feat(#72): provide command line interface

PDFMergerBase.js

@@ -1,6 +1,6 @@
 import { PDFDocument } from 'pdf-lib'
 
-import { parsePagesString } from './parsePagesString'
+import { parsePagesString } from './parsePagesString.js'
 
 /**
  * @typedef {Object} Metadata

README.md

@@ -14,8 +14,33 @@ This library is inspired by the [PHP library PDFMerger](https://github.com/myoky
 
 `npm install --save pdf-merger-js`
 
+of global installation if you want to use the cli tool:
+
+`npm install -g pdf-merger-js`
+
 ## Usage
 
+### CLI
+
+```
+Options:
+  -V, --version              output the version number
+  -o, --output <outputFile>  Merged PDF output file path
+  -v, --verbose              Print verbose output
+  -s, --silent               do not print any output to stdout. Overwrites --verbose
+  -h, --help                 display help for command
+```
+
+#### Example calls
+
+Merge pages 1-2 from the first input with pages 1,2 and 5-7 from the second pdf document:
+
+`pdf-merge --output ./merged.pdf ./input1.pdf#1-2 ./input2.pdf#1,2,5-7`
+
+Get two pdf files from the an url and merge the first one with pages 2-3 from the second one:
+
+`pdf-merge --verbose --output ./sample.pdf Testfile.pdf https://pdfobject.com/pdf/sample.pdf https://upload.wikimedia.org/wikipedia/commons/1/13/Example.pdf#2-3`
+
 ### node.js
 
 The node.js version has the following export functions:

cli.js

@@ -0,0 +1,68 @@
+#!/usr/bin/env node
+
+import fs from 'fs-extra'
+import { program } from 'commander'
+
+import PDFMerger from './index.js'
+import { parsePagesString } from './parsePagesString.js'
+
+function main (packageJson) {
+  program
+    .version(packageJson.version)
+    .description(packageJson.description)
+    .option('-o, --output <outputFile>', 'Merged PDF output file path')
+    .option('-v, --verbose', 'Print verbose output')
+    .option('-s, --silent', 'do not print any output to stdout. Overwrites --verbose')
+    .arguments('<inputFiles...>')
+    .action(async (inputFiles, cmd) => {
+      const outputFile = cmd.output
+      const verbose = cmd.verbose && !cmd.silent
+      const silent = cmd.silent
+
+      if (!outputFile) {
+        console.error('Please provide an output file using the --output flag')
+        return
+      }
+
+      if (!inputFiles || !inputFiles.length) {
+        console.error('Please provide at least one input file')
+        return
+      }
+
+      try {
+        const merger = new PDFMerger()
+
+        for (const inputFile of inputFiles) {
+          const [filePath, pagesString] = inputFile.split('#')
+          const pages = pagesString ? parsePagesString(pagesString) : null
+          if (verbose) {
+            if (pages && pages.length) {
+              console.log(`adding page${pages.length > 1 ? 's' : ''} ${pages.join(',')} from ${filePath} to output...`)
+            } else {
+              console.log(`adding all pages from ${filePath} to output...`)
+            }
+          }
+          await merger.add(filePath, pages)
+        }
+
+        if (verbose) {
+          console.log(`Saving merged output to ${outputFile}...`)
+        }
+
+        await merger.save(outputFile)
+
+        if (!silent) {
+          console.log(`Merged pages successfully into ${outputFile}`)
+        }
+      } catch (error) {
+        console.error('An error occurred while merging the PDFs:', error)
+      }
+    })
+
+  program.parse(process.argv)
+}
+
+(() => {
+  const packageJson = fs.readJsonSync(new URL('./package.json', import.meta.url))
+  main(packageJson)
+})()

package.json

@@ -9,6 +9,9 @@
   "main": "./index.js",
   "types": "./index.d.ts",
   "browser": "./browser.js",
+  "bin": {
+    "pdf-merge": "cli.js"
+  },
   "scripts": {
     "standard": "standard",
     "standard:fix": "standard --fix",
@@ -29,6 +32,7 @@
   "author": "nbesli",
   "license": "MIT",
   "dependencies": {
+    "commander": "^11.1.0",
     "pdf-lib": "^1.17.1"
   },
   "devDependencies": {

