|
def | __init__ (self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None) |
|
def | parseImpl (self, instring, loc, doActions=True) |
|
def | __str__ (self) |
|
def | __init__ (self) |
|
def | __init__ (self, savelist=False) |
|
def | copy (self) |
|
def | setName (self, name) |
|
def | setResultsName (self, name, listAllMatches=False) |
|
def | setBreak (self, breakFlag=True) |
|
def | setParseAction (self, *fns, **kwargs) |
|
def | addParseAction (self, *fns, **kwargs) |
|
def | addCondition (self, *fns, **kwargs) |
|
def | setFailAction (self, fn) |
|
def | preParse (self, instring, loc) |
|
def | postParse (self, instring, loc, tokenlist) |
|
def | tryParse (self, instring, loc) |
|
def | canParseNext (self, instring, loc) |
|
def | parseString (self, instring, parseAll=False) |
|
def | scanString (self, instring, maxMatches=_MAX_INT, overlap=False) |
|
def | transformString (self, instring) |
|
def | searchString (self, instring, maxMatches=_MAX_INT) |
|
def | split (self, instring, maxsplit=_MAX_INT, includeSeparators=False) |
|
def | __add__ (self, other) |
|
def | __radd__ (self, other) |
|
def | __sub__ (self, other) |
|
def | __rsub__ (self, other) |
|
def | __mul__ (self, other) |
|
def | __rmul__ (self, other) |
|
def | __or__ (self, other) |
|
def | __ror__ (self, other) |
|
def | __xor__ (self, other) |
|
def | __rxor__ (self, other) |
|
def | __and__ (self, other) |
|
def | __rand__ (self, other) |
|
def | __invert__ (self) |
|
def | __iter__ (self) |
|
def | __getitem__ (self, key) |
|
def | __call__ (self, name=None) |
|
def | suppress (self) |
|
def | leaveWhitespace (self) |
|
def | setWhitespaceChars (self, chars) |
|
def | parseWithTabs (self) |
|
def | ignore (self, other) |
|
def | setDebugActions (self, startAction, successAction, exceptionAction) |
|
def | setDebug (self, flag=True) |
|
def | __repr__ (self) |
|
def | streamline (self) |
|
def | checkRecursion (self, parseElementList) |
|
def | validate (self, validateTrace=None) |
|
def | parseFile (self, file_or_filename, parseAll=False) |
|
def | __eq__ (self, other) |
|
def | __ne__ (self, other) |
|
def | __hash__ (self) |
|
def | __req__ (self, other) |
|
def | __rne__ (self, other) |
|
def | matches (self, testString, parseAll=True) |
|
def | runTests (self, tests, parseAll=True, comment='#', fullDump=True, printResults=True, failureTests=False, postParse=None, file=None) |
|
Token for matching words composed of allowed character sets.
Defined with string containing all allowed initial characters, an
optional string containing allowed body characters (if omitted,
defaults to the initial character set), and an optional minimum,
maximum, and/or exact length. The default value for ``min`` is
1 (a minimum value < 1 is not valid); the default values for
``max`` and ``exact`` are 0, meaning no maximum or exact
length restriction. An optional ``excludeChars`` parameter can
list characters that might be found in the input ``bodyChars``
string; useful to define a word of all printables except for one or
two characters, for instance.
:class:`srange` is useful for defining custom character set strings
for defining ``Word`` expressions, using range notation from
regular expression character sets.
A common mistake is to use :class:`Word` to match a specific literal
string, as in ``Word("Address")``. Remember that :class:`Word`
uses the string argument to define *sets* of matchable characters.
This expression would match "Add", "AAA", "dAred", or any other word
made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an
exact literal string, use :class:`Literal` or :class:`Keyword`.
pyparsing includes helper strings for building Words:
- :class:`alphas`
- :class:`nums`
- :class:`alphanums`
- :class:`hexnums`
- :class:`alphas8bit` (alphabetic characters in ASCII range 128-255
- accented, tilded, umlauted, etc.)
- :class:`punc8bit` (non-alphabetic characters in ASCII range
128-255 - currency, symbols, superscripts, diacriticals, etc.)
- :class:`printables` (any non-whitespace character)
Example::
# a word composed of digits
integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9"))
# a word with a leading capital, and zero or more lowercase
capital_word = Word(alphas.upper(), alphas.lower())
# hostnames are alphanumeric, with leading alpha, and '-'
hostname = Word(alphas, alphanums + '-')
# roman numeral (not a strict parser, accepts invalid mix of characters)
roman = Word("IVXLCDM")
# any string of non-whitespace characters, except for ','
csv_value = Word(printables, excludeChars=",")