pygments-dig-lexer/dig-lexer.py

# -*- coding: utf-8 -*-
#
# https://gitlab.com/s3lph/pygments-dig-lexer
#
# SPDX-FileCopyrightText: 2020 s3lph
# SPDX-License-Identifier: MIT

from pygments.lexer import ExtendedRegexLexer
from pygments.token import *

REPLY_CODES = {
    'NOERROR': Name.Function,
    'NXDOMAIN': String.Escape,
    'REFUSED': String.Escape,
    'NOTAUTH': String.Escape,
    'NOTZONE': String.Escape
}

class CustomLexer(ExtendedRegexLexer):
    name = 'Dig'
    aliases = ['dig']
    filenames = ['*.zone']

    def parse_dig_header(lexer, re, ctx):
        yield re.start('c1'), Comment.Hashbang, re.group('c1')
        yield re.start('version'), String.Doc, re.group('version')
        yield re.start('c2'), Comment.Hashbang, re.group('c2')
        yield re.start('query'), Name.Function, re.group('query')
        ctx.pos = re.end()

    def parse_response_header(lexer, re, ctx):
        yield re.start('c1'), Comment.Hashbang, re.group('c1')
        yield re.start('opcode'), String.Doc, re.group('opcode')
        yield re.start('c2'), Comment.Hashbang, re.group('c2')
        yield re.start('rcode'), REPLY_CODES.get(re.group('rcode'), Name.Tag), re.group('rcode')
        yield re.start('c3'), Comment.Hashbang, re.group('c3')
        yield re.start('nonce'), String.Doc, re.group('nonce')
        yield re.start('c4'), Comment.Hashbang, re.group('c4')
        yield re.start('flags'), String.Doc, re.group('flags')
        yield re.start('c5'), Comment.Hashbang, re.group('c5')
        yield re.start('nquery'), String.Doc, re.group('nquery')
        yield re.start('c6'), Comment.Hashbang, re.group('c6')
        yield re.start('nanswer'), String.Doc, re.group('nanswer')
        yield re.start('c7'), Comment.Hashbang, re.group('c7')
        yield re.start('nauth'), String.Doc, re.group('nauth')
        yield re.start('c8'), Comment.Hashbang, re.group('c8')
        yield re.start('nadd'), String.Doc, re.group('nadd')
        ctx.pos = re.end()

    def parse_rdns(lexer, re, ctx):
        yield re.start('c1'), Comment.Hashbang, re.group('c1')
        yield re.start('pl64'), Name.Class, re.group('pl64')
        yield re.start('pl48'), Number.Integer, re.group('pl48')
        yield re.start('pl32'), Name.Class, re.group('pl32')
        yield re.start('pl16'), Name.Tag, re.group('pl16')
        yield re.start('pl0'), String.Doc, re.group('pl0')
        yield re.start('end'), Comment.Hashbang, re.group('end')
        ctx.pos = re.end()

    tokens = {
        'root': [
            (r'(?P<c1>; <<>>)(?P<version>.*)(?P<c2><<>>)(?P<query>.*\n)', parse_dig_header),
            (r'(?P<c1>;; ->>HEADER<<- opcode: )(?P<opcode>[^\s]+)(?P<c2>, status: )(?P<rcode>[^\s]+)(?P<c3>, id: )(?P<nonce>[^\s]+\n)(?P<c4>;; flags: )(?P<flags>[^;]+)(?P<c5>; QUERY: )(?P<nquery>\d+)(?P<c6>, ANSWER: )(?P<nanswer>\d+)(?P<c7>, AUTHORITY: )(?P<nauth>\d+)(?P<c8>, ADDITIONAL: )(?P<nadd>\d+\n)', parse_response_header),
            (r'(?P<c1>;)(?P<pl64>([0-9a-fA-F]\.){16})(?P<pl48>([0-9a-fA-F]\.){4})(?P<pl32>([0-9a-fA-F]\.){4})(?P<pl16>([0-9a-fA-F]\.){4})(?P<pl0>([0-9a-fA-F]\.){4})(?P<end>ip6\.arpa\..*$)', parse_rdns),
            (r';;.*', Generic.Subheading),  # comment section headers
            (r';.*', Comment.Single),
            (r'\n', Generic),
            (r'^', Generic, 'rname')
        ],
        'rname': [
            (r'\s', Generic, 'wsp1'),
            (r'\\[0-7]{3}', String.Escape),
            (r'\\.', String.Escape),
            (r'.', Name.Function)
        ],
        'wsp1': [
            (r'\s', Generic),
            (r'[0-9]+', Number.Integer, 'wsp2'),
        ],
        'wsp2': [
            (r'\s', Generic),
            (r'[^\s]+', Name.Class, 'wsp3'),
        ],
        'wsp3': [
            (r'\s', Generic),
            (r'[^\s]+', Name.Tag, 'value'),
        ],
        'value': [
            (r';.*$', Comment.Special),
            (r'\(', Punctuation, 'multiline'),
            (r'\n', Generic, '#pop:5'),
            (r'\s', Generic),
            (r'"', String.Double, 'string'),
            (r'.', String.Single)
        ],
        'string': [
            (r'\\[0-7]{3}', String.Escape),
            (r'\\.', String.Escape),
            (r'"', String.Double, '#pop'),
            (r'.', String.Double)
        ],
        'multiline': [
            (r';.*$', Comment.Special),
            (r'\)', Punctuation, '#pop'),
            (r'\s', Generic),
            (r'"', String.Double, 'string'),
            (r'.', String.Single)
        ]
    }