fix: canonicalize mailing list sourceUrl trailing slash (CM-1318)

Signed-off-by: Uroš Marolt <uros@marolt.me>

Author: themarolt

backend/src/api/integration/helpers/mailingListAuthenticate.ts

@@ -29,6 +29,15 @@ const isSafeSourceUrl = (sourceUrl: string): boolean => {
   }
 }
 
+// "https://host/list" and "https://host/list/" must resolve to the same DB
+// row — the worker's ensure_mirror() already normalizes to this form before
+// cloning (mirror_service.py), so storage must match or the same archive
+// ends up mirrored twice under two rows. Kept as a plain function (not a
+// zod .transform()/.preprocess()) since either makes the field optional in
+// z.infer with the installed zod v4 — reproduced in isolation, unrelated to
+// this schema's nesting.
+export const canonicalizeSourceUrl = (sourceUrl: string): string => sourceUrl.replace(/\/+$/, '')
+
 export const bodySchema = z.object({
   lists: z
     .array(
@@ -42,14 +51,20 @@ export const bodySchema = z.object({
       }),
     )
     .min(1, 'lists must contain at least one mailing list')
-    .refine((lists) => new Set(lists.map((l) => l.sourceUrl)).size === lists.length, {
-      message: 'lists contains duplicate sourceUrl entries',
-    }),
+    .refine(
+      (lists) =>
+        new Set(lists.map((l) => canonicalizeSourceUrl(l.sourceUrl))).size === lists.length,
+      { message: 'lists contains duplicate sourceUrl entries' },
+    ),
 })
 
 export default async (req, res) => {
   new PermissionChecker(req).validateHas(Permissions.values.tenantEdit)
   const integrationData = validateOrThrow(bodySchema, req.body)
+  integrationData.lists = integrationData.lists.map((l) => ({
+    ...l,
+    sourceUrl: canonicalizeSourceUrl(l.sourceUrl),
+  }))
 
   const payload = await new IntegrationService(req).mailingListConnectOrUpdate(integrationData)
   await req.responseHandler.success(req, res, payload)

backend/src/bin/scripts/create-mailing-list-integration.ts

@@ -7,7 +7,10 @@ import * as fs from 'fs'
 
 import { DEFAULT_TENANT_ID, generateUUIDv1 } from '@crowd/common'
 
-import { bodySchema } from '@/api/integration/helpers/mailingListAuthenticate'
+import {
+  bodySchema,
+  canonicalizeSourceUrl,
+} from '@/api/integration/helpers/mailingListAuthenticate'
 import SegmentRepository from '@/database/repositories/segmentRepository'
 import SequelizeRepository from '@/database/repositories/sequelizeRepository'
 import IntegrationService from '@/services/integrationService'
@@ -81,7 +84,8 @@ if (parameters.help || !parameters.file) {
     // so a malformed file (non-array, missing fields, duplicate/non-https
     // sourceUrl) fails fast here instead of reaching IntegrationService with
     // whatever shape the file happened to contain.
-    const { lists } = validateOrThrow(bodySchema, { lists: parsed })
+    const { lists: parsedLists } = validateOrThrow(bodySchema, { lists: parsed })
+    const lists = parsedLists.map((l) => ({ ...l, sourceUrl: canonicalizeSourceUrl(l.sourceUrl) }))
 
     const repoOptions = await SequelizeRepository.getDefaultIRepositoryOptions()
     repoOptions.currentTenant = { id: DEFAULT_TENANT_ID }
@@ -104,7 +108,9 @@ if (parameters.help || !parameters.file) {
       process.exit(1)
     }
 
-    console.log(`Segment: ${repoOptions.currentSegments[0].id} (${repoOptions.currentSegments[0].name})`)
+    console.log(
+      `Segment: ${repoOptions.currentSegments[0].id} (${repoOptions.currentSegments[0].name})`,
+    )
     console.log('Lists:', JSON.stringify(lists, null, 2))
 
     const integration = await new IntegrationService(repoOptions).mailingListConnectOrUpdate(