# module pyparsing.py
#
# Copyright (c) 2003-2018  Paul T. McGuire
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#

__doc__ = \
"""
pyparsing module - Classes and methods to define and execute parsing grammars
=============================================================================

The pyparsing module is an alternative approach to creating and executing simple grammars,
vs. the traditional lex/yacc approach, or the use of regular expressions.  With pyparsing, you
don't need to learn a new syntax for defining grammars or matching expressions - the parsing module
provides a library of classes that you use to construct the grammar directly in Python.

Here is a program to parse "Hello, World!" (or any greeting of the form 
C{"<salutation>, <addressee>!"}), built up using L{Word}, L{Literal}, and L{And} elements 
(L{'+'<ParserElement.__add__>} operator gives L{And} expressions, strings are auto-converted to
L{Literal} expressions)::

    from pip._vendor.pyparsing import Word, alphas

    # define grammar of a greeting
    greet = Word(alphas) + "," + Word(alphas) + "!"

    hello = "Hello, World!"
    print (hello, "->", greet.parseString(hello))

The program outputs the following::

    Hello, World! -> ['Hello', ',', 'World', '!']

The Python representation of the grammar is quite readable, owing to the self-explanatory
class names, and the use of '+', '|' and '^' operators.

The L{ParseResults} object returned from L{ParserElement.parseString<ParserElement.parseString>} can be accessed as a nested list, a dictionary, or an
object with named attributes.

The pyparsing module handles some of the problems that are typically vexing when writing text parsers:
 - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello  ,  World  !", etc.)
 - quoted strings
 - embedded comments


Getting Started -
-----------------
Visit the classes L{ParserElement} and L{ParseResults} to see the base classes that most other pyparsing
classes inherit from. Use the docstrings for examples of how to:
 - construct literal match expressions from L{Literal} and L{CaselessLiteral} classes
 - construct character word-group expressions using the L{Word} class
 - see how to create repetitive expressions using L{ZeroOrMore} and L{OneOrMore} classes
 - use L{'+'<And>}, L{'|'<MatchFirst>}, L{'^'<Or>}, and L{'&'<Each>} operators to combine simple expressions into more complex ones
 - associate names with your parsed results using L{ParserElement.setResultsName}
 - find some helpful expression short-cuts like L{delimitedList} and L{oneOf}
 - find more useful common expressions in the L{pyparsing_common} namespace class
"""

__version__ = "2.2.1"
__versionTime__ = "18 Sep 2018 00:49 UTC"
__author__ = "Paul McGuire <ptmcg@users.sourceforge.net>"

import string
from weakref import ref as wkref
import copy
import sys
import warnings
import re
import sre_constants
import collections
import pprint
import traceback
import types
from datetime import datetime

try:
    from _thread import RLock
except ImportError:
    from threading import RLock

try:
    # Python 3
    from collections.abc import Iterable
    from collections.abc import MutableMapping
except ImportError:
    # Python 2.7
    from collections import Iterable
    from collections import MutableMapping

try:
    from collections import OrderedDict as _OrderedDict
except ImportError:
    try:
        from ordereddict import OrderedDict as _OrderedDict
    except ImportError:
        _OrderedDict = None

#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) )

__all__ = [
'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty',
'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal',
'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or',
'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException',
'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException',
'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 
'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore',
'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col',
'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString',
'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums',
'htmlComment', 'javaStyleComment', 'line', 'lineEnd', 'lineStart', 'lineno',
'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral',
'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables',
'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity', 
'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd',
'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute',
'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation','locatedExpr', 'withClass',
'CloseMatch', 'tokenMap', 'pyparsing_common',
]

system_version = tuple(sys.version_info)[:3]
PY_3 = system_version[0] == 3
if PY_3:
    _MAX_INT = sys.maxsize
    basestring = str
    unichr = chr
    _ustr = str

    # build list of single arg builtins, that can be used as parse actions
    singleArgBuiltins = [sum, len, sorted, reversed, list, tuple, set, any, all, min, max]

else:
    _MAX_INT = sys.maxint
    range = xrange

    def _ustr(obj):
        """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries
           str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It
           then < returns the unicode object | encodes it with the default encoding | ... >.
        """
        if isinstance(obj,unicode):
            return obj

        try:
            # If this works, then _ustr(obj) has the same behaviour as str(obj), so
            # it won't break any existing code.
            return str(obj)

        except UnicodeEncodeError:
            # Else encode it
            ret = unicode(obj).encode(sys.getdefaultencoding(), 'xmlcharrefreplace')
            xmlcharref = Regex(r'&#\d+;')
            xmlcharref.setParseAction(lambda t: '\\u' + hex(int(t[0][2:-1]))[2:])
            return xmlcharref.transformString(ret)

    # build list of single arg builtins, tolerant of Python version, that can be used as parse actions
    singleArgBuiltins = []
    import __builtin__
    for fname in "sum len sorted reversed list tuple set any all min max".split():
        try:
            singleArgBuiltins.append(getattr(__builtin__,fname))
        except AttributeError:
            continue
            
_generatorType = type((y for y in range(1)))
 
def _xml_escape(data):
    """Escape &, <, >, ", ', etc. in a string of data."""

    # ampersand must be replaced first
    from_symbols = '&><"\''
    to_symbols = ('&'+s+';' for s in "amp gt lt quot apos".split())
    for from_,to_ in zip(from_symbols, to_symbols):
        data = data.replace(from_, to_)
    return data

class _Constants(object):
    pass

alphas     = string.ascii_uppercase + string.ascii_lowercase
nums       = "0123456789"
hexnums    = nums + "ABCDEFabcdef"
alphanums  = alphas + nums
_bslash    = chr(92)
printables = "".join(c for c in string.printable if c not in string.whitespace)

class ParseBaseException(Exception):
    """base exception class for all parsing runtime exceptions"""
    # Performance tuning: we construct a *lot* of these, so keep this
    # constructor as small and fast as possible
    def __init__( self, pstr, loc=0, msg=None, elem=None ):
        self.loc = loc
        if msg is None:
            self.msg = pstr
            self.pstr = ""
        else:
            self.msg = msg
            self.pstr = pstr
        self.parserElement = elem
        self.args = (pstr, loc, msg)

    @classmethod
    def _from_exception(cls, pe):
        """
        internal factory method to simplify creating one type of ParseException 
        from another - avoids having __init__ signature conflicts among subclasses
        """
        return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement)

    def __getattr__( self, aname ):
        """supported attributes by name are:
            - lineno - returns the line number of the exception text
            - col - returns the column number of the exception text
            - line - returns the line containing the exception text
        """
        if( aname == "lineno" ):
            return lineno( self.loc, self.pstr )
        elif( aname in ("col", "column") ):
            return col( self.loc, self.pstr )
        elif( aname == "line" ):
            return line( self.loc, self.pstr )
        else:
            raise AttributeError(aname)

    def __str__( self ):
        return "%s (at char %d), (line:%d, col:%d)" % \
                ( self.msg, self.loc, self.lineno, self.column )
    def __repr__( self ):
        return _ustr(self)
    def markInputline( self, markerString = ">!<" ):
        """Extracts the exception line from the input string, and marks
           the location of the exception with a special symbol.
        """
        line_str = self.line
        line_column = self.column - 1
        if markerString:
            line_str = "".join((line_str[:line_column],
                                markerString, line_str[line_column:]))
        return line_str.strip()
    def __dir__(self):
        return "lineno col line".split() + dir(type(self))

class ParseException(ParseBaseException):
    """
    Exception thrown when parse expressions don't match class;
    supported attributes by name are:
     - lineno - returns the line number of the exception text
     - col - returns the column number of the exception text
     - line - returns the line containing the exception text
        
    Example::
        try:
            Word(nums).setName("integer").parseString("ABC")
        except ParseException as pe:
            print(pe)
            print("column: {}".format(pe.col))
            
    prints::
       Expected integer (at char 0), (line:1, col:1)
        column: 1
    """
    pass

class ParseFatalException(ParseBaseException):
    """user-throwable exception thrown when inconsistent parse content
       is found; stops all parsing immediately"""
    pass

class ParseSyntaxException(ParseFatalException):
    """just like L{ParseFatalException}, but thrown internally when an
       L{ErrorStop<And._ErrorStop>} ('-' operator) indicates that parsing is to stop 
       immediately because an unbacktrackable syntax error has been found"""
    pass

#~ class ReparseException(ParseBaseException):
    #~ """Experimental class - parse actions can raise this exception to cause
       #~ pyparsing to reparse the input string:
        #~ - with a modified input string, and/or
        #~ - with a modified start location
       #~ Set the values of the ReparseException in the constructor, and raise the
       #~ exception in a parse action to cause pyparsing to use the new string/location.
       #~ Setting the values as None causes no change to be made.
       #~ """
    #~ def __init_( self, newstring, restartLoc ):
        #~ self.newParseText = newstring
        #~ self.reparseLoc = restartLoc

class RecursiveGrammarException(Exception):
    """exception thrown by L{ParserElement.validate} if the grammar could be improperly recursive"""
    def __init__( self, parseElementList ):
        self.parseElementTrace = parseElementList

    def __str__( self ):
        return "RecursiveGrammarException: %s" % self.parseElementTrace

class _ParseResultsWithOffset(object):
    def __init__(self,p1,p2):
        self.tup = (p1,p2)
    def __getitem__(self,i):
        return self.tup[i]
    def __repr__(self):
        return repr(self.tup[0])
    def setOffset(self,i):
        self.tup = (self.tup[0],i)

class ParseResults(object):
    """
    Structured parse results, to provide multiple means of access to the parsed data:
       - as a list (C{len(results)})
       - by list index (C{results[0], results[1]}, etc.)
       - by attribute (C{results.<resultsName>} - see L{ParserElement.setResultsName})

    Example::
        integer = Word(nums)
        date_str = (integer.setResultsName("year") + '/' 
                        + integer.setResultsName("month") + '/' 
                        + integer.setResultsName("day"))
        # equivalent form:
        # date_str = integer("year") + '/' + integer("month") + '/' + integer("day")

        # parseString returns a ParseResults object
        result = date_str.parseString("1999/12/31")

        def test(s, fn=repr):
            print("%s -> %s" % (s, fn(eval(s))))
        test("list(result)")
        test("result[0]")