test/cli.test.js

@@ -0,0 +1,109 @@
+import path from 'path'
+import fs from 'fs-extra'
+import util from 'util'
+import { exec } from 'child_process'
+import { jest } from '@jest/globals'
+import pdfDiff from 'pdf-diff'
+
+const asyncExec = util.promisify(exec)
+
+const __dirname = path.dirname(new URL(import.meta.url).pathname)
+const FIXTURES_DIR = path.join(__dirname, 'fixtures')
+const TMP_DIR = path.join(__dirname, 'tmp')
+
+jest.setTimeout(10000)
+
+async function mergePDFsCli (outputFile, inputFiles) {
+  const { stdout, stderr } = await asyncExec(`node ./cli.js --output ${outputFile} ${inputFiles.join(' ')}`)
+  return { stdout, stderr }
+}
+
+describe('issues', () => {
+  beforeAll(async () => {
+    await fs.ensureDir(TMP_DIR)
+  })
+
+  test('should merge two pdfs', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, 'Testfile_AB.pdf'), [
+      path.join(FIXTURES_DIR, 'Testfile_A.pdf'),
+      path.join(FIXTURES_DIR, 'Testfile_B.pdf')
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, 'Testfile_AB.pdf'),
+      path.join(TMP_DIR, 'Testfile_AB.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  test('should merge two pdfs from URL', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, 'Testfile_AB.pdf'), [
+      'https://github.com/nbesli/pdf-merger-js/raw/master/test/fixtures/Testfile_A.pdf',
+      'https://github.com/nbesli/pdf-merger-js/raw/master/test/fixtures/Testfile_B.pdf'
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, 'Testfile_AB.pdf'),
+      path.join(TMP_DIR, 'Testfile_AB.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  test('combine single pages from multiple pdfs', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, '2468.pdf'), [
+      path.join(FIXTURES_DIR, '123456789.pdf#2'),
+      path.join(FIXTURES_DIR, '123456789.pdf#4'),
+      path.join(FIXTURES_DIR, '123456789.pdf#6'),
+      path.join(FIXTURES_DIR, '123456789.pdf#8')
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, '2468.pdf'),
+      path.join(TMP_DIR, '2468.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  test('combine pages from multiple pdfs (list)', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, '2468.pdf'), [
+      path.join(FIXTURES_DIR, '123456789.pdf#2,4'),
+      path.join(FIXTURES_DIR, '123456789.pdf#6,8')
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, '2468.pdf'),
+      path.join(TMP_DIR, '2468.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  test('combine pages from multipel pdfs (rang)', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, '123456789.pdf'), [
+      path.join(FIXTURES_DIR, '123456789.pdf#1-5'),
+      path.join(FIXTURES_DIR, '123456789.pdf#6-9')
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, '123456789.pdf'),
+      path.join(TMP_DIR, '123456789.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  test('combine pages from multipel pdfs (combined list and range)', async () => {
+    await mergePDFsCli(path.join(TMP_DIR, '123456789.pdf'), [
+      path.join(FIXTURES_DIR, '123456789.pdf#1,2,3-4'),
+      path.join(FIXTURES_DIR, '123456789.pdf#5-7,8to9')
+    ])
+    const diff = await pdfDiff(
+      path.join(FIXTURES_DIR, '123456789.pdf'),
+      path.join(TMP_DIR, '123456789.pdf')
+    )
+    expect(diff).toBeFalsy()
+  })
+
+  afterEach(async () => {
+    for (const file of await fs.readdir(TMP_DIR)) {
+      await fs.unlink(path.join(TMP_DIR, file))
+    }
+  })
+
+  afterAll(async () => {
+    await fs.remove(TMP_DIR)
+  })
+})