srx-languagetool 0.8.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f73cebe4cfa7e771e3250f1f1dc13694b6450e19a4f9adf81769c5a75baa76d5
-  data.tar.gz: 35f29775c7d85150bc61551e9fb32adcb60cebc392d9d37e01d829b193a7464c
+  metadata.gz: 15d222238ca97d49bdcfd3ab55fed3ac9556cd1479ede47c6bcc126eca67db91
+  data.tar.gz: c67a1a5931a94b815d45147c091083ee776006e21003c95872b534158bdbd9fa
 SHA512:
-  metadata.gz: 548319e33a292724739e81eb28433594dfea9ec8e9e1fd78366d1847e601a5c6e1521e1fa639bd760fd33ee80d45190a83e92fdcb64d17efae730f5ac7958e6d
-  data.tar.gz: b55939faa805e0e5102a8610c4c89571f47c5002d3c7b7dfa26fa9f8785f83ce4083bec63abad845565091ddfad752c2ca6b9599a88be621e5618053ad5b0394
+  metadata.gz: bd4ad4a1740d7c1f880bcfcb32acfd6b636c1491716d59d256d60ae66b0611783f134e116c1c8c16e1acf147aced8484865492fc7293fdd8f0330bf22d622a59
+  data.tar.gz: 6c28a74647adcd1a87e26d6c4cba540fcd38f0f71c817a4ce2a59cbcbbc6e21932aee3b56e2ad316fe11c838f48a70547c518a169495f14409acac8ada194d9b

data/.github/workflows/main.yml

@@ -10,10 +10,10 @@ jobs:
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: 2.7.6
+        ruby-version: 2.7.7
     - name: Install
       run: |
-        gem install bundler -v 2.3.22
+        gem install bundler -v 2.4.1
         bundle install
     - name: Type check
       run: bundle exec solargraph typecheck --level typed

data/.ruby-version

@@ -1 +1 @@
-2.7.6
+2.7.7

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## [Unreleased]
 
+## [0.9.0] - 2022-12-30
+
+- Update rules to LanguageTool 6.0
+
 ## [0.8.0] - 2022-09-29
 
 - Update rules to LanguageTool 5.9

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    srx-languagetool (0.8.0)
+    srx-languagetool (0.9.0)
       srx (< 1.0)
 
 GEM
@@ -9,47 +9,47 @@ GEM
   specs:
     ast (2.4.2)
     backport (1.2.0)
-    benchmark (0.2.0)
+    benchmark (0.2.1)
     byebug (11.1.3)
     diff-lcs (1.5.0)
     e2mmap (0.1.0)
     jaro_winkler (1.5.4)
-    json (2.6.2)
+    json (2.6.3)
     kramdown (2.4.0)
       rexml
     kramdown-parser-gfm (1.1.0)
       kramdown (~> 2.0)
     minitest (5.16.3)
-    nokogiri (1.13.8-x86_64-darwin)
+    nokogiri (1.13.10-x86_64-darwin)
       racc (~> 1.4)
     parallel (1.22.1)
-    parser (3.1.2.1)
+    parser (3.1.3.0)
       ast (~> 2.4.1)
-    racc (1.6.0)
+    racc (1.6.2)
     rainbow (3.1.1)
     rake (13.0.6)
-    regexp_parser (2.6.0)
+    regexp_parser (2.6.1)
     reverse_markdown (2.1.1)
       nokogiri
     rexml (3.2.5)
-    rspec-expectations (3.11.1)
+    rspec-expectations (3.12.1)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.11.0)
-    rspec-support (3.11.1)
-    rubocop (1.36.0)
+      rspec-support (~> 3.12.0)
+    rspec-support (3.12.0)
+    rubocop (1.41.1)
       json (~> 2.3)
       parallel (~> 1.10)
       parser (>= 3.1.2.1)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
-      rubocop-ast (>= 1.20.1, < 2.0)
+      rubocop-ast (>= 1.23.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.21.0)
+    rubocop-ast (1.24.1)
       parser (>= 3.1.1.0)
     ruby-progressbar (1.11.0)
-    solargraph (0.47.1)
+    solargraph (0.48.0)
       backport (~> 1.2)
       benchmark
       bundler (>= 1.17.2)
@@ -76,6 +76,7 @@ GEM
 PLATFORMS
   x86_64-darwin-20
   x86_64-darwin-21
+  x86_64-darwin-22
 
 DEPENDENCIES
   byebug
@@ -87,4 +88,4 @@ DEPENDENCIES
   srx-languagetool!
 
 BUNDLED WITH
-   2.3.22
+   2.4.1

data/lib/srx/languagetool/version.rb

@@ -2,6 +2,6 @@
 
 module Srx
   module Languagetool
-    VERSION = '0.8.0'
+    VERSION = '0.9.0'
   end
 end

