}
}
}
+
+ public void testURLFormatting() {
+ }
public void testEnItWiktionary() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-IT_enwiktionary.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-IT.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index enIndex = dict.indices.get(0);
final RowBase row = enIndex.rows.get(4);
- assertEquals("The numeral 00\tzeranta (noun) {m|f|inv}", row.getRawText(false));
+ assertEquals("-ical", row.getRawText(false));
+
+ final Index itIndex = dict.indices.get(1);
+ {
+ final List<RowBase> rows = itIndex.multiWordSearch("come mai", Arrays.asList("come", "mai"), new AtomicBoolean(false));
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() > 0);
+ assertTrue(rows.get(0).toString().startsWith("come mai@"));
+ assertTrue(rows.get(0) instanceof TokenRow);
+ assertTrue(!((TokenRow)rows.get(0)).getIndexEntry().htmlEntries.isEmpty());
+ }
+
+ {
+ final IndexEntry searchResult = itIndex.findInsertionPoint("azzurro", new AtomicBoolean(
+ false));
+ HtmlEntry htmlEntry = searchResult.htmlEntries.get(0);
+ System.out.println("azzurro:\n" + htmlEntry.getHtml());
+ }
raf.close();
}
+ public void testFr() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "FR.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index frIndex = dict.indices.get(0);
+
+ // Now they're all cached, we shouldn't have to search.
+ for (final IndexEntry indexEntry : frIndex.sortedIndexEntries) {
+ System.out.println(indexEntry.token);
+ }
+
+ raf.close();
+ }
+
+
+ public void testDeEnWiktionary() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "DE-EN.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+
+ final Index deIndex = dict.indices.get(0);
+
+ {
+ final IndexEntry searchResult = deIndex.findInsertionPoint("rot", new AtomicBoolean(
+ false));
+ HtmlEntry htmlEntry = searchResult.htmlEntries.get(0);
+ System.out.println("rot:\n" + htmlEntry.getHtml());
+ }
+
+ raf.close();
+ }
+
public void testGermanMetadata() throws IOException {
final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false)));
assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false)));
-
+
raf.close();
}
final Index deIndex = dict.indices.get(0);
{
- final List<RowBase> rows = deIndex.multiWordSearch(Arrays.asList("aaa", "aaab"), new AtomicBoolean(false));
+ final List<RowBase> rows = deIndex.multiWordSearch("aaa aaab", Arrays.asList("aaa", "aaab"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
}
}
public void testMultiSearchBig() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "DE-EN_chemnitz_enwiktionary.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "DE-EN.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index enIndex = dict.indices.get(1);
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("train", "station"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("train station", Arrays.asList("train", "station"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
- assertEquals("Bahnhof {{de-noun|g=m|genitive=Bahnhofs|genitive2=Bahnhofes|plural=Bahnhöfe}}\ttrain station", rows.get(0).toString());
+ assertTrue(rows.get(0).toString().startsWith("train station@"));
}
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("a", "train", "station"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("a train station", Arrays.asList("a", "train", "station"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertEquals("Bahnhofsuhr {{de-noun|g=f|plural=Bahnhofsuhren}}\tstation clock (at a train station)", rows.get(0).toString());
}
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("a", "station"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("a station", Arrays.asList("a", "station"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
- assertEquals("Kraftwerk {n}\tpower plant (a station built for the production of electric power) (noun)", rows.get(0).toString());
+ assertEquals("Abfahrthalle {en-noun}\tDeparture room of a station.", rows.get(0).toString());
}
{
// Should print: Giving up, too many words with prefix: p
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("p", "eat"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("p eat", Arrays.asList("p", "eat"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertTrue(rows.toString().contains("verschlingen; verputzen\tto dispatch (eat)"));
{
// Should print: Giving up, too many words with prefix: p
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("p", "p"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("p p", Arrays.asList("p", "p"), new AtomicBoolean(false));
assertTrue(rows.size() >= 1000);
}
{
// Should print: Giving up, too many words with prefix: a
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("a", "a"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("a a", Arrays.asList("a", "a"), new AtomicBoolean(false));
assertTrue(rows.size() >= 1000);
}
{
// Should print: Giving up, too many words with prefix: a
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("b", "ba"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("b ba", Arrays.asList("b", "ba"), new AtomicBoolean(false));
assertTrue(rows.size() >= 1000);
}
{
// Should print: Giving up, too many words with prefix: a
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("b", "ba"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("b ba", Arrays.asList("b", "ba"), new AtomicBoolean(false));
assertTrue(rows.size() >= 1000);
}
}
public void testMultiSearchBigAF() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-AF_enwiktionary.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-AF.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index enIndex = dict.indices.get(0);
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("pig", "eats"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("pig eats", Arrays.asList("pig", "eats"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertEquals("pig (someone who overeats or eats rapidly) (noun)\tvark", rows.get(0).toString());
}
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("pig", "eat"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("pig eat", Arrays.asList("pig", "eat"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertEquals("pig (someone who overeats or eats rapidly) (noun)\tvark", rows.get(0).toString());
}
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("pi", "ea"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("pi ea", Arrays.asList("pi", "ea"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertTrue(rows.toString().contains("pig (someone who overeats or eats rapidly) (noun)\tvark"));
}
{
- final List<RowBase> rows = enIndex.multiWordSearch(Arrays.asList("p", "eat"), new AtomicBoolean(false));
+ final List<RowBase> rows = enIndex.multiWordSearch("p eat", Arrays.asList("p", "eat"), new AtomicBoolean(false));
System.out.println(CollectionUtil.join(rows, "\n "));
assertTrue(rows.toString(), rows.size() > 0);
assertTrue(rows.toString().contains("pig (someone who overeats or eats rapidly) (noun)\tvark"));
public void testExactSearch() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-ZH_enwiktionary.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-cmn.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
- final Index zhIndex = dict.indices.get(1);
+ final Index cmnIndex = dict.indices.get(1);
final Random random = new Random(10);
for (int i = 0; i < 1000; ++i) {
- final int ii = random.nextInt(zhIndex.sortedIndexEntries.size());
- final IndexEntry indexEntry = zhIndex.sortedIndexEntries.get(ii);
- final IndexEntry found = zhIndex.findExact(indexEntry.token);
+ final int ii = random.nextInt(cmnIndex.sortedIndexEntries.size());
+ final IndexEntry indexEntry = cmnIndex.sortedIndexEntries.get(ii);
+ final IndexEntry found = cmnIndex.findExact(indexEntry.token);
assertNotNull(found);
assertEquals(indexEntry.token, found.token);
assertEquals(indexEntry, found); // Test of caching....
}
public void testThai() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-TH_enwiktionary.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-TH.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index thIndex = dict.indices.get(1);
raf.close();
}
+ public void testNorwegian() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-NL.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index nlIndex = dict.indices.get(1);
+
+ IndexEntry entry = nlIndex.findInsertionPoint("Xhosa", new AtomicBoolean(false));
+ assertEquals("Xhosa", entry.token);
+
+ entry = nlIndex.findInsertionPoint("Zyne", new AtomicBoolean(false));
+ assertEquals("Zyne", entry.token);
+
+ raf.close();
+ }
}