1 # -----------------------------------------------------------------------------
4 # Copyright (C) 2001-2009,
5 # David M. Beazley (Dabeaz LLC)
8 # Redistribution and use in source and binary forms, with or without
9 # modification, are permitted provided that the following conditions are
12 # * Redistributions of source code must retain the above copyright notice,
13 # this list of conditions and the following disclaimer.
14 # * Redistributions in binary form must reproduce the above copyright notice,
15 # this list of conditions and the following disclaimer in the documentation
16 # and/or other materials provided with the distribution.
17 # * Neither the name of the David Beazley or Dabeaz LLC may be used to
18 # endorse or promote products derived from this software without
19 # specific prior written permission.
21 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
22 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
23 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
24 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
25 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
26 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
27 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
28 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
29 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
30 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
31 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
32 # -----------------------------------------------------------------------------
35 __tabversion__ = "3.2" # Version of table file used
37 import re, sys, types, copy, os
39 # This tuple contains known string types
42 StringTypes = (types.StringType, types.UnicodeType)
43 except AttributeError:
45 StringTypes = (str, bytes)
47 # Extract the code attribute of a function. Different implementations
48 # are for Python 2/3 compatibility.
50 if sys.version_info[0] < 3:
57 # This regular expression is used to match valid token names
58 _is_identifier = re.compile(r'^[a-zA-Z0-9_]+$')
60 # Exception thrown when invalid token encountered and no default error
63 class LexError(Exception):
64 def __init__(self,message,s):
65 self.args = (message,)
68 # Token class. This class is used to represent the tokens produced.
69 class LexToken(object):
71 return "LexToken(%s,%r,%d,%d)" % (self.type,self.value,self.lineno,self.lexpos)
75 # This object is a stand-in for a logging object created by the
78 class PlyLogger(object):
81 def critical(self,msg,*args,**kwargs):
82 self.f.write((msg % args) + "\n")
84 def warning(self,msg,*args,**kwargs):
85 self.f.write("WARNING: "+ (msg % args) + "\n")
87 def error(self,msg,*args,**kwargs):
88 self.f.write("ERROR: " + (msg % args) + "\n")
93 # Null logger is used when no output is generated. Does nothing.
94 class NullLogger(object):
95 def __getattribute__(self,name):
97 def __call__(self,*args,**kwargs):
100 # -----------------------------------------------------------------------------
101 # === Lexing Engine ===
103 # The following Lexer class implements the lexer runtime. There are only
104 # a few public methods and attributes:
106 # input() - Store a new string in the lexer
107 # token() - Get the next token
108 # clone() - Clone the lexer
110 # lineno - Current line number
111 # lexpos - Current position in the input string
112 # -----------------------------------------------------------------------------
116 self.lexre = None # Master regular expression. This is a list of
117 # tuples (re,findex) where re is a compiled
118 # regular expression and findex is a list
119 # mapping regex group numbers to rules
120 self.lexretext = None # Current regular expression strings
121 self.lexstatere = {} # Dictionary mapping lexer states to master regexs
122 self.lexstateretext = {} # Dictionary mapping lexer states to regex strings
123 self.lexstaterenames = {} # Dictionary mapping lexer states to symbol names
124 self.lexstate = "INITIAL" # Current lexer state
125 self.lexstatestack = [] # Stack of lexer states
126 self.lexstateinfo = None # State information
127 self.lexstateignore = {} # Dictionary of ignored characters for each state
128 self.lexstateerrorf = {} # Dictionary of error functions for each state
129 self.lexreflags = 0 # Optional re compile flags
130 self.lexdata = None # Actual input data (as a string)
131 self.lexpos = 0 # Current position in input text
132 self.lexlen = 0 # Length of the input text
133 self.lexerrorf = None # Error rule (if any)
134 self.lextokens = None # List of valid tokens
135 self.lexignore = "" # Ignored characters
136 self.lexliterals = "" # Literal characters that can be passed through
137 self.lexmodule = None # Module
138 self.lineno = 1 # Current line number
139 self.lexoptimize = 0 # Optimized mode
141 def clone(self,object=None):
144 # If the object parameter has been supplied, it means we are attaching the
145 # lexer to a new object. In this case, we have to rebind all methods in
146 # the lexstatere and lexstateerrorf tables.
