@sylphx/pdf-reader-mcp 2.0.7 → 2.1.0

package/dist/index.js

@@ -316,6 +316,7 @@ var extractPageContent = async (pdfDocument, pageNum, includeImages, sourceDescr
 
 // src/pdf/loader.ts
 import fs from "node:fs/promises";
+import { createRequire } from "node:module";
 import { getDocument } from "pdfjs-dist/legacy/build/pdf.mjs";
 
 // src/utils/errors.ts
@@ -341,6 +342,8 @@ var resolvePath = (userPath) => {
 
 // src/pdf/loader.ts
 var logger3 = createLogger("Loader");
+var require2 = createRequire(import.meta.url);
+var CMAP_URL = require2.resolve("pdfjs-dist/package.json").replace("package.json", "cmaps/");
 var MAX_PDF_SIZE = 100 * 1024 * 1024;
 var loadPdfDocument = async (source, sourceDescription) => {
   let pdfDataSource;
@@ -370,7 +373,12 @@ var loadPdfDocument = async (source, sourceDescription) => {
     }
     throw new PdfError(errorCode, `Failed to prepare PDF source ${sourceDescription}. Reason: ${message}`, { cause: err instanceof Error ? err : undefined });
   }
-  const loadingTask = getDocument(pdfDataSource);
+  const documentParams = pdfDataSource instanceof Uint8Array ? { data: pdfDataSource } : pdfDataSource;
+  const loadingTask = getDocument({
+    ...documentParams,
+    cMapUrl: CMAP_URL,
+    cMapPacked: true
+  });
   try {
     return await loadingTask.promise;
   } catch (err) {
@@ -455,27 +463,32 @@ var determinePagesToProcess = (targetPages, totalPages, includeFullText) => {
 };
 
 // src/schemas/readPdf.ts
-import { z } from "zod";
-var pageSpecifierSchema = z.union([
-  z.array(z.number().int().min(1)).min(1).describe("Array of page numbers (1-based)"),
-  z.string().min(1).refine((val) => /^[0-9,-]+$/.test(val.replace(/\s/g, "")), {
-    message: "Page string must contain only numbers, commas, and hyphens."
-  }).describe('Page range string (e.g., "1-5,10,15-20")')
-]);
-var pdfSourceSchema = z.object({
-  path: z.string().min(1).optional().describe("Path to the local PDF file (absolute or relative to cwd)."),
-  url: z.string().url().optional().describe("URL of the PDF file."),
-  pages: pageSpecifierSchema.optional().describe("Extract text only from specific pages (1-based) or ranges for this source. If provided, 'include_full_text' is ignored for this source.")
-}).strict().refine((data) => !!(data.path && !data.url) || !!(!data.path && data.url), {
-  message: "Each source must have either 'path' or 'url', but not both."
+import {
+  array,
+  bool,
+  description,
+  gte,
+  int,
+  min,
+  num,
+  object,
+  optional,
+  str,
+  union
+} from "@sylphx/vex";
+var pageSpecifierSchema = union(array(num(int, gte(1))), str(min(1)));
+var pdfSourceSchema = object({
+  path: optional(str(min(1), description("Path to the local PDF file (absolute or relative to cwd)."))),
+  url: optional(str(min(1), description("URL of the PDF file."))),
+  pages: optional(pageSpecifierSchema)
+});
+var readPdfArgsSchema = object({
+  sources: array(pdfSourceSchema),
+  include_full_text: optional(bool(description("Include the full text content of each PDF (only if 'pages' is not specified for that source)."))),
+  include_metadata: optional(bool(description("Include metadata and info objects for each PDF."))),
+  include_page_count: optional(bool(description("Include the total number of pages for each PDF."))),
+  include_images: optional(bool(description("Extract and include embedded images from the PDF pages as base64-encoded data.")))
 });
-var readPdfArgsSchema = z.object({
-  sources: z.array(pdfSourceSchema).min(1).describe("An array of PDF sources to process, each can optionally specify pages."),
-  include_full_text: z.boolean().optional().default(false).describe("Include the full text content of each PDF (only if 'pages' is not specified for that source)."),
-  include_metadata: z.boolean().optional().default(true).describe("Include metadata and info objects for each PDF."),
-  include_page_count: z.boolean().optional().default(true).describe("Include the total number of pages for each PDF."),
-  include_images: z.boolean().optional().default(false).describe("Extract and include embedded images from the PDF pages as base64-encoded data.")
-}).strict();
 
 // src/handlers/readPdf.ts
 var logger5 = createLogger("ReadPdf");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sylphx/pdf-reader-mcp",
-  "version": "2.0.7",
+  "version": "2.1.0",
   "description": "An MCP server providing tools to read PDF files.",
   "type": "module",
   "bin": {
@@ -71,18 +71,17 @@
     "prepare": "node_modules/.bin/lefthook install || true"
   },
   "dependencies": {
-    "@sylphx/mcp-server-sdk": "1.3.0",
+    "@sylphx/mcp-server-sdk": "^2.1.0",
+    "@sylphx/vex": "^0.1.11",
     "glob": "^13.0.0",
     "pdfjs-dist": "^5.4.449",
-    "pngjs": "^7.0.0",
-    "zod": "4.2.0-canary.20251124T022609",
-    "zod-to-json-schema": "^3.25.0"
+    "pngjs": "^7.0.0"
   },
   "devDependencies": {
     "@biomejs/biome": "^2.3.8",
     "@solidjs/router": "^0.15.4",
     "@sylphx/biome-config": "^0.4.1",
-    "@sylphx/bump": "^0.12.1",
+    "@sylphx/bump": "^1.6.1",
     "@sylphx/doctor": "^1.32.1",
     "@sylphx/leaf": "^1.0.0",
     "@sylphx/leaf-theme-default": "^1.0.0",