Skip to content

P
Production Test Suite - base
Commit 316248bb authored by Juan David González Cobas's avatar Juan David González Cobas
Browse files
Options

tps: add ply parser support for complex sequencing

parent 54411fa8
Hide whitespace changes
Inline Side-by-side
Showing with 5369 additions and 0 deletions
ply/__init__.py 0 → 100644
View file @ 316248bb
# PLY package
# Author: David Beazley (dave@dabeaz.com)
__all__ = ['lex','yacc']
ply/cpp.py 0 → 100644
View file @ 316248bb
# -----------------------------------------------------------------------------
# cpp.py
#
# Author: David Beazley (http://www.dabeaz.com)
# Copyright (C) 2007
# All rights reserved
#
# This module implements an ANSI-C style lexical preprocessor for PLY.
# -----------------------------------------------------------------------------
from __future__ import generators
# -----------------------------------------------------------------------------
# Default preprocessor lexer definitions. These tokens are enough to get
# a basic preprocessor working. Other modules may import these if they want
# -----------------------------------------------------------------------------
tokens = (
'CPP_ID','CPP_INTEGER', 'CPP_FLOAT', 'CPP_STRING', 'CPP_CHAR', 'CPP_WS', 'CPP_COMMENT', 'CPP_POUND','CPP_DPOUND'
)
literals = "+-*/%|&~^<>=!?()[]{}.,;:\\\'\""
# Whitespace
def t_CPP_WS(t):
r'\s+'
t.lexer.lineno += t.value.count("\n")
return t
t_CPP_POUND = r'\#'
t_CPP_DPOUND = r'\#\#'
# Identifier
t_CPP_ID = r'[A-Za-z_][\w_]*'
# Integer literal
def CPP_INTEGER(t):
r'(((((0x)|(0X))[0-9a-fA-F]+)|(\d+))([uU]|[lL]|[uU][lL]|[lL][uU])?)'
return t
t_CPP_INTEGER = CPP_INTEGER
# Floating literal
t_CPP_FLOAT = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?'
# String literal
def t_CPP_STRING(t):
r'\"([^\\\n]|(\\(.|\n)))*?\"'
t.lexer.lineno += t.value.count("\n")
return t
# Character constant 'c' or L'c'
def t_CPP_CHAR(t):
r'(L)?\'([^\\\n]|(\\(.|\n)))*?\''
t.lexer.lineno += t.value.count("\n")
return t
# Comment
def t_CPP_COMMENT(t):
r'(/\*(.|\n)*?\*/)|(//.*?\n)'
t.lexer.lineno += t.value.count("\n")
return t
def t_error(t):
t.type = t.value[0]
t.value = t.value[0]
t.lexer.skip(1)
return t
import re
import copy
import time
import os.path
# -----------------------------------------------------------------------------
# trigraph()
#
# Given an input string, this function replaces all trigraph sequences.
# The following mapping is used:
#
# ??= #
# ??/ \
# ??' ^
# ??( [
# ??) ]
# ??! |
# ??< {
# ??> }
# ??- ~
# -----------------------------------------------------------------------------
_trigraph_pat = re.compile(r'''\?\?[=/\'\(\)\!<>\-]''')
_trigraph_rep = {
'=':'#',
'/':'\\',
"'":'^',
'(':'[',
')':']',
'!':'|',
'<':'{',
'>':'}',
'-':'~'
}
def trigraph(input):
return _trigraph_pat.sub(lambda g: _trigraph_rep[g.group()[-1]],input)
# ------------------------------------------------------------------
# Macro object
#
# This object holds information about preprocessor macros
#
# .name - Macro name (string)
# .value - Macro value (a list of tokens)
# .arglist - List of argument names
# .variadic - Boolean indicating whether or not variadic macro
# .vararg - Name of the variadic parameter
#
# When a macro is created, the macro replacement token sequence is
# pre-scanned and used to create patch lists that are later used
# during macro expansion
# ------------------------------------------------------------------
class Macro(object):
def __init__(self,name,value,arglist=None,variadic=False):
self.name = name
self.value = value
self.arglist = arglist
self.variadic = variadic
if variadic:
self.vararg = arglist[-1]
self.source = None
# ------------------------------------------------------------------
# Preprocessor object
#
# Object representing a preprocessor. Contains macro definitions,
# include directories, and other information
# ------------------------------------------------------------------
class Preprocessor(object):
def __init__(self,lexer=None):
if lexer is None:
lexer = lex.lexer
self.lexer = lexer
self.macros = { }
self.path = []
self.temp_path = []
# Probe the lexer for selected tokens
self.lexprobe()
tm = time.localtime()
self.define("__DATE__ \"%s\"" % time.strftime("%b %d %Y",tm))
self.define("__TIME__ \"%s\"" % time.strftime("%H:%M:%S",tm))
self.parser = None
# -----------------------------------------------------------------------------
# tokenize()
#
# Utility function. Given a string of text, tokenize into a list of tokens
# -----------------------------------------------------------------------------
def tokenize(self,text):
tokens = []
self.lexer.input(text)
while True:
tok = self.lexer.token()
if not tok: break
tokens.append(tok)
return tokens
# ---------------------------------------------------------------------
# error()
#
# Report a preprocessor error/warning of some kind
# ----------------------------------------------------------------------
def error(self,file,line,msg):
print("%s:%d %s" % (file,line,msg))
# ----------------------------------------------------------------------
# lexprobe()
#
# This method probes the preprocessor lexer object to discover
# the token types of symbols that are important to the preprocessor.
# If this works right, the preprocessor will simply "work"
# with any suitable lexer regardless of how tokens have been named.
# ----------------------------------------------------------------------
def lexprobe(self):
# Determine the token type for identifiers
self.lexer.input("identifier")
tok = self.lexer.token()
if not tok or tok.value != "identifier":
print("Couldn't determine identifier type")
else:
self.t_ID = tok.type
# Determine the token type for integers
self.lexer.input("12345")
tok = self.lexer.token()
if not tok or int(tok.value) != 12345:
print("Couldn't determine integer type")
else:
self.t_INTEGER = tok.type
self.t_INTEGER_TYPE = type(tok.value)
# Determine the token type for strings enclosed in double quotes
self.lexer.input("\"filename\"")
tok = self.lexer.token()
if not tok or tok.value != "\"filename\"":
print("Couldn't determine string type")
else:
self.t_STRING = tok.type
# Determine the token type for whitespace--if any
self.lexer.input(" ")
tok = self.lexer.token()
if not tok or tok.value != " ":
self.t_SPACE = None
else:
self.t_SPACE = tok.type
# Determine the token type for newlines
self.lexer.input("\n")
tok = self.lexer.token()
if not tok or tok.value != "\n":
self.t_NEWLINE = None
print("Couldn't determine token for newlines")
else:
self.t_NEWLINE = tok.type
self.t_WS = (self.t_SPACE, self.t_NEWLINE)
# Check for other characters used by the preprocessor
chars = [ '<','>','#','##','\\','(',')',',','.']
