regex_with_dict_lookup.py

# Adapting https://gist.github.com/angelogladding/c61488d2dd82fb73b9078541a4e2ea13 for library use

import re
from urllib.parse import urlparse

REST = r"(?P<rest>.*)"
DOMAIN_PATTERN = r"^(?P<domain>\w.[^/]+)/" + REST

url_summary_templates = {
    "github.com": [
        (
            r"github.com/(?P<user>\w+)/(?P<project>[\w-]+)/",
            "A comment in the {project} GitHub repository",
        ),
        (
            r"github.com/(?P<user>\w+)/(?P<project>[\w-]+)/issues/(?P<issue>\d+)",
            "A comment on an issue in the {project} GitHub repository",
        ),
        (
            r"github.com/(?P<user>\w+)/(?P<project>[\w-]+)/pulls/(?P<pull>\d+)",
            "A comment on a pull request in the {project} GitHub repository",
        ),
    ],
    "twitter.com": [
        (
            r"twitter.com/(?P<user>\w+)" + REST,
            "A tweet by @{user}",
        ),
    ],
    "upcoming.com": [
        (
            "",
            "An event on Upcoming",
        )
    ],
    "calagator.com": [
        (
            "",
            "An event on Calagator",
        )
    ],
    "events.indieweb.org": [
        (
            "",
            "An event on Calagator",
        )
    ],
    "indieweb.org": [
        (
            r"^indieweb.org/(?P<page>[\w-]+)",
            "The {page} page on the IndieWeb wiki",
        )
    ]
}

def get_summary(url: str, custom_properties: dict = {}):
    """
    Return a text summary for given `url`.
    
    >>> get_summary("https://github.com/capjamesg/indieweb-utils/pulls/1")
    'A comment on a pull request in the indieweb-utils GitHub repository'
    
    """

    url_summary_templates.update(custom_properties)

    results = url_summary_templates.get(urlparse(url).netloc, [])

    url = url.replace("https://", "").replace("http://", "")

    for pattern, summary in results:
        if pattern == "":
            return summary

        if match := re.match(pattern, url):
            return summary.format(**match.groupdict())

    domain = re.match(DOMAIN_PATTERN, url)

    if domain:
        return "A post on " + domain.groupdict()["domain"]

    return ""

print(get_summary("https://github.com/capjamesg/indieweb-utils/pulls/1"))
print(get_summary("https://twitter.com/indieweb"))
print(get_summary("https://eventbrite.co.uk/test"))
print(get_summary("http://upcoming.com/test"))
print(get_summary("https://indieweb.org/coffee"))