75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
import re
|
|
from urllib.parse import urlsplit, urlunsplit
|
|
|
|
from tasks.models import TaskExternalLink
|
|
|
|
HTTP_LINK_PATTERN = re.compile(r"https?://[^\s<>\"']+", re.IGNORECASE)
|
|
TRAILING_LINK_PUNCTUATION = ".,;:!?)]}"
|
|
|
|
|
|
def normalize_http_link(value):
|
|
candidate = str(value or "").strip().rstrip(TRAILING_LINK_PUNCTUATION)
|
|
if not candidate or len(candidate) > 2048:
|
|
return None
|
|
try:
|
|
parsed = urlsplit(candidate)
|
|
except ValueError:
|
|
return None
|
|
if parsed.scheme.lower() not in {"http", "https"} or not parsed.hostname:
|
|
return None
|
|
return urlunsplit(
|
|
(
|
|
parsed.scheme.lower(),
|
|
parsed.netloc.lower(),
|
|
parsed.path,
|
|
parsed.query,
|
|
parsed.fragment,
|
|
)
|
|
)
|
|
|
|
|
|
def http_link_identity(value):
|
|
normalized = normalize_http_link(value)
|
|
if normalized is None:
|
|
return None
|
|
parsed = urlsplit(normalized)
|
|
path = "" if parsed.path == "/" else parsed.path
|
|
return urlunsplit(
|
|
(parsed.scheme, parsed.netloc, path, parsed.query, parsed.fragment)
|
|
)
|
|
|
|
|
|
def extract_http_links(text):
|
|
links = []
|
|
identities = set()
|
|
for match in HTTP_LINK_PATTERN.finditer(text or ""):
|
|
link = normalize_http_link(match.group(0))
|
|
identity = http_link_identity(link)
|
|
if link is None or identity is None or identity in identities:
|
|
continue
|
|
identities.add(identity)
|
|
links.append(link)
|
|
return links
|
|
|
|
|
|
def add_comment_links_to_task(*, task, text, created_by):
|
|
existing_identities = {
|
|
identity
|
|
for url in task.external_links.values_list("url", flat=True)
|
|
if (identity := http_link_identity(url)) is not None
|
|
}
|
|
created = []
|
|
for url in extract_http_links(text):
|
|
identity = http_link_identity(url)
|
|
if identity in existing_identities:
|
|
continue
|
|
link, was_created = TaskExternalLink.objects.get_or_create(
|
|
task=task,
|
|
url=url,
|
|
defaults={"created_by": created_by},
|
|
)
|
|
existing_identities.add(identity)
|
|
if was_created:
|
|
created.append(link)
|
|
return created
|