for c in chars:
self.lexer.input(c)
tok = self.lexer.token()
if not tok or tok.value != c:
print("Unable to lex '%s' required for preprocessor" % c)
# ----------------------------------------------------------------------
# add_path()
#
# Adds a search path to the preprocessor.
# ----------------------------------------------------------------------
def add_path(self,path):
self.path.append(path)
# ----------------------------------------------------------------------
# group_lines()
#
# Given an input string, this function splits it into lines. Trailing whitespace
# is removed. Any line ending with \ is grouped with the next line. This
# function forms the lowest level of the preprocessor---grouping into text into
# a line-by-line format.
# ----------------------------------------------------------------------
def group_lines(self,input):
lex = self.lexer.clone()
lines = [x.rstrip() for x in input.splitlines()]
for i in xrange(len(lines)):
j = i+1
while lines[i].endswith('\\') and (j < len(lines)):
lines[i] = lines[i][:-1]+lines[j]
lines[j] = ""
j += 1
input = "\n".join(lines)
lex.input(input)
lex.lineno = 1
current_line = []
while True:
tok = lex.token()
if not tok:
break
current_line.append(tok)
if tok.type in self.t_WS and '\n' in tok.value:
yield current_line
current_line = []
if current_line:
yield current_line
# ----------------------------------------------------------------------
# tokenstrip()
#
# Remove leading/trailing whitespace tokens from a token list
# ----------------------------------------------------------------------
def tokenstrip(self,tokens):
i = 0
while i < len(tokens) and tokens[i].type in self.t_WS:
i += 1
del tokens[:i]
i = len(tokens)-1
while i >= 0 and tokens[i].type in self.t_WS:
i -= 1
del tokens[i+1:]
return tokens
# ----------------------------------------------------------------------
# collect_args()
#
# Collects comma separated arguments from a list of tokens. The arguments
# must be enclosed in parenthesis. Returns a tuple (tokencount,args,positions)
# where tokencount is the number of tokens consumed, args is a list of arguments,
# and positions is a list of integers containing the starting index of each
# argument. Each argument is represented by a list of tokens.
#
# When collecting arguments, leading and trailing whitespace is removed
# from each argument.
#
# This function properly handles nested parenthesis and commas---these do not
# define new arguments.
# ----------------------------------------------------------------------
def collect_args(self,tokenlist):
args = []
positions = []
current_arg = []
nesting = 1
tokenlen = len(tokenlist)
# Search for the opening '('.
i = 0
while (i < tokenlen) and (tokenlist[i].type in self.t_WS):
i += 1
if (i < tokenlen) and (tokenlist[i].value == '('):
positions.append(i+1)
else:
self.error(self.source,tokenlist[0].lineno,"Missing '(' in macro arguments")
return 0, [], []
i += 1
while i < tokenlen:
t = tokenlist[i]
if t.value == '(':
current_arg.append(t)
nesting += 1
elif t.value == ')':
nesting -= 1
if nesting == 0:
if current_arg:
args.append(self.tokenstrip(current_arg))
positions.append(i)
return i+1,args,positions
current_arg.append(t)
elif t.value == ',' and nesting == 1:
args.append(self.tokenstrip(current_arg))
positions.append(i+1)
current_arg = []
else:
current_arg.append(t)
i += 1
# Missing end argument
self.error(self.source,tokenlist[-1].lineno,"Missing ')' in macro arguments")
return 0, [],[]
# ----------------------------------------------------------------------
# macro_prescan()
#
# Examine the macro value (token sequence) and identify patch points
# This is used to speed up macro expansion later on---we'll know
# right away where to apply patches to the value to form the expansion
# ----------------------------------------------------------------------
def macro_prescan(self,macro):
macro.patch = [] # Standard macro arguments
macro.str_patch = [] # String conversion expansion
macro.var_comma_patch = [] # Variadic macro comma patch
i = 0
while i < len(macro.value):
if macro.value[i].type == self.t_ID and macro.value[i].value in macro.arglist:
argnum = macro.arglist.index(macro.value[i].value)
# Conversion of argument to a string
if i > 0 and macro.value[i-1].value == '#':
macro.value[i] = copy.copy(macro.value[i])
macro.value[i].type = self.t_STRING
del macro.value[i-1]
macro.str_patch.append((argnum,i-1))
continue
# Concatenation
elif (i > 0 and macro.value[i-1].value == '##'):
macro.patch.append(('c',argnum,i-1))
del macro.value[i-1]
continue
elif ((i+1) < len(macro.value) and macro.value[i+1].value == '##'):
macro.patch.append(('c',argnum,i))
i += 1
continue
# Standard expansion
else:
macro.patch.append(('e',argnum,i))
elif macro.value[i].value == '##':
if macro.variadic and (i > 0) and (macro.value[i-1].value == ',') and \
((i+1) < len(macro.value)) and (macro.value[i+1].type == self.t_ID) and \
(macro.value[i+1].value == macro.vararg):
macro.var_comma_patch.append(i-1)
i += 1
macro.patch.sort(key=lambda x: x[2],reverse=True)
# ----------------------------------------------------------------------
# macro_expand_args()
#
# Given a Macro and list of arguments (each a token list), this method
# returns an expanded version of a macro. The return value is a token sequence
# representing the replacement macro tokens
# ----------------------------------------------------------------------
def macro_expand_args(self,macro,args):
# Make a copy of the macro token sequence
rep = [copy.copy(_x) for _x in macro.value]
# Make string expansion patches. These do not alter the length of the replacement sequence
str_expansion = {}
for argnum, i in macro.str_patch:
if argnum not in str_expansion:
str_expansion[argnum] = ('"%s"' % "".join([x.value for x in args[argnum]])).replace("\\","\\\\")
rep[i] = copy.copy(rep[i])
rep[i].value = str_expansion[argnum]
# Make the variadic macro comma patch. If the variadic macro argument is empty, we get rid
comma_patch = False
if macro.variadic and not args[-1]:
for i in macro.var_comma_patch:
rep[i] = None
comma_patch = True
# Make all other patches. The order of these matters. It is assumed that the patch list
# has been sorted in reverse order of patch location since replacements will cause the
# size of the replacement sequence to expand from the patch point.
expanded = { }
for ptype, argnum, i in macro.patch:
# Concatenation. Argument is left unexpanded
if ptype == 'c':
rep[i:i+1] = args[argnum]
# Normal expansion. Argument is macro expanded first
elif ptype == 'e':
if argnum not in expanded:
expanded[argnum] = self.expand_macros(args[argnum])
rep[i:i+1] = expanded[argnum]
# Get rid of removed comma if necessary
if comma_patch:
rep = [_i for _i in rep if _i]
return rep
# ----------------------------------------------------------------------
# expand_macros()
#
# Given a list of tokens, this function performs macro expansion.
# The expanded argument is a dictionary that contains macros already
# expanded. This is used to prevent infinite recursion.
# ----------------------------------------------------------------------
def expand_macros(self,tokens,expanded=None):
if expanded is None:
expanded = {}
i = 0
while i < len(tokens):
t = tokens[i]
if t.type == self.t_ID:
if t.value in self.macros and t.value not in expanded:
# Yes, we found a macro match
expanded[t.value] = True
m = self.macros[t.value]
if not m.arglist:
# A simple macro
ex = self.expand_macros([copy.copy(_x) for _x in m.value],expanded)
for e in ex:
e.lineno = t.lineno
tokens[i:i+1] = ex
i += len(ex)
else:
# A macro with arguments
j = i + 1
while j < len(tokens) and tokens[j].type in self.t_WS:
j += 1
if tokens[j].value == '(':
tokcount,args,positions = self.collect_args(tokens[j:])
if not m.variadic and len(args) != len(m.arglist):
self.error(self.source,t.lineno,"Macro %s requires %d arguments" % (t.value,len(m.arglist)))
i = j + tokcount
elif m.variadic and len(args) < len(m.arglist)-1:
if len(m.arglist) > 2:
self.error(self.source,t.lineno,"Macro %s must have at least %d arguments" % (t.value, len(m.arglist)-1))
else:
self.error(self.source,t.lineno,"Macro %s must have at least %d argument" % (t.value, len(m.arglist)-1))
i = j + tokcount
else:
if m.variadic:
if len(args) == len(m.arglist)-1:
args.append([])
else:
args[len(m.arglist)-1] = tokens[j+positions[len(m.arglist)-1]:j+tokcount-1]
del args[len(m.arglist):]
# Get macro replacement text
rep = self.macro_expand_args(m,args)
rep = self.expand_macros(rep,expanded)
for r in rep:
r.lineno = t.lineno
tokens[i:j+tokcount] = rep
i += len(rep)
del expanded[t.value]
continue
elif t.value == '__LINE__':
t.type = self.t_INTEGER
t.value = self.t_INTEGER_TYPE(t.lineno)
i += 1
return tokens
# ----------------------------------------------------------------------
# evalexpr()
#
# Evaluate an expression token sequence for the purposes of evaluating
# integral expressions.
# ----------------------------------------------------------------------
def evalexpr(self,tokens):
# tokens = tokenize(line)
# Search for defined macros
i = 0
while i < len(tokens):
if tokens[i].type == self.t_ID and tokens[i].value == 'defined':
j = i + 1
needparen = False
result = "0L"
while j < len(tokens):
if tokens[j].type in self.t_WS:
j += 1
continue
elif tokens[j].type == self.t_ID:
if tokens[j].value in self.macros:
result = "1L"
else:
result = "0L"
if not needparen: break
elif tokens[j].value == '(':
needparen = True
elif tokens[j].value == ')':
break
else:
self.error(self.source,tokens[i].lineno,"Malformed defined()")
j += 1
tokens[i].type = self.t_INTEGER
tokens[i].value = self.t_INTEGER_TYPE(result)
del tokens[i+1:j+1]
i += 1
tokens = self.expand_macros(tokens)
for i,t in enumerate(tokens):
if t.type == self.t_ID:
tokens[i] = copy.copy(t)
tokens[i].type = self.t_INTEGER
tokens[i].value = self.t_INTEGER_TYPE("0L")
elif t.type == self.t_INTEGER:
tokens[i] = copy.copy(t)
# Strip off any trailing suffixes
tokens[i].value = str(tokens[i].value)
while tokens[i].value[-1] not in "0123456789abcdefABCDEF":
tokens[i].value = tokens[i].value[:-1]
expr = "".join([str(x.value) for x in tokens])
expr = expr.replace("&&"," and ")
expr = expr.replace("||"," or ")
expr = expr.replace("!"," not ")
try:
result = eval(expr)
except StandardError:
self.error(self.source,tokens[0].lineno,"Couldn't evaluate expression")
result = 0
return result
# ----------------------------------------------------------------------
# parsegen()
#
# Parse an input string/
# ----------------------------------------------------------------------
def parsegen(self,input,source=None):
# Replace trigraph sequences
t = trigraph(input)
lines = self.group_lines(t)
if not source:
source = ""
self.define("__FILE__ \"%s\"" % source)
self.source = source
chunk = []
enable = True
iftrigger = False
ifstack = []
for x in lines:
for i,tok in enumerate(x):
if tok.type not in self.t_WS: break
if tok.value == '#':
# Preprocessor directive
for tok in x:
if tok in self.t_WS and '\n' in tok.value:
chunk.append(tok)
dirtokens = self.tokenstrip(x[i+1:])
if dirtokens:
name = dirtokens[0].value
args = self.tokenstrip(dirtokens[1:])
else:
name = ""
args = []
if name == 'define':
if enable:
for tok in self.expand_macros(chunk):
yield tok
chunk = []
self.define(args)
elif name == 'include':
if enable:
for tok in self.expand_macros(chunk):
yield tok
chunk = []
oldfile = self.macros['__FILE__']
for tok in self.include(args):
yield tok
self.macros['__FILE__'] = oldfile
self.source = source
elif name == 'undef':
if enable:
for tok in self.expand_macros(chunk):
yield tok
chunk = []
self.undef(args)
elif name == 'ifdef':
ifstack.append((enable,iftrigger))
if enable:
if not args[0].value in self.macros:
enable = False
iftrigger = False
else:
iftrigger = True
elif name == 'ifndef':
ifstack.append((enable,iftrigger))
if enable:
if args[0].value in self.macros:
enable = False
iftrigger = False
else:
iftrigger = True
elif name == 'if':
ifstack.append((enable,iftrigger))
if enable:
result = self.evalexpr(args)
if not result:
enable = False
iftrigger = False
else:
iftrigger = True
elif name == 'elif':
if ifstack:
if ifstack[-1][0]: # We only pay attention if outer "if" allows this
if enable: # If already true, we flip enable False
enable = False
elif not iftrigger: # If False, but not triggered yet, we'll check expression
result = self.evalexpr(args)
if result:
enable = True
iftrigger = True
else:
self.error(self.source,dirtokens[0].lineno,"Misplaced #elif")
elif name == 'else':
if ifstack:
if ifstack[-1][0]:
if enable:
enable = False
elif not iftrigger:
enable = True
iftrigger = True
else:
self.error(self.source,dirtokens[0].lineno,"Misplaced #else")
elif name == 'endif':
if ifstack:
enable,iftrigger = ifstack.pop()
else:
self.error(self.source,dirtokens[0].lineno,"Misplaced #endif")
else:
# Unknown preprocessor directive
pass
else:
# Normal text
if enable:
chunk.extend(x)
for tok in self.expand_macros(chunk):
yield tok
chunk = []
# ----------------------------------------------------------------------
# include()
#
# Implementation of file-inclusion
# ----------------------------------------------------------------------
def include(self,tokens):
# Try to extract the filename and then process an include file
if not tokens:
return
if tokens:
if tokens[0].value != '<' and tokens[0].type != self.t_STRING:
tokens = self.expand_macros(tokens)
if tokens[0].value == '<':
# Include <...>
i = 1
while i < len(tokens):
if tokens[i].value == '>':
break
i += 1
else:
print("Malformed #include <...>")
return
filename = "".join([x.value for x in tokens[1:i]])
path = self.path + [""] + self.temp_path
elif tokens[0].type == self.t_STRING:
filename = tokens[0].value[1:-1]
path = self.temp_path + [""] + self.path
else:
print("Malformed #include statement")
return
for p in path:
iname = os.path.join(p,filename)
try:
data = open(iname,"r").read()
dname = os.path.dirname(iname)
if dname:
self.temp_path.insert(0,dname)
for tok in self.parsegen(data,filename):
yield tok
if dname:
del self.temp_path[0]
break
except IOError:
pass
else:
print("Couldn't find '%s'" % filename)
# ----------------------------------------------------------------------
# define()
#
# Define a new macro
# ----------------------------------------------------------------------
def define(self,tokens):
if isinstance(tokens,(str,unicode)):
tokens = self.tokenize(tokens)
linetok = tokens
try:
name = linetok[0]
if len(linetok) > 1:
mtype = linetok[1]
else:
mtype = None
if not mtype:
m = Macro(name.value,[])
self.macros[name.value] = m
elif mtype.type in self.t_WS:
# A normal macro
m = Macro(name.value,self.tokenstrip(linetok[2:]))
self.macros[name.value] = m
elif mtype.value == '(':
# A macro with arguments
tokcount, args, positions = self.collect_args(linetok[1:])
variadic = False
for a in args:
if variadic:
print("No more arguments may follow a variadic argument")
break
astr = "".join([str(_i.value) for _i in a])
if astr == "...":
variadic = True
a[0].type = self.t_ID
a[0].value = '__VA_ARGS__'
variadic = True
del a[1:]
continue
elif astr[-3:] == "..." and a[0].type == self.t_ID:
variadic = True
del a[1:]
# If, for some reason, "." is part of the identifier, strip off the name for the purposes
# of macro expansion
if a[0].value[-3:] == '...':
a[0].value = a[0].value[:-3]
continue
if len(a) > 1 or a[0].type != self.t_ID:
print("Invalid macro argument")
break
else:
mvalue = self.tokenstrip(linetok[1+tokcount:])
i = 0
while i < len(mvalue):
if i+1 < len(mvalue):
if mvalue[i].type in self.t_WS and mvalue[i+1].value == '##':
del mvalue[i]
continue
elif mvalue[i].value == '##' and mvalue[i+1].type in self.t_WS:
del mvalue[i+1]
i += 1
m = Macro(name.value,mvalue,[x[0].value for x in args],variadic)
self.macro_prescan(m)
self.macros[name.value] = m
else:
print("Bad macro definition")
except LookupError:
print("Bad macro definition")
# ----------------------------------------------------------------------
# undef()
#
# Undefine a macro
# ----------------------------------------------------------------------
def undef(self,tokens):
id = tokens[0].value
try:
del self.macros[id]
except LookupError:
pass
# ----------------------------------------------------------------------
# parse()
#
# Parse input text.
# ----------------------------------------------------------------------
def parse(self,input,source=None,ignore={}):
self.ignore = ignore
self.parser = self.parsegen(input,source)
# ----------------------------------------------------------------------
# token()
#
# Method to return individual tokens
# ----------------------------------------------------------------------
def token(self):
try:
while True:
tok = next(self.parser)
if tok.type not in self.ignore: return tok
except StopIteration:
self.parser = None
return None
if __name__ == '__main__':
import ply.lex as lex
lexer = lex.lex()
# Run a preprocessor
import sys
f = open(sys.argv[1])
input = f.read()
p = Preprocessor(lexer)
p.parse(input,sys.argv[1])
while True:
tok = p.token()
if not tok: break
print(p.source, tok)
ply/ctokens.py 0 → 100644
View file @ 316248bb
# ----------------------------------------------------------------------
# ctokens.py
#
# Token specifications for symbols in ANSI C and C++. This file is
# meant to be used as a library in other tokenizers.
# ----------------------------------------------------------------------
# Reserved words
tokens = [
# Literals (identifier, integer constant, float constant, string constant, char const)
'ID', 'TYPEID', 'ICONST', 'FCONST', 'SCONST', 'CCONST',
# Operators (+,-,*,/,%,|,&,~,^,<<,>>, ||, &&, !, <, <=, >, >=, ==, !=)
'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD',
'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFT',
'LOR', 'LAND', 'LNOT',
'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',
# Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, &=, ^=, |=)
'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL',
'LSHIFTEQUAL','RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL', 'OREQUAL',
# Increment/decrement (++,--)
'PLUSPLUS', 'MINUSMINUS',
# Structure dereference (->)
'ARROW',
# Ternary operator (?)
'TERNARY',
# Delimeters ( ) [ ] { } , . ; :
'LPAREN', 'RPAREN',
'LBRACKET', 'RBRACKET',
'LBRACE', 'RBRACE',
'COMMA', 'PERIOD', 'SEMI', 'COLON',
# Ellipsis (...)
'ELLIPSIS',
]
# Operators
t_PLUS = r'\+'
t_MINUS = r'-'
t_TIMES = r'\*'
t_DIVIDE = r'/'
t_MODULO = r'%'
t_OR = r'\|'
t_AND = r'&'
t_NOT = r'~'
t_XOR = r'\^'
t_LSHIFT = r'<<'
t_RSHIFT = r'>>'
t_LOR = r'\|\|'
t_LAND = r'&&'
t_LNOT = r'!'
