srx-languagetool 0.6.0 → 0.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8848393929f09be9f3141298d9fb3f1a33953e5e2253397105a11004c83c53e1
-  data.tar.gz: a21b9fed14c49f2f9da50dbadbe89a5cd00224b827539d9cb6674d77482c5f87
+  metadata.gz: f73cebe4cfa7e771e3250f1f1dc13694b6450e19a4f9adf81769c5a75baa76d5
+  data.tar.gz: 35f29775c7d85150bc61551e9fb32adcb60cebc392d9d37e01d829b193a7464c
 SHA512:
-  metadata.gz: 8562133261975230c8fff7f4ef08a7ef31b505cf819080a296b83934176880200677400f6bd1c93ac75e033f4e64af4a0d803810adfd68d06e2d990560b5f520
-  data.tar.gz: b5c97d8b925d425f6832fa5de77f6c98c6cbb483545219da5ee9f9905095bea9e53eda225140e10f409af87a1bd9e2c8bfccaaa08b80c88e048818e19a3ffe29
+  metadata.gz: 548319e33a292724739e81eb28433594dfea9ec8e9e1fd78366d1847e601a5c6e1521e1fa639bd760fd33ee80d45190a83e92fdcb64d17efae730f5ac7958e6d
+  data.tar.gz: b55939faa805e0e5102a8610c4c89571f47c5002d3c7b7dfa26fa9f8785f83ce4083bec63abad845565091ddfad752c2ca6b9599a88be621e5618053ad5b0394

data/.github/workflows/main.yml

@@ -10,10 +10,10 @@ jobs:
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:
-        ruby-version: 2.7.5
+        ruby-version: 2.7.6
     - name: Install
       run: |
-        gem install bundler -v 2.3.10
+        gem install bundler -v 2.3.22
         bundle install
     - name: Type check
       run: bundle exec solargraph typecheck --level typed

data/.ruby-version

@@ -1 +1 @@
-2.7.5
+2.7.6

data/CHANGELOG.md

@@ -1,6 +1,14 @@
 ## [Unreleased]
 
-## [0.6.0] - 2022-3-30
+## [0.8.0] - 2022-09-29
+
+- Update rules to LanguageTool 5.9
+
+## [0.7.0] - 2022-07-04
+
+- Update rules to LanguageTool 5.8
+
+## [0.6.0] - 2022-03-30
 
 - Update rules to LanguageTool 5.7
 

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    srx-languagetool (0.6.0)
+    srx-languagetool (0.8.0)
       srx (< 1.0)
 
 GEM
@@ -14,40 +14,42 @@ GEM
     diff-lcs (1.5.0)
     e2mmap (0.1.0)
     jaro_winkler (1.5.4)
-    kramdown (2.3.2)
+    json (2.6.2)
+    kramdown (2.4.0)
       rexml
     kramdown-parser-gfm (1.1.0)
       kramdown (~> 2.0)
-    minitest (5.15.0)
-    nokogiri (1.13.3-x86_64-darwin)
+    minitest (5.16.3)
+    nokogiri (1.13.8-x86_64-darwin)
       racc (~> 1.4)
     parallel (1.22.1)
-    parser (3.1.1.0)
+    parser (3.1.2.1)
       ast (~> 2.4.1)
     racc (1.6.0)
     rainbow (3.1.1)
     rake (13.0.6)
-    regexp_parser (2.2.1)
+    regexp_parser (2.6.0)
     reverse_markdown (2.1.1)
       nokogiri
     rexml (3.2.5)
-    rspec-expectations (3.11.0)
+    rspec-expectations (3.11.1)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.11.0)
-    rspec-support (3.11.0)
-    rubocop (1.26.1)
+    rspec-support (3.11.1)
+    rubocop (1.36.0)
+      json (~> 2.3)
       parallel (~> 1.10)
-      parser (>= 3.1.0.0)
+      parser (>= 3.1.2.1)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
-      rexml
-      rubocop-ast (>= 1.16.0, < 2.0)
+      rexml (>= 3.2.5, < 4.0)
+      rubocop-ast (>= 1.20.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 1.4.0, < 3.0)
-    rubocop-ast (1.16.0)
+    rubocop-ast (1.21.0)
       parser (>= 3.1.1.0)
     ruby-progressbar (1.11.0)
-    solargraph (0.44.3)
+    solargraph (0.47.1)
       backport (~> 1.2)
       benchmark
       bundler (>= 1.17.2)
@@ -65,10 +67,10 @@ GEM
     srx (0.6.0)
       nokogiri (~> 1.11)
     thor (1.2.1)
-    tilt (2.0.10)
-    unicode-display_width (2.1.0)
+    tilt (2.0.11)
+    unicode-display_width (2.3.0)
     webrick (1.7.0)
-    yard (0.9.27)
+    yard (0.9.28)
       webrick (~> 1.7.0)
 
