util.py :  » Content-Management-Systems » PyLucid » PyLucid_standalone » pygments » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Content Management Systems » PyLucid 
PyLucid » PyLucid_standalone » pygments » util.py
# -*- coding: utf-8 -*-
"""
    pygments.util
    ~~~~~~~~~~~~~

    Utility functions.

    :copyright: Copyright 2006-2010 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import re
import sys
import codecs


split_path_re = re.compile(r'[/\\ ]')
doctype_lookup_re = re.compile(r'''(?smx)
    (<\?.*?\?>)?\s*
    <!DOCTYPE\s+(
     [a-zA-Z_][a-zA-Z0-9]*\s+
     [a-zA-Z_][a-zA-Z0-9]*\s+
     "[^"]*")
     [^>]*>
''')
tag_re = re.compile(r'<(.+?)(\s.*?)?>.*?</.+?>(?uism)')


class ClassNotFound(ValueError):
    """
    If one of the get_*_by_* functions didn't find a matching class.
    """


class OptionError(Exception):
    pass


def get_choice_opt(options, optname, allowed, default=None, normcase=False):
    string = options.get(optname, default)
    if normcase:
        string = string.lower()
    if string not in allowed:
        raise OptionError('Value for option %s must be one of %s' %
                          (optname, ', '.join(map(str, allowed))))
    return string


def get_bool_opt(options, optname, default=None):
    string = options.get(optname, default)
    if isinstance(string, bool):
        return string
    elif isinstance(string, int):
        return bool(string)
    elif not isinstance(string, basestring):
        raise OptionError('Invalid type %r for option %s; use '
                          '1/0, yes/no, true/false, on/off' % (
                          string, optname))
    elif string.lower() in ('1', 'yes', 'true', 'on'):
        return True
    elif string.lower() in ('0', 'no', 'false', 'off'):
        return False
    else:
        raise OptionError('Invalid value %r for option %s; use '
                          '1/0, yes/no, true/false, on/off' % (
                          string, optname))


def get_int_opt(options, optname, default=None):
    string = options.get(optname, default)
    try:
        return int(string)
    except TypeError:
        raise OptionError('Invalid type %r for option %s; you '
                          'must give an integer value' % (
                          string, optname))
    except ValueError:
        raise OptionError('Invalid value %r for option %s; you '
                          'must give an integer value' % (
                          string, optname))


def get_list_opt(options, optname, default=None):
    val = options.get(optname, default)
    if isinstance(val, basestring):
        return val.split()
    elif isinstance(val, (list, tuple)):
        return list(val)
    else:
        raise OptionError('Invalid type %r for option %s; you '
                          'must give a list value' % (
                          val, optname))


def docstring_headline(obj):
    if not obj.__doc__:
        return ''
    res = []
    for line in obj.__doc__.strip().splitlines():
        if line.strip():
            res.append(" " + line.strip())
        else:
            break
    return ''.join(res).lstrip()


def make_analysator(f):
    """
    Return a static text analysation function that
    returns float values.
    """
    def text_analyse(text):
        rv = f(text)
        if not rv:
            return 0.0
        return min(1.0, max(0.0, float(rv)))
    text_analyse.__doc__ = f.__doc__
    return staticmethod(text_analyse)


def shebang_matches(text, regex):
    """
    Check if the given regular expression matches the last part of the
    shebang if one exists.

        >>> from pygments.util import shebang_matches
        >>> shebang_matches('#!/usr/bin/env python', r'python(2\.\d)?')
        True
        >>> shebang_matches('#!/usr/bin/python2.4', r'python(2\.\d)?')
        True
        >>> shebang_matches('#!/usr/bin/python-ruby', r'python(2\.\d)?')
        False
        >>> shebang_matches('#!/usr/bin/python/ruby', r'python(2\.\d)?')
        False
        >>> shebang_matches('#!/usr/bin/startsomethingwith python',
        ...                 r'python(2\.\d)?')
        True

    It also checks for common windows executable file extensions::

        >>> shebang_matches('#!C:\\Python2.4\\Python.exe', r'python(2\.\d)?')
        True

    Parameters (``'-f'`` or ``'--foo'`` are ignored so ``'perl'`` does
    the same as ``'perl -e'``)

    Note that this method automatically searches the whole string (eg:
    the regular expression is wrapped in ``'^$'``)
    """
    index = text.find('\n')
    if index >= 0:
        first_line = text[:index].lower()
    else:
        first_line = text.lower()
    if first_line.startswith('#!'):
        try:
            found = [x for x in split_path_re.split(first_line[2:].strip())
                     if x and not x.startswith('-')][-1]
        except IndexError:
            return False
        regex = re.compile('^%s(\.(exe|cmd|bat|bin))?$' % regex, re.IGNORECASE)
        if regex.search(found) is not None:
            return True
    return False


def doctype_matches(text, regex):
    """
    Check if the doctype matches a regular expression (if present).
    Note that this method only checks the first part of a DOCTYPE.
    eg: 'html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"'
    """
    m = doctype_lookup_re.match(text)
    if m is None:
        return False
    doctype = m.group(2)
    return re.compile(regex).match(doctype.strip()) is not None


def html_doctype_matches(text):
    """
    Check if the file looks like it has a html doctype.
    """
    return doctype_matches(text, r'html\s+PUBLIC\s+"-//W3C//DTD X?HTML.*')


_looks_like_xml_cache = {}
def looks_like_xml(text):
    """
    Check if a doctype exists or if we have some tags.
    """
    key = hash(text)
    try:
        return _looks_like_xml_cache[key]
    except KeyError:
        m = doctype_lookup_re.match(text)
        if m is not None:
            return True
        rv = tag_re.search(text[:1000]) is not None
        _looks_like_xml_cache[key] = rv
        return rv

# Python 2/3 compatibility

if sys.version_info < (3,0):
    b = bytes = str
    u_prefix = 'u'
    import StringIO, cStringIO
    BytesIO = cStringIO.StringIO
    StringIO = StringIO.StringIO
    uni_open = codecs.open
else:
    import builtins
    bytes = builtins.bytes
    u_prefix = ''
    def b(s):
        if isinstance(s, str):
            return bytes(map(ord, s))
        elif isinstance(s, bytes):
            return s
        else:
            raise TypeError("Invalid argument %r for b()" % (s,))
    import io
    BytesIO = io.BytesIO
    StringIO = io.StringIO
    uni_open = builtins.open
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.