@sylphx/pdf-reader-mcp 1.3.0 → 1.4.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sylphx/pdf-reader-mcp",
-  "version": "1.3.0",
+  "version": "1.4.0",
   "description": "An MCP server providing tools to read PDF files.",
   "type": "module",
   "bin": {
@@ -11,6 +11,12 @@
     "README.md",
     "LICENSE"
   ],
+  "exports": {
+    ".": {
+      "import": "./dist/index.js",
+      "types": "./dist/index.d.ts"
+    }
+  },
   "publishConfig": {
     "access": "public"
   },
@@ -19,12 +25,12 @@
   },
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/sylphlab/pdf-reader-mcp.git"
+    "url": "git+https://github.com/SylphxAI/pdf-reader-mcp.git"
   },
   "bugs": {
-    "url": "https://github.com/sylphlab/pdf-reader-mcp/issues"
+    "url": "https://github.com/SylphxAI/pdf-reader-mcp/issues"
   },
-  "homepage": "https://github.com/sylphlab/pdf-reader-mcp#readme",
+  "homepage": "https://github.com/SylphxAI/pdf-reader-mcp#readme",
   "author": "Sylphx <contact@sylphx.com> (https://sylphx.com)",
   "license": "MIT",
   "keywords": [
@@ -40,65 +46,61 @@
     "tool"
   ],
   "scripts": {
-    "build": "tsc",
+    "build": "bunup",
     "watch": "tsc --watch",
     "inspector": "npx @modelcontextprotocol/inspector dist/index.js",
-    "test": "vitest run",
-    "test:watch": "vitest watch",
-    "test:cov": "vitest run --coverage --reporter=junit --outputFile=test-report.junit.xml",
+    "test": "bun test",
+    "test:watch": "bun test --watch",
+    "test:cov": "bun test --coverage",
     "lint": "biome lint .",
     "lint:fix": "biome lint --write .",
     "format": "biome format --write .",
     "check-format": "biome format .",
     "check": "biome check .",
     "check:fix": "biome check --write .",
-    "validate": "npm run check && npm run test",
-    "docs:dev": "vitepress dev docs",
-    "docs:build": "vitepress build docs",
-    "docs:preview": "vitepress preview docs",
+    "validate": "bun run check && bun run test",
+    "docs:dev": "leaf dev docs",
+    "docs:build": "leaf build docs",
+    "docs:preview": "leaf preview docs",
     "start": "node dist/index.js",
     "typecheck": "tsc --noEmit",
-    "benchmark": "vitest bench",
+    "benchmark": "bun bench",
     "clean": "rm -rf dist coverage",
     "docs:api": "typedoc --entryPoints src/index.ts --tsconfig tsconfig.json --plugin typedoc-plugin-markdown --out docs/api --readme none",
-    "prepublishOnly": "pnpm run clean && pnpm run build",
+    "prepublishOnly": "bunx @sylphx/doctor prepublish && bun run clean && bun run build",
     "release": "standard-version",
-    "prepare": "husky"
+    "prepare": "node_modules/.bin/lefthook install || true"
   },
   "dependencies": {
-    "@modelcontextprotocol/sdk": "^1.21.0",
-    "glob": "^11.0.1",
-    "pdfjs-dist": "^5.4.296",
+    "@sylphx/mcp-server-sdk": "1.0.0",
+    "glob": "^11.1.0",
+    "pdfjs-dist": "^5.4.394",
     "pngjs": "^7.0.0",
-    "zod": "^3.25.76",
-    "zod-to-json-schema": "^3.24.6"
+    "zod": "4.2.0-canary.20251124T022609",
+    "zod-to-json-schema": "^3.25.0"
   },
   "devDependencies": {
-    "@biomejs/biome": "^2.3.2",
-    "@commitlint/cli": "^20.1.0",
-    "@commitlint/config-conventional": "^20.0.0",
+    "@biomejs/biome": "^2.3.8",
+    "@solidjs/router": "^0.15.4",
+    "@sylphx/biome-config": "^0.4.0",
+    "@sylphx/bump": "^0.12.1",
+    "@sylphx/doctor": "^1.23.3",
+    "@sylphx/leaf": "^1.0.0",
+    "@sylphx/leaf-theme-default": "^1.0.0",
+    "@sylphx/tsconfig": "^0.3.0",
     "@types/glob": "^8.1.0",
-    "@types/node": "^24.0.7",
+    "@types/node": "^24.10.1",
     "@types/pngjs": "^6.0.5",
-    "@vitest/coverage-v8": "^4.0.7",
-    "husky": "^9.1.7",
-    "lint-staged": "^16.2.6",
-    "standard-version": "^9.5.0",
-    "typedoc": "^0.28.2",
+    "bunup": "^0.16.10",
+    "lefthook": "^2.0.4",
+    "solid-js": "^1.9.10",
+    "typedoc": "^0.28.14",
     "typedoc-plugin-markdown": "^4.9.0",
-    "typescript": "^5.8.3",
-    "vitepress": "^1.6.3",
-    "vitest": "^4.0.7",
-    "vue": "^3.5.13"
-  },
-  "commitlint": {
-    "extends": [
-      "@commitlint/config-conventional"
-    ]
+    "typescript": "^5.9.3",
+    "vite": "^7.2.4"
   },
-  "lint-staged": {
-    "*.{ts,tsx,js,cjs,json}": [
-      "biome check --write --no-errors-on-unmatched --files-ignore-unknown=true"
-    ]
+  "packageManager": "bun@1.3.1",
+  "overrides": {
+    "js-yaml": "^4.1.0"
   }
 }

package/dist/handlers/index.js

@@ -1,4 +0,0 @@
-// Import only the consolidated PDF tool definition
-import { readPdfToolDefinition } from './readPdf.js';
-// Aggregate only the consolidated PDF tool definition
-export const allToolDefinitions = [readPdfToolDefinition];

package/dist/handlers/readPdf.js

@@ -1,170 +0,0 @@
-// PDF reading handler - orchestrates PDF processing workflow
-import { ErrorCode, McpError } from '@modelcontextprotocol/sdk/types.js';
-import { z } from 'zod';
-import { buildWarnings, extractMetadataAndPageCount, extractPageContent, } from '../pdf/extractor.js';
-import { loadPdfDocument } from '../pdf/loader.js';
-import { determinePagesToProcess, getTargetPages } from '../pdf/parser.js';
-import { readPdfArgsSchema } from '../schemas/readPdf.js';
-/**
- * Process a single PDF source
- */
-const processSingleSource = async (source, options) => {
-    const sourceDescription = source.path ?? source.url ?? 'unknown source';
-    let individualResult = { source: sourceDescription, success: false };
-    try {
-        // Parse target pages
-        const targetPages = getTargetPages(source.pages, sourceDescription);
-        // Load PDF document
-        const { pages: _pages, ...loadArgs } = source;
-        const pdfDocument = await loadPdfDocument(loadArgs, sourceDescription);
-        const totalPages = pdfDocument.numPages;
-        // Extract metadata and page count
-        const metadataOutput = await extractMetadataAndPageCount(pdfDocument, options.includeMetadata, options.includePageCount);
-        const output = { ...metadataOutput };
-        // Determine pages to process
-        const { pagesToProcess, invalidPages } = determinePagesToProcess(targetPages, totalPages, options.includeFullText);
-        // Add warnings for invalid pages
-        const warnings = buildWarnings(invalidPages, totalPages);
-        if (warnings.length > 0) {
-            output.warnings = warnings;
-        }
-        // Extract content with ordering preserved
-        if (pagesToProcess.length > 0) {
-            // Use new extractPageContent to preserve Y-coordinate ordering
-            const pageContents = await Promise.all(pagesToProcess.map((pageNum) => extractPageContent(pdfDocument, pageNum, options.includeImages, sourceDescription)));
-            // Store page contents for ordered retrieval
-            output.page_contents = pageContents.map((items, idx) => ({
-                page: pagesToProcess[idx],
-                items,
-            }));
-            // For backward compatibility, also provide text-only outputs
-            const extractedPageTexts = pageContents.map((items, idx) => ({
-                page: pagesToProcess[idx],
-                text: items
-                    .filter((item) => item.type === 'text')
-                    .map((item) => item.textContent)
-                    .join(''),
-            }));
-            if (targetPages) {
-                // Specific pages requested
-                output.page_texts = extractedPageTexts;
-            }
-            else {
-                // Full text requested
-                output.full_text = extractedPageTexts.map((p) => p.text).join('\n\n');
-            }
-            // Extract image metadata for JSON response
-            if (options.includeImages) {
-                const extractedImages = pageContents
-                    .flatMap((items) => items.filter((item) => item.type === 'image' && item.imageData))
-                    .map((item) => item.imageData)
-                    .filter((img) => img !== undefined);
-                if (extractedImages.length > 0) {
-                    output.images = extractedImages;
-                }
-            }
-        }
-        individualResult = { ...individualResult, data: output, success: true };
-    }
-    catch (error) {
-        let errorMessage = `Failed to process PDF from ${sourceDescription}.`;
-        if (error instanceof McpError) {
-            errorMessage = error.message;
-        } /* c8 ignore next */
-        else if (error instanceof Error) {
-            errorMessage += ` Reason: ${error.message}`;
-        }
-        else {
-            errorMessage += ` Unknown error: ${JSON.stringify(error)}`;
-        }
-        individualResult.error = errorMessage;
-        individualResult.success = false;
-        individualResult.data = undefined;
-    }
-    return individualResult;
-};
-/**
- * Main handler function for read_pdf tool
- */
-export const handleReadPdfFunc = async (args) => {
-    let parsedArgs;
-    try {
-        parsedArgs = readPdfArgsSchema.parse(args);
-    }
-    catch (error) {
-        if (error instanceof z.ZodError) {
-            throw new McpError(ErrorCode.InvalidParams, `Invalid arguments: ${error.issues.map((e) => `${e.path.join('.')} (${e.message})`).join(', ')}`);
-        }
-        /* c8 ignore next */
-        const message = error instanceof Error ? error.message : String(error);
-        /* c8 ignore next */
-        throw new McpError(ErrorCode.InvalidParams, `Argument validation failed: ${message}`);
-    }
-    const { sources, include_full_text, include_metadata, include_page_count, include_images } = parsedArgs;
-    // Process all sources concurrently
-    const results = await Promise.all(sources.map((source) => processSingleSource(source, {
-        includeFullText: include_full_text,
-        includeMetadata: include_metadata,
-        includePageCount: include_page_count,
-        includeImages: include_images,
-    })));
-    // Build content parts - start with structured JSON for backward compatibility
-    const content = [];
-    // Strip image data and page_contents from JSON to keep it manageable
-    const resultsForJson = results.map((result) => {
-        if (result.data) {
-            const { images, page_contents, ...dataWithoutBinaryContent } = result.data;
-            // Include image count and metadata in JSON, but not the base64 data
-            if (images) {
-                const imageInfo = images.map((img) => ({
-                    page: img.page,
-                    index: img.index,
-                    width: img.width,
-                    height: img.height,
-                    format: img.format,
-                }));
-                return { ...result, data: { ...dataWithoutBinaryContent, image_info: imageInfo } };
-            }
-            return { ...result, data: dataWithoutBinaryContent };
-        }
-        return result;
-    });
-    // First content part: Structured JSON results
-    content.push({
-        type: 'text',
-        text: JSON.stringify({ results: resultsForJson }, null, 2),
-    });
-    // Add page content in exact Y-coordinate order
-    for (const result of results) {
-        if (!result.success || !result.data?.page_contents)
-            continue;
-        // Process each page's content items in order
-        for (const pageContent of result.data.page_contents) {
-            for (const item of pageContent.items) {
-                if (item.type === 'text' && item.textContent) {
-                    // Add text content part
-                    content.push({
-                        type: 'text',
-                        text: item.textContent,
-                    });
-                }
-                else if (item.type === 'image' && item.imageData) {
-                    // Add image content part (all images are now encoded as PNG)
-                    content.push({
-                        type: 'image',
-                        data: item.imageData.data,
-                        mimeType: 'image/png',
-                    });
-                }
-            }
-        }
-    }
-    return { content };
-};
-// Export the tool definition
-export const readPdfToolDefinition = {
-    name: 'read_pdf',
-    description: 'Reads content/metadata/images from one or more PDFs (local/URL). Each source can specify pages to extract.',
-    schema: readPdfArgsSchema,
-    handler: handleReadPdfFunc,
-};