├── .gitignore ├── LICENSE ├── pom.xml └── src ├── main └── java │ └── cn │ └── dyz │ └── tools │ └── file │ ├── BigFileReader.java │ ├── IHandle.java │ └── Main.java └── test └── java └── cn └── dyz └── tools └── AppTest.java /.gitignore: -------------------------------------------------------------------------------- 1 | *.class 2 | 3 | # Mobile Tools for Java (J2ME) 4 | .mtj.tmp/ 5 | 6 | # Package Files # 7 | *.jar 8 | *.war 9 | *.ear 10 | 11 | # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml 12 | hs_err_pid* 13 | .settings/ 14 | target/ 15 | .classpath 16 | .project 17 | -------------------------------------------------------------------------------- /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 | 203 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 3 | 4.0.0 4 | 5 | cn.dyz.tools 6 | ToolClass 7 | 0.0.1-SNAPSHOT 8 | jar 9 | 10 | ToolClass 11 | http://maven.apache.org 12 | 13 | 14 | UTF-8 15 | 16 | 17 | 18 | 19 | junit 20 | junit 21 | 3.8.1 22 | test 23 | 24 | 25 | 26 | -------------------------------------------------------------------------------- /src/main/java/cn/dyz/tools/file/BigFileReader.java: -------------------------------------------------------------------------------- 1 | package cn.dyz.tools.file; 2 | 3 | import java.io.ByteArrayOutputStream; 4 | import java.io.File; 5 | import java.io.FileNotFoundException; 6 | import java.io.IOException; 7 | import java.io.RandomAccessFile; 8 | import java.io.UnsupportedEncodingException; 9 | import java.nio.MappedByteBuffer; 10 | import java.nio.channels.FileChannel.MapMode; 11 | import java.util.HashSet; 12 | import java.util.Set; 13 | import java.util.concurrent.CyclicBarrier; 14 | import java.util.concurrent.ExecutorService; 15 | import java.util.concurrent.Executors; 16 | import java.util.concurrent.atomic.AtomicLong; 17 | 18 | public class BigFileReader { 19 | private int threadSize; 20 | private String charset; 21 | private int bufferSize; 22 | private IHandle handle; 23 | private ExecutorService executorService; 24 | private long fileLength; 25 | private RandomAccessFile rAccessFile; 26 | private Set startEndPairs; 27 | private CyclicBarrier cyclicBarrier; 28 | private AtomicLong counter = new AtomicLong(0); 29 | 30 | private BigFileReader(File file,IHandle handle,String charset,int bufferSize,int threadSize){ 31 | this.fileLength = file.length(); 32 | this.handle = handle; 33 | this.charset = charset; 34 | this.bufferSize = bufferSize; 35 | this.threadSize = threadSize; 36 | try { 37 | this.rAccessFile = new RandomAccessFile(file,"r"); 38 | } catch (FileNotFoundException e) { 39 | e.printStackTrace(); 40 | } 41 | this.executorService = Executors.newFixedThreadPool(threadSize); 42 | startEndPairs = new HashSet(); 43 | } 44 | 45 | public void start(){ 46 | long everySize = this.fileLength/this.threadSize; 47 | try { 48 | calculateStartEnd(0, everySize); 49 | } catch (IOException e) { 50 | e.printStackTrace(); 51 | return; 52 | } 53 | 54 | final long startTime = System.currentTimeMillis(); 55 | cyclicBarrier = new CyclicBarrier(startEndPairs.size(),new Runnable() { 56 | 57 | @Override 58 | public void run() { 59 | System.out.println("use time: "+(System.currentTimeMillis()-startTime)); 60 | System.out.println("all line: "+counter.get()); 61 | } 62 | }); 63 | for(StartEndPair pair:startEndPairs){ 64 | System.out.println("分配分片："+pair); 65 | this.executorService.execute(new SliceReaderTask(pair)); 66 | } 67 | } 68 | 69 | private void calculateStartEnd(long start,long size) throws IOException{ 70 | if(start>fileLength-1){ 71 | return; 72 | } 73 | StartEndPair pair = new StartEndPair(); 74 | pair.start=start; 75 | long endPosition = start+size-1; 76 | if(endPosition>=fileLength-1){ 77 | pair.end=fileLength-1; 78 | startEndPairs.add(pair); 79 | return; 80 | } 81 | 82 | rAccessFile.seek(endPosition); 83 | byte tmp =(byte) rAccessFile.read(); 84 | while(tmp!='\n' && tmp!='\r'){ 85 | endPosition++; 86 | if(endPosition>=fileLength-1){ 87 | endPosition=fileLength-1; 88 | break; 89 | } 90 | rAccessFile.seek(endPosition); 91 | tmp =(byte) rAccessFile.read(); 92 | } 93 | pair.end=endPosition; 94 | startEndPairs.add(pair); 95 | 96 | calculateStartEnd(endPosition+1, size); 97 | 98 | } 99 | 100 | 101 | 102 | public void shutdown(){ 103 | try { 104 | this.rAccessFile.close(); 105 | } catch (IOException e) { 106 | e.printStackTrace(); 107 | } 108 | this.executorService.shutdown(); 109 | } 110 | private void handle(byte[] bytes) throws UnsupportedEncodingException{ 111 | String line = null; 112 | if(this.charset==null){ 113 | line = new String(bytes); 114 | }else{ 115 | line = new String(bytes,charset); 116 | } 117 | if(line!