1 package org.apache.lucene.analysis;
3 import org.apache.lucene.analysis.standard.StandardAnalyzer;
4 import org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer;
5 import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
6 import org.apache.lucene.util.Version;
8 import java.io.BufferedReader;
9 import java.io.IOException;
10 import java.io.InputStreamReader;
11 import java.io.Reader;
12 import java.io.StringReader;
13 import java.util.ArrayList;
14 import java.util.Arrays;
15 import java.util.List;
18 * Licensed to the Apache Software Foundation (ASF) under one or more
19 * contributor license agreements. See the NOTICE file distributed with
20 * this work for additional information regarding copyright ownership.
21 * The ASF licenses this file to You under the Apache License, Version 2.0
22 * (the "License"); you may not use this file except in compliance with
23 * the License. You may obtain a copy of the License at
25 * http://www.apache.org/licenses/LICENSE-2.0
27 * Unless required by applicable law or agreed to in writing, software
28 * distributed under the License is distributed on an "AS IS" BASIS,
29 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
30 * See the License for the specific language governing permissions and
31 * limitations under the License.
34 public class TestUAX29URLEmailTokenizer extends BaseTokenStreamTestCase {
36 public void testHugeDoc() throws IOException {
37 StringBuilder sb = new StringBuilder();
38 char whitespace[] = new char[4094];
39 Arrays.fill(whitespace, ' ');
40 sb.append(whitespace);
41 sb.append("testing 1234");
42 String input = sb.toString();
43 UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(TEST_VERSION_CURRENT, new StringReader(input));
44 BaseTokenStreamTestCase.assertTokenStreamContents(tokenizer, new String[] { "testing", "1234" });
47 private Analyzer a = new ReusableAnalyzerBase() {
49 protected TokenStreamComponents createComponents
50 (String fieldName, Reader reader) {
52 Tokenizer tokenizer = new UAX29URLEmailTokenizer(TEST_VERSION_CURRENT, reader);
53 return new TokenStreamComponents(tokenizer);
58 /** Passes through tokens with type "<URL>" and blocks all other types. */
59 private class URLFilter extends TokenFilter {
60 private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
61 public URLFilter(TokenStream in) {
65 public final boolean incrementToken() throws java.io.IOException {
66 boolean isTokenAvailable = false;
67 while (input.incrementToken()) {
68 if (typeAtt.type() == UAX29URLEmailTokenizer.TOKEN_TYPES[UAX29URLEmailTokenizer.URL]) {
69 isTokenAvailable = true;
73 return isTokenAvailable;
77 /** Passes through tokens with type "<EMAIL>" and blocks all other types. */
78 private class EmailFilter extends TokenFilter {
79 private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
80 public EmailFilter(TokenStream in) {
84 public final boolean incrementToken() throws java.io.IOException {
85 boolean isTokenAvailable = false;
86 while (input.incrementToken()) {
87 if (typeAtt.type() == UAX29URLEmailTokenizer.TOKEN_TYPES[UAX29URLEmailTokenizer.EMAIL]) {
88 isTokenAvailable = true;
92 return isTokenAvailable;
96 private Analyzer urlAnalyzer = new ReusableAnalyzerBase() {
98 protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
99 UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(TEST_VERSION_CURRENT, reader);
