Mercurial > hgrepos > Python > libs > pygments-lexer-pseudocode2
changeset 39:a3151d837258
Some basic keywords for programs, algorithms, procedures and functions; also comments (single and multiline) and "remarks"
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Fri, 24 Apr 2026 09:44:34 +0200 |
| parents | 69522d4cafac |
| children | df08226a6984 |
| files | pygments_lexer_pseudocode2/bases.py pygments_lexer_pseudocode2/pseudocode.py tests/test_pseudo.py |
| diffstat | 3 files changed, 63 insertions(+), 4 deletions(-) [+] |
line wrap: on
line diff
--- a/pygments_lexer_pseudocode2/bases.py Wed Apr 22 16:27:35 2026 +0200 +++ b/pygments_lexer_pseudocode2/bases.py Fri Apr 24 09:44:34 2026 +0200 @@ -9,7 +9,7 @@ from pygments.lexer import RegexLexer, combined, bygroups, include -from pygments.token import Number, String +from pygments.token import Number, String, Comment class LexBase(RegexLexer): @@ -117,4 +117,10 @@ 'py-strings-single': py_innerstring_rules(String.Single), 'py-strings-double': py_innerstring_rules(String.Double), # SPDX-SnippetEnd + 'multiline-nested-comment': [ + (r'[^*/]+', Comment.Multiline), + (r'/\*', Comment.Multiline, '#push'), + (r'\*/', Comment.Multiline, '#pop'), + (r'[*/]', Comment.Multiline), + ] }
--- a/pygments_lexer_pseudocode2/pseudocode.py Wed Apr 22 16:27:35 2026 +0200 +++ b/pygments_lexer_pseudocode2/pseudocode.py Fri Apr 24 09:44:34 2026 +0200 @@ -13,8 +13,8 @@ import re -from pygments.lexer import include -from pygments.token import (Keyword, Text, Whitespace) +from pygments.lexer import include, bygroups +from pygments.token import (Comment, Keyword, Text, Whitespace) # # Relative imports do not work with pygments.lexers.load_lexer_from_file() @@ -51,6 +51,19 @@ "FN": "FUNCTION", "CLASS": "CLASS", } + SYMBOLS = { + "REMARK": "▷", # U+25B7: Unicode 1.0 (Arrows) + "Remark": "▷", + "remark": "▷", + "REM": "▷", + "Rem": "▷", + "rem": "▷", + "R": "▷", + "r": "▷", + "BLOCK": "┃", # U+2503: Unicode 1.0 (Bow Drawing) + "Block": "┃", + "block": "┃", + } def op_translate(toktype): @@ -60,9 +73,23 @@ return _op_translate + def op_symbol(toktype): + + def _op_symbol(lexer, match, ctx=None): + kw = match.group() + yield match.start(), toktype, lexer.SYMBOLS.get(kw, kw) + + return _op_symbol + tokens = { "root": [ (r"\n", Whitespace), + (r"/\*", Comment.Multiline, "multiline-nested-comment"), + (r"//.*$", Comment.Single), + (r"(?:\\)(REMARK|Remark|remark|REM|Rem|rem|R|r)\b(.*)$", + bygroups(op_symbol(Comment.Single), Comment.Single)), + (r"(?:\\)(BLOCK|Block|block)\b(.*)$", + bygroups(op_symbol(Text), Text)), (r"\\\n", Text), (r"(?i)\\(" r"(?:prog(?:ram)?)" @@ -92,7 +119,7 @@ "PROG": "PROGRAMM", "PROGRAM": "PROGRAMM", "ALGO": "ALGORITHMUS", - "ALGORITHM": "ALGORITHM", + "ALGORITHM": "ALGORITHMUS", "PROC": "PROZEDUR", "PROCEDURE": "PROZEDUR", "FUNC": "FUNKTION",
--- a/tests/test_pseudo.py Wed Apr 22 16:27:35 2026 +0200 +++ b/tests/test_pseudo.py Fri Apr 24 09:44:34 2026 +0200 @@ -180,6 +180,32 @@ ], pygments.lex("\\FN", self.lexer)) + def test_remark_1(self): + self.assertTokenStreamEqualComplete( + [("Comment.Single", "▷"), + ("Comment.Single", " the remark"), + ("Text.Whitespace", "\n"), + ], + pygments.lex("\\REMARK the remark\n", self.lexer)) + + def test_remark_2(self): + self.assertTokenStreamEqualComplete( + [("Comment.Single", "▷"), + ("Comment.Single", " the remark 1"), + ("Text.Whitespace", "\n"), + ("Comment.Single", "▷"), + ("Comment.Single", " the remark 2"), + ("Text.Whitespace", "\n"), + ("Comment.Single", "▷"), + ("Comment.Single", " the remark 3"), + ("Text.Whitespace", "\n"), + ], + pygments.lex( + """\\REMARK the remark 1 +\\Rem the remark 2 +\\r the remark 3 +""", self.lexer)) + if __name__ == "__main__": unittest.main()