python字符串操作和string模块代码分析

任何语言都离不开字符，那就会涉及对字符的操作，尤其是脚本语言更是频繁，不管是生产环境还是面试考验都要面对字符串的操作。

    python的字符串操作通过2部分的方法函数基本上就可以解决所有的字符串操作需求：

• python的字符串属性函数
• python的string模块

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

1. 字符串属性函数  

     系统版本：CentOS release 6.2 (Final)2.6.32-220.el6.x86_64

     python版本：Python 2.6.6

字符串属性方法

 >>> str='string learn'
 >>> dir(str)
 ['__add__', '__class__', '__contains__', '__delattr__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__getitem__', '__getnewargs__', '__getslice__', '__gt__', '__hash__', '__init__', '__le__', '__len__', '__lt__', '__mod__', '__mul__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__rmod__', '__rmul__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', '_formatter_field_name_split', '_formatter_parser', 'capitalize', 'center', 'count', 'decode', 'encode', 'endswith', 'expandtabs', 'find', 'format', 'index', 'isalnum', 'isalpha', 'isdigit', 'islower', 'isspace', 'istitle', 'isupper', 'join', 'ljust', 'lower', 'lstrip', 'partition', 'replace', 'rfind', 'rindex', 'rjust', 'rpartition', 'rsplit', 'rstrip', 'split', 'splitlines', 'startswith', 'strip', 'swapcase', 'title', 'translate', 'upper', 'zfill']

可以将这些方法按功能用途划分为以下几种类型：

字符串格式输出对齐

 >>> str='stRINg lEArn'
 >>>
 >>> str.center(20)      #生成20个字符长度，str排中间
 '    stRINg lEArn    '
 >>>
 >>> str.ljust(20)       #str左对齐
 'stRINg lEArn        '
 >>>
 >>> str.rjust(20)       #str右对齐
 '        stRINg lEArn'
 >>>
 >>> str.zfill(20)       #str右对齐，左边填充0
 '00000000stRINg lEArn'

大小写转换

 >>> str='stRINg lEArn'
 >>>
 >>> str.upper() #转大写
 'STRING LEARN'
 >>>
 >>> str.lower() #转小写
 'string learn'
 >>>
 >>> str.capitalize() #字符串首为大写，其余小写
 'String learn'
 >>>
 >>> str.swapcase() #大小写对换
 'STrinG LeaRN'
 >>>
 >>> str.title() #以分隔符为标记，首字符为大写，其余为小写
 'String Learn'

字符串条件判断

 >>> str='0123'
 >>> str.isalnum()  #是否全是字母和数字，并至少有一个字符
 True
 >>> str.isdigit()   #是否全是数字，并至少有一个字符
 True

 >>> str='abcd'
 >>> str.isalnum()
 True
 >>> str.isalpha()   #是否全是字母，并至少有一个字符
 True
 >>> str.islower()   #是否全是小写，当全是小写和数字一起时候，也判断为True
 True

 >>> str='abcd0123'
 >>> str.islower()   #同上
 True
 >>> str.isalnum()
 True

 >>> str=' '
 >>> str.isspace()    #是否全是空白字符，并至少有一个字符
 True
 >>> str='ABC'
 >>> str.isupper()    #是否全是大写，当全是大写和数字一起时候，也判断为True
 True
 >>> str='Abb Acc'
 >>> str.istitle()    #所有单词字首都是大写，标题
 True

 >>> str='string learn'
 >>> str.startswith('str') #判断字符串以'str'开头
 True
 >>> str.endswith('arn')   #判读字符串以'arn'结尾
 True

