Fixing goldens after refactoring.

[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 87ea308b363b60fdb2a9f00786c92b66739aeb0d..5a4a86a65fee222c82714d3b916e2cff9d86b15e 100644 (file)
--- a/src/com/hughes/android/dictionary/engine/IndexBuilder.java
+++ b/src/com/hughes/android/dictionary/engine/IndexBuilder.java
@@ -32,13 +32,15 @@ public class IndexBuilder {
   
   final DictionaryBuilder dictionaryBuilder;
   public final Index index;
+  final Set<String> stoplist;
 
   final SortedMap<String, TokenData> tokenToData;
 
-  IndexBuilder(final DictionaryBuilder dictionaryBuilder, final String shortName, final String longName, final Language language, final String normalizerRules, final boolean swapPairEntries) {
+  IndexBuilder(final DictionaryBuilder dictionaryBuilder, final String shortName, final String longName, final Language language, final String normalizerRules, final Set<String> stoplist, final boolean swapPairEntries) {
     this.dictionaryBuilder = dictionaryBuilder;
     index = new Index(dictionaryBuilder.dictionary, shortName, longName, language, normalizerRules, swapPairEntries);
     tokenToData = new TreeMap<String, TokenData>(new NormalizeComparator(index.normalizer(), language.getCollator()));
+    this.stoplist = stoplist;
   }
   
   public void build() {
@@ -72,15 +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));
     }
   }
   
@@ -96,7 +98,7 @@ public class IndexBuilder {
     }
   }
 
-  public TokenData getOrCreateTokenData(final String token) {
+  private TokenData getOrCreateTokenData(final String token) {
     TokenData tokenData = tokenToData.get(token);
     if (tokenData == null) {
       tokenData = new TokenData(token);
@@ -105,31 +107,36 @@ public class IndexBuilder {
     return tokenData;
   }
 
-  public List<IndexedEntry> getOrCreateEntries(final String token, final EntryTypeName entryTypeName) {
+  private List<IndexedEntry> getOrCreateEntries(final String token, final EntryTypeName entryTypeName) {
     final TokenData tokenData = getOrCreateTokenData(token);
     List<IndexedEntry> entries = tokenData.typeToEntries.get(entryTypeName);
     if (entries == null) {
       entries = new ArrayList<IndexedEntry>();
       tokenData.typeToEntries.put(entryTypeName, entries);
     }
+    if (token.contains("Aosta")) {
+      System.out.println("asdfasdf");
+    }
     return entries;
   }
 
   public void addEntryWithTokens(final IndexedEntry indexedEntry, final Set<String> tokens,
       final EntryTypeName entryTypeName) {
     for (final String token : tokens) {
+      if (entryTypeName.overridesStopList || !stoplist.contains(token))
       getOrCreateEntries(token, entryTypeName).add(indexedEntry);
     }    
   }
 
   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);
   }
 }