Major refactor in the way wikiText is parsed.

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

diff --git a/src/com/hughes/android/dictionary/engine/IndexBuilder.java b/src/com/hughes/android/dictionary/engine/IndexBuilder.java
index 98c24e5bdc52ec50e86a0befa5f7e1366657a7e4..81de5a2901e6d534a4ea63617dda451973613d24 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/IndexBuilder.java
+++ b/src/com/hughes/android/dictionary/engine/IndexBuilder.java
@@ -74,15 +74,15 @@ public class IndexBuilder {
           .normalizer().transliterate(tokenData.token), startRow, numRows));
     }
     
-    final List<IndexEntry> sortedEntries = new ArrayList<IndexEntry>(index.sortedIndexEntries);
-    Collections.sort(sortedEntries, new Comparator<IndexEntry>() {
+    final List<IndexEntry> entriesSortedByRows = new ArrayList<IndexEntry>(index.sortedIndexEntries);
+    Collections.sort(entriesSortedByRows, new Comparator<IndexEntry>() {
       @Override
       public int compare(IndexEntry object1, IndexEntry object2) {
         return object2.numRows - object1.numRows;
       }});
     System.out.println("Most common tokens:");
-    for (int i = 0; i < 50 && i < sortedEntries.size(); ++i) {
-      System.out.println("  " + sortedEntries.get(i));
+    for (int i = 0; i < 50 && i < entriesSortedByRows.size(); ++i) {
+      System.out.println("  " + entriesSortedByRows.get(i));
     }
   }
   
@@ -126,13 +126,14 @@ public class IndexBuilder {
   }
 
   public void addEntryWithString(final IndexedEntry indexedEntry, final String untokenizedString,
-      final EntryTypeName singleTokenEntryTypeName, final EntryTypeName multiTokenEntryTypeName) {
+      final EntryTypeName entryTypeName) {
     final Set<String> tokens = DictFileParser.tokenize(untokenizedString, DictFileParser.NON_CHAR);
-    addEntryWithTokens(indexedEntry, tokens, tokens.size() == 1 ? singleTokenEntryTypeName : multiTokenEntryTypeName);
+    addEntryWithTokens(indexedEntry, tokens, tokens.size() == 1 ? entryTypeName.singleWordInstance : entryTypeName);
   }
 
-  public void addEntryWithString(final IndexedEntry indexedEntry, final String untokenizedString,
+  public void addEntryWithStringNoSingle(final IndexedEntry indexedEntry, final String untokenizedString,
       final EntryTypeName entryTypeName) {
-    addEntryWithString(indexedEntry, untokenizedString, entryTypeName, entryTypeName);
+    final Set<String> tokens = DictFileParser.tokenize(untokenizedString, DictFileParser.NON_CHAR);
+    addEntryWithTokens(indexedEntry, tokens, entryTypeName);
   }
 }