docshark 0.1.8 → 0.1.12

package/CHANGELOG.md

@@ -1,5 +1,33 @@
 # Changelog
 
+## [0.1.12](https://github.com/Michael-Obele/docshark/compare/v0.1.11...v0.1.12) (2026-03-12)
+
+
+### 🐛 Bug Fixes
+
+* **release:** update Node.js version to 24 and set registry URL ([2887a29](https://github.com/Michael-Obele/docshark/commit/2887a2920ab61adf6eb4bf4aa6b6d86143ffd34f))
+
+## [0.1.11](https://github.com/Michael-Obele/docshark/compare/v0.1.10...v0.1.11) (2026-03-11)
+
+
+### ✨ Features
+
+* Directly process raw Markdown and plain text files by checking content type and URL extension. ([a4d66b8](https://github.com/Michael-Obele/docshark/commit/a4d66b8cdd6342645b3cab292ef82c133c9ae52c))
+
+## [0.1.10](https://github.com/Michael-Obele/docshark/compare/v0.1.9...v0.1.10) (2026-03-11)
+
+
+### 📚 Documentation
+
+* Add NPM version badge to README. ([ae9c6ca](https://github.com/Michael-Obele/docshark/commit/ae9c6ca71dbd844de6b065a0e47021c7d1e3ec72))
+
+## [0.1.9](https://github.com/Michael-Obele/docshark/compare/v0.1.8...v0.1.9) (2026-03-11)
+
+
+### ✨ Features
+
+* Add NPM provenance publishing to the release workflow and set the release-please changelog type to default. ([7c6ed54](https://github.com/Michael-Obele/docshark/commit/7c6ed54ca8e51a3b73abf64cc775352937c9c1cf))
+
 ## 0.1.8 (2026-03-11)
 
 **Full Changelog**: https://github.com/Michael-Obele/docshark/compare/v0.1.7...v0.1.8

package/README.md

@@ -1,6 +1,7 @@
 # 🦈 DocShark
 
 [![Built with Bun](https://img.shields.io/badge/Bun-%23000000.svg?style=flat&logo=bun&logoColor=white)](https://bun.sh/)
+[![NPM Version](https://img.shields.io/npm/v/docshark.svg?style=flat&color=blue)](https://www.npmjs.com/package/docshark)
 [![MCP Compatible](https://img.shields.io/badge/MCP-Ready-0D1117.svg?style=flat&logo=github&logoColor=white)](https://modelcontextprotocol.io/)
 [![GitHub Release](https://img.shields.io/github/v/release/Michael-Obele/docshark?color=success)](https://github.com/Michael-Obele/docshark/releases)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

package/dist/jobs/worker.js

@@ -41,7 +41,7 @@ export class CrawlWorker {
                     await rateLimiter.wait();
                     const result = await fetchPage(url, config.renderer);
                     // Extract content + convert to markdown
-                    const { markdown, title, headings } = extractAndConvert(result.html, url);
+                    const { markdown, title, headings } = extractAndConvert(result.html, url, result.contentType);
                     if (!markdown || markdown.length < 50) {
                         crawled++;
                         continue; // Skip essentially empty pages

package/dist/processor/extractor.d.ts

@@ -1,4 +1,4 @@
-export declare function extractAndConvert(html: string, url: string): {
+export declare function extractAndConvert(html: string, url: string, contentType?: string): {
     markdown: string;
     title: string;
     headings: Array<{

package/dist/processor/extractor.js

@@ -25,7 +25,23 @@ turndown.addRule('removeImages', {
     filter: 'img',
     replacement: () => '',
 });
-export function extractAndConvert(html, url) {
+export function extractAndConvert(html, url, contentType = 'text/html') {
+    const isMarkdown = url.endsWith('.md') || url.endsWith('.txt') || contentType.includes('text/plain') || contentType.includes('text/markdown');
+    if (isMarkdown && !html.trim().startsWith('<!DOCTYPE') && !html.trim().startsWith('<html')) {
+        const markdown = html.trim();
+        const titleMatch = markdown.match(/^#\s+(.+)$/m);
+        let title = titleMatch ? titleMatch[1].trim() : url.split('/').pop() || 'Untitled';
+        if (title.endsWith('.txt') || title.endsWith('.md')) {
+            title = title.slice(0, -4);
+        }
+        const headings = [];
+        const headingRegex = /^(#{1,6})\s+(.+)$/gm;
+        let match;
+        while ((match = headingRegex.exec(markdown)) !== null) {
+            headings.push({ level: match[1].length, text: match[2].trim() });
+        }
+        return { markdown, title, headings };
+    }
     const { document } = parseHTML(html);
     // Set the document URL for Readability to resolve relative links
     if (url) {

package/dist/scraper/fetcher.js

@@ -17,7 +17,7 @@ export async function fetchPage(url, renderer = 'auto') {
         return result;
     }
     // Auto mode: check if content is too short (possibly JS-rendered)
-    const { markdown } = extractAndConvert(result.html, url);
+    const { markdown } = extractAndConvert(result.html, url, result.contentType);
     if (markdown.length >= MIN_CONTENT_LENGTH) {
         return result;
     }
@@ -52,6 +52,7 @@ async function fetchWithRetry(url, retries = MAX_RETRIES) {
                 status: response.status,
                 etag: response.headers.get('etag'),
                 lastModified: response.headers.get('last-modified'),
+                contentType: response.headers.get('content-type') || undefined,
             };
         }
         catch (err) {

package/dist/types.d.ts

@@ -59,6 +59,7 @@ export interface FetchResult {
     etag?: string | null;
     lastModified?: string | null;
     unchanged?: boolean;
+    contentType?: string;
 }
 export interface CrawlConfig {
     renderer?: 'auto' | 'fetch' | 'puppeteer';

package/dist/version.d.ts

@@ -1 +1 @@
-export declare const VERSION = "0.1.8";
+export declare const VERSION = "0.1.12";

package/dist/version.js

@@ -1,2 +1,2 @@
 // This file is automatically updated by release-please
-export const VERSION = '0.1.8'; // x-release-please-version
+export const VERSION = '0.1.12'; // x-release-please-version

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "docshark",
-  "version": "0.1.8",
+  "version": "0.1.12",
   "description": "🦈 Documentation MCP Server — scrape, index, and search any doc website",
   "type": "module",
   "main": "./dist/index.js",
@@ -21,6 +21,16 @@
     "LICENSE",
     "CHANGELOG.md"
   ],
+  "author": "Michael Obele",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Michael-Obele/docshark.git"
+  },
+  "bugs": {
+    "url": "https://github.com/Michael-Obele/docshark/issues"
+  },
+  "homepage": "https://github.com/Michael-Obele/docshark#readme",
   "scripts": {
     "start": "bun run src/cli.ts start",
     "dev": "bun run --watch src/cli.ts start",