150 for key, ritem in self.lexstatere.items():
152 for cre, findex in ritem:
155 if not f or not f[0]:
158 newfindex.append((getattr(object,f[0].__name__),f[1]))
159 newre.append((cre,newfindex))
161 c.lexstatere = newtab
162 c.lexstateerrorf = { }
163 for key, ef in self.lexstateerrorf.items():
164 c.lexstateerrorf[key] = getattr(object,ef.__name__)
168 # ------------------------------------------------------------
169 # writetab() - Write lexer information to a table file
170 # ------------------------------------------------------------
171 def writetab(self,tabfile,outputdir=""):
172 if isinstance(tabfile,types.ModuleType):
174 basetabfilename = tabfile.split(".")[-1]
175 filename = os.path.join(outputdir,basetabfilename)+".py"
176 tf = open(filename,"w")
177 tf.write("# %s.py. This file automatically created by PLY (version %s). Don't edit!\n" % (tabfile,__version__))
178 tf.write("_tabversion = %s\n" % repr(__version__))
179 tf.write("_lextokens = %s\n" % repr(self.lextokens))
180 tf.write("_lexreflags = %s\n" % repr(self.lexreflags))
181 tf.write("_lexliterals = %s\n" % repr(self.lexliterals))
182 tf.write("_lexstateinfo = %s\n" % repr(self.lexstateinfo))
185 # Collect all functions in the initial state
186 initial = self.lexstatere["INITIAL"]
191 initialfuncs.append(f)
193 for key, lre in self.lexstatere.items():
195 for i in range(len(lre)):
196 titem.append((self.lexstateretext[key][i],_funcs_to_names(lre[i][1],self.lexstaterenames[key][i])))
199 tf.write("_lexstatere = %s\n" % repr(tabre))
200 tf.write("_lexstateignore = %s\n" % repr(self.lexstateignore))
203 for key, ef in self.lexstateerrorf.items():
205 taberr[key] = ef.__name__
208 tf.write("_lexstateerrorf = %s\n" % repr(taberr))
211 # ------------------------------------------------------------
212 # readtab() - Read lexer information from a tab file
213 # ------------------------------------------------------------
214 def readtab(self,tabfile,fdict):
215 if isinstance(tabfile,types.ModuleType):
218 if sys.version_info[0] < 3:
219 exec("import %s as lextab" % tabfile)
222 exec("import %s as lextab" % tabfile, env,env)
223 lextab = env['lextab']
225 if getattr(lextab,"_tabversion","0.0") != __version__:
226 raise ImportError("Inconsistent PLY version")
228 self.lextokens = lextab._lextokens
229 self.lexreflags = lextab._lexreflags
230 self.lexliterals = lextab._lexliterals
231 self.lexstateinfo = lextab._lexstateinfo
232 self.lexstateignore = lextab._lexstateignore
233 self.lexstatere = { }
234 self.lexstateretext = { }
235 for key,lre in lextab._lexstatere.items():
238 for i in range(len(lre)):
239 titem.append((re.compile(lre[i][0],lextab._lexreflags | re.VERBOSE),_names_to_funcs(lre[i][1],fdict)))
240 txtitem.append(lre[i][0])
241 self.lexstatere[key] = titem
242 self.lexstateretext[key] = txtitem
243 self.lexstateerrorf = { }
244 for key,ef in lextab._lexstateerrorf.items():
245 self.lexstateerrorf[key] = fdict[ef]
246 self.begin('INITIAL')
248 # ------------------------------------------------------------
249 # input() - Push a new string into the lexer
250 # ------------------------------------------------------------
252 # Pull off the first character to see if s looks like a string
254 if not isinstance(c,StringTypes):
255 raise ValueError("Expected a string")
260 # ------------------------------------------------------------
261 # begin() - Changes the lexing state
262 # ------------------------------------------------------------
263 def begin(self,state):
264 if not state in self.lexstatere:
265 raise ValueError("Undefined state")
266 self.lexre = self.lexstatere[state]
267 self.lexretext = self.lexstateretext[state]
268 self.lexignore = self.lexstateignore.get(state,"")
269 self.lexerrorf = self.lexstateerrorf.get(state,None)
270 self.lexstate = state
272 # ------------------------------------------------------------
