Merge pull request #391 from andygrunwald/andygrunwald/csv-import-coerce-custom-field-types

fix: coerce boolean and numeric values in custom CSV columns

apps/api/src/jobs/__tests__/import-processor.test.ts

@@ -1,6 +1,7 @@
 import {beforeEach, describe, expect, it} from 'vitest';
 import {factories, getPrismaClient} from '../../../../../test/helpers';
 import {ContactService} from '../../services/ContactService.js';
+import {coerceCustomValue} from '../import-processor.js';
 
 /**
  * Tests for Contact Import Processor - Subscription Status Preservation
@@ -279,3 +280,51 @@ describe('Contact Import - Subscription Status Preservation', () => {
     });
   });
 });
+
+describe('coerceCustomValue', () => {
+  describe('boolean coercion', () => {
+    it.each(['true', 'TRUE', 'True', ' true ', 'yes', 'YES', 'Yes'])('coerces %j to true', value => {
+      expect(coerceCustomValue(value)).toBe(true);
+    });
+
+    it.each(['false', 'FALSE', 'False', ' false ', 'no', 'NO', 'No'])('coerces %j to false', value => {
+      expect(coerceCustomValue(value)).toBe(false);
+    });
+  });
+
+  describe('number coercion', () => {
+    it.each([
+      ['42', 42],
+      ['-7', -7],
+      ['3.14', 3.14],
+      [' 42 ', 42],
+      ['0.5', 0.5],
+      ['-0.25', -0.25],
+      ['0', 0],
+      ['1', 1],
+    ])('coerces %j to %j', (value, expected) => {
+      expect(coerceCustomValue(value)).toBe(expected);
+    });
+
+    it.each(['01234', '+42', '.5', '42.', '1e10', 'NaN', 'Infinity', '1.2.3', '4-2'])(
+      'leaves %j as a string (preserves IDs / rejects loose formats)',
+      value => {
+        expect(coerceCustomValue(value)).toBe(value);
+      },
+    );
+
+    it('"1.0" is a number (does not match the boolean truthy set)', () => {
+      expect(coerceCustomValue('1.0')).toBe(1);
+    });
+  });
+
+  describe('passthrough', () => {
+    it.each(['Alice', 'true!', 'yesno', 'maybe'])('leaves %j as a string', value => {
+      expect(coerceCustomValue(value)).toBe(value);
+    });
+
+    it('leaves empty string as empty string', () => {
+      expect(coerceCustomValue('')).toBe('');
+    });
+  });
+});

apps/api/src/jobs/import-processor.ts

@@ -123,7 +123,11 @@ export function createImportWorker() {
 
               // Extract custom data (all fields except email and subscribed)
               const {email: _, subscribed: __, ...customData} = record;
-              const data = Object.keys(customData).length > 0 ? customData : undefined;
+              const customEntries = Object.entries(customData);
+              const data =
+                customEntries.length > 0
+                  ? Object.fromEntries(customEntries.map(([k, v]) => [k, coerceCustomValue(v)]))
+                  : undefined;
 
               // Check if contact exists before upserting
               const existingContact = await ContactService.findByEmail(projectId, email);
@@ -216,3 +220,30 @@ function isValidEmail(email: string): boolean {
   const emailRegex = /^[^\s@]+@[^\s@]+\.[^\s@]+$/;
   return emailRegex.test(email);
 }
+
+// Values considered as boolean during import.
+// Numbers (0, 1) are intentionally absent.
+const BOOLEAN_TRUE = new Set(['true', 'yes']);
+const BOOLEAN_FALSE = new Set(['false', 'no']);
+
+// Strict integer-or-decimal number detection pattern.
+// Valid: 0, 42, -42, 3.14
+// Rejected: 007, +42, 1.2.3, 1e5
+const NUMERIC_RE = /^-?(0|[1-9]\d*)(\.\d+)?$/;
+
+/**
+ * Coerces a raw string into its most natural primitive type: `boolean`,
+ * `number`, or `string`. Values that match neither are
+ * returned unchanged.
+ *
+ * @param value The raw string to coerce.
+ * @returns The coerced value as `boolean`, `number`, or `string`.
+ */
+export function coerceCustomValue(value: string): string | boolean | number {
+  const trimmed = value.trim();
+  const lower = trimmed.toLowerCase();
+  if (BOOLEAN_TRUE.has(lower)) return true;
+  if (BOOLEAN_FALSE.has(lower)) return false;
+  if (NUMERIC_RE.test(trimmed)) return Number(trimmed);
+  return value;
+}

apps/wiki/content/docs/guides/importing-contacts.mdx

@@ -37,6 +37,8 @@ In this example, every imported contact ends up with `data.firstName`, `data.pla
 - **Email column**: must be present and valid. Rows with missing or invalid emails are reported back as errors.
 - **Reserved column names**: `id`, `subscribed`, `createdAt`, `updatedAt`, and the auto-generated URL variables (`unsubscribeUrl`, etc.) are silently filtered out. Don't include them as columns.
 - **Date columns**: use ISO 8601 (`2026-05-06T12:00:00Z`) so they're typed as dates and become usable with `within` / `olderThan` segment operators.
+- **Boolean columns**: `true`, `false`, `yes`, `no` (case-insensitive) are stored as booleans and get the boolean toggle in segment filters.
+- **Numeric columns**: plain integers and decimals (`42`, `3.14`) are stored as numbers and become usable with `gt` / `lt` segment operators. Leading-zero values (`01234`), `+`-prefixed numbers, and scientific notation stay strings so IDs, zip codes, and phone numbers aren't corrupted.
 - **Existing contacts**: if a row's email matches an existing contact, the import **updates** the contact (merging the CSV's columns into `data`). It doesn't create a duplicate or overwrite the whole record.
 
 ## Importing your CSV