def handle_links()

in bleach/linkifier.py [0:0]

• 54 lines of code
• 22 McCabe index (conditional complexity)

    def handle_links(self, src_iter):
        """Handle links in character tokens"""
        in_a = False  # happens, if parse_email=True and if a mail was found
        for token in src_iter:
            if in_a:
                if token["type"] == "EndTag" and token["name"] == "a":
                    in_a = False
                yield token
                continue
            elif token["type"] == "StartTag" and token["name"] == "a":
                in_a = True
                yield token
                continue
            if token["type"] == "Characters":
                text = token["data"]
                new_tokens = []
                end = 0

                for match in self.url_re.finditer(text):
                    if match.start() > end:
                        new_tokens.append(
                            {"type": "Characters", "data": text[end : match.start()]}
                        )

                    url = match.group(0)
                    prefix = suffix = ""

                    # Sometimes we pick up too much in the url match, so look for
                    # bits we should drop and remove them from the match
                    url, prefix, suffix = self.strip_non_url_bits(url)

                    # If there's no protocol, add one
                    if PROTO_RE.search(url):
                        href = url
                    else:
                        href = "http://%s" % url

                    attrs = {(None, "href"): href, "_text": url}
                    attrs = self.apply_callbacks(attrs, True)

                    if attrs is None:
                        # Just add the text
                        new_tokens.append(
                            {"type": "Characters", "data": prefix + url + suffix}
                        )

                    else:
                        # Add the "a" tag!
                        if prefix:
                            new_tokens.append({"type": "Characters", "data": prefix})

                        _text = attrs.pop("_text", "")
                        new_tokens.extend(
                            [
                                {"type": "StartTag", "name": "a", "data": attrs},
                                {"type": "Characters", "data": str(_text)},
                                {"type": "EndTag", "name": "a"},
                            ]
                        )

                        if suffix:
                            new_tokens.append({"type": "Characters", "data": suffix})

                    end = match.end()

                if new_tokens:
                    # Yield the adjusted set of tokens and then continue
                    # through the loop
                    if end < len(text):
                        new_tokens.append({"type": "Characters", "data": text[end:]})

                    yield from new_tokens

                    continue

            yield token