# -----------------------------------------------------------------------------
# ply: lex.py
#
# Copyright (C) 2001-2017
# David M. Beazley (Dabeaz LLC)
# All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
# * Neither the name of the David Beazley or Dabeaz LLC may be used to
# endorse or promote products derived from this software without
# specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# -----------------------------------------------------------------------------
__version__ = '3.10'
__tabversion__ = '3.10'
import re
import sys
import types
import copy
import os
import inspect
# This tuple contains known string types
try:
# Python 2.6
StringTypes = (types.StringType, types.UnicodeType)
except AttributeError:
# Python 3.0
StringTypes = (str, bytes)
# This regular expression is used to match valid token names
_is_identifier = re.compile(r'^[a-zA-Z0-9_]+$')
# Exception thrown when invalid token encountered and no default error
# handler is defined.
class LexError(Exception):
def __init__(self, message, s):
self.args = (message,)
self.text = s
# Token class. This class is used to represent the tokens produced.
class LexToken(object):
def __str__(self):
return 'LexToken(%s,%r,%d,%d)' % (self.type, self.value, self.lineno, self.lexpos)
def __repr__(self):
return str(self)
# This object is a stand-in for a logging object created by the
# logging module.
class PlyLogger(object):
def __init__(self, f):
self.f = f
def critical(self, msg, *args, **kwargs):
self.f.write((msg % args) + '\n')
def warning(self, msg, *args, **kwargs):
self.f.write('WARNING: ' + (msg % args) + '\n')
def error(self, msg, *args, **kwargs):
self.f.write('ERROR: ' + (msg % args) + '\n')
info = critical
debug = critical
# Null logger is used when no output is generated. Does nothing.
class NullLogger(object):
def __getattribute__(self, name):
return self
def __call__(self, *args, **kwargs):
return self
# -----------------------------------------------------------------------------
# === Lexing Engine ===
#
# The following Lexer class implements the lexer runtime. There are only
# a few public methods and attributes:
#
# input() - Store a new string in the lexer
# token() - Get the next token
# clone() - Clone the lexer
#
# lineno - Current line number
# lexpos - Current position in the input string
# -----------------------------------------------------------------------------
class Lexer:
def __init__(self):
self.lexre = None # Master regular expression. This is a list of
# tuples (re, findex) where re is a compiled
# regular expression and findex is a list
# mapping regex group numbers to rules
self.lexretext = None # Current regular expression strings
self.lexstatere = {} # Dictionary mapping lexer states to master regexs
self.lexstateretext = {} # Dictionary mapping lexer states to regex strings
self.lexstaterenames = {} # Dictionary mapping lexer states to symbol names
self.lexstate = 'INITIAL' # Current lexer state
self.lexstatestack = [] # Stack of lexer states
self.lexstateinfo = None # State information
self.lexstateignore = {} # Dictionary of ignored characters for each state
self.lexstateerrorf = {} # Dictionary of error functions for each state
self.lexstateeoff = {} # Dictionary of eof functions for each state
self.lexreflags = 0 # Optional re compile flags
self.lexdata = None # Actual input data (as a string)
self.lexpos = 0 # Current position in input text
self.lexlen = 0 # Length of the input text
self.lexerrorf = None # Error rule (if any)
self.lexeoff = None # EOF rule (if any)
self.lextokens = None # List of valid tokens
self.lexignore = '' # Ignored characters
self.lexliterals = '' # Literal characters that can be passed through
self.lexmodule = None # Module
self.lineno = 1 # Current line number
self.lexoptimize = False # Optimized mode
def clone(self, object=None):
c = copy.copy(self)
# If the object parameter has been supplied, it means we are attaching the
# lexer to a new object. In this case, we have to rebind all methods in
# the lexstatere and lexstateerrorf tables.
if object:
newtab = {}
for key, ritem in self.lexstatere.items():
newre = []
for cre, findex in ritem:
newfindex = []
for f in findex:
if not f or not f[0]:
newfindex.append(f)
continue
newfindex.append((getattr(object, f[0].__name__), f[1]))
newre.append((cre, newfindex))
newtab[key] = newre
c.lexstatere = newtab
c.lexstateerrorf = {}
for key, ef in self.lexstateerrorf.items():
c.lexstateerrorf[key] = getattr(object, ef.__name__)
c.lexmodule = object
return c
# ------------------------------------------------------------
# writetab() - Write lexer information to a table file
# ------------------------------------------------------------
def writetab(self, lextab, outputdir=''):
if isinstance(lextab, types.ModuleType):
raise IOError("Won't overwrite existing lextab module")
basetabmodule = lextab.split('.')[-1]
filename = os.path.join(outputdir, basetabmodule) + '.py'
with open(filename, 'w') as tf:
tf.write('# %s.py. This file automatically created by PLY (version %s). Don\'t edit!\n' % (basetabmodule, __version__))
tf.write('_tabversion = %s\n' % repr(__tabversion__))
tf.write('_lextokens = set(%s)\n' % repr(tuple(self.lextokens)))
tf.write('_lexreflags = %s\n' % repr(self.lexreflags))
tf.write('_lexliterals = %s\n' % repr(self.lexliterals))
tf.write('_lexstateinfo = %s\n' % repr(self.lexstateinfo))
# Rewrite the lexstatere table, replacing function objects with function names
tabre = {}
for statename, lre in self.lexstatere.items():
titem = []
for (pat, func), retext, renames in zip(lre, self.lexstateretext[statename], self.lexstaterenames[statename]):
titem.append((retext, _funcs_to_names(func, renames)))
tabre[statename] = titem
tf.write('_lexstatere = %s\n' % repr(tabre))
tf.write('_lexstateignore = %s\n' % repr(self.lexstateignore))
taberr = {}
for statename, ef in self.lexstateerrorf.items():
taberr[statename] = ef.__name__ if ef else None
tf.write('_lexstateerrorf = %s\n' % repr(taberr))
tabeof = {}
for statename, ef in self.lexstateeoff.items():
tabeof[statename] = ef.__name__ if ef else None
tf.write('_lexstateeoff = %s\n' % repr(tabeof))
# ------------------------------------------------------------
# readtab() - Read lexer information from a tab file
# ------------------------------------------------------------
def readtab(self, tabfile, fdict):
if isinstance(tabfile, types.ModuleType):
lextab = tabfile
else:
exec('import %s' % tabfile)
lextab = sys.modules[tabfile]
if getattr(lextab, '_tabversion', '0.0') != __tabversion__:
raise ImportError('Inconsistent PLY version')
self.lextokens = lextab._lextokens
self.lexreflags = lextab._lexreflags
self.lexliterals = lextab._lexliterals
self.lextokens_all = self.lextokens | set(self.lexliterals)
self.lexstateinfo = lextab._lexstateinfo
self.lexstateignore = lextab._lexstateignore
self.lexstatere = {}
self.lexstateretext = {}
for statename, lre in lextab._lexstatere.items():
titem = []
txtitem = []
for pat, func_name in lre:
titem.append((re.compile(pat, lextab._lexreflags), _names_to_funcs(func_name, fdict)))
self.lexstatere[statename] = titem
self.lexstateretext[statename] = txtitem
self.lexstateerrorf = {}
for statename, ef in lextab._lexstateerrorf.items():
self.lexstateerrorf[statename] = fdict[ef]
self.lexstateeoff = {}
for statename, ef in lextab._lexstateeoff.items():
self.lexstateeoff[statename] = fdict[ef]
self.begin('INITIAL')
# ------------------------------------------------------------
# input() - Push a new string into the lexer
# ------------------------------------------------------------
def input(self, s):
# Pull off the first character to see if s looks like a string
c = s[:1]
if not isinstance(c, StringTypes):
raise ValueError('Expected a string')
self.lexdata = s
self.lexpos = 0
self.lexlen = len(s)
# ------------------------------------------------------------
# begin() - Changes the lexing state
# ------------------------------------------------------------
def begin(self, state):
if state not in self.lexstatere:
raise ValueError('Undefined state')
self.lexre = self.lexstatere[state]
self.lexretext = self.lexstateretext[state]
self.lexignore = self.lexstateignore.get(state, '')
self.lexerrorf = self.lexstateerrorf.get(state, None)
self.lexeoff = self.lexstateeoff.get(state, None)
self.lexstate = state
# ------------------------------------------------------------
# push_state() - Changes the lexing state and saves old on stack
# ------------------------------------------------------------
def push_state(self, state):
self.lexstatestack.append(self.lexstate)
self.begin(state)
# ------------------------------------------------------------
# pop_state() - Restores the previous state
# ------------------------------------------------------------
def pop_state(self):
self.begin(self.lexstatestack.pop())
# ------------------------------------------------------------
# current_state() - Returns the current lexing state
# ------------------------------------------------------------
def current_state(self):
return self.lexstate
# ------------------------------------------------------------
# skip() - Skip ahead n characters
# ------------------------------------------------------------
def skip(self, n):
self.lexpos += n
# ------------------------------------------------------------
# opttoken() - Return the next token from the Lexer
#
# Note: This function has been carefully implemented to be as fast
# as possible. Don't make changes unless you really know what
# you are doing
# ------------------------------------------------------------
def token(self):
# Make local copies of frequently referenced attributes
lexpos = self.lexpos
lexlen = self.lexlen
lexignore = self.lexignore
lexdata = self.lexdata
while lexpos < lexlen:
# This code provides some short-circuit code for whitespace, tabs, and other ignored characters
if lexdata[lexpos] in lexignore:
lexpos += 1
continue
# Look for a regular expression match
for lexre, lexindexfunc in self.lexre:
m = lexre.match(lexdata, lexpos)
if not m:
continue
# Create a token for return
tok = LexToken()
tok.value = m.group()
tok.lineno = self.lineno
tok.lexpos = lexpos
i = m.lastindex
func, tok.type = lexindexfunc[i]
if not func:
# If no token type was set, it's an ignored token
if tok.type:
self.lexpos = m.end()
return tok
else:
lexpos = m.end()
break
lexpos = m.end()
# If token is processed by a function, call it
Loading ...