data/lib/srx/segment.srx

@@ -4,8 +4,10 @@
 <formathandle type="start" include="no"></formathandle>
 <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="sr" useMappedRules="yes">Поштовани господине одн. госпођо. Видео сам </okpsrx:sample>
+<okpsrx:options oneSegmentIncludesAll="no" trimLeadingWhitespaces="no" trimTrailingWhitespaces="no" useJavaRegex="yes"></okpsrx:options>
+<okpsrx:sample language="pl" useMappedRules="yes">Als een hoogleraar met emeritaat ('pensioen') is, mag hij de functieaanduiding prof. blijven gebruiken, maar hij heeft tevens het recht gekregen om het bijvoeglijk naamwoord emeritus (Latijn voor 'uitgediend') aan zijn functietitel toe te voegen: em. prof. dr.
+Tussen de twee wereldoorlogen vestigde prof. ir. Messerschmitt zich in Augsburg waar hij met behulp van een oudere, rijke vriendin (met wie hij later trouwde) zijn eerste vliegtuigen bouwde, het waren passagierstoestellen.
+250 p. n.e.</okpsrx:sample>
 <okpsrx:rangeRule></okpsrx:rangeRule>
 </header>
 <body>
@@ -1084,6 +1086,11 @@
 <beforebreak>[\.!?…]['"\u00BB\u2019\u201D\u203A\u0002]*\p{Pe}\s</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
+<!--p. n.e. (błędny podział wiersza)-->
+<rule break="no">
+<beforebreak>p\.\s</beforebreak>
+<afterbreak>n\.\s?e\.</afterbreak>
+</rule>
 <rule break="yes">
 <beforebreak>[\.!?…]['"\p{Pe}\u00BB\u2019\u201D\u203A\u0002¹²³]*\s</beforebreak>
 <afterbreak></afterbreak>
@@ -1106,7 +1113,7 @@
 <beforebreak>[\u00A0\s]</beforebreak>
 <afterbreak>\n</afterbreak>
 </rule>
-<rule break="no"><!-- Hello (Hi! ) my name is Chris -->
+<rule break="no">
 <beforebreak>[a-zA-Z][!\?][\s\u00A0]</beforebreak>
 <afterbreak>\)[\s\u00A0][a-zA-Z]</afterbreak>
 </rule>
@@ -1114,96 +1121,96 @@
 <beforebreak>Yahoo![\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
-<rule break="no"><!-- U.S.A (no dot at end) -->
+<rule break="no">
 <beforebreak>[A-Z]\.[A-Z]\.</beforebreak>
 <afterbreak>[A-Z]\b</afterbreak>
 </rule>
-<rule break="no"><!-- A.I (no dot at end) -->
+<rule break="no">
 <beforebreak>\bA\.</beforebreak>
 <afterbreak>I\b</afterbreak>
 </rule>
-<rule break="no"><!-- S.I (no dot at end) -->
+<rule break="no">
 <beforebreak>\bS\.</beforebreak>
 <afterbreak>I\b</afterbreak>
 </rule>
-<rule break="no"><!-- L.A (no dot at end) -->
+<rule break="no">
 <beforebreak>\bL\.</beforebreak>
 <afterbreak>A\b</afterbreak>
 </rule>
-<rule break="no"><!-- U.S (no dot at end) -->
+<rule break="no">
 <beforebreak>\bU\.</beforebreak>
 <afterbreak>[SK]\b</afterbreak>
 </rule>
-<rule break="no"><!-- I.S (no dot at end) -->
+<rule break="no">
 <beforebreak>\bI\.</beforebreak>
 <afterbreak>S\b</afterbreak>
 </rule>
-<rule break="no"><!-- M.Z (no dot at end) -->
+<rule break="no">
 <beforebreak>\bM\.</beforebreak>
 <afterbreak>Z\b</afterbreak>
 </rule>
-<rule break="no"><!-- URLs without "www."-->
+<rule break="no">
 <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"><!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
+<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|be|dev|co|fr|dk|se)(\.|\b)</afterbreak>
 </rule>
-<rule break="no"><!-- No. 5 -->
+<rule break="no">
 <beforebreak>\b[nN]o\.[\s\u00A0]</beforebreak>
 <afterbreak>\p{N}</afterbreak>
 </rule>
-<rule break="no"><!-- Ph.D. -->
+<rule break="no">
 <beforebreak>\bP[Hh]\.[\s\u00A0]?</beforebreak>
 <afterbreak>D\.?</afterbreak>
 </rule>
-<rule break="no"><!-- min. -->
+<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|[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>
 <afterbreak>[^\p{Lu}]|I</afterbreak>
 </rule>
-<rule break="no"><!-- hr. -->
+<rule break="no">
 <beforebreak>\b(hr)\.[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{Lu}]|I</afterbreak>
 </rule>
-<rule break="no"><!-- Fig. 8 -->
+<rule break="no">
 <beforebreak>\b([Vv]ol|[Ff]ig|[Dd]ef|[Ee]q|[Ll]em|[Pp]rop|[Tt]hm)s?\.[\s\u00A0]</beforebreak>
 <afterbreak>\p{N}|[IXV]+</afterbreak>
 </rule>
-<rule break="no"><!-- Fig. (8) -->
+<rule break="no">
 <beforebreak>\b([Ff]ig|[Dd]ef|[Ee]q|[Ll]em|[Pp]rop|[Tt]hm)s?\.[\s\u00A0]</beforebreak>
 <afterbreak>\(\p{N}\)</afterbreak>
 </rule>
-<rule break="no"><!-- I'm (...) great! -->
+<rule break="no">
 <beforebreak>(…|\.\.\.)[\s\u00A0]?\)[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{P}]</afterbreak>
 </rule>
-<rule break="no"><!-- I will work with someone (Chris or ...?). -->
+<rule break="no">
 <beforebreak>(…|\.\.\.)[\s\u00A0]?\?\)[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{P}]</afterbreak>
 </rule>
-<rule break="no"><!-- e.g. -->
+<rule break="no">
 <beforebreak>\be\.g\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- vs. -->
+<rule break="no">
 <beforebreak>\b[Vv]s\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- pp. -->
+<rule break="no">
 <beforebreak>\b(pp|PP)\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- esp. -->
+<rule break="no">
 <beforebreak>\be[sx]p\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!--"Etc." can end the sentence, so we check for the uppercase letter after it.-->
-<rule break="no"><!-- Etc. -->
+<rule break="no">
 <beforebreak>\b[Ee]tc\.[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{Lu}]</afterbreak>
 </rule>
-<rule break="no"><!-- BTW (by the way) -->
+<rule break="no">
 <beforebreak>\b([Bb]tw|BTW)\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
@@ -1251,39 +1258,39 @@
 <beforebreak>(?i)FRITZ!</beforebreak>
 <afterbreak>(?i)Box</afterbreak>
 </rule>
-<rule break="no"><!-- https://de.wikipedia.org/wiki/VW_ID.3 -->
+<rule break="no">
 <beforebreak>ID.</beforebreak>
 <afterbreak>3|4|Buzz|Crozz</afterbreak>
 </rule>
