچشسیبلاتنمکگ\ظطزرذدپوًٌٍَُِّْA-Z]\.\s</beforebreak>
+<beforebreak>[^\.]\s[ضصثقفغعهخحجچشسیبلاتنمکگ\ظطزرذدپوًٌٍَُِّْA-Z]\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6583,7 +6698,7 @@
 </rule>
 <!--Не раздвајај у случају као на пр.: "Петар I дошао је ..."-->
 <rule break="no">
-<beforebreak>[\s ][IVX]+\s</beforebreak>
+<beforebreak>[\s ][IVX]+\s</beforebreak>
 <afterbreak>[^\p{Lu}]+</afterbreak>
 </rule>
 <!--Не раздвајај у случају као "од 13. до 14. века"-->
@@ -6837,6 +6952,7 @@
 <languagemap languagepattern="(ML|ml).*" languagerulename="Generic"></languagemap>
 <languagemap languagepattern="(TL|tl).*" languagerulename="Generic"></languagemap>
 <languagemap languagepattern="(AST|ast).*" languagerulename="Generic"></languagemap>
+<languagemap languagepattern="(CRH|crh).*" languagerulename="Generic"></languagemap>
 <languagemap languagepattern=".*" languagerulename="Default"></languagemap>
 </maprules>
 </body>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: srx-languagetool
 version: !ruby/object:Gem::Version
-  version: 0.12.0
+  version: 0.14.0
 platform: ruby
 authors:
 - Aaron Madlon-Kay
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-10-07 00:00:00.000000000 Z
+date: 2024-09-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: srx
@@ -24,7 +24,7 @@ dependencies:
     - - "<"
       - !ruby/object:Gem::Version
         version: '1.0'
-description: 
+description:
 email:
 - aaron@madlon-kay.com
 executables: []
@@ -58,7 +58,7 @@ metadata:
   source_code_uri: https://github.com/amake/srx-languagetool-ruby.git
   changelog_uri: https://github.com/amake/srx-languagetool-ruby/blob/master/CHANGELOG.md
   rubygems_mfa_required: 'true'
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -73,8 +73,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.6
-signing_key: 
+rubygems_version: 3.5.7
+signing_key:
 specification_version: 4
 summary: SRX segmentation rules from LanguageTool
 test_files: []