Add new plugin to handle pdf files (#8817)

Adds support for PDF as a content source.

Related to #8711

packages/gatsby-transformer-pdf/.babelrc

@@ -0,0 +1,5 @@
+{
+  "presets": [
+    ["../../.babel-preset.js"]
+  ]
+}

packages/gatsby-transformer-pdf/.gitignore

@@ -0,0 +1,2 @@
+/*.js
+!index.js

packages/gatsby-transformer-pdf/.npmignore

@@ -0,0 +1,34 @@
+# Logs
+logs
+*.log
+
+# Runtime data
+pids
+*.pid
+*.seed
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+
+# Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (http://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directory
+# https://www.npmjs.org/doc/misc/npm-faq.html#should-i-check-my-node_modules-folder-into-git
+node_modules
+*.un~
+yarn.lock
+src
+flow-typed
+coverage
+decls
+examples

packages/gatsby-transformer-pdf/README.md

@@ -0,0 +1,58 @@
+# gatsby-transformer-pdf
+
+Use [pdf2Json](`https://github.com/modesty/pdf2json`) to extract textual content of pdf files.
+
+## Install
+
+`npm install --save gatsby-transformer-pdf`
+
+You also need to have gatsby-source-filesystem installed and configured so it points to your files.
+
+## How to use
+
+```javascript
+// In your gatsby-config.js
+module.exports = {
+  plugins: [
+    {
+      resolve: `gatsby-source-filesystem`,
+      options: {
+        name: `data`,
+        path: `${__dirname}/src/data/`,
+      },
+    },
+    `gatsby-transformer-pdf`,
+  ],
+}
+```
+
+Then you'll be able to query the textual content of your pdfs files like:
+
+```javascript
+{
+  allPdf {
+    edges {
+      node {
+        content
+      }
+    }
+  }
+}
+```
+Which would return:
+
+```javascript
+{
+  "data": {
+    "allPdf": {
+      "edges": [
+        {
+          "node": {
+            "content": "1 Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed vel purus id tortor \r\neleifend vulputate. Integer interdum ultricies ligula, nec mattis lorem viverra ac. \r\n"
+          }
+        }
+      ]
+    }
+  }
+}
+```

packages/gatsby-transformer-pdf/index.js

@@ -0,0 +1 @@
+// noop

packages/gatsby-transformer-pdf/package.json

@@ -0,0 +1,36 @@
+{
+  "name": "gatsby-transformer-pdf",
+  "description": "Gatsby transformer plugin for pdf",
+  "version": "1.0.9",
+  "author": "Alex Munoz <almunozdo@gmail.com>",
+  "bugs": {
+    "url": "https://github.com/gatsbyjs/gatsby/issues"
+  },
+  "dependencies": {
+    "@babel/runtime": "^7.0.0",
+    "bluebird": "^3.5.2",
+    "pdf2json": "^1.1.7"
+  },
+  "devDependencies": {
+    "@babel/cli": "^7.0.0",
+    "@babel/core": "^7.0.0",
+    "cross-env": "^5.1.4"
+  },
+  "homepage": "https://github.com/gatsbyjs/gatsby/tree/master/packages/gatsby-transformer-pdf#readme",
+  "keywords": [
+    "gatsby",
+    "gatsby-plugin",
+    "pdf"
+  ],
+  "license": "MIT",
+  "main": "index.js",
+  "peerDependencies": {
+    "gatsby": ">=2.0.0"
+  },
+  "repository": "https://github.com/gatsbyjs/gatsby/tree/master/packages/gatsby-transformer-pdf",
+  "scripts": {
+    "build": "babel src --out-dir . --ignore **/__tests__",
+    "prepare": "cross-env NODE_ENV=production npm run build",
+    "watch": "babel -w src --out-dir . --ignore **/__tests__"
+  }
+}

packages/gatsby-transformer-pdf/src/gatsby-node.js

@@ -0,0 +1,49 @@
+const Promise = require(`bluebird`)
+const PDFParser = require(`pdf2json`)
+
+const convertToJson = path =>
+  new Promise((res, rej) => {
+    const pdfParser = new PDFParser(this, 1)
+    pdfParser.loadPDF(path)
+    pdfParser
+      .on(`pdfParser_dataReady`, pdfData => {
+        res(pdfParser.getRawTextContent())
+      })
+      .on(`pdfParser_dataError`, errData => {
+        rej(`PDF to JSON conversion failed!`)
+      })
+  })
+
+async function onCreateNode({
+  node,
+  actions,
+  loadNodeContent,
+  createNodeId,
+  createContentDigest,
+}) {
+  const { createNode, createParentChildLink } = actions
+
+  // Filter out non-pdf content
+  if (node.extension !== `pdf`) {
+    return
+  }
+
+  let parsedContent = await convertToJson(node.absolutePath)
+
+  const pdfNode = {
+    id: createNodeId(`${node.id} >>> ${node.extension}`),
+    children: [],
+    parent: node.id,
+    internal: {
+      type: `pdf`,
+    },
+  }
+
+  pdfNode.content = parsedContent
+  pdfNode.internal.contentDigest = createContentDigest(pdfNode)
+
+  createNode(pdfNode)
+  createParentChildLink({ parent: node, child: pdfNode })
+}
+
+exports.onCreateNode = onCreateNode