def regexes(self, ast, *args):
pattern = ''.join(ast)
try:
re.compile(pattern, RE_FLAGS)
except (TypeError, re.error) as e:
raise FailedSemantics('regexp error: ' + str(e))
return ast
def regex(self, ast, *args):
pattern = ast
try:
re.compile(pattern, RE_FLAGS)
except (TypeError, re.error) as e:
raise FailedSemantics('regexp error: ' + str(e))
return pattern
def pattern(self, ast, *args):
pattern = ast
try:
re.compile(pattern, RE_FLAGS)
except (TypeError, re.error) as e:
raise FailedSemantics('regexp error: ' + str(e))
return grammars.Pattern(pattern)
def __init__(
self,
whitespace=re.compile('((?!^)(?![\\r\\n])\\s)+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re=None,
eol_comments_re='#[^\\r\\n]*',
ignorecase=None,
left_recursion=False,
parseinfo=True,
keywords=None,
namechars='',
buffer_class=PythonBuffer,
**kwargs
):
if keywords is None:
keywords = KEYWORDS
super(PythonParser, self).__init__(
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
parseinfo=parseinfo,
keywords=keywords,
namechars=namechars,
buffer_class=buffer_class,
**kwargs
)
def main(
filename,
startrule,
trace=False,
whitespace=None,
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
left_recursion=True,
**kwargs):
with open(filename) as f:
text = f.read()
whitespace = whitespace or re.compile('\\s+', RE_FLAGS | re.DOTALL)
parser = SqlParser(parseinfo=False)
ast = parser.parse(
text,
startrule,
filename=filename,
trace=trace,
whitespace=whitespace,
nameguard=nameguard,
ignorecase=ignorecase,
**kwargs)
return ast
def __init__(self,
whitespace=re.compile('[\\t ]+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re=None,
eol_comments_re=None,
ignorecase=None,
left_recursion=False,
parseinfo=True,
keywords=None,
namechars='',
buffer_class=GnomicBuffer,
**kwargs):
if keywords is None:
keywords = KEYWORDS
super(GnomicParser, self).__init__(whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
parseinfo=parseinfo,
keywords=keywords,
namechars=namechars,
buffer_class=buffer_class,
**kwargs)
def __init__(self,
whitespace=re.compile('[\\t\\n\\s]+', RE_FLAGS | re.DOTALL),
nameguard=False,
comments_re='\\/\\*(.|\\s|\\n)*?\\*\\/',
eol_comments_re='\\/\\/.*?$',
ignorecase=None,
left_recursion=False,
parseinfo=True,
keywords=None,
namechars='',
buffer_class=CropBuffer,
**kwargs):
if keywords is None:
keywords = KEYWORDS
super(CropParser, self).__init__(whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
parseinfo=parseinfo,
keywords=keywords,
namechars=namechars,
buffer_class=buffer_class,
**kwargs)
def _scanre(self, pattern, ignorecase=None, offset=0):
ignorecase = ignorecase if ignorecase is not None else self.ignorecase
if isinstance(pattern, RETYPE):
re = pattern
elif pattern in self._re_cache:
re = self._re_cache[pattern]
else:
flags = RE_FLAGS | (regexp.IGNORECASE if ignorecase else 0)
re = regexp.compile(pattern, flags)
self._re_cache[pattern] = re
return re.match(self.text, self.pos + offset)
def parse(self,
text,
rule_name=None,
start=None,
filename=None,
semantics=None,
trace=False,
context=None,
whitespace=None,
left_recursion=None,
comments_re=None,
eol_comments_re=None,
parseinfo=None,
**kwargs):
start = start if start is not None else rule_name
start = start if start is not None else self.rules[0].name
ctx = context or ModelContext(
self.rules,
trace=trace,
keywords=self.keywords,
**kwargs)
if whitespace is None:
whitespace = self.whitespace
if whitespace:
whitespace = re.compile(whitespace)
if left_recursion is None:
left_recursion = self.left_recursion
if parseinfo is None:
parseinfo = self._use_parseinfo
if comments_re is None:
comments_re = self.comments_re
if eol_comments_re is None:
eol_comments_re = self.eol_comments_re
return ctx.parse(
text,
rule_name=start,
filename=filename,
semantics=semantics,
trace=trace,
whitespace=whitespace,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
left_recursion=left_recursion,
parseinfo=parseinfo,
**kwargs
)
def build_whitespace_re(whitespace):
if whitespace is None:
return WHITESPACE_RE
elif isinstance(whitespace, RETYPE):
return whitespace
elif whitespace:
if not isinstance(whitespace, strtype):
