教新手使用java如何对一个大的文本文件内容进行去重
目录
- 有内存溢出风险的写法:
- 总结
有内存溢出风险的写法:
public static void distinct() { File ff = new File("G://password/all.txt"); File distinctedFile = new File("G://password/all-distinced.txt"); PrintWriter pw = null; Set<String> allHash = null; FileReader fr = null; BufferedReader br = null; try { pw = new PrintWriter(distinctedFile); allHash = new HashSet<String>(); fr = new FileReader(ff); br = new BufferedReader(fr); String line = null; while((line=br.readLine())!=null){ line = line.trim(); if(line != ""){ allHash.add(line); } } } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { try { if(null != fr){ fr.close(); } } catch (IOException e) { e.printStackTrace(); } try { if(null != br){ br.close(); } } catch (IOException e) { e.printStackTrace(); } } for(String s:allHash){ pw.println(s); } pw.close(); }
jvm内存溢出:
Exception in thread "main" java.lang.OutOfMemoryError: GC overhead limit exceeded at java.util.HashMap.newNode(HashMap.java:1734) at java.util.HashMap.putVal(HashMap.java:630) at java.util.HashMap.put(HashMap.java:611) at java.util.HashSet.add(HashSet.java:219) at encode.Main.distinct(Main.java:180) at encode.Main.main(Main.java:215)
通过hashCode取模拆分写法:
import java.io.BufferedReader; import java.io.File; import java.io.FileNotFoundException; import java.io.FileReader; import java.io.IOException; import java.io.PrintWriter; import java.util.HashSet; import java.util.Set; public class DistinctFileUtil { /** * 将文件hash取模之后放到不同的小文件中 * @param targetFile 要去重的文件路径 * @param splitSize 将目标文件切割成多少份hash取模的小文件个数 * @return */ public static File[] splitFile(String targetFile,int splitSize){ File file = new File(targetFile); BufferedReader reader = null; PrintWriter[] pws = new PrintWriter[splitSize]; File[] littleFiles = new File[splitSize]; String parentPath = file.getParent(); File tempFolder = new File(parentPath + File.separator + "test"); if(!tempFolder.exists()){ tempFolder.mkdir(); } for(int i=0;i<splitSize;i++){ littleFiles[i] = new File(tempFolder.getAbsolutePath() + File.separator + i + ".txt"); if(littleFiles[i].exists()){ littleFiles[i].delete(); } try { pws[i] = new PrintWriter(littleFiles[i]); } catch (FileNotFoundException e) { e.printStackTrace(); } } try { reader = new BufferedReader(new FileReader(file)); String tempString = null; while ((tempString = reader.readLine()) != null) { tempString = tempString.trim(); if(tempString != ""){ //关键是将每行数据hash取模之后放到对应取模值的文件中,确保hash值相同的字符串都在同一个文件里面 int index = Math.abs(tempString.hashCode() % splitSize); pws[index].println(tempString); } } } catch (Exception e) { e.printStackTrace(); } finally { if (reader != null) { try { reader.close(); } catch (IOException e1) { e1.printStackTrace(); } } for(int i=0;i<splitSize;i++){ if(pws[i] != null){ pws[i].close(); } } } return littleFiles; } /** * 对小文件进行去重合并 * @param littleFiles 切割之后的小文件数组 * @param distinctFilePath 去重之后的文件路径 * @param splitSize 小文件大小 */ public static void distinct(File[] littleFiles,String distinctFilePath,int splitSize){ File distinctedFile = new File(distinctFilePath); FileReader[] frs = new FileReader[splitSize]; BufferedReader[] brs = new BufferedReader[splitSize]; PrintWriter pw = null; try { if(distinctedFile.exists()){ distinctedFile.delete(); } distinctedFile.createNewFile(); pw = new PrintWriter(distinctedFile); Set<String> unicSet = new HashSet<String>(); for(int i=0;i<splitSize;i++){ if(littleFiles[i].exists()){ System.out.println("开始对小文件:" + littleFiles[i].getName() + "去重"); frs[i] = new FileReader(littleFiles[i]); brs[i] = new BufferedReader(frs[i]); String line = null; while((line = brs[i].readLine())!=null){ if(line != ""){ unicSet.add(line); } } for(String s:unicSet){ pw.println(s); } unicSet.clear(); System.gc(); } } } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e1){ e1.printStackTrace(); } finally { for(int i=0;i<splitSize;i++){ try { if(null != brs[i]){ brs[i].close(); } if(null != frs[i]){ frs[i].close(); } } catch (IOException e) { e.printStackTrace(); } //合并完成之后删除临时小文件 if(littleFiles[i].exists()){ littleFiles[i].delete(); } } if(null != pw){ pw.close(); } } } public static void main(String[] args) throws IOException { int splitSize = 20; File[] files = splitFile("G://test/bigfile.txt",splitSize); distinct(files,"G://test/bigfile-distinct.txt",splitSize); } }
总结
本篇文章的内容就到这了,希望大家可以喜欢,也希望大家可以多多关注我们的其他精彩内容!
赞 (0)