-<rule break="no"><!-- Ph.D. (see rule PH_D) -->
+<rule break="no">
 <beforebreak>\bP[Hh]\.?[\s\u00A0]?[Dd]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- "I have a B. Eng. degree" (see rule BACHELOR_ABBR) -->
+<rule break="no">
 <beforebreak>\b(P[hH][dD]|BSc|BEng|BComp|BArch|MSc|MEng|MComp)\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- "I have a LL.B degree." (see rule PH_D) -->
+<rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?[BM]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- B.Eng. (Bachelor of Engineering) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Eng\.?</afterbreak>
 </rule>
-<rule break="no"><!-- LL.B. (Bachelor of Laws) -->
+<rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?</beforebreak>
 <afterbreak>[BM]\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Sc. (Bachelor of Science) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Sc\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Comp. (Bachelor of Computing) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Comp?\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Arch. (Bachelor of Architecture) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Arch\.?</afterbreak>
 </rule>
@@ -1375,7 +1382,7 @@
 <beforebreak>\b\p{L}\.</beforebreak>
 <afterbreak>\p{L}\.</afterbreak>
 </rule>
-<rule break="no"><!-- Jones v. Smith -->
+<rule break="no">
 <beforebreak>\p{Lu}\p{L}+[\s\u00A0]v\.[\s\u00A0]</beforebreak>
 <afterbreak>\p{Lu}\p{L}+</afterbreak>
 </rule>
@@ -1388,7 +1395,7 @@
 <afterbreak>\p{Ll}+</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>[\.\s\u00A0](?!(on|it|of|to|be|by|at|he|we|so|do|if|up|my|me|us|go|am))\p{L}{1,2}\.[\s\u00A0]</beforebreak><!-- not 'no'/'in', these could be abbreviations-->
+<beforebreak>[\.\s\u00A0](?!(on|it|of|to|be|by|at|he|we|so|do|if|up|my|me|us|go|am))\p{L}{1,2}\.[\s\u00A0]</beforebreak>
 <afterbreak>[\p{N}\p{Ll}]</afterbreak>
 </rule>
 <rule break="no">
@@ -1419,8 +1426,8 @@
 <beforebreak>\(\p{Ll}+\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- i.e. -->
-<beforebreak>i\.e\.[\s\u00A0]</beforebreak><!-- "i.e." is never at end of sentence -->
+<rule break="no">
+<beforebreak>i\.e\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="yes">
@@ -1532,37 +1539,44 @@
 </languagerule>
 <languagerule languagerulename="Dutch">
 <rule break="no">
-<!-- sp.a  -->
 <beforebreak>\b(sp|SP)</beforebreak>
 <afterbreak>\.[aA]\b</afterbreak>
 </rule>
 <rule break="no">
-<!-- .Net  -->
 <beforebreak>\s[.]</beforebreak>
 <afterbreak>[Nn][Ee][Tt](\b|-)</afterbreak>
 </rule>
-<rule break="no"><!-- quoted sentence in sentence -->
+<rule break="no">
 <beforebreak>[.?!][’'"]</beforebreak>
 <afterbreak> [a-z]</afterbreak>
 </rule>
-<rule break="no"><!-- URLs without "www."-->
+<rule break="no">
 <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"><!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
+<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>
 </rule>
-<rule break="no"><!-- Abbreviated books of the Bible and biblical apocrypha-->
+<rule break="no">
+<beforebreak>\b(blz|pag|fig)\.\s</beforebreak>
+<afterbreak>[0-9]</afterbreak>
+</rule>
+<!--Abbrevs that can happen in sentence and at end-->
+<rule break="no">
+<beforebreak>\b(enz|etc|zat|ambt|al|ver|art|wed|lab|bv|Bros)\.\s</beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
+</rule>
+<rule break="no">
 <beforebreak>\b(Ge?n|Ex|Le?v|Nu?m|D(eu)?t|Jo?z|Ri|R[ei]cht|Sa?m|Ko?n|Kr[on]{0,2}|Neh?|Est?|Jb|Ps|Spr?|Pr[ed]{0,2}|H(oog)?l|Je?s|Je?r|Kl(aagl)?|Ez(ech)?|Da?n|Ho?s|Jl|Am|Ob|Mc|Mi[ch]{0,2}|Nah?|Hk|Hab|Zf|[SZ]ef|Ha?g|Zc|Zach|Ma?l|Ma?t|Mk|Mar|Lk|Jh|H(an)?d|Ro?m|Kor|Ga?l|Ef|Fp|Fil|Ko|[CK]ol|Th|Th?e[s]{1,2}|Tm|Ti?t|Fm|Fil(em)?|Hb|Hebr?|Jk|Ja[ck]|Pe?tr?|Joh|Jud|Op(enb)?|Wijsh|Tob|Sir|Bar|Makk)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Drs|Art|Afr|Am|Ar|Br|Cie|Comp|Dhr|([Pp]rof\.)?[Dd]r|Em|Fa|Kon|Bros|Stb)\.\s</beforebreak>
-<afterbreak></afterbreak>
+<beforebreak>\b(Drs|Art|Afr|Am|Ar|Br|Cie|Comp|Dhr|(Prof\.)?[Dd]r|Em|Fa|Kon|Stb)\.\s</beforebreak>
+<afterbreak>\p{Lu}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Mej|Mevr|Mgr|Mw|Ndl|Ned|Nl|No|Prof|Secr|Chr|Jac)\.\s</beforebreak>
+<beforebreak>\b([Mm]ej|[Mm]evr|[Mm]rs|[Mm]s|[Mm]gr|[Mm]w|Ndl|Ned|Nl|No|Prof|[Ss]ecr|Chr|Jac|[Ww]ed)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1570,23 +1584,27 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(abs|abstr|adj|adm|afb|[Aa]fd|afk|afl|milj|zgn|plv|bvb|bv|afm|evt|exp)\.\s</beforebreak>
+<beforebreak>\b(abs|abstr|adj|adm|[Aa]fb|[Aa]fd|afk|afl|milj|zgn|plv|bvb|afm|evt|exp|vs)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(al|ald|alg|amb|ambt|anat|antrop|apoth)\.\s</beforebreak>
+<beforebreak>\b(ald|alg|amb|anat|antrop|apoth)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<rule break="yes">
+<beforebreak>\seen\sprof\.\s</beforebreak>
+<afterbreak>\p{Lu}</afterbreak>
+</rule>
 <rule break="no">
 <beforebreak>\b(alc|bro|opm|acc)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(arch|archeol|art|bc|bep|betr|bez|bibl|bijl|[Bb]ijv)\.\s</beforebreak>
+<beforebreak>\b(arch|archeolbc|bep|betr|bez|bibl|bijl|[Bb]ijv)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(bijz|blz|bw|ca|cat|centr|cf|cfr|cmpl)\.\s</beforebreak>
+<beforebreak>\b(bijz|bw|ca|cat|centr|cf|cfr|cmpl)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1594,7 +1612,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(ed|em|enz|etc|ev|[Ee]xcl|fa|fam|fig|fin|fl|fr.)\.\s</beforebreak>
+<beforebreak>\b([Ee]d|em|ev|[Ee]xcl|[Ff]a|[Ff]am|[fF]ig|fin|fl|fr)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1602,39 +1620,39 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(jl|jr|kr|kt|lab|lic|ll|lt|lw|max|mevr|mi|[Mm]in|mld)\.\s</beforebreak>
