/ usr / lib / python3 / dist-packages / pygments / [ HOME SHELL ]

Name	Size	Permission	Action
__pycache__	[ DIR ]	drwxr-xr-x
filters	[ DIR ]	drwxr-xr-x
formatters	[ DIR ]	drwxr-xr-x
lexers	[ DIR ]	drwxr-xr-x
styles	[ DIR ]	drwxr-xr-x
__init__.py	2.93 KB	-rw-r--r--
__main__.py	348 B	-rw-r--r--
cmdline.py	22.71 KB	-rw-r--r--
console.py	1.66 KB	-rw-r--r--
filter.py	1.89 KB	-rw-r--r--
formatter.py	2.83 KB	-rw-r--r--
lexer.py	31.11 KB	-rw-r--r--
modeline.py	986 B	-rw-r--r--
plugin.py	1.67 KB	-rw-r--r--
regexopt.py	3 KB	-rw-r--r--
scanner.py	3.02 KB	-rw-r--r--
sphinxext.py	4.49 KB	-rw-r--r--
style.py	6.1 KB	-rw-r--r--
token.py	6 KB	-rw-r--r--
unistring.py	61.71 KB	-rw-r--r--
util.py	8.91 KB	-rw-r--r--

Code Editor : regexopt.py

"""
    pygments.regexopt
    ~~~~~~~~~~~~~~~~~

An algorithm that generates optimized regexes for matching long lists of
    literal strings.

:copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
from re import escape
from os.path import commonprefix
from itertools import groupby
from operator import itemgetter

CS_ESCAPE = re.compile(r'[\[\^\\\-\]]')
FIRST_ELEMENT = itemgetter(0)

def make_charset(letters):
    return '[' + CS_ESCAPE.sub(lambda m: '\\' + m.group(), ''.join(letters)) + ']'

def regex_opt_inner(strings, open_paren):
    """Return a regex that matches any string in the sorted list of strings."""
    close_paren = open_paren and ')' or ''
    # print strings, repr(open_paren)
    if not strings:
        # print '-> nothing left'
        return ''
    first = strings[0]
    if len(strings) == 1:
        # print '-> only 1 string'
        return open_paren + escape(first) + close_paren
    if not first:
        # print '-> first string empty'
        return open_paren + regex_opt_inner(strings[1:], '(?:') \
            + '?' + close_paren
    if len(first) == 1:
        # multiple one-char strings? make a charset
        oneletter = []
        rest = []
        for s in strings:
            if len(s) == 1:
                oneletter.append(s)
            else:
                rest.append(s)
        if len(oneletter) > 1:  # do we have more than one oneletter string?
            if rest:
                # print '-> 1-character + rest'
                return open_paren + regex_opt_inner(rest, '') + '|' \
                    + make_charset(oneletter) + close_paren
            # print '-> only 1-character'
            return open_paren + make_charset(oneletter) + close_paren
    prefix = commonprefix(strings)
    if prefix:
        plen = len(prefix)
        # we have a prefix for all strings
        # print '-> prefix:', prefix
        return open_paren + escape(prefix) \
            + regex_opt_inner([s[plen:] for s in strings], '(?:') \
            + close_paren
    # is there a suffix?
    strings_rev = [s[::-1] for s in strings]
    suffix = commonprefix(strings_rev)
    if suffix:
        slen = len(suffix)
        # print '-> suffix:', suffix[::-1]
        return open_paren \
            + regex_opt_inner(sorted(s[:-slen] for s in strings), '(?:') \
            + escape(suffix[::-1]) + close_paren
    # recurse on common 1-string prefixes
    # print '-> last resort'
    return open_paren + \
        '|'.join(regex_opt_inner(list(group[1]), '')
                 for group in groupby(strings, lambda s: s[0] == first[0])) \
        + close_paren

def regex_opt(strings, prefix='', suffix=''):
    """Return a compiled regex that matches any string in the given list.

The strings to match must be literal strings, not regexes.  They will be
    regex-escaped.

*prefix* and *suffix* are pre- and appended to the final regex.
    """
    strings = sorted(strings)
    return prefix + regex_opt_inner(strings, '(') + suffix

Urban Research Lab

Urban Research Lab

The Urban Research Lab (URL) at IIIT-Delhi was established in 2020, during a time when the pandemic brought the complexities of urban life more visible than ever. What started as an initiative by faculty and students has grown into a collaborative space for critically exploring and reimagining the urban questions through research, dialogue, and interdisciplinary engagement.