all-in-mcp 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

all_in_mcp/academic_platforms/__init__.py

@@ -3,4 +3,4 @@ from .base import PaperSource
 from .cryptobib import CryptoBibSearcher
 from .iacr import IACRSearcher
 
-__all__ = ["PaperSource", "CryptoBibSearcher", "IACRSearcher"]
+__all__ = ["CryptoBibSearcher", "IACRSearcher", "PaperSource"]

all_in_mcp/academic_platforms/cryptobib.py

@@ -1,6 +1,5 @@
 # all_in_mcp/academic_platforms/cryptobib.py
 import logging
-import os
 import random
 import re
 from datetime import datetime
@@ -118,7 +117,7 @@ class CryptoBibSearcher(PaperSource):
 
             # Extract fields using a more robust approach
             # First, normalize the text by removing extra whitespace
-            normalized_text = re.sub(r"\s+", " ", bibtex_text)
+            re.sub(r"\s+", " ", bibtex_text)
 
             # Extract fields with better pattern matching
             field_dict = {}
@@ -263,7 +262,7 @@ class CryptoBibSearcher(PaperSource):
             # Convert query to lowercase for case-insensitive search
             query_lower = query.lower()
 
-            with open(self.bib_file_path, "r", encoding="utf-8") as f:
+            with open(self.bib_file_path, encoding="utf-8") as f:
                 for line_num, line in enumerate(f, 1):
                     # Check if this is the start of a new entry
                     if line.strip().startswith("@") and not in_entry:
@@ -395,10 +394,10 @@ class CryptoBibSearcher(PaperSource):
             in_entry = False
             brace_count = 0
 
-            with open(self.bib_file_path, "r", encoding="utf-8") as f:
+            with open(self.bib_file_path, encoding="utf-8") as f:
                 for line in f:
                     # Check if this is the start of the entry we're looking for
-                    if line.strip().startswith(f"@") and entry_key in line:
+                    if line.strip().startswith("@") and entry_key in line:
                         current_entry = line
                         in_entry = True
                         brace_count = line.count("{") - line.count("}")

all_in_mcp/paper.py

@@ -1,6 +1,12 @@
 # all_in_mcp/paper.py
+import io
 from dataclasses import dataclass
 from datetime import datetime
+from pathlib import Path
+from urllib.parse import urlparse
+
+import httpx
+from pypdf import PdfReader
 
 
 @dataclass
@@ -62,3 +68,134 @@ class Paper:
             "references": self.references,
             "extra": self.extra,
         }
+
+    def read_content(self) -> str:
+        """
+        Read the full text content of this paper's PDF.
+
+        Returns:
+            str: Extracted text content from the paper's PDF
+
+        Raises:
+            ValueError: If no PDF URL is available
+            Exception: If PDF cannot be read or processed
+        """
+        if not self.pdf_url:
+            raise ValueError("No PDF URL available for this paper")
+
+        return read_pdf(self.pdf_url)
+
+
+def read_pdf(pdf_source: str | Path) -> str:
+    """
+    Extract text content from a PDF file (local or online).
+
+    Args:
+        pdf_source: Path to local PDF file or URL to online PDF
+
+    Returns:
+        str: Extracted text content from the PDF
+
+    Raises:
+        FileNotFoundError: If local file doesn't exist
+        ValueError: If URL is invalid or PDF cannot be processed
+        Exception: For other PDF processing errors
+    """
+    try:
+        if isinstance(pdf_source, str | Path):
+            pdf_source_str = str(pdf_source)
+
+            # Check if it's a URL
+            parsed = urlparse(pdf_source_str)
+            if parsed.scheme in ("http", "https"):
+                # Handle online PDF
+                return _read_pdf_from_url(pdf_source_str)
+            else:
+                # Handle local file
+                return _read_pdf_from_file(Path(pdf_source_str))
+        else:
+            raise ValueError("pdf_source must be a string or Path object")
+
+    except Exception as e:
+        raise Exception(f"Failed to read PDF from {pdf_source}: {e!s}") from e
+
+
+def _read_pdf_from_file(file_path: Path) -> str:
+    """Read PDF from local file path."""
+    if not file_path.exists():
+        raise FileNotFoundError(f"PDF file not found: {file_path}")
+
+    if not file_path.suffix.lower() == ".pdf":
+        raise ValueError(f"File must have .pdf extension: {file_path}")
+
+    try:
+        with open(file_path, "rb") as file:
+            pdf_reader = PdfReader(file)
+            text_content = []
+
+            for page_num, page in enumerate(pdf_reader.pages):
+                try:
+                    page_text = page.extract_text()
+                    if page_text.strip():  # Only add non-empty pages
+                        text_content.append(
+                            f"--- Page {page_num + 1} ---\n{page_text}\n"
+                        )
+                except Exception as e:
+                    text_content.append(
+                        f"--- Page {page_num + 1} (Error reading page: {e!s}) ---\n"
+                    )
+
+            return "\n".join(text_content)
+
+    except Exception as e:
+        raise Exception(f"Error reading PDF file {file_path}: {e!s}") from e
+
+
+def _read_pdf_from_url(url: str) -> str:
+    """Download and read PDF from URL."""
+    try:
+        # Download PDF with proper headers
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
+        }
+
+        with httpx.Client(timeout=30.0, headers=headers) as client:
+            response = client.get(url)
+            response.raise_for_status()
+
+            # Check if content is actually a PDF
+            content_type = response.headers.get("content-type", "").lower()
+            if "application/pdf" not in content_type and not url.lower().endswith(
+                ".pdf"
+            ):
+                # Try to detect PDF by content
+                if not response.content.startswith(b"%PDF"):
+                    raise ValueError(f"URL does not point to a valid PDF file: {url}")
+
+            # Read PDF from bytes
+            pdf_bytes = io.BytesIO(response.content)
+            pdf_reader = PdfReader(pdf_bytes)
+            text_content = []
+
+            for page_num, page in enumerate(pdf_reader.pages):
+                try:
+                    page_text = page.extract_text()
+                    if page_text.strip():  # Only add non-empty pages
+                        text_content.append(
+                            f"--- Page {page_num + 1} ---\n{page_text}\n"
+                        )
+                except Exception as e:
+                    text_content.append(
+                        f"--- Page {page_num + 1} (Error reading page: {e!s}) ---\n"
+                    )
+
+            return "\n".join(text_content)
+
+    except httpx.RequestError as e:
+        raise Exception(f"Network error downloading PDF from {url}: {e!s}") from e
+    except httpx.HTTPStatusError as e:
+        raise Exception(
+            f"HTTP error {e.response.status_code} downloading PDF from {url}"
+        ) from e
+    except Exception as e:
+        raise Exception(f"Error processing PDF from URL {url}: {e!s}") from e