字符串搜索定位与替换

 >>> str='string lEARn'
 >>>
 >>> str.find('a')      #查找字符串，没有则返回-1，有则返回查到到第一个匹配的索引
 -1
 >>> str.find('n')
 4
 >>> str.rfind('n')     #同上，只是返回的索引是最后一次匹配的
 11
 >>>
 >>> str.index('a')     #如果没有匹配则报错
 Traceback (most recent call last):
   File "", line 1, in <module>
 ValueError: substring not found
 >>> str.index('n')     #同find类似,返回第一次匹配的索引值
 4
 >>> str.rindex('n')    #返回最后一次匹配的索引值
 11
 >>>
 >>> str.count('a')     #字符串中匹配的次数
 0
 >>> str.count('n')     #同上
 2
 >>>
 >>> str.replace('EAR','ear')  #匹配替换
 'string learn'
 >>> str.replace('n','N')
 'striNg lEARN'
 >>> str.replace('n','N',1)
 'striNg lEARn'
 >>>
 >>>
 >>> str.strip('n')   #删除字符串首尾匹配的字符，通常用于默认删除回车符
 'string lEAR'
 >>> str.lstrip('n')  #左匹配
 'string lEARn'
 >>> str.rstrip('n')  #右匹配
 'string lEAR'
 >>>
 >>> str=' tab'
 >>> str.expandtabs()  #把制表符转为空格
 '      tab'
 >>> str.expandtabs(2) #指定空格数
 ' tab'

字符串编码与解码

 >>> str='字符串学习'
 >>> str
 '\xe5\xad\x97\xe7\xac\xa6\xe4\xb8\xb2\xe5\xad\xa6\xe4\xb9\xa0'
 >>>
 >>> str.decode('utf-8')               #解码过程，将utf-8解码为unicode
 u'\u5b57\u7b26\u4e32\u5b66\u4e60'

 >>> str.decode('utf-8').encode('gbk')  #编码过程，将unicode编码为gbk
 '\xd7\xd6\xb7\xfb\xb4\xae\xd1\xa7\xcf\xb0'
 >>> str.decode('utf-8').encode('utf-8')  #将unicode编码为utf-8
 '\xe5\xad\x97\xe7\xac\xa6\xe4\xb8\xb2\xe5\xad\xa6\xe4\xb9\xa0'

字符串分割变换

 >>> str='Learn string'
 >>> '-'.join(str)
 'L-e-a-r-n- -s-t-r-i-n-g'
 >>> l1=['Learn','string']
 >>> '-'.join(l1)
 'Learn-string'
 >>>
 >>> str.split('n')
 ['Lear', ' stri', 'g']
 >>> str.split('n',1)
 ['Lear', ' string']
 >>> str.rsplit('n',1)
 ['Learn stri', 'g']
 >>>
 >>> str.splitlines()
 ['Learn string']
 >>>
 >>> str.partition('n')
 ('Lear', 'n', ' string')
 >>> str.rpartition('n')
 ('Learn stri', 'n', 'g')

string模块源代码

 """A collection of string operations (most are no longer used).

 Warning: most of the code you see here isn't normally used nowadays.
 Beginning with Python 1.6, many of these functions are implemented as
 methods on the standard string object. They used to be implemented by
 a built-in module called strop, but strop is now obsolete itself.

 Public module variables:

 whitespace -- a string containing all characters considered whitespace
 lowercase -- a string containing all characters considered lowercase letters
 uppercase -- a string containing all characters considered uppercase letters
 letters -- a string containing all characters considered letters
 digits -- a string containing all characters considered decimal digits
 hexdigits -- a string containing all characters considered hexadecimal digits
 octdigits -- a string containing all characters considered octal digits
 punctuation -- a string containing all characters considered punctuation
 printable -- a string containing all characters considered printable

 """

 # Some strings for ctype-style character classification
 whitespace = ' \t\n\r\v\f'
 lowercase = 'abcdefghijklmnopqrstuvwxyz'
 uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
 letters = lowercase + uppercase
 ascii_lowercase = lowercase
 ascii_uppercase = uppercase
 ascii_letters = ascii_lowercase + ascii_uppercase
 digits = '0123456789'
 hexdigits = digits + 'abcdef' + 'ABCDEF'
 octdigits = '01234567'
 punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""
 printable = digits + letters + punctuation + whitespace

 # Case conversion helpers
 # Use str to convert Unicode literal in case of -U
 l = map(chr, xrange(256))
 _idmap = str('').join(l)
 del l

 # Functions which aren't available as string methods.

 # Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def".
 def capwords(s, sep=None):
     """capwords(s [,sep]) -> string

     Split the argument into words using split, capitalize each
     word using capitalize, and join the capitalized words using
     join. If the optional second argument sep is absent or None,
     runs of whitespace characters are replaced by a single space
     and leading and trailing whitespace are removed, otherwise
     sep is used to split and join the words.

