Python实现汉字转拼音：基于Delphi源码的移植与解析
本文介绍如何使用Python实现汉字转拼音的功能，并对比了原始的Delphi实现代码。通过加载外部资源文件进行汉字编码匹配，Python版本简化了资源加载逻辑，提供了完整的转换函数及主程序示例，适用于需要批量处理中文文本拼音转换的场景。
Delphi源码解析与Python移植
此前曾注意到Delphi中有一段获取汉字拼音的代码，经查找并研究后，其核心逻辑如下所示。
具体实现代码参考如下：
function get_hz_pywb(hzstr: string; pytype: integer): string;
var
I: Integer;
allstr: string;
hh: THandle;
pp: pointer;
ss: TStringList;
function retturn_wbpy(tempstr: string; tqtype: integer): string;
var
outstr, str: string;
i: integer;
begin
//################### 汉字查询电位
i := 0;
while i <= ss.Count - 1 do
begin
str := ss.Strings[i];
if (tempstr = trim(str[1] + str[2])) or (tempstr = trim(str[3] + str[4])) then
begin
str := ss.Strings[i];
Break;
end;
i := i + 1;
end;
//###################
outstr := ''; //提取编码
if tqtype = 1 then
begin
for i := pos('①', str) + 2 to pos('②', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 2 then
begin
for i := pos('②', str) + 2 to pos('③', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 3 then
begin
for i := pos('③', str) + 2 to pos('④', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 4 then
begin
for i := pos('④', str) + 2 to length(str) do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
Result := trim(outstr);
end;
begin
//加载资源文件,将内容赋值给 s
ss := TStringList.Create;
hh := FindResource(hInstance, 'mywb', 'TXT');
hh := LoadResource(hInstance, hh);
pp := LockResource(hh);
ss.Text := pchar(pp);
UnLockResource(hh);
FreeResource(hh);
allstr := '';
i := 0;
while i <= length(hzstr) do //提取汉字字符
begin
if (Ord(hzstr[I]) > 127) then
begin
if allstr = '' then
allstr := retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype)
else
allstr := allstr + retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype);
i := i + 2;
end
else
begin
if allstr = '' then allstr := hzstr[I] else allstr := allstr + hzstr[I];
i := i + 1;
end;
end;
ss.Free;
Result := trim(allstr);
en
function get_hz_pywb(hzstr: string; pytype: integer): string;
var
I: Integer;
allstr: string;
hh: THandle;
pp: pointer;
ss: TStringList;
function retturn_wbpy(tempstr: string; tqtype: integer): string;
var
outstr, str: string;
i: integer;
begin
//################### 汉字查询电位
i := 0;
while i <= ss.Count - 1 do
begin
str := ss.Strings[i];
if (tempstr = trim(str[1] + str[2])) or (tempstr = trim(str[3] + str[4])) then
begin
str := ss.Strings[i];
Break;
end;
i := i + 1;
end;
//###################
outstr := ''; //提取编码
if tqtype = 1 then
begin
for i := pos('①', str) + 2 to pos('②', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 2 then
begin
for i := pos('②', str) + 2 to pos('③', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 3 then
begin
for i := pos('③', str) + 2 to pos('④', str) - 1 do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
if tqtype = 4 then
begin
for i := pos('④', str) + 2 to length(str) do
if str[i] <> '' then if outstr = '' then outstr := str[i] else outstr := outstr + str[i];
end;
Result := trim(outstr);
end;
begin
//加载资源文件,将内容赋值给 s
ss := TStringList.Create;
hh := FindResource(hInstance, 'mywb', 'TXT');
hh := LoadResource(hInstance, hh);
pp := LockResource(hh);
ss.Text := pchar(pp);
UnLockResource(hh);
FreeResource(hh);
allstr := '';
i := 0;
while i <= length(hzstr) do //提取汉字字符
begin
if (Ord(hzstr[I]) > 127) then
begin
if allstr = '' then
allstr := retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype)
else
allstr := allstr + retturn_wbpy(hzstr[I] + hzstr[I + 1], pytype);
i := i + 2;
end
else
begin
if allstr = '' then allstr := hzstr[I] else allstr := allstr + hzstr[I];
i := i + 1;
end;
end;
ss.Free;
Result := trim(allstr);
en
该实现依赖一个外部资源文件，后续将提供该文件的下载地址。
随后，作者将其转换为Python代码以供参考研究。
Python实现代码如下：
# -*-coding:utf-8-*-
# 返回汉字的拼音
def Return_pinyin(word):
global reslist
for line in reslist:
if (word==line[0]+line[1]) or (word==line[2]+line[3]):
str = line
break
# 取①和②之间的内容
s = str.find(u'①')+4
e = str.find(u'②')+3
return str[s:e]
def GetPy(word):
#首先装载资源文件
i=0
allstr = ''
while i<len(word):
if ord(word[i])>127:
if allstr:
allstr += Return_pinyin(word[i]+word[i+1])
else:
allstr = Return_pinyin(word[i]+word[i+1])
i +=2
else:
if allstr:
allstr += word[i]
else:
allstr = word[i]
i +=1
return allstr
if __name__=='__main__':
f = open('wbtext1.txt','r')
reslist = f.readlines()
f.close()
word = raw_input(u'请输入汉字: ')
print GetPy(word).lower()
欢迎就相关问题进行交流讨论。
免责声明：本文内容仅供参考，不代表本站观点。转载或引用请注明出处。