100 tokenizer.setMaxTokenLength(Integer.MAX_VALUE); // Tokenize arbitrary length URLs
101 TokenFilter filter = new URLFilter(tokenizer);
102 return new TokenStreamComponents(tokenizer, filter);
106 private Analyzer emailAnalyzer = new ReusableAnalyzerBase() {
108 protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
109 UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(TEST_VERSION_CURRENT, reader);
110 TokenFilter filter = new EmailFilter(tokenizer);
111 return new TokenStreamComponents(tokenizer, filter);
116 public void testArmenian() throws Exception {
117 BaseTokenStreamTestCase.assertAnalyzesTo(a, "Վիքիպեդիայի 13 միլիոն հոդվածները (4,600` հայերեն վիքիպեդիայում) գրվել են կամավորների կողմից ու համարյա բոլոր հոդվածները կարող է խմբագրել ցանկաց մարդ ով կարող է բացել Վիքիպեդիայի կայքը։",
118 new String[] { "Վիքիպեդիայի", "13", "միլիոն", "հոդվածները", "4,600", "հայերեն", "վիքիպեդիայում", "գրվել", "են", "կամավորների", "կողմից",
119 "ու", "համարյա", "բոլոր", "հոդվածները", "կարող", "է", "խմբագրել", "ցանկաց", "մարդ", "ով", "կարող", "է", "բացել", "Վիքիպեդիայի", "կայքը" } );
122 public void testAmharic() throws Exception {
123 BaseTokenStreamTestCase.assertAnalyzesTo(a, "ዊኪፔድያ የባለ ብዙ ቋንቋ የተሟላ ትክክለኛና ነጻ መዝገበ ዕውቀት (ኢንሳይክሎፒዲያ) ነው። ማንኛውም",
124 new String[] { "ዊኪፔድያ", "የባለ", "ብዙ", "ቋንቋ", "የተሟላ", "ትክክለኛና", "ነጻ", "መዝገበ", "ዕውቀት", "ኢንሳይክሎፒዲያ", "ነው", "ማንኛውም" } );
127 public void testArabic() throws Exception {
128 BaseTokenStreamTestCase.assertAnalyzesTo(a, "الفيلم الوثائقي الأول عن ويكيبيديا يسمى \"الحقيقة بالأرقام: قصة ويكيبيديا\" (بالإنجليزية: Truth in Numbers: The Wikipedia Story)، سيتم إطلاقه في 2008.",
129 new String[] { "الفيلم", "الوثائقي", "الأول", "عن", "ويكيبيديا", "يسمى", "الحقيقة", "بالأرقام", "قصة", "ويكيبيديا",
130 "بالإنجليزية", "Truth", "in", "Numbers", "The", "Wikipedia", "Story", "سيتم", "إطلاقه", "في", "2008" } );
133 public void testAramaic() throws Exception {
134 BaseTokenStreamTestCase.assertAnalyzesTo(a, "ܘܝܩܝܦܕܝܐ (ܐܢܓܠܝܐ: Wikipedia) ܗܘ ܐܝܢܣܩܠܘܦܕܝܐ ܚܐܪܬܐ ܕܐܢܛܪܢܛ ܒܠܫܢ̈ܐ ܣܓܝܐ̈ܐ܂ ܫܡܗ ܐܬܐ ܡܢ ܡ̈ܠܬܐ ܕ\"ܘܝܩܝ\" ܘ\"ܐܝܢܣܩܠܘܦܕܝܐ\"܀",
135 new String[] { "ܘܝܩܝܦܕܝܐ", "ܐܢܓܠܝܐ", "Wikipedia", "ܗܘ", "ܐܝܢܣܩܠܘܦܕܝܐ", "ܚܐܪܬܐ", "ܕܐܢܛܪܢܛ", "ܒܠܫܢ̈ܐ", "ܣܓܝܐ̈ܐ", "ܫܡܗ",
136 "ܐܬܐ", "ܡܢ", "ܡ̈ܠܬܐ", "ܕ", "ܘܝܩܝ", "ܘ", "ܐܝܢܣܩܠܘܦܕܝܐ"});
139 public void testBengali() throws Exception {
140 BaseTokenStreamTestCase.assertAnalyzesTo(a, "এই বিশ্বকোষ পরিচালনা করে উইকিমিডিয়া ফাউন্ডেশন (একটি অলাভজনক সংস্থা)। উইকিপিডিয়ার শুরু ১৫ জানুয়ারি, ২০০১ সালে। এখন পর্যন্ত ২০০টিরও বেশী ভাষায় উইকিপিডিয়া রয়েছে।",
141 new String[] { "এই", "বিশ্বকোষ", "পরিচালনা", "করে", "উইকিমিডিয়া", "ফাউন্ডেশন", "একটি", "অলাভজনক", "সংস্থা", "উইকিপিডিয়ার",
142 "শুরু", "১৫", "জানুয়ারি", "২০০১", "সালে", "এখন", "পর্যন্ত", "২০০টিরও", "বেশী", "ভাষায়", "উইকিপিডিয়া", "রয়েছে" });
145 public void testFarsi() throws Exception {
146 BaseTokenStreamTestCase.assertAnalyzesTo(a, "ویکی پدیای انگلیسی در تاریخ ۲۵ دی ۱۳۷۹ به صورت مکملی برای دانشنامهٔ تخصصی نوپدیا نوشته شد.",
147 new String[] { "ویکی", "پدیای", "انگلیسی", "در", "تاریخ", "۲۵", "دی", "۱۳۷۹", "به", "صورت", "مکملی",
148 "برای", "دانشنامهٔ", "تخصصی", "نوپدیا", "نوشته", "شد" });
151 public void testGreek() throws Exception {
152 BaseTokenStreamTestCase.assertAnalyzesTo(a, "Γράφεται σε συνεργασία από εθελοντές με το λογισμικό wiki, κάτι που σημαίνει ότι άρθρα μπορεί να προστεθούν ή να αλλάξουν από τον καθένα.",
153 new String[] { "Γράφεται", "σε", "συνεργασία", "από", "εθελοντές", "με", "το", "λογισμικό", "wiki", "κάτι", "που",
154 "σημαίνει", "ότι", "άρθρα", "μπορεί", "να", "προστεθούν", "ή", "να", "αλλάξουν", "από", "τον", "καθένα" });
157 public void testThai() throws Exception {
158 BaseTokenStreamTestCase.assertAnalyzesTo(a, "การที่ได้ต้องแสดงว่างานดี. แล้วเธอจะไปไหน? ๑๒๓๔",
159 new String[] { "การที่ได้ต้องแสดงว่างานดี", "แล้วเธอจะไปไหน", "๑๒๓๔" });
162 public void testLao() throws Exception {
163 BaseTokenStreamTestCase.assertAnalyzesTo(a, "ສາທາລະນະລັດ ປະຊາທິປະໄຕ ປະຊາຊົນລາວ",
164 new String[] { "ສາທາລະນະລັດ", "ປະຊາທິປະໄຕ", "ປະຊາຊົນລາວ" });
167 public void testTibetan() throws Exception {
168 BaseTokenStreamTestCase.assertAnalyzesTo(a, "སྣོན་མཛོད་དང་ལས་འདིས་བོད་ཡིག་མི་ཉམས་གོང་འཕེལ་དུ་གཏོང་བར་ཧ་ཅང་དགེ་མཚན་མཆིས་སོ། །",
169 new String[] { "སྣོན", "མཛོད", "དང", "ལས", "འདིས", "བོད", "ཡིག",
170 "མི", "ཉམས", "གོང", "འཕེལ", "དུ", "གཏོང", "བར",
171 "ཧ", "ཅང", "དགེ", "མཚན", "མཆིས", "སོ" });
175 * For chinese, tokenize as char (these can later form bigrams or whatever)
177 public void testChinese() throws Exception {
178 BaseTokenStreamTestCase.assertAnalyzesTo(a, "我是中国人。 1234 Tests ",
179 new String[] { "我", "是", "中", "国", "人", "1234", "Tests"});
182 public void testEmpty() throws Exception {
183 BaseTokenStreamTestCase.assertAnalyzesTo(a, "", new String[] {});
184 BaseTokenStreamTestCase.assertAnalyzesTo(a, ".", new String[] {});
185 BaseTokenStreamTestCase.assertAnalyzesTo(a, " ", new String[] {});
188 /* test various jira issues this analyzer is related to */
190 public void testLUCENE1545() throws Exception {
192 * Standard analyzer does not correctly tokenize combining character U+0364 COMBINING LATIN SMALL LETTRE E.
193 * The word "moͤchte" is incorrectly tokenized into "mo" "chte", the combining character is lost.
194 * Expected result is only on token "moͤchte".
196 BaseTokenStreamTestCase.assertAnalyzesTo(a, "moͤchte", new String[] { "moͤchte" });
199 /* Tests from StandardAnalyzer, just to show behavior is similar */
200 public void testAlphanumericSA() throws Exception {
201 // alphanumeric tokens
202 BaseTokenStreamTestCase.assertAnalyzesTo(a, "B2B", new String[]{"B2B"});
203 BaseTokenStreamTestCase.assertAnalyzesTo(a, "2B", new String[]{"2B"});
206 public void testDelimitersSA() throws Exception {
207 // other delimiters: "-", "/", ","
208 BaseTokenStreamTestCase.assertAnalyzesTo(a, "some-dashed-phrase", new String[]{"some", "dashed", "phrase"});
209 BaseTokenStreamTestCase.assertAnalyzesTo(a, "dogs,chase,cats", new String[]{"dogs", "chase", "cats"});
210 BaseTokenStreamTestCase.assertAnalyzesTo(a, "ac/dc", new String[]{"ac", "dc"});
213 public void testApostrophesSA() throws Exception {
214 // internal apostrophes: O'Reilly, you're, O'Reilly's
215 BaseTokenStreamTestCase.assertAnalyzesTo(a, "O'Reilly", new String[]{"O'Reilly"});
216 BaseTokenStreamTestCase.assertAnalyzesTo(a, "you're", new String[]{"you're"});
217 BaseTokenStreamTestCase.assertAnalyzesTo(a, "she's", new String[]{"she's"});
218 BaseTokenStreamTestCase.assertAnalyzesTo(a, "Jim's", new String[]{"Jim's"});
219 BaseTokenStreamTestCase.assertAnalyzesTo(a, "don't", new String[]{"don't"});
220 BaseTokenStreamTestCase.assertAnalyzesTo(a, "O'Reilly's", new String[]{"O'Reilly's"});
223 public void testNumericSA() throws Exception {
224 // floating point, serial, model numbers, ip addresses, etc.