 PLATFORMS
@@ -85,4 +87,4 @@ DEPENDENCIES
   srx-languagetool!
 
 BUNDLED WITH
-   2.3.10
+   2.3.22

data/lib/srx/languagetool/version.rb

@@ -2,6 +2,6 @@
 
 module Srx
   module Languagetool
-    VERSION = '0.6.0'
+    VERSION = '0.8.0'
   end
 end

data/lib/srx/segment.srx

@@ -1159,7 +1159,7 @@
 <afterbreak>D\.?</afterbreak>
 </rule>
 <rule break="no"><!-- min. -->
-<beforebreak>\b([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|[Mm]in|[Mm]ax|[Gg]ovt|[Rr]etd|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|[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. -->
@@ -1553,6 +1553,10 @@
 <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-->
+<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>
@@ -1578,7 +1582,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(arch|archeol|art|bc|betr|bez|bibl|bijl|bijv)\.\s</beforebreak>
+<beforebreak>\b(arch|archeol|art|bc|bep|betr|bez|bibl|bijl|[Bb]ijv)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1590,15 +1594,15 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(ed|em|enz|etc|ev|excl|fa|fam|fig|fl|fr.)\.\s</beforebreak>
+<beforebreak>\b(ed|em|enz|etc|ev|[Ee]xcl|fa|fam|fig|fin|fl|fr.)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(geb|get|gld|id|incl|ing|intern|ir|jhr|jkvr)\.\s</beforebreak>
+<beforebreak>\b(geb|[Gg]em|get|gld|id|[Ii]ncl|ind|inf|ing|intern|inz|ir|jhr|jkvr)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(jl|jr|kr|kt|lab|lic|ll|lt|lw|max|mi|min|mld)\.\s</beforebreak>
+<beforebreak>\b(jl|jr|kr|kt|lab|lic|ll|lt|lw|max|mevr|mi|[Mm]in|mld)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1606,11 +1610,11 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(opm|org|ov|pag|par|penn|plm|plv)\.\s</beforebreak>
+<beforebreak>\b(opm|org|ov|pag|par|penn|([1-3][\.e]?)[\s]?pers|plm|plv)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(prov|pseud|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|tk)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -1622,7 +1626,7 @@
 <afterbreak>Chr</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(uitsl|ver|vgl|vnl|vnw|voorz|ww|zat|zg)\.\s</beforebreak>
+<beforebreak>\b(uitsl|ver|vgl|vnl|vnw|voorz|ww|zat|[Zz]elfst|zgn?)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -4373,7 +4377,7 @@
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(уд|ул|уч|физ|х|хор|э)\.\s</beforebreak>
+<beforebreak>\b(уд|ул|уч|физ|х|хор|э|Эл|эл)\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -4717,6 +4721,12 @@
 </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>
@@ -4773,6 +4783,10 @@
 </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/>
+</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/>
 </rule>
@@ -4794,7 +4808,7 @@
 </rule>
 <!-- Abbreviations that can finish sentences -->
 <rule break="no">
-<beforebreak>\b([Ee]ds?|[Cc]oords?|grs?|Sr|Jr|Admón|Inc|Co|Hnos|Vda|[VU]d[s]?)\.[\p{Pe}\p{Pf}\p{Pd}"']*[\s\u00A0]</beforebreak>