273 # push_state() - Changes the lexing state and saves old on stack
274 # ------------------------------------------------------------
275 def push_state(self,state):
276 self.lexstatestack.append(self.lexstate)
279 # ------------------------------------------------------------
280 # pop_state() - Restores the previous state
281 # ------------------------------------------------------------
283 self.begin(self.lexstatestack.pop())
285 # ------------------------------------------------------------
286 # current_state() - Returns the current lexing state
287 # ------------------------------------------------------------
288 def current_state(self):
291 # ------------------------------------------------------------
292 # skip() - Skip ahead n characters
293 # ------------------------------------------------------------
297 # ------------------------------------------------------------
298 # opttoken() - Return the next token from the Lexer
300 # Note: This function has been carefully implemented to be as fast
301 # as possible. Don't make changes unless you really know what
303 # ------------------------------------------------------------
305 # Make local copies of frequently referenced attributes
308 lexignore = self.lexignore
309 lexdata = self.lexdata
311 while lexpos < lexlen:
312 # This code provides some short-circuit code for whitespace, tabs, and other ignored characters
313 if lexdata[lexpos] in lexignore:
317 # Look for a regular expression match
318 for lexre,lexindexfunc in self.lexre:
319 m = lexre.match(lexdata,lexpos)
322 # Create a token for return
324 tok.value = m.group()
325 tok.lineno = self.lineno
329 func,tok.type = lexindexfunc[i]
332 # If no token type was set, it's an ignored token
334 self.lexpos = m.end()
342 # If token is processed by a function, call it
344 tok.lexer = self # Set additional attributes useful in token rules
350 # Every function must return a token, if nothing, we just move to next token
352 lexpos = self.lexpos # This is here in case user has updated lexpos.
353 lexignore = self.lexignore # This is here in case there was a state change
356 # Verify type of the token. If not in the token map, raise an error
357 if not self.lexoptimize:
358 if not newtok.type in self.lextokens:
359 raise LexError("%s:%d: Rule '%s' returned an unknown token type '%s'" % (
360 func_code(func).co_filename, func_code(func).co_firstlineno,
361 func.__name__, newtok.type),lexdata[lexpos:])
365 # No match, see if in literals
366 if lexdata[lexpos] in self.lexliterals:
368 tok.value = lexdata[lexpos]
369 tok.lineno = self.lineno
372 self.lexpos = lexpos + 1
375 # No match. Call t_error() if defined.
378 tok.value = self.lexdata[lexpos:]
379 tok.lineno = self.lineno
384 newtok = self.lexerrorf(tok)
385 if lexpos == self.lexpos:
386 # Error method didn't change text position at all. This is an error.
387 raise LexError("Scanning error. Illegal character '%s'" % (lexdata[lexpos]), lexdata[lexpos:])
389 if not newtok: continue
393 raise LexError("Illegal character '%s' at index %d" % (lexdata[lexpos],lexpos), lexdata[lexpos:])
395 self.lexpos = lexpos + 1
396 if self.lexdata is None:
397 raise RuntimeError("No input string given with input()")
412 # -----------------------------------------------------------------------------
413 # ==== Lex Builder ===
415 # The functions and classes below are used to collect lexing information
416 # and build a Lexer object from it.
417 # -----------------------------------------------------------------------------
419 # -----------------------------------------------------------------------------
420 # get_caller_module_dict()
422 # This function returns a dictionary containing all of the symbols defined within
423 # a caller further down the call stack. This is used to get the environment
424 # associated with the yacc() call if none was provided.
425 # -----------------------------------------------------------------------------
427 def get_caller_module_dict(levels):
431 e,b,t = sys.exc_info()
436 ldict = f.f_globals.copy()
437 if f.f_globals != f.f_locals:
438 ldict.update(f.f_locals)
442 # -----------------------------------------------------------------------------
445 # Given a list of regular expression functions, this converts it to a list
446 # suitable for output to a table file
447 # -----------------------------------------------------------------------------
449 def _funcs_to_names(funclist,namelist):
451 for f,name in zip(funclist,namelist):
453 result.append((name, f[1]))
458 # -----------------------------------------------------------------------------
461 # Given a list of regular expression function names, this converts it back to
463 # -----------------------------------------------------------------------------
465 def _names_to_funcs(namelist,fdict):
469 result.append((fdict[n[0]],n[1]))
474 # -----------------------------------------------------------------------------
477 # This function takes a list of all of the regex components and attempts to
478 # form the master regular expression. Given limitations in the Python re
479 # module, it may be necessary to break the master regex into separate expressions.
480 # -----------------------------------------------------------------------------
482 def _form_master_re(relist,reflags,ldict,toknames):
483 if not relist: return []
484 regex = "|".join(relist)
486 lexre = re.compile(regex,re.VERBOSE | reflags)
488 # Build the index to function map for the matching engine
489 lexindexfunc = [ None ] * (max(lexre.groupindex.values())+1)
490 lexindexnames = lexindexfunc[:]
492 for f,i in lexre.groupindex.items():
493 handle = ldict.get(f,None)
494 if type(handle) in (types.FunctionType, types.MethodType):
495 lexindexfunc[i] = (handle,toknames[f])
497 elif handle is not None:
499 if f.find("ignore_") > 0:
500 lexindexfunc[i] = (None,None)
502 lexindexfunc[i] = (None, toknames[f])
504 return [(lexre,lexindexfunc)],[regex],[lexindexnames]
506 m = int(len(relist)/2)
508 llist, lre, lnames = _form_master_re(relist[:m],reflags,ldict,toknames)
509 rlist, rre, rnames = _form_master_re(relist[m:],reflags,ldict,toknames)
510 return llist+rlist, lre+rre, lnames+rnames
512 # -----------------------------------------------------------------------------
513 # def _statetoken(s,names)
515 # Given a declaration name s of the form "t_" and a dictionary whose keys are
516 # state names, this function returns a tuple (states,tokenname) where states
517 # is a tuple of state names and tokenname is the name of the token. For example,
518 # calling this with s = "t_foo_bar_SPAM" might return (('foo','bar'),'SPAM')
519 # -----------------------------------------------------------------------------
521 def _statetoken(s,names):
524 for i in range(1,len(parts)):
525 if not parts[i] in names and parts[i] != 'ANY': break
527 states = tuple(parts[1:i])
529 states = ('INITIAL',)
532 states = tuple(names)
534 tokenname = "_".join(parts[i:])
535 return (states,tokenname)
538 # -----------------------------------------------------------------------------
541 # This class represents information needed to build a lexer as extracted from a
543 # -----------------------------------------------------------------------------
544 class LexerReflect(object):
545 def __init__(self,ldict,log=None,reflags=0):
547 self.error_func = None
549 self.reflags = reflags
550 self.stateinfo = { 'INITIAL' : 'inclusive'}
555 self.log = PlyLogger(sys.stderr)
559 # Get all of the basic information
566 # Validate all of the information
567 def validate_all(self):
568 self.validate_tokens()
569 self.validate_literals()
570 self.validate_rules()
574 def get_tokens(self):
575 tokens = self.ldict.get("tokens",None)
577 self.log.error("No token list is defined")
