docs/xml_lexer.py

from pygments.lexer import RegexLexer
from pygments.token import Text, Comment, Operator, Name, String
from pygments.lexers import _lexer_cache
from pygments.lexers._mapping import LEXERS


def italic_attr(lexer, m):
    yield m.start(), String, '"'
    yield m.start() + 2, Comment, m.group()[3:-1]
    yield m.end() - 1, String, '"'


def italic_generic(lexer, m):
    yield m.start(), Comment, m.group()


def italic_tag(lexer, m):
    yield m.start(), Name.Tag, "<"
    name = m.group()[3:]
    if name.endswith(">"):
        yield m.start() + 1, Comment, name[:-1]
        yield m.end() - 1, Name.Tag, ">"
    else:
        yield m.start() + 1, Comment, name


def italic_tag_close(lexer, m):
    yield m.start(), Name.Tag, "</"
    yield m.start() + 4, Comment, m.group()[4:-1]
    yield m.end() - 1, Name.Tag, ">"


def repeat_tag_close(lexer, m):
    before, _, after = m.group().partition("[]")
    yield m.start(), Name.Tag, before
    yield m.start() + len(before), Operator, "[]"
    yield m.start() + len(before) + 2, Name.Tag, after


def italic_attr_name(lexer, m):
    name, _, after = m.group().partition("*")
    yield m.start(), Name.Attribute, name
    yield m.start() + len(name), Operator, "*"
    yield m.start() + len(name) + 1, Name.Attribute, after


class CustomXMLLexer(RegexLexer):
    name = "customxml"
    aliases = ["cxml"]

    tokens = {
        'root': [
            (r'\s*\.\.\.\w*', Comment),
            ('[^<&]+', Text),
            (r'&\S*?;', Name.Entity),
            (r'\<\!\[CDATA\[.*?\]\]\>', Comment.Preproc),
            (r'<!--(.|\n)*?-->', Comment.Multiline),
            (r'<\?.*?\?>', Comment.Preproc),
            ('<![^>]*>', Comment.Preproc),
            (r'<\s*[\w:.-]+', Name.Tag, 'tag'),
            (r'<\s*/\s*[\w:.-]+\s*>', Name.Tag),
            (r'<\s*\?\?[\w:.-]+', italic_tag, 'tag'),
            (r'<\s*/\s*\?\?[\w:.-]+\s*>', italic_tag_close),
            (r'<\s*/\s*[\w:.-]+\[\]\s*>', repeat_tag_close),
        ],
        'tag': [
            (r'\*', Operator),
            (r'\[\]', Operator),
            (r'\s+', Text),
            (r'\.\.\.\w*', italic_generic),
            (r'[\w.:-]+\s*=', Name.Attribute, 'attr'),
            (r'[\w.:-]+\*\s*=', italic_attr_name, 'attr'),
            (r'/?\s*>', Name.Tag, '#pop'),
        ],
        'attr': [
            (r'\s+', Text),
            (r'"\?\?[^"]*?"', italic_attr, "#pop"),
            ('".*?"', String, '#pop'),
            ("'.*?'", String, '#pop'),
            (r'[^\s>]+', String, '#pop'),
        ],
    }

    def analyse_text(text):
        print("hi?")


_lexer_cache[CustomXMLLexer.__name__] = CustomXMLLexer

LEXERS["CustomXMLLexer"] = ("xml_lexer", "CustomXMLLexer", ("cxml", ), (), ())

__all__ = ("CustomXMLLexer", )