├── .gitignore ├── .travis.yml ├── LICENSE ├── README.md ├── docs └── wiki │ ├── Home.md │ └── media │ └── 1.png ├── pom.xml └── src ├── main ├── java │ └── com │ │ └── mindflow │ │ └── py4j │ │ ├── Converter.java │ │ ├── PinyinConverter.java │ │ ├── exception │ │ └── IllegalPinyinException.java │ │ ├── util │ │ ├── ArrayUtils.java │ │ ├── IoUtils.java │ │ └── StringUtils.java │ │ └── voc │ │ └── Py4jDictionary.java └── resources │ └── META-INF │ └── vocabulary │ └── py4j.txt └── test └── java └── com └── mindflow └── py4j ├── PinyinConverterTest.java └── ThreadSafeTest.java /.gitignore: -------------------------------------------------------------------------------- 1 | # maven ignore 2 | *target/ 3 | !tools/*.jar 4 | *.war 5 | *.zip 6 | *.tar 7 | *.tar.gz 8 | 9 | # Java class files 10 | *.class 11 | 12 | # eclipse ignore 13 | *.settings/ 14 | .project 15 | .classpath 16 | 17 | # idea ignore 18 | .idea/ 19 | *.ipr 20 | *.iml 21 | *.iws 22 | 23 | # temp ignore 24 | *.log 25 | *.log.* 26 | *.cache 27 | *.diff 28 | *.patch 29 | *.tmp 30 | 31 | # system ignore 32 | .DS_Store 33 | Thumbs.db 34 | 35 | sublime-project 36 | sublime-project.sublime-workspace 37 | 38 | coverage-report/ 39 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: java 2 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Kitty 2 | [![License](https://img.shields.io/badge/license-Apache%202-green.svg)](https://www.apache.org/licenses/LICENSE-2.0) [![Release Version](https://img.shields.io/badge/release-1.0.0-red.svg)](https://github.com/TFrise/py4j/releases) [![Build Status](https://travis-ci.org/TFrise/py4j.svg?branch=master)](https://travis-ci.org/TFrise/py4j) 3 | 4 | ## Overview 5 | A open-source Java library for converting Chinese to Pinyin. 6 | 7 | ## Features 8 | * solve Chinese polyphone 9 | * support external custom extension dictionary 10 | 11 | ## maven dependency 12 | ``` 13 | 14 | com.mindflow 15 | py4j 16 | 1.0.0 17 | 18 | ``` 19 | 20 | ## Usage 21 | ### 1. single char 22 | ``` 23 | Converter converter = new PinyinConverter(); 24 | 25 | char[] chs = {'长', '行', '藏', '度', '阿', '佛', '2', 'A', 'a'}; 26 | for(char ch : chs){ 27 | String[] arr_py = converter.getPinyin(ch); 28 | System.out.println(ch+"\t"+Arrays.toString(arr_py)); 29 | } 30 | ``` 31 | 32 | output: 33 | ``` 34 | 长 [chang, zhang] 35 | 行 [xing, hang, heng] 36 | 藏 [zang, cang] 37 | 度 [du, duo] 38 | 阿 [a, e] 39 | 佛 [fo, fu] 40 | 2 [2] 41 | A [A] 42 | a [a] 43 | ``` 44 | 45 | ### 2. word 46 | ``` 47 | Converter converter = new PinyinConverter(); 48 | 49 | final String[] arr = {"肯德基", "重庆银行", "长沙银行", "便宜坊", "西藏", "藏宝图", "出差", "参加", "列车长"}; 50 | for (String chinese : arr){ 51 | String py = converter.getPinyin(chinese); 52 | System.out.println(chinese+"\t"+py); 53 | } 54 | ``` 55 | 56 | output: 57 | ``` 58 | 肯德基 KenDeJi 59 | 重庆银行 ChongQingYinHang 60 | 长沙银行 ChangShaYinHang 61 | 便宜坊 BianYiFang 62 | 西藏 XiZang 63 | 藏宝图 CangBaoTu 64 | 出差 ChuChai 65 | 参加 CanJia 66 | 列车长 LieCheZhang 67 | ``` 68 | 69 | ### 3.Extension vocabulary 70 | Create a file named **py4j.txt** in your project's classpath **META-INF/vocabulary** directory. 71 | 72 | Just like this:
73 | ![Extension](docs/wiki/media/1.png) 74 | 75 | 76 | **py4j.txt** Content format: 77 | ``` 78 | bian#扁/便/便宜坊 79 | du#读/都/度 80 | 81 | ``` 82 | 83 | ## Performance Tips 84 | > Py4j instances are Thread-safe so you can reuse them freely across multiple threads. 85 | 86 | Testcase: 87 | ``` 88 | final String[] arr = {"大夫", "重庆银行", "长沙银行", "便宜坊", "西藏", "藏宝图", "出差", "参加", "列车长"}; 89 | final Converter converter = new PinyinConverter(); 90 | 91 | int threadNum = 20; 92 | ExecutorService pool = Executors.newFixedThreadPool(threadNum); 93 | for(int i=0;i() { 95 | @Override 96 | public Void call() throws Exception { 97 | 98 | System.out.println("thread "+Thread.currentThread().getName()+" start"); 99 | for(int i=0;i<1000;i++){ 100 | converter.getPinyin(arr[i%arr.length]); 101 | } 102 | System.out.println("thread "+Thread.currentThread().getName()+" over"); 103 | return null; 104 | } 105 | }); 106 | } 107 | 108 | pool.shutdown(); 109 | ``` 110 | -------------------------------------------------------------------------------- /docs/wiki/Home.md: -------------------------------------------------------------------------------- 1 | # Home -------------------------------------------------------------------------------- /docs/wiki/media/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/TFdream/py4j/5b23bfd3e2170e969c0b8eca744011b6c02aa8ad/docs/wiki/media/1.png -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 3 | 4.0.0 4 | 5 | com.mindflow 6 | py4j 7 | 1.0.0 8 | jar 9 | 10 | py4j 11 | http://maven.apache.org 12 | 13 | 14 | 1.7 15 | UTF-8 16 | 17 | 18 | 19 | 20 | com.belerweb 21 | pinyin4j 22 | 2.5.0 23 | 24 | 25 | 26 | com.google.guava 27 | guava 28 | 18.0 29 | 30 | 31 | 32 | 33 | org.slf4j 34 | slf4j-api 35 | 1.7.21 36 | 37 | 38 | 39 | junit 40 | junit 41 | 4.12 42 | test 43 | 44 | 45 | 46 | 47 | 48 | 49 | org.apache.maven.plugins 50 | maven-compiler-plugin 51 | 3.5.1 52 | 53 | ${java.version} 54 | ${java.version} 55 | ${java.version} 56 | ${java.version} 57 | 58 | 59 | 60 | 61 | 62 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/Converter.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j; 2 | 3 | import com.mindflow.py4j.exception.IllegalPinyinException; 4 | 5 | /** 6 | * @author Ricky Fung 7 | */ 8 | public interface Converter { 9 | 10 | String[] getPinyin(char ch) throws IllegalPinyinException; 11 | 12 | String getPinyin(String chinese) throws IllegalPinyinException; 13 | } 14 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/PinyinConverter.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j; 2 | 3 | import com.mindflow.py4j.exception.IllegalPinyinException; 4 | import com.mindflow.py4j.util.ArrayUtils; 5 | import com.mindflow.py4j.util.StringUtils; 6 | import com.google.common.collect.ArrayListMultimap; 7 | import com.mindflow.py4j.voc.Py4jDictionary; 8 | import net.sourceforge.pinyin4j.PinyinHelper; 9 | import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType; 10 | import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat; 11 | import net.sourceforge.pinyin4j.format.HanyuPinyinToneType; 12 | import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType; 13 | import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination; 14 | 15 | /** 16 | * 17 | * @author Ricky Fung 18 | */ 19 | public class PinyinConverter implements Converter { 20 | private final ArrayListMultimap duoYinZiMap; 21 | public PinyinConverter(){ 22 | this.duoYinZiMap = Py4jDictionary.getDefault().getDuoYinZiMap(); 23 | } 24 | 25 | @Override 26 | public String[] getPinyin(char ch) throws IllegalPinyinException { 27 | try{ 28 | HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat(); 29 | outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE); 30 | outputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE); 31 | outputFormat.setVCharType(HanyuPinyinVCharType.WITH_V); 32 | 33 | if(ch>=32 && ch<=125){ //ASCII >=33 ASCII<=125的直接返回 ,ASCII码表：http://www.asciitable.com/ 34 | return new String[]{String.valueOf(ch)}; 35 | } 36 | return ArrayUtils.distinct(PinyinHelper.toHanyuPinyinStringArray(ch, outputFormat)); 37 | } catch (BadHanyuPinyinOutputFormatCombination e) { 38 | throw new IllegalPinyinException(e); 39 | } 40 | 41 | } 42 | 43 | @Override 44 | public String getPinyin(String chinese) throws IllegalPinyinException { 45 | if(StringUtils.isEmpty(chinese)){ 46 | return null; 47 | } 48 | 49 | chinese = chinese.replaceAll("[\\.，\\,！·\\!？\\?；\\;\\(\\)（）\\[\\]\\:： ]+", " ").trim(); 50 | 51 | StringBuilder py_sb = new StringBuilder(32); 52 | char[] chs = chinese.toCharArray(); 53 | for(int i=0;i=1 && i+1<=chinese.length()){ 67 | left = chinese.substring(i-1,i+1); 68 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(left)){ 69 | resultPy = py; 70 | break; 71 | } 72 | } 73 | 74 | String right = null; //向右多取一个字,例如 [长]沙 75 | if(i<=chinese.length()-2){ 76 | right = chinese.substring(i,i+2); 77 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(right)){ 78 | resultPy = py; 79 | break; 80 | } 81 | } 82 | 83 | String middle = null; //左右各多取一个字,例如 龙[爪]槐 84 | if(i>=1 && i+2<=chinese.length()){ 85 | middle = chinese.substring(i-1,i+2); 86 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(middle)){ 87 | resultPy = py; 88 | break; 89 | } 90 | } 91 | String left3 = null; //向左多取2个字,如 芈月[传],列车长 92 | if(i>=2 && i+1<=chinese.length()){ 93 | left3 = chinese.substring(i-2,i+1); 94 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(left3)){ 95 | resultPy = py; 96 | break; 97 | } 98 | } 99 | 100 | String right3 = null; //向右多取2个字,如 [长]孙无忌 101 | if(i<=chinese.length()-3){ 102 | right3 = chinese.substring(i,i+3); 103 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(right3)){ 104 | resultPy = py; 105 | break; 106 | } 107 | } 108 | 109 | if(duoYinZiMap.containsKey(py) && duoYinZiMap.get(py).contains(String.valueOf(chs[i]))){ //默认拼音 110 | defaultPy = py; 111 | } 112 | } 113 | 114 | if(StringUtils.isEmpty(resultPy)){ 115 | if(StringUtils.isNotEmpty(defaultPy)){ 116 | resultPy = defaultPy; 117 | }else{ 118 | resultPy = py_arr[0]; 119 | } 120 | } 121 | py_sb.append(convertInitialToUpperCase(resultPy)); 122 | } 123 | } 124 | 125 | return py_sb.toString(); 126 | } 127 | 128 | private String convertInitialToUpperCase(String str) { 129 | if (str == null || str.length()==0) { 130 | return ""; 131 | } 132 | return str.substring(0, 1).toUpperCase()+str.substring(1); 133 | } 134 | } 135 | 136 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/exception/IllegalPinyinException.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j.exception; 2 | 3 | /** 4 | * 5 | * @author Ricky Fung 6 | */ 7 | public class IllegalPinyinException extends Exception { 8 | 9 | private static final long serialVersionUID = 4447260855879734366L; 10 | 11 | public IllegalPinyinException() { 12 | } 13 | 14 | public IllegalPinyinException(String message) { 15 | super(message); 16 | } 17 | 18 | public IllegalPinyinException(String message, Throwable cause) { 19 | super(message, cause); 20 | } 21 | 22 | public IllegalPinyinException(Throwable cause) { 23 | super(cause); 24 | } 25 | } 26 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/util/ArrayUtils.