+<beforebreak>\b(jl|jr|kr|kt|lic|ll|lt|lw|max|[Mm]evr|mi|[Mm]in|mld)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(mln|mr|mw|nl|no|nr|nrs|ob|obl|ong|onov|o.a)\.\s</beforebreak>
+<beforebreak>\b(mln|[Mm]r|[Mm]w|nl|no|nr|nrs|ob|obl|ong|onov)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(opm|org|ov|pag|par|penn|([1-3][\.e]?)[\s]?pers|plm|plv)\.\s</beforebreak>
+<beforebreak>\b(opm|org|ov|[Pp]ag|par|penn|([1-3][\.e]?)[\s]?pers|plm|plv)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(prov|pseud|psych|qty|red|ref|resp|soc|st|tab|tel|temp|tk)\.\s</beforebreak>
+<beforebreak>\b(prov|pseud|psych|qty|red|ref|resp|soc|st|tab|tel|temp|prof|tk)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b([A-Z]|Adr|Chr|Fr|Fred|IJ|Jac|Joh|Ph|St|Th|Tj|v|v\.(\s)?d)\.(\s)?</beforebreak>
-<afterbreak>[A-Z]</afterbreak>
+<afterbreak>\p{Lu}</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b[vn]\.\s</beforebreak>
 <afterbreak>Chr</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(uitsl|ver|vgl|vnl|vnw|voorz|ww|zat|[Zz]elfst|zgn?)\.\s</beforebreak>
-<afterbreak></afterbreak>
+<beforebreak>\b(uitsl|vgl|vnl|vnw|voorz|ww|zat|[Zz]elfst|zgn?)\.\s</beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(mm|cm|km|mg|kg|h|kW|mW)\.\s</beforebreak>
+<beforebreak>\b(mm|cm|km|ml|mg|kg|h|kW|kg|mW)\.\s</beforebreak>
 <afterbreak>\p{Ll}|\p{Lu}{2,}</afterbreak>
 </rule>
 <rule break="yes">
-<beforebreak>\b(mm|cm|km|ml|kg|kW|h|mg)\.\s</beforebreak>
+<beforebreak>\b(mm|cm|km|ml|mg|kg|h|kW|kg|mW)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1686,10 +1704,6 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b\p{Lu}\p{Ll}\.\s?</beforebreak>
-<afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
-</rule>
-<rule break="no">
 <beforebreak>\.\p{Lu}\p{Ll}\.\s?</beforebreak>
 <afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
 </rule>
@@ -1698,14 +1712,6 @@
 <beforebreak>\b\d+\.\s</beforebreak>
 <afterbreak>\p{Ll}|\p{Lu}{2,}</afterbreak>
 </rule>
-<rule break="yes">
-<beforebreak>\been\sprof\.\s</beforebreak>
-<afterbreak>[^\p{Ll}]</afterbreak>
-</rule>
-<rule break="no">
-<beforebreak>\bprof\.\s</beforebreak>
-<afterbreak></afterbreak>
-</rule>
 <rule break="no">
 <beforebreak>[.!?…][’'"]\s</beforebreak>
 <afterbreak>[a-z]</afterbreak>
@@ -1723,11 +1729,11 @@
 <afterbreak>[a-z]</afterbreak>
 </rule>
 <rule break="yes">
-<beforebreak>[\.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002¹²³]*\s</beforebreak>
+<beforebreak>[.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002¹²³]*\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="yes">
-<beforebreak>[\.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002]*</beforebreak>
+<beforebreak>[.!?…][’'"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002]*</beforebreak>
 <afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
 </rule>
 <rule break="yes">
@@ -1768,31 +1774,29 @@
 <afterbreak>['"\u00BB\u2019\u201D\u203A\u00AB\p{Pe}\u0002][A-Z][a-z]</afterbreak>
 </rule>
 <rule break="no">
-<!-- "E. coli etc. -->
 <beforebreak>"[A-Z][.]\s</beforebreak>
 <afterbreak>[a-z]</afterbreak>
 </rule>
 <rule break="no">
-<!-- Cornelisz. -->
 <beforebreak>[A-Z][a-z].*sz[.]\s</beforebreak>
 <afterbreak>[a-z]</afterbreak>
 </rule>
 <rule break="no">
-<!-- De n. XIV/vagus (nervus) -->
 <beforebreak>De n[.]\s</beforebreak>
 <afterbreak>[a-z]|[XIV]</afterbreak>
 </rule>
 <rule break="no">
-<!-- MOL.E -->
 <beforebreak>[A-Z]{2,5}[.]</beforebreak>
 <afterbreak>[A-Z]</afterbreak>
 </rule>
 <rule break="no">
-<!-- ..." betekent  -->
 <beforebreak>\.\.</beforebreak>
 <afterbreak>" [a-z]</afterbreak>
 </rule>
-<!-- ##### end of Dutch #### -->
+<rule break="no">
+<beforebreak>\sBTW\.</beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
+</rule>
 </languagerule>
 <languagerule languagerulename="Slovak">
 <rule break="no">
@@ -4370,7 +4374,7 @@
 </rule>
 <rule break="no">
 <beforebreak>\b(р|ред|Рис|рус|с|сб|св|См|см|сов|соч|соц|спец|ср|ст|стр|т|тел|Тел|тех|тов|тт|туп)\.\s</beforebreak>
-<afterbreak></afterbreak>
+<afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b(руб|Руб|тыс|Тыс|трлн)\.\s</beforebreak>
@@ -4654,7 +4658,7 @@
 <afterbreak>[XIV\d]+\b</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b([Ee]ds?|[Cc]oords?|\d+(r|n|t|è|é|a|rs|ns|es)|masc|fem|sing|pl|adj|adv|g|kg|m|km|cm|ha|u|h|hrs|s|ss|alt|cant|cast|cert|com|dir|gr|nom|parc|pres|set|Sr|Jr|Admón|Adm|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]</beforebreak>
+<beforebreak>\b([Ee]ds?|[Cc]oords?|\d+(r|n|t|è|é|a|rs|ns|es)|seg|masc|fem|sing|pl|adj|adv|g|kg|m|km|cm|ha|u|h|hrs|s|ss|alt|cant|cast|cert|com|dir|gr|nom|parc|pres|set|Sr|Jr|Admón|Adm|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]</beforebreak>
 <afterbreak>[\-¡¿«»"'\u2018\u201C\p{Ps}\u2012\u2013\u2014\u2015\u2053]*\p{Ll}</afterbreak>
 </rule>
 <!-- Any word in acronyms like U.S.A.F or F. B. I. or C. or c.s.p. or p. e. -->
@@ -4721,12 +4725,10 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="Spanish">
-
 <rule break="no">
 <beforebreak>¿[^?]+:[\s\u00A0]</beforebreak>
 <afterbreak>.</afterbreak>
 </rule>
-
 <rule break="no">
 <beforebreak>Yahoo![\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
@@ -4742,7 +4744,7 @@
 <!-- initials: A. C. Jones. Problem: [...] de Alfons I. Él era [...] -->
 <rule break="no">
 <beforebreak>\b[A-ZÀÉÈÍÓÒÚ]\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <!-- Ellipsis: ... lowercase -->
 <rule break="no">
@@ -4772,39 +4774,37 @@
 <afterbreak>[\-¡¿«»"'\u2018\u201C\p{Ps}\u2012\u2013\u2014\u2015\u2053]*\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<!-- URLs without "www."-->
 <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">
-<!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
 <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>
 </rule>
 <!-- Abbreviations that cannot finish sentences-->
 <rule break="no">
 <beforebreak>\b((?iu)(en|febr|mzo|abr|my|jun|jul|ag|agt|set|sept|setbre|oct|nov|novbre|dic|dicbre))\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b(dc|(?iu)(n|[Aa]yto|Mr|C|Dr|Dra|E|Emm|Emma|Excm|Excma|Hble|I|Il·lm|Il·lma|Il·ltre|Im|Ima|Mgfc|Mgfca|Mn|R|Rev|Sr|Sra|Sres|Sras|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></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b([Aa]vda|[Pp][ol]|Pl?za|[Aa]dm|[Dd]pto|Sr|Mr|Srta|ej)\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b(Dña|Dr[a]?|Sra|Sto|S(ri)?ta|Ldo|Ing|Prof|Excmo|Ilmo|Mgfco|admdor|admdora)\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b([Aa]rt|[Cc]ód|[Ss]ecc|[Tt]ít)\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\b([Ee]d(it)?|[Nn]o|n|[Nn]úm|[Pp]ág|p|c|\d+er)|[V\.]gr\.[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <!-- Abbreviations that can finish sentences -->
 <rule break="no">
@@ -4837,7 +4837,7 @@
 <!-- Composed abbrev. -->
 <rule break="no">
 <beforebreak>\bet al\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]</beforebreak>
-<afterbreak/>
+<afterbreak></afterbreak>
 </rule>
 <!-- Units -->
 <rule break="no">
@@ -4859,11 +4859,11 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="German">
-<rule break="no"><!-- URLs without "www."-->
+<rule break="no">
 <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"><!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
+<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>
 </rule>
@@ -4882,27 +4882,27 @@
 <beforebreak>[^-\p{L}'’/°]\p{L}[\.!?…]['|"|“|«|\)|\]|\}]?[\u00A0\s]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- special case: "Das 1. Internationale Filmfestival findet nächste Woche statt." -->
+<rule break="no">
 <beforebreak>([Dd](as|er|ie|iese[rsmn]?|en|em)|[kmsd]?ein(e[rsnm]?)?|am|fürs|ins|zum|im|am|zur) \d+\.[\u00A0\s]+</beforebreak>
 <afterbreak>[A-ZÄÖÜ].*</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>Ust.</beforebreak><!-- needed for German rule UST_ID -->
+<beforebreak>Ust.</beforebreak>
 <afterbreak>Id</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>Prof.</beforebreak><!-- needed for German rule ABKUERZUNG_LEERZEICHEN -->
+<beforebreak>Prof.</beforebreak>
 <afterbreak>Dr</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>Dr.</beforebreak><!-- needed for German rule ABKUERZUNG_LEERZEICHEN -->
+<beforebreak>Dr.</beforebreak>
 <afterbreak>iur|med|oec|phil|rer|theol</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>(?i)FRITZ!</beforebreak>
 <afterbreak>(?i)Box</afterbreak>
 </rule>
-<rule break="no"><!-- https://de.wikipedia.org/wiki/VW_ID.3 -->
+<rule break="no">
 <beforebreak>ID.</beforebreak>
 <afterbreak>3|4|Buzz|Crozz</afterbreak>
 </rule>
@@ -4972,7 +4972,7 @@
 </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" -->
@@ -5012,11 +5012,11 @@
 </rule>
 <!-- German abbreviations -->
 <rule break="no">
-<beforebreak>\b(betr|Geb|Stk|ggü|Mag|mtl|versch|[Ss]tellv|d|Übers|usw|[Bb]zw|Ab[hkst]|[Aa]bzü?gl|[Ll]tda|[Ee]inschl|[Vv]mtl|Ev|bezgl|Abzw|[Vv]sl|ahd|Akk|aktual|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|[Aa]utom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|Bez|Bhf|bspw|btto|bw|Dtl|Dez)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(betr|Geb|Stk|ggü|Mag|mtl|[Pp]arl|versch|[Ss]tellv|d|Übers|usw|[Bb]zw|Ab[hkst]|[Aa]bzü?gl|[Ll]tda|[Ee]inschl|[Vv]mtl|Ev|bezgl|Abzw|[Vv]sl|ahd|Akk|aktual|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|[Aa]utom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|Bez|Bhf|bspw|btto|bw|Dtl|Dez)\.[\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?|exkl|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|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>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5028,11 +5028,11 @@
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(ff|Fa|fachspr|fam|fem|Fem|Fr|franz|frz?|[Aa]ltfranz|frdl|Frl|Fut|Gd|gebr?|Gebr|geh|geleg|gen|Gen|germ|gesch|ges|get|ggf|Ggf|Ggs|ggT|Gr|[Gg]rds|griech)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(ff|Fa|fachspr|fam|fem|Fem|Fr|franz|[Ff]rz?|[Aa]ltfranz|frdl|Frl|Fut|Gd|gebr?|Gebr|geh|geleg|gen|Gen|germ|gesch|ges|get|ggf|Ggf|Ggs|ggT|Gr|[Gg]rds|griech)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(hebr|hg|hl|Hrsg|Hg|hist|hochd|hochspr|Hptst|Hr|hrsg|Allg|IdNr|ill|inkl|incl|Ind|Inf|Ing|ital|Tr|jap|Jb|Jg|Jhd?|Jhdts?|jmd[mns]?|jur|Kap|kart|kath|kfm|kaufm|Kfm|kgl|Kl|Konj|königl|Krs?|Kto)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\b(hebr|hg|hl|Hrsg|Hg|hist|hochd|hochspr|Hptst|Hr|hrsg|Allg|IdNr|ill|[Ii]nkl|[Ii]ncl|[Ee]hem|Ind|Inf|Ing|ital|Tr|jap|Jb|Jg|Jhd?|Jhdts?|jmd[mns]?|jur|Kap|kart|kath|kfm|kaufm|Kfm|kgl|Kl|Konj|königl|Krs?|Kto)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5048,7 +5048,11 @@
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Tel|teilw|Temp|trans|Tsd|übertr|übl|ff|überarb|ugs|univ|unveränd|urspr|USt|UST|USt\-IdNr|[Aa][bn]schl|sw|kl|[Gg]r|vgl|vll|Vll|vlt|Vlt|vllt|Vllt|Vgl|Vol|vollst|vorm|Vp|Vs|vs|wesentl|wg|Whg|Hd|Ztr|zus|Zus|zzt?|zzgl|zB|zb|Zz|Zt|zw|Min|Bzgl|bzgl|bezügl|Frhr|ggfs|insb|autom|Mw[sS]t)\.[\u00A0\s]{1,2}</beforebreak>
+<beforebreak>\d+\.\d+\.[\u00A0\s]</beforebreak>