t_LT = r'<'
t_GT = r'>'
t_LE = r'<='
t_GE = r'>='
t_EQ = r'=='
t_NE = r'!='
# Assignment operators
t_EQUALS = r'='
t_TIMESEQUAL = r'\*='
t_DIVEQUAL = r'/='
t_MODEQUAL = r'%='
t_PLUSEQUAL = r'\+='
t_MINUSEQUAL = r'-='
t_LSHIFTEQUAL = r'<<='
t_RSHIFTEQUAL = r'>>='
t_ANDEQUAL = r'&='
t_OREQUAL = r'\|='
t_XOREQUAL = r'^='
# Increment/decrement
t_INCREMENT = r'\+\+'
t_DECREMENT = r'--'
# ->
t_ARROW = r'->'
# ?
t_TERNARY = r'\?'
# Delimeters
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_LBRACKET = r'\['
t_RBRACKET = r'\]'
t_LBRACE = r'\{'
t_RBRACE = r'\}'
t_COMMA = r','
t_PERIOD = r'\.'
t_SEMI = r';'
t_COLON = r':'
t_ELLIPSIS = r'\.\.\.'
# Identifiers
t_ID = r'[A-Za-z_][A-Za-z0-9_]*'
# Integer literal
t_INTEGER = r'\d+([uU]|[lL]|[uU][lL]|[lL][uU])?'
# Floating literal
t_FLOAT = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?'
# String literal
t_STRING = r'\"([^\\\n]|(\\.))*?\"'
# Character constant 'c' or L'c'
t_CHARACTER = r'(L)?\'([^\\\n]|(\\.))*?\''
# Comment (C-Style)
def t_COMMENT(t):
r'/\*(.|\n)*?\*/'
t.lexer.lineno += t.value.count('\n')
return t
# Comment (C++-Style)
def t_CPPCOMMENT(t):
r'//.*\n'
t.lexer.lineno += 1
return t
ply/lex.py 0 → 100644
View file @ 316248bb
# -----------------------------------------------------------------------------
# ply: lex.py
#
# Copyright (C) 2001-2011,
# 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__ = "3.4"
__tabversion__ = "3.2" # Version of table file used
import re, sys, types, copy, os
# This tuple contains known string types
try:
# Python 2.6
StringTypes = (types.StringType, types.UnicodeType)
except AttributeError:
# Python 3.0
StringTypes = (str, bytes)
# Extract the code attribute of a function. Different implementations
# are for Python 2/3 compatibility.
if sys.version_info[0] < 3:
def func_code(f):
return f.func_code
else:
def func_code(f):
return f.__code__
# 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.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.lexoptimize = 0 # 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,tabfile,outputdir=""):
if isinstance(tabfile,types.ModuleType):
return
basetabfilename = tabfile.split(".")[-1]
filename = os.path.join(outputdir,basetabfilename)+".py"
tf = open(filename,"w")
tf.write("# %s.py. This file automatically created by PLY (version %s). Don't edit!\n" % (tabfile,__version__))
tf.write("_tabversion = %s\n" % repr(__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 = { }
# Collect all functions in the initial state
initial = self.lexstatere["INITIAL"]
initialfuncs = []
for part in initial:
for f in part[1]:
if f and f[0]:
initialfuncs.append(f)
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],self.lexstaterenames[key][i])))
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):
if isinstance(tabfile,types.ModuleType):
lextab = tabfile
else:
if sys.version_info[0] < 3:
exec("import %s as lextab" % tabfile)
else:
env = { }
exec("import %s as lextab" % tabfile, env,env)
lextab = env['lextab']
if getattr(lextab,"_tabversion","0.0") != __version__:
raise ImportError("Inconsistent PLY version")
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 | re.VERBOSE),_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):
# 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 not state 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.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
tok.lexer = self # Set additional attributes useful in token rules
self.lexmatch = m
self.lexpos = lexpos
newtok = func(tok)
# Every function must return a token, if nothing, we just move to next token
if not newtok:
lexpos = self.lexpos # This is here in case user has updated lexpos.
lexignore = self.lexignore # This is here in case there was a state change
break
# Verify type of the token. If not in the token map, raise an error
if not self.lexoptimize:
if not newtok.type in self.lextokens:
raise LexError("%s:%d: Rule '%s' returned an unknown token type '%s'" % (
func_code(func).co_filename, func_code(func).co_firstlineno,
func.__name__, newtok.type),lexdata[lexpos:])
return newtok
else:
# No match, see if in literals
if lexdata[lexpos] in self.lexliterals:
tok = LexToken()
tok.value = lexdata[lexpos]
tok.lineno = self.lineno
tok.type = tok.value
tok.lexpos = lexpos
self.lexpos = lexpos + 1
return tok
# No match. Call t_error() if defined.
if self.lexerrorf:
tok = LexToken()
tok.value = self.lexdata[lexpos:]
tok.lineno = self.lineno
tok.type = "error"
tok.lexer = self
tok.lexpos = lexpos
self.lexpos = lexpos
newtok = self.lexerrorf(tok)
if lexpos == self.lexpos:
# Error method didn't change text position at all. This is an error.
raise LexError("Scanning error. Illegal character '%s'" % (lexdata[lexpos]), lexdata[lexpos:])
lexpos = self.lexpos
if not newtok: continue
return newtok
self.lexpos = lexpos
raise LexError("Illegal character '%s' at index %d" % (lexdata[lexpos],lexpos), lexdata[lexpos:])
self.lexpos = lexpos + 1
if self.lexdata is None:
raise RuntimeError("No input string given with input()")
return None
# Iterator interface
def __iter__(self):
return self
def next(self):
t = self.token()
if t is None:
raise StopIteration
return t
__next__ = next
# -----------------------------------------------------------------------------
# ==== Lex Builder ===
#
# The functions and classes below are used to collect lexing information
# and build a Lexer object from it.
# -----------------------------------------------------------------------------
# -----------------------------------------------------------------------------
# get_caller_module_dict()
#
# This function returns a dictionary containing all of the symbols defined within
# a caller further down the call stack. This is used to get the environment
# associated with the yacc() call if none was provided.
# -----------------------------------------------------------------------------
def get_caller_module_dict(levels):
try:
raise RuntimeError
except RuntimeError:
e,b,t = sys.exc_info()
f = t.tb_frame
while levels > 0:
f = f.f_back
levels -= 1
ldict = f.f_globals.copy()
if f.f_globals != f.f_locals:
ldict.update(f.f_locals)
return ldict
# -----------------------------------------------------------------------------
# _funcs_to_names()
#
# Given a list of regular expression functions, this converts it to a list
# suitable for output to a table file
# -----------------------------------------------------------------------------
def _funcs_to_names(funclist,namelist):
result = []
for f,name in zip(funclist,namelist):
if f and f[0]:
result.append((name, f[1]))
else:
result.append(f)
return result
# -----------------------------------------------------------------------------
# _names_to_funcs()
#
# Given a list of regular expression function names, this converts it back to
# functions.
# -----------------------------------------------------------------------------
def _names_to_funcs(namelist,fdict):
result = []
for n in namelist:
if n and n[0]:
result.append((fdict[n[0]],n[1]))
else:
result.append(n)
return result
# -----------------------------------------------------------------------------
# _form_master_re()
#
# This function takes a list of all of the regex components and attempts to
# form the master regular expression. Given limitations in the Python re
# module, it may be necessary to break the master regex into separate expressions.
# -----------------------------------------------------------------------------
def _form_master_re(relist,reflags,ldict,toknames):
if not relist: return []
regex = "|".join(relist)
try:
lexre = re.compile(regex,re.VERBOSE | reflags)
# Build the index to function map for the matching engine
lexindexfunc = [ None ] * (max(lexre.groupindex.values())+1)
lexindexnames = lexindexfunc[:]
for f,i in lexre.groupindex.items():
handle = ldict.get(f,None)
if type(handle) in (types.FunctionType, types.MethodType):
lexindexfunc[i] = (handle,toknames[f])
lexindexnames[i] = f
elif handle is not None:
lexindexnames[i] = f
if f.find("ignore_") > 0:
lexindexfunc[i] = (None,None)
else:
lexindexfunc[i] = (None, toknames[f])
return [(lexre,lexindexfunc)],[regex],[lexindexnames]
except Exception:
m = int(len(relist)/2)
if m == 0: m = 1
llist, lre, lnames = _form_master_re(relist[:m],reflags,ldict,toknames)
rlist, rre, rnames = _form_master_re(relist[m:],reflags,ldict,toknames)
return llist+rlist, lre+rre, lnames+rnames
# -----------------------------------------------------------------------------
# def _statetoken(s,names)
#
# Given a declaration name s of the form "t_" and a dictionary whose keys are
# state names, this function returns a tuple (states,tokenname) where states
# is a tuple of state names and tokenname is the name of the token. For example,
# calling this with s = "t_foo_bar_SPAM" might return (('foo','bar'),'SPAM')
# -----------------------------------------------------------------------------
def _statetoken(s,names):
nonstate = 1
parts = s.split("_")
for i in range(1,len(parts)):
if not parts[i] in names and parts[i] != 'ANY': break
if i > 1:
states = tuple(parts[1:i])
else:
states = ('INITIAL',)
if 'ANY' in states:
states = tuple(names)
tokenname = "_".join(parts[i:])
return (states,tokenname)
# -----------------------------------------------------------------------------
# LexerReflect()
#
# This class represents information needed to build a lexer as extracted from a
# user's input file.
# -----------------------------------------------------------------------------
class LexerReflect(object):
def __init__(self,ldict,log=None,reflags=0):
self.ldict = ldict
self.error_func = None
self.tokens = []
self.reflags = reflags
self.stateinfo = { 'INITIAL' : 'inclusive'}
self.files = {}
self.error = 0
if log is None:
self.log = PlyLogger(sys.stderr)
else:
self.log = log
# Get all of the basic information
def get_all(self):
self.get_tokens()
self.get_literals()
self.get_states()
self.get_rules()
# Validate all of the information
def validate_all(self):
self.validate_tokens()
self.validate_literals()
self.validate_rules()
return self.error
# Get the tokens map
def get_tokens(self):
tokens = self.ldict.get("tokens",None)
if not tokens:
self.log.error("No token list is defined")
self.error = 1
return
if not isinstance(tokens,(list, tuple)):
self.log.error("tokens must be a list or tuple")
self.error = 1
return
if not tokens:
self.log.error("tokens is empty")
self.error = 1
return
self.tokens = tokens
# Validate the tokens
def validate_tokens(self):
terminals = {}
for n in self.tokens:
if not _is_identifier.match(n):
self.log.error("Bad token name '%s'",n)
self.error = 1
if n in terminals:
self.log.warning("Token '%s' multiply defined", n)
terminals[n] = 1
# Get the literals specifier
def get_literals(self):
self.literals = self.ldict.get("literals","")
# Validate literals
def validate_literals(self):
try:
for c in self.literals:
if not isinstance(c,StringTypes) or len(c) > 1:
self.log.error("Invalid literal %s. Must be a single character", repr(c))
self.error = 1
continue
except TypeError:
self.log.error("Invalid literals specification. literals must be a sequence of characters")
self.error = 1
def get_states(self):
self.states = self.ldict.get("states",None)
# Build statemap
if self.states:
if not isinstance(self.states,(tuple,list)):
self.log.error("states must be defined as a tuple or list")
self.error = 1
else:
for s in self.states:
if not isinstance(s,tuple) or len(s) != 2:
self.log.error("Invalid state specifier %s. Must be a tuple (statename,'exclusive|inclusive')",repr(s))
self.error = 1
continue
name, statetype = s
if not isinstance(name,StringTypes):
self.log.error("State name %s must be a string", repr(name))
self.error = 1
continue
if not (statetype == 'inclusive' or statetype == 'exclusive'):
self.log.error("State type for state %s must be 'inclusive' or 'exclusive'",name)
self.error = 1
continue
if name in self.stateinfo:
self.log.error("State '%s' already defined",name)
self.error = 1
continue
self.stateinfo[name] = statetype
# Get all of the symbols with a t_ prefix and sort them into various
# categories (functions, strings, error functions, and ignore characters)
def get_rules(self):
tsymbols = [f for f in self.ldict if f[:2] == 't_' ]
# Now build up a list of functions and a list of strings
self.toknames = { } # Mapping of symbols to token names
self.funcsym = { } # Symbols defined as functions
self.strsym = { } # Symbols defined as strings
self.ignore = { } # Ignore strings by state
self.errorf = { } # Error functions by state
for s in self.stateinfo:
self.funcsym[s] = []
self.strsym[s] = []
if len(tsymbols) == 0:
self.log.error("No rules of the form t_rulename are defined")
self.error = 1
return
for f in tsymbols:
t = self.ldict[f]
states, tokname = _statetoken(f,self.stateinfo)
self.toknames[f] = tokname
if hasattr(t,"__call__"):
if tokname == 'error':
for s in states:
self.errorf[s] = t
elif tokname == 'ignore':
line = func_code(t).co_firstlineno
file = func_code(t).co_filename
self.log.error("%s:%d: Rule '%s' must be defined as a string",file,line,t.__name__)
self.error = 1
else:
for s in states:
self.funcsym[s].append((f,t))
elif isinstance(t, StringTypes):
if tokname == 'ignore':
for s in states:
self.ignore[s] = t
if "\\" in t:
self.log.warning("%s contains a literal backslash '\\'",f)
elif tokname == 'error':
self.log.error("Rule '%s' must be defined as a function", f)
self.error = 1
else:
for s in states:
self.strsym[s].append((f,t))
else:
self.log.error("%s not defined as a function or string", f)
self.error = 1
# Sort the functions by line number
for f in self.funcsym.values():
if sys.version_info[0] < 3:
f.sort(lambda x,y: cmp(func_code(x[1]).co_firstlineno,func_code(y[1]).co_firstlineno))
else:
# Python 3.0
f.sort(key=lambda x: func_code(x[1]).co_firstlineno)
# Sort the strings by regular expression length
for s in self.strsym.values():
if sys.version_info[0] < 3:
s.sort(lambda x,y: (len(x[1]) < len(y[1])) - (len(x[1]) > len(y[1])))
else:
# Python 3.0
s.sort(key=lambda x: len(x[1]),reverse=True)
# Validate all of the t_rules collected
def validate_rules(self):
for state in self.stateinfo:
# Validate all rules defined by functions
for fname, f in self.funcsym[state]:
line = func_code(f).co_firstlineno
file = func_code(f).co_filename
self.files[file] = 1
tokname = self.toknames[fname]
if isinstance(f, types.MethodType):
reqargs = 2
else:
reqargs = 1
nargs = func_code(f).co_argcount
if nargs > reqargs:
self.log.error("%s:%d: Rule '%s' has too many arguments",file,line,f.__name__)
self.error = 1
continue
if nargs < reqargs:
self.log.error("%s:%d: Rule '%s' requires an argument", file,line,f.__name__)
self.error = 1
continue
if not f.__doc__:
self.log.error("%s:%d: No regular expression defined for rule '%s'",file,line,f.__name__)
self.error = 1
continue
try:
c = re.compile("(?P<%s>%s)" % (fname,f.__doc__), re.VERBOSE | self.reflags)
if c.match(""):
self.log.error("%s:%d: Regular expression for rule '%s' matches empty string", file,line,f.__name__)
self.error = 1
except re.error:
_etype, e, _etrace = sys.exc_info()
self.log.error("%s:%d: Invalid regular expression for rule '%s'. %s", file,line,f.__name__,e)
if '#' in f.__doc__:
self.log.error("%s:%d. Make sure '#' in rule '%s' is escaped with '\\#'",file,line, f.__name__)
self.error = 1
# Validate all rules defined by strings
for name,r in self.strsym[state]:
tokname = self.toknames[name]
if tokname == 'error':
self.log.error("Rule '%s' must be defined as a function", name)
self.error = 1
continue
if not tokname in self.tokens and tokname.find("ignore_") < 0:
self.log.error("Rule '%s' defined for an unspecified token %s",name,tokname)
self.error = 1
continue
try:
c = re.compile("(?P<%s>%s)" % (name,r),re.VERBOSE | self.reflags)
if (c.match("")):
self.log.error("Regular expression for rule '%s' matches empty string",name)
self.error = 1
except re.error:
_etype, e, _etrace = sys.exc_info()
self.log.error("Invalid regular expression for rule '%s'. %s",name,e)
if '#' in r:
self.log.error("Make sure '#' in rule '%s' is escaped with '\\#'",name)
self.error = 1
if not self.funcsym[state] and not self.strsym[state]:
self.log.error("No rules defined for state '%s'",state)
self.error = 1
# Validate the error function
efunc = self.errorf.get(state,None)
if efunc:
f = efunc
line = func_code(f).co_firstlineno
file = func_code(f).co_filename
self.files[file] = 1
if isinstance(f, types.MethodType):
reqargs = 2
else:
reqargs = 1
nargs = func_code(f).co_argcount
if nargs > reqargs:
self.log.error("%s:%d: Rule '%s' has too many arguments",file,line,f.__name__)
self.error = 1
if nargs < reqargs:
self.log.error("%s:%d: Rule '%s' requires an argument", file,line,f.__name__)
self.error = 1
for f in self.files:
self.validate_file(f)
