android 汉字转拼音带多音字识别功能，供大家参考，具体内容如下

问题来源

在做地名按首字母排序的时候出现了这样一个bug。长沙会被翻译拼音成zhangsha，重庆会被翻译拼音成zhong qing。于是排序出了问题。

汉字转拼音库和多音字识别库1.多音字对应的词汇库

2.文字的二进制大小对应的拼音库

关键代码

1.我在这里首先将要转化的文字转化成对应的”gb2312”编码。汉字转化成二进制编码一般占两个字节，如果一个字节返回字符，如果是两个字节算一下偏移量。代码如下

/** * 汉字转成ascii码 * * @param chs * @return */

private int getchsascii(string chs) {

int asc = 0;

try {

byte[] bytes = chs.getbytes("gb2312");

if (bytes == null || bytes.length > 2 || bytes.length <= 0) {

throw new runtimeexception("illegal resource string");

}

if (bytes.length == 1) {

asc = bytes[0];

}

if (bytes.length == 2) {

int hightbyte = 256 + bytes[0];

int lowbyte = 256 + bytes[1];

asc = (256 * hightbyte + lowbyte) - 256 * 256;

}

} catch (exception e) {

system.out.println("error:chinesespelling.class-getchsascii(string chs)" + e);

}

return asc;

}

2.将单个汉字获取的拼音再和多音字库的hashmap进行比较，代码如下：

public string getsellingwithpolyphone(string chs){

if(polyphonemap != null && polyphonemap.isempty()){

polyphonemap = initdictionary();

}

string key, value, resultpy = null;

buffer = new stringbuilder();

for (int i = 0; i < chs.length(); i++) {

key = chs.substring(i, i + 1);

if (key.getbytes().length >= 2) {

value = (string) convert(key);

if (value == null) {

value = "unknown";

}

} else {

value = key;

}

resultpy = value;

string left = null;

if(i>=1 && i+1 <= chs.length()){

left = chs.substring(i-1,i+1);

if(polyphonemap.containskey(value) && polyphonemap.get(value).contains(left)){

resultpy = value;

}

}

// if(chs.contains("重庆")){

string right = null; //向右多取一个字,例如 [长]沙

if(i<=chs.length()-2){

right = chs.substring(i,i+2);

if(polyphonemap.containskey(right)){

resultpy = polyphonemap.get(right);

}

}

// }

string middle = null; //左右各多取一个字,例如 龙[爪]槐

if(i>=1 && i+2<=chs.length()){

middle = chs.substring(i-1,i+2);

if(polyphonemap.containskey(value) && polyphonemap.get(value).contains(middle)){

resultpy = value;

}

}

string left3 = null; //向左多取2个字,如 芈月[传],列车长

if(i>=2 && i+1<=chs.length()){

left3 = chs.substring(i-2,i+1);

if(polyphonemap.containskey(value) && polyphonemap.get(value).contains(left3)){

resultpy = value;

}

}

string right3 = null; //向右多取2个字,如 [长]孙无忌

if(i<=chs.length()-3){

right3 = chs.substring(i,i+3);

if(polyphonemap.containskey(value) && polyphonemap.get(value).contains(right3)){

resultpy = value;

}

}

buffer.append(resultpy);

}

return buffer.tostring();

}

3.将asserts文件内容解析生成hashmap列表.

public hashmap initdictionary(){

string filename = "py4j.dic";

inputstreamreader inputreader = null;

bufferedreader bufferedreader = null;

hashmap polyphonemap = new hashmap();

try{

inputreader = new inputstreamreader(myapplication.mcontext.getresources().getassets().open(filename),"utf-8");

bufferedreader = new bufferedreader(inputreader);

string line = null;

while((line = bufferedreader.readline()) != null){

string[] arr = line.split(pinyin_separator);

if(isnotempty(arr[1])){

string[] dyzs = arr[1].split(word_separator);

for(string dyz: dyzs){

if(isnotempty(dyz)){

polyphonemap.put(dyz.trim(),arr[0]);

}

}

}

}

}catch(exception e){

e.printstacktrace();

}finally{

if(inputreader != null){

try {

inputreader.close();

} catch (ioexception e) {

// todo auto-generated catch block

e.printstacktrace();

}

}

if(bufferedreader != null){

try {

bufferedreader.close();

} catch (ioexception e) {

// todo auto-generated catch block

e.printstacktrace();

}

}

}

return polyphonemap;

}

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持萬仟网。