225 BaseTokenStreamTestCase.assertAnalyzesTo(a, "21.35", new String[]{"21.35"});
226 BaseTokenStreamTestCase.assertAnalyzesTo(a, "R2D2 C3PO", new String[]{"R2D2", "C3PO"});
227 BaseTokenStreamTestCase.assertAnalyzesTo(a, "216.239.63.104", new String[]{"216.239.63.104"});
230 public void testTextWithNumbersSA() throws Exception {
232 BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones", new String[]{"David", "has", "5000", "bones"});
235 public void testVariousTextSA() throws Exception {
237 BaseTokenStreamTestCase.assertAnalyzesTo(a, "C embedded developers wanted", new String[]{"C", "embedded", "developers", "wanted"});
238 BaseTokenStreamTestCase.assertAnalyzesTo(a, "foo bar FOO BAR", new String[]{"foo", "bar", "FOO", "BAR"});
239 BaseTokenStreamTestCase.assertAnalyzesTo(a, "foo bar . FOO <> BAR", new String[]{"foo", "bar", "FOO", "BAR"});
240 BaseTokenStreamTestCase.assertAnalyzesTo(a, "\"QUOTED\" word", new String[]{"QUOTED", "word"});
243 public void testKoreanSA() throws Exception {
245 BaseTokenStreamTestCase.assertAnalyzesTo(a, "안녕하세요 한글입니다", new String[]{"안녕하세요", "한글입니다"});
248 public void testOffsets() throws Exception {
249 BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones",
250 new String[] {"David", "has", "5000", "bones"},
251 new int[] {0, 6, 10, 15},
252 new int[] {5, 9, 14, 20});
255 public void testTypes() throws Exception {
256 BaseTokenStreamTestCase.assertAnalyzesTo(a, "David has 5000 bones",
257 new String[] {"David", "has", "5000", "bones"},
258 new String[] { "<ALPHANUM>", "<ALPHANUM>", "<NUM>", "<ALPHANUM>" });
261 public void testWikiURLs() throws Exception {
262 Reader reader = null;
263 String luceneResourcesWikiPage;
265 reader = new InputStreamReader(getClass().getResourceAsStream
266 ("LuceneResourcesWikiPage.html"), "UTF-8");
267 StringBuilder builder = new StringBuilder();
268 char[] buffer = new char[1024];
270 while (-1 != (numCharsRead = reader.read(buffer))) {
271 builder.append(buffer, 0, numCharsRead);
273 luceneResourcesWikiPage = builder.toString();
275 if (null != reader) {
279 assertTrue(null != luceneResourcesWikiPage
280 && luceneResourcesWikiPage.length() > 0);
281 BufferedReader bufferedReader = null;
284 List<String> urlList = new ArrayList<String>();
285 bufferedReader = new BufferedReader(new InputStreamReader
286 (getClass().getResourceAsStream("LuceneResourcesWikiPageURLs.txt"), "UTF-8"));
288 while (null != (line = bufferedReader.readLine())) {
290 if (line.length() > 0) {
294 urls = urlList.toArray(new String[urlList.size()]);
296 if (null != bufferedReader) {
297 bufferedReader.close();
300 assertTrue(null != urls && urls.length > 0);
301 BaseTokenStreamTestCase.assertAnalyzesTo
302 (urlAnalyzer, luceneResourcesWikiPage, urls);
305 public void testEmails() throws Exception {
306 Reader reader = null;
307 String randomTextWithEmails;
309 reader = new InputStreamReader(getClass().getResourceAsStream
310 ("random.text.with.email.addresses.txt"), "UTF-8");
311 StringBuilder builder = new StringBuilder();
312 char[] buffer = new char[1024];
314 while (-1 != (numCharsRead = reader.read(buffer))) {
315 builder.append(buffer, 0, numCharsRead);
317 randomTextWithEmails = builder.toString();
319 if (null != reader) {
323 assertTrue(null != randomTextWithEmails
324 && randomTextWithEmails.length() > 0);
325 BufferedReader bufferedReader = null;
328 List<String> emailList = new ArrayList<String>();
329 bufferedReader = new BufferedReader(new InputStreamReader
