Truncate a string without ending in the middle of a word

Question

I am looking for a way to truncate a string in Python that will not cut off the string in the middle of a word.

For example:

Original:          \"This is          


        

Answer 1

def smart_truncate1(text, max_length=100, suffix='...'):
    """Returns a string of at most `max_length` characters, cutting
    only at word-boundaries. If the string was truncated, `suffix`
    will be appended.
    """

    if len(text) > max_length:
        pattern = r'^(.{0,%d}\S)\s.*' % (max_length-len(suffix)-1)
        return re.sub(pattern, r'\1' + suffix, text)
    else:
        return text

OR

def smart_truncate2(text, min_length=100, suffix='...'):
    """If the `text` is more than `min_length` characters long,
    it will be cut at the next word-boundary and `suffix`will
    be appended.
    """

    pattern = r'^(.{%d,}?\S)\s.*' % (min_length-1)
    return re.sub(pattern, r'\1' + suffix, text)

OR

def smart_truncate3(text, length=100, suffix='...'):
    """Truncates `text`, on a word boundary, as close to
    the target length it can come.
    """

    slen = len(suffix)
    pattern = r'^(.{0,%d}\S)\s+\S+' % (length-slen-1)
    if len(text) > length:
        match = re.match(pattern, text)
        if match:
            length0 = match.end(0)
            length1 = match.end(1)
            if abs(length0+slen-length) < abs(length1+slen-length):
                return match.group(0) + suffix
            else:
                return match.group(1) + suffix
    return text