一个从源代码里提取中文字符串的java类

工作中需要优化代码里的中文警示语和异常信息，实在比较多，所以就写了个程序专门从代码里提取中文字符串。

java做的，比较简单，放上来备忘

        package com.extractstr.app;

import java.io.*;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * 搜索字符串并输出到控制台
 */
public class ExtractStr {
    public static String getHelpString(String[] args){
        String result = String.format("%s [path]", new Object[]{"a"});
        return result;
    }

    private void getFiles(String rootPath, final String fileExt, List<File> fileList){
        File f =new File(rootPath);
        File[] list=f.listFiles(new FileFilter() {
            @Override
            public boolean accept(File f) {
                boolean ret = f.isDirectory() || (f.isFile() && f.getName().endsWith(fileExt));
                return ret;
            }
        });
        for(File fn : list){
            if (fn.isDirectory()){
                this.getFiles(fn.getAbsolutePath(), fileExt, fileList);
            }else{
                fileList.add(fn);
            }
        }
    }

    public List<File> run(String rootPath, String fileExt){
        List<File> result = new LinkedList<File>();
        this.getFiles(rootPath, fileExt, result);
        return result;
    }

    public List<String> parserSourceFile(List<String> patternList, File file, int miniCharCount) throws Exception {
        List<String> result = new LinkedList<String>();
        BufferedReader r = new BufferedReader(new FileReader(file));
        char[] buffer = new char[(int)file.length()];
        r.read(buffer, 0, (int)file.length());
        String text=new String(buffer, 0, buffer.length);

        for(String patternStr : patternList){
            //Pattern pattern = Pattern.compile("\"(.*?)\"");
            Pattern pattern = Pattern.compile(patternStr);
            Matcher matchers= pattern.matcher(text);
            while(matchers.find()){
                String t=matchers.group();
                if (t.length()>=miniCharCount)
                    result.add(t);
            }
        }
        return result;
    }

    public static void main(String []args){
        if (args.length==0){
            StringBuilder sb = new StringBuilder()
                    .append("未传入需要搜索的有效的源代码路径")
                    .append("\n")
                    .append(ExtractStr.getHelpString(args));
            System.out.println(sb.toString());
            System.exit(1);
        }
        List<String> searchFolders=new ArrayList<String>(100);
        for(int i=0; i<=args.length-1;i++){
            File f=new File(args[i]);
            if (!f.isDirectory() || !f.exists())
                continue;
            searchFolders.add(f.getAbsolutePath());
        }

        List<String> patternList = new LinkedList<String>();
        patternList.add("‘([\\u4E00-\\u9FA5]+)‘");
        patternList.add("\"([\\u4E00-\\u9FA5]+)\"");

        ExtractStr es = new ExtractStr();
        List<File> fileList = new ArrayList<File>(1000);
        for(String sarchFolder : searchFolders){
            List<File> t=es.run(sarchFolder, ".php");
            fileList.addAll(t);
        }

        Set<String> outList=new HashSet<String>();
        for(File f : fileList){
            try{
                List<String> items=es.parserSourceFile(patternList, f, 12);
                outList.addAll(items);
            }catch(Exception e){
                e.printStackTrace();
            }
        }
        for(String str : outList){
            System.out.println(str);
        }
    }
}

    

对于拼接字符串的中文输出支持的不算好，而且也对中文的长度有限制（最少12个字符）

原文：http://my.oschina.net/jim19770812/blog/467598