330 (getClass().getResourceAsStream
331 ("email.addresses.from.random.text.with.email.addresses.txt"), "UTF-8"));
333 while (null != (line = bufferedReader.readLine())) {
335 if (line.length() > 0) {
339 emails = emailList.toArray(new String[emailList.size()]);
341 if (null != bufferedReader) {
342 bufferedReader.close();
345 assertTrue(null != emails && emails.length > 0);
346 BaseTokenStreamTestCase.assertAnalyzesTo
347 (emailAnalyzer, randomTextWithEmails, emails);
350 public void testURLs() throws Exception {
351 Reader reader = null;
352 String randomTextWithURLs;
354 reader = new InputStreamReader(getClass().getResourceAsStream
355 ("random.text.with.urls.txt"), "UTF-8");
356 StringBuilder builder = new StringBuilder();
357 char[] buffer = new char[1024];
359 while (-1 != (numCharsRead = reader.read(buffer))) {
360 builder.append(buffer, 0, numCharsRead);
362 randomTextWithURLs = builder.toString();
364 if (null != reader) {
368 assertTrue(null != randomTextWithURLs
369 && randomTextWithURLs.length() > 0);
370 BufferedReader bufferedReader = null;
373 List<String> urlList = new ArrayList<String>();
374 bufferedReader = new BufferedReader(new InputStreamReader
375 (getClass().getResourceAsStream
376 ("urls.from.random.text.with.urls.txt"), "UTF-8"));
378 while (null != (line = bufferedReader.readLine())) {
380 if (line.length() > 0) {
384 urls = urlList.toArray(new String[urlList.size()]);
386 if (null != bufferedReader) {
387 bufferedReader.close();
390 assertTrue(null != urls && urls.length > 0);
391 BaseTokenStreamTestCase.assertAnalyzesTo
392 (urlAnalyzer, randomTextWithURLs, urls);
395 public void testUnicodeWordBreaks() throws Exception {
396 WordBreakTestUnicode_6_0_0 wordBreakTest = new WordBreakTestUnicode_6_0_0();
397 wordBreakTest.test(a);
400 public void testSupplementary() throws Exception {
401 BaseTokenStreamTestCase.assertAnalyzesTo(a, "𩬅艱鍟䇹愯瀛",
402 new String[] {"𩬅", "艱", "鍟", "䇹", "愯", "瀛"},
403 new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>" });
406 public void testKorean() throws Exception {
407 BaseTokenStreamTestCase.assertAnalyzesTo(a, "훈민정음",
408 new String[] { "훈민정음" },
409 new String[] { "<HANGUL>" });
412 public void testJapanese() throws Exception {
413 BaseTokenStreamTestCase.assertAnalyzesTo(a, "仮名遣い カタカナ",
414 new String[] { "仮", "名", "遣", "い", "カタカナ" },
415 new String[] { "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<IDEOGRAPHIC>", "<HIRAGANA>", "<KATAKANA>" });
418 public void testCombiningMarks() throws Exception {
419 checkOneTerm(a, "ざ", "ざ"); // hiragana
420 checkOneTerm(a, "ザ", "ザ"); // katakana
421 checkOneTerm(a, "壹゙", "壹゙"); // ideographic
422 checkOneTerm(a, "아゙", "아゙"); // hangul
425 /** @deprecated remove this and sophisticated backwards layer in 5.0 */
427 public void testCombiningMarksBackwards() throws Exception {
428 Analyzer a = new ReusableAnalyzerBase() {
430 protected TokenStreamComponents createComponents
431 (String fieldName, Reader reader) {
433 Tokenizer tokenizer = new UAX29URLEmailTokenizer(reader);
434 return new TokenStreamComponents(tokenizer);
437 checkOneTerm(a, "ざ", "さ"); // hiragana Bug
438 checkOneTerm(a, "ザ", "ザ"); // katakana Works
439 checkOneTerm(a, "壹゙", "壹"); // ideographic Bug
440 checkOneTerm(a, "아゙", "아゙"); // hangul Works
443 /** blast some random strings through the analyzer */
444 public void testRandomStrings() throws Exception {
445 checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);