forked from python/cpython
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
bpo-40939: Use the new grammar for the grammar specification document…
…ation (pythonGH-19969) (We censor the heck out of actions and some other stuff using a custom "highlighter".) Co-authored-by: Guido van Rossum <guido@python.org>
- Loading branch information
1 parent
3c3ae53
commit 718d817
Showing
4 changed files
with
91 additions
and
210 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,7 +1,19 @@ | ||
Full Grammar specification | ||
========================== | ||
|
||
This is the full Python grammar, as it is read by the parser generator and used | ||
to parse Python source files: | ||
This is the full Python grammar, derived directly from the grammar | ||
used to generate the CPython parser (see :source:`Grammar/python.gram`). | ||
The version here omits details related to code generation and | ||
error recovery. | ||
|
||
.. literalinclude:: ../../Grammar/Grammar | ||
The notation is a mixture of `EBNF | ||
<https://en.wikipedia.org/wiki/Extended_Backus%E2%80%93Naur_form>`_ | ||
and `PEG <https://en.wikipedia.org/wiki/Parsing_expression_grammar>`_. | ||
In particular, ``&`` followed by a symbol, token or parenthesized | ||
group indicates a positive lookahead (i.e., is required to match but | ||
not consumed), while ``!`` indicates a negative lookahead (i.e., is | ||
required _not_ to match). We use the ``|`` separator to mean PEG's | ||
"ordered choice" (written as ``/`` in traditional PEG grammars). | ||
|
||
.. literalinclude:: ../../Grammar/python.gram | ||
:language: peg |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,75 @@ | ||
from pygments.lexer import RegexLexer, bygroups, include | ||
from pygments.token import Comment, Generic, Keyword, Name, Operator, Punctuation, Text | ||
|
||
from sphinx.highlighting import lexers | ||
|
||
|
||
class PEGLexer(RegexLexer): | ||
"""Pygments Lexer for PEG grammar (.gram) files | ||
This lexer strips the following elements from the grammar: | ||
- Meta-tags | ||
- Variable assignments | ||
- Actions | ||
- Lookaheads | ||
- Rule types | ||
- Rule options | ||
- Rules named `invalid_*` or `incorrect_*` | ||
""" | ||
|
||
name = "PEG" | ||
aliases = ["peg"] | ||
filenames = ["*.gram"] | ||
_name = r"([^\W\d]\w*)" | ||
_text_ws = r"(\s*)" | ||
|
||
tokens = { | ||
"ws": [(r"\n", Text), (r"\s+", Text), (r"#.*$", Comment.Singleline),], | ||
"lookaheads": [ | ||
(r"(?<=\|\s)(&\w+\s?)", bygroups(None)), | ||
(r"(?<=\|\s)(&'.+'\s?)", bygroups(None)), | ||
(r'(?<=\|\s)(&".+"\s?)', bygroups(None)), | ||
(r"(?<=\|\s)(&\(.+\)\s?)", bygroups(None)), | ||
], | ||
"metas": [ | ||
(r"(@\w+ '''(.|\n)+?''')", bygroups(None)), | ||
(r"^(@.*)$", bygroups(None)), | ||
], | ||
"actions": [(r"{(.|\n)+?}", bygroups(None)),], | ||
"strings": [ | ||
(r"'\w+?'", Keyword), | ||
(r'"\w+?"', Keyword), | ||
(r"'\W+?'", Text), | ||
(r'"\W+?"', Text), | ||
], | ||
"variables": [(_name + _text_ws + "(=)", bygroups(None, None, None),),], | ||
"invalids": [ | ||
(r"^(\s+\|\s+invalid_\w+\s*\n)", bygroups(None)), | ||
(r"^(\s+\|\s+incorrect_\w+\s*\n)", bygroups(None)), | ||
(r"^(#.*invalid syntax.*(?:.|\n)*)", bygroups(None),), | ||
], | ||
"root": [ | ||
include("invalids"), | ||
include("ws"), | ||
include("lookaheads"), | ||
include("metas"), | ||
include("actions"), | ||
include("strings"), | ||
include("variables"), | ||
(r"\b(?!(NULL|EXTRA))([A-Z_]+)\b\s*(?!\()", Text,), | ||
( | ||
r"^\s*" + _name + "\s*" + "(\[.*\])?" + "\s*" + "(\(.+\))?" + "\s*(:)", | ||
bygroups(Name.Function, None, None, Punctuation), | ||
), | ||
(_name, Name.Function), | ||
(r"[\||\.|\+|\*|\?]", Operator), | ||
(r"{|}|\(|\)|\[|\]", Punctuation), | ||
(r".", Text), | ||
], | ||
} | ||
|
||
|
||
def setup(app): | ||
lexers["peg"] = PEGLexer() | ||
return {"version": "1.0", "parallel_read_safe": True} |
This file was deleted.
Oops, something went wrong.