// Chemnitz
static final Pattern DOUBLE_COLON = Pattern.compile(" :: ");
- static final Pattern PIPE = Pattern.compile(" \\| ");
+ static final Pattern PIPE = Pattern.compile("\\|");
static final Pattern SPACES = Pattern.compile("\\s+");
static final Pattern DE_NOUN = Pattern.compile("([^ ]+) *\\{(m|f|n|pl)\\}");
public void parseFile(final File file) throws IOException {
final BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file), charset));
String line;
+ int count = 0;
while ((line = reader.readLine()) != null) {
+ if (count % 10000 == 0) {
+ logger.info("count=" + count + ", line=" + line);
+ }
parseLine(line);
+ ++count;
}
}
final Pair[] pairs = new Pair[subfields[0].length];
for (int i = 0; i < pairs.length; ++i) {
+ subfields[0][i] = subfields[0][i].trim();
+ subfields[1][i] = subfields[1][i].trim();
pairs[i] = new Pair(subfields[0][i], subfields[1][i]);
}
final PairEntry pairEntry = new PairEntry(pairs);
final EntryData entryData = new EntryData(dictBuilder.dictionary.pairEntries.size(), pairEntry);
dictBuilder.dictionary.pairEntries.add(pairEntry);
- dictBuilder.entryDatas.add(entryData); // TODO: delete me.
for (int l = 0; l < 2; ++l) {
// alreadyDone.clear();
public class DictionaryTest extends TestCase {
-
- RandomAccessFile raf;
- Dictionary dict;
- Index deIndex;
-
- @Override
- public void setUp() {
- try {
- raf = new RandomAccessFile("testdata/de_en.dict", "r");
- dict = new Dictionary(raf);
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
-
- deIndex = dict.indices.get(0);
-}
-
- @Override
- public void tearDown() {
- try {
- raf.close();
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
- }
-
-
+
public void testGermanMetadata() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.dict", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
assertEquals("de", deIndex.shortName);
assertEquals("de->en", deIndex.longName);
+
+ raf.close();
}
public void testGermanIndex() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.dict", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
for (final Index.IndexEntry indexEntry : deIndex.sortedIndexEntries) {
System.out.println("testing: " + indexEntry.token);
final Index.SearchResult searchResult = deIndex.findLongestSubstring(indexEntry.token, new AtomicBoolean(
assertSearchResult("aaac", "aaac", deIndex.findLongestSubstring("aAac", new AtomicBoolean(false)));
// Before the beginning.
+ assertSearchResult("40", "40" /* special case */, deIndex.findLongestSubstring("", new AtomicBoolean(false)));
assertSearchResult("40", "40" /* special case */, deIndex.findLongestSubstring("__", new AtomicBoolean(false)));
// After the end.
assertSearchResult("ab", "aaac", deIndex.findLongestSubstring("aaaca", new AtomicBoolean(false)));
assertSearchResult("machen", "machen", deIndex.findLongestSubstring("m", new AtomicBoolean(false)));
+ assertFalse(deIndex.findLongestSubstring("macdddd", new AtomicBoolean(false)).success);
+
assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("ueberprüfe", new AtomicBoolean(false)));
assertSearchResult("überprüfe", "überprüfe", deIndex.findLongestSubstring("ueberpruefe", new AtomicBoolean(false)));
assertSearchResult("überprüfen", "überprüfe", deIndex.findLongestSubstring("überprüfeBLEH", new AtomicBoolean(false)));
+ // Check that search in lowercase works.
+ assertSearchResult("Alibi", "Alibi", deIndex.findLongestSubstring("alib", new AtomicBoolean(false)));
+ assertTrue(deIndex.findLongestSubstring("alib", new AtomicBoolean(false)).success);
+ System.out.println(deIndex.findLongestSubstring("alib", new AtomicBoolean(false)).toString());
+
+ raf.close();
}
private void assertSearchResult(final String insertionPoint, final String longestPrefix,
assertEquals(longestPrefix, actual.longestPrefix.token);
}
- public void testGermanTokenRows() {
+ public void testGermanTokenRows() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.dict", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
// Pre-cache a few of these, just to make sure that's working.
for (int i = 0; i < deIndex.rows.size(); i += 7) {
deIndex.rows.get(i).getTokenRow(true);
// This will break if the Row cache isn't big enough.
assertEquals(lastTokenRow, row.getTokenRow(false));
}
+
+ raf.close();
}
public void testGermanSort() {
"Großformats",
"Großpoo",
"Großpoos",
+ "Hörweite",
+ "hos",
+ "Höschen",
+ "Hostel",
"hulle",
"Hulle",
"hülle",
assertEquals("es", Language.lookup("es").getSymbol());
}
+ public void testTextNorm() {
+ assertEquals("hoschen", "Höschen".toLowerCase(Language.de.locale));
+ }
+
+ public void testChemnitz() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile("testdata/de-en_chemnitz.dict", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
+ //assertSearchResult("Höschen", "Hos", deIndex.findLongestSubstring("Hos", new AtomicBoolean(false)));
+ //assertSearchResult("Höschen", "hos", deIndex.findLongestSubstring("hos", new AtomicBoolean(false)));
+
+
+ raf.close();
+ }
}
package com.hughes.android.dictionary.engine;
import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
import java.util.EnumMap;
import java.util.HashSet;
import java.util.List;
import java.util.SortedMap;
import java.util.TreeMap;
+import com.hughes.android.dictionary.engine.Index.IndexEntry;
+
public class IndexBuilder {
final List<RowBase> rows = index.rows;
for (final TokenData tokenData : tokenToData.values()) {
tokenEntryDatas.clear();
- final int indexRow = index.sortedIndexEntries.size();
- index.sortedIndexEntries.add(new Index.IndexEntry(tokenData.token, rows.size()));
- rows.add(new TokenRow(indexRow, rows.size(), index));
- System.out.println("Added TokenRow: " + rows.get(rows.size() - 1));
- int count = 0;
- System.out.println("TOKEN: " + tokenData.token);
+ final int indexIndex = index.sortedIndexEntries.size();
+ final int startRow = rows.size();
+ rows.add(new TokenRow(indexIndex, rows.size(), index));
+// System.out.println("Added TokenRow: " + rows.get(rows.size() - 1));
+ int numRows = 0;
+// System.out.println("TOKEN: " + tokenData.token);
for (final Map.Entry<EntryTypeName, List<EntryData>> typeToEntry : tokenData.typeToEntries.entrySet()) {
for (final EntryData entryData : typeToEntry.getValue()) {
if (tokenEntryDatas.add(entryData)) {
rows.add(new PairEntry.Row(entryData.index(), rows.size(), index));
- ++count;
+ ++numRows;
- System.out.print(" " + typeToEntry.getKey() + ": ");
- rows.get(rows.size() - 1).print(System.out);
- System.out.println();
+// System.out.print(" " + typeToEntry.getKey() + ": ");
+ // rows.get(rows.size() - 1).print(System.out);
+// System.out.println();
}
}
}
+ index.sortedIndexEntries.add(new Index.IndexEntry(tokenData.token, startRow, numRows));
+ }
+
+ final List<IndexEntry> sortedEntries = new ArrayList<IndexEntry>(index.sortedIndexEntries);
+ Collections.sort(sortedEntries, 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));
}
}