+<beforebreak>\b([Ee]ds?|[Cc]oords?|grs?|Sr|Jr|Admón|Inc|Co|Hnos|Vda|[VUuv]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. -->
@@ -4860,14 +4874,18 @@
 </rule>
 <!-- Split at e.g. "1a. Und ..." -->
 <rule break="yes">
-<beforebreak>\d+[a-z]\.[\u00A0\s]</beforebreak>
+<beforebreak>\d+[a-z]\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{Lu}</afterbreak>
 </rule>
 <!-- Don't split at e.g. "d. h." -->
 <rule break="no">
-<beforebreak>[^-\p{L}'’/]\p{L}[\.!?…]['|"|“|«|\)|\]|\}]?[\u00A0\s]</beforebreak>
+<beforebreak>[^-\p{L}'’/°]\p{L}[\.!?…]['|"|“|«|\)|\]|\}]?[\u00A0\s]</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<rule break="no"><!-- special case: "Das 1. Internationale Filmfestival findet nächste Woche statt." -->
+<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 -->
 <afterbreak>Id</afterbreak>
@@ -4889,8 +4907,12 @@
 <afterbreak>3|4|Buzz|Crozz</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>[1-3]\.[\u00A0\s]</beforebreak>
-<afterbreak>Liga|Bundesliga|Fußball(-B|b)undesliga</afterbreak>
+<beforebreak>[1-3]\.[\u00A0\s]{1,2}</beforebreak>
+<afterbreak>Liga|Bundesliga|(Fußball|Handball|Basketball)(-B|b)undesliga</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\d+\.[\u00A0\s]{1,2}</beforebreak>
+<afterbreak>Klässler[sn]?</afterbreak>
 </rule>
 <rule break="no">
 <beforebreak>\bP[Hh]\.</beforebreak>
@@ -4904,43 +4926,43 @@
 <!-- Don't split after a white-space followed by a single letter followed
          by a dot followed by another whitespace. e.g. " p. " -->
 <rule break="no">
-<beforebreak>[\u00A0\s]\p{L}\.[\u00A0\s]</beforebreak>
+<beforebreak>[\u00A0\s]\p{L}\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{L}\.</afterbreak>
 </rule>
 <!-- Don't split at "bla bla... yada yada" -->
 <rule break="no">
-<beforebreak>[\[\(]?\.\.\.[\]\)]?[\u00A0\s]</beforebreak>
+<beforebreak>[\[\(]?\.\.\.[\]\)]?[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- Don't split [.?!] when they're quoted -->
 <rule break="no">
-<beforebreak>['"„][\.!?…]['"“][\u00A0\s]</beforebreak>
+<beforebreak>['"„][\.!?…]['"“«»][\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- Don't break after quote unless there's a capital letter
          e.g.: "That's right!" he said. -->
 <rule break="no">
-<beforebreak>["'“][\u00A0\s]</beforebreak>
+<beforebreak>["'“«»][\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <!-- e.g. "Das ist . so." - assume one sentence. -->
 <rule break="no">
-<beforebreak>[\u00A0\s]([\.!?]{1,3}|…)['|"|“|«|\)|\]|\}]?[\u00A0\s]</beforebreak>
+<beforebreak>[\u00A0\s]([\.!?]{1,3}|…)['|"|“|«|\)|\]|\}]?[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- Numbers, dates e.g. "3.10. datiert" -->
 <rule break="no">
-<beforebreak>\b\d+\.[\u00A0\s]</beforebreak>
+<beforebreak>\b\d+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{Ll}|\p{Lu}{2,}</afterbreak>
 </rule>
