Android 汉语转拼音实现

举报
帅次 发表于 2024/11/20 16:35:35 2024/11/20
【摘要】 1、准确、完善的字库； 2、拼音转换速度快； 3、多拼音格式输出支持； 4、常见多音字识别； 5、简繁体中文转换； 6、支持添加用户自定义字典。

​

 一、需求与需求分析

        根据语音识别到的人名匹配应用内联系人并拨打电话。

        经调研总结了以下几种常用的处理方法：

        （1）pinyin4j(开源库)

        （2）jpinyin(开源库)

        （3）ASCII码映射

二、pinyin4j

        支持多种拼音系统（简体和繁体），包括汉语拼音、通用拼音、威妥玛拼音、MPS2、耶鲁拼音和国语拼音。支持多种发音和自定义输出。

        查看源码发现入参仅支持 char 类型。不太符合要求，继续寻找pinyin4j升级版=》jpinyin。

/**
 * A class provides several utility functions to convert Chinese characters
 * (both Simplified and Tranditional) into various Chinese Romanization
 * representations
 * 
 * @author Li Min (xmlerlimin@gmail.com)
 */
public class PinyinHelper {
  /**
   * Get all unformmatted Hanyu Pinyin presentations of a single Chinese
   * character (both Simplified and Tranditional)
   * 
   * <p>
   * For example, <br/> If the input is '间', the return will be an array with
   * two Hanyu Pinyin strings: <br/> "jian1" <br/> "jian4" <br/> <br/> If the
   * input is '李', the return will be an array with single Hanyu Pinyin
   * string: <br/> "li3"
   * 
   * <p>
   * <b>Special Note</b>: If the return is "none0", that means the input
   * Chinese character exists in Unicode CJK talbe, however, it has no
   * pronounciation in Chinese
   * 
   * @param ch
   *            the given Chinese character
   * 
   * @return a String array contains all unformmatted Hanyu Pinyin
   *         presentations with tone numbers; null for non-Chinese character
   * 
   */
  static public String[] toHanyuPinyinStringArray(char ch) {
    return getUnformattedHanyuPinyinStringArray(ch);
  }

  static public String[] toHanyuPinyinStringArray(char ch, HanyuPinyinOutputFormat outputFormat)
      throws BadHanyuPinyinOutputFormatCombination {
    return getFormattedHanyuPinyinStringArray(ch, outputFormat);
  }

   。。。。。。
  /**
   * Get all unformmatted Tongyong Pinyin presentations of a single Chinese
   * character (both Simplified and Tranditional)
   * 
   * @param ch
   *            the given Chinese character
   * 
   * @return a String array contains all unformmatted Tongyong Pinyin
   *         presentations with tone numbers; null for non-Chinese character
   * 
   * @see #toHanyuPinyinStringArray(char)
   * 
   */
  static public String[] toTongyongPinyinStringArray(char ch) {
    return convertToTargetPinyinStringArray(ch, PinyinRomanizationType.TONGYONG_PINYIN);
  }

  static public String toHanyuPinyinString(String str, HanyuPinyinOutputFormat outputFormat,
      String seperater) throws BadHanyuPinyinOutputFormatCombination {

    StringBuffer resultPinyinStrBuf = new StringBuffer();

    for (int i = 0; i < str.length(); i++) {
      String mainPinyinStrOfChar = getFirstHanyuPinyinString(str.charAt(i), outputFormat);

      if (null != mainPinyinStrOfChar) {
        resultPinyinStrBuf.append(mainPinyinStrOfChar);
        if (i != str.length() - 1) { // avoid appending at the end
          resultPinyinStrBuf.append(seperater);
        }
      } else {
        resultPinyinStrBuf.append(str.charAt(i));
      }
    }

    return resultPinyinStrBuf.toString();
  }

  /**
   * Get the first Hanyu Pinyin of a Chinese character <b> This function will
   * be removed in next release. </b>
   * 
   * @param ch
   *            The given Unicode character
   * @param outputFormat
   *            Describes the desired format of returned Hanyu Pinyin string
   * @return Return the first Hanyu Pinyin of given Chinese character; return
   *         null if the input is not a Chinese character
   * 
   * @deprecated DO NOT use it again because the first retrived pinyin string
   *             may be a wrong pronouciation in a certain sentence context.
   *             <b> This function will be removed in next release. </b>
   */
  static private String getFirstHanyuPinyinString(char ch, HanyuPinyinOutputFormat outputFormat)
      throws BadHanyuPinyinOutputFormatCombination {
    String[] pinyinStrArray = getFormattedHanyuPinyinStringArray(ch, outputFormat);

    if ((null != pinyinStrArray) && (pinyinStrArray.length > 0)) {
      return pinyinStrArray[0];
    } else {
      return null;
    }
  }

