/lib/django-0.96/django/utils/text.py

import re

from django.conf import settings

# Capitalizes the first letter of a string.
capfirst = lambda x: x and x[0].upper() + x[1:]

def wrap(text, width):
    """
    A word-wrap function that preserves existing line breaks and most spaces in
    the text. Expects that existing line breaks are posix newlines.
    """
    def _generator():
        it = iter(text.split(' '))
        word = it.next()
        yield word
        pos = len(word) - word.rfind('\n') - 1
        for word in it:
            if "\n" in word:
                lines = word.split('\n')
            else:
                lines = (word,)
            pos += len(lines[0]) + 1
            if pos > width:
                yield '\n'
                pos = len(lines[-1])
            else:
                yield ' '
                if len(lines) > 1:
                    pos = len(lines[-1])
            yield word
    return "".join(_generator())

def truncate_words(s, num):
    "Truncates a string after a certain number of words."
    length = int(num)
    words = s.split()
    if len(words) > length:
        words = words[:length]
        if not words[-1].endswith('...'):
            words.append('...')
    return ' '.join(words)

def truncate_html_words(s, num):
    """
    Truncates html to a certain number of words (not counting tags and comments).
    Closes opened tags if they were correctly closed in the given html.
    """
    length = int(num)
    if length <= 0:
        return ''
    html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
    # Set up regular expressions
    re_words = re.compile(r'&.*?;|<.*?>|([A-Za-z0-9][\w-]*)')
    re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
    # Count non-HTML words and keep note of open tags
    pos = 0
    ellipsis_pos = 0
    words = 0
    open_tags = []
    while words <= length:
        m = re_words.search(s, pos)
        if not m:
            # Checked through whole string
            break
        pos = m.end(0)
        if m.group(1):
            # It's an actual non-HTML word
            words += 1
            if words == length:
                ellipsis_pos = pos
            continue
        # Check for tag
        tag = re_tag.match(m.group(0))
        if not tag or ellipsis_pos:
            # Don't worry about non tags or tags after our truncate point
            continue
        closing_tag, tagname, self_closing = tag.groups()
        tagname = tagname.lower()  # Element names are always case-insensitive
        if self_closing or tagname in html4_singlets:
            pass
        elif closing_tag:
            # Check for match in open tags list
            try:
                i = open_tags.index(tagname)
            except ValueError:
                pass
            else:
                # SGML: An end tag closes, back to the matching start tag, all unclosed intervening start tags with omitted end tags
                open_tags = open_tags[i+1:]
        else:
            # Add it to the start of the open tags list
            open_tags.insert(0, tagname)
    if words <= length:
        # Don't try to close tags if we don't need to truncate
        return s
    out = s[:ellipsis_pos] + ' ...'
    # Close any tags still open
    for tag in open_tags:
        out += '</%s>' % tag
    # Return string
    return out

def get_valid_filename(s):
    """
    Returns the given string converted to a string that can be used for a clean
    filename. Specifically, leading and trailing spaces are removed; other
    spaces are converted to underscores; and all non-filename-safe characters
    are removed.
    >>> get_valid_filename("john's portrait in 2004.jpg")
    'johns_portrait_in_2004.jpg'
    """
    s = s.strip().replace(' ', '_')
    return re.sub(r'[^-A-Za-z0-9_.]', '', s)

def get_text_list(list_, last_word='or'):
    """
    >>> get_text_list(['a', 'b', 'c', 'd'])
    'a, b, c or d'
    >>> get_text_list(['a', 'b', 'c'], 'and')
    'a, b and c'
    >>> get_text_list(['a', 'b'], 'and')
    'a and b'
    >>> get_text_list(['a'])
    'a'
    >>> get_text_list([])
    ''
    """
    if len(list_) == 0: return ''
    if len(list_) == 1: return list_[0]
    return '%s %s %s' % (', '.join([str(i) for i in list_][:-1]), last_word, list_[-1])

def normalize_newlines(text):
    return re.sub(r'\r\n|\r|\n', '\n', text)

def recapitalize(text):
    "Recapitalizes text, placing caps after end-of-sentence punctuation."
#     capwords = ()
    text = text.lower()
    capsRE = re.compile(r'(?:^|(?<=[\.\?\!] ))([a-z])')
    text = capsRE.sub(lambda x: x.group(1).upper(), text)
#     for capword in capwords:
#         capwordRE = re.compile(r'\b%s\b' % capword, re.I)
#         text = capwordRE.sub(capword, text)
    return text

def phone2numeric(phone):
    "Converts a phone number with letters into its numeric equivalent."
    letters = re.compile(r'[A-PR-Y]', re.I)
    char2number = lambda m: {'a': '2', 'c': '2', 'b': '2', 'e': '3',
         'd': '3', 'g': '4', 'f': '3', 'i': '4', 'h': '4', 'k': '5',
         'j': '5', 'm': '6', 'l': '5', 'o': '6', 'n': '6', 'p': '7',
         's': '7', 'r': '7', 'u': '8', 't': '8', 'w': '9', 'v': '8',
         'y': '9', 'x': '9'}.get(m.group(0).lower())
    return letters.sub(char2number, phone)

# From http://www.xhaus.com/alan/python/httpcomp.html#gzip
# Used with permission.
def compress_string(s):
    import cStringIO, gzip
    zbuf = cStringIO.StringIO()
    zfile = gzip.GzipFile(mode='wb', compresslevel=6, fileobj=zbuf)
    zfile.write(s)
    zfile.close()
    return zbuf.getvalue()

ustring_re = re.compile(u"([\u0080-\uffff])")

def javascript_quote(s, quote_double_quotes=False):

    def fix(match):
        return r"\u%04x" % ord(match.group(1))

    if type(s) == str:
        s = s.decode(settings.DEFAULT_CHARSET)
    elif type(s) != unicode:
        raise TypeError, s
    s = s.replace('\\', '\\\\')
    s = s.replace('\r', '\\r')
    s = s.replace('\n', '\\n')
    s = s.replace('\t', '\\t')
    s = s.replace("'", "\\'")
    if quote_double_quotes:
        s = s.replace('"', '&quot;')
    return str(ustring_re.sub(fix, s))

smart_split_re = re.compile('("(?:[^"\\\\]*(?:\\\\.[^"\\\\]*)*)"|\'(?:[^\'\\\\]*(?:\\\\.[^\'\\\\]*)*)\'|[^\\s]+)')
def smart_split(text):
    """
    Generator that splits a string by spaces, leaving quoted phrases together.
    Supports both single and double quotes, and supports escaping quotes with
    backslashes. In the output, strings will keep their initial and trailing
    quote marks.
    >>> list(smart_split('This is "a person\'s" test.'))
    ['This', 'is', '"a person\'s"', 'test.']
    """
    for bit in smart_split_re.finditer(text):
        bit = bit.group(0)
        if bit[0] == '"':
            yield '"' + bit[1:-1].replace('\\"', '"').replace('\\\\', '\\') + '"'
        elif bit[0] == "'":
            yield "'" + bit[1:-1].replace("\\'", "'").replace("\\\\", "\\") + "'"
        else:
            yield bit