VimPlug/parso
1
0
Fork 0
mirror of https://github.com/davidhalter/parso.git synced 2026-02-25 11:07:38 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Separate generating dfas from parsing

Browse Source
This commit is contained in:
Dave Halter
2018-06-13 20:46:36 +02:00
parent 6e5a520e7b
commit fc5560874b
1 changed files with 16 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
parso/pgen2/pgen.py
View File

@@ -161,8 +161,6 @@ class _GrammarParser():
self._gettoken() # Initialize lookahead self._gettoken() # Initialize lookahead
def parse(self): def parse(self):
dfas = {}
start_symbol = None
# grammar: (NEWLINE | rule)* ENDMARKER # grammar: (NEWLINE | rule)* ENDMARKER
while self.type != token.ENDMARKER: while self.type != token.ENDMARKER:
while self.type == token.NEWLINE: while self.type == token.NEWLINE:
@@ -175,19 +173,7 @@ class _GrammarParser():
a, z = self._parse_rhs() a, z = self._parse_rhs()
self._expect(token.NEWLINE) self._expect(token.NEWLINE)
#_dump_nfa(a, z) yield a, z
dfa = _make_dfa(a, z)
#_dump_dfa(self._current_rule_name, dfa)
# oldlen = len(dfa)
_simplify_dfa(dfa)
# newlen = len(dfa)
dfas[self._current_rule_name] = dfa
#print(self._current_rule_name, oldlen, newlen)
if start_symbol is None:
start_symbol = self._current_rule_name
return dfas, start_symbol
def _parse_rhs(self): def _parse_rhs(self):
# rhs: items ('|' items)* # rhs: items ('|' items)*
@@ -432,6 +418,20 @@ def generate_grammar(bnf_grammar, token_namespace):
It's not EBNF according to ISO/IEC 14977. It's a dialect Python uses in its It's not EBNF according to ISO/IEC 14977. It's a dialect Python uses in its
own parser. own parser.
""" """
dfas, start_symbol = _GrammarParser(bnf_grammar).parse() dfas = {}
start_symbol = None
for a, z in _GrammarParser(bnf_grammar).parse():
#_dump_nfa(a, z)
dfa = _make_dfa(a, z)
#_dump_dfa(self._current_rule_name, dfa)
# oldlen = len(dfa)
_simplify_dfa(dfa)
# newlen = len(dfa)
dfas[a.from_rule] = dfa
#print(self._current_rule_name, oldlen, newlen)
if start_symbol is None:
start_symbol = a.from_rule
p = ParserGenerator(dfas, token_namespace) p = ParserGenerator(dfas, token_namespace)
return p.make_grammar(Grammar(bnf_grammar, start_symbol)) return p.make_grammar(Grammar(bnf_grammar, start_symbol))