chore(prettier): fix prettier formatting arc

.editorconfig

@@ -0,0 +1,15 @@
+# EditorConfig helps developers define and maintain consistent
+# coding styles between different editors or IDEs
+# http://editorconfig.org
+root = true
+
+[*]
+indent_style = space
+indent_size = 2
+end_of_line = lf
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+
+[*.md]
+trim_trailing_whitespace = false

.eslintrc.yml

@@ -166,4 +166,4 @@ overrides:
                 'private-instance-method',
               ],
           },
-        ]
+        ]

.github/workflows/CI.yml

@@ -97,7 +97,7 @@ jobs:
           #   docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-alpine
           #   build: |
           #     set -e &&
-          #     rustup target add aarch64-unknown-linux-musl && 
+          #     rustup target add aarch64-unknown-linux-musl &&
           #     yarn build --target aarch64-unknown-linux-musl
           #   env:
           #     CXXFLAGS: '--stdlib=libc++ -L/usr/lib/llvm-18/lib -static'
@@ -258,7 +258,6 @@ jobs:
         run: ls -R .
         shell: bash
 
-
   test-linux-x64-gnu-binding:
     name: Test bindings on Linux-x64-gnu - node@${{ matrix.node }}
     needs:

.github/workflows/book.yml

@@ -26,4 +26,4 @@ jobs:
         if: ${{ github.ref == 'refs/heads/main' }}
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: ./book/book
+          publish_dir: ./book/book

.prettierignore

@@ -0,0 +1,2 @@
+target
+.yarn

.taplo.toml

@@ -0,0 +1,7 @@
+exclude = ["node_modules/**/*.toml"]
+
+# https://taplo.tamasfe.dev/configuration/formatter-options.html
+[formatting]
+align_entries = true
+indent_tables = true
+reorder_keys  = true

.vscode/settings.json

@@ -1,3 +1,3 @@
 {
-    "rust-analyzer.procMacro.ignored": { "napi-derive": ["napi"] }
-}
+  "rust-analyzer.procMacro.ignored": { "napi-derive": ["napi"] }
+}

.yarnrc.yml

@@ -1,5 +1,5 @@
 nodeLinker: node-modules
 
-npmAuditRegistry: "https://registry.npmjs.org"
+npmAuditRegistry: https://registry.npmjs.org
 
-yarnPath: .yarn/releases/yarn-4.3.1.cjs
+yarnPath: .yarn/releases/yarn-3.6.4.cjs

README.md

@@ -7,124 +7,119 @@ The [spider](https://github.com/spider-rs/spider) project ported to Node.js
 1. `npm i @spider-rs/spider-rs --save`
 
 ```ts
-import { Website, pageTitle } from "@spider-rs/spider-rs";
+import { Website, pageTitle } from '@spider-rs/spider-rs'
 
-const website = new Website("https://rsseau.fr")
+const website = new Website('https://rsseau.fr')
   .withHeaders({
-    authorization: "somerandomjwt",
+    authorization: 'somerandomjwt',
   })
   .withBudget({
-    "*": 20, // limit max request 20 pages for the website
-    "/docs": 10, // limit only 10 pages on the `/docs` paths
+    '*': 20, // limit max request 20 pages for the website
+    '/docs': 10, // limit only 10 pages on the `/docs` paths
   })
-  .withBlacklistUrl(["/resume"]) // regex or pattern matching to ignore paths
-  .build();
+  .withBlacklistUrl(['/resume']) // regex or pattern matching to ignore paths
+  .build()
 
 // optional: page event handler
 const onPageEvent = (_err, page) => {
-  const title = pageTitle(page); // comment out to increase performance if title not needed
-  console.info(`Title of ${page.url} is '${title}'`);
+  const title = pageTitle(page) // comment out to increase performance if title not needed
+  console.info(`Title of ${page.url} is '${title}'`)
   website.pushData({
     status: page.statusCode,
     html: page.content,
     url: page.url,
     title,
-  });
-};
+  })
+}
 
-await website.crawl(onPageEvent);
-await website.exportJsonlData("./storage/rsseau.jsonl");
-console.log(website.getLinks());
+await website.crawl(onPageEvent)
+await website.exportJsonlData('./storage/rsseau.jsonl')
+console.log(website.getLinks())
 ```
 
 Collect the resources for a website.
 
 ```ts
-import { Website } from "@spider-rs/spider-rs";
+import { Website } from '@spider-rs/spider-rs'
 
-const website = new Website("https://rsseau.fr")
+const website = new Website('https://rsseau.fr')
   .withBudget({
-    "*": 20,
-    "/docs": 10,
+    '*': 20,
+    '/docs': 10,
   })
   // you can use regex or string matches to ignore paths
-  .withBlacklistUrl(["/resume"])
-  .build();
+  .withBlacklistUrl(['/resume'])
+  .build()
 
-await website.scrape();
-console.log(website.getPages());
+await website.scrape()
+console.log(website.getPages())
 ```
 
 Run the crawls in the background on another thread.
 
 ```ts
-import { Website } from "@spider-rs/spider-rs";
+import { Website } from '@spider-rs/spider-rs'
 
-const website = new Website("https://rsseau.fr");
+const website = new Website('https://rsseau.fr')
 
 const onPageEvent = (_err, page) => {
-  console.log(page);
-};
+  console.log(page)
+}
 
-await website.crawl(onPageEvent, true);
+await website.crawl(onPageEvent, true)
 // runs immediately
 ```
 
 Use headless Chrome rendering for crawls.
 
 ```ts
-import { Website } from "@spider-rs/spider-rs";
+import { Website } from '@spider-rs/spider-rs'
 
-const website = new Website("https://rsseau.fr").withChromeIntercept(
-  true,
-  true,
-);
+const website = new Website('https://rsseau.fr').withChromeIntercept(true, true)
 
 const onPageEvent = (_err, page) => {
-  console.log(page);
-};
+  console.log(page)
+}
 
 // the third param determines headless chrome usage.
-await website.crawl(onPageEvent, false, true);
-console.log(website.getLinks());
+await website.crawl(onPageEvent, false, true)
+console.log(website.getLinks())
 ```
 
 Cron jobs can be done with the following.
 
 ```ts
-import { Website } from "@spider-rs/spider-rs";
+import { Website } from '@spider-rs/spider-rs'
 
-const website = new Website("https://choosealicense.com").withCron(
-  "1/5 * * * * *",
-);
+const website = new Website('https://choosealicense.com').withCron('1/5 * * * * *')
 // sleep function to test cron
 const stopCron = (time: number, handle) => {
   return new Promise((resolve) => {
     setTimeout(() => {
-      resolve(handle.stop());
-    }, time);
-  });
-};
+      resolve(handle.stop())
+    }, time)
+  })
+}
 
-const links = [];
+const links = []
 
 const onPageEvent = (err, value) => {
-  links.push(value);
-};
+  links.push(value)
+}
 
-const handle = await website.runCron(onPageEvent);
+const handle = await website.runCron(onPageEvent)
 
 // stop the cron in 4 seconds
-await stopCron(4000, handle);
+await stopCron(4000, handle)
 ```
 
 Use the crawl shortcut to get the page content and url.
 
 ```ts
-import { crawl } from "@spider-rs/spider-rs";
+import { crawl } from '@spider-rs/spider-rs'
 
-const { links, pages } = await crawl("https://rsseau.fr");
-console.log(pages);
+const { links, pages } = await crawl('https://rsseau.fr')
+console.log(pages)
 ```
 
 ## Benchmarks