| Current File : /home/mmdealscpanel/yummmdeals.com/pgen2.zip |
PK �C[��r� � __init__.pynu �[��� # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""The pgen2 package."""
PK �C[�2��� � parse.pynu �[��� # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""Parser engine for the grammar tables generated by pgen.
The grammar table must be loaded first.
See Parser/parser.c in the Python distribution for additional info on
how this parsing engine works.
"""
# Local imports
from . import token
class ParseError(Exception):
"""Exception to signal the parser is stuck."""
def __init__(self, msg, type, value, context):
Exception.__init__(self, "%s: type=%r, value=%r, context=%r" %
(msg, type, value, context))
self.msg = msg
self.type = type
self.value = value
self.context = context
def __reduce__(self):
return type(self), (self.msg, self.type, self.value, self.context)
class Parser(object):
"""Parser engine.
The proper usage sequence is:
p = Parser(grammar, [converter]) # create instance
p.setup([start]) # prepare for parsing
<for each input token>:
if p.addtoken(...): # parse a token; may raise ParseError
break
root = p.rootnode # root of abstract syntax tree
A Parser instance may be reused by calling setup() repeatedly.
A Parser instance contains state pertaining to the current token
sequence, and should not be used concurrently by different threads
to parse separate token sequences.
See driver.py for how to get input tokens by tokenizing a file or
string.
Parsing is complete when addtoken() returns True; the root of the
abstract syntax tree can then be retrieved from the rootnode
instance variable. When a syntax error occurs, addtoken() raises
the ParseError exception. There is no error recovery; the parser
cannot be used after a syntax error was reported (but it can be
reinitialized by calling setup()).
"""
def __init__(self, grammar, convert=None):
"""Constructor.
The grammar argument is a grammar.Grammar instance; see the
grammar module for more information.
The parser is not ready yet for parsing; you must call the
setup() method to get it started.
The optional convert argument is a function mapping concrete
syntax tree nodes to abstract syntax tree nodes. If not
given, no conversion is done and the syntax tree produced is
the concrete syntax tree. If given, it must be a function of
two arguments, the first being the grammar (a grammar.Grammar
instance), and the second being the concrete syntax tree node
to be converted. The syntax tree is converted from the bottom
up.
A concrete syntax tree node is a (type, value, context, nodes)
tuple, where type is the node type (a token or symbol number),
value is None for symbols and a string for tokens, context is
None or an opaque value used for error reporting (typically a
(lineno, offset) pair), and nodes is a list of children for
symbols, and None for tokens.
An abstract syntax tree node may be anything; this is entirely
up to the converter function.
"""
self.grammar = grammar
self.convert = convert or (lambda grammar, node: node)
def setup(self, start=None):
"""Prepare for parsing.
This *must* be called before starting to parse.
The optional argument is an alternative start symbol; it
defaults to the grammar's start symbol.
You can use a Parser instance to parse any number of programs;
each time you call setup() the parser is reset to an initial
state determined by the (implicit or explicit) start symbol.
"""
if start is None:
start = self.grammar.start
# Each stack entry is a tuple: (dfa, state, node).
# A node is a tuple: (type, value, context, children),
# where children is a list of nodes or None, and context may be None.
newnode = (start, None, None, [])
stackentry = (self.grammar.dfas[start], 0, newnode)
self.stack = [stackentry]
self.rootnode = None
self.used_names = set() # Aliased to self.rootnode.used_names in pop()
def addtoken(self, type, value, context):
"""Add a token; return True iff this is the end of the program."""
# Map from token to label
ilabel = self.classify(type, value, context)
# Loop until the token is shifted; may raise exceptions
while True:
dfa, state, node = self.stack[-1]
states, first = dfa
arcs = states[state]
# Look for a state with this label
for i, newstate in arcs:
t, v = self.grammar.labels[i]
if ilabel == i:
# Look it up in the list of labels
assert t < 256
# Shift a token; we're done with it
self.shift(type, value, newstate, context)
# Pop while we are in an accept-only state
state = newstate
while states[state] == [(0, state)]:
self.pop()
if not self.stack:
# Done parsing!
return True
dfa, state, node = self.stack[-1]
states, first = dfa
# Done with this token
return False
elif t >= 256:
# See if it's a symbol and if we're in its first set
itsdfa = self.grammar.dfas[t]
itsstates, itsfirst = itsdfa
if ilabel in itsfirst:
# Push a symbol
self.push(t, self.grammar.dfas[t], newstate, context)
break # To continue the outer while loop
else:
if (0, state) in arcs:
# An accepting state, pop it and try something else
self.pop()
if not self.stack:
# Done parsing, but another token is input
raise ParseError("too much input",
type, value, context)
else:
# No success finding a transition
raise ParseError("bad input", type, value, context)
def classify(self, type, value, context):
"""Turn a token into a label. (Internal)"""
if type == token.NAME:
# Keep a listing of all used names
self.used_names.add(value)
# Check for reserved words
ilabel = self.grammar.keywords.get(value)
if ilabel is not None:
return ilabel
ilabel = self.grammar.tokens.get(type)
if ilabel is None:
raise ParseError("bad token", type, value, context)
return ilabel
def shift(self, type, value, newstate, context):
"""Shift a token. (Internal)"""
dfa, state, node = self.stack[-1]
newnode = (type, value, context, None)
newnode = self.convert(self.grammar, newnode)
if newnode is not None:
node[-1].append(newnode)
self.stack[-1] = (dfa, newstate, node)
def push(self, type, newdfa, newstate, context):
"""Push a nonterminal. (Internal)"""
dfa, state, node = self.stack[-1]
newnode = (type, None, context, [])
self.stack[-1] = (dfa, newstate, node)
self.stack.append((newdfa, 0, newnode))
def pop(self):
"""Pop a nonterminal. (Internal)"""
popdfa, popstate, popnode = self.stack.pop()
newnode = self.convert(self.grammar, popnode)
if newnode is not None:
if self.stack:
dfa, state, node = self.stack[-1]
node[-1].append(newnode)
else:
self.rootnode = newnode
self.rootnode.used_names = self.used_names
PK �C[�����% �% conv.pynu �[��� # Copyright 2004-2005 Elemental Security, Inc. All Rights Reserved.
# Licensed to PSF under a Contributor Agreement.
"""Convert graminit.[ch] spit out by pgen to Python code.
Pgen is the Python parser generator. It is useful to quickly create a
parser from a grammar file in Python's grammar notation. But I don't
want my parsers to be written in C (yet), so I'm translating the
parsing tables to Python data structures and writing a Python parse
engine.
Note that the token numbers are constants determined by the standard
Python tokenizer. The standard token module defines these numbers and
their names (the names are not used much). The token numbers are
hardcoded into the Python tokenizer and into pgen. A Python
implementation of the Python tokenizer is also available, in the
standard tokenize module.
On the other hand, symbol numbers (representing the grammar's
non-terminals) are assigned by pgen based on the actual grammar
input.
Note: this module is pretty much obsolete; the pgen module generates
equivalent grammar tables directly from the Grammar.txt input file
without having to invoke the Python pgen C program.
"""
# Python imports
import re
# Local imports
from pgen2 import grammar, token
class Converter(grammar.Grammar):
"""Grammar subclass that reads classic pgen output files.
The run() method reads the tables as produced by the pgen parser
generator, typically contained in two C files, graminit.h and
graminit.c. The other methods are for internal use only.
See the base class for more documentation.
"""
def run(self, graminit_h, graminit_c):
"""Load the grammar tables from the text files written by pgen."""
self.parse_graminit_h(graminit_h)
self.parse_graminit_c(graminit_c)
self.finish_off()
def parse_graminit_h(self, filename):
"""Parse the .h file written by pgen. (Internal)
This file is a sequence of #define statements defining the
nonterminals of the grammar as numbers. We build two tables
mapping the numbers to names and back.
"""
try:
f = open(filename)
except OSError as err:
print("Can't open %s: %s" % (filename, err))
return False
self.symbol2number = {}
self.number2symbol = {}
lineno = 0
for line in f:
lineno += 1
mo = re.match(r"^#define\s+(\w+)\s+(\d+)$", line)
if not mo and line.strip():
print("%s(%s): can't parse %s" % (filename, lineno,
line.strip()))
else:
symbol, number = mo.groups()
number = int(number)
assert symbol not in self.symbol2number
assert number not in self.number2symbol
self.symbol2number[symbol] = number
self.number2symbol[number] = symbol
return True
def parse_graminit_c(self, filename):
"""Parse the .c file written by pgen. (Internal)
The file looks as follows. The first two lines are always this:
#include "pgenheaders.h"
#include "grammar.h"
After that come four blocks:
1) one or more state definitions
2) a table defining dfas
3) a table defining labels
4) a struct defining the grammar
A state definition has the following form:
- one or more arc arrays, each of the form:
static arc arcs_<n>_<m>[<k>] = {
{<i>, <j>},
...
};
- followed by a state array, of the form:
static state states_<s>[<t>] = {
{<k>, arcs_<n>_<m>},
...
};
"""
try:
f = open(filename)
except OSError as err:
print("Can't open %s: %s" % (filename, err))
return False
# The code below essentially uses f's iterator-ness!
lineno = 0
# Expect the two #include lines
lineno, line = lineno+1, next(f)
assert line == '#include "pgenheaders.h"\n', (lineno, line)
lineno, line = lineno+1, next(f)
assert line == '#include "grammar.h"\n', (lineno, line)
# Parse the state definitions
lineno, line = lineno+1, next(f)
allarcs = {}
states = []
while line.startswith("static arc "):
while line.startswith("static arc "):
mo = re.match(r"static arc arcs_(\d+)_(\d+)\[(\d+)\] = {$",
line)
assert mo, (lineno, line)
n, m, k = list(map(int, mo.groups()))
arcs = []
for _ in range(k):
lineno, line = lineno+1, next(f)
mo = re.match(r"\s+{(\d+), (\d+)},$", line)
assert mo, (lineno, line)
i, j = list(map(int, mo.groups()))
arcs.append((i, j))
lineno, line = lineno+1, next(f)
assert line == "};\n", (lineno, line)
allarcs[(n, m)] = arcs
lineno, line = lineno+1, next(f)
mo = re.match(r"static state states_(\d+)\[(\d+)\] = {$", line)
assert mo, (lineno, line)
s, t = list(map(int, mo.groups()))
assert s == len(states), (lineno, line)
state = []
for _ in range(t):
lineno, line = lineno+1, next(f)
mo = re.match(r"\s+{(\d+), arcs_(\d+)_(\d+)},$", line)
assert mo, (lineno, line)
k, n, m = list(map(int, mo.groups()))
arcs = allarcs[n, m]
assert k == len(arcs), (lineno, line)
state.append(arcs)
states.append(state)
lineno, line = lineno+1, next(f)
assert line == "};\n", (lineno, line)
lineno, line = lineno+1, next(f)
self.states = states
# Parse the dfas
dfas = {}
mo = re.match(r"static dfa dfas\[(\d+)\] = {$", line)
assert mo, (lineno, line)
ndfas = int(mo.group(1))
for i in range(ndfas):
lineno, line = lineno+1, next(f)
mo = re.match(r'\s+{(\d+), "(\w+)", (\d+), (\d+), states_(\d+),$',
line)
assert mo, (lineno, line)
symbol = mo.group(2)
number, x, y, z = list(map(int, mo.group(1, 3, 4, 5)))
assert self.symbol2number[symbol] == number, (lineno, line)
assert self.number2symbol[number] == symbol, (lineno, line)
assert x == 0, (lineno, line)
state = states[z]
assert y == len(state), (lineno, line)
lineno, line = lineno+1, next(f)
mo = re.match(r'\s+("(?:\\\d\d\d)*")},$', line)
assert mo, (lineno, line)
first = {}
rawbitset = eval(mo.group(1))
for i, c in enumerate(rawbitset):
byte = ord(c)
for j in range(8):
if byte & (1<<j):
first[i*8 + j] = 1
dfas[number] = (state, first)
lineno, line = lineno+1, next(f)
assert line == "};\n", (lineno, line)
self.dfas = dfas
# Parse the labels
labels = []
lineno, line = lineno+1, next(f)
mo = re.match(r"static label labels\[(\d+)\] = {$", line)
assert mo, (lineno, line)
nlabels = int(mo.group(1))
for i in range(nlabels):
lineno, line = lineno+1, next(f)
mo = re.match(r'\s+{(\d+), (0|"\w+")},$', line)
assert mo, (lineno, line)
x, y = mo.groups()
x = int(x)
if y == "0":
y = None
else:
y = eval(y)
labels.append((x, y))
lineno, line = lineno+1, next(f)
assert line == "};\n", (lineno, line)
self.labels = labels
# Parse the grammar struct
lineno, line = lineno+1, next(f)
assert line == "grammar _PyParser_Grammar = {\n", (lineno, line)
lineno, line = lineno+1, next(f)
mo = re.match(r"\s+(\d+),$", line)
assert mo, (lineno, line)
ndfas = int(mo.group(1))
assert ndfas == len(self.dfas)
lineno, line = lineno+1, next(f)
assert line == "\tdfas,\n", (lineno, line)
lineno, line = lineno+1, next(f)
mo = re.match(r"\s+{(\d+), labels},$", line)
assert mo, (lineno, line)
nlabels = int(mo.group(1))
assert nlabels == len(self.labels), (lineno, line)
lineno, line = lineno+1, next(f)
mo = re.match(r"\s+(\d+)$", line)
assert mo, (lineno, line)
start = int(mo.group(1))
assert start in self.number2symbol, (lineno, line)
self.start = start
lineno, line = lineno+1, next(f)
assert line == "};\n", (lineno, line)
try:
lineno, line = lineno+1, next(f)
except StopIteration:
pass
else:
assert 0, (lineno, line)
def finish_off(self):
"""Create additional useful structures. (Internal)."""
self.keywords = {} # map from keyword strings to arc labels
self.tokens = {} # map from numeric token values to arc labels
for ilabel, (type, value) in enumerate(self.labels):
if type == token.NAME and value is not None:
self.keywords[value] = ilabel
elif value is None:
self.tokens[type] = ilabel
PK �C[��S�< < &