[#60,tasks][m]: implement extract markdown tasks i.e. - [ ].

* extract tasks (find all list items and then only those with checked property or not)
* fix linting
* Add changeset
* Run format

.changeset/five-dots-speak.md

@@ -0,0 +1,6 @@
+---
+"mddb": minor
+---
+
+[ #60 , extract tasks ]
+Add tasks extraction from files. e.g `- [ ] task`

__mocks__/content/index.mdx

@@ -6,3 +6,9 @@ tags: tag1, tag2, tag3
 # Welcome
 
 [link](blog0.mdx)
+
+- [] uncompleted task 1
+- [ ] uncompleted task 2
+
+- [x] completed task 1
+- [X] completed task 2

src/lib/databaseUtils.ts

@@ -1,11 +1,5 @@
 import { Knex } from "knex";
-import {
-  MddbFile,
-  MddbTag,
-  MddbLink,
-  MddbFileTag,
-  File,
-} from "./schema.js";
+import { MddbFile, MddbTag, MddbLink, MddbFileTag, File } from "./schema.js";
 import path from "path";
 import { WikiLink } from "./parseFile.js";
 

src/lib/parseFile.ts

@@ -24,6 +24,9 @@ export function parseFile(source: string, options?: ParsingOptions) {
   // Links
   const links = extractWikiLinks(ast, options);
 
+  const tasks = extractTasks(ast);
+  metadata.tasks = tasks;
+
   return {
     metadata,
     links,
@@ -155,6 +158,40 @@ export const extractWikiLinks = (ast: Root, options?: ParsingOptions) => {
   return wikiLinks;
 };
 
+export interface Task {
+  description: string;
+  checked: boolean;
+}
+
+export const extractTasks = (ast: Root) => {
+  const nodes = selectAll("*", ast);
+  const tasks: Task[] = [];
+  nodes.map((node: any) => {
+    if (node.type === "listItem") {
+      const description = recursivelyExtractText(node).trim();
+      const checked = node.checked;
+      if (checked !== null && checked !== undefined) {
+        tasks.push({
+          description,
+          checked,
+        });
+      }
+    }
+  });
+
+  return tasks;
+};
+
+function recursivelyExtractText(node: any) {
+  if (node.value) {
+    return node.value;
+  } else if (node.children) {
+    return node.children.map(recursivelyExtractText).join(" ");
+  } else {
+    return "";
+  }
+}
+
 // links = extractWikiLinks({
 //   source,
 //   // TODO pass slug instead of file path as hrefs/srcs are sluggified too

src/tests/extractTasks.spec.ts

@@ -0,0 +1,72 @@
+import { extractTasks, processAST } from "../lib/parseFile";
+
+const getTasksFromSource = (source: string) => {
+  const ast = processAST(source, {});
+  const tasks = extractTasks(ast);
+  return tasks;
+};
+
+describe("extractTasks", () => {
+  test("should extract uncompleted tasks from body", () => {
+    const tasks = getTasksFromSource(
+      "- [] uncompleted task 1\n- [ ] uncompleted task 2"
+    );
+    const expectedTasks = [
+      { description: "uncompleted task 2", checked: false },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+
+  test("should extract completed tasks from body", () => {
+    const tasks = getTasksFromSource(
+      "- [x] completed task 1\n- [X] completed task 2"
+    );
+    const expectedTasks = [
+      { description: "completed task 1", checked: true },
+      { description: "completed task 2", checked: true },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+
+  test("should handle mixed completed and uncompleted tasks", () => {
+    const tasks = getTasksFromSource(
+      "- [x] completed task\n- [ ] uncompleted task"
+    );
+    const expectedTasks = [
+      { description: "completed task", checked: true },
+      { description: "uncompleted task", checked: false },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+
+  test("should handle tasks with leading and trailing spaces", () => {
+    const tasks = getTasksFromSource(
+      "- [x]  completed task  \n- [ ]  uncompleted task  "
+    );
+    const expectedTasks = [
+      { description: "completed task", checked: true },
+      { description: "uncompleted task", checked: false },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+
+  test("should handle tasks with different checkbox formats", () => {
+    const tasks = getTasksFromSource(
+      "- [x] task 1\n- [X] task 2\n- [ ] task 3"
+    );
+    const expectedTasks = [
+      { description: "task 1", checked: true },
+      { description: "task 2", checked: true },
+      { description: "task 3", checked: false },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+
+  test("should handle tasks with special characters", () => {
+    const tasks = getTasksFromSource("- [x] task with $pecial character$");
+    const expectedTasks = [
+      { description: "task with $pecial character$", checked: true },
+    ];
+    expect(tasks).toEqual(expectedTasks);
+  });
+});

src/tests/parseFile.spec.ts

@@ -10,6 +10,8 @@ tags: a, b, c
 [[blog/Some Other Link]]
 [[blog/Some Other Link|Page Alias]]
 ![[Some Image.png]]
+- [ ] uncompleted task
+- [x] completed task
 `;
 
 describe("parseFile", () => {
@@ -18,6 +20,10 @@ describe("parseFile", () => {
       title: "Hello World",
       authors: ["John Doe", "Jane Doe"],
       tags: ["a", "b", "c"],
+      tasks: [
+        { description: "uncompleted task", checked: false },
+        { description: "completed task", checked: true },
+      ],
     };
     const expectedLinks = [
       {
@@ -63,6 +69,10 @@ describe("parseFile", () => {
       title: "Hello World",
       authors: ["John Doe", "Jane Doe"],
       tags: ["a", "b", "c"],
+      tasks: [
+        { description: "uncompleted task", checked: false },
+        { description: "completed task", checked: true },
+      ],
     };
     const expectedLinks = [
       {

src/tests/process.spec.ts

@@ -21,6 +21,20 @@ describe("Can parse a file and get file info", () => {
     expect(fileInfo.metadata).toEqual({
       title: "Homepage",
       tags: ["tag1", "tag2", "tag3"],
+      tasks: [
+        {
+          checked: false,
+          description: "uncompleted task 2",
+        },
+        {
+          checked: true,
+          description: "completed task 1",
+        },
+        {
+          checked: true,
+          description: "completed task 2",
+        },
+      ],
     });
     expect(fileInfo.links).toEqual([
       {