diff --git a/venv/Lib/site-packages/pip/_vendor/pygments/filters/__init__.py b/venv/Lib/site-packages/pip/_vendor/pygments/filters/__init__.py new file mode 100644 index 0000000..97380c9 --- /dev/null +++ b/venv/Lib/site-packages/pip/_vendor/pygments/filters/__init__.py @@ -0,0 +1,940 @@ +""" + pygments.filters + ~~~~~~~~~~~~~~~~ + + Module containing filter lookup functions and default + filters. + + :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS. + :license: BSD, see LICENSE for details. +""" + +import re + +from pip._vendor.pygments.token import String, Comment, Keyword, Name, Error, Whitespace, \ + string_to_tokentype +from pip._vendor.pygments.filter import Filter +from pip._vendor.pygments.util import get_list_opt, get_int_opt, get_bool_opt, \ + get_choice_opt, ClassNotFound, OptionError +from pip._vendor.pygments.plugin import find_plugin_filters + + +def find_filter_class(filtername): + """Lookup a filter by name. Return None if not found.""" + if filtername in FILTERS: + return FILTERS[filtername] + for name, cls in find_plugin_filters(): + if name == filtername: + return cls + return None + + +def get_filter_by_name(filtername, **options): + """Return an instantiated filter. + + Options are passed to the filter initializer if wanted. + Raise a ClassNotFound if not found. + """ + cls = find_filter_class(filtername) + if cls: + return cls(**options) + else: + raise ClassNotFound(f'filter {filtername!r} not found') + + +def get_all_filters(): + """Return a generator of all filter names.""" + yield from FILTERS + for name, _ in find_plugin_filters(): + yield name + + +def _replace_special(ttype, value, regex, specialttype, + replacefunc=lambda x: x): + last = 0 + for match in regex.finditer(value): + start, end = match.start(), match.end() + if start != last: + yield ttype, value[last:start] + yield specialttype, replacefunc(value[start:end]) + last = end + if last != len(value): + yield ttype, value[last:] + + +class CodeTagFilter(Filter): + """Highlight special code tags in comments and docstrings. + + Options accepted: + + `codetags` : list of strings + A list of strings that are flagged as code tags. The default is to + highlight ``XXX``, ``TODO``, ``FIXME``, ``BUG`` and ``NOTE``. + + .. versionchanged:: 2.13 + Now recognizes ``FIXME`` by default. + """ + + def __init__(self, **options): + Filter.__init__(self, **options) + tags = get_list_opt(options, 'codetags', + ['XXX', 'TODO', 'FIXME', 'BUG', 'NOTE']) + self.tag_re = re.compile(r'\b({})\b'.format('|'.join([ + re.escape(tag) for tag in tags if tag + ]))) + + def filter(self, lexer, stream): + regex = self.tag_re + for ttype, value in stream: + if ttype in String.Doc or \ + ttype in Comment and \ + ttype not in Comment.Preproc: + yield from _replace_special(ttype, value, regex, Comment.Special) + else: + yield ttype, value + + +class SymbolFilter(Filter): + """Convert mathematical symbols such as \\ in Isabelle + or \\longrightarrow in LaTeX into Unicode characters. + + This is mostly useful for HTML or console output when you want to + approximate the source rendering you'd see in an IDE. + + Options accepted: + + `lang` : string + The symbol language. Must be one of ``'isabelle'`` or + ``'latex'``. The default is ``'isabelle'``. + """ + + latex_symbols = { + '\\alpha' : '\U000003b1', + '\\beta' : '\U000003b2', + '\\gamma' : '\U000003b3', + '\\delta' : '\U000003b4', + '\\varepsilon' : '\U000003b5', + '\\zeta' : '\U000003b6', + '\\eta' : '\U000003b7', + '\\vartheta' : '\U000003b8', + '\\iota' : '\U000003b9', + '\\kappa' : '\U000003ba', + '\\lambda' : '\U000003bb', + '\\mu' : '\U000003bc', + '\\nu' : '\U000003bd', + '\\xi' : '\U000003be', + '\\pi' : '\U000003c0', + '\\varrho' : '\U000003c1', + '\\sigma' : '\U000003c3', + '\\tau' : '\U000003c4', + '\\upsilon' : '\U000003c5', + '\\varphi' : '\U000003c6', + '\\chi' : '\U000003c7', + '\\psi' : '\U000003c8', + '\\omega' : '\U000003c9', + '\\Gamma' : '\U00000393', + '\\Delta' : '\U00000394', + '\\Theta' : '\U00000398', + '\\Lambda' : '\U0000039b', + '\\Xi' : '\U0000039e', + '\\Pi' : '\U000003a0', + '\\Sigma' : '\U000003a3', + '\\Upsilon' : '\U000003a5', + '\\Phi' : '\U000003a6', + '\\Psi' : '\U000003a8', + '\\Omega' : '\U000003a9', + '\\leftarrow' : '\U00002190', + '\\longleftarrow' : '\U000027f5', + '\\rightarrow' : '\U00002192', + '\\longrightarrow' : '\U000027f6', + '\\Leftarrow' : '\U000021d0', + '\\Longleftarrow' : '\U000027f8', + '\\Rightarrow' : '\U000021d2', + '\\Longrightarrow' : '\U000027f9', + '\\leftrightarrow' : '\U00002194', + '\\longleftrightarrow' : '\U000027f7', + '\\Leftrightarrow' : '\U000021d4', + '\\Longleftrightarrow' : '\U000027fa', + '\\mapsto' : '\U000021a6', + '\\longmapsto' : '\U000027fc', + '\\relbar' : '\U00002500', + '\\Relbar' : '\U00002550', + '\\hookleftarrow' : '\U000021a9', + '\\hookrightarrow' : '\U000021aa', + '\\leftharpoondown' : '\U000021bd', + '\\rightharpoondown' : '\U000021c1', + '\\leftharpoonup' : '\U000021bc', + '\\rightharpoonup' : '\U000021c0', + '\\rightleftharpoons' : '\U000021cc', + '\\leadsto' : '\U0000219d', + '\\downharpoonleft' : '\U000021c3', + '\\downharpoonright' : '\U000021c2', + '\\upharpoonleft' : '\U000021bf', + '\\upharpoonright' : '\U000021be', + '\\restriction' : '\U000021be', + '\\uparrow' : '\U00002191', + '\\Uparrow' : '\U000021d1', + '\\downarrow' : '\U00002193', + '\\Downarrow' : '\U000021d3', + '\\updownarrow' : '\U00002195', + '\\Updownarrow' : '\U000021d5', + '\\langle' : '\U000027e8', + '\\rangle' : '\U000027e9', + '\\lceil' : '\U00002308', + '\\rceil' : '\U00002309', + '\\lfloor' : '\U0000230a', + '\\rfloor' : '\U0000230b', + '\\flqq' : '\U000000ab', + '\\frqq' : '\U000000bb', + '\\bot' : '\U000022a5', + '\\top' : '\U000022a4', + '\\wedge' : '\U00002227', + '\\bigwedge' : '\U000022c0', + '\\vee' : '\U00002228', + '\\bigvee' : '\U000022c1', + '\\forall' : '\U00002200', + '\\exists' : '\U00002203', + '\\nexists' : '\U00002204', + '\\neg' : '\U000000ac', + '\\Box' : '\U000025a1', + '\\Diamond' : '\U000025c7', + '\\vdash' : '\U000022a2', + '\\models' : '\U000022a8', + '\\dashv' : '\U000022a3', + '\\surd' : '\U0000221a', + '\\le' : '\U00002264', + '\\ge' : '\U00002265', + '\\ll' : '\U0000226a', + '\\gg' : '\U0000226b', + '\\lesssim' : '\U00002272', + '\\gtrsim' : '\U00002273', + '\\lessapprox' : '\U00002a85', + '\\gtrapprox' : '\U00002a86', + '\\in' : '\U00002208', + '\\notin' : '\U00002209', + '\\subset' : '\U00002282', + '\\supset' : '\U00002283', + '\\subseteq' : '\U00002286', + '\\supseteq' : '\U00002287', + '\\sqsubset' : '\U0000228f', + '\\sqsupset' : '\U00002290', + '\\sqsubseteq' : '\U00002291', + '\\sqsupseteq' : '\U00002292', + '\\cap' : '\U00002229', + '\\bigcap' : '\U000022c2', + '\\cup' : '\U0000222a', + '\\bigcup' : '\U000022c3', + '\\sqcup' : '\U00002294', + '\\bigsqcup' : '\U00002a06', + '\\sqcap' : '\U00002293', + '\\Bigsqcap' : '\U00002a05', + '\\setminus' : '\U00002216', + '\\propto' : '\U0000221d', + '\\uplus' : '\U0000228e', + '\\bigplus' : '\U00002a04', + '\\sim' : '\U0000223c', + '\\doteq' : '\U00002250', + '\\simeq' : '\U00002243', + '\\approx' : '\U00002248', + '\\asymp' : '\U0000224d', + '\\cong' : '\U00002245', + '\\equiv' : '\U00002261', + '\\Join' : '\U000022c8', + '\\bowtie' : '\U00002a1d', + '\\prec' : '\U0000227a', + '\\succ' : '\U0000227b', + '\\preceq' : '\U0000227c', + '\\succeq' : '\U0000227d', + '\\parallel' : '\U00002225', + '\\mid' : '\U000000a6', + '\\pm' : '\U000000b1', + '\\mp' : '\U00002213', + '\\times' : '\U000000d7', + '\\div' : '\U000000f7', + '\\cdot' : '\U000022c5', + '\\star' : '\U000022c6', + '\\circ' : '\U00002218', + '\\dagger' : '\U00002020', + '\\ddagger' : '\U00002021', + '\\lhd' : '\U000022b2', + '\\rhd' : '\U000022b3', + '\\unlhd' : '\U000022b4', + '\\unrhd' : '\U000022b5', + '\\triangleleft' : '\U000025c3', + '\\triangleright' : '\U000025b9', + '\\triangle' : '\U000025b3', + '\\triangleq' : '\U0000225c', + '\\oplus' : '\U00002295', + '\\bigoplus' : '\U00002a01', + '\\otimes' : '\U00002297', + '\\bigotimes' : '\U00002a02', + '\\odot' : '\U00002299', + '\\bigodot' : '\U00002a00', + '\\ominus' : '\U00002296', + '\\oslash' : '\U00002298', + '\\dots' : '\U00002026', + '\\cdots' : '\U000022ef', + '\\sum' : '\U00002211', + '\\prod' : '\U0000220f', + '\\coprod' : '\U00002210', + '\\infty' : '\U0000221e', + '\\int' : '\U0000222b', + '\\oint' : '\U0000222e', + '\\clubsuit' : '\U00002663', + '\\diamondsuit' : '\U00002662', + '\\heartsuit' : '\U00002661', + '\\spadesuit' : '\U00002660', + '\\aleph' : '\U00002135', + '\\emptyset' : '\U00002205', + '\\nabla' : '\U00002207', + '\\partial' : '\U00002202', + '\\flat' : '\U0000266d', + '\\natural' : '\U0000266e', + '\\sharp' : '\U0000266f', + '\\angle' : '\U00002220', + '\\copyright' : '\U000000a9', + '\\textregistered' : '\U000000ae', + '\\textonequarter' : '\U000000bc', + '\\textonehalf' : '\U000000bd', + '\\textthreequarters' : '\U000000be', + '\\textordfeminine' : '\U000000aa', + '\\textordmasculine' : '\U000000ba', + '\\euro' : '\U000020ac', + '\\pounds' : '\U000000a3', + '\\yen' : '\U000000a5', + '\\textcent' : '\U000000a2', + '\\textcurrency' : '\U000000a4', + '\\textdegree' : '\U000000b0', + } + + isabelle_symbols = { + '\\' : '\U0001d7ec', + '\\' : '\U0001d7ed', + '\\' : '\U0001d7ee', + '\\' : '\U0001d7ef', + '\\' : '\U0001d7f0', + '\\' : '\U0001d7f1', + '\\' : '\U0001d7f2', + '\\' : '\U0001d7f3', + '\\' : '\U0001d7f4', + '\\' : '\U0001d7f5', + '\\' : '\U0001d49c', + '\\' : '\U0000212c', + '\\' : '\U0001d49e', + '\\' : '\U0001d49f', + '\\' : '\U00002130', + '\\' : '\U00002131', + '\\' : '\U0001d4a2', + '\\' : '\U0000210b', + '\\' : '\U00002110', + '\\' : '\U0001d4a5', + '\\' : '\U0001d4a6', + '\\' : '\U00002112', + '\\' : '\U00002133', + '\\' : '\U0001d4a9', + '\\' : '\U0001d4aa', + '\\