+<afterbreak>[\-–][\u00A0\s]\d+</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b(Tel|teilw|Temp|trans|Tsd|übertr|übl|ff|überarb|ugs|univ|unveränd|urspr|USt|UST|USt\-IdNr|[Aa][bn]schl|sw|kl|[Gg]r|vgl|vll|Vll|vlt|Vlt|vllt|Vllt|Vgl|Vol|vollst|vorm|Vp|Vs|vs|wesentl|[Rr]echts?staatl|[Ss]taatl|wg|Whg|Hd|Ztr|zus|Zus|zzt?|zzgl|zB|zb|Zz|Zt|zw|Min|Bzgl|bzgl|bezügl|Frhr|ggfs|insb|autom|Mw[sS]t)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- Break rules -->
@@ -5159,27 +5163,27 @@
 <beforebreak>\b(Mrs?|No|pp|St|no|Sr|Jr|Bros|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Ju[nl]|Aug|Sep|Sept|Oct|Okt|Nov|Dec|PhD|al|cf|Inc|Ms|Gen|Sen|Prof|Corp|Co)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- Ph.D. -->
+<rule break="no">
 <beforebreak>\bP[Hh]\.\s?</beforebreak>
 <afterbreak>D\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Eng. (Bachelor of Engineering) -->
+<rule break="no">
 <beforebreak>\b[BM]\.\s?</beforebreak>
 <afterbreak>Eng\.?</afterbreak>
 </rule>
-<rule break="no"><!-- LL.B. (Bachelor of Laws) -->
+<rule break="no">
 <beforebreak>\bLL\.\s?</beforebreak>
 <afterbreak>[BM]\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Sc. (Bachelor of Science) -->
+<rule break="no">
 <beforebreak>\b[BM]\.\s?</beforebreak>
 <afterbreak>Sc\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Comp. (Bachelor of Computing) -->
+<rule break="no">
 <beforebreak>\b[BM]\.\s?</beforebreak>
 <afterbreak>Comp?\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Arch. (Bachelor of Architecture) -->
+<rule break="no">
 <beforebreak>\b[BM]\.\s?</beforebreak>
 <afterbreak>Arch\.?</afterbreak>
 </rule>
@@ -5309,16 +5313,15 @@
 <beforebreak>\.\[\d+\][\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- URLs without "www."-->
+<rule break="no">
 <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"><!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
+<rule break="no">
 <beforebreak>\b[A-Za-z0-9\-]+\.</beforebreak>
 <afterbreak>[A-Za-z0-9\-]+\.(fr|com|net|org|info|de|es|edu|co|eu|nl|io|cn|uk|gov|biz|ca|tk|ru|br|jp|pl)(\.|\b)</afterbreak>
 </rule>
 <rule break="no">
-<!-- gaffa.org -->
 <beforebreak>\b[A-Za-z0-9\-]+\.</beforebreak>
 <afterbreak>[A-Za-z]{2,5}(\.|\b)</afterbreak>
 </rule>
@@ -5363,15 +5366,15 @@
 <beforebreak>\b\p{L}\.</beforebreak>
 <afterbreak>\p{L}\.</afterbreak>
 </rule>
-<rule break="no"><!-- Je suis (...) Chris. -->
+<rule break="no">
 <beforebreak>(…|\.\.\.)[\s\u00A0]?\)[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{P}]</afterbreak>
 </rule>
-<rule break="no"><!-- Je suis (...?) Chris. -->
+<rule break="no">
 <beforebreak>(…|\.\.\.)[\s\u00A0]?\?\)[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{P}]</afterbreak>
 </rule>
-<rule break="no"><!-- Jones v. Smith -->
+<rule break="no">
 <beforebreak>\p{Lu}\p{L}+[\s\u00A0]v\.[\s\u00A0]</beforebreak>
 <afterbreak>\p{Lu}\p{L}+</afterbreak>
 </rule>
@@ -5411,44 +5414,44 @@
 <beforebreak>\(\p{Ll}+\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- i.e. -->
-<beforebreak>i\.e\.[\s\u00A0]</beforebreak><!-- "i.e." is never at end of sentence -->
+<rule break="no">
+<beforebreak>i\.e\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- U.S.A (no dot at end) -->
+<rule break="no">
 <beforebreak>[A-Z]\.[A-Z]\.</beforebreak>
 <afterbreak>[A-Z]\b</afterbreak>
 </rule>
-<rule break="no"><!-- L.A (no dot at end) -->
+<rule break="no">
 <beforebreak>\bL\.</beforebreak>
 <afterbreak>A\b</afterbreak>
 </rule>
-<rule break="no"><!-- U.S (no dot at end) -->
+<rule break="no">
 <beforebreak>\bU\.</beforebreak>
 <afterbreak>[SK]\b</afterbreak>
 </rule>
-<rule break="no"><!-- No. 5 -->
+<rule break="no">
 <beforebreak>\b[nN]o\.[\s\u00A0]</beforebreak>
 <afterbreak>\p{N}</afterbreak>
 </rule>
-<rule break="no"><!-- Ph.D. -->
+<rule break="no">
 <beforebreak>\bP[Hh]\.[\s\u00A0]?</beforebreak>
 <afterbreak>D\.?</afterbreak>
 </rule>
-<rule break="no"><!-- e.g. -->
+<rule break="no">
 <beforebreak>\be\.g\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- vs. -->
+<rule break="no">
 <beforebreak>\bvs\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!--"Etc." can end the sentence, so we check for the uppercase letter after it.-->
-<rule break="no"><!-- Etc. -->
+<rule break="no">
 <beforebreak>\b[Ee]tc\.[\s\u00A0]</beforebreak>
 <afterbreak>[^\p{Lu}]</afterbreak>
 </rule>
-<rule break="no"><!-- BTW (by the way) -->
+<rule break="no">
 <beforebreak>\b([Bb]tw|BTW)\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
@@ -5456,39 +5459,39 @@
 <beforebreak>(?i)FRITZ!</beforebreak>
 <afterbreak>(?i)Box</afterbreak>
 </rule>
-<rule break="no"><!-- https://de.wikipedia.org/wiki/VW_ID.3 -->
+<rule break="no">
 <beforebreak>ID.</beforebreak>
 <afterbreak>3|4|Buzz|Crozz</afterbreak>
 </rule>
-<rule break="no"><!-- Ph.D. (see rule PH_D) -->
+<rule break="no">
 <beforebreak>\bP[Hh]\.?[\s\u00A0]?[Dd]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- "I have a B. Eng. degree" (see rule BACHELOR_ABBR) -->
+<rule break="no">
 <beforebreak>\b(P[hH][dD]|BSc|BEng|BComp|BArch|MSc|MEng|MComp)\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- "I have a LL.B degree." (see rule PH_D) -->
+<rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?[BM]\.[\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<rule break="no"><!-- B.Eng. (Bachelor of Engineering) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Eng\.?</afterbreak>
 </rule>
-<rule break="no"><!-- LL.B. (Bachelor of Laws) -->
+<rule break="no">
 <beforebreak>\bLL\.[\s\u00A0]?</beforebreak>
 <afterbreak>[BM]\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Sc. (Bachelor of Science) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Sc\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Comp. (Bachelor of Computing) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Comp?\.?</afterbreak>
 </rule>
-<rule break="no"><!-- B.Arch. (Bachelor of Architecture) -->
+<rule break="no">
 <beforebreak>\b[BM]\.[\s\u00A0]?</beforebreak>
 <afterbreak>Arch\.?</afterbreak>
 </rule>
@@ -5534,7 +5537,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Ukrainian">
 <!-- when sentence starts with ellipsis: ...Мазій і Юхим теж. -->
 <rule break="no">
@@ -5547,8 +5549,8 @@
 <afterbreak>\p{Lu}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>[.!?…][\h]+</beforebreak>
-<afterbreak>[\h]*([«"„“(]|[&#x2010;-&#x2015;-][\h])\p{Ll}</afterbreak>
+<beforebreak>[.!?…][»“]?[\h]+</beforebreak>
+<afterbreak>[\h]*([«"„“(]|[‐-―-][\h])\p{Ll}</afterbreak>
 </rule>
 <rule break="yes">
 <beforebreak>\v[\h]*</beforebreak>
@@ -5562,7 +5564,7 @@
 <!-- various punctuation between lowercase letters -->
 <rule break="no">
 <beforebreak>\b\p{Ll}+[.!?][\h\v]*</beforebreak>
-<afterbreak>\h*(([\(«]|[\[&#x2010;-&#x2015;-][\h\v]*)?\p{Ll})</afterbreak>
+<afterbreak>\h*(([\(«]|[\[‐-―-][\h\v]*)?\p{Ll})</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>([\[\(]*[\]\)]*|\.\.\.|…)[\h\v]+</beforebreak>
@@ -5583,7 +5585,6 @@
 <beforebreak>(^[\h\v]*|\([\h\v]*|[«„"]|(\b[А-ЯІЇЄҐACEIHOPX]\.-))[А-ЯІЇЄҐA-Z]\.[\h\v]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<!-- І. В. Коваль, Т. 2, C. 202 -->
 <!-- Іван Ч. (1914 р. н.) -->
 <rule break="no">
 <beforebreak>[\h\v][А-ЯІЇЄҐ]\.[\h\v]*</beforebreak>
@@ -5606,7 +5607,7 @@
 -->
 <rule break="no">
 <beforebreak>\b([0-9]{2}|[0-9]{4})[\h\v]+р\.[\h\v]+</beforebreak>
-<afterbreak>[\h\v]*[№0-9&#x2010;-&#x2015;-]</afterbreak>
+<afterbreak>[\h\v]*[№0-9‐-―-]</afterbreak>
 </rule>
 <!-- річка - р. Дніпро -->
 <rule break="no">
@@ -5615,7 +5616,7 @@
 </rule>
 <!-- У травні 1949 р. Грушківський район -->
 <rule break="no">
-<beforebreak>[А-ЯІЇЄҐ][а-яіїєґ'’-]*([\h]+[а-яіїєґ'’-]+)?[\h](\d{4}[&#x2010;-&#x2015;-])*\d{4}[\h]*р\.[\h\v]*</beforebreak>
+<beforebreak>[А-ЯІЇЄҐ][а-яіїєґ'’-]*([\h]+[а-яіїєґ'’-]+)?[\h](\d{4}[‐-―-])*\d{4}[\h]*р\.[\h\v]*</beforebreak>
 <afterbreak>[\v\h]*(?!(На|Але|Так?)[\h\v]+)[А-ЯІЇЄҐA-Z][^\h\v]</afterbreak>
 </rule>
 <!-- 15 вересня 1995 р. Україною було підписно -->
@@ -5635,22 +5636,27 @@
 </rule>
 <!-- усталені скорочення, що не збігаються з нескороченими словами -->
 <rule break="no">
-<!-- unfortunately \b ignores \u0301 -->
-<beforebreak>\b(укр|рос|англ|амер|італ|ісп|нім|фр(анц)?|лат|грец(ьк))\.[\h\v]*</beforebreak>
+<beforebreak>\b(укр|рос|англ?|амер|італ|ісп|нім|фр(анц)?|лат|грец(ьк)?)\.[\h\v]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<!-- unfortunately \b ignores \u0301 -->
-<beforebreak>\b(абз|арк|ауд|бл|буд|бульв|вул|держ|дод|зав|зб|зв|зовн|екон|к|кв|канд|кн|напр|нац|обл|оп|пл|пол|поч|пп|пор|просп|розд|стор|табл|[Тт]]ел|ч|част)\.[\h\v]*</beforebreak>
+<beforebreak>\b(абз|арк|ауд|бл|буд|бульв|вул|держ|дод|зав|зб|зв|зовн|екон|к|кв|канд|кн|напр|нпр|нац|обл|оп|пл|пол|поч|пп|пор|просп|розд|стор|табл|[Тт]]ел|ч|част)\.[\h\v]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<!-- unfortunately \b ignores \u0301 -->
 <beforebreak>\b[сС]т\.[\h\v]</beforebreak>
 <afterbreak>[\h]*(?!([АВУОІЄ]|На|Але|Так?)[\h\v])</afterbreak>
 </rule>
+<!-- нар. 1945 р. | (1966 р. нар.) | 1975 — нар. Осипчук -->
+<rule break="no">
+<beforebreak>([0-9]|[-–—])[\h\v]+нар\.[\h\v]*</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\bнар\.[\h\v]*</beforebreak>
+<afterbreak>([0-9]|бл\.|арт\.)</afterbreak>
+</rule>
 <rule break="no">
-<!-- no break only for дол. США -->
 <beforebreak>\bдол\.[\h\v]*</beforebreak>
 <afterbreak>США</afterbreak>
 </rule>
@@ -5666,7 +5672,7 @@
 </rule>
 <!-- Верховний орган, див. Африканський національний конгрес -->
 <rule break="no">
-<beforebreak>[,&#x2010;-&#x2015;-][\h\v]*(див)\.[\h\v]*</beforebreak>
+<beforebreak>[,‐-―-][\h\v]*(див)\.[\h\v]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- скорочення в дужках:
@@ -5678,10 +5684,14 @@
 </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|упоряд|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)\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*[А-ЯІЇЄҐA-Z]</afterbreak>
 </rule>
 <rule break="no">
+<beforebreak>(?&lt;![іи]\s+)\bдр\.[\h\v]*</beforebreak>
+<afterbreak>[\h\v]*[А-ЯІЇЄҐ]</afterbreak>
+</rule>
+<rule break="no">
 <beforebreak>\bМан\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*([Сс]іті|[Юю]н)</afterbreak>
 </rule>
@@ -5690,18 +5700,16 @@
 <beforebreak>[^0-9][\h\v]+[Гг]р\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*[А-ЯІЇЄҐA-Z]</afterbreak>
 </rule>
-<!-- арт. - артикул -->
 <!-- TODO: арт. - артист -->
 <rule break="no">
 <beforebreak>\b([Аа]рт|[Мм]ал|[Рр]ис)\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*[0-9]</afterbreak>
 </rule>
-<!-- ХІІ р., 3-6 арт. -->
+<!-- ХІІ р., 3-6 арт., 2-3 тт. -->
 <rule break="no">
-<beforebreak>[0-9][\h\v]+арт\.[\h\v]*</beforebreak>
+<beforebreak>[0-9][\h\v]+(арт|тт)\.[\h\v]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
-<!-- місто, але принаймні з парою літер в назві бо є ще метри (м) -->
 <!-- але розбиваємо «всього 20 м. Почалося» -->
 <rule break="no">
 <beforebreak>(?&lt;!\d[\h\v]*)\bм\.[\h\v]*</beforebreak>
@@ -5725,10 +5733,8 @@
 <!-- статус правових держав. — Авт.). -->
 <rule break="no">
 <beforebreak></beforebreak>
-<afterbreak>[\h\v]*[&#x2010;-&#x2015;-][\h\v]*([Рр]ед|[Аа]вт)[\h\v]*\.[\)\]]</afterbreak>
+<afterbreak>[\h\v]*[‐-―-][\h\v]*([Рр]ед|[Аа]вт)[\h\v]*\.[\)\]]</afterbreak>
 </rule>
-<!-- force the break  -->