     """
     return (sep or ' ').join(x.capitalize() for x in s.split(sep))


 # Construct a translation string
 _idmapL = None
 def maketrans(fromstr, tostr):
     """maketrans(frm, to) -> string

     Return a translation table (a string of 256 bytes long)
     suitable for use in string.translate. The strings frm and to
     must be of the same length.

     """
     if len(fromstr) != len(tostr):
         raise ValueError, "maketrans arguments must have same length"
     global _idmapL
     if not _idmapL:
         _idmapL = list(_idmap)
     L = _idmapL[:]
     fromstr = map(ord, fromstr)
     for i in range(len(fromstr)):
         L[fromstr[i]] = tostr[i]
     return ''.join(L)



 ####################################################################
 import re as _re

 class _multimap:
     """Helper class for combining multiple mappings.

     Used by .{safe_,}substitute() to combine the mapping and keyword
     arguments.
     """
     def __init__(self, primary, secondary):
         self._primary = primary
         self._secondary = secondary

     def __getitem__(self, key):
         try:
             return self._primary[key]
         except KeyError:
             return self._secondary[key]


 class _TemplateMetaclass(type):
     pattern = r"""
     %(delim)s(?:
       (?P%(delim)s) | # Escape sequence of two delimiters
       (?P%(id)s) | # delimiter and a Python identifier
       {(?P%(id)s)} | # delimiter and a braced identifier
       (?P) # Other ill-formed delimiter exprs
     )
     """

     def __init__(cls, name, bases, dct):
         super(_TemplateMetaclass, cls).__init__(name, bases, dct)
         if 'pattern' in dct:
             pattern = cls.pattern
         else:
             pattern = _TemplateMetaclass.pattern % {
                 'delim' : _re.escape(cls.delimiter),
                 'id' : cls.idpattern,
                 }
         cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE)


 class Template:
     """A string class for supporting $-substitutions."""
     __metaclass__ = _TemplateMetaclass

     delimiter = '$'
     idpattern = r'[_a-z][_a-z0-9]*'

     def __init__(self, template):
         self.template = template

     # Search for $$, $identifier, ${identifier}, and any bare $'s

     def _invalid(self, mo):
         i = mo.start('invalid')
         lines = self.template[:i].splitlines(True)
         if not lines:
             colno = 1
             lineno = 1
         else:
             colno = i - len(''.join(lines[:-1]))
             lineno = len(lines)
         raise ValueError('Invalid placeholder in string: line %d, col %d' %
                          (lineno, colno))

     def substitute(self, *args, **kws):
         if len(args) > 1:
             raise TypeError('Too many positional arguments')
         if not args:
             mapping = kws
         elif kws:
             mapping = _multimap(kws, args[0])
         else:
             mapping = args[0]
         # Helper function for .sub()
         def convert(mo):
             # Check the most common path first.
             named = mo.group('named') or mo.group('braced')
             if named is not None:
                 val = mapping[named]
                 # We use this idiom instead of str() because the latter will
                 # fail if val is a Unicode containing non-ASCII characters.
                 return '%s' % (val,)
             if mo.group('escaped') is not None:
                 return self.delimiter
             if mo.group('invalid') is not None:
                 self._invalid(mo)
             raise ValueError('Unrecognized named group in pattern',
                              self.pattern)
         return self.pattern.sub(convert, self.template)

     def safe_substitute(self, *args, **kws):
         if len(args) > 1:
             raise TypeError('Too many positional arguments')
         if not args:
             mapping = kws
         elif kws:
             mapping = _multimap(kws, args[0])
         else:
             mapping = args[0]
         # Helper function for .sub()
         def convert(mo):
             named = mo.group('named')
             if named is not None:
                 try:
                     # We use this idiom instead of str() because the latter
                     # will fail if val is a Unicode containing non-ASCII
                     return '%s' % (mapping[named],)
                 except KeyError:
                     return self.delimiter + named
             braced = mo.group('braced')
             if braced is not None:
                 try:
                     return '%s' % (mapping[braced],)
                 except KeyError:
                     return self.delimiter + '{' + braced + '}'
             if mo.group('escaped') is not None:
                 return self.delimiter
             if mo.group('invalid') is not None:
                 return self.delimiter
             raise ValueError('Unrecognized named group in pattern',
                              self.pattern)
         return self.pattern.sub(convert, self.template)



 ####################################################################
 # NOTE: Everything below here is deprecated. Use string methods instead.
 # This stuff will go away in Python 3.0.