' : '\U0001d5c9', + '\\' : '\U0001d5ca', + '\\' : '\U0001d5cb', + '\\' : '\U0001d5cc', + '\\' : '\U0001d5cd', + '\\' : '\U0001d5ce', + '\\' : '\U0001d5cf', + '\\' : '\U0001d5d0', + '\\' : '\U0001d5d1', + '\\' : '\U0001d5d2', + '\\' : '\U0001d5d3', + '\\' : '\U0001d504', + '\\' : '\U0001d505', + '\\' : '\U0000212d', + '\\

' : '\U0001d507', + '\\' : '\U0001d508', + '\\' : '\U0001d509', + '\\' : '\U0001d50a', + '\\' : '\U0000210c', + '\\' : '\U00002111', + '\\' : '\U0001d50d', + '\\' : '\U0001d50e', + '\\' : '\U0001d50f', + '\\' : '\U0001d510', + '\\' : '\U0001d511', + '\\' : '\U0001d512', + '\\' : '\U0001d513', + '\\' : '\U0001d514', + '\\' : '\U0000211c', + '\\' : '\U0001d516', + '\\' : '\U0001d517', + '\\' : '\U0001d518', + '\\' : '\U0001d519', + '\\' : '\U0001d51a', + '\\' : '\U0001d51b', + '\\' : '\U0001d51c', + '\\' : '\U00002128', + '\\' : '\U0001d51e', + '\\' : '\U0001d51f', + '\\' : '\U0001d520', + '\\
' : '\U0001d521', + '\\' : '\U0001d522', + '\\' : '\U0001d523', + '\\' : '\U0001d524', + '\\' : '\U0001d525', + '\\' : '\U0001d526', + '\\' : '\U0001d527', + '\\' : '\U0001d528', + '\\' : '\U0001d529', + '\\' : '\U0001d52a', + '\\' : '\U0001d52b', + '\\' : '\U0001d52c', + '\\' : '\U0001d52d', + '\\' : '\U0001d52e', + '\\' : '\U0001d52f', + '\\' : '\U0001d530', + '\\' : '\U0001d531', + '\\' : '\U0001d532', + '\\' : '\U0001d533', + '\\' : '\U0001d534', + '\\' : '\U0001d535', + '\\' : '\U0001d536', + '\\' : '\U0001d537', + '\\' : '\U000003b1', + '\\' : '\U000003b2', + '\\' : '\U000003b3', + '\\' : '\U000003b4', + '\\' : '\U000003b5', + '\\' : '\U000003b6', + '\\' : '\U000003b7', + '\\' : '\U000003b8', + '\\' : '\U000003b9', + '\\' : '\U000003ba', + '\\' : '\U000003bb', + '\\' : '\U000003bc', + '\\' : '\U000003bd', + '\\' : '\U000003be', + '\\' : '\U000003c0', + '\\' : '\U000003c1', + '\\' : '\U000003c3', + '\\' : '\U000003c4', + '\\' : '\U000003c5', + '\\' : '\U000003c6', + '\\' : '\U000003c7', + '\\' : '\U000003c8', + '\\' : '\U000003c9', + '\\' : '\U00000393', + '\\' : '\U00000394', + '\\' : '\U00000398', + '\\' : '\U0000039b', + '\\' : '\U0000039e', + '\\' : '\U000003a0', + '\\' : '\U000003a3', + '\\' : '\U000003a5', + '\\' : '\U000003a6', + '\\' : '\U000003a8', + '\\' : '\U000003a9', + '\\' : '\U0001d539', + '\\' : '\U00002102', + '\\' : '\U00002115', + '\\' : '\U0000211a', + '\\' : '\U0000211d', + '\\' : '\U00002124', + '\\' : '\U00002190', + '\\' : '\U000027f5', + '\\' : '\U00002192', + '\\' : '\U000027f6', + '\\' : '\U000021d0', + '\\' : '\U000027f8', + '\\' : '\U000021d2', + '\\' : '\U000027f9', + '\\' : '\U00002194', + '\\' : '\U000027f7', + '\\' : '\U000021d4', + '\\' : '\U000027fa', + '\\' : '\U000021a6', + '\\' : '\U000027fc', + '\\' : '\U00002500', + '\\' : '\U00002550', + '\\' : '\U000021a9', + '\\' : '\U000021aa', + '\\' : '\U000021bd', + '\\' : '\U000021c1', + '\\' : '\U000021bc', + '\\' : '\U000021c0', + '\\' : '\U000021cc', + '\\' : '\U0000219d', + '\\' : '\U000021c3', + '\\' : '\U000021c2', + '\\' : '\U000021bf', + '\\' : '\U000021be', + '\\' : '\U000021be', + '\\' : '\U00002237', + '\\' : '\U00002191', + '\\' : '\U000021d1', + '\\' : '\U00002193', + '\\' : '\U000021d3', + '\\' : '\U00002195', + '\\' : '\U000021d5', + '\\' : '\U000027e8', + '\\' : '\U000027e9', + '\\' : '\U00002308', + '\\' : '\U00002309', + '\\' : '\U0000230a', + '\\' : '\U0000230b', + '\\' : '\U00002987', + '\\' : '\U00002988', + '\\' : '\U000027e6', + '\\' : '\U000027e7', + '\\' : '\U00002983', + '\\' : '\U00002984', + '\\' : '\U000000ab', + '\\' : '\U000000bb', + '\\' : '\U000022a5', + '\\' : '\U000022a4', + '\\' : '\U00002227', + '\\' : '\U000022c0', + '\\' : '\U00002228', + '\\' : '\U000022c1', + '\\' : '\U00002200', + '\\' : '\U00002203', + '\\' : '\U00002204', + '\\' : '\U000000ac', + '\\' : '\U000025a1', + '\\' : '\U000025c7', + '\\' : '\U000022a2', + '\\' : '\U000022a8', + '\\' : '\U000022a9', + '\\' : '\U000022ab', + '\\' : '\U000022a3', + '\\' : '\U0000221a', + '\\' : '\U00002264', + '\\' : '\U00002265', + '\\' : '\U0000226a', + '\\' : '\U0000226b', + '\\' : '\U00002272', + '\\' : '\U00002273', + '\\' : '\U00002a85', + '\\' : '\U00002a86', + '\\' : '\U00002208', + '\\' : '\U00002209', + '\\' : '\U00002282', + '\\' : '\U00002283', + '\\' : '\U00002286', + '\\' : '\U00002287', + '\\' : '\U0000228f', + '\\' : '\U00002290', + '\\' : '\U00002291', + '\\' : '\U00002292', + '\\' : '\U00002229', + '\\' : '\U000022c2', + '\\' : '\U0000222a', + '\\' : '\U000022c3', + '\\' : '\U00002294', + '\\' : '\U00002a06', + '\\' : '\U00002293', + '\\' : '\U00002a05', + '\\' : '\U00002216', + '\\' : '\U0000221d', + '\\' : '\U0000228e', + '\\' : '\U00002a04', + '\\' : '\U00002260', + '\\' : '\U0000223c', + '\\' : '\U00002250', + '\\' : '\U00002243', + '\\' : '\U00002248', + '\\' : '\U0000224d', + '\\' : '\U00002245', + '\\' : '\U00002323', + '\\' : '\U00002261', + '\\' : '\U00002322', + '\\' : '\U000022c8', + '\\' : '\U00002a1d', + '\\' : '\U0000227a', + '\\' : '\U0000227b', + '\\' : '\U0000227c', + '\\' : '\U0000227d', + '\\' : '\U00002225', + '\\' : '\U000000a6', + '\\' : '\U000000b1', + '\\' : '\U00002213', + '\\' : '\U000000d7', + '\\
' : '\U000000f7', + '\\' : '\U000022c5', + '\\' : '\U000022c6', + '\\' : '\U00002219', + '\\' : '\U00002218', + '\\' : '\U00002020', + '\\' : '\U00002021', + '\\' : '\U000022b2', + '\\' : '\U000022b3', + '\\' : '\U000022b4', + '\\' : '\U000022b5', + '\\' : '\U000025c3', + '\\' : '\U000025b9', + '\\' : '\U000025b3', + '\\' : '\U0000225c', + '\\' : '\U00002295', + '\\' : '\U00002a01', + '\\' : '\U00002297', + '\\' : '\U00002a02', + '\\' : '\U00002299', + '\\' : '\U00002a00', + '\\' : '\U00002296', + '\\' : '\U00002298', + '\\' : '\U00002026', + '\\' : '\U000022ef', + '\\' : '\U00002211', + '\\' : '\U0000220f', + '\\' : '\U00002210', + '\\' : '\U0000221e', + '\\' : '\U0000222b', + '\\' : '\U0000222e', + '\\' : '\U00002663', + '\\' : '\U00002662', + '\\' : '\U00002661', + '\\' : '\U00002660', + '\\' : '\U00002135', + '\\' : '\U00002205', + '\\' : '\U00002207', + '\\' : '\U00002202', + '\\' : '\U0000266d', + '\\' : '\U0000266e', + '\\' : '\U0000266f', + '\\' : '\U00002220', + '\\' : '\U000000a9', + '\\' : '\U000000ae', + '\\' : '\U000000ad', + '\\' : '\U000000af', + '\\' : '\U000000bc', + '\\' : '\U000000bd', + '\\' : '\U000000be', + '\\' : '\U000000aa', + '\\' : '\U000000ba', + '\\
' : '\U000000a7', + '\\' : '\U000000b6', + '\\' : '\U000000a1', + '\\' : '\U000000bf', + '\\' : '\U000020ac', + '\\' : '\U000000a3', + '\\' : '\U000000a5', + '\\' : '\U000000a2', + '\\' : '\U000000a4', + '\\' : '\U000000b0', + '\\' : '\U00002a3f', + '\\' : '\U00002127', + '\\' : '\U000025ca', + '\\' : '\U00002118', + '\\' : '\U00002240', + '\\' : '\U000022c4', + '\\' : '\U000000b4', + '\\' : '\U00000131', + '\\' : '\U000000a8', + '\\' : '\U000000b8', + '\\' : '\U000002dd', + '\\' : '\U000003f5', + '\\' : '\U000023ce', + '\\' : '\U00002039', + '\\' : '\U0000203a', + '\\' : '\U00002302', + '\\<^sub>' : '\U000021e9', + '\\<^sup>' : '\U000021e7', + '\\<^bold>' : '\U00002759', + '\\<^bsub>' : '\U000021d8', + '\\<^esub>' : '\U000021d9', + '\\<^bsup>' : '\U000021d7', + '\\<^esup>' : '\U000021d6', + } + + lang_map = {'isabelle' : isabelle_symbols, 'latex' : latex_symbols} + + def __init__(self, **options): + Filter.__init__(self, **options) + lang = get_choice_opt(options, 'lang', + ['isabelle', 'latex'], 'isabelle') + self.symbols = self.lang_map[lang] + + def filter(self, lexer, stream): + for ttype, value in stream: + if value in self.symbols: + yield ttype, self.symbols[value] + else: + yield ttype, value + + +class KeywordCaseFilter(Filter): + """Convert keywords to lowercase or uppercase or capitalize them, which + means first letter uppercase, rest lowercase. + + This can be useful e.g. if you highlight Pascal code and want to adapt the + code to your styleguide. + + Options accepted: + + `case` : string + The casing to convert keywords to. Must be one of ``'lower'``, + ``'upper'`` or ``'capitalize'``. The default is ``'lower'``. + """ + + def __init__(self, **options): + Filter.__init__(self, **options) + case = get_choice_opt(options, 'case', + ['lower', 'upper', 'capitalize'], 'lower') + self.convert = getattr(str, case) + + def filter(self, lexer, stream): + for ttype, value in stream: + if ttype in Keyword: + yield ttype, self.convert(value) + else: + yield ttype, value + + +class NameHighlightFilter(Filter): + """Highlight a normal Name (and Name.*) token with a different token type. + + Example:: + + filter = NameHighlightFilter( + names=['foo', 'bar', 'baz'], + tokentype=Name.Function, + ) + + This would highlight the names "foo", "bar" and "baz" + as functions. `Name.Function` is the default token type. + + Options accepted: + + `names` : list of strings + A list of names that should be given the different token type. + There is no default. + `tokentype` : TokenType or string + A token type or a string containing a token type name that is + used for highlighting the strings in `names`. The default is + `Name.Function`. + """ + + def __init__(self, **options): + Filter.__init__(self, **options) + self.names = set(get_list_opt(options, 'names', [])) + tokentype = options.get('tokentype') + if tokentype: + self.tokentype = string_to_tokentype(tokentype) + else: + self.tokentype = Name.Function + + def filter(self, lexer, stream): + for ttype, value in stream: + if ttype in Name and value in self.names: + yield self.tokentype, value + else: + yield ttype, value + + +class ErrorToken(Exception): + pass + + +class RaiseOnErrorTokenFilter(Filter): + """Raise an exception when the lexer generates an error token. + + Options accepted: + + `excclass` : Exception class + The exception class to raise. + The default is `pygments.filters.ErrorToken`. + + .. versionadded:: 0.8 + """ + + def __init__(self, **options): + Filter.__init__(self, **options) + self.exception = options.get('excclass', ErrorToken) + try: + # issubclass() will raise TypeError if first argument is not a class + if not issubclass(self.exception, Exception): + raise TypeError + except TypeError: + raise OptionError('excclass option is not an exception class') + + def filter(self, lexer, stream): + for ttype, value in stream: + if ttype is Error: + raise self.exception(value) + yield ttype, value + + +class VisibleWhitespaceFilter(Filter): + """Convert tabs, newlines and/or spaces to visible characters. + + Options accepted: + + `spaces` : string or bool + If this is a one-character string, spaces will be replaces by this string. + If it is another true value, spaces will be replaced by ``·`` (unicode + MIDDLE DOT). If it is a false value, spaces will not be replaced. The + default is ``False``. + `tabs` : string or bool + The same as for `spaces`, but the default replacement character is ``»`` + (unicode RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK). The default value + is ``False``. Note: this will not work if the `tabsize` option for the + lexer is nonzero, as tabs will already have been expanded then. + `tabsize` : int + If tabs are to be replaced by this filter (see the `tabs` option), this + is the total number of characters that a tab should be expanded to. + The default is ``8``. + `newlines` : string or bool + The same as for `spaces`, but the default replacement character is ``¶`` + (unicode PILCROW SIGN). The default value is ``False``. + `wstokentype` : bool + If true, give whitespace the special `Whitespace` token type. This allows + styling the visible whitespace differently (e.g. greyed out), but it can + disrupt background colors. The default is ``True``. + + .. versionadded:: 0.8 + """ + + def __init__(self, **options): + Filter.__init__(self, **options) + for name, default in [('spaces', '·'), + ('tabs', '»'), + ('newlines', '¶')]: + opt = options.get(name, False) + if isinstance(opt, str) and len(opt) == 1: + setattr(self, name, opt) + else: + setattr(self, name, (opt and default or '')) + tabsize = get_int_opt(options, 'tabsize', 8) + if self.tabs: + self.tabs += ' ' * (tabsize - 1) + if self.newlines: + self.newlines += '\n' + self.wstt = get_bool_opt(options, 'wstokentype', True) + + def filter(self, lexer, stream): + if self.wstt: + spaces = self.spaces or ' ' + tabs = self.tabs or '\t' + newlines = self.newlines or '\n' + regex = re.compile(r'\s') + + def replacefunc(wschar): + if wschar == ' ': + return spaces + elif wschar == '\t': + return tabs + elif wschar == '\n': + return newlines + return wschar + + for ttype, value in stream: + yield from _replace_special(ttype, value, regex, Whitespace, + replacefunc) + else: + spaces, tabs, newlines = self.spaces, self.tabs, self.newlines + # simpler processing + for ttype, value in stream: + if spaces: + value = value.replace(' ', spaces) + if tabs: + value = value.replace('\t', tabs) + if newlines: + value = value.replace('\n', newlines) + yield ttype, value + + +class GobbleFilter(Filter): + """Gobbles source code lines (eats initial characters). + + This filter drops the first ``n`` characters off every line of code. This + may be useful when the source code fed to the lexer is indented by a fixed + amount of space that isn't desired in the output. + + Options accepted: + + `n` : int + The number of characters to gobble. + + .. versionadded:: 1.2 + """ + def __init__(self, **options): + Filter.__init__(self, **options) + self.n = get_int_opt(options, 'n', 0) + + def gobble(self, value, left): + if left < len(value): + return value[left:], 0 + else: + return '', left - len(value) + + def filter(self, lexer, stream): + n = self.n + left = n # How many characters left to gobble. + for ttype, value in stream: + # Remove ``left`` tokens from first line, ``n`` from all others. + parts = value.split('\n') + (parts[0], left) = self.gobble(parts[0], left) + for i in range(1, len(parts)): + (parts[i], left) = self.gobble(parts[i], n) + value = '\n'.join(parts) + + if value != '': + yield ttype, value + + +class TokenMergeFilter(Filter): + """Merges consecutive tokens with the same token type in the output + stream of a lexer. + + .. versionadded:: 1.2 + """ + def __init__(self, **options): + Filter.__init__(self, **options) + + def filter(self, lexer, stream): + current_type = None + current_value = None + for ttype, value in stream: + if ttype is current_type: + current_value += value + else: + if current_type is not None: + yield current_type, current_value + current_type = ttype + current_value = value + if current_type is not None: + yield current_type, current_value + + +FILTERS = { + 'codetagify': CodeTagFilter, + 'keywordcase': KeywordCaseFilter, + 'highlight': NameHighlightFilter, + 'raiseonerror': RaiseOnErrorTokenFilter, + 'whitespace': VisibleWhitespaceFilter, + 'gobble': GobbleFilter, + 'tokenmerge': TokenMergeFilter, + 'symbols': SymbolFilter, +}

' : '\U0001d4ab', + '\\' : '\U0001d4ac', + '\\' : '\U0000211b', + '\\' : '\U0001d4ae', + '\\' : '\U0001d4af', + '\\' : '\U0001d4b0', + '\\' : '\U0001d4b1', + '\\' : '\U0001d4b2', + '\\' : '\U0001d4b3', + '\\' : '\U0001d4b4', + '\\' : '\U0001d4b5', + '\\' : '\U0001d5ba', + '\\' : '\U0001d5bb', + '\\' : '\U0001d5bc', + '\\' : '\U0001d5bd', + '\\' : '\U0001d5be', + '\\' : '\U0001d5bf', + '\\' : '\U0001d5c0', + '\\' : '\U0001d5c1', + '\\' : '\U0001d5c2', + '\\' : '\U0001d5c3', + '\\' : '\U0001d5c4', + '\\' : '\U0001d5c5', + '\\' : '\U0001d5c6', + '\\' : '\U0001d5c7', + '\\' : '\U0001d5c8', + '\\