Question

所以我有一个文件，我想排队并替换一些非常相似的单词，实际上其中一些是其他单词的子串：

uint8=("UINT8 ","PIN_UINT8 ")
uint16=("UINT16 ","PIN_UINT16 ")
uint32=("UINT32 ","PIN_UINT32 ")
uint64=("UINT64 ","PIN_UINT64 ")
int8=("INT8 ","PIN_INT32 ")
int16=("INT16 ","PIN_INT16 ")
int32=("INT32 ","PIN_INT32 ")
int64=("INT64 ","PIN_INT64 ")

这些是替代品。但我需要小心，因为INT8是UINT8的子字符串，所以即使我有匹配，我也需要检查它是UINT8还是INT8。

我写了一些代码，但还远未奏效。

while pos!=-1:
                                print line[pos:]
                                if "INT8 " in line[pos:]:
                                    pos=line.find("INT8",pos_final)
                                    if "U" == line[pos-1]:
                                        line = line.rstrip().replace(*uint8)
                                    else:
                                        print line[pos-1]
                                        line = line.rstrip().replace(*int8)
                                    pos+=5 #len(PIN_)+1
                                elif "INT16 " in line[pos:]:
                                    pos=line.find("INT16",pos_final)
                                    if "U" == line[pos-1]:
                                        line = line.rstrip().replace(*uint16)
                                    else:
                                        print line[pos-1]
                                        line = line.rstrip().replace(*int16) 
                                    pos+=5                       
                                elif "INT32 " in line[pos:]:
                                    pos=line.find("INT32",pos_final)
                                    if "U" == line[pos-1]:
                                        line = line.rstrip().replace(*uint32)
                                    else:
                                        print line[pos-1]
                                        line = line.rstrip().replace(*int32) 
                                    pos+=5                       
                                elif "INT64 " in line[pos:]:
                                    pos=line.find("INT64",pos_final)
                                    if "U" == line[pos-1]:
                                        line = line.rstrip().replace(*uint64)
                                    else:
                                        print line[pos-1]
                                        line = line.rstrip().replace(*int64)
                                    pos+=5
                                else:
                                    pos =-1

这里有一些文件行，因此您可以知道响应是否正确并且有效：

UINT32 CacheSize() const { return _cacheSize; }
UINT32 LineSize() const { return _lineSize; }
UINT32 Associativity(UINT64 obj, INT8 obj2) const { return _associativity; }
VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex) const
VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex, UINT32 & lineIndex) const
{
    const UINT32 lineMask = _lineSize - 1;

Answer 1

你可以使用re模块，尝试下面的代码

import re
text = """UINT32 CacheSize() const { return _cacheSize; }
    UINT32 LineSize() const { return _lineSize; }
    UINT32 Associativity(UINT64 obj, INT8 obj2) const { return _associativity; }
    VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex) const
    VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex, UINT32 & lineIndex) const
    {
        const UINT32 lineMask  = _lineSize - 1 INT8;
"""

for line in text.split("\n"):
    line = re.sub("UINT8 ","PIN_UINT8 ", line)
    line = re.sub("UINT16 ","PIN_UINT16 ", line)
    line = re.sub("UINT32 ","PIN_UINT32 ", line)
    line = re.sub("UINT64 ","PIN_UINT64 ", line)
    line = re.sub("[^UPIN_]INT8 ","PIN_INT32 ", line)
    line = re.sub("[^UPIN_]INT16 ","PIN_INT16 ", line)
    line = re.sub("[^UPIN_]INT32 ","PIN_INT32 ", line)
    line = re.sub("[^UPIN_]INT64 ","PIN_INT64 ", line)
    print "\t\t",line

<强>输出

PIN_UINT32 CacheSize() const { return _cacheSize; }
PIN_UINT32 LineSize() const { return _lineSize; }
PIN_UINT32 Associativity(PIN_UINT64 obj,PIN_INT32 obj2) const { return _associativity; }
VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, PIN_UINT32 & setIndex) const
VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, PIN_UINT32 & setIndex, PIN_UINT32 & lineIndex) const
{
    const PIN_UINT32 lineMask  = _lineSize - 1PIN_INT32 ;

Answer 2

我假设您的文件中没有INT7。

import re
text = """UINT32 CacheSize() const { return _cacheSize; }
    UINT32 LineSize() const { return _lineSize; }
    UINT32 Associativity(UINT64 obj, INT8 obj2) const { return _associativity; }
    VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex) const
    VOID SplitAddress(const ADDRINT addr, CACHE_TAG & tag, UINT32 & setIndex, UINT32 & lineIndex) const
    {
        const UINT32 lineMask  = _lineSize - 1 INT8;
"""
for line in text.split("\n"):
    print re.sub(r'(U?INT\d+?)',r'PIN_\1', line)

智能替换重复值python

2 个答案: