Revision: 8838
          
http://languagetool.svn.sourceforge.net/languagetool/?rev=8838&view=rev
Author:   jaumeortola
Date:     2013-01-04 14:20:37 +0000 (Fri, 04 Jan 2013)
Log Message:
-----------
[ca] New rules for detecting typographical errors in "ela geminada" and 
"point". 

Modified Paths:
--------------
    
trunk/JLanguageTool/src/main/java/org/languagetool/tokenizers/ca/CatalanWordTokenizer.java
    trunk/JLanguageTool/src/main/resources/org/languagetool/rules/ca/grammar.xml

Modified: 
trunk/JLanguageTool/src/main/java/org/languagetool/tokenizers/ca/CatalanWordTokenizer.java
===================================================================
--- 
trunk/JLanguageTool/src/main/java/org/languagetool/tokenizers/ca/CatalanWordTokenizer.java
  2013-01-04 12:08:52 UTC (rev 8837)
+++ 
trunk/JLanguageTool/src/main/java/org/languagetool/tokenizers/ca/CatalanWordTokenizer.java
  2013-01-04 14:20:37 UTC (rev 8838)
@@ -89,8 +89,9 @@
                final StringTokenizer st = new 
StringTokenizer(text.replaceAll("([\\p{L}])['’]([\\p{L}])", "$1##CA_APOS##$2")
                                .replaceAll("([\\p{L}])-([\\p{L}])-([\\p{L}])", 
"$1##CA_HYPHEN##$2##CA_HYPHEN##$3")  //it's necessary for words like 
"vint-i-quatre" 
                                .replaceAll("([\\p{L}])-([\\p{Ll}\\d])", 
"$1##CA_HYPHEN##$2")
-                               .replaceAll("([\\d]).([\\d])", 
"$1##CA_DECIMALPOINT##$2")
-                               .replaceAll("([\\d]),([\\d])", 
"$1##CA_DECIMALCOMMA##$2"),
+                               .replaceAll("([\\d])\\.([\\d])", 
"$1##CA_DECIMALPOINT##$2")
+                               .replaceAll("([\\d]),([\\d])", 
"$1##CA_DECIMALCOMMA##$2")
+                               .replaceAll("l\\.l", "##ELA_GEMINADA##"), // 
allows correcting typographical errors in "ela geminada"  
                                "\u0020\u00A0\u115f\u1160\u1680" 
                                                + 
"\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007"
                                                + 
"\u2008\u2009\u200A\u200B\u200c\u200d\u200e\u200f"
@@ -104,7 +105,8 @@
                
                while (st.hasMoreElements()) {
                        s=st.nextToken().replaceAll("##CA_APOS##", 
"'").replaceAll("##CA_HYPHEN##", "-")
-                                       .replaceAll("##CA_DECIMALPOINT##", 
".").replaceAll("##CA_DECIMALCOMMA##", ",");
+                                       .replaceAll("##CA_DECIMALPOINT##", 
".").replaceAll("##CA_DECIMALCOMMA##", ",")
+                                       .replaceAll("##ELA_GEMINADA##", "l.l");
                        Matcher matcher=null;
                        boolean matchFound=false;
                        int j=0;

Modified: 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/ca/grammar.xml
===================================================================
--- 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/ca/grammar.xml    
    2013-01-04 12:08:52 UTC (rev 8837)
+++ 
trunk/JLanguageTool/src/main/resources/org/languagetool/rules/ca/grammar.xml    
    2013-01-04 14:20:37 UTC (rev 8838)
@@ -8564,6 +8564,32 @@
         </rule>
     </category>
     <category name="A1) Ortotipografia">
+        <rule id="ELA_GEMINADA" name="Errors en la ela geminada.">
+            <pattern case_sensitive="no">
+                <marker>
+                    <token regexp="yes">.+l\.l.+</token>
+                </marker>
+            </pattern>
+            <message>¿Volíeu dir <suggestion><match no="1" 
regexp_match="(.+l)\.(l.+)" regexp_replace="$1·$2"/></suggestion></message>
+            <example type="incorrect" correction="sol·licitud">La 
<marker>sol.licitud</marker>.</example>
+            <example type="correct">la col·laboració</example>
+        </rule>
+        <rule id="ESPAI_DESPRES_DE_PUNT" name="Comprova que hi ha espai deprés 
de punt.">
+            <pattern case_sensitive="no">
+                <marker>
+                    <token>.</token>
+                    <token spacebefore="no"><exception postag="SENT_END" 
/><exception regexp="yes">[.)"’”»]</exception></token>
+                </marker>
+            </pattern>
+            <message>Falta un espai després del punt <suggestion><match 
no="1"/> <match no="2" case_conversion="startupper"/></suggestion></message>
+            <example type="incorrect" correction=". Sempre">És 
així<marker>.sempre</marker>.</example>
+            <example type="correct">És així. Sempre.</example>
+            <example type="correct">És així.</example>
+            <example type="correct">És així...</example>
+            <example type="correct">(És així...)</example>
+            <example type="correct">És així. </example>
+            <example type="correct">És així.» </example>
+        </rule>
         <rule id="PUNT_EN_ABREVIATURES" name="Comprova que hi ha punt en 
abreviatures: pàg., núm., etc.">
             <pattern case_sensitive="no">
                 <marker>

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


------------------------------------------------------------------------------
Master HTML5, CSS3, ASP.NET, MVC, AJAX, Knockout.js, Web API and
much more. Get web development skills now with LearnDevNow -
350+ hours of step-by-step video tutorials by Microsoft MVPs and experts.
SALE $99.99 this month only -- learn more at:
http://p.sf.net/sfu/learnmore_122812
_______________________________________________
Languagetool-commits mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/languagetool-commits

Reply via email to