Python string.split() Examples

def _format_changelog(self, changelog):
        """Format the changelog correctly and convert it to a list of strings
        """
        if not changelog:
            return changelog
        new_changelog = []
        for line in string.split(string.strip(changelog), '\n'):
            line = string.strip(line)
            if line[0] == '*':
                new_changelog.extend(['', line])
            elif line[0] == '-':
                new_changelog.append(line)
            else:
                new_changelog.append('  ' + line)

        # strip trailing newline inserted by first changelog entry
        if not new_changelog[0]:
            del new_changelog[0]

        return new_changelog

    # _format_changelog()

# class bdist_rpm 

def _initializePOSTables():
    global _POSNormalizationTable, _POStoDictionaryTable
    _POSNormalizationTable = {}
    _POStoDictionaryTable = {}
    for pos, abbreviations in (
	    (NOUN, "noun n n."),
	    (VERB, "verb v v."),
	    (ADJECTIVE, "adjective adj adj. a s"),
	    (ADVERB, "adverb adv adv. r")):
	tokens = string.split(abbreviations)
	for token in tokens:
	    _POSNormalizationTable[token] = pos
	    _POSNormalizationTable[string.upper(token)] = pos
    for dict in Dictionaries:
	_POSNormalizationTable[dict] = dict.pos
	_POStoDictionaryTable[dict.pos] = dict 

def _parse_record(s):
    """
    Deprecated: use C{StandardFormat.fields()}
    
    @param s: toolbox record as a string
    @type  s: L{string}
    @rtype: iterator over L{list(string)}
    """

    s = "\n" + s                                         # Fields (even first) must start w/ a carriage return 
    if s.endswith("\n") : s = s[:-1]                     # Remove single extra carriage return
    for field in split(s, sep="\n\\")[1:] :              # Parse by carriage return followed by backslash
        parsed_field = split(field, sep=" ", maxsplit=1) # Split properly delineated field
        try :
            yield (parsed_field[0], parsed_field[1])
        except IndexError :
            yield (parsed_field[0], '') 

def type_identityref_values(self, t):
        base_idn = t.search_one('base')
        if base_idn:
            # identity has a base
            idn_key = None
            base_idns = base_idn.arg.split(':')
            if len(base_idns) > 1:
                for module in self.module_prefixes:
                    if base_idns[0] == self.module_prefixes[module][0]:
                        idn_key = module + ':' + base_idns[1]
                        break
            else:
                idn_key = self.name + ':' + base_idn.arg

            if idn_key is None:
                return ''

            value_stmts = []
            stmts = self.identity_deps.get(idn_key, [])
            for value in stmts:
                ids = value.split(':')
                value_stmts.append(self.module_prefixes[ids[0]][0] + ':' + ids[1])
            if stmts:
                return '|'.join(sorted(value_stmts))
        return '' 

def _substitute(self, str):
        """
        Substitute words in the string, according to the specified reflections,
        e.g. "I'm" -> "you are"
        
        @type str: C{string}
        @param str: The string to be mapped
        @rtype: C{string}
        """

        words = ""
        for word in string.split(string.lower(str)):
            if self._reflections.has_key(word):
                word = self._reflections[word]
            words += ' ' + word
        return words 

def _initializePOSTables():
    global _POSNormalizationTable, _POStoDictionaryTable
    _POSNormalizationTable = {}
    _POStoDictionaryTable = {}
    for pos, abbreviations in (
	    (NOUN, "noun n n."),
	    (VERB, "verb v v."),
	    (ADJECTIVE, "adjective adj adj. a s"),
	    (ADVERB, "adverb adv adv. r")):
	tokens = string.split(abbreviations)
	for token in tokens:
	    _POSNormalizationTable[token] = pos
	    _POSNormalizationTable[string.upper(token)] = pos
    for dict in Dictionaries:
	_POSNormalizationTable[dict] = dict.pos
	_POStoDictionaryTable[dict.pos] = dict 

def version_checker(cur_ver,ref_ver):
	"""
	Checks version in major/minor format of a current version versus a reference version.
	Supports 2 or more level versioning, only 2 levels checked)

	Input:
	cur_ver: float or string of version to check
	ref_ver: float or string of reference version

	Returns:
	bool for pass or fail
	"""
	cur_ver = str(cur_ver)
	ref_ver = str(ref_ver)
	cur_Varr = [int(vvv) for vvv in cur_ver.split('.')[0:2]]
	cur_V = cur_Varr[0]*10**2 + cur_Varr[1]%100
	ref_Varr = [int(vvv) for vvv in ref_ver.split('.')[0:2]]
	ref_V = ref_Varr[0]*10**2 + ref_Varr[1]%100
	if cur_V > ref_V: return True
	return False