  // ! Hidden constructor
  private PinyinHelper() {}
}


三、jpinyin

        JPinyin是一个汉字转拼音的Java开源类库，在PinYin4j的功能基础上做了一些改进。

3.1 JPinyin主要特性

        1、准确、完善的字库；Unicode编码从4E00-9FA5范围及3007（〇）的20903个汉字中，JPinyin能转换除46个异体字（异体字不存在标准拼音）之外的所有汉字；

        2、拼音转换速度快；经测试，转换Unicode编码从4E00-9FA5范围的20902个汉字，JPinyin耗时约100毫秒。

        3、多拼音格式输出支持；JPinyin支持多种拼音输出格式：带音标、不带音标、数字表示音标以及拼音首字母输出格式；

        4、常见多音字识别；JPinyin支持常见多音字的识别，其中包括词组、成语、地名等；

        5、简繁体中文转换；

        6、支持添加用户自定义字典；

3.2 集成

        app/build.gradle

implementation 'com.github.stuxuhai:jpinyin:1.1.7'

3.3 使用及效果

        var content:String = binding!!.etContent.text.toString()
        //上海 重庆 重量 长安 长大
        if (!StringUtils.isEmpty(content)) {
            // shànghǎi chóngqìng zhòngliàng chángān chángdà
            PinyinHelper.convertToPinyinString(content, "", PinyinFormat.WITH_TONE_MARK)
            // shang4hai3 chong2qing4 zhong4liang4 chang2an1 chang2da4
            PinyinHelper.convertToPinyinString(content, "", PinyinFormat.WITH_TONE_NUMBER)
            // shanghai chongqing zhongliang changan changda
            PinyinHelper.convertToPinyinString(content, "", PinyinFormat.WITHOUT_TONE)
            // sh cq zl ca cd
            PinyinHelper.getShortPinyin(content)
        }

        重庆和重量识别到了 chóngqìng zhòngliàng。

        长安和长大识别异常 changan changda。

        这个识别效果就看产品评估一下能不能给过了？

四、ASCII码映射

        优点：使用这个方法只需要一个类就可以搞定了，方便简单，无需添加依赖。

        缺点：相对于之前介绍的两种开源库来说，这种方法没那么强大，只能获取一些简单的汉字拼音。

4.1 TextPinyinUtil工具类

package com.scc.pinyin

/**
 * TextPinyinUtil
 * @desc 汉字转拼音工具
 * @date 2024/8/19
 */
class TextPinyinUtil {
    private var buffer: StringBuilder? = null

    // 汉字转成ASCII码
    private fun getChsAscii(chs: String): Int {
        var asc = 0
        try {
            val bytes = chs.toByteArray(charset("gbk"))
            if (bytes == null || bytes.size > 2 || bytes.size <= 0) {
                throw RuntimeException("illegal resource string")
            }
            if (bytes.size == 1) {
                asc = bytes[0].toInt()
            }
            if (bytes.size == 2) {
                val hightByte = 256 + bytes[0]
                val lowByte = 256 + bytes[1]
                asc = 256 * hightByte + lowByte - 256 * 256
            }
        } catch (e: Exception) {
            println("ERROR:ChineseSpelling.class-getChsAscii(String chs)$e")
        }
        return asc
    }

    // 单字解析
    fun convert(str: String): String? {
        var result: String? = null
        val ascii = getChsAscii(str)
        if (ascii > 0 && ascii < 160) {
            result = ascii.toChar().toString()
        } else {
            for (i in pyvalue.size - 1 downTo 0) {
                if (pyvalue[i] <= ascii) {
                    result = pystr[i]
                    break
                }
            }
        }
        return result
    }

    // 词组解析
    fun getPinyin(chs: String): String {
        var key: String
        var value: String?
        buffer = StringBuilder()
        for (i in 0 until chs.length) {
            key = chs.substring(i, i + 1)
            // 判断是否为汉字（汉字为两个以上字符）
            if (key.toByteArray().size >= 2) {
                value = convert(key)
                if (value == null) {
                    value = "unknown"
                }
            } else {
                value = key
            }
            buffer!!.append(value)
        }
        return buffer.toString()
    }

    companion object {
        private val pyvalue = intArrayOf(-20319,-20317,-20304,-20295,-20292,-20283,-20265,-20257,-20242,-20230,-20051,-20036,-20032,-20026,-20002,-19990,-19986,-19982,-19976,-19805,-19784,-19775,-19774,-19763,
            -19756,-19751,-19746,-19741,-19739,-19728,-19725,-19715,-19540,-19531,-19525,-19515,-19500,-19484,-19479,-19467,-19289,-19288,-19281,-19275,-19270,-19263,-19261,-19249,-19243,-19242,-19238,-19235,
            -19227,-19224,-19218,-19212,-19038,-19023,-19018,-19006,-19003,-18996,-18977,-18961,-18952,-18783,-18774,-18773,-18763,-18756,-18741,-18735,-18731,-18722,-18710,-18697,-18696,-18526,-18518,-18501,
            -18490,-18478,-18463,-18448,-18447,-18446,-18239,-18237,-18231,-18220,-18211,-18201,-18184,-18183,-18181,-18012,-17997,-17988,-17970,-17964,-17961,-17950,-17947,-17931,-17928,-17922,-17759,-17752,
            -17733,-17730,-17721,-17703,-17701,-17697,-17692,-17683,-17676,-17496,-17487,-17482,-17468,-17454,-17433,-17427,-17417,-17202,-17185,-16983,-16970,-16942,-16915,-16733,-16708,-16706,-16689,-16664,
            -16657,-16647,-16474,-16470,-16465,-16459,-16452,-16448,-16433,-16429,-16427,-16423,-16419,-16412,-16407,-16403,-16401,-16393,-16220,-16216,-16212,-16205,-16202,-16187,-16180,-16171,-16169,-16158,
            -16155,-15959,-15958,-15944,-15933,-15920,-15915,-15903,-15889,-15878,-15707,-15701,-15681,-15667,-15661,-15659,-15652,-15640,-15631,-15625,-15454,-15448,-15436,-15435,-15419,-15416,-15408,-15394,
            -15385,-15377,-15375,-15369,-15363,-15362,-15183,-15180,-15165,-15158,-15153,-15150,-15149,-15144,-15143,-15141,-15140,-15139,-15128,-15121,-15119,-15117,-15110,-15109,-14941,-14937,-14933,-14930,
            -14929,-14928,-14926,-14922,-14921,-14914,-14908,-14902,-14894,-14889,-14882,-14873,-14871,-14857,-14678,-14674,-14670,-14668,-14663,-14654,-14645,-14630,-14594,-14429,-14407,-14399,-14384,-14379,
            -14368,-14355,-14353,-14345,-14170,-14159,-14151,-14149,-14145,-14140,-14137,-14135,-14125,-14123,-14122,-14112,-14109,-14099,-14097,-14094,-14092,-14090,-14087,-14083,-13917,-13914,-13910,-13907,
            -13906,-13905,-13896,-13894,-13878,-13870,-13859,-13847,-13831,-13658,-13611,-13601,-13406,-13404,-13400,-13398,-13395,-13391,-13387,-13383,-13367,-13359,-13356,-13343,-13340,-13329,-13326,-13318,
            -13147,-13138,-13120,-13107,-13096,-13095,-13091,-13076,-13068,-13063,-13060,-12888,-12875,-12871,-12860,-12858,-12852,-12849,-12838,-12831,-12829,-12812,-12802,-12607,-12597,-12594,-12585,-12556,
            -12359,-12346,-12320,-12300,-12120,-12099,-12089,-12074,-12067,-12058,-12039,-11867,-11861,-11847,-11831,-11798,-11781,-11604,-11589,-11536,-11358,-11340,-11339,-11324,-11303,-11097,-11077,-11067,
            -11055,-11052,-11045,-11041,-11038,-11024,-11020,-11019,-11018,-11014,-10838,-10832,-10815,-10800,-10790,-10780,-10764,-10587,-10544,-10533,-10519,-10331,-10329,-10328,-10322,-10315,-10309,-10307,
            -10296,-10281,-10274,-10270,-10262,-10260,-10256,-10254
        )
        private val pystr = arrayOf("a","ai","an","ang","ao","ba","bai","ban","bang","bao","bei","ben","beng","bi","bian","biao","bie","bin","bing","bo","bu","ca","cai","can","cang","cao","ce","ceng","cha",
            "chai","chan","chang","chao","che","chen","cheng","chi","chong","chou","chu","chuai","chuan","chuang","chui","chun","chuo","ci","cong","cou","cu","cuan","cui","cun","cuo","da","dai","dan","dang",
            "dao","de","deng","di","dian","diao","die","ding","diu","dong","dou","du","duan","dui","dun","duo","e","en","er","fa","fan","fang","fei","fen","feng","fo","fou","fu","ga","gai","gan","gang","gao",
            "ge","gei","gen","geng","gong","gou","gu","gua","guai","guan","guang","gui","gun","guo","ha","hai","han","hang","hao","he","hei","hen","heng","hong","hou","hu","hua","huai","huan","huang","hui","hun",
            "huo","ji","jia","jian","jiang","jiao","jie","jin","jing","jiong","jiu","ju","juan","jue","jun","ka","kai","kan","kang","kao","ke","ken","keng","kong","kou","ku","kua","kuai","kuan","kuang","kui","kun",
            "kuo","la","lai","lan","lang","lao","le","lei","leng","li","lia","lian","liang","liao","lie","lin","ling","liu","long","lou","lu","lv","luan","lue","lun","luo","ma","mai","man","mang","mao","me","mei",
            "men","meng","mi","mian","miao","mie","min","ming","miu","mo","mou","mu","na","nai","nan","nang","nao","ne","nei","nen","neng","ni","nian","niang","niao","nie","nin","ning","niu","nong","nu","nv","nuan",
            "nue","nuo","o","ou","pa","pai","pan","pang","pao","pei","pen","peng","pi","pian","piao","pie","pin","ping","po","pu","qi","qia","qian","qiang","qiao","qie","qin","qing","qiong","qiu","qu","quan","que","qun",
            "ran","rang","rao","re","ren","reng","ri","rong","rou","ru","ruan","rui","run","ruo","sa","sai","san","sang","sao","se","sen","seng","sha","shai","shan","shang","shao","she","shen","sheng","shi","shou","shu",
            "shua","shuai","shuan","shuang","shui","shun","shuo","si","song","sou","su","suan","sui","sun","suo","ta","tai","tan","tang","tao","te","teng","ti","tian","tiao","tie","ting","tong","tou","tu","tuan","tui",
            "tun","tuo","wa","wai","wan","wang","wei","wen","weng","wo","wu","xi","xia","xian","xiang","xiao","xie","xin","xing","xiong","xiu","xu","xuan","xue","xun","ya","yan","yang","yao","ye","yi","yin","ying","yo",
            "yong","you","yu","yuan","yue","yun","za","zai","zan","zang","zao","ze","zei","zen","zeng","zha","zhai","zhan","zhang","zhao","zhe","zhen","zheng","zhi","zhong","zhou","zhu","zhua","zhuai","zhuan","zhuang",
            "zhui","zhun","zhuo","zi","zong","zou","zu","zuan","zui","zun","zuo"
        )
        val instance = TextPinyinUtil()