-<!-- часто зустрічається крапка+U+202F+пробіл, який srx чомусь не розбиває на речення -->
 <!-- але лишаємо ініціали: С.\u202F Шелухин -->
 <rule break="yes">
 <beforebreak>(?&lt;!\h[А-ЯІЇЄҐ])[.!?…]{1,3}\u202F[\h\v]+</beforebreak>
@@ -5746,10 +5752,9 @@
 <!-- “Слон” (2008 р.) У минулому харків’янка -->
 <rule break="yes">
 <beforebreak>[.!?…]['»"„“”)\]›]?[\h\v]+</beforebreak>
-<afterbreak>([&#x2010;-&#x2015;-][\h\v]*)?\p{Lu}[^\p{Lu}]</afterbreak>
+<afterbreak>([‐-―-][\h\v]*)?\p{Lu}[^\p{Lu}]</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Belarusian">
 <rule break="no">
 <beforebreak>\b\d+\.\s</beforebreak>
@@ -6016,11 +6021,11 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="Portuguese">
-<rule break="no"><!-- URLs without "www."-->
+<rule break="no">
 <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"><!-- Subdomains without "www." (e.g. foo.MyDomain.com)-->
+<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>
 </rule>
@@ -6515,7 +6520,7 @@
 </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"-->
@@ -6654,83 +6659,83 @@
 </rule>
 </languagerule>
 <languagerule languagerulename="Arabic">
- <rule break="no">
- <beforebreak>\bwww\.</beforebreak>
- <afterbreak>\w</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[\[\(]*…[\]\)]* </beforebreak>
- <afterbreak>\p{Ll}</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\p{Ps}[!?؟]+\p{Pe} </beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[\.!?؟…]+\p{Pe} </beforebreak>
- <afterbreak>\p{Ll}</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[«»"”']\s*</beforebreak>
- <afterbreak>\s*\p{Ll}</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[«'"„][\.!?؟…]['"”»]\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\b\p{L}\.\s</beforebreak>
- <afterbreak>\p{L}\.\s</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\b\p{L}\.</beforebreak>
- <afterbreak>\p{L}\.</afterbreak>
- </rule>
- <rule break="yes">
- <beforebreak>[^,،][\s]\p{L}{2}\.\s</beforebreak>
- <afterbreak>\p{N}+\)\s</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[\.\s]\p{L}{1,2}\.\s</beforebreak>
- <afterbreak>[\p{N}\p{Ll}]</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[\[\(]*\.\.\.[\]\)]* </beforebreak>
- <afterbreak>[^\p{Lu}]</afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\b\p{Lu}\.\s\p{Lu}\.\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\b\p{Lu}\.\p{Lu}\.\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[^\.]\s[ابتقجحخدذصضعغفقكلمنهوىيءةأ١٢٣٤٥٦٧٨٩٠A-Z]\.\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>[^\.]\s[\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652\u0653\u0654\u0655\u0656\u0640]\.\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="no">
- <beforebreak>\(\p{Ll}+\.\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="yes">
- <beforebreak>[\.!?؟…][«»\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s</beforebreak>
- <afterbreak></afterbreak>
- </rule>
- <rule break="yes">
- <beforebreak>[\.!?؟…][«»'"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*</beforebreak>
- <afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
- </rule>
- <rule break="yes">
- <beforebreak>\s\p{L}[\.!?؟…]\s</beforebreak>
- <afterbreak>\p{Lu}\p{Ll}</afterbreak>
- </rule>
- </languagerule>
+<rule break="no">
+<beforebreak>\bwww\.</beforebreak>
+<afterbreak>\w</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[\[\(]*…[\]\)]* </beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\p{Ps}[!?؟]+\p{Pe} </beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[\.!?؟…]+\p{Pe} </beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[«»"”']\s*</beforebreak>
+<afterbreak>\s*\p{Ll}</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[«'"„][\.!?؟…]['"”»]\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b\p{L}\.\s</beforebreak>
+<afterbreak>\p{L}\.\s</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b\p{L}\.</beforebreak>
+<afterbreak>\p{L}\.</afterbreak>
+</rule>
+<rule break="yes">
+<beforebreak>[^,،][\s]\p{L}{2}\.\s</beforebreak>
+<afterbreak>\p{N}+\)\s</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[\.\s]\p{L}{1,2}\.\s</beforebreak>
+<afterbreak>[\p{N}\p{Ll}]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[\[\(]*\.\.\.[\]\)]* </beforebreak>
+<afterbreak>[^\p{Lu}]</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b\p{Lu}\.\s\p{Lu}\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\b\p{Lu}\.\p{Lu}\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[^\.]\s[ابتقجحخدذصضعغفقكلمنهوىيءةأ١٢٣٤٥٦٧٨٩٠A-Z]\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>[^\.]\s[\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652\u0653\u0654\u0655\u0656\u0640]\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\(\p{Ll}+\.\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="yes">
+<beforebreak>[\.!?؟…][«»\u00BB\u2019\u201D\u203A"'\p{Pe}\u0002¹²³]*\s</beforebreak>
+<afterbreak></afterbreak>
+</rule>
+<rule break="yes">
+<beforebreak>[\.!?؟…][«»'"\u00BB\u2019\u201D\u203A\p{Pe}\u0002]*</beforebreak>
+<afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
+</rule>
+<rule break="yes">
+<beforebreak>\s\p{L}[\.!?؟…]\s</beforebreak>
+<afterbreak>\p{Lu}\p{Ll}</afterbreak>
+</rule>
+</languagerule>
 </languagerules>
 <maprules>
 <languagemap languagepattern=".*" languagerulename="GeneralImportant"></languagemap>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: srx-languagetool
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.9.0
 platform: ruby
 authors:
 - Aaron Madlon-Kay
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2022-09-29 00:00:00.000000000 Z
+date: 2022-12-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: srx