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j.util; 2 | 3 | import java.util.HashSet; 4 | 5 | /** 6 | * @author Ricky Fung 7 | */ 8 | public class ArrayUtils { 9 | 10 | private ArrayUtils() {} 11 | 12 | public static String[] distinct(String[] arr) { 13 | if(arr==null || arr.length==0) { 14 | return arr; 15 | } 16 | HashSet set = new HashSet<>(); 17 | for (String str : arr) { 18 | set.add(str); 19 | } 20 | return set.toArray(new String[0]); 21 | } 22 | } 23 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/util/IoUtils.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j.util; 2 | 3 | import java.io.Closeable; 4 | import java.io.IOException; 5 | import java.io.InputStream; 6 | import java.io.OutputStream; 7 | 8 | /** 9 | * 10 | * @author Ricky Fung 11 | */ 12 | public class IoUtils { 13 | 14 | public static void closeQuietly(InputStream input){ 15 | closeQuietly((Closeable)input); 16 | } 17 | 18 | public static void closeQuietly(OutputStream output){ 19 | closeQuietly((Closeable)output); 20 | } 21 | 22 | public static void closeQuietly(Closeable closeable) { 23 | try { 24 | if(closeable != null) { 25 | closeable.close(); 26 | } 27 | } catch (IOException e) { 28 | e.printStackTrace(); 29 | } 30 | } 31 | 32 | public static void closeQuietly(Closeable... closeables){ 33 | for (Closeable closeable : closeables){ 34 | closeQuietly(closeable); 35 | } 36 | } 37 | 38 | public static long copy(InputStream in, OutputStream out, int bufferSize) throws IOException { 39 | byte[] buff = new byte[bufferSize]; 40 | return copy(in, out, buff); 41 | } 42 | 43 | public static long copy(InputStream in, OutputStream out) throws IOException { 44 | byte[] buff = new byte[1024]; 45 | return copy(in, out, buff); 46 | } 47 | 48 | public static long copy(InputStream in, OutputStream out, byte[] buff) throws IOException { 49 | long count = 0; 50 | int len = -1; 51 | while((len=in.read(buff, 0, buff.length))!=-1){ 52 | out.write(buff, 0, len); 53 | count += len; 54 | } 55 | return count; 56 | } 57 | } 58 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/util/StringUtils.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j.util; 2 | 3 | /** 4 | * ${DESCRIPTION} 5 | * 6 | * @author Ricky Fung 7 | */ 8 | public class StringUtils { 9 | 10 | public static final String EMPTY = ""; 11 | 12 | public static boolean isEmpty(final CharSequence cs) { 13 | return cs == null || cs.length() == 0; 14 | } 15 | 16 | public static boolean isNotEmpty(final CharSequence str) { 17 | return !isEmpty(str); 18 | } 19 | 20 | public static boolean isBlank(final CharSequence cs) { 21 | int strLen; 22 | if (cs == null || (strLen = cs.length()) == 0) { 23 | return true; 24 | } 25 | for (int i = 0; i < strLen; i++) { 26 | if (Character.isWhitespace(cs.charAt(i)) == false) { 27 | return false; 28 | } 29 | } 30 | return true; 31 | } 32 | 33 | public static boolean isNotBlank(final CharSequence cs) { 34 | return !isBlank(cs); 35 | } 36 | 37 | public static boolean equals(String str1, String str2) { 38 | return str1 == null?str2 == null:str1.equals(str2); 39 | } 40 | 41 | public static boolean equalsIgnoreCase(String str1, String str2) { 42 | return str1 == null?str2 == null:str1.equalsIgnoreCase(str2); 43 | } 44 | 45 | public static boolean contains(String[] arr, String searchStr) { 46 | if (arr == null || searchStr == null) { 47 | return false; 48 | } 49 | for(String str : arr) { 50 | if(searchStr.equals(str)){ 51 | return true; 52 | } 53 | } 54 | return false; 55 | } 56 | 57 | /** 58 | * StringUtils.capitalize(null) = null 59 | * StringUtils.capitalize("") = "" 60 | * StringUtils.capitalize("cat") = "Cat" 61 | * StringUtils.capitalize("cAt") = "CAt" 62 | * StringUtils.capitalize("'cat'") = "'cat'" 63 | * 64 | * @param str 65 | * @return 66 | */ 67 | public static String capitalize(final String str) { 68 | int strLen; 69 | if (str == null || (strLen = str.length()) == 0) { 70 | return str; 71 | } 72 | 73 | final char firstChar = str.charAt(0); 74 | final char newChar = Character.toTitleCase(firstChar); 75 | if (firstChar == newChar) { 76 | // already capitalized 77 | return str; 78 | } 79 | 80 | char[] newChars = new char[strLen]; 81 | newChars[0] = newChar; 82 | str.getChars(1,strLen, newChars, 1); 83 | return String.valueOf(newChars); 84 | } 85 | } 86 | -------------------------------------------------------------------------------- /src/main/java/com/mindflow/py4j/voc/Py4jDictionary.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j.voc; 2 | 3 | import com.mindflow.py4j.util.IoUtils; 4 | import com.mindflow.py4j.util.StringUtils; 5 | import com.google.common.collect.ArrayListMultimap; 6 | import org.slf4j.Logger; 7 | import org.slf4j.LoggerFactory; 8 | 9 | import java.io.BufferedReader; 10 | import java.io.IOException; 11 | import java.io.InputStream; 12 | import java.io.InputStreamReader; 13 | import java.net.URL; 14 | import java.util.Enumeration; 15 | 16 | /** 17 | * 18 | * @author Ricky Fung 19 | */ 20 | public class Py4jDictionary { 21 | private final Logger logger = LoggerFactory.getLogger(this.getClass()); 22 | 23 | private static final String PREFIX = "META-INF/vocabulary/"; 24 | 25 | private ArrayListMultimap duoYinZiMap; 26 | 27 | private static final String CONFIG_NAME = "py4j.txt"; 28 | 29 | private static final String PINYIN_SEPARATOR = "#"; 30 | 31 | private static final String WORD_SEPARATOR = "/"; 32 | 33 | private volatile boolean initialized; 34 | 35 | public Py4jDictionary(){ 36 | 37 | } 38 | 39 | public static Py4jDictionary getDefault(){ 40 | return SingletonHolder.INSTANCE; 41 | } 42 | 43 | public ArrayListMultimap getDuoYinZiMap(){ 44 | checkInit(); 45 | return duoYinZiMap; 46 | } 47 | 48 | private void checkInit() { 49 | if (!initialized) { 50 | loadVocabulary(); 51 | } 52 | } 53 | 54 | private synchronized void loadVocabulary() { 55 | if(initialized){ 56 | return; 57 | } 58 | this.duoYinZiMap = loadVocabulary0(CONFIG_NAME); 59 | initialized = true; 60 | } 61 | 62 | private ArrayListMultimap loadVocabulary0(String name) { 63 | debug("******start load py4j config******"); 64 | ArrayListMultimap duoYinZiMap = ArrayListMultimap.create(512, 32); 65 | String filename = PREFIX + name; 66 | try{ 67 | ClassLoader cl = Thread.currentThread().getContextClassLoader(); 68 | Enumeration urls = cl.getResources(filename); 69 | if(urls!=null){ 70 | while (urls.hasMoreElements()) { 71 | URL url = urls.nextElement(); 72 | parseURL(url, duoYinZiMap); 73 | } 74 | } 75 | } catch (Exception e){ 76 | error("caught exception when load py4j vocabulary", e); 77 | throw new RuntimeException("caught exception when load py4j vocabulary", e); 78 | } 79 | debug("******load py4j config over******"); 80 | debug("py4j map key size:{}", duoYinZiMap.keySet().size()); 81 | return duoYinZiMap; 82 | } 83 | 84 | private void parseURL(URL url, ArrayListMultimap duoYinZiMap){ 85 | debug("load py4j dictionary file:{}", url.getPath()); 86 | InputStream in = null; 87 | BufferedReader br = null; 88 | try { 89 | in = url.openStream(); 90 | br = new BufferedReader(new InputStreamReader(in, "UTF-8")); 91 | String line = null; 92 | while ((line = br.readLine()) != null) { 93 | 94 | String[] arr = line.split(PINYIN_SEPARATOR); 95 | 96 | if (StringUtils.isNotEmpty(arr[1])) { 97 | String[] dyzs = arr[1].split(WORD_SEPARATOR); 98 | for (String dyz : dyzs) { 99 | if (StringUtils.isNotEmpty(dyz)) { 100 | duoYinZiMap.put(arr[0], dyz.trim()); 101 | } 102 | } 103 | } 104 | } 105 | } catch (IOException e) { 106 | throw new RuntimeException(String.format("load py4j config:%s error", url), e); 107 | } finally { 108 | IoUtils.closeQuietly(br); 109 | IoUtils.closeQuietly(in); 110 | } 111 | } 112 | 113 | private void error(String msg, Throwable err){ 114 | logger.error(msg, err); 115 | } 116 | 117 | private void debug(String msg, Object... args) { 118 | if(logger.isDebugEnabled()) { 119 | logger.debug(msg, args); 120 | } 121 | } 122 | 123 | private static class SingletonHolder { 124 | private static final Py4jDictionary INSTANCE = new Py4jDictionary(); 125 | } 126 | } 127 | -------------------------------------------------------------------------------- /src/main/resources/META-INF/vocabulary/py4j.txt: -------------------------------------------------------------------------------- 1 | a#阿 2 | ao#拗口/违拗/拗断/执拗/拗口/拗口风/拗口令/拗曲/拗性/拗折/警拗 3 | ai#艾 4 | bang#膀/磅/蚌 5 | ba#扒 6 | bai#叔伯/百/柏杨/㧳/梵呗/呗佛/呗音/呗唱/呗偈/呗声/呗赞/赞呗 7 | bao#剥皮/薄/暴/堡/曝 8 | bei#呗 9 | beng#蚌埠 10 | bi#复辟/臂/秘鲁/泌阳 11 | bing#屏息/屏弃/屏气/屏除/屏声 12 | bian#扁/便/便宜坊 13 | bo#薄荷/单薄/伯/泊/波/柏/萝卜/孛 14 | bu#卜/柨 15 | can#参 16 | cang#藏/欌 17 | cen#参差 18 | ceng#曾/噌 19 | cha#差/刹那/宝刹/一刹/查/碴/喳喳/喀喳 20 | chai#公差/差役/专差/官差/听差/美差/办差/差事/差使/肥差/当差/钦差/苦差/出差 21 | chan#颤/单于/禅 22 | chang#长/厂 23 | chao#朝/嘲/焯 24 | che#工尺/车 25 | chen#称职/匀称/称心/相称/对称 26 | cheng#称/乘/澄/噌吰/橙 秤/盛满/盛器/盛饭 27 | chu#畜 28 | chui#椎心 29 | chuai#揣 30 | chuan#传 31 | chi#匙/尺/吃 32 | chong#重庆/重重/虫 33 | chou#臭/帱 34 | chuang#经幢 35 | chuo#绰 36 | ci#参差/鳞差/伺候/龟兹 37 | cuan#攒聚/攒动/攒集/攒宫/攒所 38 | cuo#撮儿/撮要/撮合 39 | da#大/嗒 40 | dao#叨/帱载/帱察 41 | dai#大夫 42 | dan#单/弹/掸/澹 43 | dang#铛 44 | de#的/得 45 | di#堤/底/怎的/有的/目的/标的/打的/的确/有的放/的卢/矢之的/言中的/语中的/的士/地/提防/快的/美的 46 | diao#蓝调/调调/音调/论调/格调/调令/低调/笔调/基调/强调/声调/滥调/老调/色调/单调/腔调/跑调/曲调/步调/语调/主调/情调 47 | ding#丁 48 | du#读/都/度 49 | dou#全都/句读 50 | duo#舵/测度/忖度/揣度/猜度 51 | dun#粮囤/盾/顿/沌/敦 52 | e#阿谀/阿胶/阿弥/恶/擜 53 | er#儿 54 | fan#番 55 | feng#冯 56 | fei#婔 57 | fo#佛 58 | fu#仿佛/果脯/罘/莩 59 | fou#否 60 | fiao#覅 61 | ga#咖喱/伽马/嘎/戛纳 62 | gai#盖 63 | gao#告 64 | gang#扛鼎 65 | ge#革/蛤蚧/文蛤/蛤蜊/咯 66 | gei#给 67 | geng#脖颈 68 | gong#女红/共 69 | gu#谷/中鹄/鼓 70 | gui#龟/柜/硅/倭傀/傀异/傀然/傀垒/傀怪/傀卓/傀奇/傀伟/傀民/傀俄/琦傀/奇傀 71 | gua#呱 72 | guan#纶巾/东莞 73 | guang#广 74 | ha#蛤/哈/虾蟆 75 | hai#还/嗨/咳声/咳笑 76 | hao#貉子/貉绒 77 | hang#夯/总行/分行/支行/行业/排行/行情/央行/商行/外行/银行/中行/交行/招行/农行/工行/建行/商行/酒行/麻行/琴行/行业/同行/行列/行货/行会/行家/巷道/引吭/扼吭/批吭/搤吭/高吭/喉吭/咔吭/絶吭/吭嗌/吭咽/吭首 78 | he#和/合/核/鶴/猲 79 | heng#道行/涥 80 | hu#鹄/水浒/嗀/唬 81 | hua#滑/呚/椛 82 | huan#归还/放还/奉还/圜 83 | hui#会/浍河/媈/灳/哕/瑗珲 84 | hong#红/虹 85 | huo#软和/热和/暖和 86 | hun#尡/珲 87 | ji#病革/给养/自给/给水/薪给/给予/供给/稽/缉/藉/奇数/亟/诘屈/荠菜/愱 88 | jia#雪茄/伽/家/价/贾/戛 89 | jian#见/浅浅 90 | jiang#降 91 | jiao#嚼舌/嚼字/嚼蜡/角/剿/饺/脚/蕉/矫/睡觉/侥/校对/校验/校正/校准/审校/校场/校核/校勘/校订/校阅/校样 92 | jie#解/慰藉/蕴藉/诘/媘/煯 93 | jin#矜/劲/禁 94 | jing#颈/景/强劲/劲风/劲旅/劲敌/劲射/苍劲/遒劲/劲草 95 | jiong#炅 96 | ju#咀/居/桔/句/婮 97 | jun#均 98 | juan#棚圈/圈养/猪圈/羊圈 99 | jue#主角/角色/旦角/女角/丑角/角力/名角/配角/嚼/觉/䏐 100 | jun#龟裂/俊 101 | ka#咖/卡/喀 102 | kai#楷 103 | kang#扛 104 | ke#咳/壳 105 | keng#吭 106 | kuai#会计/财会/浍 107 | kui#傀 108 | kuo#括 109 | la#癞痢/腊/蜡 110 | lai#癞疮/癞子/癞蛤/癞皮 111 | lao#积潦/络子/落枕/落价/粩/姥 112 | le#乐/勒/了 113 | lei#勒紧 114 | lo#然咯 115 | lou#佝偻/泄露/露面/露脸/露骨/露底/露馅/露一手/露相/露马脚/露怯 116 | long#里弄/弄堂/泷 117 | li#跞/礼/櫔/栃 118 | liao#了解/了结/明了/了得/末了/未了/了如/潦/撩 119 | liang#靓/俩 120 | lie#挘 121 | lin#崊 122 | ling#霗/令 123 | liu#六/遛 124 | lu#碌/陆/露 125 | luo#络/落/漯/囖/洜/泺 126 | lv#率/绿 127 | lve#鋢/稤 128 | lun#纶 129 | ma#嫲/抹布/抹脸/抹桌子/摩挲 130 | mai#埋 131 | man#埋怨/蔓 132 | mai#脉 133 | mang#氓/芒 134 | mao#冒 135 | me#嚒 136 | men#椚 137 | meng#群氓/盟/癦 138 | mei#没/旀 139 | mo#淹没/没收/出没/沉没/没落/吞没/覆没/没入/埋没/鬼没/隐没/湮没/辱没/脉脉/模/摩/抹 140 | mou#绸缪/牟 141 | mi#秘/泌尿/分泌/谜/檷枸 142 | mian#渑 143 | ming#掵 144 | miu#谬/谬论/纰缪 145 | mu#大模/字模/模板/模样/模具/装模/模子/牟尼/子牟/夷牟/悬牟/相牟/头牟/宾牟/曹牟/岑牟/兜牟/卢牟/弥牟/牟食/牟槊/牟衫/牟光/牟牟/牟甲 146 | na#哪/娜/那 147 | nao#臑 148 | nan#南 149 | ne#哪吒/呢 150 | nei#氞 151 | neus#莻 152 | nong#弄/燶 153 | ni#毛呢/花呢/呢绒/线呢/呢料/呢子/呢喃/溺/檷 154 | niao#尿/鸟/便溺 155 | nian#粘膜/粘度/粘土/粘合剂/粘液/粘稠/粘合/粘着/粘结/粘性/粘附/不粘锅/粘糊/粘虫/粘聚/粘滞/焾/哖 156 | niang#酿 157 | nin#脌 158 | ning#倿/拧 159 | niu#拗/汼 160 | nu#努 161 | nuo#婀娜/袅娜/喏 162 | nv#女 163 | nve#疟/硸 164 | o#喔/筽 165 | ou#膒 166 | pa#扒手/扒窃/扒外/扒分/扒糕/扒灰/扒犁/扒龙/扒搂/扒山虎/扒艇 167 | pai#派/迫击/迫击炮 168 | pao#刨/炮/萢 169 | pan#番禺 170 | pang#胖/膀/磅 171 | pei#蓜 172 | pi#辟/否极/臧否/龙陂/芘 173 | pian#扁舟/便宜/魸 174 | piao#朴姓/饿莩/饥莩/葭莩 175 | pin#穦 176 | ping#屏/苹/冯河 177 | po#湖泊/血泊 /迫/朴刀/坡/陂 178 | pu#一曝十寒/里堡/十里堡/脯/朴/曝晒/瀑/埔 179 | qi#期/其/泣/祇 180 | qiu#龟兹/湭 181 | qi#稽首/缉鞋/栖/奇/漆/齐 182 | qia#卡脖/卡子/关卡/卡壳/哨卡/边卡/发卡/峠 183 | qiao#雀盲/雀子/地壳/甲壳/躯壳 184 | qian#纤/乾/浅 185 | qiang#强/㛨/㩖/䅚/䵁 186 | qie#茄/趔趄/聺/籡 187 | qin#亲/沁 188 | qing#干亲/亲家 189 | qiong#熍 190 | qu#区/趣/爠 191 | quan#圈/券 192 | que#雀/炔 193 | re#声喏/唱喏 194 | rong#嬫 195 | ruo#若/嵶 196 | saeng#栍 197 | sang#槡 198 | sai#塞/嘥 199 | sao#螦 200 | se#堵塞/搪塞/茅塞/闭塞/鼻塞/梗塞/阻塞/淤塞/拥塞/哽塞/色 201 | sha#莎/刹车/急刹/厦/杉木/杉篙 202 | shai#色子 203 | shao#勺/红苕 204 | shan#姓单/单县/杉/敾/禅让/受禅/禅变/禅代/禅诰 205 | shang#衣裳 206 | she#拾级/折本/射/蛇 207 | shen#沙参/野参/参王/人参/红参/丹参/山参/海参/鹿参/什么/身/沈/桑椹/食椹/烂椹/木椹 208 | sheng#野乘/千乘/史乘/省/晟/盛/陹/渑水 209 | shi#钥匙/什/识/似的/食/石/氏/拾/适/瑡 210 | shiwa#瓧 211 | shuai#表率/率性/率直/率真/粗率/率领/轻率/直率/草率/大率/坦率/衰 212 | shuang#泷水/鏯 213 | shu#属/数/术/熟 214 | shui#游说 215 | shuo#数见/说 216 | si#伺/似/思 217 | sou#蓃/摗 218 | su#宿/鯂 219 | sui#尿泡 220 | ta#拓片/拓印/拓本/拓墨/拓写/拓手/拓工/碑拓/疲沓/拖沓/杂沓/沓/塔/鸿塔 221 | tang#汤/镗 222 | tao#陶 223 | tan#反弹/弹性/弹簧/弹力/弹奏/弹跳/弹指/弹劾/弹唱/弹射/弹性体/吹弹/评弹/乱弹琴/弹压/弹指/弹簧/弹冠/弹雀/弹雀/弹丝/弹丸/澹台 224 | te#脦 225 | teng#虅 226 | ti#提/体 227 | tiao#调/苕 228 | ting#町/听 229 | tong#通 230 | tu#迌 231 | tuan#湪 232 | tui#褪 233 | tuo#拓/袥 234 | tun#囤/屯 235 | wei#尾/蔚/圩堤/圩垸/圩田/圩子/赶圩/歌圩 236 | weng#攚 237 | wu#无/可恶/交恶/好恶/厌恶/憎恶/嫌恶/痛恶/深恶/兀 238 | wan#藤蔓/枝蔓/根蔓/蔓草/瓜蔓/蔓儿/莞/万/百万/皖 239 | wang#亡 240 | wai#崴 241 | xia#虾/吓/夏/厦门/厦大/唬杀 242 | xi#栖/系/蹊/洗/溪/戏/焁/铣/褶衣/褶裤 243 | xiao#校/切削/削面/刀削/刮削 244 | xian#纤细/光纤/纤巧/纤柔/纤小/纤维/纤瘦/纤纤/化纤/纤秀/棉纤/纤尘/铣铁/金铣 245 | xiang#投降/巷 246 | xie#解数/出血/采血/换血/血糊/尿血/淤血/放血/血晕/血淋/便血/吐血/咯血/叶韵/蝎/蝎子/邪/猲猲 247 | xin#嬜/邤 248 | xiu#铜臭/乳臭/成宿/星宿/璓 249 | xin#馨/信/鸿信 250 | xing#深省/省视/内省/不省人事/省悟/省察/行/荥 251 | xiong#匂 252 | xu#牧畜/畜产/畜牧/畜养/并畜/畜锐/吁/圩/浒 253 | xuan#箮 254 | xue#削/血/樰 255 | xun#荨/寻 256 | ya#琊 257 | yao#钥/耀/曜/佋侥/侥觎/侥僺/侥利/侥傒/侥觊/侥会/侥滥/侥望/侥求/侥竞/侥薄/侥躐/侥取/侥奇/侥忝/侥速/侥冀/侥冒/疟子 258 | yan#咽/殷红/朱殷/腌/烟/曕 259 | ye#液/抽咽/哽咽/咽炎/呜咽/幽咽/悲咽/叶/葉/璍/潱/拽步/拽扶/拽扎 260 | yi#自艾/遗/屹/嬄/噫 261 | yin#殷/栶 262 | ying#荥经/緓/灜 263 | yo#杭育 264 | yong#涌/硧 265 | you#牗 266 | yu#余/呼吁/吁请/吁求/育/熨帖/熨烫/於 267 | yuan#员/茒/圜丘 268 | yun#熨 269 | yue#约/乐音/器乐/乐律/乐章/音乐/乐理/民乐/乐队/声乐/奏乐/弦乐/乐坛/管乐/配乐/乐曲/乐谱/锁钥/密钥/乐团/乐器/嬳/咽哕/唾哕/发哕/干哕/哕吐/哕饭/哕呕/哕息/哕厥/哕噫/哕逆/哕咽/哕骂/哕心/哕喈/口哕/呕哕 