Function urlize

deps/v8/third_party/jinja2/utils.py:221–339

Convert URLs in text into clickable links. This may not recognize links in some situations. Usually, a more comprehensive formatter, such as a Markdown library, is a better choice. Works on ``http://``, ``https://``, ``www.``, ``mailto:``, and email addresses. Links with traili

(
    text: str,
    trim_url_limit: t.Optional[int] = None,
    rel: t.Optional[str] = None,
    target: t.Optional[str] = None,
    extra_schemes: t.Optional[t.Iterable[str]] = None,
)

def urlize(
    text: str,
    trim_url_limit: t.Optional[int] = None,
    rel: t.Optional[str] = None,
    target: t.Optional[str] = None,
    extra_schemes: t.Optional[t.Iterable[str]] = None,
) -> str:
    """Convert URLs in text into clickable links.

    This may not recognize links in some situations. Usually, a more
    comprehensive formatter, such as a Markdown library, is a better
    choice.

    Works on ``http://``, ``https://``, ``www.``, ``mailto:``, and email
    addresses. Links with trailing punctuation (periods, commas, closing
    parentheses) and leading punctuation (opening parentheses) are
    recognized excluding the punctuation. Email addresses that include
    header fields are not recognized (for example,
    ``mailto:address@example.com?cc=copy@example.com``).

    :param text: Original text containing URLs to link.
    :param trim_url_limit: Shorten displayed URL values to this length.
    :param target: Add the ``target`` attribute to links.
    :param rel: Add the ``rel`` attribute to links.
    :param extra_schemes: Recognize URLs that start with these schemes
        in addition to the default behavior.

    .. versionchanged:: 3.0
        The ``extra_schemes`` parameter was added.

    .. versionchanged:: 3.0
        Generate ``https://`` links for URLs without a scheme.

    .. versionchanged:: 3.0
        The parsing rules were updated. Recognize email addresses with
        or without the ``mailto:`` scheme. Validate IP addresses. Ignore
        parentheses and brackets in more cases.
    """
    if trim_url_limit is not None:

        def trim_url(x: str) -> str:
            if len(x) > trim_url_limit:  # type: ignore
                return f"{x[:trim_url_limit]}..."

            return x

    else:

        def trim_url(x: str) -> str:
            return x

    words = re.split(r"(\s+)", str(markupsafe.escape(text)))
    rel_attr = f' rel="{markupsafe.escape(rel)}"' if rel else ""
    target_attr = f' target="{markupsafe.escape(target)}"' if target else ""

    for i, word in enumerate(words):
        head, middle, tail = "", word, ""
        match = re.match(r"^([(<]|&lt;)+", middle)