VimPlug/parso
1
0
Fork 0
mirror of https://github.com/davidhalter/parso.git synced 2025-12-07 13:24:39 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Document pgen grammars a bit better

Browse Source
This commit is contained in:
Dave Halter
2018-06-13 00:27:51 +02:00
parent bae56e72e1
commit f8558df27a
1 changed files with 19 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
parso/pgen2/pgen.py
View File

@@ -5,6 +5,19 @@
# Copyright David Halter and Contributors # Copyright David Halter and Contributors
# Modifications are dual-licensed: MIT and PSF. # Modifications are dual-licensed: MIT and PSF.
"""
Specifying grammars in pgen is possible with this grammar::
grammar: (NEWLINE | rule)* ENDMARKER
rule: NAME ':' rhs NEWLINE
rhs: items ('|' items)*
items: item+
item: '[' rhs ']' | atom ['+' | '*']
atom: '(' rhs ')' | NAME | STRING
This grammar is self-referencing.
"""
from parso.pgen2.grammar import Grammar from parso.pgen2.grammar import Grammar
from parso.python import token from parso.python import token
from parso.python import tokenize from parso.python import tokenize
@@ -155,11 +168,11 @@ class _GrammarParser():
def _parse(self): def _parse(self):
dfas = {} dfas = {}
start_symbol = None start_symbol = None
# MSTART: (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:
self._gettoken() self._gettoken()
# RULE: NAME ':' RHS NEWLINE # rule: NAME ':' rhs NEWLINE
name = self._expect(token.NAME) name = self._expect(token.NAME)
self._expect(token.COLON) self._expect(token.COLON)
a, z = self._parse_rhs() a, z = self._parse_rhs()
@@ -260,7 +273,7 @@ class _GrammarParser():
break break
def _parse_rhs(self): def _parse_rhs(self):
# RHS: ALT ('|' ALT)* # rhs: items ('|' items)*
a, z = self._parse_alt() a, z = self._parse_alt()
if self.value != "|": if self.value != "|":
return a, z return a, z
@@ -277,7 +290,7 @@ class _GrammarParser():
return aa, zz return aa, zz
def _parse_alt(self): def _parse_alt(self):
# ALT: ITEM+ # items: item+
a, b = self._parse_item() a, b = self._parse_item()
while (self.value in ("(", "[") or while (self.value in ("(", "[") or
self.type in (token.NAME, token.STRING)): self.type in (token.NAME, token.STRING)):
@@ -287,7 +300,7 @@ class _GrammarParser():
return a, b return a, b
def _parse_item(self): def _parse_item(self):
# ITEM: '[' RHS ']' | ATOM ['+' | '*'] # item: '[' rhs ']' | atom ['+' | '*']
if self.value == "[": if self.value == "[":
self._gettoken() self._gettoken()
a, z = self._parse_rhs() a, z = self._parse_rhs()
@@ -307,7 +320,7 @@ class _GrammarParser():
return a, a return a, a
def _parse_atom(self): def _parse_atom(self):
# ATOM: '(' RHS ')' | NAME | STRING # atom: '(' rhs ')' | NAME | STRING
if self.value == "(": if self.value == "(":
self._gettoken() self._gettoken()
a, z = self._parse_rhs() a, z = self._parse_rhs()