python匹配类体或函数体，用以插入代码
把下面的python脚本保存为 code_analyze.py
# -*- coding:utf-8 -*-
#import re
def delete_comm(str_ = ""):
"删除C语言上的 /* */ 与 // 的注释的代码"
need_ = True
while need_:
need_ = False
str_ = str_.strip()
str_len = len(str_)
i = 0
while (i < str_len and i < 3000):
c = str_[i]
if c == '"':
i += 1
while i < str_len:
c2 = str_[i]
if c2 == '"':
break
elif c2 == '\\':
i += 1
i += 1
i += 1
elif c == '/':
f_c = i
i += 1
if i > str_len:
break
if str_[i] == '/':
f = str_.find('\n', i)
if f < i:
return str_[0, f_c]
i = f + 1
str_ = str_[:f_c] + str_[i:]
str_len = len(str_)
need_ = True
break
elif str_[i] == '*':
f = str_.find("*/", i)
if f < i:
return str_
i = f + 2
str_ = str_[:f_c]+str_[i:]
need_ = True
break
else:
i += 1
return str_
def is_space(c):
return c == ' ' or c == '\t' or c == '\r' or c == '\n'
def slice_to_idx_ls(text='', start_bk='(',start_pos = 0):
right_to_left = {'}':'{', ']' : '[' , ')':'('}
res = []
i = start_pos
ix = text.find(start_bk, i)
if (ix < i ) and (ix > len(text)):
return None
i = ix
bk_stack = []
bk_stack.append(start_bk)
res.append(i)
i += 1
while is_space(text[i]):
i += 1
while i < len(text):
c = text[i]
if c == '{' or c == '[' or c == '(':
bk_stack.append(c)
i += 1
elif c == '}' or c == ']' or c == ')':
if bk_stack[-1] != right_to_left[c]:
return None
bk_stack = bk_stack[:-1]
if len(bk_stack) == 0:
res.append(i)
return res
i += 1
while is_space(text[i]):
i += 1
elif c == '/':
i += 1
c2 = text[i]
if c2 == '/':
ix = text.find('\n', i)
i = ix + 1
elif c2 == '*':
ix = text.find('*/',i)
i = ix + 2
elif c == '"':
i += 1
while i < len(text):
c2 = text[i]
if c2 == '\\':
i += 1
elif c2 == '"':
break
i+=1
i+=1
elif c == ',':
if len(bk_stack) == 1:
res.append(i)
i += 1
else:
i += 1
return None
def split_args(text, start_bk = '(', start_pos = 0):
"切分如同 func_name(a, \"ww,ww\" , b(function(){}), c() ) 这类的文本，成['func_name', 'a', ' \"ww,ww\" ', ' b(function(){})', ' c() '] "
sl = slice_to_idx_ls(text, start_bk, start_pos)
if not sl:
return None
res = []
lst = start_pos
text_len = len(text)
for cur in sl:
if lst > text_len or cur > text_len or lst < 0 or cur - lst < 0:
raise "split_args:ERROR:unknown"
res.append(text[lst: cur])
lst = cur + 1
return res
def set_str_value(text, start_mark, start_pos, value):
idx = text.find(start_mark, start_pos)
if idx < 0:
return False
len_text = len(text)
i = idx + len(start_mark)
idx1 = -1
idx2 = -1
while i < len_text:
c = text[i]
if c == '/':
i += 1
c2 = text[i]
if c2 == '/':
ix = text.find('\n', i)
if ix < i:
return False
i = ix + 1
elif c2 == '*':
ix = text.find('*/', i)
if ix < i:
return False
i = ix + 2
elif c == '"':
idx1 = i
i += 1
while i < len_text:
c2 = text[i]
if c2 == '\\':
i += 1
elif c2 == '"':
idx2 = i
break
i+=1
i+=1
elif c == '\'':
idx1 = i
i += 1
while i < len_text:
c2 = text[i]
if c2 == '\\':