 <!-- z.B. "Das hier ist ein(!) Satz." -->
 <rule break="no">
-<beforebreak>[\(\[][!?]{1,3}[\]\)][\u00A0\s]</beforebreak>
+<beforebreak>[\(\[][!?]{1,3}[\]\)][\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- z.B. "Das hier ist (genau!) ein Satz." -->
 <rule break="no">
-<beforebreak>[!?]{1,3}[\)\]][\u00A0\s]</beforebreak>
+<beforebreak>[!?]{1,3}[\)\]][\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- z.B. "bla (...) blubb" -> kein Satzende -->
@@ -4950,75 +4972,83 @@
 </rule>
 <!-- don't split at cases like "Friedrich II. wird auch..." -->
 <rule break="no">
-<beforebreak>[\u00A0\s ][IVX]+\.[\u00A0\s]</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" -->
 <rule break="no">
-<beforebreak>\d+\.[\u00A0\s]</beforebreak>
+<beforebreak>\d+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>(und|oder|bis)[\u00A0\s]</afterbreak>
 </rule>
 <!-- einige deutsche Monate, vor denen eine Zahl erscheinen kann,
          ohne dass eine Satzgrenze erkannt wird
          (z.B. "am 13. Dezember" -> keine Satzgrenze) -->
 <rule break="no">
-<beforebreak>\d+\.[\u00A0\s]</beforebreak>
+<beforebreak>\d+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>Januar|Jänner|Februar|März|Merz|April|Mai|Ju[ln]i|August|September|Oktober|November|Dezember</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\d+\.[\u00A0\s]</beforebreak>
+<beforebreak>\d+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>J[aä]n|Febr?|Mär|Apr|Mai|Ju[nl]|Aug|Sept?|Okt|Nov|Dez</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>(Jan|Jän|Febr?|Mär|Apr|Mai|Ju[nl]|Aug|Sept?|Okt|Nov|Dez)\.[\u00A0\s]</beforebreak>
+<beforebreak>(Jan|Jän|Febr?|Mär|Apr|Mai|Ju[nl]|Aug|Sept?|Okt|Nov|Dez)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\d\d(\d\d)?</afterbreak>
 </rule>
 <!-- ähnliche Fälle außerhalb der Monatsnamen -->
 <rule break="no">
-<beforebreak>\d+\.[\u00A0\s]</beforebreak>
+<beforebreak>\d+\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak>Amtsperiode|Breitengrads?|Breitengrades|Jubiläum|Jhd?|Jhdts?|Konferenz|(Jahres|Partei)(-K|k)onferenz|Längengrade?s?|Tags?|Tages|(Jahres|Spiel|Partei|Geburts)tag|(Jahres|Spiel|Partei|Geburts)tages|(Jahres|Spiel|Partei|Geburts)tags|Jahrhunderts?|Jahrtausend|Platz|Platzes|Lebensjahrs?|Lebensjahres|Lochs?|Loches|Grads|Grades|Obergeschoss|Stock(werk)?s?|Etage|Klasse|Runde|Bezirk|Etappe|Staffel|Sinfonie</afterbreak>
 </rule>
 <!-- English abbreviations - but these work globally for all languages -->
 <rule break="no">
-<beforebreak>\b(Mrs?|No|pp|St|no|Sr|Jr|Bros|etc|[Bb]tw|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Ju[nl]|Aug|Sept?|O[ck]t|Nov|Dec|PhD|BSc|BEng|BComp|BArch|al|cf|Inc|Ms|MEng|MSc|MComp|Gen|Sen|Prof|Corp|Co|co|Ltd|Buchst)\.[\u00A0\s]</beforebreak>
+<beforebreak>\b(Mrs?|No|pp|St|no|Sr|Jr|[Ss]ek|Bros|etc|[Bb]tw|vs|esp|[Ff]ig|Jan|Feb|Mar|Apr|Ju[nl]|Aug|Sept?|O[ck]t|Nov|Dec|PhD|BSc|BEng|BComp|BArch|al|cf|Inc|Ms|MEng|MSc|MComp|Gen|Sen|Prof|Corp|Co|co|Ltd|Buchst)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- Latin abbreviations - but these work globally for all languages -->