581 if not isinstance(tokens,(list, tuple)):
582 self.log.error("tokens must be a list or tuple")
587 self.log.error("tokens is empty")
593 # Validate the tokens
594 def validate_tokens(self):
596 for n in self.tokens:
597 if not _is_identifier.match(n):
598 self.log.error("Bad token name '%s'",n)
601 self.log.warning("Token '%s' multiply defined", n)
604 # Get the literals specifier
605 def get_literals(self):
606 self.literals = self.ldict.get("literals","")
609 def validate_literals(self):
611 for c in self.literals:
612 if not isinstance(c,StringTypes) or len(c) > 1:
613 self.log.error("Invalid literal %s. Must be a single character", repr(c))
618 self.log.error("Invalid literals specification. literals must be a sequence of characters")
621 def get_states(self):
622 self.states = self.ldict.get("states",None)
625 if not isinstance(self.states,(tuple,list)):
626 self.log.error("states must be defined as a tuple or list")
629 for s in self.states:
630 if not isinstance(s,tuple) or len(s) != 2:
631 self.log.error("Invalid state specifier %s. Must be a tuple (statename,'exclusive|inclusive')",repr(s))
635 if not isinstance(name,StringTypes):
636 self.log.error("State name %s must be a string", repr(name))
639 if not (statetype == 'inclusive' or statetype == 'exclusive'):
640 self.log.error("State type for state %s must be 'inclusive' or 'exclusive'",name)
643 if name in self.stateinfo:
644 self.log.error("State '%s' already defined",name)
647 self.stateinfo[name] = statetype
649 # Get all of the symbols with a t_ prefix and sort them into various
650 # categories (functions, strings, error functions, and ignore characters)
653 tsymbols = [f for f in self.ldict if f[:2] == 't_' ]
655 # Now build up a list of functions and a list of strings
657 self.toknames = { } # Mapping of symbols to token names
658 self.funcsym = { } # Symbols defined as functions
659 self.strsym = { } # Symbols defined as strings
660 self.ignore = { } # Ignore strings by state
661 self.errorf = { } # Error functions by state
663 for s in self.stateinfo:
667 if len(tsymbols) == 0:
668 self.log.error("No rules of the form t_rulename are defined")
674 states, tokname = _statetoken(f,self.stateinfo)
675 self.toknames[f] = tokname
677 if hasattr(t,"__call__"):
678 if tokname == 'error':
681 elif tokname == 'ignore':
682 line = func_code(t).co_firstlineno
683 file = func_code(t).co_filename
684 self.log.error("%s:%d: Rule '%s' must be defined as a string",file,line,t.__name__)
688 self.funcsym[s].append((f,t))
689 elif isinstance(t, StringTypes):
690 if tokname == 'ignore':
694 self.log.warning("%s contains a literal backslash '\\'",f)
696 elif tokname == 'error':
697 self.log.error("Rule '%s' must be defined as a function", f)
701 self.strsym[s].append((f,t))
703 self.log.error("%s not defined as a function or string", f)
706 # Sort the functions by line number
707 for f in self.funcsym.values():
708 if sys.version_info[0] < 3:
709 f.sort(lambda x,y: cmp(func_code(x[1]).co_firstlineno,func_code(y[1]).co_firstlineno))
712 f.sort(key=lambda x: func_code(x[1]).co_firstlineno)
714 # Sort the strings by regular expression length
715 for s in self.strsym.values():
716 if sys.version_info[0] < 3:
717 s.sort(lambda x,y: (len(x[1]) < len(y[1])) - (len(x[1]) > len(y[1])))
720 s.sort(key=lambda x: len(x[1]),reverse=True)
722 # Validate all of the t_rules collected
723 def validate_rules(self):
724 for state in self.stateinfo:
725 # Validate all rules defined by functions
729 for fname, f in self.funcsym[state]:
730 line = func_code(f).co_firstlineno
731 file = func_code(f).co_filename
734 tokname = self.toknames[fname]
735 if isinstance(f, types.MethodType):
739 nargs = func_code(f).co_argcount
741 self.log.error("%s:%d: Rule '%s' has too many arguments",file,line,f.__name__)
746 self.log.error("%s:%d: Rule '%s' requires an argument", file,line,f.__name__)