270 | za#绑扎/结扎/包扎/捆扎/咱家 271 | zan#攒/咱 272 | zang#宝藏/藏历/藏文/藏语/藏青/藏族/藏医/藏药/藏蓝/西藏 273 | zai#牛仔/龟仔/龙仔/鼻仔/羊仔/仔仔/麻仔/麵包仔/麦旺仔/鸿仔/煲仔/福仔/畠 274 | zao#栆 275 | ze#择 276 | zeng#曾国藩/曾孙/曾祖父/曾祖/曾祖母/曾孙女/曾巩/囎/缯 277 | zong#综/繌 278 | zha#扎/柞狭/柞薪/柞子/柞鄂/柞叶/柞撒/槱柞/一柞/五柞宫/五柞/雠柞/芟柞/蜡祭/喳 279 | zhai#宅/夈/择席/择菜 280 | zhan#粘 281 | zhang#列车长/行长/村长/镇长/乡长/区长/县长/市长/省长/会长/班长/排长/连长/营长/团长/旅长/师长/军长/委员长/局长/厅长/所长/部长/组长/生长/长大/长高/长个/ 282 | zhao#朝朝/明朝/朝晖/朝夕/朝思/今朝/朝气/朝三/朝秦/朝霞/鹰爪/龙爪/魔爪/爪牙/着急/着迷/着火/怎么着/正着/着凉/一着/犯不着/着数/这么着/犯得着/着慌/着忙/数得着/龙爪槐/嘲哳/嘲惹 283 | zhe#折/着/褶 284 | zhen#殝/椹 285 | zhi#标识/吱/殖/枝/方祇/后祇/皇祇/黄祇/皇地祇/金祇/祇树/月氏 286 | zhong#重/种 287 | zhou#粥 288 | zhu#属意/著/駯 289 | zhua#爪子 290 | zhuai#拽 291 | zhuan#芈月传/外传/传记/自传/正传/小传/评传/传略/别传 292 | zhui#椎/隹 293 | zhuo#执著/着装/着落/着意/着力/附着/着笔/胶着/着实/衣着/着眼/着想/着重/穿着/执着/着墨/着实/沉着/着陆/着想/着色/焯见/焯烁/辉焯 294 | zhuang#幢房/一幢/幢楼/庒 295 | zi#仔/兹 296 | zu#足 297 | zuo#柞/穝 298 | -------------------------------------------------------------------------------- /src/test/java/com/mindflow/py4j/PinyinConverterTest.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j; 2 | 3 | import com.mindflow.py4j.exception.IllegalPinyinException; 4 | import org.junit.*; 5 | 6 | import java.util.Arrays; 7 | 8 | /** 9 | * Unit test for simple App. 10 | */ 11 | public class PinyinConverterTest { 12 | private Converter converter; 13 | 14 | @Before 15 | public void init(){ 16 | converter = new PinyinConverter(); 17 | } 18 | 19 | @Test 20 | public void testChinesePy() throws IllegalPinyinException { 21 | 22 | final String[] arr = {"肯德基", "重庆银行", "长沙银行", "便宜坊", "西藏", "藏宝图", "出差", "参加", "列车长"}; 23 | 24 | for (String chinese : arr){ 25 | String py = converter.getPinyin(chinese); 26 | System.out.println(chinese+"\t"+py); 27 | } 28 | } 29 | 30 | @Test 31 | public void testCharPy() throws IllegalPinyinException { 32 | 33 | char[] chs = {'嗯', '长', '行', '藏', '度', '阿', '佛', '2', 'A', 'a'}; 34 | for(char ch : chs){ 35 | String[] arr_py = converter.getPinyin(ch); 36 | System.out.println(ch+"\t"+Arrays.toString(arr_py)); 37 | } 38 | } 39 | 40 | @After 41 | public void destroy(){ 42 | converter = null; 43 | } 44 | } 45 | -------------------------------------------------------------------------------- /src/test/java/com/mindflow/py4j/ThreadSafeTest.java: -------------------------------------------------------------------------------- 1 | package com.mindflow.py4j; 2 | 3 | import java.util.concurrent.Callable; 4 | import java.util.concurrent.ExecutorService; 5 | import java.util.concurrent.Executors; 6 | 7 | /** 8 | * ${DESCRIPTION} 9 | * 10 | * @author Ricky Fung 11 | * @create 2017-02-16 23:57 12 | */ 13 | public class ThreadSafeTest { 14 | 15 | public static void main(String[] args) { 16 | 17 | final String[] arr = {"大夫", "重庆银行", "长沙银行", "便宜坊", "西藏", "藏宝图", "出差", "参加", "列车长"}; 18 | final Converter converter = new PinyinConverter(); 19 | 20 | int threadNum = 20; 21 | ExecutorService pool = Executors.newFixedThreadPool(threadNum); 22 | for(int i=0;i() { 24 | @Override 25 | public Void call() throws Exception { 26 | 27 | System.out.println("thread "+Thread.currentThread().getName()+" start"); 28 | for(int i=0;i<1000;i++){ 29 | converter.getPinyin(arr[i%arr.length]); 30 | } 31 | System.out.println("thread "+Thread.currentThread().getName()+" over"); 32 | return null; 33 | } 34 | }); 35 | } 36 | 37 | pool.shutdown(); 38 | } 39 | } 40 | --------------------------------------------------------------------------------