学步园

最近做程序用到汉字转汉语拼音的问题，首先想到Google一下，但是拿来看了一下源码，不是甚清楚。

后来想到自己Delphi有一个获得拼音的代码。于是找了出来。研究了一下代码如下：

function get_hz_pywb(hzstr: string; pytype: integer): string;<br /> var<br /> I: Integer;<br /> allstr: string;<br /> hh: THandle;<br /> pp: pointer;<br /> ss: TStringList;</p> <p> function retturn_wbpy(tempstr: string; tqtype: integer): string;<br /> var<br /> outstr, str: string;<br /> i: integer;<br /> begin<br /> //################### 汉字查询电位<br /> i := 0;<br /> while i <= ss.Count - 1 do<br /> begin<br /> str := ss.Strings[i];<br /> if (tempstr = trim(str[1] + str[2])) or (tempstr = trim(str[3] + str[4])) then<br /> begin<br /> str := ss.Strings[i];<br /> Break;<br /> end;<br /> i := i + 1;<br /> end;<br /> //###################<br /> outstr := ''; //提取编码<br /> if tqtype = 1 then<br /> begin<br /> for i := pos('①', str) + 2 to pos('②', str) - 1 do<br /> if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];<br /> end;<br /> if tqtype = 2 then<br /> begin<br /> for i := pos('②', str) + 2 to pos('③', str) - 1 do<br /> if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];<br /> end;<br /> if tqtype = 3 then<br /> begin<br /> for i := pos('③', str) + 2 to pos('④', str) - 1 do<br /> if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];<br /> end;<br /> if tqtype = 4 then<br /> begin<br /> for i := pos('④', str) + 2 to length(str) do<br /> if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];<br /> end;<br /> Result := trim(outstr);<br /> end;<br /> begin<br /> //加载资源文件,将内容赋值给 s<br /> ss := TStringList.Create;<br /> hh := FindResource(hInstance, 'mywb', 'TXT');<br /> hh := LoadResource(hInstance, hh);<br /> pp := LockResource(hh);<br /> ss.Text := pchar(pp);<br /> UnLockResource(hh);<br /> FreeResource(hh);<br /> allstr := '';<br /> i := 0;<br /> while i <= length(hzstr) do //提取汉字字符<br /> begin<br /> if (Ord(hzstr[I]) > 127) then<br /> begin<br /> if allstr = '' then<br /> allstr := retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype)<br /> else<br /> allstr := allstr + retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype);<br /> i := i + 2;<br /> end<br /> else<br /> begin<br /> if allstr = '' then allstr := hzstr[I] else allstr := allstr + hzstr[I];<br /> i := i + 1;<br /> end;<br /> end;<br /> ss.Free;</p> <p> Result := trim(allstr);<br /> en

这是 http://download.csdn.net/source/1050411资源地址。

我把他改成Python代码供大家研究。。。。

# -*-coding:utf-8-*-<br /> # 返回汉字的拼音<br /> def Return_pinyin(word):<br /> global reslist<br /> for line in reslist:<br /> if (word==line[0]+line[1]) or (word==line[2]+line[3]):<br /> str = line<br /> break<br /> # 取①和②之间的内容<br /> s = str.find(u'①')+4<br /> e = str.find(u'②')+3<br /> return str[s:e]</p> <p>def GetPy(word):<br /> #首先装载资源文件<br /> i=0<br /> allstr = ''<br /> while i<len(word):<br /> if ord(word[i])>127:<br /> if allstr:<br /> allstr += Return_pinyin(word[i]+word[i+1])<br /> else:<br /> allstr = Return_pinyin(word[i]+word[i+1])<br /> i +=2<br /> else:<br /> if allstr:<br /> allstr += word[i]<br /> else:<br /> allstr = word[i]<br /> i +=1<br /> return allstr<br /> if __name__=='__main__':<br /> f = open('wbtext1.txt','r')<br /> reslist = f.readlines()<br /> f.close()<br /> word = raw_input(u'请输入汉字: ')<br /> print GetPy(word).lower()

如果大家有什么问题欢迎讨论。。。。。。