#Run dependency check 

def version_checker(cur_ver,ref_ver):
	"""
	Checks version in major/minor format of a current version versus a reference version.
	Supports 2 or more level versioning, only 2 levels checked)

	Input:
	cur_ver: float or string of version to check
	ref_ver: float or string of reference version

	Returns:
	bool for pass or fail
	"""
	cur_ver = str(cur_ver)
	ref_ver = str(ref_ver)
	cur_Varr = [int(vvv) for vvv in cur_ver.split('.')[0:2]]
	cur_V = cur_Varr[0]*10**2 + cur_Varr[1]%100
	ref_Varr = [int(vvv) for vvv in ref_ver.split('.')[0:2]]
	ref_V = ref_Varr[0]*10**2 + ref_Varr[1]%100
	if cur_V > ref_V: return True
	return False

#Run dependency check 

def ParseMetricFile(file_name, metric_column):
  """
  Convert a metrics file into a set of numbers.
  This returns a sorted list of tuples with the first number
  being from the first column (bitrate) and the second being from
  metric_column (counting from 0).
  """
  metric_set1 = set([])
  metric_file = open(file_name, "r")
  for line in metric_file:
    metrics = string.split(line)
    if HasMetrics(line):
      if metric_column < len(metrics):
        my_tuple = float(metrics[0]), float(metrics[metric_column])
      else:
        my_tuple = float(metrics[0]), 0
      metric_set1.add(my_tuple)
  metric_set1_sorted = sorted(metric_set1)
  return metric_set1_sorted 

def main():
    print "This program converts a sequence of ASCII numbers into"
    print "the string of text that it represents."
    print
    
    inString = raw_input("Please enter the ASCII-encoded message: ")

    message = []
    for numStr in string.split(inString):
        asciiNum = eval(numStr) 
        message1 = ord(asciiNum)          # convert digits to a number
        message.append(message1)

    print message
        
    print "The decoded message is:","".join(message) 

def round_sig_error(x, ex, n, paren=False):
   '''Find ex rounded to n sig-figs and make the floating point x
   match the number of decimals.  If [paren], the string is
   returned as quantity(error) format'''
   stex = round_sig(ex,n)
   if stex.find('.') < 0:
      extra_zeros = len(stex) - n
      sigfigs = len(str(int(x))) - extra_zeros
      stx = round_sig(x,sigfigs)
   else:
      num_after_dec = len(string.split(stex,'.')[1])
      stx = ("%%.%df" % num_after_dec) % (x)
   if paren:
      if stex.find('.') >= 0:
         stex = stex[stex.find('.')+1:]
      return "%s(%s)" % (stx,stex)
   return stx,stex 

def round_sig_error2(x, ex1, ex2, n):
   '''Find min(ex1,ex2) rounded to n sig-figs and make the floating point x
   and max(ex,ex2) match the number of decimals.'''
   minerr = min(ex1,ex2)
   minstex = round_sig(minerr,n)
   if minstex.find('.') < 0:
      extra_zeros = len(minstex) - n
      sigfigs = len(str(int(x))) - extra_zeros
      stx = round_sig(x,sigfigs)
      maxstex = round_sig(max(ex1,ex2),sigfigs)
   else:
      num_after_dec = len(string.split(minstex,'.')[1])
      stx = ("%%.%df" % num_after_dec) % (x)
      maxstex = ("%%.%df" % num_after_dec) % (max(ex1,ex2))
   if ex1 < ex2:
      return stx,minstex,maxstex
   else:
      return stx,maxstex,minstex 

def _extract_authdata(item):
    '''
    Extract version, authority tag, and authority data from a single array item of AuthenticationAuthority

    item
        The NSString instance representing the authority string

    returns
        version (default 1.0.0), tag, data as a tuple
    '''
    parts = string.split(item, ';', 2)

    if not parts[0]:
        parts[0] = '1.0.0'

    return {
        'version': parts[0],
        'tag': parts[1],
        'data': parts[2]
    } 

def find_exe(self, exe):
        """Return path to an MSVC executable program.

        Tries to find the program in several places: first, one of the
        MSVC program search paths from the registry; next, the directories
        in the PATH environment variable.  If any of those work, return an
        absolute path that is known to exist.  If none of them work, just
        return the original program name, 'exe'.
        """

        for p in self.__paths:
            fn = os.path.join(os.path.abspath(p), exe)
            if os.path.isfile(fn):
                return fn

        # didn't find it; try existing path
        for p in string.split(os.environ['Path'],';'):
            fn = os.path.join(os.path.abspath(p),exe)
            if os.path.isfile(fn):
                return fn

        return exe 

def get_build_version():
    """Return the version of MSVC that was used to build Python.

