Port to typescript

vHanda · Sep 10, 2018 · 5d345d9 · 5d345d9
1 parent c80a8c3
commit 5d345d9
Show file tree

Hide file tree

Showing 12 changed files with 230 additions and 214 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1 +1,2 @@
 node_modules
+dist
diff --git a/README.MD b/README.MD
@@ -1,3 +1,6 @@
+[![code style: prettier](https://img.shields.io/badge/code_style-prettier-ff69b4.svg?style=flat-square)](https://github.com/prettier/prettier)
+
+
 This is a tool which converts the Google Keep archive to markdown documents with YAML front matter. The Google Keep archive can be obtained from the Google Takeout page.
 
 https://www.google.com/settings/takeout/custom/keep
diff --git a/main.js b/main.js
diff --git a/package.json b/package.json
@@ -4,7 +4,7 @@
   "description": "This is a tool which converts the Google Keep archive to markdown documents with YAML front matter. The Google Keep archive can be obtained from the Google Takeout page.",
   "main": "index.js",
   "scripts": {
-    "test": "./node_modules/.bin/mocha -u tdd ./"
+    "test": "./node_modules/.bin/mocha -u tdd ./dist/*.test.js"
   },
   "author": "",
   "dependencies": {
@@ -16,6 +16,9 @@
     "uuid": "^3.0.1"
   },
   "devDependencies": {
-    "chai": "^3.5.0"
+    "@types/mocha": "^5.2.5",
+    "@types/node": "^10.9.4",
+    "chai": "^3.5.0",
+    "typescript": "^3.0.3"
   }
 }
diff --git a/parser.js b/parser.js
diff --git a/parser.test.js b/parser.test.js
diff --git a/serializer.js b/serializer.js
diff --git a/src/main.ts b/src/main.ts
@@ -0,0 +1,39 @@
+#!/usr/bin/env node
+
+var fs = require("fs");
+var parser = require("./parser.js");
+var serializer = require("./serializer.js");
+
+// TODO: parse argv and get directory file list
+//       parse output
+//
+
+// Take notes and then convert it into markdown
+//
+// .content
+// -> This needs to be converted to markdown
+//    -> listitem
+//
+
+if (process.argv.length != 4) {
+  console.log("Usage main.js inputDir outputDir");
+  process.exit(1);
+}
+
+var inputDir = process.argv[2];
+var outputDir = process.argv[3];
+
+var convert = function(filePath, outputDir) {
+  var data = fs.readFileSync(filePath);
+  var note = parser(data);
+  var output = serializer.serialize(note);
+
+  output.forEach(d => {
+    console.log(filePath, d[0]);
+    fs.writeFileSync(outputDir + "/" + d[0], d[1]);
+  });
+};
+
+var files = fs.readdirSync(inputDir);
+files = files.filter(t => t.endsWith(".html"));
+files.forEach(filePath => convert(inputDir + "/" + filePath, outputDir));
diff --git a/src/parser.test.ts b/src/parser.test.ts
@@ -0,0 +1,27 @@
+var assert = require("chai").assert;
+import { parse } from "./parser";
+
+suite("Parser", function() {
+  test("Should parse some basic info", function() {
+    var data = `
+		<html><body><div class="note DEFAULT"><div class="heading">
+		21 Jun 2016, 22:39:47</div>
+		<div class="title">Ll</div>
+		<div class="content">Hearts of darkness<br>Water ship down<br>The Dubliners<br><br></div>
+		<div class="labels"><span class="label">Reading List</span><span class="label">Another Tag</span></div>
+		</div></body></html>
+		`;
+
+    console.log(parse);
+    var note = parse(data);
+    assert.deepEqual(note.title, "Ll");
+    // FIXME: Is the extra space really required?
+    assert.deepEqual(
+      note.content,
+      "Hearts of darkness  \nWater ship down  \nThe Dubliners"
+    );
+    assert.deepEqual(note.tags, ["Reading List", "Another Tag"]);
+    assert.notOk(note.archived);
+    assert.deepEqual(note.date, "2016-06-21T20:39:47.000Z");
+  });
+});
diff --git a/src/parser.ts b/src/parser.ts
@@ -0,0 +1,78 @@
+var cheerio = require("cheerio");
+var toMarkdown = require("to-markdown");
+var moment = require("moment");
+
+function getImages(node) {
+  var images = [];
+  if (node instanceof Array) {
+    node.forEach(child => {
+      images = images.concat(getImages(child));
+    });
+    return images;
+  }
+
+  if (node.name == "img") {
+    var img = node.attribs.src;
+    images.push(img);
+    return images;
+  }
+
+  if (!node.children) return [];
+
+  node.children.forEach(child => {
+    images = images.concat(getImages(child));
+  });
+  return images;
+}
+
+var converter = {
+  filter: "div",
+  /*
+    filter: function(node) {
+        return node.className.indexOf('listitem') != -1;
+    },
+    */
+  replacement: function(innerHTML, node) {
+    return innerHTML + " ";
+  }
+};
+
+export interface Note {
+    content: string;
+    title: string;
+    date: string;
+    archived: boolean;
+    tags: string[];
+    attachments: string[];
+}
+
+export function parse(data) {
+  var $ = cheerio.load(data);
+
+  var note = {} as Note;
+  note.content = $(".content").html();
+  note.content = toMarkdown(note.content, { converters: [converter] }).trim();
+
+  // FIXME: What about timezone?
+  note.date = $(".heading")
+    .text()
+    .trim();
+  note.date = moment(note.date).toISOString();
+
+  note.title = $(".title")
+    .text()
+    .trim();
+  note.archived = $.contains(".archived");
+
+  note.tags = $("span.label").toArray().map(function(elem) {
+    if (!elem.children) {
+      return null;
+    }
+    return elem.children[0].data;
+  });
+
+  var attachments = $("div.attachments").toArray();
+  note.attachments = getImages(attachments);
+
+  return note;
+}