refactor(utils): add slugify and adopt it at the eight sites that hand-rolled it (#7018)

The same three-step derivation — lowercase, collapse each non-alphanumeric run
to a hyphen, strip the leading and trailing one — sat in eight files. Two of
them carried a TSDoc line whose only job was to warn that they mirrored a third
(`instance-org.ts`: "Derives a slug the same way the admin organization API
does"; `consolidate-users-into-organization.ts`: "Mirrors the slug derivation
used by POST /api/v1/admin/organizations"). A comment asserting two
implementations agree is the shape duplication takes when it cannot be checked.

All eight were semantically identical. Two anchored the strip with `-+` rather
than `-`, and one followed it with a `--+` collapse, but `[^a-z0-9]+` has
already collapsed every run by that point, so neither could ever match more than
the single-hyphen form. Nothing changes.

Truncation stays at the call sites. Four of them bound the result — at 24, 64
and 80 — and only `copy-chats.ts` strips again afterwards, because slicing can
land mid-run and leave a trailing hyphen the earlier strip never saw. Folding a
`maxLength` into the helper would have had to pick one of those behaviors and
silently impose it on the others.

`artifact-stylesheet.ts` keeps its copy: it lives inside the `SIM_ARTIFACT_SHELL`
template literal and runs in the viewer's browser, where there is no import to
resolve.

Author: waleedlatif1

apps/sim/app/(landing)/models/utils.ts

@@ -1,4 +1,5 @@
 import type { ComponentType } from 'react'
+import { slugify } from '@sim/utils/string'
 import { type ModelCapabilities, PROVIDER_DEFINITIONS } from '@/providers/models'
 
 const PROVIDER_PREFIXES: Record<string, string[]> = {
@@ -224,14 +225,6 @@ function trimTrailingZeros(value: string): string {
   return value.replace(/\.0+$/, '').replace(/(\.\d*?)0+$/, '$1')
 }
 
-function slugify(value: string): string {
-  return value
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-+|-+$/g, '')
-    .replace(/--+/g, '-')
-}
-
 function getProviderPrefixes(providerId: string): string[] {
   return PROVIDER_PREFIXES[providerId] ?? [`${providerId}/`]
 }

apps/sim/app/api/v1/admin/organizations/route.ts

@@ -25,6 +25,7 @@ import { AuditAction, AuditResourceType, recordAudit } from '@sim/audit'
 import { db, dbReplica } from '@sim/db'
 import { member, organization, user } from '@sim/db/schema'
 import { createLogger } from '@sim/logger'
+import { slugify } from '@sim/utils/string'
 import { count, eq } from 'drizzle-orm'
 import {
   adminV1CreateOrganizationContract,
@@ -142,12 +143,7 @@ export const POST = withRouteHandler(
         )
       }
 
-      const slug =
-        requestedSlug?.trim() ||
-        name
-          .toLowerCase()
-          .replace(/[^a-z0-9]+/g, '-')
-          .replace(/^-|-$/g, '')
+      const slug = requestedSlug?.trim() || slugify(name)
 
       const { organizationId, memberId } = await createOrganizationWithOwner({
         ownerUserId: ownerId,

apps/sim/app/workspace/[workspaceId]/skills/components/utils.ts

@@ -1,3 +1,4 @@
+import { slugify } from '@sim/utils/string'
 import { isApiClientError } from '@/lib/api/client/errors'
 
 export interface ParsedSkill {
@@ -75,12 +76,7 @@ function inferNameFromHeading(markdown: string): string {
   const headingMatch = markdown.match(/^#{1,3}\s+(.+)$/m)
   if (!headingMatch) return ''
 
-  return headingMatch[1]
-    .trim()
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-|-$/g, '')
-    .slice(0, 64)
+  return slugify(headingMatch[1]).slice(0, 64)
 }
 
 /**

apps/sim/ee/workspace-forking/lib/copy/copy-chats.ts

@@ -3,6 +3,7 @@ import { createLogger } from '@sim/logger'
 import { generateId, generateShortId } from '@sim/utils/id'
 import { isRecordLike } from '@sim/utils/object'
 import { randomInt } from '@sim/utils/random'
+import { slugify } from '@sim/utils/string'
 import { and, inArray, isNull } from 'drizzle-orm'
 import type { DbOrTx } from '@/lib/db/types'
 
@@ -18,14 +19,14 @@ export interface ForkChatCopyPair {
   workflowName: string
 }
 
-/** Lowercase a display name into the chat identifier charset (`[a-z0-9-]`), bounded. */
+/**
+ * Lowercase a display name into the chat identifier charset (`[a-z0-9-]`), bounded.
+ *
+ * The trailing strip runs again after the bound: truncation can land mid-run and
+ * leave a hyphen the pre-truncation strip never saw.
+ */
 function slugifyForIdentifier(value: string): string {
-  const slug = value
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-+|-+$/g, '')
-    .slice(0, 24)
-    .replace(/-+$/g, '')
+  const slug = slugify(value).slice(0, 24).replace(/-+$/g, '')
   return slug || 'chat'
 }
 

apps/sim/lib/billing/enterprise-owner-claim.ts

@@ -4,7 +4,7 @@ import { member, outboxEvent, user, workspace } from '@sim/db/schema'
 import { createLogger } from '@sim/logger'
 import { safeCompare } from '@sim/security/compare'
 import { generateId } from '@sim/utils/id'
-import { normalizeEmail } from '@sim/utils/string'
+import { normalizeEmail, slugify } from '@sim/utils/string'
 import { and, count, desc, eq, or, sql } from 'drizzle-orm'
 import { z } from 'zod'
 import { getEmailSubject, renderEnterpriseOwnerInvitationEmail } from '@/components/emails'
@@ -855,11 +855,7 @@ function sameWorkspaceSet(left: string[], right: string[]): boolean {
 }
 
 function claimOrganizationSlug(name: string, claimId: string): string {
-  const base = name
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-|-$/g, '')
-    .slice(0, 80)
+  const base = slugify(name).slice(0, 80)
   return `${base || 'organization'}-${claimId.replace(/[^a-z0-9]/g, '')}`
 }
 

apps/sim/lib/billing/enterprise-provisioning.ts

@@ -14,7 +14,7 @@ import {
 import { isOrgAdminRole, permissionSatisfies } from '@sim/platform-authz/workspace'
 import { generateId } from '@sim/utils/id'
 import { isRecordLike } from '@sim/utils/object'
-import { normalizeEmail } from '@sim/utils/string'
+import { normalizeEmail, slugify } from '@sim/utils/string'
 import {
   and,
   count,
@@ -998,11 +998,7 @@ export async function reviewEnterpriseProvisioning(
 }
 
 function slugifyOrganizationName(name: string, organizationId: string): string {
-  const base = name
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-|-$/g, '')
-    .slice(0, 80)
+  const base = slugify(name).slice(0, 80)
   return `${base || 'organization'}-${organizationId.slice(-8)}`
 }
 

apps/sim/lib/organizations/instance-org.ts

@@ -19,6 +19,7 @@ import { db } from '@sim/db'
 import { member, organization, user } from '@sim/db/schema'
 import { createLogger } from '@sim/logger'
 import { getErrorMessage } from '@sim/utils/errors'
+import { slugify } from '@sim/utils/string'
 import { eq, sql } from 'drizzle-orm'
 import {
   createOrganizationWithOwnerTx,
@@ -33,14 +34,6 @@ const logger = createLogger('InstanceOrganization')
 /** Bounds the wait for a concurrent provisioning attempt on another replica. */
 const INSTANCE_ORG_LOCK_TIMEOUT_MS = 10_000
 
-/** Derives a slug the same way the admin organization API does. */
-function slugifyOrganizationName(name: string): string {
-  return name
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-|-$/g, '')
-}
-
 interface InstanceOrganizationConfig {
   name: string
   slug: string
@@ -61,7 +54,7 @@ export function getInstanceOrganizationConfig(): InstanceOrganizationConfig | nu
   const name = env.INSTANCE_ORG_NAME?.trim()
   if (!name) return null
 
-  const slug = env.INSTANCE_ORG_SLUG?.trim() || slugifyOrganizationName(name)
+  const slug = env.INSTANCE_ORG_SLUG?.trim() || slugify(name)
   if (!slug) {
     logger.error('INSTANCE_ORG_NAME does not yield a usable slug; set INSTANCE_ORG_SLUG', { name })
     return null

apps/sim/scripts/consolidate-users-into-organization.ts

@@ -65,7 +65,7 @@ import { db } from '@sim/db'
 import { member, organization, session, user, workspace } from '@sim/db/schema'
 import { createLogger } from '@sim/logger'
 import { getErrorMessage } from '@sim/utils/errors'
-import { normalizeEmail } from '@sim/utils/string'
+import { normalizeEmail, slugify } from '@sim/utils/string'
 import { and, count, eq, inArray, isNull, ne } from 'drizzle-orm'
 import {
   createOrganizationWithOwner,
@@ -202,14 +202,6 @@ function parseArgs(argv: string[]): Options {
   return options
 }
 
-/** Mirrors the slug derivation used by `POST /api/v1/admin/organizations`. */
-function slugifyOrganizationName(name: string): string {
-  return name
-    .toLowerCase()
-    .replace(/[^a-z0-9]+/g, '-')
-    .replace(/^-|-$/g, '')
-}
-
 async function findUserByEmail(email: string): Promise<UserRow | null> {
   const [row] = await db
     .select({ id: user.id, email: user.email, name: user.name })
@@ -244,7 +236,7 @@ async function resolveTargetOrganization(options: Options): Promise<TargetOrgani
     ? eq(organization.id, options.orgId)
     : options.orgSlug
       ? eq(organization.slug, options.orgSlug)
-      : eq(organization.slug, slugifyOrganizationName(options.orgName as string))
+      : eq(organization.slug, slugify(options.orgName as string))
 
   const [existing] = await db
     .select({ id: organization.id, name: organization.name, slug: organization.slug })
@@ -302,7 +294,7 @@ async function resolveTargetOrganization(options: Options): Promise<TargetOrgani
   return {
     id: null,
     name: options.orgName,
-    slug: options.orgSlug?.trim() || slugifyOrganizationName(options.orgName),
+    slug: options.orgSlug?.trim() || slugify(options.orgName),
     ownerUserId: owner.id,
     ownerEmail: owner.email,
     mustBeCreated: true,

packages/utils/src/string.test.ts

@@ -9,10 +9,40 @@ import {
   projectEscapedMarkdownForSearch,
   sanitizeForJsonb,
   sanitizeValueForJsonb,
+  slugify,
   stripVersionSuffix,
   truncate,
 } from './string.js'
 
+describe('slugify', () => {
+  it('lowercases and hyphenates a display name', () => {
+    expect(slugify('Acme Corp')).toBe('acme-corp')
+  })
+
+  it('collapses each run of non-alphanumerics into a single hyphen', () => {
+    expect(slugify('Sim.ai <> RVTech')).toBe('sim-ai-rvtech')
+  })
+
+  it('drops leading and trailing separators', () => {
+    expect(slugify('  !!Hello World!!  ')).toBe('hello-world')
+  })
+
+  it('returns an empty string when nothing survives', () => {
+    expect(slugify('***')).toBe('')
+    expect(slugify('')).toBe('')
+  })
+
+  /* ASCII-only: the class drops non-Latin text rather than transliterating it. */
+  it('drops characters outside the ASCII alphanumerics', () => {
+    expect(slugify('Café')).toBe('caf')
+    expect(slugify('日本語')).toBe('')
+  })
+
+  it('preserves digits and hyphens already in the input', () => {
+    expect(slugify('workspace-2024')).toBe('workspace-2024')
+  })
+})
+
 describe('truncate', () => {
   it('appends the suffix when the string exceeds the slice length', () => {
     expect(truncate('hello world', 8)).toBe('hello wo...')

packages/utils/src/string.ts

@@ -33,6 +33,31 @@ export function truncate(str: string, sliceLength: number, suffix = '...'): stri
   return str.length > sliceLength ? str.slice(0, sliceLength) + suffix : str
 }
 
+/**
+ * Lowercases `value` into the `[a-z0-9-]` charset: every run of other characters
+ * becomes one hyphen, and leading and trailing hyphens are dropped.
+ *
+ * ASCII-only by design — the character class drops accented and non-Latin text
+ * rather than transliterating it, so `'Café'` yields `'caf'` and a wholly
+ * non-Latin name yields `''`. Callers that need a non-empty result supply their
+ * own fallback, because what to fall back to is theirs to decide.
+ *
+ * Truncation is likewise the caller's: slicing a slug can leave a trailing
+ * hyphen, and whether to strip it, and at what length, varies by the identifier
+ * being built.
+ *
+ * @example
+ * slugify('Acme Corp')       // 'acme-corp'
+ * slugify('  !!Hello!!  ')   // 'hello'
+ * slugify('***')             // ''
+ */
+export function slugify(value: string): string {
+  return value
+    .toLowerCase()
+    .replace(/[^a-z0-9]+/g, '-')
+    .replace(/^-|-$/g, '')
+}
+
 /**
  * Strips a trailing `_vN` version suffix from `value`, yielding the base type.
  * Only the single trailing suffix is removed; leading occurrences are left intact.