Adding zendesk exclude org option (#75)

Signed-off-by: Denis Jannot <denis.jannot@solo.io>

Author: djannot

README.md

@@ -218,6 +218,7 @@ Configuration is managed through two files:
         *   `start_date`: (Optional) Only process tickets/articles updated since this date (e.g., `'2025-01-01'`).
         *   `ticket_status`: (Optional) Filter tickets by status (defaults to `['new', 'open', 'pending', 'hold', 'solved']`).
         *   `ticket_priority`: (Optional) Filter tickets by priority (defaults to all priorities).
+        *   `excluded_organizations`: (Optional) An array of Zendesk organization names whose tickets should be skipped. The sync will abort if any name cannot be resolved.
 
         For S3 buckets (`type: 's3'`):
         *   `bucket`: The S3 bucket name.
@@ -359,6 +360,7 @@ Configuration is managed through two files:
         start_date: '2025-01-01'
         ticket_status: ['open', 'pending']
         ticket_priority: ['high']
+        excluded_organizations: ['Acme Corp', 'Internal Testing']
         max_size: 1048576
         database_config:
           type: 'sqlite'

doc2vec.ts

@@ -1326,6 +1326,9 @@ export class Doc2Vec {
         // transitioning to closed get updated rather than left stale)
         const statusFilter = new Set(config.ticket_status || ['new', 'open', 'pending', 'hold', 'solved', 'closed']);
 
+        const excludedOrgNames = new Set((config.excluded_organizations || []).map(n => n.toLowerCase()));
+        const excludedOrgIds = new Set<number>();
+
         const fetchWithRetry = async (url: string, retries = 3): Promise<any> => {
             for (let attempt = 0; attempt < retries; attempt++) {
                 try {
@@ -1409,6 +1412,12 @@ export class Doc2Vec {
                 return;
             }
 
+            // Skip tickets belonging to excluded organizations
+            if (ticket.organization_id && excludedOrgIds.has(ticket.organization_id)) {
+                logger.debug(`Ticket #${ticketId} belongs to excluded organization ${ticket.organization_id} — skipping`);
+                return;
+            }
+
             // Skip tickets whose status is outside the configured filter
             if (!statusFilter.has(ticket.status)) {
                 logger.debug(`Ticket #${ticketId} has status '${ticket.status}' outside configured filter — skipping`);
@@ -1441,6 +1450,28 @@ export class Doc2Vec {
             await this.processChunksForUrl(chunks, url, dbConnection, logger);
         };
 
+        if (excludedOrgNames.size > 0) {
+            logger.info(`Resolving ${excludedOrgNames.size} excluded organization name(s) to IDs`);
+            const resolvedNames = new Set<string>();
+            let orgsUrl: string | null = `${baseUrl}/organizations.json?page[size]=100`;
+            while (orgsUrl) {
+                const orgsData: any = await fetchWithRetry(orgsUrl);
+                for (const org of orgsData?.organizations || []) {
+                    const orgName = (org.name || '').toLowerCase();
+                    if (excludedOrgNames.has(orgName)) {
+                        excludedOrgIds.add(org.id);
+                        resolvedNames.add(orgName);
+                    }
+                }
+                orgsUrl = orgsData?.meta?.has_more ? orgsData?.links?.next : null;
+            }
+            logger.info(`Excluding tickets from ${excludedOrgIds.size} organization(s): ${[...excludedOrgIds].join(', ')}`);
+            const unresolved = [...excludedOrgNames].filter(name => !resolvedNames.has(name));
+            if (unresolved.length > 0) {
+                throw new Error(`Cannot resolve excluded organization(s): ${unresolved.join(', ')}. Aborting to avoid syncing data for them.`);
+            }
+        }
+
         logger.info(`Fetching Zendesk tickets updated since ${lastRunDate}`);
 
         // Build query parameters — use the status filter for the search query

package.json

@@ -1,6 +1,6 @@
 {
     "name": "doc2vec",
-    "version": "2.9.2",
+    "version": "2.10.0",
     "type": "commonjs",
     "description": "",
     "main": "dist/doc2vec.js",

types.ts

@@ -44,6 +44,7 @@ export interface ZendeskSourceConfig extends BaseSourceConfig {
     start_date?: string;           // For incremental updates (default: start of current year)
     ticket_status?: string[];      // Filter tickets by status (default: ['new', 'open', 'pending', 'hold', 'solved'])
     ticket_priority?: string[];    // Filter tickets by priority (default: all)
+    excluded_organizations?: string[]; // Organization names whose tickets should be skipped
 }
 
 // Configuration specific to code sources (local directory or GitHub repo)