import java.io.IOException;
import java.io.RandomAccessFile;
+import java.util.Arrays;
+import java.util.List;
+import java.util.Random;
import java.util.concurrent.atomic.AtomicBoolean;
import junit.framework.TestCase;
import com.hughes.android.dictionary.engine.Index.IndexEntry;
-import com.hughes.android.dictionary.engine.PairEntry.Row;
+import com.hughes.util.CollectionUtil;
public class DictionaryTest extends TestCase {
static final String TEST_OUTPUTS = com.hughes.android.dictionary.engine.DictionaryBuilderTest.TEST_OUTPUTS;
- static final String OUTPUTS = com.hughes.android.dictionary.engine.DictionaryBuilderTest.OUTPUTS;
+ public static final String OUTPUTS = "data/outputs/";
@Override
protected void setUp() {
final Index enIndex = dict.indices.get(0);
final RowBase row = enIndex.rows.get(4);
- assertEquals("carbonyl chloride (the compound COCl<sub>2</sub>) (noun)\tossicloruro di carbonio", row.getRawText(false));
+ assertEquals("The numeral 00\tzeranta (noun) {m|f|inv}", row.getRawText(false));
raf.close();
}
final Dictionary dict = new Dictionary(raf);
final Index deIndex = dict.indices.get(0);
- assertEquals("de", deIndex.shortName);
- assertEquals("de->en", deIndex.longName);
+ assertEquals("DE", deIndex.shortName);
+ assertEquals("DE->EN", deIndex.longName);
assertEquals(2, dict.sources.size());
assertEquals("chemnitz", dict.sources.get(0).name);
- assertEquals(0, dict.sources.get(0).pairEntryStart);
assertEquals("dictcc", dict.sources.get(1).name);
- assertEquals(0, dict.sources.get(1).pairEntryStart); // TODO: rethink this
+
+ assertEquals("dictcc", dict.pairEntries.get(0).entrySource.name);
+ assertEquals("chemnitz", dict.pairEntries.get(1).entrySource.name);
raf.close();
}
}
public void testChemnitz() throws IOException {
- final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "/de-en_chemnitz.quickdic", "r");
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
final Dictionary dict = new Dictionary(raf);
final Index deIndex = dict.indices.get(0);
raf.close();
}
+ public void testMultiSearch() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(TEST_OUTPUTS + "de-en.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index deIndex = dict.indices.get(0);
+
+ {
+ final List<RowBase> rows = deIndex.multiWordSearch(Arrays.asList("aaa", "aaab"), new AtomicBoolean(false));
+ System.out.println(CollectionUtil.join(rows, "\n "));
+ assertTrue(rows.toString(), rows.size() > 0);
+ }
+
+ raf.close();
+ }
+
+ public void testMultiSearchBig() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "DE-EN_chemnitz_enwiktionary.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));
+ 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());
+ }
+
+ {
+ final List<RowBase> rows = enIndex.multiWordSearch(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));
+ 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());
+ }
+
+ {
+ // Should print: Giving up, too many words with prefix: p
+ final List<RowBase> rows = enIndex.multiWordSearch(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));
+ 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));
+ 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));
+ 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));
+ assertTrue(rows.size() >= 1000);
+ }
+
+ raf.close();
+ }
+
+ public void testMultiSearchBigAF() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-AF_enwiktionary.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));
+ 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));
+ 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));
+ 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));
+ 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"));
+ }
+
+
+ raf.close();
+ }
+
+
+ public void testExactSearch() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-ZH_enwiktionary.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index zhIndex = 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);
+ assertNotNull(found);
+ assertEquals(indexEntry.token, found.token);
+ assertEquals(indexEntry, found); // Test of caching....
+ }
+
+ raf.close();
+ }
+
+ public void testThai() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-TH_enwiktionary.quickdic", "r");
+ final Dictionary dict = new Dictionary(raf);
+ final Index thIndex = dict.indices.get(1);
+
+ final IndexEntry entry = thIndex.findInsertionPoint("ดี", new AtomicBoolean(false));
+ assertEquals("di", entry.token);
+
+ raf.close();
+ }
+
+ public void testNorwegiani() throws IOException {
+ final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-NL_enwiktionary.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();
+ }
}