=null && !"".equals(line)){ 118 | this.handle.handle(line); 119 | counter.incrementAndGet(); 120 | } 121 | } 122 | private static class StartEndPair{ 123 | public long start; 124 | public long end; 125 | 126 | @Override 127 | public String toString() { 128 | return "star="+start+";end="+end; 129 | } 130 | 131 | @Override 132 | public int hashCode() { 133 | final int prime = 31; 134 | int result = 1; 135 | result = prime * result + (int) (end ^ (end >>> 32)); 136 | result = prime * result + (int) (start ^ (start >>> 32)); 137 | return result; 138 | } 139 | 140 | @Override 141 | public boolean equals(Object obj) { 142 | if (this == obj) 143 | return true; 144 | if (obj == null) 145 | return false; 146 | if (getClass() != obj.getClass()) 147 | return false; 148 | StartEndPair other = (StartEndPair) obj; 149 | if (end != other.end) 150 | return false; 151 | if (start != other.start) 152 | return false; 153 | return true; 154 | } 155 | 156 | } 157 | private class SliceReaderTask implements Runnable{ 158 | private long start; 159 | private long sliceSize; 160 | private byte[] readBuff; 161 | /** 162 | * @param start read position (include) 163 | * @param end the position read to(include) 164 | */ 165 | public SliceReaderTask(StartEndPair pair) { 166 | this.start = pair.start; 167 | this.sliceSize = pair.end-pair.start+1; 168 | this.readBuff = new byte[bufferSize]; 169 | } 170 | 171 | @Override 172 | public void run() { 173 | try { 174 | MappedByteBuffer mapBuffer = rAccessFile.getChannel().map(MapMode.READ_ONLY,start, this.sliceSize); 175 | ByteArrayOutputStream bos = new ByteArrayOutputStream(); 176 | for(int offset=0;offset0){ 195 | handle(bos.toByteArray()); 196 | } 197 | cyclicBarrier.await();//测试性能用 198 | }catch (Exception e) { 199 | e.printStackTrace(); 200 | } 201 | } 202 | 203 | } 204 | 205 | public static class Builder{ 206 | private int threadSize=1; 207 | private String charset=null; 208 | private int bufferSize=1024*1024; 209 | private IHandle handle; 210 | private File file; 211 | public Builder(String file,IHandle handle){ 212 | this.file = new File(file); 213 | if(!this.file.exists()) 214 | throw new IllegalArgumentException("文件不存在！"); 215 | this.handle = handle; 216 | } 217 | 218 | public Builder withTreahdSize(int size){ 219 | this.threadSize = size; 220 | return this; 221 | } 222 | 223 | public Builder withCharset(String charset){ 224 | this.charset= charset; 225 | return this; 226 | } 227 | 228 | public Builder withBufferSize(int bufferSize){ 229 | this.bufferSize = bufferSize; 230 | return this; 231 | } 232 | 233 | public BigFileReader build(){ 234 | return new BigFileReader(this.file,this.handle,this.charset,this.bufferSize,this.threadSize); 235 | } 236 | } 237 | 238 | 239 | } 240 | -------------------------------------------------------------------------------- /src/main/java/cn/dyz/tools/file/IHandle.java: -------------------------------------------------------------------------------- 1 | package cn.dyz.tools.file; 2 | 3 | public interface IHandle { 4 | 5 | public void handle(String line); 6 | } 7 | -------------------------------------------------------------------------------- /src/main/java/cn/dyz/tools/file/Main.java: -------------------------------------------------------------------------------- 1 | package cn.dyz.tools.file; 2 | 3 | public class Main { 4 | 5 | public static void main(String[] args) { 6 | BigFileReader.Builder builder = new BigFileReader.Builder("d:/reliability.txt",new IHandle() { 7 | 8 | @Override 9 | public void handle(String line) { 10 | //System.out.println(line); 11 | //increat(); 12 | } 13 | }); 14 | builder.withTreahdSize(10) 15 | .withCharset("gbk") 16 | .withBufferSize(1024*1024); 17 | BigFileReader bigFileReader = builder.build(); 18 | bigFileReader.start(); 19 | } 20 | 21 | } 22 | -------------------------------------------------------------------------------- /src/test/java/cn/dyz/tools/AppTest.java: -------------------------------------------------------------------------------- 1 | package cn.dyz.tools; 2 | 3 | import junit.framework.Test; 4 | import junit.framework.TestCase; 5 | import junit.framework.TestSuite; 6 | 7 | /** 8 | * Unit test for simple App. 9 | */ 10 | public class AppTest 11 | extends TestCase 12 | { 13 | /** 14 | * Create the test case 15 | * 16 | * @param testName name of the test case 17 | */ 18 | public AppTest( String testName ) 19 | { 20 | super( testName ); 21 | } 22 | 23 | /** 24 | * @return the suite of tests being tested 25 | */ 26 | public static Test suite() 27 | { 28 | return new TestSuite( AppTest.class ); 29 | } 30 | 31 | /** 32 | * Rigourous Test :-) 33 | */ 34 | public void testApp() 35 | { 36 | assertTrue( true ); 37 | } 38 | } 39 | --------------------------------------------------------------------------------