Merge pull request #103 from neutron0831/chapter/03/regular-expression

Chapter 3: Regular Expression

Author: neutron0831

.github/workflows/test.yml

@@ -14,6 +14,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
       - uses: actions/setup-node@v3
         with:
           node-version: latest
@@ -26,8 +28,7 @@ jobs:
       - name: Get pnpm store directory
         id: pnpm-cache
         shell: bash
-        run: |
-          echo "STORE_PATH=$(pnpm store path)" >> $GITHUB_OUTPUT
+        run: echo "STORE_PATH=$(pnpm store path)" >> $GITHUB_OUTPUT
       - uses: actions/cache@v3
         name: Setup pnpm cache
         with:
@@ -38,4 +39,8 @@ jobs:
       - name: Install dependencies
         run: pnpm install
       - name: Test
-        run: pnpm test
+        env:
+          NODE_OPTIONS: --max_old_space_size=6144
+        run: |
+          TEST_FILES=$(git diff --diff-filter=ACMR --name-only origin/${{ github.base_ref }}...origin/${{ github.head_ref }} **/*.test.ts)
+          pnpm vitest --silent --run $TEST_FILES

.lintstagedrc.js

@@ -1,5 +1,7 @@
 module.exports = {
   '*.{js,ts,vue}': ['eslint --fix'],
   '*.{js,ts,json}': ['prettier --write'],
-  '*.test.{js,ts}': ['vitest --silent --run'],
+  '*.test.{js,ts}': [
+    'cross-env NODE_OPTIONS="--max-old-space-size=6144" vitest --silent --run',
+  ],
 }

CHANGELOG.md

@@ -1,5 +1,50 @@
 # Changelog
 
+<a name="0.3.0"></a>
+## [v0.3.0](https://github.com/neutron0831/nlp100-ts/compare/v0.2.0...v0.3.0) (2023-04-19)
+
+### Added
+
+- 👷‍♂️ Run `test.yml` only for untested tests [[82a2fa9](https://github.com/neutron0831/nlp100-ts/commit/82a2fa9)]
+- ✅ Add Exercise 29 test ([#29](https://github.com/neutron0831/nlp100-ts/issues/29)) [[23a5be3](https://github.com/neutron0831/nlp100-ts/commit/23a5be3)]
+- ✨ Add Exercise 29 ([#29](https://github.com/neutron0831/nlp100-ts/issues/29)) [[3fd8fc1](https://github.com/neutron0831/nlp100-ts/commit/3fd8fc1)]
+- ✅ Add Exercise 28 test ([#28](https://github.com/neutron0831/nlp100-ts/issues/28)) [[3c48f58](https://github.com/neutron0831/nlp100-ts/commit/3c48f58)]
+- ✨ Add Exercise 28 ([#28](https://github.com/neutron0831/nlp100-ts/issues/28)) [[ab7468e](https://github.com/neutron0831/nlp100-ts/commit/ab7468e)]
+- ✅ Add Exercise 27 test ([#27](https://github.com/neutron0831/nlp100-ts/issues/27)) [[c4ad8bc](https://github.com/neutron0831/nlp100-ts/commit/c4ad8bc)]
+- ✨ Add Exercise 27 ([#27](https://github.com/neutron0831/nlp100-ts/issues/27)) [[f7812cc](https://github.com/neutron0831/nlp100-ts/commit/f7812cc)]
+- ✅ Add Exercise 26 test ([#26](https://github.com/neutron0831/nlp100-ts/issues/26)) [[56ae4d9](https://github.com/neutron0831/nlp100-ts/commit/56ae4d9)]
+- ✨ Add Exercise 26 ([#26](https://github.com/neutron0831/nlp100-ts/issues/26)) [[f0cd6de](https://github.com/neutron0831/nlp100-ts/commit/f0cd6de)]
+- ✅ Add Exercise 25 test ([#25](https://github.com/neutron0831/nlp100-ts/issues/25)) [[62a0ccc](https://github.com/neutron0831/nlp100-ts/commit/62a0ccc)]
+- ✨ Add Exercise 25 ([#25](https://github.com/neutron0831/nlp100-ts/issues/25)) [[cd9d727](https://github.com/neutron0831/nlp100-ts/commit/cd9d727)]
+- ✅ Add Exercise 24 test ([#24](https://github.com/neutron0831/nlp100-ts/issues/24)) [[c87677a](https://github.com/neutron0831/nlp100-ts/commit/c87677a)]
+- ✨ Add Exercise 24 ([#24](https://github.com/neutron0831/nlp100-ts/issues/24)) [[5cae007](https://github.com/neutron0831/nlp100-ts/commit/5cae007)]
+- ✅ Add Exercise 23 test ([#23](https://github.com/neutron0831/nlp100-ts/issues/23)) [[c49d1c1](https://github.com/neutron0831/nlp100-ts/commit/c49d1c1)]
+- ✨ Add Exercise 23 ([#23](https://github.com/neutron0831/nlp100-ts/issues/23)) [[3622d9c](https://github.com/neutron0831/nlp100-ts/commit/3622d9c)]
+- ✅ Add Exercise 22 test ([#22](https://github.com/neutron0831/nlp100-ts/issues/22)) [[64df6f2](https://github.com/neutron0831/nlp100-ts/commit/64df6f2)]
+- ✨ Add Exercise 22 ([#22](https://github.com/neutron0831/nlp100-ts/issues/22)) [[6a873b3](https://github.com/neutron0831/nlp100-ts/commit/6a873b3)]
+- ✅ Add Exercise 21 test ([#21](https://github.com/neutron0831/nlp100-ts/issues/21)) [[d967eed](https://github.com/neutron0831/nlp100-ts/commit/d967eed)]
+- ✨ Add Exercise 21 ([#21](https://github.com/neutron0831/nlp100-ts/issues/21)) [[908322f](https://github.com/neutron0831/nlp100-ts/commit/908322f)]
+- ✅ Add Exercise 20 test ([#20](https://github.com/neutron0831/nlp100-ts/issues/20)) [[714ba20](https://github.com/neutron0831/nlp100-ts/commit/714ba20)]
+- ✨ Add Exercise 20 ([#20](https://github.com/neutron0831/nlp100-ts/issues/20)) [[99f7ac9](https://github.com/neutron0831/nlp100-ts/commit/99f7ac9)]
+- ✨ Update `AttachmentPanel.vue` [[0bc47ad](https://github.com/neutron0831/nlp100-ts/commit/0bc47ad)]
+
+### Changed
+
+- 📱 Wrap words when the output is long [[85e3e48](https://github.com/neutron0831/nlp100-ts/commit/85e3e48)]
+- 🚸 Scroll to exercises after rendering [[7d1f15a](https://github.com/neutron0831/nlp100-ts/commit/7d1f15a)]
+- 🍱 Add `enwiki-country.json.gz` [[72bde9e](https://github.com/neutron0831/nlp100-ts/commit/72bde9e)]
+- 👽 Update `pnpm-lock.yaml` [[88373fd](https://github.com/neutron0831/nlp100-ts/commit/88373fd)]
+
+### Fixed
+
+- 🚑 Update a personal access token [[5abb560](https://github.com/neutron0831/nlp100-ts/commit/5abb560)]
+
+### Miscellaneous
+
+- 📝 Add `README.md` of Chapter 3 [[e688799](https://github.com/neutron0831/nlp100-ts/commit/e688799)]
+- 🩹 Add `?url` suffix [[3ff2c0a](https://github.com/neutron0831/nlp100-ts/commit/3ff2c0a)]
+
+
 <a name="0.2.0"></a>
 ## [v0.2.0](https://github.com/neutron0831/nlp100-ts/compare/v0.1.1...v0.2.0) (2023-03-26)
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "nlp100-ts",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "description": "NLP 100 Exercise 2020 (Rev 2) in TypeScript",
   "keywords": [
     "nlp100",
@@ -9,13 +9,16 @@
   "license": "MIT",
   "author": "NEUTRON <neutron0831@gmail.com> (https://github.com/neutron0831)",
   "homepage": "https://nlp100-ts.netlify.app",
+  "config": {
+    "MAX_OLD_SPACE_SIZE": "--max-old-space-size=6144"
+  },
   "scripts": {
     "postinstall": "husky install && chmod +x .husky/*",
     "dev": "vite",
     "build": "vue-tsc --noEmit && vite build --target esnext",
     "preview": "vite preview",
-    "test": "vitest --silent",
-    "test:ch": "vitest src/chapters/$ch/test",
+    "test": "NODE_OPTIONS=$npm_package_config_MAX_OLD_SPACE_SIZE vitest --silent",
+    "test:ch": "NODE_OPTIONS=$npm_package_config_MAX_OLD_SPACE_SIZE vitest src/chapters/$ch/test",
     "lint": "eslint --ext .js,.ts,.vue --fix --no-error-on-unmatched-pattern src",
     "format": "prettier --write --ignore-unknown --no-error-on-unmatched-pattern src",
     "commitmsg": "commitlint --config .commitlintrc.js --edit $GIT_PARAMS",
@@ -27,6 +30,7 @@
     "core-js": "^3.8.3",
     "lodash": "^4.17.21",
     "papaparse": "^5.4.1",
+    "path-browserify": "^1.0.1",
     "pinia": "^2.0.23",
     "rehype-highlight": "^6.0.0",
     "rehype-katex": "^6.0.2",
@@ -59,6 +63,7 @@
     "@vitejs/plugin-vue": "^3.0.3",
     "@vue/eslint-config-typescript": "^11.0.0",
     "commitlint": "^17.4.4",
+    "cross-env": "^7.0.3",
     "eslint": "^8.22.0",
     "eslint-config-prettier": "^8.6.0",
     "eslint-plugin-vue": "^9.3.0",

pnpm-lock.yaml

@@ -0,0 +1,51 @@
+# Chapter 3: Regular Expression
+
+The file [enwiki-country.json.gz](../../assets/enwiki-country.json.gz) stores Wikipedia articles in the format:
+
+- Each line stores a Wikipedia article in JSON format
+- Each JSON document has key-value pairs:
+  - Title of the article as the value for the `title` key
+  - Body of the article as the value for the `text` key
+- The entire file is compressed by gzip
+
+Write codes that perform the following jobs.
+
+## 20. [Read JSON documents](./ex20.ts)
+
+Read the JSON documents and output the body of the article about the United Kingdom. Reuse the output in problems 21-29.
+
+## 21. [Lines with category names](./ex21.ts)
+
+Extract lines that define the categories of the article.
+
+## 22. [Category names](./ex22.ts)
+
+Extract the category names of the article.
+
+## 23. [Section structure](./ex23.ts)
+
+Extract section names in the article with their levels. For example, the level of the section is 1 for the MediaWiki markup `"== Section name =="`.
+
+## 24. [Media references](./ex24.ts)
+
+Extract references to media files linked from the article.
+
+## 25. [Infobox](./ex25.ts)
+
+Extract field names and their values in the Infobox "country", and store them in a dictionary object.
+
+## 26. [Remove emphasis markups](./ex26.ts)
+
+In addition to the process of the problem 25, remove emphasis MediaWiki markups from the values. See [Help:Cheatsheet](https://en.wikipedia.org/wiki/Help:Cheatsheet).
+
+## 27. [Remove internal links](./ex27.ts)
+
+In addition to the process of the problem 26, remove internal links from the values. See [Help:Cheatsheet](https://en.wikipedia.org/wiki/Help:Cheatsheet).
+
+## 28. [Remove MediaWiki markups](./ex28.ts)
+
+In addition to the process of the problem 27, remove MediaWiki markups from the values as much as you can, and obtain the basic information of the country in plain text format.
+
+## 29. [Country flag](./ex29.ts)
+
+Obtain the URL of the country flag by using the analysis result of Infobox. (Hint: convert a file reference to a URL by calling [imageinfo](https://www.mediawiki.org/wiki/API:Imageinfo) in [MediaWiki API](https://www.mediawiki.org/wiki/API:Main_page))

src/assets/enwiki-country.json.gz

@@ -0,0 +1,33 @@
+// Using custom plugin [gzip-import.ts](https://gist.github.com/neutron0831/73cfd03ef5bc14cfb132cc32a7445b35)
+import enwikiCountryJson from '@/assets/enwiki-country.json.gz?raw'
+
+/**
+ *
+ * @interface Article
+ * @property {string} title - Title of the article
+ * @property {string} text  - Body of the article
+ */
+export interface Article {
+  title: string
+  text: string
+}
+
+/**
+ * ### 20. Read JSON documents
+ * Read the JSON documents and output the body of the article about the United Kingdom. Reuse the output in problems 21-29.
+ *
+ * @returns {Promise<Article>}
+ */
+async function ex20(): Promise<Article> {
+  const enwikiCountries: Article[] = enwikiCountryJson
+    .trim()
+    .split('\n')
+    .map((line: string) => JSON.parse(line))
+  const unitedKingdom = enwikiCountries.find(
+    (country) => country.title === 'United Kingdom',
+  )!
+
+  return unitedKingdom
+}
+
+export { ex20 }

src/chapters/03/README.md

@@ -0,0 +1,17 @@
+import { ex20 } from './ex20'
+import { map } from 'lodash'
+
+/**
+ * ### 21. Lines with category names
+ * Extract lines that define the categories of the article.
+ *
+ * @returns {Promise<string[]>}
+ */
+async function ex21(): Promise<string[]> {
+  const { text } = await ex20()
+  const categories = map([...text.matchAll(/(\[\[Category:.*\]\])/g)], 1)
+
+  return categories
+}
+
+export { ex21 }

src/chapters/03/ex20.ts

@@ -0,0 +1,20 @@
+import { ex21 } from './ex21'
+import { map } from 'lodash'
+
+/**
+ * ### 22. Category names
+ * Extract the category names of the article.
+ *
+ * @returns {Promise<string[]>}
+ */
+async function ex22(): Promise<string[]> {
+  const categories = await ex21()
+  const categoryNames = map(
+    [...categories.join('\n').matchAll(/\[\[Category:(.*)\]\]/g)],
+    1,
+  )
+
+  return categoryNames
+}
+
+export { ex22 }