django1/django/utils/html.py

"""HTML utilities suitable for global use."""

import re
from html.parser import HTMLParser
from urllib.parse import (
    parse_qsl, quote, unquote, urlencode, urlsplit, urlunsplit,
)

from django.utils.encoding import force_text
from django.utils.functional import Promise, keep_lazy, keep_lazy_text
from django.utils.http import RFC3986_GENDELIMS, RFC3986_SUBDELIMS
from django.utils.safestring import SafeData, SafeText, mark_safe
from django.utils.text import normalize_newlines

# Configuration for urlize() function.
TRAILING_PUNCTUATION_RE = re.compile(
    '^'           # Beginning of word
    '(.*?)'       # The URL in word
    '([.,:;!]+)'  # Allowed non-wrapping, trailing punctuation
    '$'           # End of word
)
WRAPPING_PUNCTUATION = [('(', ')'), ('<', '>'), ('[', ']'), ('&lt;', '&gt;'), ('"', '"'), ('\'', '\'')]

# List of possible strings used for bullets in bulleted lists.
DOTS = ['&middot;', '*', '\u2022', '&#149;', '&bull;', '&#8226;']

unencoded_ampersands_re = re.compile(r'&(?!(\w+|#\d+);)')
word_split_re = re.compile(r'''([\s<>"']+)''')
simple_url_re = re.compile(r'^https?://\[?\w', re.IGNORECASE)
simple_url_2_re = re.compile(r'^www\.|^(?!http)\w[^@]+\.(com|edu|gov|int|mil|net|org)($|/.*)$', re.IGNORECASE)
simple_email_re = re.compile(r'^\S+@\S+\.\S+$')

_html_escapes = {
    ord('&'): '&amp;',
    ord('<'): '&lt;',
    ord('>'): '&gt;',
    ord('"'): '&quot;',
    ord("'"): '&#39;',
}


@keep_lazy(str, SafeText)
def escape(text):
    """
    Return the given text with ampersands, quotes and angle brackets encoded
    for use in HTML.

    Always escape input, even if it's already escaped and marked as such.
    This may result in double-escaping. If this is a concern, use
    conditional_escape() instead.
    """
    return mark_safe(str(text).translate(_html_escapes))


_js_escapes = {
    ord('\\'): '\\u005C',
    ord('\''): '\\u0027',
    ord('"'): '\\u0022',
    ord('>'): '\\u003E',
    ord('<'): '\\u003C',
    ord('&'): '\\u0026',
    ord('='): '\\u003D',
    ord('-'): '\\u002D',
    ord(';'): '\\u003B',
    ord('`'): '\\u0060',
    ord('\u2028'): '\\u2028',
    ord('\u2029'): '\\u2029'
}

# Escape every ASCII character with a value less than 32.
_js_escapes.update((ord('%c' % z), '\\u%04X' % z) for z in range(32))


@keep_lazy(str, SafeText)
def escapejs(value):
    """Hex encode characters for use in JavaScript strings."""
    return mark_safe(str(value).translate(_js_escapes))


def conditional_escape(text):
    """
    Similar to escape(), except that it doesn't operate on pre-escaped strings.

    This function relies on the __html__ convention used both by Django's
    SafeData class and by third-party libraries like markupsafe.
    """
    if isinstance(text, Promise):
        text = str(text)
    if hasattr(text, '__html__'):
        return text.__html__()
    else:
        return escape(text)


def format_html(format_string, *args, **kwargs):
    """
    Similar to str.format, but pass all arguments through conditional_escape(),
    and call mark_safe() on the result. This function should be used instead
    of str.format or % interpolation to build up small HTML fragments.
    """
    args_safe = map(conditional_escape, args)
    kwargs_safe = {k: conditional_escape(v) for (k, v) in kwargs.items()}
    return mark_safe(format_string.format(*args_safe, **kwargs_safe))


def format_html_join(sep, format_string, args_generator):
    """
    A wrapper of format_html, for the common case of a group of arguments that
    need to be formatted using the same format string, and then joined using
    'sep'. 'sep' is also passed through conditional_escape.

    'args_generator' should be an iterator that returns the sequence of 'args'
    that will be passed to format_html.

