summaryrefslogtreecommitdiffstats
path: root/Doc/tools/extensions
diff options
context:
space:
mode:
authorPablo Galindo <Pablogsal@gmail.com>2020-07-27 18:20:36 (GMT)
committerGitHub <noreply@github.com>2020-07-27 18:20:36 (GMT)
commit72cabb2aa636272e608285f5a6ba83b62be9be4e (patch)
treec43c2815b9aa9389413934136c7be9ac514c6081 /Doc/tools/extensions
parent67987acd5dc9776f55f4e139e2b3d9e7a6434d9f (diff)
downloadcpython-72cabb2aa636272e608285f5a6ba83b62be9be4e.zip
cpython-72cabb2aa636272e608285f5a6ba83b62be9be4e.tar.gz
cpython-72cabb2aa636272e608285f5a6ba83b62be9be4e.tar.bz2
bpo-40939: Use the new grammar for the grammar specification documentation (GH-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>
Diffstat (limited to 'Doc/tools/extensions')
-rw-r--r--Doc/tools/extensions/peg_highlight.py75
1 files changed, 75 insertions, 0 deletions
diff --git a/Doc/tools/extensions/peg_highlight.py b/Doc/tools/extensions/peg_highlight.py
new file mode 100644
index 0000000..f02515d
--- /dev/null
+++ b/Doc/tools/extensions/peg_highlight.py
@@ -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}