# -----------------------------------------------------------------------------
# validate_file()
#
# This checks to see if there are duplicated t_rulename() functions or strings
# in the parser input file. This is done using a simple regular expression
# match on each line in the given file.
# -----------------------------------------------------------------------------
def validate_file(self,filename):
import os.path
base,ext = os.path.splitext(filename)
if ext != '.py': return # No idea what the file is. Return OK
try:
f = open(filename)
lines = f.readlines()
f.close()
except IOError:
return # Couldn't find the file. Don't worry about it
fre = re.compile(r'\s*def\s+(t_[a-zA-Z_0-9]*)\(')
sre = re.compile(r'\s*(t_[a-zA-Z_0-9]*)\s*=')
counthash = { }
linen = 1
for l in lines:
m = fre.match(l)
if not m:
m = sre.match(l)
if m:
name = m.group(1)
prev = counthash.get(name)
if not prev:
counthash[name] = linen
else:
self.log.error("%s:%d: Rule %s redefined. Previously defined on line %d",filename,linen,name,prev)
self.error = 1
linen += 1
# -----------------------------------------------------------------------------
# lex(module)
#
# Build all of the regular expression rules from definitions in the supplied module
# -----------------------------------------------------------------------------
def lex(module=None,object=None,debug=0,optimize=0,lextab="lextab",reflags=0,nowarn=0,outputdir="", debuglog=None, errorlog=None):
global lexer
ldict = None
stateinfo = { 'INITIAL' : 'inclusive'}
lexobj = Lexer()
lexobj.lexoptimize = optimize
global token,input
if errorlog is None:
errorlog = PlyLogger(sys.stderr)
if debug:
if debuglog is None:
debuglog = PlyLogger(sys.stderr)
# Get the module dictionary used for the lexer
if object: module = object
if module:
_items = [(k,getattr(module,k)) for k in dir(module)]
ldict = dict(_items)
else:
ldict = get_caller_module_dict(2)
# Collect parser information from the dictionary
linfo = LexerReflect(ldict,log=errorlog,reflags=reflags)
linfo.get_all()
if not optimize:
if linfo.validate_all():
raise SyntaxError("Can't build lexer")
if optimize and lextab:
try:
lexobj.readtab(lextab,ldict)
token = lexobj.token
input = lexobj.input
lexer = lexobj
return lexobj
except ImportError:
pass
# Dump some basic debugging information
if debug:
debuglog.info("lex: tokens = %r", linfo.tokens)
debuglog.info("lex: literals = %r", linfo.literals)
debuglog.info("lex: states = %r", linfo.stateinfo)
# Build a dictionary of valid token names
lexobj.lextokens = { }
for n in linfo.tokens:
lexobj.lextokens[n] = 1
# Get literals specification
if isinstance(linfo.literals,(list,tuple)):
lexobj.lexliterals = type(linfo.literals[0])().join(linfo.literals)
else:
lexobj.lexliterals = linfo.literals
# Get the stateinfo dictionary
stateinfo = linfo.stateinfo
regexs = { }
# Build the master regular expressions
for state in stateinfo:
regex_list = []
# Add rules defined by functions first
for fname, f in linfo.funcsym[state]:
line = func_code(f).co_firstlineno
file = func_code(f).co_filename
regex_list.append("(?P<%s>%s)" % (fname,f.__doc__))
if debug:
debuglog.info("lex: Adding rule %s -> '%s' (state '%s')",fname,f.__doc__, state)
# Now add all of the simple rules
for name,r in linfo.strsym[state]:
regex_list.append("(?P<%s>%s)" % (name,r))
if debug:
debuglog.info("lex: Adding rule %s -> '%s' (state '%s')",name,r, state)
regexs[state] = regex_list
# Build the master regular expressions
if debug:
debuglog.info("lex: ==== MASTER REGEXS FOLLOW ====")
for state in regexs:
lexre, re_text, re_names = _form_master_re(regexs[state],reflags,ldict,linfo.toknames)
lexobj.lexstatere[state] = lexre
lexobj.lexstateretext[state] = re_text
lexobj.lexstaterenames[state] = re_names
if debug:
for i in range(len(re_text)):
debuglog.info("lex: state '%s' : regex[%d] = '%s'",state, i, re_text[i])
# For inclusive states, we need to add the regular expressions from the INITIAL state
for state,stype in stateinfo.items():
if state != "INITIAL" and stype == 'inclusive':
lexobj.lexstatere[state].extend(lexobj.lexstatere['INITIAL'])
lexobj.lexstateretext[state].extend(lexobj.lexstateretext['INITIAL'])
lexobj.lexstaterenames[state].extend(lexobj.lexstaterenames['INITIAL'])
lexobj.lexstateinfo = stateinfo
lexobj.lexre = lexobj.lexstatere["INITIAL"]
lexobj.lexretext = lexobj.lexstateretext["INITIAL"]
lexobj.lexreflags = reflags
# Set up ignore variables
lexobj.lexstateignore = linfo.ignore
lexobj.lexignore = lexobj.lexstateignore.get("INITIAL","")
# Set up error functions
lexobj.lexstateerrorf = linfo.errorf
lexobj.lexerrorf = linfo.errorf.get("INITIAL",None)
if not lexobj.lexerrorf:
errorlog.warning("No t_error rule is defined")
# Check state information for ignore and error rules
for s,stype in stateinfo.items():
if stype == 'exclusive':
if not s in linfo.errorf:
errorlog.warning("No error rule is defined for exclusive state '%s'", s)
if not s in linfo.ignore and lexobj.lexignore:
errorlog.warning("No ignore rule is defined for exclusive state '%s'", s)
elif stype == 'inclusive':
if not s in linfo.errorf:
linfo.errorf[s] = linfo.errorf.get("INITIAL",None)
if not s in linfo.ignore:
linfo.ignore[s] = linfo.ignore.get("INITIAL","")
# Create global versions of the token() and input() functions
token = lexobj.token
input = lexobj.input
lexer = lexobj
# If in optimize mode, we write the lextab
if lextab and optimize:
lexobj.writetab(lextab,outputdir)
return lexobj
# -----------------------------------------------------------------------------
# runmain()
#
# This runs the lexer as a main program
# -----------------------------------------------------------------------------
def runmain(lexer=None,data=None):
if not data:
try:
filename = sys.argv[1]
f = open(filename)
data = f.read()
f.close()
except IndexError:
sys.stdout.write("Reading from standard input (type EOF to end):\n")
data = sys.stdin.read()
if lexer:
_input = lexer.input
else:
_input = input
_input(data)
if lexer:
_token = lexer.token
else:
_token = token
while 1:
tok = _token()
if not tok: break
sys.stdout.write("(%s,%r,%d,%d)\n" % (tok.type, tok.value, tok.lineno,tok.lexpos))
# -----------------------------------------------------------------------------
# @TOKEN(regex)
#
# This decorator function can be used to set the regex expression on a function
# when its docstring might need to be set in an alternative way
# -----------------------------------------------------------------------------
def TOKEN(r):
def set_doc(f):
if hasattr(r,"__call__"):
f.__doc__ = r.__doc__
else:
f.__doc__ = r
return f
return set_doc
# Alternative spelling of the TOKEN decorator
Token = TOKEN
ply/yacc.py 0 → 100644
View file @ 316248bb
This source diff could not be displayed because it is too large. You can view the blob instead.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment