feat: add yup support for validation

.github/workflows/release.yml

@@ -41,13 +41,13 @@ jobs:
           node-version: 20.x
 
       - name: Install Dependencies
-        run: npm install
+        run: npm install -g pnpm && pnpm install
 
       - name: Create Release Pull Request or Publish to npm
         id: changesets
         uses: changesets/action@v1
         with:
-          publish: npm run release
+          publish: pnpm run release
         env:
           GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

README.md

@@ -17,13 +17,13 @@ Effect Schema, allowing you to use your preferred validation tool.
 
 ### Schema Support
 
-| Schema Library                                       | Status              | Notes                                                              |
-| ---------------------------------------------------- | ------------------- | ------------------------------------------------------------------ |
-| [Zod](https://github.com/colinhacks/zod)             | ✅ Supported        | Default schema tool for `xscrape`                                  |
-| [Effect/Schema](https://github.com/Effect-TS/effect) | ✅ Supported        | Support for Effect/Schema for additional flexibility               |
-| [Joi](https://github.com/sideway/joi)                | ✅ Supported        | Support for Joi for those familiar with server-side validation     |
-| [Yup](https://github.com/jquense/yup)                | 🚧 Planned          | Adding Yup support for schema validation in front-end applications |
-| Others...                                            | 🔄 In Consideration | Potential support for other schema tools as per user feedback      |
+| Schema Library                                       | Status              | Notes                                                         |
+| ---------------------------------------------------- | ------------------- | ------------------------------------------------------------- |
+| [Zod](https://github.com/colinhacks/zod)             | ✅ Supported        | Default schema tool for `xscrape`                             |
+| [Effect/Schema](https://github.com/Effect-TS/effect) | ✅ Supported        | Support for Effect/Schema for additional flexibility          |
+| [Joi](https://github.com/sideway/joi)                | ✅ Supported        | Support for Joi for validation                                |
+| [Yup](https://github.com/jquense/yup)                | ✅ Supported        | Support for Yup for validation                                |
+| Others...                                            | 🔄 In Consideration | Potential support for other schema tools as per user feedback |
 
 ## Installation
 

package.json

@@ -63,6 +63,7 @@
         "cheerio": "^1.0.0",
         "effect": "^3.10.4",
         "joi": "^17.13.3",
+        "yup": "^1.4.0",
         "zod": "^3.23.8"
     }
 }

src/createScraper.yup.test.ts

@@ -0,0 +1,187 @@
+import { createScraper } from '@/createScraper.js';
+import { describe, test, expect } from 'vitest';
+import * as yup from 'yup';
+import { YupValidator } from '@/validators/yup.js';
+import { type SchemaFieldDefinitions } from '@/types.js';
+
+const schema = yup.object({
+  title: yup.string().default('No title'),
+  description: yup.string().required(),
+  keywords: yup.array().of(yup.string()).default([]),
+  views: yup.number().default(0),
+});
+
+const schemaWithNested = yup.object({
+  title: yup.string().default('No title nested'),
+  image: yup
+    .object({
+      url: yup.string().required(),
+      width: yup.number().required(),
+      height: yup.number().required(),
+    })
+    .default(() => ({ url: '', width: 0, height: 0 }))
+    .optional(),
+});
+
+type FieldDefinitions = SchemaFieldDefinitions<yup.InferType<typeof schema>>;
+type NestedFieldDefinitions = SchemaFieldDefinitions<
+  yup.InferType<typeof schemaWithNested>
+>;
+
+const fields: FieldDefinitions = {
+  title: {
+    selector: 'title',
+  },
+  description: {
+    selector: 'meta[name="description"]',
+    attribute: 'content',
+    defaultValue: 'No description',
+  },
+  keywords: {
+    selector: 'meta[name="keywords"]',
+    attribute: 'content',
+    transform: (value) => value.split(','),
+    defaultValue: [],
+  },
+  views: {
+    selector: 'meta[name="views"]',
+    attribute: 'content',
+    transform: (value) => parseInt(value, 10),
+    defaultValue: 0,
+  },
+};
+
+const nestedFields: NestedFieldDefinitions = {
+  title: {
+    selector: 'title',
+  },
+  image: {
+    fields: {
+      url: {
+        selector: 'meta[property="og:image"]',
+        attribute: 'content',
+      },
+      width: {
+        selector: 'meta[property="og:image:width"]',
+        attribute: 'content',
+        transform: (value) => parseInt(value, 10),
+      },
+      height: {
+        selector: 'meta[property="og:image:height"]',
+        attribute: 'content',
+        transform: (value) => parseInt(value, 10),
+      },
+    },
+  },
+};
+
+const html = `
+<!DOCTYPE html>
+<html>
+<head>
+  <meta name="description" content="An example description.">
+  <meta name="keywords" content="typescript,html,parsing">
+  <meta name="views" content="1234">
+  <title>Example Title</title>
+</head>
+<body></body>
+</html>
+`;
+
+const htmlWithNested = `
+<!DOCTYPE html>
+<html>
+<head>
+  <title>Example Title</title>
+  <meta property="og:image" content="https://example.se/images/c12ffe73-3227-4a4a-b8ad-a3003cdf1d70?h=708&amp;tight=false&amp;w=1372">
+  <meta property="og:image:width" content="1372">
+  <meta property="og:image:height" content="708">
+</head>
+<body></body>
+</html>
+`;
+
+describe('xscrape with Yup', () => {
+  test('extracts data from HTML', () => {
+    const validator = new YupValidator(schema);
+    const scraper = createScraper({
+      fields,
+      validator,
+    });
+    const data = scraper(html);
+
+    expect(data).toEqual({
+      title: 'Example Title',
+      description: 'An example description.',
+      keywords: ['typescript', 'html', 'parsing'],
+      views: 1234,
+    });
+  });
+
+  test('handles missing data', () => {
+    const validator = new YupValidator(schema);
+    const scraper = createScraper({
+      fields,
+      validator,
+    });
+    const data = scraper('<html><head></head><body></body></html>');
+
+    expect(data).toEqual({
+      title: 'No title',
+      description: 'No description',
+      keywords: [],
+      views: 0,
+    });
+  });
+
+  test('handles multiple values', () => {
+    const validator = new YupValidator(schema);
+    const scraper = createScraper({
+      fields,
+      validator,
+    });
+    const data = scraper(
+      '<html><head><meta name="keywords" content="typescript,html,parsing"></head><body></body></html>',
+    );
+
+    expect(data).toEqual({
+      title: 'No title',
+      description: 'No description',
+      keywords: ['typescript', 'html', 'parsing'],
+      views: 0,
+    });
+  });
+
+  test('handles invalid data', () => {
+    const validator = new YupValidator(schema);
+    const scraper = createScraper({
+      fields,
+      validator,
+    });
+    try {
+      scraper(
+        '<html><head><meta name="keywords" content="invalid"></head><body></body></html>',
+      );
+    } catch (error) {
+      expect(error).toBeInstanceOf(Error);
+    }
+  });
+
+  test('extracts nested data from HTML', () => {
+    const validator = new YupValidator(schemaWithNested);
+    const scraper = createScraper({
+      fields: nestedFields,
+      validator,
+    });
+    const data = scraper(htmlWithNested);
+
+    expect(data).toEqual({
+      title: 'Example Title',
+      image: {
+        url: 'https://example.se/images/c12ffe73-3227-4a4a-b8ad-a3003cdf1d70?h=708&tight=false&w=1372',
+        width: 1372,
+        height: 708,
+      },
+    });
+  });
+});

src/validators/index.ts

@@ -1,3 +1,4 @@
 export * from '@/validators/effect.js';
 export * from '@/validators/zod.js';
 export * from '@/validators/joi.js';
+export * from '@/validators/yup.js';

src/validators/yup.ts

@@ -0,0 +1,25 @@
+import { type SchemaValidator } from '@/types.js';
+import * as yup from 'yup';
+
+export class YupValidator<T> implements SchemaValidator<T> {
+  constructor(private schema: yup.Schema<T>) {}
+
+  validate(data: unknown): T {
+    try {
+      return this.schema.validateSync(data, {
+        stripUnknown: true,
+        strict: false,
+        abortEarly: false,
+      });
+    } catch (error) {
+      if (error instanceof yup.ValidationError) {
+        throw new Error(this.formatError(error));
+      }
+      throw error;
+    }
+  }
+
+  private formatError(error: yup.ValidationError): string {
+    return error.errors.join('\n');
+  }
+}