X-Git-Url: http://gitweb.fperrin.net/?a=blobdiff_plain;f=src%2Fcom%2Fhughes%2Fandroid%2Fdictionary%2Fengine%2FDictionaryTest.java;h=e766eca1e1248c748be61c7b75564d35ce8b6e71;hb=58fd4402729f38bf4408e8fef487a9bc359e45a0;hp=696b8bed29801d4fc06ac1130666f96ecef369ff;hpb=a8052a74747df9244c098041dc82c745f64d51c6;p=DictionaryPC.git diff --git a/src/com/hughes/android/dictionary/engine/DictionaryTest.java b/src/com/hughes/android/dictionary/engine/DictionaryTest.java index 696b8be..e766eca 100644 --- a/src/com/hughes/android/dictionary/engine/DictionaryTest.java +++ b/src/com/hughes/android/dictionary/engine/DictionaryTest.java @@ -16,15 +16,21 @@ package com.hughes.android.dictionary.engine; 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; + public static final String OUTPUTS = "data/outputs/"; @Override protected void setUp() { @@ -36,37 +42,88 @@ public class DictionaryTest extends TestCase { } } } + + public void testURLFormatting() { + } public void testEnItWiktionary() throws IOException { - final RandomAccessFile raf = new RandomAccessFile("dictOutputs/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 PairEntry.Row row = (Row) enIndex.rows.get(2); - assertEquals("z", row.getRawText(false)); + final RowBase row = enIndex.rows.get(4); + assertEquals("-ical", row.getRawText(false)); + + final Index itIndex = dict.indices.get(1); + { + final List 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("testdata/de-en.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); - 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(113, dict.sources.get(1).pairEntryStart); + + assertEquals("dictcc", dict.pairEntries.get(0).entrySource.name); + assertEquals("chemnitz", dict.pairEntries.get(1).entrySource.name); raf.close(); } public void testGermanIndex() throws IOException { - final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.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); @@ -116,7 +173,7 @@ public class DictionaryTest extends TestCase { } public void testGermanTokenRows() throws IOException { - final RandomAccessFile raf = new RandomAccessFile("testdata/de-en.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); @@ -147,15 +204,171 @@ public class DictionaryTest extends TestCase { } public void testChemnitz() throws IOException { - final RandomAccessFile raf = new RandomAccessFile("dictOutputs/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); assertSearchResult("Höschen", "Hos", deIndex.findInsertionPoint("Hos", new AtomicBoolean(false))); assertSearchResult("Höschen", "hos", deIndex.findInsertionPoint("hos", new AtomicBoolean(false))); + + 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 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); + } + raf.close(); } + public void testMultiSearchBig() throws IOException { + 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 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); + assertTrue(rows.get(0).toString().startsWith("train station@")); + } + + { + final List 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 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("Abfahrthalle {en-noun}\tDeparture room of a station.", rows.get(0).toString()); + } + + { + // Should print: Giving up, too many words with prefix: p + final List 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 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 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 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 rows = enIndex.multiWordSearch("b ba", 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.quickdic", "r"); + final Dictionary dict = new Dictionary(raf); + final Index enIndex = dict.indices.get(0); + + { + final List 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 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 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 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")); + } + + + raf.close(); + } + + + public void testExactSearch() throws IOException { + final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-cmn.quickdic", "r"); + final Dictionary dict = new Dictionary(raf); + 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(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.... + } + + raf.close(); + } + + public void testThai() throws IOException { + final RandomAccessFile raf = new RandomAccessFile(OUTPUTS + "EN-TH.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 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(); + } }