 # Backward compatible names for exceptions
 index_error = ValueError
 atoi_error = ValueError
 atof_error = ValueError
 atol_error = ValueError

 # convert UPPER CASE letters to lower case
 def lower(s):
     """lower(s) -> string

     Return a copy of the string s converted to lowercase.

     """
     return s.lower()

 # Convert lower case letters to UPPER CASE
 def upper(s):
     """upper(s) -> string

     Return a copy of the string s converted to uppercase.

     """
     return s.upper()

 # Swap lower case letters and UPPER CASE
 def swapcase(s):
     """swapcase(s) -> string

     Return a copy of the string s with upper case characters
     converted to lowercase and vice versa.

     """
     return s.swapcase()

 # Strip leading and trailing tabs and spaces
 def strip(s, chars=None):
     """strip(s [,chars]) -> string

     Return a copy of the string s with leading and trailing
     whitespace removed.
     If chars is given and not None, remove characters in chars instead.
     If chars is unicode, S will be converted to unicode before stripping.

     """
     return s.strip(chars)

 # Strip leading tabs and spaces
 def lstrip(s, chars=None):
     """lstrip(s [,chars]) -> string

     Return a copy of the string s with leading whitespace removed.
     If chars is given and not None, remove characters in chars instead.

     """
     return s.lstrip(chars)

 # Strip trailing tabs and spaces
 def rstrip(s, chars=None):
     """rstrip(s [,chars]) -> string

     Return a copy of the string s with trailing whitespace removed.
     If chars is given and not None, remove characters in chars instead.

     """
     return s.rstrip(chars)


 # Split a string into a list of space/tab-separated words
 def split(s, sep=None, maxsplit=-1):
     """split(s [,sep [,maxsplit]]) -> list of strings

     Return a list of the words in the string s, using sep as the
     delimiter string. If maxsplit is given, splits at no more than
     maxsplit places (resulting in at most maxsplit+1 words). If sep
     is not specified or is None, any whitespace string is a separator.

     (split and splitfields are synonymous)

     """
     return s.split(sep, maxsplit)
 splitfields = split

 # Split a string into a list of space/tab-separated words
 def rsplit(s, sep=None, maxsplit=-1):
     """rsplit(s [,sep [,maxsplit]]) -> list of strings

     Return a list of the words in the string s, using sep as the
     delimiter string, starting at the end of the string and working
     to the front. If maxsplit is given, at most maxsplit splits are
     done. If sep is not specified or is None, any whitespace string
     is a separator.
     """
     return s.rsplit(sep, maxsplit)

 # Join fields with optional separator
 def join(words, sep = ' '):
     """join(list [,sep]) -> string

     Return a string composed of the words in list, with
     intervening occurrences of sep. The default separator is a
     single space.

     (joinfields and join are synonymous)

     """
     return sep.join(words)
 joinfields = join

 # Find substring, raise exception if not found
 def index(s, *args):
     """index(s, sub [,start [,end]]) -> int

     Like find but raises ValueError when the substring is not found.

     """
     return s.index(*args)

 # Find last substring, raise exception if not found
 def rindex(s, *args):
     """rindex(s, sub [,start [,end]]) -> int

     Like rfind but raises ValueError when the substring is not found.

     """
     return s.rindex(*args)

 # Count non-overlapping occurrences of substring
 def count(s, *args):
     """count(s, sub[, start[,end]]) -> int

     Return the number of occurrences of substring sub in string
     s[start:end]. Optional arguments start and end are
     interpreted as in slice notation.

     """
     return s.count(*args)

 # Find substring, return -1 if not found
 def find(s, *args):
     """find(s, sub [,start [,end]]) -> in

     Return the lowest index in s where substring sub is found,
     such that sub is contained within s[start,end]. Optional
     arguments start and end are interpreted as in slice notation.

     Return -1 on failure.

     """
     return s.find(*args)

 # Find last substring, return -1 if not found
 def rfind(s, *args):
     """rfind(s, sub [,start [,end]]) -> int

     Return the highest index in s where substring sub is found,
     such that sub is contained within s[start,end]. Optional
     arguments start and end are interpreted as in slice notation.

     Return -1 on failure.

     """
     return s.rfind(*args)

 # for a bit of speed
 _float = float
 _int = int
 _long = long

 # Convert string to float
 def atof(s):
     """atof(s) -> float

     Return the floating point number represented by the string s.

     """
     return _float(s)


 # Convert string to integer
 def atoi(s , base=10):
     """atoi(s [,base]) -> int

     Return the integer represented by the string s in the given
     base, which defaults to 10. The string s must consist of one
     or more digits, possibly preceded by a sign. If base is 0, it
     is chosen from the leading characters of s, 0 for octal, 0x or
     0X for hexadecimal. If base is 16, a preceding 0x or 0X is
     accepted.

     """
     return _int(s, base)


 # Convert string to long integer
 def atol(s, base=10):
     """atol(s [,base]) -> long

     Return the long integer represented by the string s in the
     given base, which defaults to 10. The string s must consist
     of one or more digits, possibly preceded by a sign. If base
     is 0, it is chosen from the leading characters of s, 0 for
     octal, 0x or 0X for hexadecimal. If base is 16, a preceding
     0x or 0X is accepted. A trailing L or l is not accepted,
     unless base is 0.

     """
     return _long(s, base)


 # Left-justify a string
 def ljust(s, width, *args):
     """ljust(s, width[, fillchar]) -> string

     Return a left-justified version of s, in a field of the
     specified width, padded with spaces as needed. The string is
     never truncated. If specified the fillchar is used instead of spaces.

     """
     return s.ljust(width, *args)

 # Right-justify a string
 def rjust(s, width, *args):
     """rjust(s, width[, fillchar]) -> string

     Return a right-justified version of s, in a field of the
     specified width, padded with spaces as needed. The string is
     never truncated. If specified the fillchar is used instead of spaces.

     """
     return s.rjust(width, *args)

 # Center a string
 def center(s, width, *args):
     """center(s, width[, fillchar]) -> string

     Return a center version of s, in a field of the specified
     width. padded with spaces as needed. The string is never
     truncated. If specified the fillchar is used instead of spaces.

     """
     return s.center(width, *args)

 # Zero-fill a number, e.g., (12, 3) --> '012' and (-3, 3) --> '-03'
 # Decadent feature: the argument may be a string or a number
 # (Use of this is deprecated; it should be a string as with ljust c.s.)
 def zfill(x, width):
     """zfill(x, width) -> string

     Pad a numeric string x with zeros on the left, to fill a field
     of the specified width. The string x is never truncated.

     """
     if not isinstance(x, basestring):
         x = repr(x)
     return x.zfill(width)

 # Expand tabs in a string.
 # Doesn't take non-printing chars into account, but does understand \n.
 def expandtabs(s, tabsize=8):
     """expandtabs(s [,tabsize]) -> string

     Return a copy of the string s with all tab characters replaced
     by the appropriate number of spaces, depending on the current
     column, and the tabsize (default 8).

     """
     return s.expandtabs(tabsize)

 # Character translation through look-up table.
 def translate(s, table, deletions=""):
     """translate(s,table [,deletions]) -> string

     Return a copy of the string s, where all characters occurring
     in the optional argument deletions are removed, and the
     remaining characters have been mapped through the given
     translation table, which must be a string of length 256. The
     deletions argument is not allowed for Unicode strings.

     """
     if deletions or table is None:
         return s.translate(table, deletions)
     else:
         # Add s[:0] so that if s is Unicode and table is an 8-bit string,
         # table is converted to Unicode. This means that table *cannot*
         # be a dictionary -- for that feature, use u.translate() directly.
         return s.translate(table + s[:0])

 # Capitalize a string, e.g. "aBc dEf" -> "Abc def".
 def capitalize(s):
     """capitalize(s) -> string

     Return a copy of the string s with only its first character
     capitalized.

     """
     return s.capitalize()

 # Substring replacement (global)
 def replace(s, old, new, maxsplit=-1):
     """replace (str, old, new[, maxsplit]) -> string

     Return a copy of string str with all occurrences of substring
     old replaced by new. If the optional argument maxsplit is
     given, only the first maxsplit occurrences are replaced.

     """
     return s.replace(old, new, maxsplit)


 # Try importing optional built-in module "strop" -- if it exists,
 # it redefines some string operations that are 100-1000 times faster.
 # It also defines values for whitespace, lowercase and uppercase
 # that match <ctype.h>'s definitions.

 try:
     from strop import maketrans, lowercase, uppercase, whitespace
     letters = lowercase + uppercase
 except ImportError:
     pass # Use the original versions

 ########################################################################
 # the Formatter class
 # see PEP 3101 for details and purpose of this class

 # The hard parts are reused from the C implementation. They're exposed as "_"
 # prefixed methods of str and unicode.

 # The overall parser is implemented in str._formatter_parser.
 # The field name parser is implemented in str._formatter_field_name_split

 class Formatter(object):
     def format(self, format_string, *args, **kwargs):
         return self.vformat(format_string, args, kwargs)

     def vformat(self, format_string, args, kwargs):
         used_args = set()
         result = self._vformat(format_string, args, kwargs, used_args, 2)
         self.check_unused_args(used_args, args, kwargs)
         return result

     def _vformat(self, format_string, args, kwargs, used_args, recursion_depth):
         if recursion_depth < 0:
             raise ValueError('Max string recursion exceeded')
         result = []
         for literal_text, field_name, format_spec, conversion in \
                 self.parse(format_string):

             # output the literal text
             if literal_text:
                 result.append(literal_text)

             # if there's a field, output it
             if field_name is not None:
                 # this is some markup, find the object and do
                 # the formatting

                 # given the field_name, find the object it references
                 # and the argument it came from
                 obj, arg_used = self.get_field(field_name, args, kwargs)
                 used_args.add(arg_used)

                 # do any conversion on the resulting object
                 obj = self.convert_field(obj, conversion)

                 # expand the format spec, if needed
                 format_spec = self._vformat(format_spec, args, kwargs,
                                             used_args, recursion_depth-1)

                 # format the object and append to the result
                 result.append(self.format_field(obj, format_spec))

         return ''.join(result)


     def get_value(self, key, args, kwargs):
         if isinstance(key, (int, long)):
             return args[key]
         else:
             return kwargs[key]


     def check_unused_args(self, used_args, args, kwargs):
         pass


     def format_field(self, value, format_spec):
         return format(value, format_spec)


     def convert_field(self, value, conversion):
         # do any conversion on the resulting object
         if conversion == 'r':
             return repr(value)
         elif conversion == 's':
             return str(value)
         elif conversion is None:
             return value
         raise ValueError("Unknown converion specifier {0!s}".format(conversion))


     # returns an iterable that contains tuples of the form:
     # (literal_text, field_name, format_spec, conversion)
     # literal_text can be zero length
     # field_name can be None, in which case there's no
     # object to format and output
     # if field_name is not None, it is looked up, formatted
     # with format_spec and conversion and then used
     def parse(self, format_string):
         return format_string._formatter_parser()


     # given a field_name, find the object it references.
     # field_name: the field being looked up, e.g. "0.name"
     # or "lookup[3]"
     # used_args: a set of which args have been used
     # args, kwargs: as passed in to vformat
     def get_field(self, field_name, args, kwargs):
         first, rest = field_name._formatter_field_name_split()

         obj = self.get_value(first, args, kwargs)

         # loop through the rest of the field_name, doing
         # getattr or getitem as needed
         for is_attr, i in rest:
             if is_attr:
                 obj = getattr(obj, i)
             else:
                 obj = obj[i]

         return obj, first