22995037636

Committed 12 Mar 2026 09:24AM UTC coverage: 81.129% (-0.4%) from 81.522%

Build # 22995037636

Build Type

push

github

Committed by

web-flow

Commit Message

apps/summarization: refactor export (#88)

Coverage Stats

74 of 360 new or added lines in 16 files covered. (20.56%)

7386 of 9104 relevant lines covered (81.13%)

0.81 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

12.9

/apps/summarization/export_utils/processing/extractors.py

1	import re	1✔
2
3
4	def extract_attachments(text):	1✔
5	"""Extract upload links from HTML text"""
NEW 6	if not text:	×
NEW 7	return []	×
8
9	# Find all links containing /uploads/ (both href and src attributes)
NEW 10	pattern_href = r'href="([^"]?/uploads/[^"]?)"'	×
NEW 11	pattern_src = r'src="([^"]?/uploads/[^"]?)"'	×
12
NEW 13	attachments_href = re.findall(pattern_href, text)	×
NEW 14	attachments_src = re.findall(pattern_src, text)	×
15
16	# Combine and deduplicate
NEW 17	attachments = list(dict.fromkeys(attachments_href + attachments_src))	×
18
NEW 19	return attachments	×
20
21
22	def extract_comments(queryset, include_ratings=True, include_children=True):	1✔
23	"""
24	Extract comments from any model with a 'comments' GenericRelation.
25	Filters out removed, censored, or blocked comments.
26	Recursively includes child comments.
27
28	Args:
29	queryset: Comment queryset (e.g., obj.comments.all())
30	include_ratings: Whether to include ratings on comments
31	include_children: Whether to recursively include child comments
32
33	Returns:
34	List of comment dictionaries with nested 'replies' key
35	"""
NEW 36	comments_list = []	×
37
38	# Filter out unwanted comments at the queryset level
NEW 39	filtered_queryset = queryset.filter(	×
40	is_removed=False, is_censored=False, is_blocked=False
41	)
42
NEW 43	for comment in filtered_queryset:	×
NEW 44	comment_data = {	×
45	"id": comment.id,
46	"text": comment.comment,
47	# "created": comment.created.isoformat(),
48	}
49
50	# Optional fields
NEW 51	if hasattr(comment, "comment_categories") and comment.comment_categories:	×
NEW 52	comment_data["comment_categories"] = comment.comment_categories	×
53
NEW 54	if include_ratings and hasattr(comment, "ratings"):	×
NEW 55	comment_data["ratings"] = [	×
56	{
57	"id": rating.id,
58	"value": rating.value,
59	}
60	for rating in comment.ratings.all()
61	]
62
63	# Recursively include child comments (they will also be filtered)
NEW 64	if include_children and hasattr(comment, "child_comments"):	×
NEW 65	child_comments = comment.child_comments.all()	×
NEW 66	if child_comments.exists():	×
NEW 67	comment_data["replies"] = extract_comments(	×
68	child_comments,
69	include_ratings=include_ratings,
70	include_children=True,
71	)
NEW 72	comment_data["reply_count"] = len(comment_data["replies"])	×
73
NEW 74	comments_list.append(comment_data)	×
75
NEW 76	return comments_list	×
77
78
79	def extract_ratings(queryset):	1✔
80	"""
81	Extract ratings from any model with a 'ratings' GenericRelation.
82
83	Args:
84	queryset: Rating queryset (e.g., obj.ratings.all())
85
86	Returns:
87	List of rating dictionaries
88	"""
NEW 89	ratings_list = []	×
NEW 90	for rating in queryset:	×
NEW 91	ratings_list.append(	×
92	{
93	"id": rating.id,
94	"value": rating.value,
95	}
96	)
NEW 97	return ratings_list	×

liqd / roots / 22995037636

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous