Revision: 8572
          
http://languagetool.svn.sourceforge.net/languagetool/?rev=8572&view=rev
Author:   milek_pl
Date:     2012-12-17 17:28:00 +0000 (Mon, 17 Dec 2012)
Log Message:
-----------
[pl] fix errors in sentence segmentation to make two rules active again

Modified Paths:
--------------
    trunk/JLanguageTool/src/main/resources/org/languagetool/resource/segment.srx
    trunk/JLanguageTool/src/main/resources/org/languagetool/rules/pl/grammar.xml

Modified: 
trunk/JLanguageTool/src/main/resources/org/languagetool/resource/segment.srx
===================================================================
--- 
trunk/JLanguageTool/src/main/resources/org/languagetool/resource/segment.srx    
    2012-12-17 17:25:24 UTC (rev 8571)
+++ 
trunk/JLanguageTool/src/main/resources/org/languagetool/resource/segment.srx    
    2012-12-17 17:28:00 UTC (rev 8572)
@@ -4,10 +4,11 @@
 <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="no"></okpsrx:options>
+<okpsrx:options oneSegmentIncludesAll="no" trimLeadingWhitespaces="no" 
trimTrailingWhitespaces="no" useJavaRegex="yes"></okpsrx:options>
 <okpsrx:sample language="pl_two" useMappedRules="no">Ingevolge paragraaf 
4.7.4. van het SGR is ...
 Jestem zły, bo... (wpisz własną odpowiedź) drażni mnie krowa.
 Kierownictwo toleruje pracę z konieczności ("Skąd wezmę innego pracownika?") i 
jest zadowolone. Józek D. (45 l.) T.Love
+Ad. 1, 5 ha. ziemi na Mazurach
 Planowany wzrost przychodów najludniejszych gmin w br. będzie o 2 pkt. proc. 
wyższy od prognozowanej na br. stopy średniorocznej inflacji (15 proc.) 
natomiast wzrost wydatków przewyższa o 12 pkt. proc. stopę inflacji (co za 
dziwota! - przyp. red.) i tak dalej.
 Nie jesteś Rosjaninem? - spytał przedstawiciel okręgu. 11.X.2001 (b. dobra 
gra).
 Temperatura wody w systemie wynosi 30°C.W skład obiegu..
@@ -25,7 +26,6 @@
 </header>
 <body>
 <languagerules>
-
 <languagerule languagerulename="Greek">
 <!--κ.λπ. - και λοιπά-->
 <rule break="no">
@@ -55,10 +55,10 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Polish">
+<!--includes v"ad." misused as abbreviation-->
 <rule break="no">
-<beforebreak>\badw\.\s</beforebreak>
+<beforebreak>\b[Aa]dw?\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 <rule break="no">
@@ -925,6 +925,11 @@
 <beforebreak>\b[Nn]a\sos\.\s</beforebreak>
 <afterbreak></afterbreak>
 </rule>
+<!--20 ha. ziemi na Mazurach-->
+<rule break="no">
+<beforebreak>\bha\.\s</beforebreak>
+<afterbreak>[\p{Ll}]</afterbreak>
+</rule>
 <!--min. 30 zł lub cena min. od 30 zł-->
 <rule break="no">
 <beforebreak>\bmin\.\s</beforebreak>
@@ -1041,7 +1046,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="English">
 <rule break="no">
 <beforebreak>\b[nN]o\.\s</beforebreak>
@@ -1217,7 +1221,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Romanian">
 <rule break="no">
 <beforebreak>\b\d+\.\s</beforebreak>
@@ -1312,7 +1315,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Dutch">
 <rule break="no">
 <beforebreak>\b(Afr|Am|Ar|Br|Cie|Comp|Dhr|Dr|Em|Fa|Kon)\.\s</beforebreak>
@@ -1464,7 +1466,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Slovak">
 <rule break="no">
 
<beforebreak>\b(Bc|Mgr|RNDr|PharmDr|PhDr|JUDr|PaedDr|ThDr|Ing|MUDr|MDDr|MVDr|Dr|ThLic|PhD|ArtD|ThDr|Dr|DrSc|CSs|prof)\.\s</beforebreak>
@@ -3139,7 +3140,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Icelandic">
 <!-- Numbers -->
 <rule break="no">
@@ -3965,7 +3965,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Russian">
 <rule break="no">
 <beforebreak>\b\d+\.\s</beforebreak>
@@ -4065,7 +4064,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Default">
 <rule break="yes">
 <beforebreak>\u2029</beforebreak>
@@ -4082,21 +4080,18 @@
 <afterbreak></afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="ByLineBreak">
 <rule break="yes">
 <beforebreak>\r?\n</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="ByTwoLineBreaks">
 <rule break="yes">
 <beforebreak>\r?\n\s*\r?\n[\t]*</beforebreak>
 <afterbreak></afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Slovenian">
 <rule break="no">
 <beforebreak>\b[dD]r\.\s</beforebreak>
@@ -4251,7 +4246,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Catalan">
 <!-- Abbreviations that cannot finish sentences-->
 <rule break="no">
@@ -4320,7 +4314,6 @@
 <afterbreak>[¡¿«»"'\p{Ps}]*\p{Lu}\p{L}*</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Spanish">
 <!-- Abbreviations that cannot finish sentences-->
 <rule break="no">
@@ -4389,7 +4382,6 @@
 <afterbreak>[¡¿«»"'\p{Ps}]*\p{Lu}\p{L}*</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="German">
 <!-- Split e.g.: He won't. Really. -->
 <rule break="yes">
@@ -4538,7 +4530,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Danish">
 <!-- Split e.g.: He won't. Really. -->
 <rule break="yes">
@@ -4692,7 +4683,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Esperanto">
 <!-- Esperanto abbreviations (see 
http://eo.lernu.net/lernado/gramatiko/demandoj/mallongigoj.php) -->
 <rule break="no">
@@ -4721,7 +4711,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Ukrainian">
 <rule break="no">
 <beforebreak>\b\d+\.\s</beforebreak>
@@ -4861,7 +4850,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Belarusian">
 <rule break="no">
 <beforebreak>\b\d+\.\s</beforebreak>
@@ -4949,7 +4937,6 @@
 <afterbreak>\p{Lu}\p{Ll}</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Galician">
 <!-- s. XIX; s.IX; sec. XX; séc. XX -->
 <rule break="no">
@@ -5065,7 +5052,6 @@
 <afterbreak>['"«¡¿\p{Ps}\p{Pi}]?\p{Lu}\p{Ll}*</afterbreak>
 </rule>
 </languagerule>
-
 <languagerule languagerulename="Japanese">
 <rule break="no">
 
<beforebreak>[:]+[\p{Pe}\p{Pf}\p{Po}"-[\u002C\u003A\u003B\u055D\u060C\u061B\u0703\u0704\u0705\u0706\u0707\u0708\u0709\u07F8\u1363\u1364\u1365\u1366\u1802\u1804\u1808\u204F\u205D\u3001\uA60D\uFE10\uFE11\uFE13\uFE14\uFE50\uFE51\uFE54\uFE55\uFF0C\uFF1A\uFF1B\uFF64]]*</beforebreak>

Modified: 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/pl/grammar.xml
===================================================================
--- 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/pl/grammar.xml    
    2012-12-17 17:25:24 UTC (rev 8571)
+++ 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/pl/grammar.xml    
    2012-12-17 17:28:00 UTC (rev 8572)
@@ -8810,8 +8810,7 @@
             <short>Błąd ortograficzny</short>
             <example type="correct">Ruda Śląska, Katow., Chorzów</example>
             <example correction="Katow." type="incorrect">Ruda Śląska, 
<marker>Ka-ce</marker>, Chorzów</example>
-        </rule>
-        <!-- commented out because of the warning in PatternRuleTest if 
CHECK_WITH_SENTENCE_SPLITTING = true
+        </rule>        
         <rule id="AD_KROPKA" name="„ad.” (ad)">
             <pattern>
                 <marker>
@@ -8825,7 +8824,7 @@
             <example type="correct">Ad 1.</example>
             <example correction="Ad" type="incorrect"><marker>Ad.</marker> 
1.</example>
         </rule>
-        -->
+        
         <rulegroup id="LICZBY_SLOWNIE_SKROT" name="Skrótowy zapis liczb: 
10-tka (dziesiątka) itd.">
             <rule>
                 <pattern>
@@ -9808,8 +9807,7 @@
                 <example type="correct">On mieszka pod nr. 2.</example>
                 <example type="correct">Oto samochód nr 2.</example>
                 <example correction="nr 2" type="incorrect">Oto samochód 
<marker>nr. 2</marker>.</example>
-            </rule>
-            <!-- commented out because of the warning in PatternRuleTest if 
CHECK_WITH_SENTENCE_SPLITTING = true
+            </rule>            
             <rule>
                 <pattern>
                     <token regexp="yes">\d+</token>
@@ -9824,8 +9822,7 @@
                 <example type="correct">Ha, ha, ha!</example>
                 <example correction="gr" type="incorrect">Ten palmtop waży 100 
<marker>gr.</marker>, jest więc bardzo lekki.</example>
                 <example type="correct">Apollo (gr. Apollon, zwany też Phoibos 
&quot;Jaśniejący&quot;)</example>
-            </rule>
-           -->
+            </rule>           
             <rule>
                 <pattern>
                     <token 
regexp="yes">dl|ml|dag|cm|dm|zł|kg|mln|mld|min|npl|pkt|pg|tg|cos|cosec|sec|sin|rkm|wg</token>

This was sent by the SourceForge.net collaborative development platform, the 
world's largest Open Source development site.


------------------------------------------------------------------------------
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
Remotely access PCs and mobile devices and provide instant support
Improve your efficiency, and focus on delivering more value-add services
Discover what IT Professionals Know. Rescue delivers
http://p.sf.net/sfu/logmein_12329d2d
_______________________________________________
Languagetool-commits mailing list
Languagetool-commits@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/languagetool-commits

Reply via email to