 <rule break="no">
-<beforebreak>\b(spp?)\.[\u00A0\s]</beforebreak>
+<beforebreak>\b(spp?)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <!-- German abbreviations -->
 <rule break="no">
-<beforebreak>\b(ggü|Mag|mtl|versch|d|Übers|usw|Bzw|bzw|Ab[hkst]|abzgl|[Ee]inschl|[Vv]mtl|Ev|bezgl|Abzw|[Vv]sl|ahd|Akk|aktual|allg|alltagsspr|altdt|alttest|amerikan|Anh|Ank|Anm|Art|autom|Auftragsnr|Az|Bat|bayr|Bde?|bearb|Bed|Bem|bes|bez|Bez|Bhf|bspw|btto|bw|Dtl|Dez)\.[\u00A0\s]</beforebreak>
+<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>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(cts?|Ca|ca|chem|chin|Chr|cresc|dat|Dat|desgl|ders|dgl|Dipl|Dir?|Doz?|durchg|durchges|Dr|dt|ebd|Ed|eigtl|Eigtl|eigl|Eigl|akt|Engl|engl|Erg|al|et[cw]|Etw|ev(tl)?|Evtl|Evt|evt|exkl|Expl|Exz)\.[\u00A0\s]</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?|exkl|Expl|Exz)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\bDipl\.-[A-Z][a-z]{2,4}\.[\u00A0\s]</beforebreak>
+<beforebreak>\bDipl\.-[A-Z][a-z]{2,4}\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></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]</beforebreak>
+<beforebreak>\b[BM]\.[\u00A0\s]Sc\.[\u00A0\s]</beforebreak>
+<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>
 <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]</beforebreak>
+<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>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(lat|lfd|Lit|lt|Lz|Mask|mask|max|Mrd|mdal|me[dt]|phil|mhd|Mio?|mind?|Mo|mod|nachm|nördlBr|neutr|Nhd|Nom|Nrn?|Num|Obj|od|dgl|offz)\.[\u00A0\s]</beforebreak>
+<beforebreak>\b([A-ZÖÄÜ][a-zöäüß]+nr|tel|[Gg]em|Pat|prov|Betr|lat|lfd|Lit|lt|Lz|Mask|mask|max|Mrd|mdal|me[dt]|phil|mhd|Mio?|mio|mind?|Mo|mod|nachm|nördlBr|neutr|Nhd|Nom|Nrn?|Num|Obj|od|dgl|offz)\.[\u00A0\s]{1,2}</beforebreak>
 <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]</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|Std?|stacc|Str|stud|Subst|sva|svw|sZ)\.[\u00A0\s]{1,2}</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Tel|teilw|Temp|trans|Tsd|übertr|übl|ff|überarb|ugs|univ|unveränd|urspr|USt|UST|USt\-IdNr|sw|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]</beforebreak>
+<beforebreak>([A-ZÖÄÜ][a-zöäüß]+str)\.[\u00A0\s]{1,2}</beforebreak>
+<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>
 <afterbreak></afterbreak>
 </rule>
 <!-- Break rules -->
@@ -5031,7 +5061,7 @@
 <afterbreak>\p{Lu}[^\p{Lu}]</afterbreak>
 </rule>
 <rule break="yes">
-<beforebreak>[\u00A0\s]\p{L}[\.!?…][\u00A0\s]</beforebreak>
+<beforebreak>[\u00A0\s]\p{L}[\.!?…][\u00A0\s]{1,2}</beforebreak>
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 <!-- z.B. 2 sentences: “Liebst du mich?” “Ja!” -->
@@ -5250,6 +5280,18 @@
