lex.py

M5,一个功能强大的多处理器系统模拟器.很多针对处理器架构,性能的研究都使用它作为模拟平台

#-----------------------------------------------------------------------------
# ply: lex.py
#
# Author: David M. Beazley ([e-mail])
#
# Copyright (C) 2001-2007, David M. Beazley
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
#
# See the file COPYING for a complete copy of the LGPL.
#-----------------------------------------------------------------------------

__version__ = "2.3"

import re, sys, types

# Regular expression used to match valid token names
_is_identifier = re.compile(r'^[a-zA-Z0-9_]+$')

# Available instance types.  This is used when lexers are defined by a class.
# It's a little funky because I want to preserve backwards compatibility
# with Python 2.0 where types.ObjectType is undefined.

try:
   _INSTANCETYPE = (types.InstanceType, types.ObjectType)
except AttributeError:
   _INSTANCETYPE = types.InstanceType
   class object: pass       # Note: needed if no new-style classes present

# 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
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)
    def skip(self,n):
        self.lexer.skip(n)

# -----------------------------------------------------------------------------
# Lexer class
#
# This class encapsulates all of the methods and data associated with a lexer.
#
#    input()          -  Store a new string in the lexer
#    token()          -  Get the next token
# -----------------------------------------------------------------------------

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.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.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.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.lexdebug = 0             # Debugging mode
        self.lexoptimize = 0          # Optimized mode

    def clone(self,object=None):
        c = Lexer()
        c.lexstatere = self.lexstatere
        c.lexstateinfo = self.lexstateinfo
        c.lexstateretext = self.lexstateretext
        c.lexstate = self.lexstate
        c.lexstatestack = self.lexstatestack
        c.lexstateignore = self.lexstateignore
        c.lexstateerrorf = self.lexstateerrorf
        c.lexreflags = self.lexreflags
        c.lexdata = self.lexdata
        c.lexpos = self.lexpos
        c.lexlen = self.lexlen
        c.lextokens = self.lextokens
        c.lexdebug = self.lexdebug
        c.lineno = self.lineno
        c.lexoptimize = self.lexoptimize
        c.lexliterals = self.lexliterals
        c.lexmodule   = self.lexmodule

        # 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

        # Set up other attributes
        c.begin(c.lexstate)
        return c

    # ------------------------------------------------------------
    # writetab() - Write lexer information to a table file
    # ------------------------------------------------------------
    def writetab(self,tabfile):
        tf = open(tabfile+".py","w")
        tf.write("# %s.py. This file automatically created by PLY (version %s). Don't edit!\n" % (tabfile,__version__))
        tf.write("_lextokens    = %s\n" % repr(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))

        tabre = { }
        for key, lre in self.lexstatere.items():
             titem = []
             for i in range(len(lre)):
                  titem.append((self.lexstateretext[key][i],_funcs_to_names(lre[i][1])))
             tabre[key] = titem

        tf.write("_lexstatere   = %s\n" % repr(tabre))
        tf.write("_lexstateignore = %s\n" % repr(self.lexstateignore))

        taberr = { }
        for key, ef in self.lexstateerrorf.items():
             if ef:
                  taberr[key] = ef.__name__
             else:
                  taberr[key] = None
        tf.write("_lexstateerrorf = %s\n" % repr(taberr))
        tf.close()

    # ------------------------------------------------------------
    # readtab() - Read lexer information from a tab file
    # ------------------------------------------------------------
    def readtab(self,tabfile,fdict):
        exec "import %s as lextab" % tabfile
        self.lextokens      = lextab._lextokens
        self.lexreflags     = lextab._lexreflags
        self.lexliterals    = lextab._lexliterals
        self.lexstateinfo   = lextab._lexstateinfo
        self.lexstateignore = lextab._lexstateignore
        self.lexstatere     = { }
        self.lexstateretext = { }
        for key,lre in lextab._lexstatere.items():
             titem = []
             txtitem = []
             for i in range(len(lre)):
                  titem.append((re.compile(lre[i][0],lextab._lexreflags),_names_to_funcs(lre[i][1],fdict)))
                  txtitem.append(lre[i][0])
             self.lexstatere[key] = titem
             self.lexstateretext[key] = txtitem
        self.lexstateerrorf = { }
        for key,ef in lextab._lexstateerrorf.items():
             self.lexstateerrorf[key] = fdict[ef]
        self.begin('INITIAL')

    # ------------------------------------------------------------
    # input() - Push a new string into the lexer
    # ------------------------------------------------------------
    def input(self,s):
        if not (isinstance(s,types.StringType) or isinstance(s,types.UnicodeType)):
            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 not self.lexstatere.has_key(state):
            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.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

    # ------------------------------------------------------------
    # token() - 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

                # Set last match in lexer so that rules can access it if they want
                self.lexmatch = m

                # Create a token for return
                tok = LexToken()
                tok.value = m.group()
                tok.lineno = self.lineno
                tok.lexpos = lexpos
                tok.lexer = self

                lexpos = m.end()
                i = m.lastindex
                func,tok.type = lexindexfunc[i]
                self.lexpos = lexpos

                if not func:
                   # If no token type was set, it's an ignored token
                   if tok.type: return tok
                   break

                # if func not callable, it means it's an ignored token
                if not callable(func):
                   break