# a list or a set?
whitespace = ''.join(c for c in whitespace)
return regexp.compile('[%s]+' % regexp.escape(whitespace),
RE_FLAGS)
else:
return None
def build_whitespace_re(whitespace):
if whitespace is None:
return WHITESPACE_RE
elif isinstance(whitespace, RETYPE):
return whitespace
elif whitespace:
if not isinstance(whitespace, strtype):
# a list or a set?
whitespace = ''.join(c for c in whitespace)
return regexp.compile(
'[%s]+' % regexp.escape(whitespace), RE_FLAGS
)
else:
return None
def __init__(self,
whitespace=re.compile('[\\t ]+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='{\\-.*?\\-}',
eol_comments_re=None,
ignorecase=None,
left_recursion=True,
**kwargs):
super(grammerParser, self).__init__(whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
**kwargs)
def _scanre(self, pattern, ignorecase=None, offset=0):
ignorecase = ignorecase if ignorecase is not None else self.ignorecase
if isinstance(pattern, RETYPE):
re = pattern
elif pattern in self._re_cache:
re = self._re_cache[pattern]
else:
flags = RE_FLAGS | (regexp.IGNORECASE if ignorecase else 0)
re = regexp.compile(
pattern,
flags
)
self._re_cache[pattern] = re
return re.match(self.text, self.pos + offset)
def parse(self,
text,
rule_name=None,
start=None,
filename=None,
semantics=None,
trace=False,
context=None,
whitespace=None,
left_recursion=None,
comments_re=None,
eol_comments_re=None,
parseinfo=None,
**kwargs):
start = start if start is not None else rule_name
start = start if start is not None else self.rules[0].name
ctx = context or ModelContext(
self.rules, trace=trace, keywords=self.keywords, **kwargs)
if whitespace is None:
whitespace = self.whitespace
if whitespace:
whitespace = re.compile(whitespace)
if left_recursion is None:
left_recursion = self.left_recursion
if parseinfo is None:
parseinfo = self._use_parseinfo
if comments_re is None:
comments_re = self.comments_re
if eol_comments_re is None:
eol_comments_re = self.eol_comments_re
return ctx.parse(text,
rule_name=start,
filename=filename,
semantics=semantics,
trace=trace,
whitespace=whitespace,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
left_recursion=left_recursion,
parseinfo=parseinfo,
**kwargs)
def __init__(self,
text,
whitespace=re.compile('\\s+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
namechars='',
**kwargs):
super(SqlBuffer, self).__init__(text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs)
def __init__(self,
whitespace=re.compile('[\\t ]+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='{\\-.*?\\-}',
eol_comments_re=None,
ignorecase=None,
left_recursion=True,
**kwargs):
super(grammerParser, self).__init__(
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
**kwargs
)
def __init__(self,
text,
whitespace=re.compile('[\\t\\n\\s]+', RE_FLAGS | re.DOTALL),
nameguard=False,
comments_re='\\/\\*(.|\\s|\\n)*?\\*\\/',
eol_comments_re='\\/\\/.*?$',
ignorecase=None,
namechars='',
**kwargs):
super(CropBuffer, self).__init__(text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs)
def __init__(self,
text,
whitespace=re.compile('[\\t ]+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re=None,
eol_comments_re=None,
ignorecase=None,
namechars='',
**kwargs):
super(GnomicBuffer, self).__init__(text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs)
def __init__(self,
text,
whitespace=re.compile('((?!^)(?![\\r\\n])\\s)+',
RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re=None,
eol_comments_re='#[^\\r\\n]*',
ignorecase=None,
namechars='',
**kwargs):
super(PythonBuffer, self).__init__(text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs)
def parse(self,
text,
start=None,
filename=None,
semantics=None,
trace=False,
context=None,
whitespace=None,
left_recursion=None,
comments_re=None,
eol_comments_re=None,
**kwargs):
ctx = context or ModelContext(
self.rules,
trace=trace,
keywords=self.keywords,
**kwargs)
if whitespace is None:
whitespace = self.whitespace
if whitespace:
whitespace = re.compile(whitespace)
if left_recursion is None:
left_recursion = self.left_recursion
if comments_re is None:
comments_re = self.comments_re
if eol_comments_re is None:
eol_comments_re = self.eol_comments_re
return ctx.parse(
text,
start or self.rules[0].name,
filename=filename,
semantics=semantics,
trace=trace,
whitespace=whitespace,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
left_recursion=left_recursion,
**kwargs
)
def __init__(self,
whitespace=re.compile('\\s+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
left_recursion=True,
keywords=KEYWORDS,
namechars='',
**kwargs):
super(SqlParser, self).__init__(whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
keywords=keywords,
namechars=namechars,
**kwargs)
def __init__(self,
text,
whitespace=re.compile('\\s+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
namechars='',
**kwargs):
super(SqlBuffer, self).__init__(
text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs
)
def __init__(
self,
text,
whitespace=re.compile('((?!^)(?![\\r\\n])\\s)+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re=None,
eol_comments_re='#[^\\r\\n]*',
ignorecase=None,
namechars='',
**kwargs
):
super(PythonBuffer, self).__init__(
text,
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
namechars=namechars,
**kwargs
)
def __init__(self,
whitespace=re.compile('\\s+', RE_FLAGS | re.DOTALL),
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
left_recursion=True,
keywords=KEYWORDS,
namechars='',
**kwargs):
super(SqlParser, self).__init__(
whitespace=whitespace,
nameguard=nameguard,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
ignorecase=ignorecase,
left_recursion=left_recursion,
keywords=keywords,
namechars=namechars,
**kwargs
)
def parse(self,
text,
start=None,
filename=None,
semantics=None,
trace=False,
context=None,
whitespace=None,
left_recursion=None,
comments_re=None,
eol_comments_re=None,
**kwargs):
ctx = context or ModelContext(
self.rules, trace=trace, keywords=self.keywords, **kwargs)
if whitespace is None:
whitespace = self.whitespace
if whitespace:
whitespace = re.compile(whitespace)
if left_recursion is None:
left_recursion = self.left_recursion
if comments_re is None:
comments_re = self.comments_re
if eol_comments_re is None:
eol_comments_re = self.eol_comments_re
return ctx.parse(text,
start or self.rules[0].name,
filename=filename,
semantics=semantics,
trace=trace,
whitespace=whitespace,
comments_re=comments_re,
eol_comments_re=eol_comments_re,
left_recursion=left_recursion,
**kwargs)
def main(filename,
startrule,
trace=False,
whitespace=None,
nameguard=None,
comments_re='/\\*[\\s\\S]*?\\*/',
eol_comments_re='--.*?$',
ignorecase=True,
left_recursion=True,
**kwargs):
with open(filename) as f:
text = f.read()
whitespace = whitespace or re.compile('\\s+', RE_FLAGS | re.DOTALL)
parser = SqlParser(parseinfo=False)
ast = parser.parse(text,
startrule,
filename=filename,
trace=trace,
whitespace=whitespace,
nameguard=nameguard,
ignorecase=ignorecase,
**kwargs)
return ast
def __postinit__(self, ast):
super(Pattern, self).__postinit__(ast)
if not isinstance(ast, list):
ast = [ast]
self.patterns = ast
re.compile(self.pattern, RE_FLAGS)
def __postinit__(self, ast):
super(Pattern, self).__postinit__(ast)
if not isinstance(ast, list):
ast = [ast]
self.patterns = ast
re.compile(self.pattern, RE_FLAGS)
def __postinit__(self, ast):
re.compile(ast, RE_FLAGS)
super(Pattern, self).__postinit__(ast)
self.pattern = ast
def __postinit__(self, ast):
re.compile(ast, RE_FLAGS)
super(Pattern, self).__postinit__(ast)
self.pattern = ast
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
import os
from bisect import bisect_left
from collections import namedtuple
from grako.util import ustr, strtype, re as regexp, WHITESPACE_RE, RE_FLAGS
from grako.exceptions import ParseError
# TODO: There could be a file buffer using random access
__all__ = ['Buffer']
RETYPE = type(regexp.compile('.'))
PosLine = namedtuple('PosLine', ['pos', 'line'])
LineInfo = namedtuple(
'LineInfo',
['filename', 'line', 'col', 'start', 'end', 'text']
)
class Buffer(object):
def __init__(self,
text,
filename=None,
