Skip to content

Instantly share code, notes, and snippets.

@AvatarQing

AvatarQing/AndroidStringXmlParser

Last active January 3, 2016 23:29
Show Gist options
  • Save AvatarQing/8535604 to your computer and use it in GitHub Desktop.
Save AvatarQing/8535604 to your computer and use it in GitHub Desktop.
Download ZIP
以Http Post方式调用谷歌翻译接口。支持翻译文本文件。需要引入HttpClient4包。解决HTML特殊字符编码问题http://blog.csdn.net/lonfee88/article/details/8642584
Raw
AndroidStringXmlParser
package translate;
import java.io.File;
import java.util.ArrayList;
import java.util.List;
import java.util.Map.Entry;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class AndroidStringXmlParser {
/** 左分隔符 */
public static final String DIVIDER_LEFT = "[[[";
/** 右分隔符 */
public static final String DIVIDER_RIGHT = "]]]";
/** 匹配诸如<string name = "xxx" >yyy</string >的字符串 */
private static String mStringTagRegExp = "(<string\\s+name\\s*=\\s*\"\\w+\"\\s*>)([\\s\\S]*?)(</string\\s*>)";
// private static String mDividerRegExp =
// "[\\(|（]{3}([\\s\\S]*?)[）|\\)]{3}";
private static String mDividerRegExp = "\\[\\s*?\\[\\s*?\\[\\s*?([\\s\\S]*?)\\]\\s*\\]\\s*\\]\\s*?";
/**
* 从string.xml中解析出<string>标记间的内容
*
* @param xmlText
* string.xml的整个文本内容
*/
public static String parseTextFromStringTag(String xmlText) {
// 最终文本
StringBuilder finalText = new StringBuilder();
// 匹配正则表达式
Matcher matcher = Pattern.compile(mStringTagRegExp).matcher(xmlText);
while (matcher.find()) {
// 截取<string></string>标记中间的内容
finalText.append(DIVIDER_LEFT + matcher.group(2) + DIVIDER_RIGHT);
}
System.out.println(finalText.toString() + "\n"
+ "^^^^^^^^^^^^^^^^^^^^^^^^^");
// 返回最终结果
return finalText.toString();
}
/**
* 按分隔符切割文本，生成为string.xml的格式内容
*
* @param xmlText
* 原来的string.xml
* @param text
* 待切割的文本
*/
public static String convertTextToStringTag(String xmlText, String text) {
String finalText = null;
if (xmlText != null && text != null) {
// 临时变量声明
int i = 0;
String tagStart = null;
String tagEnd = null;
finalText = new String(xmlText);
List<String> contents = new ArrayList<String>();
System.out.println(text + "\n" + "!!!!!!!!!!!!!!!!!!!!");
// 分割出各个string标签的内容
// 匹配正则表达式
Matcher matcherForDivider = Pattern.compile(mDividerRegExp)
.matcher(text);
while (matcherForDivider.find()) {
System.out.println(matcherForDivider.group(0) + "\n"
+ "============");
contents.add(matcherForDivider.group(1));
}
// 匹配正则表达式
Matcher matcherForStringTag = Pattern.compile(mStringTagRegExp)
.matcher(xmlText);
while (matcherForStringTag.find() && i < contents.size()) {
// 替换<string></string>标记中间的内容
tagStart = matcherForStringTag.group(1);
tagEnd = matcherForStringTag.group(3);
System.out.println(matcherForStringTag.group(0) + "\n"
+ tagStart + contents.get(i) + tagEnd + "\n"
+ "-------------");
finalText = finalText.replaceFirst(
matcherForStringTag.group(0),
tagStart + contents.get(i) + tagEnd);
i++;
}
}
return finalText;
}
/** 翻译strings.xml各节点的内容，重新生成strings.xml */
public static void translateStringXml(String originalLaunguage,
String destLaunguage, String destPath, String rawText,
String trimmedText) {
final String fileName = "strings.xml";
final String subDirNamePattern = "values-%s";
String subDirName = null;
String finalSaveDir = null;
// 生成目录名
subDirName = String.format(subDirNamePattern, destLaunguage);
// 最终保存路径
finalSaveDir = destPath + File.separator + subDirName + File.separator
+ fileName;
// 调用翻译接口
String transText = GoogleTranslate.translate(trimmedText,
originalLaunguage, destLaunguage);
// 处理翻译后的文本，格式化为需要的格式
String finalText = AndroidStringXmlParser.convertTextToStringTag(
rawText, transText);
// 将翻译出的文本保存到目标路径
FileUtils.writeStringToFile(finalText, finalSaveDir);
}
/** 将指定文件文本翻译为多国语言 */
public static void translateToMultipleLaunguage(String originalLaunguage,
String originalPath, String destPath) {
String destLaunguage = null;
// 读取源文本
String rawText = FileUtils.readStringFromFile(originalPath);
// 截取所要翻译的片段
String trimmedText = AndroidStringXmlParser
.parseTextFromStringTag(rawText);
// 获取所有语言的编码集合
Set<Entry<String, String>> allLanguageEntries = Language.LANGUAGE
.entrySet();
for (Entry<String, String> entry : allLanguageEntries) {
// 获取某一个语言编码代号
destLaunguage = entry.getValue();
translateStringXml(originalLaunguage, destLaunguage, destPath,
rawText, trimmedText);
}
}
}
Raw
Decorder
package translate;
public class Decorder {
/** 将html特殊字符编码转化为正常显示的字符 */
public static String encodeCesToChars(String paramStr) {
paramStr = paramStr.replace("&nbsp;", " ").replace("&lt;", "<")
.replace("&gt;", ">").replace("&amp;", "&")
.replace("&quot;", "\"").replace("&apos;", "'");
return new String(paramStr);
}
}
Raw
FileUtils
package translate;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
public class FileUtils {
public static final String ENCODING = "utf-8";
/**
* 从指定文件读出文本字符串
*
* @param path
* 文件路径
*/
public static String readStringFromFile(String path) {
String result = null;
if (path != null) {
File file = new File(path);
if (file.exists()) {
BufferedReader br = null;
try {
br = new BufferedReader(new InputStreamReader(
new FileInputStream(file), ENCODING));
String temp = null;
StringBuilder sb = new StringBuilder();
while ((temp = br.readLine()) != null) {
sb.append(temp);
}
result = sb.toString();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (br != null) {
try {
br.close();
System.out.println("Succeeded to read text from "
+ path);
} catch (IOException e) {
e.printStackTrace();
br = null;
}
}
}
}
}
return result;
}
/**
* 将文本字符串写到一个指定的文件中
*
* @param text
* 欲写入的文本字符串
* @param path
* 保存的文件路径
*
*/
public static void writeStringToFile(String text, String path) {
if (path != null) {
File file = new File(path);
if (file.getParentFile() != null) {
file.getParentFile().mkdirs();
}
BufferedWriter bw = null;
try {
bw = new BufferedWriter(new OutputStreamWriter(
new FileOutputStream(file), ENCODING));
bw.write(text);
} catch (IOException e) {
e.printStackTrace();
} finally {
if (bw != null) {
try {
bw.close();
System.out
.println("Succeeded to write text to " + path);
} catch (IOException e) {
e.printStackTrace();
bw = null;
System.out.println("Failed to write text to " + path);
}
}
}
}
}
}
Raw
GoogleTranslate
package translate;
/**
* 原文：http://ahomeeye.javaeye.com/blog/841298
* 需要引入HttpClient4包
* @author ahomeeye
* @modifer Avatar Qing
*/
import java.net.URLEncoder;
import java.util.ArrayList;
import java.util.List;
import org.apache.http.HttpResponse;
import org.apache.http.NameValuePair;
import org.apache.http.client.entity.UrlEncodedFormEntity;
import org.apache.http.client.methods.HttpPost;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.message.BasicNameValuePair;
import org.apache.http.protocol.HTTP;
import org.apache.http.util.EntityUtils;
public class GoogleTranslate {
private static final String UTF_8 = "UTF-8";
private static HttpPost httppost;
private static HttpResponse response;
private static final DefaultHttpClient httpclient = new DefaultHttpClient();
public static String encode(String value, String charset) {
try {
return URLEncoder.encode(value, charset);
} catch (Exception e) {
e.printStackTrace();
return null;
}
}
/*
* @param text 翻译原文
*
* @param lanFrom 源语言
*
* @param lanTo 目标语言
*
* @return 翻译后的字符串
*/
public static String translate(String text, String lanFrom, String lanTo) {
List<NameValuePair> qparams = new ArrayList<NameValuePair>();
qparams.add(new BasicNameValuePair("client", "t"));
qparams.add(new BasicNameValuePair("hl", "en"));
qparams.add(new BasicNameValuePair("ie", UTF_8));
qparams.add(new BasicNameValuePair("oe", UTF_8));
qparams.add(new BasicNameValuePair("sl", lanFrom));
qparams.add(new BasicNameValuePair("text", text));
qparams.add(new BasicNameValuePair("tl", lanTo));
// HttpClient提交post请求
httppost = new HttpPost("http://translate.google.com/translate_t#");
String cookie = "Cookie PREF=ID=8daa1f767f10d1fe:U=f5ac701cf7d3f2e0:FF=0:LD=en:CR=2:TM=1277174286:LM=1289370601:S=q7yslRWEZs3uK1H8; NID=39=UO-TWo9HzzjHc-d_wYm7BVR1cH33KpqaN5h5877_i29nERA93FeG1GSuV3ZSvsOx8D-TnHKpB9m0KhZRH8U9uPwoE-arYd0bAyAlILyXZxLO2_TyGQhJpcMiOLVEuCpq; SID=DQAAAHoAAADMlGzeKhnGkbkIJ36tVO0ZPXgmQ6Cth7Oa6geyyE1WJooW8P01uKUHNrsRkjggvFMAWIWB9J5i18z0F6GjC_oV79mSwXEDGuRFGhRnDyJdid3ptjFW0pIyt4_2D6AMIqtOWF71aWdvY7IvAU1AWMNs8fBZHAOgRqtf3aCUkr36ZA; HSID=A6-YJTnhjBdFWukoR";
httppost.addHeader("Cookie", cookie);
String responseBody = "";
String content = "";
try {
// 将参数封装到post数据包中
httppost.setEntity(new UrlEncodedFormEntity(qparams, HTTP.UTF_8));
response = httpclient.execute(httppost);
responseBody = EntityUtils.toString(response.getEntity());
// 过滤出所需翻译后的内容
int tmp1 = responseBody.indexOf("result_box");
int tmp2 = responseBody.indexOf(">", tmp1);
int tmp3 = responseBody.indexOf("</div>", tmp2);
// 替换换行符和其他网页标签
String htmlTagRegExp = "<[^>]*>";
content = responseBody.substring(tmp2 + 1, tmp3)
.replaceAll("<br>", "\n").replaceAll(htmlTagRegExp, "");
content = Decorder.encodeCesToChars(content);
} catch (Exception e) {
return content;
} finally {
httppost.abort();
}
return content;
}
/*
* 重载上面的translate()方法，实现文本数组的翻译
*/
public static String[] translate(String[] text, String lanFrom, String lanTo) {
if (text == null || text.length < 1) {
return null;
}
StringBuilder sb = new StringBuilder();
for (int i = 0; i < text.length; i++) {
if (i < text.length - 1) {
sb.append(text[i]).append("BBaaBB");
} else {
sb.append(text[i]);
}
}
return translate(sb.toString(), lanFrom, lanTo).split("BBaaBB");
}
public static void main(String[] args) {
// testTranslateString();
// testTranslateTextFile(args);
testTranslateAndroidStringXml(args);
}
private static void testTranslateAndroidStringXml(String[] args) {
// TEST
args = new String[] { "f:\\strings.xml", "f:\\test" };
// 源语言
String originalLaunguage = null;
// 目标语言
// String destLaunguage = null;
String destLaunguage = "en";
// 源文件路径
String originalPath = args[0];
// 目标文件路径
String destPath = args[1];
AndroidStringXmlParser.translateToMultipleLaunguage(originalLaunguage,
originalPath, destPath);
// TEST
// String rawText = FileUtils.readStringFromFile(originalPath);
// String trimmedText = AndroidStringXmlParser
// .parseTextFromStringTag(rawText);
// AndroidStringXmlParser.translateStringXml(originalLaunguage,
// destLaunguage, destPath, rawText, trimmedText);
}
private static void testTranslateTextFile(String[] args) {
// 源语言
String originalLaunguage = args[0];
// 目标语言
String destLaunguage = args[1];
// 源文件路径
String originalPath = args[2];
// 目标文件路径
String destPath = args[3];
// 原始文本
String originalText = FileUtils.readStringFromFile(originalPath);
// 目标文本
String destText = translate(originalText, originalLaunguage,
destLaunguage);
FileUtils.writeStringToFile(destText, destPath);
}
private static void testTranslateString() {
String text = "乐盟软件管家☆这是一张图片☆应用推荐";
String tranText = GoogleTranslate.translate(text, "zh-CN", "ja");
System.out.println("tranText=" + tranText);
// String[] arrayText = { "我来自广东梅州。", "我爱你，梅州！" };
// String[] tranArray = GoogleTranslate
// .translate(arrayText, "zh-CN", "en");
// for (int i = 0; i < tranArray.length; i++) {
// System.out.println("tranArray[" + i + "]=" + tranArray[i]);
// }
}
}
Raw
Language
package translate;
import java.util.HashMap;
import java.util.Map;
public class Language {
/**
* Key -> Value 语言 -> 单词表示
*/
public static final Map<String, String> LANGUAGE = new HashMap<String, String>();
static {
LANGUAGE.put("阿尔巴尼亚语", "sq");
LANGUAGE.put("阿拉伯语", "ar");
LANGUAGE.put("阿塞拜疆语", "az");
LANGUAGE.put("爱尔兰语", "ga");
LANGUAGE.put("爱沙尼亚语", "et");
LANGUAGE.put("巴斯克语", "eu");
LANGUAGE.put("白俄罗斯语", "be");
LANGUAGE.put("保加利亚语", "bg");
LANGUAGE.put("冰岛语", "is");
LANGUAGE.put("波兰语", "pl");
LANGUAGE.put("波斯语", "fa");
LANGUAGE.put("布尔语", "af");
LANGUAGE.put("南非荷兰语", "af");
LANGUAGE.put("丹麦语", "da");
LANGUAGE.put("德语", "de");
LANGUAGE.put("俄语", "ru");
LANGUAGE.put("法语", "fr");
LANGUAGE.put("菲律宾语", "tl");
LANGUAGE.put("芬兰语", "fi");
LANGUAGE.put("格鲁吉亚语", "ka");
LANGUAGE.put("古吉拉特语", "gu");
LANGUAGE.put("海地克里奥尔语", "ht");
LANGUAGE.put("韩语", "ko");
LANGUAGE.put("荷兰语", "nl");
LANGUAGE.put("加利西亚语", "gl");
LANGUAGE.put("加泰罗尼亚语", "ca");
LANGUAGE.put("捷克语", "cs");
LANGUAGE.put("卡纳达语", "kn");
LANGUAGE.put("克罗地亚语", "hr");
LANGUAGE.put("拉丁语", "la");
LANGUAGE.put("拉脱维亚语", "lv");
LANGUAGE.put("老挝语", "lo");
LANGUAGE.put("立陶宛语", "lt");
LANGUAGE.put("罗马尼亚语", "ro");
LANGUAGE.put("马耳他语", "mt");
LANGUAGE.put("马来语", "ms");
LANGUAGE.put("马其顿语", "mk");
LANGUAGE.put("孟加拉语", "bn");
LANGUAGE.put("挪威语", "no");
LANGUAGE.put("葡萄牙语", "pt");
LANGUAGE.put("日语", "ja");
LANGUAGE.put("瑞典语", "sv");
LANGUAGE.put("塞尔维亚语", "sr");
LANGUAGE.put("世界语", "eo");
LANGUAGE.put("斯洛伐克语", "sk");
LANGUAGE.put("斯洛文尼亚语", "sl");
LANGUAGE.put("斯瓦希里语", "sw");
LANGUAGE.put("泰卢固语", "te");
LANGUAGE.put("泰米尔语", "ta");
LANGUAGE.put("泰语", "th");
LANGUAGE.put("土耳其语", "tr");
LANGUAGE.put("威尔士语", "cy");
LANGUAGE.put("乌尔都语", "ur");
LANGUAGE.put("乌克兰语", "uk");
LANGUAGE.put("希伯来语", "iw");
LANGUAGE.put("希腊语", "el");
LANGUAGE.put("西班牙语", "es");
LANGUAGE.put("匈牙利语", "hu");
LANGUAGE.put("亚美尼亚语", "hy");
LANGUAGE.put("意大利语", "it");
LANGUAGE.put("意第绪语", "yi");
LANGUAGE.put("印地语", "hi");
LANGUAGE.put("印尼语", "id");
LANGUAGE.put("英语", "en");
LANGUAGE.put("越南语", "vi");
LANGUAGE.put("中文繁体", "zh-TW");
LANGUAGE.put("中文简体", "zh-CN");
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment