用VC实现汉字转拼音首字母

最新推荐文章于 2015-03-09 09:01:00 发布

原创最新推荐文章于 2015-03-09 09:01:00 发布 · 3.1k 阅读

3 ·

CC 4.0 BY-SA版权

文章标签：

#string #null #parameters #delete #character #date

技术笔记专栏收录该内容

26 篇文章

订阅专栏

本文介绍了一个用于从中文字符串中提取每个汉字对应的拼音首字母的算法实现。该算法使用了Unicode到MultiByte的转换，并提供了针对不同编码标准（如std::string和std::wstring）的函数。通过实例演示了如何将“WPS电子表格”转换为“WPSDZBG”。

参考代码：http://blog.youkuaiyun.com/lixiaosan/archive/2006/05/26/756350.aspx
lixiaosan的代码用的是CString在Unicode下有问题，我这里稍作修改，用stl::string和stl::wstring替换CString

代码为两个文件：GenFirstPYLetter.h，GenFirstPYLetter.cpp

/* ------------------------------------------------------------------------- // FileName : GenFirstPYLetter.h // Creator : debehe // Date : 2009/9/28 17:40:24 // Brief : 需要用MultiByte才能正确转换 // Unicode转成MultiByte时不要用W2A // // $Id: $ // -----------------------------------------------------------------------*/ // How to use: // // std::wstring strA = L"WPS电子表格"; // std::wstring strOutput; // BOOL bRet = GenFirstPYLetter(strA, strOutput); // // 结果应该是: // strOutput == L"WPSDZBG"; // bRet == TRUE; // 以字母开头 // ------------------------------------------------------------------------- #ifndef __GETFIRSTLETTER_H__ #define __GETFIRSTLETTER_H__ #include <Windows.h> #include <string> // ------------------------------------------------------------------------- /* @ Function : GenFirstPYLetter @ brief : 转换汉字为拼音首字母 @ parameter : [in]strName @ parameter : [out]strResult @ return : 是否以字母开头 @ remark : @ Date : 2009/9/28 20:37:19 linyehui @*/ BOOL GenFirstPYLetter(std::string strName, std::string&strResult ); BOOL GenFirstPYLetter(std::wstring strName, std::wstring&strResult); // ------------------------------------------------------------------------- // $Log: $ #endif /* __GETFIRSTLETTER_H__ */

/* ------------------------------------------------------------------------- // FileName : GenFirstPYLetter.cpp // Creator : debehe // Date : 2009/9/28 17:40:31 // Brief : 需要用MultiByte才能正确转换 // Unicode转成MultiByte时不要用W2A // // $Id: $ // -----------------------------------------------------------------------*/ #include "stdafx.h" #include "GenFirstPYLetter.h" #include <Windows.h> // ------------------------------------------------------------------------- /******************************************************************************************** /* Syntax /* void FirstLetter(int nCode, CString& strLetter) /* Remarks: /* Get the first letter of pinyin according to specified Chinese character code. /* Parameters: /* nCode - the code of the chinese character. /* strLetter - a CString object that is to receive the string of the first letter. /* Return Values: /* None. /* Author: /* lixiaosan /* Create Date: /* 05-26-2006 /********************************************************************************************/ void FirstLetter(int nCode, std::string& strLetter) { if(nCode >= 1601 && nCode < 1637) strLetter = "A"; if(nCode >= 1637 && nCode < 1833) strLetter = "B"; if(nCode >= 1833 && nCode < 2078) strLetter = "C"; if(nCode >= 2078 && nCode < 2274) strLetter = "D"; if(nCode >= 2274 && nCode < 2302) strLetter = "E"; if(nCode >= 2302 && nCode < 2433) strLetter = "F"; if(nCode >= 2433 && nCode < 2594) strLetter = "G"; if(nCode >= 2594 && nCode < 2787) strLetter = "H"; if(nCode >= 2787 && nCode < 3106) strLetter = "J"; if(nCode >= 3106 && nCode < 3212) strLetter = "K"; if(nCode >= 3212 && nCode < 3472) strLetter = "L"; if(nCode >= 3472 && nCode < 3635) strLetter = "M"; if(nCode >= 3635 && nCode < 3722) strLetter = "N"; if(nCode >= 3722 && nCode < 3730) strLetter = "O"; if(nCode >= 3730 && nCode < 3858) strLetter = "P"; if(nCode >= 3858 && nCode < 4027) strLetter = "Q"; if(nCode >= 4027 && nCode < 4086) strLetter = "R"; if(nCode >= 4086 && nCode < 4390) strLetter = "S"; if(nCode >= 4390 && nCode < 4558) strLetter = "T"; if(nCode >= 4558 && nCode < 4684) strLetter = "W"; if(nCode >= 4684 && nCode < 4925) strLetter = "X"; if(nCode >= 4925 && nCode < 5249) strLetter = "Y"; if(nCode >= 5249 && nCode < 5590) strLetter = "Z"; } BOOL GenFirstPYLetter(std::string strName, std::string&strResult ) { BOOL bStartByLetter = FALSE; unsigned char ucHigh, ucLow; int nCode; std::string strRet; strResult.clear(); if (strName.empty()) return FALSE; if ((unsigned char)strName[0] < 0x80 ) bStartByLetter = TRUE; for (size_t i=0; i < strName.size(); i++) { if ( (unsigned char)strName[i] < 0x80 ) { strResult += strName[i]; continue; } ucHigh = (unsigned char)strName[i]; ucLow = (unsigned char)strName[i+1]; if ( ucHigh < 0xa1 || ucLow < 0xa1) continue; else // Treat code by section-position as an int type parameter, // so make following change to nCode. nCode = (ucHigh - 0xa0) * 100 + ucLow - 0xa0; FirstLetter(nCode, strRet); strResult += strRet; i++; } return bStartByLetter; } BOOL GenFirstPYLetter(std::wstring strName, std::wstring&strResult) { std::string strSource; std::string strOutput; // Unicode转换成MultiByte DWORD dwNum = WideCharToMultiByte(CP_OEMCP,NULL,strName.c_str(),-1,NULL,0,NULL,FALSE); char *psText; psText = new char[dwNum]; if(!psText) { delete []psText; return FALSE; } else { WideCharToMultiByte (CP_OEMCP,NULL,strName.c_str(),-1,psText,dwNum,NULL,FALSE); strSource = psText; delete []psText; } // 转调 BOOL bRet = GenFirstPYLetter(strSource, strOutput); // MultiByte转换成Unicode dwNum = MultiByteToWideChar (CP_ACP, 0, strOutput.c_str(), -1, NULL, 0); wchar_t *pwText; pwText = new wchar_t[dwNum]; if(!pwText) { delete []pwText; return FALSE; } else { MultiByteToWideChar (CP_ACP, 0, strOutput.c_str(), -1, pwText, dwNum); strResult = pwText; delete [] pwText; } return bRet; } // ------------------------------------------------------------------------- // $Log: $