最近喜欢上高品质音乐了，但是cue很多抓下来是繁体中文，看上去略不爽。大陆的windows都是用的GBK编码，准备拿来转码一下。分三步。
第一步，下载GBK中文字库。放到wps里，然后进行繁简体转换，得到繁简对应。放到txt文件中，使用ANSI编码。
第二步，对字库进行预处理。包括两部分：去重，排序。
去重指把繁简体相同的字符去掉。
代码：
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
/*
* @author GT
* find the different characters in two files
* 2013.1.17
* */
public class FindDifferent {
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub
System.out.println(System.getProperty("file.encoding"));
if (args.length != 2) {
System.err.println("not enough files");
return;
} else {
BufferedReader br1 = new BufferedReader(new FileReader(args[0]));
BufferedReader br2 = new BufferedReader(new FileReader(args[1]));
BufferedWriter bw1 = new BufferedWriter(new FileWriter("d"
+ args[0]));
BufferedWriter bw2 = new BufferedWriter(new FileWriter("d"
+ args[1]));
String line1 = null;
String line2 = null;
while ((line1 = br1.readLine()) != null
&& (line2 = br2.readLine()) != null) {
line1 = line1.trim();
line2 = line2.trim();
if (line1.length() != line2.length()) {
System.err.println("not same length " + line1.length()
+ " " + line2.length());
continue;
} else {
for (int i = 0; i < line1.length(); ++i) {
if (line1.charAt(i) != line2.charAt(i)) {
bw1.append(line1.charAt(i));
bw2.append(line2.charAt(i));
}
}
}
}
bw1.flush();
bw2.flush();
br1.close();
br2.close();
bw1.close();
bw2.close();
}
}
}
转好的文件已经上传，地址：http://download.csdn.net/detail/pouloghost/5005734
排序使用堆排，需要对繁简体两个文件进行相同操作，以保证对应。代码
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
/*
* @author GT
* sort the characters in ascending order
* from trad.txt simp.txt to traditional.txt simple.txt
* 2013.1.17
* */
public class SortFile {
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub
BufferedReader br = new BufferedReader(new FileReader("trad.txt"));
StringBuffer trad = new StringBuffer(br.readLine());
br.close();
br = new BufferedReader(new FileReader("simp.txt"));
StringBuffer simp = new StringBuffer(br.readLine());
br.close();
buildHeap(trad, simp);
// System.out.println(trad);
int size = trad.length();
for (int i = trad.length() - 1; i > 0; --i) {
exchange(trad, simp, 0, i);
--size;
maxHeapify(trad, simp, 0, size);
}
System.out.println("traditional in order " + check(trad));
// System.out.println(trad);
// System.out.println(check(simp));
FileWriter fr = new FileWriter("traditional.txt");
fr.write(trad.toString());
fr.flush();
fr.close();
fr = new FileWriter("simple.txt");
fr.write(simp.toString());
fr.flush();
fr.close();
}
private static void maxHeapify(StringBuffer trad, StringBuffer simp, int i,
int size) {
int left = 2 * i + 1;
int right = 2 * i + 2;
int max = i;
if (left < size && ((int) trad.charAt(i) < (int) trad.charAt(left))) {
max = left;
}
if (right < size && ((int) trad.charAt(max) < (int) trad.charAt(right))) {
max = right;
}
if (max != i) {
exchange(trad, simp, i, max);
maxHeapify(trad, simp, max, size);
}
}
private static void exchange(StringBuffer trad, StringBuffer simp, int a,
int b) {
char tradTemp = trad.charAt(a);
char simpTemp = simp.charAt(a);
trad.setCharAt(a, trad.charAt(b));
simp.setCharAt(a, simp.charAt(b));
trad.setCharAt(b, tradTemp);
simp.setCharAt(b, simpTemp);
}
private static void buildHeap(StringBuffer trad, StringBuffer simp) {
for (int i = trad.length() / 2; i > -1; --i) {
maxHeapify(trad, simp, i, trad.length());
}
}
private static boolean check(StringBuffer trad) {
boolean res = true;
for (int i = 0; i < trad.length() - 1; ++i) {
if ((int) trad.charAt(i) > (int) trad.charAt(i + 1)) {
System.out.println(i);
res = false;
break;
}
}
return res;
}
}
第三步，使用繁简体对应表，处理文件。代码
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
/*
* @author GT
* change all tradition Chinese in the file and store the simplified version in simple+filename
* all encoded by GBK
* 2013.1.17
* */
public class Main {
static String traditional = null;
static String simple = null;
/**
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub
if (args.length != 1) {
System.err.println("not enough files");
return;
} else {
// initial
initial();
//
BufferedReader br = new BufferedReader(new FileReader(args[0]));
BufferedWriter bw = new BufferedWriter(new FileWriter("simple"
+ args[0]));
String line = null;
while ((line = br.readLine()) != null) {
simplify(line, bw);
bw.newLine();
}
bw.flush();
br.close();
bw.close();
}
}
private static void initial() throws IOException {
BufferedReader br = new BufferedReader(
new FileReader("traditional.txt"));
traditional = br.readLine();
br.close();
br = new BufferedReader(new FileReader("simple.txt"));
simple = br.readLine();
br.close();
// for (int i = 0; i < 100; ++i) {
// System.out.printf("%d ", (int) tradition.charAt(i));
// }
}
private static void simplify(String line, BufferedWriter bw)
throws IOException {
// TODO Auto-generated method stub
int index = -1;
for (int i = 0; i < line.length(); ++i) {
if ((index = find(line.charAt(i))) != -1) {
bw.append(simple.charAt(index));
} else {
bw.append(line.charAt(i));
}
}
}
/*
* binary search 2013.1.18
*/
private static int find(char ch) {
// TODO Auto-generated method stub
int low, high, mid, res;
low = 0;
high = traditional.length();
res = -1;
while (low <= high) {
mid = (low + high) / 2;
if (traditional.charAt(mid) == ch) {
res = mid;
break;
} else {
if ((int) traditional.charAt(mid) < (int) ch) {
low = mid + 1;
} else {
high = mid - 1;
}
}
}
return res;
// return tradition.indexOf(ch);
}
}