    For Python 2.3 and up, the version number is included in
    sys.version.  For earlier versions, assume the compiler is MSVC 6.
    """

    prefix = "MSC v."
    i = string.find(sys.version, prefix)
    if i == -1:
        return 6
    i = i + len(prefix)
    s, rest = sys.version[i:].split(" ", 1)
    majorVersion = int(s[:-2]) - 6
    minorVersion = int(s[2:3]) / 10.0
    # I don't think paths are affected by minor version in version 6
    if majorVersion == 6:
        minorVersion = 0
    if majorVersion >= 6:
        return majorVersion + minorVersion
    # else we don't know what version of the compiler this is
    return None 

def SubstituteInString(inString, evalEnv):
	substChar = "$"
	fields = string.split(inString, substChar)
	newFields = []
	for i in range(len(fields)):
		didSubst = 0
		strVal = fields[i]
		if i%2!=0:
			try:
				strVal = eval(strVal,evalEnv[0], evalEnv[1])
				newFields.append(strVal)
				didSubst = 1
			except:
				traceback.print_exc()
				print "Could not substitute", strVal
		if not didSubst:
			newFields.append(strVal)
	return string.join(map(str, newFields), "") 

def _norm_version(version, build=''):

    """ Normalize the version and build strings and return a single
        version string using the format major.minor.build (or patchlevel).
    """
    l = string.split(version,'.')
    if build:
        l.append(build)
    try:
        ints = map(int,l)
    except ValueError:
        strings = l
    else:
        strings = map(str,ints)
    version = string.join(strings[:3],'.')
    return version 

def help(self, request):
        if type(request) is type(''):
            request = request.strip()
            if request == 'help': self.intro()
            elif request == 'keywords': self.listkeywords()
            elif request == 'symbols': self.listsymbols()
            elif request == 'topics': self.listtopics()
            elif request == 'modules': self.listmodules()
            elif request[:8] == 'modules ':
                self.listmodules(split(request)[1])
            elif request in self.symbols: self.showsymbol(request)
            elif request in self.keywords: self.showtopic(request)
            elif request in self.topics: self.showtopic(request)
            elif request: doc(request, 'Help on %s:')
        elif isinstance(request, Helper): self()
        else: doc(request, 'Help on %s:')
        self.output.write('\n') 

def locate(path, forceload=0):
    """Locate an object by name or dotted path, importing as necessary."""
    parts = [part for part in split(path, '.') if part]
    module, n = None, 0
    while n < len(parts):
        nextmodule = safeimport(join(parts[:n+1], '.'), forceload)
        if nextmodule: module, n = nextmodule, n + 1
        else: break
    if module:
        object = module
        for part in parts[n:]:
            try: object = getattr(object, part)
            except AttributeError: return None
        return object
    else:
        if hasattr(__builtin__, path):
            return getattr(__builtin__, path)

# --------------------------------------- interactive interpreter interface 

def source_synopsis(file):
    line = file.readline()
    while line[:1] == '#' or not strip(line):
        line = file.readline()
        if not line: break
    line = strip(line)
    if line[:4] == 'r"""': line = line[1:]
    if line[:3] == '"""':
        line = line[3:]
        if line[-1:] == '\\': line = line[:-1]
        while not strip(line):
            line = file.readline()
            if not line: break
        result = strip(split(line, '"""')[0])
    else: result = None
    return result 

def _format_changelog(self, changelog):
        """Format the changelog correctly and convert it to a list of strings
        """
        if not changelog:
            return changelog
        new_changelog = []
        for line in string.split(string.strip(changelog), '\n'):
            line = string.strip(line)
            if line[0] == '*':
                new_changelog.extend(['', line])
            elif line[0] == '-':
                new_changelog.append(line)
            else:
                new_changelog.append('  ' + line)

        # strip trailing newline inserted by first changelog entry
        if not new_changelog[0]:
            del new_changelog[0]

        return new_changelog

    # _format_changelog()

# class bdist_rpm 

def get_build_version():
    """Return the version of MSVC that was used to build Python.

    For Python 2.3 and up, the version number is included in
    sys.version.  For earlier versions, assume the compiler is MSVC 6.
    """

    prefix = "MSC v."
    i = string.find(sys.version, prefix)
    if i == -1:
        return 6
    i = i + len(prefix)
    s, rest = sys.version[i:].split(" ", 1)
    majorVersion = int(s[:-2]) - 6
    minorVersion = int(s[2:3]) / 10.0
    # I don't think paths are affected by minor version in version 6
    if majorVersion == 6:
        minorVersion = 0
    if majorVersion >= 6:
        return majorVersion + minorVersion
    # else we don't know what version of the compiler this is
    return None 

def encode_name(name, type, scope):
    if name == '*':
        name += '\0' * 15
    elif len(name) > 15:
        name = name[:15] + chr(type)
    else:
        name = string.ljust(name, 15) + chr(type)

    encoded_name = chr(len(name) * 2) + re.sub('.', _do_first_level_encoding, name)
    if scope:
        encoded_scope = ''
        for s in string.split(scope, '.'):
            encoded_scope = encoded_scope + chr(len(s)) + s
        return encoded_name + encoded_scope + '\0'
    else:
        return encoded_name.encode('ascii') + '\0'

# Internal method for use in encode_name() 

def showtopic(self, topic, more_xrefs=''):
        try:
            import pydoc_data.topics
        except ImportError:
            self.output.write('''
Sorry, topic and keyword documentation is not available because the
module "pydoc_data.topics" could not be found.
''')
            return
        target = self.topics.get(topic, self.keywords.get(topic))
        if not target:
            self.output.write('no documentation found for %s\n' % repr(topic))
            return
        if type(target) is type(''):
            return self.showtopic(target, more_xrefs)

        label, xrefs = target
        try:
            doc = pydoc_data.topics.topics[label]
        except KeyError:
            self.output.write('no documentation found for %s\n' % repr(topic))
            return
        pager(strip(doc) + '\n')
        if more_xrefs:
            xrefs = (xrefs or '') + ' ' + more_xrefs
        if xrefs:
            import StringIO, formatter
            buffer = StringIO.StringIO()
            formatter.DumbWriter(buffer).send_flowing_data(
                'Related help topics: ' + join(split(xrefs), ', ') + '\n')
            self.output.write('\n%s\n' % buffer.getvalue()) 

def __init__(self, ret_type, name, params, mods=None):
        self.param_list = map(lambda s: s.strip(), string.split(params, ","))
        self.param_list = filter(lambda s: s, self.param_list)
        self.ret_type = ret_type
        self.name = name
        self.mods = mods
        self.is_invokable = True 

def cleandoc(doc):
    """Clean up indentation from docstrings.

    Any whitespace that can be uniformly removed from the second line
    onwards is removed."""
    try:
        lines = string.split(string.expandtabs(doc), '\n')
    except UnicodeError:
        return None
    else:
        # Find minimum indentation of any non-blank lines after first line.
        margin = sys.maxint
        for line in lines[1:]:
            content = len(string.lstrip(line))
            if content:
                indent = len(line) - content
                margin = min(margin, indent)
        # Remove indentation.
        if lines:
            lines[0] = lines[0].lstrip()
        if margin < sys.maxint:
            for i in range(1, len(lines)): lines[i] = lines[i][margin:]
        # Remove any trailing or leading blank lines.
        while lines and not lines[-1]:
            lines.pop()
        while lines and not lines[0]:
            lines.pop(0)
        return string.join(lines, '\n') 

def python_version_tuple():

    """ Returns the Python version as tuple (major, minor, patchlevel)
        of strings.

        Note that unlike the Python sys.version, the returned value
        will always include the patchlevel (it defaults to 0).

    """
    return tuple(string.split(_sys_version()[1], '.')) 

def _parse_release_file(firstline):

    # Default to empty 'version' and 'id' strings.  Both defaults are used
    # when 'firstline' is empty.  'id' defaults to empty when an id can not
    # be deduced.
    version = ''
    id = ''

    # Parse the first line
    m = _lsb_release_version.match(firstline)
    if m is not None:
        # LSB format: "distro release x.x (codename)"
        return tuple(m.groups())

    # Pre-LSB format: "distro x.x (codename)"
    m = _release_version.match(firstline)
    if m is not None:
        return tuple(m.groups())

    # Unkown format... take the first two words
    l = string.split(string.strip(firstline))
    if l:
        version = l[0]
        if len(l) > 1:
            id = l[1]
    return '', version, id 

def repr1(self, x, level):
        if hasattr(type(x), '__name__'):
            methodname = 'repr_' + join(split(type(x).__name__), '_')
            if hasattr(self, methodname):
                return getattr(self, methodname)(x, level)
        return cram(stripid(repr(x)), self.maxother) 

def indent(self, text, prefix='    '):
        """Indent text by prepending a given prefix to each line."""
        if not text: return ''
        lines = split(text, '\n')
        lines = map(lambda line, prefix=prefix: prefix + line, lines)
        if lines: lines[-1] = rstrip(lines[-1])
        return join(lines, '\n')