Mercurial > hgrepos > Python > libs > pygments-lexer-pseudocode2
diff pygments_lexer_pseudocode2/uniprops.py @ 105:cec52d83869a
Handle much more characters from the Unicode codeset in expressions.
While there: FIX: Add forgotten Punctuation characters `?' and `@'.
While there: Allow the escaping of single and double quotes that normally
start a string (e.g. for expressions like f' is the first derivation of f).
| author | Franz Glasner <fzglas.hg@dom66.de> |
|---|---|
| date | Mon, 04 May 2026 16:30:36 +0200 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pygments_lexer_pseudocode2/uniprops.py Mon May 04 16:30:36 2026 +0200 @@ -0,0 +1,48 @@ +# -*- coding: utf-8 -*- +# :- +# SPDX-FileCopyrightText: © 2026 Franz Glasner +# SPDX-License-Identifier: MIT +# :- +r"""A somewhat changed variant of :mod:`pygments.unistring`. + +We handle ASCII characters mostly ourself. + +""" + +__all__ = [] + + +import pygments.unistring + + +def _remove_ascii(s): + """Remove the characters in the ASCII range from `s` and return the + adjusted string. + + Assumes that in `s` the ASCII chars are sorted before the Unicode + codepoints as in :mod:`pygments.unistring`. + + """ + idx = 0 + while ord(s[idx]) < 0x80: + idx += 1 + if idx > 0: + return s[idx:] + else: + # nothing changed + return s + + +Pc = _remove_ascii(pygments.unistring.Pc) +Pd = _remove_ascii(pygments.unistring.Pd) +Pe = _remove_ascii(pygments.unistring.Pe) +Ps = _remove_ascii(pygments.unistring.Ps) +Pi = _remove_ascii(pygments.unistring.Pi) +Pf = _remove_ascii(pygments.unistring.Pf) +Po = _remove_ascii(pygments.unistring.Po) +Sc = _remove_ascii(pygments.unistring.Sc) +So = _remove_ascii(pygments.unistring.So) +Sm = _remove_ascii(pygments.unistring.Sm) +Zl = _remove_ascii(pygments.unistring.Zl) +Zp = _remove_ascii(pygments.unistring.Zp) +Zs = _remove_ascii(pygments.unistring.Zs)