 <beforebreak>[\s\u00A0]</beforebreak>
 <afterbreak>[»”’"'›]</afterbreak>
 </rule>
+<rule break="no">
+<beforebreak>ambass|cuil|p|liv|assoc|bibl|ENREG|al|phot|circ|concl|deb|dest|dupl|éd|écon|incl?|ital|jur|juris|jurispr|larg|lex|législ|longit|(?-i)RR|(?-i)ÉÉm|(?-i)EExc|métr|méd|néol|obs|plur|préf|prog|publ|trib|trim|suiv|(?-i)LL|env|élem|ér|ét|hon|hypexp|conj|coop|ch|alph|anglic|app|pr|collab|paragr|sect|para|commiss|coord|dép|dir|gér|secour|sén|gén|abrév|adj|adr|anon|append|av|auj|bibl|bibliogr|bdc|boul|bull|bur|caar|cat|cell|chap|cir|compl|cf|corres|dest|dict|div|dom|dr|édif|éd|électr|élém|encycl|fig|fl|graph|hist|hyp|ill|imm|imp|impr|incl|inc|ind|in[gtvf]|jur|lat|litt|liq|loc|liv|livr|méd|mém|pl|réd|rel|sc|suiv|sup|suppl|trad|univ|mus|pharm|soc|pol|compt|urb|act|confect|exp|réal|prov|introd|inv|tial|enr|ép|équiv|esp|étym|excl|exc|ap|arr|arch|adv|al|anc|angl|ann|gest|gouv|prés|rect|représ|resp|scrut|vol|coll|réf|id|sqq?|janv|fév|avr|juill|oct|nov|déc|admin</beforebreak>
+<afterbreak>\p{Ll}.*</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>\p{Ll}.*</beforebreak>
+<afterbreak>ambass|cuil|p|liv|assoc|bibl|oct|déc|jan|fév|avr|juil|sept|nov|ENREG|al|circ|concl|deb|dest|dupl|éd|écon|incl?|ital|jur|juris|jurispr|larg|lex|législ|longit|(?-i)RR|(?-i)ÉÉm|(?-i)EExc|métr|méd|néol|obs|plur|préf|prog|publ|trib|trim|suiv|(?-i)LL|env|élem|ér|ét|hon|hypexp|conj|coop|ch|alph|anglic|app|pr|collab|paragr|sect|para|commiss|coord|dép|dir|gér|secour|sén|gén|abrév|adj|adr|anon|append|av|auj|bibl|bibliogr|bdc|boul|bull|bur|caar|cat|cell|chap|cir|compl|cf|corres|dest|dict|div|dom|dr|édif|éd|électr|élém|encycl|fig|fl|graph|hist|hyp|ill|imm|imp|impr|incl|inc|ind|in[gtvf]|jur|lat|litt|liq|loc|liv|livr|méd|mém|pl|réd|rel|sc|suiv|sup|suppl|trad|univ|mus|pharm|soc|pol|compt|urb|act|confect|exp|réal|prov|introd|inv|tial|enr|ép|équiv|esp|étym|excl|exc|ap|arr|arch|adv|al|anc|angl|ann|gest|gouv|prés|rect|représ|resp|scrut|vol|coll|réf|id|sqq?|janv|fév|avr|juill|oct|nov|déc|admin</afterbreak>
+</rule>
+<rule break="no">
+<beforebreak>.*°C</beforebreak>
+<afterbreak>de</afterbreak>
+</rule>
 <rule break="yes">
 <beforebreak>[\.!?][\s\u00A0][»”’"'›][\s\u00A0]</beforebreak>
 <afterbreak>[«“‘‹"'\p{Lu}]</afterbreak>
@@ -5258,6 +5300,11 @@
 <beforebreak>Yahoo![\s\u00A0]</beforebreak>
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
+<!-- !? + lowercase -->
+<rule break="no">
+<beforebreak>(\!|\?)[\s\u00A0]</beforebreak>
+<afterbreak>\p{Ll}</afterbreak>
+</rule>
 <rule break="yes">
 <beforebreak>\.\[\d+\][\s\u00A0]</beforebreak>
 <afterbreak></afterbreak>
@@ -5599,7 +5646,7 @@
 </rule>
 <rule break="no">
 <!-- unfortunately \b ignores \u0301 -->
-<beforebreak>\bст\.[\h\v]</beforebreak>
+<beforebreak>\b[сС]т\.[\h\v]</beforebreak>
 <afterbreak>[\h]*(?!([АВУОІЄ]|На|Але|Так?)[\h\v])</afterbreak>
 </rule>
 <rule break="no">
@@ -5631,7 +5678,7 @@
 </rule>
