Reduce low risk duplication (#79)

* clean up helpers

* shared in it's own top level folder

* workspaces setup

* build fix

* disable workspaces?

* run ci

* rename job-flow to gradcracker

* optional dependencies

* formatting?

* more optional modules

* allow post install runs

* node bump

* remove post install

* add optionals

* add more

* formatting

* comments, but im unsure

* run typescript DIRECTLY

* better build

* camoufox simplification

* lint

* build process doesn't exist

* build fix

* lockfile

* type check everything, build only for client

* rename steps correctly

* import from package!

* fix formatting

* don't fetch twice

* fix concern

extractors/gradcracker/Dockerfile

@@ -7,8 +7,9 @@ FROM apify/actor-node-playwright-chrome:20-1.50.1 AS builder
 # to speed up the build using Docker layer cache.
 COPY --chown=myuser package*.json ./
 
-# Install all dependencies. Don't audit to speed up the installation.
-RUN npm install --include=dev --audit=false
+# Install all dependencies with cache mount for faster rebuilds
+RUN --mount=type=cache,target=/root/.npm \
+    npm install --include=dev --audit=false --progress=false
 
 # Next, copy the source files using the user set
 # in the base image.
@@ -33,14 +34,16 @@ ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=0
 # Install NPM packages, skip optional and development dependencies to
 # keep the image small. Avoid logging too much and print the dependency
 # tree for debugging
-RUN npm --quiet set progress=false \
-    && npm install --omit=dev \
+RUN --mount=type=cache,target=/root/.npm \
+    npm --quiet set progress=false \
+    && npm install --omit=dev --progress=false \
     && echo "Installed NPM packages:" \
     && (npm list --omit=dev --all || true) \
     && echo "Node.js version:" \
     && node --version \
     && echo "NPM version:" \
-    && npm --version
+    && npm --version \
+    && npm run get-binaries
 
 # Next, copy the remaining files and directories with the source code.
 # Since we do this after NPM install, quick build will be really fast

extractors/gradcracker/package.json

@@ -1,29 +1,30 @@
 {
-  "name": "job-flow",
+  "name": "gradcracker-extractor",
   "version": "0.0.1",
   "type": "module",
   "description": "This is an example of a Crawlee project.",
   "dependencies": {
     "camoufox-js": "^0.8.0",
     "crawlee": "^3.0.0",
-    "playwright": "*"
+    "playwright": "*",
+    "tsx": "^4.4.0"
   },
   "devDependencies": {
     "@apify/tsconfig": "^0.1.0",
     "@types/fs-extra": "^11",
     "@types/node": "^24.0.0",
     "fs-extra": "^11.3.0",
-    "tsx": "^4.4.0",
     "typescript": "~5.9.0"
   },
+  "optionalDependencies": {
+    "impit-linux-x64-gnu": "^0.1.0"
+  },
   "scripts": {
-    "start": "npm run start:dev",
-    "start:prod": "node dist/main.js",
+    "start": "tsx src/main.ts",
     "start:dev": "tsx src/main.ts",
-    "build": "tsc",
+    "check:types": "tsc --noEmit",
     "test": "echo \"Error: oops, the actor has no tests yet, sad!\" && exit 1",
-    "get-binaries": "camoufox-js fetch",
-    "postinstall": "npm run get-binaries"
+    "get-binaries": "camoufox-js fetch"
   },
   "author": "It's not you it's me",
   "license": "ISC"

extractors/ukvisajobs/package.json

@@ -3,24 +3,26 @@
   "version": "0.0.1",
   "type": "module",
   "description": "UK Visa Jobs extractor - fetches job listings that may sponsor work visas",
-  "main": "dist/main.js",
+  "main": "src/main.ts",
   "dependencies": {
     "camoufox-js": "^0.8.0",
-    "playwright": "^1.57.0"
+    "playwright": "^1.57.0",
+    "tsx": "^4.4.0",
+    "job-ops-shared": "^1.0.0"
   },
   "devDependencies": {
     "@apify/tsconfig": "^0.1.0",
     "@types/node": "^24.0.0",
-    "tsx": "^4.4.0",
     "typescript": "~5.9.0"
   },
+  "optionalDependencies": {
+    "impit-linux-x64-gnu": "^0.1.0"
+  },
   "scripts": {
-    "start": "npm run start:dev",
-    "start:prod": "node dist/main.js",
+    "start": "tsx src/main.ts",
     "start:dev": "tsx src/main.ts",
-    "build": "tsc",
-    "get-binaries": "camoufox-js fetch",
-    "postinstall": "npm run get-binaries"
+    "check:types": "tsc --noEmit",
+    "get-binaries": "camoufox-js fetch"
   },
   "author": "",
   "license": "ISC"

extractors/ukvisajobs/src/main.ts

@@ -1,4 +1,4 @@
-/**
+/**
  * UK Visa Jobs Extractor
  *
  * Fetches job listings from my.ukvisajobs.com that may sponsor work visas.
@@ -16,6 +16,10 @@
 import { mkdir, readFile, writeFile } from "node:fs/promises";
 import { dirname, join } from "node:path";
 import { fileURLToPath } from "node:url";
+import {
+  toNumberOrNull,
+  toStringOrNull,
+} from "job-ops-shared/utils/type-conversion";
 import type { Request } from "playwright";
 
 const __dirname = dirname(fileURLToPath(import.meta.url));
@@ -103,29 +107,6 @@ class UkVisaJobsAuthError extends Error {
   }
 }
 
-function toStringOrNull(value: unknown): string | null {
-  if (value === null || value === undefined) return null;
-  if (typeof value === "string") {
-    const trimmed = value.trim();
-    return trimmed.length > 0 ? trimmed : null;
-  }
-  if (typeof value === "number" || typeof value === "boolean")
-    return String(value);
-  return null;
-}
-
-function toNumberOrNull(value: unknown): number | null {
-  if (value === null || value === undefined) return null;
-  if (typeof value === "number") return Number.isFinite(value) ? value : null;
-  if (typeof value === "string") {
-    const trimmed = value.trim();
-    if (!trimmed) return null;
-    const parsed = Number(trimmed);
-    return Number.isFinite(parsed) ? parsed : null;
-  }
-  return null;
-}
-
 async function fetchPage(
   pageNo: number,
   session: UkVisaJobsAuthSession,

extractors/ukvisajobs/tsconfig.build.json

@@ -0,0 +1,8 @@
+{
+  "extends": "./tsconfig.json",
+  "compilerOptions": {
+    "paths": {
+      "@shared/*": ["../../shared/dist/*"]
+    }
+  }
+}

extractors/ukvisajobs/tsconfig.json

@@ -6,7 +6,11 @@
     "target": "ES2022",
     "outDir": "dist",
     "noUnusedLocals": false,
-    "lib": ["DOM"]
+    "lib": ["DOM"],
+    "baseUrl": ".",
+    "paths": {
+      "@shared/*": ["../../shared/src/*"]
+    }
   },
   "include": ["./src/**/*"]
 }