    Example:

      format_html_join('\n', "<li>{} {}</li>", ((u.first_name, u.last_name)
                                                  for u in users))
    """
    return mark_safe(conditional_escape(sep).join(
        format_html(format_string, *tuple(args))
        for args in args_generator))


@keep_lazy_text
def linebreaks(value, autoescape=False):
    """Convert newlines into <p> and <br />s."""
    value = normalize_newlines(value)
    paras = re.split('\n{2,}', str(value))
    if autoescape:
        paras = ['<p>%s</p>' % escape(p).replace('\n', '<br />') for p in paras]
    else:
        paras = ['<p>%s</p>' % p.replace('\n', '<br />') for p in paras]
    return '\n\n'.join(paras)


class MLStripper(HTMLParser):
    def __init__(self):
        super().__init__(convert_charrefs=False)
        self.reset()
        self.fed = []

    def handle_data(self, d):
        self.fed.append(d)

    def handle_entityref(self, name):
        self.fed.append('&%s;' % name)

    def handle_charref(self, name):
        self.fed.append('&#%s;' % name)

    def get_data(self):
        return ''.join(self.fed)


def _strip_once(value):
    """
    Internal tag stripping utility used by strip_tags.
    """
    s = MLStripper()
    s.feed(value)
    s.close()
    return s.get_data()


@keep_lazy_text
def strip_tags(value):
    """Return the given HTML with all tags stripped."""
    # Note: in typical case this loop executes _strip_once once. Loop condition
    # is redundant, but helps to reduce number of executions of _strip_once.
    value = force_text(value)
    while '<' in value and '>' in value:
        new_value = _strip_once(value)
        if len(new_value) >= len(value):
            # _strip_once was not able to detect more tags
            break
        value = new_value
    return value


@keep_lazy_text
def strip_spaces_between_tags(value):
    """Return the given HTML with spaces between tags removed."""
    return re.sub(r'>\s+<', '><', force_text(value))


def smart_urlquote(url):
    """Quote a URL if it isn't already quoted."""
    def unquote_quote(segment):
        segment = unquote(segment)
        # Tilde is part of RFC3986 Unreserved Characters
        # http://tools.ietf.org/html/rfc3986#section-2.3
        # See also http://bugs.python.org/issue16285
        segment = quote(segment, safe=RFC3986_SUBDELIMS + RFC3986_GENDELIMS + '~')
        return force_text(segment)

    # Handle IDN before quoting.
    try:
        scheme, netloc, path, query, fragment = urlsplit(url)
    except ValueError:
        # invalid IPv6 URL (normally square brackets in hostname part).
        return unquote_quote(url)

    try:
        netloc = netloc.encode('idna').decode('ascii')  # IDN -> ACE
    except UnicodeError:  # invalid domain part
        return unquote_quote(url)

    if query:
        # Separately unquoting key/value, so as to not mix querystring separators
        # included in query values. See #22267.
        query_parts = [(unquote(q[0]), unquote(q[1]))
                       for q in parse_qsl(query, keep_blank_values=True)]
        # urlencode will take care of quoting
        query = urlencode(query_parts)

    path = unquote_quote(path)
    fragment = unquote_quote(fragment)

    return urlunsplit((scheme, netloc, path, query, fragment))


@keep_lazy_text
def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
    """
    Convert any URLs in text into clickable links.

    Works on http://, https://, www. links, and also on links ending in one of
    the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org).
    Links can have trailing punctuation (periods, commas, close-parens) and
    leading punctuation (opening parens) and it'll still do the right thing.

    If trim_url_limit is not None, truncate the URLs in the link text longer
    than this limit to trim_url_limit-3 characters and append an ellipsis.

    If nofollow is True, give the links a rel="nofollow" attribute.

    If autoescape is True, autoescape the link text and URLs.
    """
    safe_input = isinstance(text, SafeData)

    def trim_url(x, limit=trim_url_limit):
        if limit is None or len(x) <= limit:
            return x
        return '%s...' % x[:max(0, limit - 3)]

    def unescape(text, trail):
        """
        If input URL is HTML-escaped, unescape it so that it can be safely fed
        to smart_urlquote. For example:
        http://example.com?x=1&amp;y=&lt;2&gt; => http://example.com?x=1&y=<2>
        """
        unescaped = (text + trail).replace(
            '&amp;', '&').replace('&lt;', '<').replace(
            '&gt;', '>').replace('&quot;', '"').replace('&#39;', "'")
        if trail and unescaped.endswith(trail):
            # Remove trail for unescaped if it was not consumed by unescape
            unescaped = unescaped[:-len(trail)]
        elif trail == ';':
            # Trail was consumed by unescape (as end-of-entity marker), move it to text
            text += trail
            trail = ''
        return text, unescaped, trail

    def trim_punctuation(lead, middle, trail):
        """
        Trim trailing and wrapping punctuation from `middle`. Return the items
        of the new state.
        """
        # Continue trimming until middle remains unchanged.
        trimmed_something = True
        while trimmed_something:
            trimmed_something = False

            # Trim trailing punctuation.
            match = TRAILING_PUNCTUATION_RE.match(middle)
            if match:
                middle = match.group(1)
                trail = match.group(2) + trail
                trimmed_something = True

            # Trim wrapping punctuation.
            for opening, closing in WRAPPING_PUNCTUATION:
                if middle.startswith(opening):
                    middle = middle[len(opening):]
                    lead += opening
                    trimmed_something = True
                # Keep parentheses at the end only if they're balanced.
                if (middle.endswith(closing) and
                        middle.count(closing) == middle.count(opening) + 1):
                    middle = middle[:-len(closing)]
                    trail = closing + trail
                    trimmed_something = True
        return lead, middle, trail

    words = word_split_re.split(force_text(text))
    for i, word in enumerate(words):
        if '.' in word or '@' in word or ':' in word:
            # lead: Current punctuation trimmed from the beginning of the word.
            # middle: Current state of the word.
            # trail: Current punctuation trimmed from the end of the word.
            lead, middle, trail = '', word, ''
            # Deal with punctuation.
            lead, middle, trail = trim_punctuation(lead, middle, trail)

            # Make URL we want to point to.
            url = None
            nofollow_attr = ' rel="nofollow"' if nofollow else ''
            if simple_url_re.match(middle):
                middle, middle_unescaped, trail = unescape(middle, trail)
                url = smart_urlquote(middle_unescaped)
            elif simple_url_2_re.match(middle):
                middle, middle_unescaped, trail = unescape(middle, trail)
                url = smart_urlquote('http://%s' % middle_unescaped)
            elif ':' not in middle and simple_email_re.match(middle):
                local, domain = middle.rsplit('@', 1)
                try:
                    domain = domain.encode('idna').decode('ascii')
                except UnicodeError:
                    continue
                url = 'mailto:%s@%s' % (local, domain)
                nofollow_attr = ''

            # Make link.
            if url:
                trimmed = trim_url(middle)
                if autoescape and not safe_input:
                    lead, trail = escape(lead), escape(trail)
                    trimmed = escape(trimmed)
                middle = '<a href="%s"%s>%s</a>' % (escape(url), nofollow_attr, trimmed)
                words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
            else:
                if safe_input:
                    words[i] = mark_safe(word)
                elif autoescape:
                    words[i] = escape(word)
        elif safe_input:
            words[i] = mark_safe(word)
        elif autoescape:
            words[i] = escape(word)
    return ''.join(words)


def avoid_wrapping(value):
    """
    Avoid text wrapping in the middle of a phrase by adding non-breaking
    spaces where there previously were normal spaces.
    """
    return value.replace(" ", "\xa0")


def html_safe(klass):
    """
    A decorator that defines the __html__ method. This helps non-Django
    templates to detect classes whose __str__ methods return SafeText.
    """
    if '__html__' in klass.__dict__:
        raise ValueError(
            "can't apply @html_safe to %s because it defines "
            "__html__()." % klass.__name__
        )
    if '__str__' not in klass.__dict__:
        raise ValueError(
            "can't apply @html_safe to %s because it doesn't "
            "define __str__()." % klass.__name__
        )
    klass_str = klass.__str__
    klass.__str__ = lambda self: mark_safe(klass_str(self))
    klass.__html__ = lambda self: str(self)
    return klass