 <!-- abbreviation with proper noun: проф. Грицько, о. Лісове -->
 <rule break="no">
-<beforebreak>\b([Аа]кад|[Пп]роф|[Дд]оц|[Аа]сист|[Рр]еж|[Аа]рх|[Сс]вв?|о|ім|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|упоряд|чл\.-кор|[Пп]реп)\.[\h\v]*</beforebreak>
 <afterbreak>[\h\v]*[А-ЯІЇЄҐA-Z]</afterbreak>
 </rule>
 <rule break="no">
@@ -5979,7 +6026,7 @@
 </rule>
 <!-- Abbreviations that cannot finish sentences-->
 <rule break="no">
-<beforebreak>\b(a|Ab|abrev|absol|acad|Açor|A\. ?D|add|adj|adv|advers|Aeron|afér|Agric|Álg|aprox|[Aa]rts?|Artilh|auxil|av|Av)\.\s?</beforebreak>
+<beforebreak>\b(a|Ab|abr|abrev|absol|acad|Açor|A\. ?D|add|adj|adv|advers|Aeron|afér|Agric|ago|Álg|aprox|[Aa]rts?|Artilh|auxil|av|Av)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -5991,7 +6038,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(D|def|dem|deprec|deriv|det|disj|[Dd]ra?s?)\.\s?</beforebreak>
+<beforebreak>\b(D|def|dem|deprec|deriv|det|dez|disj|[Dd]ra?s?)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6003,7 +6050,7 @@
 <afterbreak>\p{Ll}</afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(f|fam|Farm|fem|fig|fin|fl|fr|frac)\.\s?</beforebreak>
+<beforebreak>\b(f|fam|Farm|fem|fev|fig|fin|fl|fr|frac)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6019,7 +6066,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(Jorn|Jur)\.\s?</beforebreak>
+<beforebreak>\b(jan|jul|jun|Jorn|Jur)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6027,15 +6074,15 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(m|masc|Mat|máx|Mecân|[Mm]ed|Mil|mín|mult|Mús)\.\s?</beforebreak>
+<beforebreak>\b(m|mai|mar|masc|Mat|máx|Mecân|[Mm]ed|Mil|mín|mult|Mús)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(n|N|Náut|N.B|neg|neol|num|núm)\.\s?</beforebreak>
+<beforebreak>\b(n|N|Náut|N.B|neg|neol|nov|num|núm)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(ord)\.\s?</beforebreak>
+<beforebreak>\b(ord|out)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6051,7 +6098,7 @@
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
-<beforebreak>\b(S|S.A|símb|S. ?M|[Ss]ra?s?|[Ss]rta|suf|superl)\.\s?</beforebreak>
+<beforebreak>\b(S|S.A|set|símb|S. ?M|[Ss]ra?s?|[Ss]rta|suf|superl)\.\s?</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -6073,7 +6120,7 @@
 <!-- s. XIX; s.IX; sec. XX; séc. XX -->
 <rule break="no">
 <beforebreak>\bs([eé]c)?\.\s?</beforebreak>
-<afterbreak>[IVXVDMCL]+</afterbreak>
+<afterbreak>[IVXDMCL]+</afterbreak>
 </rule>
 <!-- English abbreviations - but these work globally for all languages -->
 <rule break="no">

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: srx-languagetool
 version: !ruby/object:Gem::Version
-  version: 0.6.0
+  version: 0.8.0
 platform: ruby
 authors:
 - Aaron Madlon-Kay
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2022-03-30 00:00:00.000000000 Z
+date: 2022-09-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: srx