i += 1
elif c2 == '\'':
idx2 = i
break
i+=1
i+=1
elif is_space(c):
i+=1
else:
return False
if idx1 != -1 and idx2 != -1:
break
if idx1 != -1 and idx2 != -1:
return text[:idx1+1]+value+text[idx2:]
return False
def find_a_string_idx(text, start_pos):
idx = start_pos
if idx < 0:
return False
len_text = len(text)
i = idx
idx1 = -1
idx2 = -1
while i < len_text:
c = text[i]
if c == '/':
i += 1
c2 = text[i]
if c2 == '/':
ix = text.find('\n', i)
if ix < i:
return None
i = ix + 1
elif c2 == '*':
ix = text.find('*/', i)
if ix < i:
return None
i = ix + 2
elif c == '"':
idx1 = i
i += 1
while i < len_text:
c2 = text[i]
if c2 == '\\':
i += 1
elif c2 == '"':
idx2 = i
break
i+=1
i+=1
elif c == '\'':
idx1 = i
i += 1
while i < len_text:
c2 = text[i]
if c2 == '\\':
i += 1
elif c2 == '\'':
idx2 = i
break
i+=1
i+=1
else:
i+=1
if idx1 != -1 and idx2 != -1:
break
if idx1 != -1 and idx2 != -1:
return (idx1, idx2)
return False
def find_all_string_pos(txt, start_pos=0):
pos_ls = []
txt_pos = start_pos
txt_len = len(txt)
if txt_pos >= txt_len:
return None
while True:
pos_ = find_a_string_idx(txt, txt_pos)
if not pos_:
break
pos_ls.append(pos_)
txt_pos = pos_[1] +1
if not pos_ls:
return None
return pos_ls
def find_all_string(txt, start_pos=0):
pos_ls = find_all_string_pos(txt, start_pos)
if not pos_ls:
return None
ls = []
for pos_ in pos_ls:
ls.append(txt[pos_[0]:pos_[1]+1])
return ls
#print delete_comm(r'''(abc/*adefe*/, "adefe"//daefafe
# faeifdjk=() )''')
#print split_args( '( wde, abde , "cdf,geg" , efg(function(){ }) )' )
#print split_args('fdafeat[ wde, abde , "cdf,geg" , efg(function(){ }) ]', '[')
#print split_args("func_name(a, \"ww,ww\" , b(function(){}), c() )")
#print split_args("this.static = []", '[')
#print set_str_value(' t="" ', 't=' , 0, 'abc')
#print set_str_value(' t= " " ', 't=',0, 'abc')
#print set_str_value(' t="" ', 't=' , 0, 'abc')
#print set_str_value(' t=/*wwww*/" " ', 't=',0, 'abc')
#print set_str_value(' t="\'" ', 't=' , 0, 'abc')
#print set_str_value(' t= " " ', 't=',0, 'abc')
#print set_str_value(' t="\\\"\\\"" ', 't=' , 0, 'abc')
#print set_str_value(' t="/*wwww*/" ', 't=',0, 'abc')
#print set_str_value(' t=\'\' ', 't=' , 0, 'abc')
#print set_str_value(' t= \' \' ', 't=',0, 'abc')
#print set_str_value(' t=\'\" \'', 't=' , 0, 'abc')
然后在同级目录中，我们创建一个测试的python脚本：test.py
import code_analyze
#import re
txt = """
public class ABC2 : DDD
{
// 加入一些干扰{}}.}\|}{
/*}*/
void a() { }
void b()
{
if (true)
{
Debug.Log("bbbbbbb");
}
}
}
public class HHHH
{
void a() { }
void b()
{
Debug.Log("aaaaaaaa");
}
}
"""
def test():
mark = 'public class ABC2 : DDD'
idx = txt.find(mark)
if idx<0:
print('not found mark:'+mark)
return
ls = code_analyze.slice_to_idx_ls(txt, '{', idx)
vidx = ls[-1]
# 插入一个Hello函数
print ( txt[:vidx] + "\n void Hello(){}\n"+txt[vidx:])
test()
测试结果如下
