1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298import { db, event, graphqlQuery, validateShortId, buildUrlSearchClause } from "#src/utils";
const BATCH_SIZE = 1000;
const csvEscape = (val: any) => {
const str = val === null || val === undefined ? "" : String(val);
return `"${str.replace(/"/g, '""')}"`;
};
export const exportAuditTable = async () => {
const auditId = (event.queryStringParameters as any).id;
const contentType = (event.queryStringParameters as any).contentType || "all";
const sortBy = (event.queryStringParameters as any).sortBy || "created_at";
const sortOrder = (event.queryStringParameters as any).sortOrder || "desc";
const tagsParam = (event.queryStringParameters as any).tags || null;
const categoriesParam =
(event.queryStringParameters as any).categories || null;
const statusParam = (event.queryStringParameters as any).status || null;
const tagFilters = tagsParam ? tagsParam.split(",").filter(Boolean) : [];
const typeFilters = categoriesParam
? categoriesParam.split(",").filter(Boolean)
: [];
const searchString = (event.queryStringParameters as any).searchString || "";
// Mirrors getAuditTable: "all" | "group" (one row per unique hash) | "hide"
// (only blockers appearing once in the latest scan).
const duplicatesMode = (event.queryStringParameters as any).duplicates || "all";
await db.connect();
const audit = (
await db.query({
text: `SELECT * FROM "audits" WHERE "id" = $1`,
values: [auditId],
})
).rows?.[0];
// Duplicated hashes in the latest scan (same definition as getAuditTable),
// for the duplicated/hide filters and the Occurrences CSV column.
const duplicateRows = (
await db.query({
text: `SELECT "content_hash_id", COUNT(*)::int AS "occurrences"
FROM "blockers"
WHERE "scan_id" = (SELECT "id" FROM "scans" WHERE "audit_id" = $1 ORDER BY "created_at" DESC LIMIT 1)
GROUP BY "content_hash_id"
HAVING COUNT(*) > 1`,
values: [auditId],
})
).rows as { content_hash_id: string; occurrences: number }[];
await db.clean();
const occurrencesByHash = new Map(
duplicateRows.map((row) => [row.content_hash_id, row.occurrences])
);
const duplicatedHashIds = duplicateRows.map((row) => row.content_hash_id);
const whereConditions: any[] = [];
if (tagFilters.length > 0) {
whereConditions.push({
blocker_messages: {
message: {
message_tags: { tag: { id: { _in: tagFilters } } },
},
},
});
}
if (typeFilters.length > 0) {
whereConditions.push({
blocker_messages: {
message: { category: { _in: typeFilters } },
},
});
}
if (statusParam) {
if (statusParam === "active") {
whereConditions.push({
blocker_messages: {
blocker: {
_not: {
ignored_blocker: { blocker_id: { _is_null: false } },
},
},
},
});
} else if (statusParam === "ignored") {
whereConditions.push({
blocker_messages: {
blocker: {
ignored_blocker: { id: { _is_null: false } },
},
},
});
} else if (statusParam === "duplicated") {
whereConditions.push({
content_hash_id: { _in: duplicatedHashIds },
});
}
}
if (duplicatesMode === "hide") {
whereConditions.push({
_not: { content_hash_id: { _in: duplicatedHashIds } },
});
}
if (searchString !== "") {
if (validateShortId(searchString)) {
whereConditions.push({ short_id: { _eq: searchString } });
} else {
whereConditions.push(buildUrlSearchClause(searchString));
}
}
const whereClause =
whereConditions.length > 0 ? { _and: whereConditions } : {};
const orderByClause =
sortBy === "url"
? { url: { url: sortOrder } }
: { created_at: sortOrder };
// Find the latest scan id for this audit so we can paginate blockers directly
const scanQuery = {
query: `query ($audit_id: uuid!) {
audits_by_pk(id: $audit_id) {
scans(order_by: {created_at: desc}, limit: 1) {
id
}
}
}`,
variables: { audit_id: auditId },
};
const scanResp = await graphqlQuery(scanQuery);
const latestScanId = scanResp.audits_by_pk?.scans?.[0]?.id;
if (!latestScanId) {
return {
statusCode: 200,
headers: {
"content-type": "text/csv; charset=utf-8",
"content-disposition": `attachment; filename="blockers-${auditId}-${new Date().toISOString().split("T")[0]}.csv"`,
},
body: "Type,URL,Issue,Code,Tags,Rules,Status,ID,Occurrences\n",
};
}
// Pull all blockers in batches to avoid Hasura row limits
const ignoredSetQuery = {
query: `query ($audit_id: uuid!) {
ignored_blockers(where: {audit_id: {_eq: $audit_id}}) {
blocker_id
}
}`,
variables: { audit_id: auditId },
};
const ignoredResp = await graphqlQuery(ignoredSetQuery);
const ignoredSet = new Set<string>(
(ignoredResp.ignored_blockers || []).map((ib: any) => ib.blocker_id)
);
const scopedWhere = {
_and: [{ scan_id: { _eq: latestScanId } }, ...whereConditions],
};
const allBlockers: any[] = [];
let offset = 0;
while (true) {
const batchQuery = {
query: `query ($limit: Int!, $offset: Int!, $where: blockers_bool_exp!, $order_by: [blockers_order_by!]) {
blockers(where: $where, limit: $limit, offset: $offset, order_by: $order_by) {
id
short_id
content_hash_id
created_at
content
url_id
url { url type }
blocker_messages {
id
message {
id
content
category
message_tags { tag { id content } }
}
}
}
}`,
variables: {
limit: BATCH_SIZE,
offset,
where: scopedWhere,
order_by: [orderByClause],
},
};
const batchResp = await graphqlQuery(batchQuery);
const batch = batchResp.blockers || [];
allBlockers.push(...batch);
if (batch.length < BATCH_SIZE) break;
offset += BATCH_SIZE;
}
let formattedBlockers = allBlockers.map((blocker) => {
const tags = blocker.blocker_messages.flatMap(
(bm: any) =>
bm.message.message_tags?.map((mt: any) => mt.tag).filter(Boolean) || []
);
const uniqueTags = Array.from(
new Map(tags.map((tag: any) => [tag.id, tag])).values()
) as any[];
const categories = Array.from(
new Set(blocker.blocker_messages.map((bm: any) => bm.message.category))
);
const messages = blocker.blocker_messages.map(
(bm: any) => bm.message.content
);
return {
id: blocker.id,
short_id: blocker.short_id,
content_hash_id: blocker.content_hash_id,
occurrences: occurrencesByHash.get(blocker.content_hash_id) ?? 1,
url: blocker.url?.url || "Unknown URL",
type: blocker.url?.type || "unknown",
content: blocker.content,
messages,
tags: uniqueTags,
categories,
};
});
if (
contentType.toLowerCase() === "html" ||
contentType.toLowerCase() === "pdf"
) {
formattedBlockers = formattedBlockers.filter(
(b) => b.type.toLowerCase() === contentType.toLowerCase()
);
}
// Group mode: keep the first row per content hash (after the contentType
// filter so the kept representative matches the requested type).
if (duplicatesMode === "group") {
const seenHashes = new Set<string>();
formattedBlockers = formattedBlockers.filter((b) => {
if (seenHashes.has(b.content_hash_id)) return false;
seenHashes.add(b.content_hash_id);
return true;
});
}
// Occurrences is appended last so consumers addressing the export by
// column position keep the original eight columns unchanged.
const headers = [
"Type",
"URL",
"Issue",
"Code",
"Tags",
"Rules",
"Status",
"ID",
"Occurrences",
];
const rows = formattedBlockers.map((b) =>
[
b.type,
b.url,
b.messages?.[0] || "",
b.content || "",
b.tags.map((t: any) => t.content).join("; "),
b.categories.join("; "),
ignoredSet.has(b.id) ? "Ignored" : "Active",
b.short_id || "",
b.occurrences,
]
.map(csvEscape)
.join(",")
);
const csv = [headers.join(","), ...rows].join("\n");
const datePart = new Date().toISOString().split("T")[0];
const filename = `blockers-${audit?.name ? audit.name.replace(/[^a-z0-9-_]/gi, "_") + "-" : ""}${auditId}-${datePart}.csv`;
return {
statusCode: 200,
headers: {
"content-type": "text/csv; charset=utf-8",
"content-disposition": `attachment; filename="${filename}"`,
},
body: csv,
};
};