fix(file-parsers): read officeparser's entry point across module systems

`officeparser` is CommonJS — `main: officeParser.js`, no `type`, no `exports`
map — so what `await import('officeparser')` yields depends on who built the
code. Node and webpack synthesize named exports from `module.exports`, so
`.parseOfficeAsync` is there. esbuild, which builds the Trigger.dev worker
bundle, puts `module.exports` on `.default` and leaves the named export
undefined, and the package is in neither `build.external` nor
`additionalPackages`, so it is bundled.

Reading the named export directly therefore worked everywhere except the
worker, where calling it threw `TypeError: parseOfficeAsync is not a function`.
All four parsers treat that as "the library failed" and answer with a scrape of
the archive, which returns `degraded: true`, and the document pipeline rejects a
degraded parse outright. The visible result was every `.pptx` and legacy `.doc`
reporting "No text could be extracted from this file — it may be scanned,
image-only, or password-protected", naming a cause that had nothing to do with
the fault. 118 pptx and 14 doc failures landed in a single burst when one
connector's sync first succeeded after ten consecutive crashes.

Resolved in one shared loader rather than per bundler: externalizing the package
has to be repeated in every build config this code runs under and regresses
silently the day one is missed.

The shape handling is split into a pure `resolveParseOfficeAsync` because the
failing shape cannot be reproduced by mocking the specifier — Vitest's
module-namespace proxy throws on a missing export rather than yielding the
`undefined` a real bundle produces, so a test going through `import` can only
assert the shape that already worked. That is also why the existing parser
suites never caught this: each mocks `officeparser` with a fabricated named
export, which presupposes the interop being broken here.

Author: waleedlatif1

apps/sim/lib/file-parsers/doc-parser.ts

@@ -1,6 +1,7 @@
 import { existsSync } from 'fs'
 import { readFile } from 'fs/promises'
 import { createLogger } from '@sim/logger'
+import { loadParseOfficeAsync } from '@/lib/file-parsers/officeparser-module'
 import type { FileParseResult, FileParser } from '@/lib/file-parsers/types'
 import { sanitizeTextForUTF8 } from '@/lib/file-parsers/utils'
 import { assertOoxmlArchiveWithinLimits } from '@/lib/file-parsers/zip-guard'
@@ -41,8 +42,8 @@ export class DocParser implements FileParser {
       assertOoxmlArchiveWithinLimits(buffer)
 
       try {
-        const officeParser = await import('officeparser')
-        const result = await officeParser.parseOfficeAsync(buffer)
+        const parseOfficeAsync = await loadParseOfficeAsync()
+        const result = await parseOfficeAsync(buffer)
 
         if (result) {
           const resultString = typeof result === 'string' ? result : String(result)

apps/sim/lib/file-parsers/docx-parser.ts

@@ -1,6 +1,7 @@
 import { readFile } from 'fs/promises'
 import { createLogger } from '@sim/logger'
 import mammoth from 'mammoth'
+import { loadParseOfficeAsync } from '@/lib/file-parsers/officeparser-module'
 import type { FileParseResult, FileParser } from '@/lib/file-parsers/types'
 import { sanitizeTextForUTF8 } from '@/lib/file-parsers/utils'
 import { assertOoxmlArchiveWithinLimits } from '@/lib/file-parsers/zip-guard'
@@ -65,8 +66,8 @@ export class DocxParser implements FileParser {
       }
 
       try {
-        const officeParser = await import('officeparser')
-        const result = await officeParser.parseOfficeAsync(buffer)
+        const parseOfficeAsync = await loadParseOfficeAsync()
+        const result = await parseOfficeAsync(buffer)
 
         if (result) {
           const resultString = typeof result === 'string' ? result : String(result)

apps/sim/lib/file-parsers/officeparser-module.test.ts

@@ -0,0 +1,46 @@
+/**
+ * @vitest-environment node
+ */
+import { describe, expect, it } from 'vitest'
+import { resolveParseOfficeAsync } from '@/lib/file-parsers/officeparser-module'
+
+const parse = async () => 'slide text'
+
+describe('resolveParseOfficeAsync', () => {
+  /**
+   * Node and webpack synthesize named exports from `officeparser`'s CommonJS
+   * `module.exports`, so this is the shape the app server sees — and the only
+   * one the code used to handle.
+   */
+  it('resolves the named export when the bundler synthesizes one', () => {
+    expect(resolveParseOfficeAsync({ parseOfficeAsync: parse })).toBe(parse)
+  })
+
+  /**
+   * esbuild — which builds the Trigger.dev worker — puts `module.exports` on
+   * `default` and leaves the named export undefined. Reading the named export
+   * directly yielded `undefined` there, and calling it threw
+   * `TypeError: parseOfficeAsync is not a function`, which every parser treats
+   * as a library failure and answers with a `degraded` scrape that the document
+   * pipeline then rejects. This is the shape that broke production: every
+   * `.pptx` and legacy `.doc` from a connector reported "No text could be
+   * extracted" while the same files parsed fine through the app.
+   */
+  it('resolves through default when the bundler namespaces the CommonJS exports', () => {
+    expect(resolveParseOfficeAsync({ default: { parseOfficeAsync: parse } })).toBe(parse)
+  })
+
+  /** A CommonJS module whose `module.exports` IS the function. */
+  it('resolves a default export that is itself callable', () => {
+    expect(resolveParseOfficeAsync({ default: parse })).toBe(parse)
+  })
+
+  /**
+   * Fails loudly rather than handing back `undefined` for a caller to invoke —
+   * the undefined call is what produced a misleading "no text could be
+   * extracted" report instead of naming the real fault.
+   */
+  it('throws when no shape exposes the entry point', () => {
+    expect(() => resolveParseOfficeAsync({})).toThrow('did not expose parseOfficeAsync')
+  })
+})

apps/sim/lib/file-parsers/officeparser-module.ts

@@ -0,0 +1,50 @@
+/** `officeparser`'s single entry point, as every parser here calls it. */
+type ParseOfficeAsync = (input: Buffer) => Promise<string>
+
+interface OfficeParserModule {
+  parseOfficeAsync?: ParseOfficeAsync
+  default?: { parseOfficeAsync?: ParseOfficeAsync } | ParseOfficeAsync
+}
+
+/**
+ * Resolves `officeparser`'s entry point across module systems.
+ *
+ * `officeparser` is CommonJS — `main: officeParser.js`, no `type` and no
+ * `exports` map — so what `await import('officeparser')` yields depends on who
+ * built the code. Node and webpack synthesize named exports from the CJS
+ * `module.exports`, so `.parseOfficeAsync` is there. esbuild, which builds the
+ * Trigger.dev worker bundle, puts `module.exports` on `.default` and leaves the
+ * named export undefined.
+ *
+ * Reading the named export directly therefore worked everywhere except the
+ * worker, where `parseOfficeAsync` was `undefined` and calling it threw
+ * `TypeError: parseOfficeAsync is not a function`. Every parser here treats that
+ * as "the library failed" and falls back to scraping the archive, which returns
+ * `degraded: true` — and the document pipeline rejects a degraded parse outright.
+ * The visible result was every `.pptx` and legacy `.doc` from a connector
+ * failing as "No text could be extracted", while the same files parsed fine
+ * through the app.
+ *
+ * Reading both shapes fixes it at the source rather than per bundler: the
+ * alternative is externalizing the package in each build config, which has to be
+ * repeated for every bundler this code runs under and silently regresses the day
+ * one is missed.
+ */
+export function resolveParseOfficeAsync(mod: OfficeParserModule): ParseOfficeAsync {
+  if (typeof mod.parseOfficeAsync === 'function') return mod.parseOfficeAsync
+  if (typeof mod.default === 'function') return mod.default
+  if (typeof mod.default?.parseOfficeAsync === 'function') return mod.default.parseOfficeAsync
+
+  throw new Error('officeparser did not expose parseOfficeAsync')
+}
+
+/**
+ * Split from {@link resolveParseOfficeAsync} so the shape handling is testable.
+ * The failing shape cannot be reproduced by mocking the specifier — Vitest's
+ * module-namespace proxy throws on a missing export rather than yielding the
+ * `undefined` the real bundle produces — so a test that goes through `import`
+ * can only assert the shape that already worked.
+ */
+export async function loadParseOfficeAsync(): Promise<ParseOfficeAsync> {
+  return resolveParseOfficeAsync((await import('officeparser')) as OfficeParserModule)
+}

apps/sim/lib/file-parsers/opendocument-parser.ts

@@ -1,6 +1,7 @@
 import { existsSync } from 'fs'
 import { readFile } from 'fs/promises'
 import { createLogger } from '@sim/logger'
+import { loadParseOfficeAsync } from '@/lib/file-parsers/officeparser-module'
 import type { FileParseResult, FileParser } from '@/lib/file-parsers/types'
 import { sanitizeTextForUTF8 } from '@/lib/file-parsers/utils'
 import { assertOoxmlArchiveWithinLimits } from '@/lib/file-parsers/zip-guard'
@@ -46,7 +47,7 @@ export class OpenDocumentParser implements FileParser {
      */
     assertOoxmlArchiveWithinLimits(buffer)
 
-    const { parseOfficeAsync } = await import('officeparser')
+    const parseOfficeAsync = await loadParseOfficeAsync()
 
     let extracted: string
     try {

apps/sim/lib/file-parsers/pptx-parser.ts

@@ -1,6 +1,7 @@
 import { existsSync } from 'fs'
 import { readFile } from 'fs/promises'
 import { createLogger } from '@sim/logger'
+import { loadParseOfficeAsync } from '@/lib/file-parsers/officeparser-module'
 import type { FileParseResult, FileParser } from '@/lib/file-parsers/types'
 import { sanitizeTextForUTF8 } from '@/lib/file-parsers/utils'
 import { assertOoxmlArchiveWithinLimits } from '@/lib/file-parsers/zip-guard'
@@ -40,8 +41,7 @@ export class PptxParser implements FileParser {
 
       let parseOfficeAsync
       try {
-        const officeParser = await import('officeparser')
-        parseOfficeAsync = officeParser.parseOfficeAsync
+        parseOfficeAsync = await loadParseOfficeAsync()
       } catch (importError) {
         logger.warn('officeparser not available, using fallback extraction')
         return this.fallbackExtraction(buffer)