diff options
| author | LaurenceWarne <17688577+LaurenceWarne@users.noreply.github.com> | 2022-08-14 23:40:46 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2022-08-15 00:40:46 +0200 |
| commit | 78efbf0bd992871e560b3997645f5b2fe29d0f3c (patch) | |
| tree | 64ec7305856254820d96bb2258dc4ebea0a3964a /pygments | |
| parent | 581f7ee2567d756c0fbfce5e99ba10d461d08acb (diff) | |
| download | pygments-git-78efbf0bd992871e560b3997645f5b2fe29d0f3c.tar.gz | |
Disable highlighting of some escape codes for python bytes literals (#2204)
Disable highlighting of unicode escape codes in python bytes literals,
as described in
https://docs.python.org/3/reference/lexical_analysis.html#string-and-bytes-literals.
So escape codes of the form "\N{name}", "\uxxxx" and "\Uxxxxxxxx" will
no longer be highlighted within bytes literals. Add tests for escape
code highlighting in string and bytes literals.
Diffstat (limited to 'pygments')
| -rw-r--r-- | pygments/lexers/python.py | 27 |
1 files changed, 20 insertions, 7 deletions
diff --git a/pygments/lexers/python.py b/pygments/lexers/python.py index 83c5ef4e..0a7e8f83 100644 --- a/pygments/lexers/python.py +++ b/pygments/lexers/python.py @@ -142,7 +142,7 @@ class PythonLexer(RegexLexer): combined('fstringescape', 'dqf')), ("([fF])(')", bygroups(String.Affix, String.Single), combined('fstringescape', 'sqf')), - # raw strings + # raw bytes and strings ('(?i)(rb|br|r)(""")', bygroups(String.Affix, String.Double), 'tdqs'), ("(?i)(rb|br|r)(''')", @@ -152,14 +152,24 @@ class PythonLexer(RegexLexer): ("(?i)(rb|br|r)(')", bygroups(String.Affix, String.Single), 'sqs'), # non-raw strings - ('([uUbB]?)(""")', bygroups(String.Affix, String.Double), + ('([uU]?)(""")', bygroups(String.Affix, String.Double), combined('stringescape', 'tdqs')), - ("([uUbB]?)(''')", bygroups(String.Affix, String.Single), + ("([uU]?)(''')", bygroups(String.Affix, String.Single), combined('stringescape', 'tsqs')), - ('([uUbB]?)(")', bygroups(String.Affix, String.Double), + ('([uU]?)(")', bygroups(String.Affix, String.Double), combined('stringescape', 'dqs')), - ("([uUbB]?)(')", bygroups(String.Affix, String.Single), + ("([uU]?)(')", bygroups(String.Affix, String.Single), combined('stringescape', 'sqs')), + # non-raw bytes + ('([bB])(""")', bygroups(String.Affix, String.Double), + combined('bytesescape', 'tdqs')), + ("([bB])(''')", bygroups(String.Affix, String.Single), + combined('bytesescape', 'tsqs')), + ('([bB])(")', bygroups(String.Affix, String.Double), + combined('bytesescape', 'dqs')), + ("([bB])(')", bygroups(String.Affix, String.Single), + combined('bytesescape', 'sqs')), + (r'[^\S\n]+', Text), include('numbers'), (r'!=|==|<<|>>|:=|[-~+/*%=<>&^|.]', Operator), @@ -343,9 +353,12 @@ class PythonLexer(RegexLexer): include('rfstringescape'), include('stringescape'), ], + 'bytesescape': [ + (r'\\([\\abfnrtv"\']|\n|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + ], 'stringescape': [ - (r'\\([\\abfnrtv"\']|\n|N\{.*?\}|u[a-fA-F0-9]{4}|' - r'U[a-fA-F0-9]{8}|x[a-fA-F0-9]{2}|[0-7]{1,3})', String.Escape) + (r'\\(N\{.*?\}|u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8})', String.Escape), + include('bytesescape') ], 'fstrings-single': fstring_rules(String.Single), 'fstrings-double': fstring_rules(String.Double), |