        /**
         * 判断是否为中文
         * @param text 内容
         * @return true=中文
         */
        fun isChinaString(text: String): Boolean {
            for (i in 0 until text.length) {
                val c = text[i]
                if (c.code >= 0x4e00 && c.code <= 0x9fbb) {
                    return true
                }
            }
            return false
        }
    }
}

4.2 使用及效果

//上海 重庆 重量 长安 长大

//shanghai zhongqing zhongliang changan changda
TextPinyinUtil.instance.getPinyin(content)

​

【版权声明】本文为华为云社区用户原创内容，未经允许不得转载，如需转载请自行联系原作者进行授权。如果您发现本社区中有涉嫌抄袭的内容，欢迎发送邮件进行举报，并提供相关证据，一经查实，本社区将立刻删除涉嫌侵权内容，举报邮箱： cloudbbs@huaweicloud.com
Android
  • 点赞
  • 收藏
  • 关注作者

评论（0）

0/1000
抱歉，系统识别当前为高风险访问，暂不支持该操作

全部回复

上滑加载中

设置昵称

在此一键设置昵称，即可参与社区互动！

*长度不超过10个汉字或20个英文字符，设置后3个月内不可修改。

*长度不超过10个汉字或20个英文字符，设置后3个月内不可修改。

确认 取消

加入云驻计划，成为创作者

  • 华为云周边好礼
  • 免费体验产品
  • 特殊身份标识
  • 线下官方门票
  • 内部专家零距离
  • 与10000+优质创作者共同成长
立即加入