751 self.log.error("%s:%d: No regular expression defined for rule '%s'",file,line,f.__name__)
756 c = re.compile("(?P<%s>%s)" % (fname,f.__doc__), re.VERBOSE | self.reflags)
758 self.log.error("%s:%d: Regular expression for rule '%s' matches empty string", file,line,f.__name__)
761 _etype, e, _etrace = sys.exc_info()
762 self.log.error("%s:%d: Invalid regular expression for rule '%s'. %s", file,line,f.__name__,e)
764 self.log.error("%s:%d. Make sure '#' in rule '%s' is escaped with '\\#'",file,line, f.__name__)
767 # Validate all rules defined by strings
768 for name,r in self.strsym[state]:
769 tokname = self.toknames[name]
770 if tokname == 'error':
771 self.log.error("Rule '%s' must be defined as a function", name)
775 if not tokname in self.tokens and tokname.find("ignore_") < 0:
776 self.log.error("Rule '%s' defined for an unspecified token %s",name,tokname)
781 c = re.compile("(?P<%s>%s)" % (name,r),re.VERBOSE | self.reflags)
783 self.log.error("Regular expression for rule '%s' matches empty string",name)
786 _etype, e, _etrace = sys.exc_info()
787 self.log.error("Invalid regular expression for rule '%s'. %s",name,e)
789 self.log.error("Make sure '#' in rule '%s' is escaped with '\\#'",name)
792 if not self.funcsym[state] and not self.strsym[state]:
793 self.log.error("No rules defined for state '%s'",state)
796 # Validate the error function
797 efunc = self.errorf.get(state,None)
800 line = func_code(f).co_firstlineno
801 file = func_code(f).co_filename
804 if isinstance(f, types.MethodType):
808 nargs = func_code(f).co_argcount
810 self.log.error("%s:%d: Rule '%s' has too many arguments",file,line,f.__name__)
814 self.log.error("%s:%d: Rule '%s' requires an argument", file,line,f.__name__)
818 self.validate_file(f)
821 # -----------------------------------------------------------------------------
824 # This checks to see if there are duplicated t_rulename() functions or strings
825 # in the parser input file. This is done using a simple regular expression
826 # match on each line in the given file.
827 # -----------------------------------------------------------------------------
829 def validate_file(self,filename):
831 base,ext = os.path.splitext(filename)
832 if ext != '.py': return # No idea what the file is. Return OK
836 lines = f.readlines()
839 return # Couldn't find the file. Don't worry about it
841 fre = re.compile(r'\s*def\s+(t_[a-zA-Z_0-9]*)\(')
842 sre = re.compile(r'\s*(t_[a-zA-Z_0-9]*)\s*=')
852 prev = counthash.get(name)
854 counthash[name] = linen
856 self.log.error("%s:%d: Rule %s redefined. Previously defined on line %d",filename,linen,name,prev)
860 # -----------------------------------------------------------------------------
863 # Build all of the regular expression rules from definitions in the supplied module
864 # -----------------------------------------------------------------------------
865 def lex(module=None,object=None,debug=0,optimize=0,lextab="lextab",reflags=0,nowarn=0,outputdir="", debuglog=None, errorlog=None):
868 stateinfo = { 'INITIAL' : 'inclusive'}
870 lexobj.lexoptimize = optimize
874 errorlog = PlyLogger(sys.stderr)
878 debuglog = PlyLogger(sys.stderr)
880 # Get the module dictionary used for the lexer
881 if object: module = object
884 _items = [(k,getattr(module,k)) for k in dir(module)]
887 ldict = get_caller_module_dict(2)
889 # Collect parser information from the dictionary
890 linfo = LexerReflect(ldict,log=errorlog,reflags=reflags)
893 if linfo.validate_all():
894 raise SyntaxError("Can't build lexer")
896 if optimize and lextab:
898 lexobj.readtab(lextab,ldict)
907 # Dump some basic debugging information
909 debuglog.info("lex: tokens = %r", linfo.tokens)
910 debuglog.info("lex: literals = %r", linfo.literals)
911 debuglog.info("lex: states = %r", linfo.stateinfo)
913 # Build a dictionary of valid token names
914 lexobj.lextokens = { }
915 for n in linfo.tokens:
916 lexobj.lextokens[n] = 1
