2 types of TokenRow.

[DictionaryPC.git] / src / com / hughes / android / dictionary / engine / WiktionarySplitter.java

diff --git a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java
index 83cb043cbf456c03c66f36a26888c3759ff89dd3..628d3567e7a1ad030a5e828599e8458088501db0 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java
+++ b/src/com/hughes/android/dictionary/engine/WiktionarySplitter.java
@@ -20,8 +20,8 @@ import java.io.File;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.util.ArrayList;
-import java.util.Arrays;
 import java.util.List;
+import java.util.Map;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
@@ -32,8 +32,12 @@ import javax.xml.parsers.SAXParserFactory;
 import org.xml.sax.Attributes;
 import org.xml.sax.SAXException;
 
+import com.hughes.android.dictionary.parser.enwiktionary.EnWiktionaryLangs;
+
 public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler {
   
+  private static final String FILE_TO_SPLIT = "data/inputs/enwiktionary-pages-articles.xml";
+  
   static class Section implements java.io.Serializable {
     private static final long serialVersionUID = -7676549898325856822L;
 
@@ -56,7 +60,7 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler {
     
     public Selector(final String filename, final String pattern) throws IOException {
       this.out = new DataOutputStream(new BufferedOutputStream(new FileOutputStream(filename)));
-      this.pattern = Pattern.compile(pattern);
+      this.pattern = Pattern.compile(pattern, Pattern.CASE_INSENSITIVE);
     }
   }
 
@@ -70,7 +74,7 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler {
     final WiktionarySplitter wiktionarySplitter = new WiktionarySplitter();
     
     // Configure things.
-    final File file = new File(args[0]);
+    
     final List<Selector> selectors = wiktionarySplitter.selectors;
     for (int i = 1; i < args.length; i += 2) {
       final Selector selector = new Selector(args[i], args[i+1]);
@@ -78,33 +82,13 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler {
     }
 
     if (selectors.isEmpty()) {
-      selectors.addAll(Arrays.asList(
-          new Selector("wikiSplit/arabic.data", ".*[Ar]rabic.*"),
-          new Selector("wikiSplit/croation.data", ".*[Cc]roation.*"),
-          new Selector("wikiSplit/czech.data", ".*[Cc]zech.*"),
-          new Selector("wikiSplit/mandarin.data", ".*[Mm]andarin|[Cc]hinese.*"),
-          new Selector("wikiSplit/dutch.data", ".*[Du]utch.*"),
-          new Selector("wikiSplit/english.data", ".*[Ee]nglish.*"),
-          new Selector("wikiSplit/french.data", ".*[Ff]rench.*"),
-          new Selector("wikiSplit/german.data", ".*[Gg]erman.*"),
-          new Selector("wikiSplit/greek.data", ".*[Gg]reek.*"),
-          new Selector("wikiSplit/hindi.data", ".*[Hh]indi.*"),
-          new Selector("wikiSplit/italian.data", ".*[Ii]talian.*"),
-          new Selector("wikiSplit/japanese.data", ".*[Jj]apanese.*"),
-          new Selector("wikiSplit/korean.data", ".*[Kk]orean.*"),
-          new Selector("wikiSplit/persian.data", ".*[Pp]ersian.*"),
-          new Selector("wikiSplit/portuguese.data", ".*[Pp]ortuguese.*"),
-          new Selector("wikiSplit/romanian.data", ".*[Rr]omanian.*"),
-          new Selector("wikiSplit/russian.data", ".*[Rr]ussian.*"),
-          new Selector("wikiSplit/spanish.data", ".*[Ss]panish.*"),
-          new Selector("wikiSplit/swedish.data", ".*[Ss]wedish.*"),
-          new Selector("wikiSplit/thai.data", ".*[Tt]hai.*"),
-          new Selector("wikiSplit/vietnamese.data", ".*[Vv]ietnamese.*")
-          ));
+      for (final Map.Entry<String, String> entry : EnWiktionaryLangs.isoCodeToWikiName.entrySet()) {
+        selectors.add(new Selector(String.format("data/inputs/enWikiSplit/%s.data", entry.getKey()), entry.getValue()));
+      }
     }
     
     // Do it.
-    parser.parse(file, wiktionarySplitter);
+    parser.parse(new File(FILE_TO_SPLIT), wiktionarySplitter);
     
     // Shutdown.
     for (final Selector selector : selectors) {
@@ -114,9 +98,12 @@ public class WiktionarySplitter extends org.xml.sax.helpers.DefaultHandler {
 
   static final Pattern headingStart = Pattern.compile("^(=+)[^=]+=+", Pattern.MULTILINE);
   
+  int pageCount = 0;
   private void endPage() {
     final String title = titleBuilder.toString();
-    System.out.println("endPage: " + title);
+    if (++pageCount % 1000 == 0) {
+      System.out.println("endPage: " + title + ", count=" + pageCount);
+    }
     
     String text = textBuilder.toString();