@sylphx/pdf-reader-mcp 1.2.0 → 1.3.2

package/dist/pdf/parser.js

@@ -1,94 +0,0 @@
-// Page range parsing utilities
-import { ErrorCode, McpError } from '@modelcontextprotocol/sdk/types.js';
-const MAX_RANGE_SIZE = 10000; // Prevent infinite loops for open ranges
-/**
- * Parse a single range part (e.g., "1-3", "5", "7-")
- */
-const parseRangePart = (part, pages) => {
-    const trimmedPart = part.trim();
-    if (trimmedPart.includes('-')) {
-        const [startStr, endStr] = trimmedPart.split('-');
-        if (startStr === undefined) {
-            throw new Error(`Invalid page range format: ${trimmedPart}`);
-        }
-        const start = parseInt(startStr, 10);
-        const end = endStr === '' || endStr === undefined ? Infinity : parseInt(endStr, 10);
-        if (Number.isNaN(start) || Number.isNaN(end) || start <= 0 || start > end) {
-            throw new Error(`Invalid page range values: ${trimmedPart}`);
-        }
-        const practicalEnd = Math.min(end, start + MAX_RANGE_SIZE);
-        for (let i = start; i <= practicalEnd; i++) {
-            pages.add(i);
-        }
-        if (end === Infinity && practicalEnd === start + MAX_RANGE_SIZE) {
-            console.warn(`[PDF Reader MCP] Open-ended range starting at ${String(start)} was truncated at page ${String(practicalEnd)}.`);
-        }
-    }
-    else {
-        const page = parseInt(trimmedPart, 10);
-        if (Number.isNaN(page) || page <= 0) {
-            throw new Error(`Invalid page number: ${trimmedPart}`);
-        }
-        pages.add(page);
-    }
-};
-/**
- * Parse page range string into array of page numbers
- * @param ranges - Range string (e.g., "1-3,5,7-10")
- * @returns Sorted array of unique page numbers
- */
-export const parsePageRanges = (ranges) => {
-    const pages = new Set();
-    const parts = ranges.split(',');
-    for (const part of parts) {
-        parseRangePart(part, pages);
-    }
-    if (pages.size === 0) {
-        throw new Error('Page range string resulted in zero valid pages.');
-    }
-    return Array.from(pages).sort((a, b) => a - b);
-};
-/**
- * Get target pages from page specification
- * @param sourcePages - Page specification (string or array)
- * @param sourceDescription - Description for error messages
- * @returns Array of page numbers or undefined
- */
-export const getTargetPages = (sourcePages, sourceDescription) => {
-    if (!sourcePages) {
-        return undefined;
-    }
-    try {
-        if (typeof sourcePages === 'string') {
-            return parsePageRanges(sourcePages);
-        }
-        // Array of page numbers
-        if (sourcePages.some((p) => !Number.isInteger(p) || p <= 0)) {
-            throw new Error('Page numbers in array must be positive integers.');
-        }
-        const uniquePages = [...new Set(sourcePages)].sort((a, b) => a - b);
-        if (uniquePages.length === 0) {
-            throw new Error('Page specification resulted in an empty set of pages.');
-        }
-        return uniquePages;
-    }
-    catch (error) {
-        const message = error instanceof Error ? error.message : String(error);
-        throw new McpError(ErrorCode.InvalidParams, `Invalid page specification for source ${sourceDescription}: ${message}`);
-    }
-};
-/**
- * Determine which pages to process based on target pages and document size
- */
-export const determinePagesToProcess = (targetPages, totalPages, includeFullText) => {
-    if (targetPages) {
-        const pagesToProcess = targetPages.filter((p) => p <= totalPages);
-        const invalidPages = targetPages.filter((p) => p > totalPages);
-        return { pagesToProcess, invalidPages };
-    }
-    if (includeFullText) {
-        const pagesToProcess = Array.from({ length: totalPages }, (_, i) => i + 1);
-        return { pagesToProcess, invalidPages: [] };
-    }
-    return { pagesToProcess: [], invalidPages: [] };
-};

package/dist/schemas/readPdf.js

@@ -1,55 +0,0 @@
-// Zod validation schemas for PDF reading
-import { z } from 'zod';
-// Schema for page specification (array of numbers or range string)
-export const 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")'),
-]);
-// Schema for a single PDF source (path or URL)
-export const pdfSourceSchema = z
-    .object({
-    path: z.string().min(1).optional().describe('Relative path to the local PDF file.'),
-    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.",
-});
-// Schema for the read_pdf tool arguments
-export const 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();

package/dist/types/pdf.js

@@ -1,2 +0,0 @@
-// PDF-related TypeScript type definitions
-export {};

package/dist/utils/pathUtils.js

@@ -1,30 +0,0 @@
-// Removed unused import: import { fileURLToPath } from 'url';
-import path from 'node:path';
-import { ErrorCode, McpError } from '@modelcontextprotocol/sdk/types.js';
-// Use the server's current working directory as the project root.
-// This relies on the process launching the server to set the CWD correctly.
-export const PROJECT_ROOT = process.cwd();
-console.info(`[Filesystem MCP - pathUtils] Project Root determined from CWD: ${PROJECT_ROOT}`); // Use info instead of log
-/**
- * Resolves a user-provided relative path against the project root,
- * ensuring it stays within the project boundaries.
- * Throws McpError on invalid input, absolute paths, or path traversal.
- * @param userPath The relative path provided by the user.
- * @returns The resolved absolute path.
- */
-export const resolvePath = (userPath) => {
-    if (typeof userPath !== 'string') {
-        throw new McpError(ErrorCode.InvalidParams, 'Path must be a string.');
-    }
-    const normalizedUserPath = path.normalize(userPath);
-    if (path.isAbsolute(normalizedUserPath)) {
-        throw new McpError(ErrorCode.InvalidParams, 'Absolute paths are not allowed.');
-    }
-    // Resolve against the calculated PROJECT_ROOT
-    const resolved = path.resolve(PROJECT_ROOT, normalizedUserPath);
-    // Security check: Ensure the resolved path is still within the project root
-    if (!resolved.startsWith(PROJECT_ROOT)) {
-        throw new McpError(ErrorCode.InvalidRequest, 'Path traversal detected. Access denied.');
-    }
-    return resolved;
-};