918 # Get literals specification
919 if isinstance(linfo.literals,(list,tuple)):
920 lexobj.lexliterals = type(linfo.literals[0])().join(linfo.literals)
922 lexobj.lexliterals = linfo.literals
924 # Get the stateinfo dictionary
925 stateinfo = linfo.stateinfo
928 # Build the master regular expressions
929 for state in stateinfo:
932 # Add rules defined by functions first
933 for fname, f in linfo.funcsym[state]:
934 line = func_code(f).co_firstlineno
935 file = func_code(f).co_filename
936 regex_list.append("(?P<%s>%s)" % (fname,f.__doc__))
938 debuglog.info("lex: Adding rule %s -> '%s' (state '%s')",fname,f.__doc__, state)
940 # Now add all of the simple rules
941 for name,r in linfo.strsym[state]:
942 regex_list.append("(?P<%s>%s)" % (name,r))
944 debuglog.info("lex: Adding rule %s -> '%s' (state '%s')",name,r, state)
946 regexs[state] = regex_list
948 # Build the master regular expressions
951 debuglog.info("lex: ==== MASTER REGEXS FOLLOW ====")
954 lexre, re_text, re_names = _form_master_re(regexs[state],reflags,ldict,linfo.toknames)
955 lexobj.lexstatere[state] = lexre
956 lexobj.lexstateretext[state] = re_text
957 lexobj.lexstaterenames[state] = re_names
959 for i in range(len(re_text)):
960 debuglog.info("lex: state '%s' : regex[%d] = '%s'",state, i, re_text[i])
962 # For inclusive states, we need to add the regular expressions from the INITIAL state
963 for state,stype in stateinfo.items():
964 if state != "INITIAL" and stype == 'inclusive':
965 lexobj.lexstatere[state].extend(lexobj.lexstatere['INITIAL'])
966 lexobj.lexstateretext[state].extend(lexobj.lexstateretext['INITIAL'])
967 lexobj.lexstaterenames[state].extend(lexobj.lexstaterenames['INITIAL'])
969 lexobj.lexstateinfo = stateinfo
970 lexobj.lexre = lexobj.lexstatere["INITIAL"]
971 lexobj.lexretext = lexobj.lexstateretext["INITIAL"]
972 lexobj.lexreflags = reflags
974 # Set up ignore variables
975 lexobj.lexstateignore = linfo.ignore
976 lexobj.lexignore = lexobj.lexstateignore.get("INITIAL","")
978 # Set up error functions
979 lexobj.lexstateerrorf = linfo.errorf
980 lexobj.lexerrorf = linfo.errorf.get("INITIAL",None)
981 if not lexobj.lexerrorf:
982 errorlog.warning("No t_error rule is defined")
984 # Check state information for ignore and error rules
985 for s,stype in stateinfo.items():
986 if stype == 'exclusive':
987 if not s in linfo.errorf:
988 errorlog.warning("No error rule is defined for exclusive state '%s'", s)
989 if not s in linfo.ignore and lexobj.lexignore:
990 errorlog.warning("No ignore rule is defined for exclusive state '%s'", s)
991 elif stype == 'inclusive':
992 if not s in linfo.errorf:
993 linfo.errorf[s] = linfo.errorf.get("INITIAL",None)
994 if not s in linfo.ignore:
995 linfo.ignore[s] = linfo.ignore.get("INITIAL","")
997 # Create global versions of the token() and input() functions
1002 # If in optimize mode, we write the lextab
1003 if lextab and optimize:
1004 lexobj.writetab(lextab,outputdir)
1008 # -----------------------------------------------------------------------------
1011 # This runs the lexer as a main program
1012 # -----------------------------------------------------------------------------
1014 def runmain(lexer=None,data=None):
1017 filename = sys.argv[1]
1022 sys.stdout.write("Reading from standard input (type EOF to end):\n")
1023 data = sys.stdin.read()
1026 _input = lexer.input
1031 _token = lexer.token
1038 sys.stdout.write("(%s,%r,%d,%d)\n" % (tok.type, tok.value, tok.lineno,tok.lexpos))
1040 # -----------------------------------------------------------------------------
1043 # This decorator function can be used to set the regex expression on a function
1044 # when its docstring might need to be set in an alternative way
1045 # -----------------------------------------------------------------------------
1049 if hasattr(r,"__call__"):
1050 f.__doc__ = r.__doc__
1056 # Alternative spelling of the TOKEN decorator