all_in_mcp/server.py

@@ -1,13 +1,13 @@
-import os
-from typing import List, Dict
 import mcp.server.stdio
 import mcp.types as types
 from mcp.server import NotificationOptions, Server
 from mcp.server.models import InitializationOptions
 
+from .academic_platforms.cryptobib import CryptoBibSearcher
+
 # Import searchers
 from .academic_platforms.iacr import IACRSearcher
-from .academic_platforms.cryptobib import CryptoBibSearcher
+from .paper import read_pdf
 
 server = Server("all-in-mcp")
 
@@ -122,6 +122,20 @@ async def handle_list_tools() -> list[types.Tool]:
                 "required": ["query"],
             },
         ),
+        types.Tool(
+            name="read-pdf",
+            description="Read and extract text content from a PDF file (local or online)",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "pdf_source": {
+                        "type": "string",
+                        "description": "Path to local PDF file or URL to online PDF",
+                    },
+                },
+                "required": ["pdf_source"],
+            },
+        ),
     ]
 
 
@@ -323,6 +337,27 @@ async def handle_call_tool(
 
                 return [types.TextContent(type="text", text=result_text)]
 
+        elif name == "read-pdf":
+            pdf_source = arguments.get("pdf_source", "")
+
+            if not pdf_source:
+                return [
+                    types.TextContent(
+                        type="text", text="Error: pdf_source parameter is required"
+                    )
+                ]
+
+            try:
+                result = read_pdf(pdf_source)
+                return [types.TextContent(type="text", text=result)]
+
+            except Exception as e:
+                return [
+                    types.TextContent(
+                        type="text", text=f"Error reading PDF from {pdf_source}: {e!s}"
+                    )
+                ]
+
         else:
             raise ValueError(f"Unknown tool: {name}")
 

{all_in_mcp-0.2.2.dist-info → all_in_mcp-0.2.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: all-in-mcp
-Version: 0.2.2
+Version: 0.2.3
 Summary: An MCP (Model Context Protocol) server providing daily-use utility functions and academic paper search capabilities
 Project-URL: Homepage, https://github.com/jiahaoxiang2000/all-in-mcp
 Project-URL: Repository, https://github.com/jiahaoxiang2000/all-in-mcp
@@ -53,6 +53,7 @@ An MCP (Model Context Protocol) server that provides daily-use utility functions
 
 - **Academic Research**: IACR ePrint Archive paper search, download, and reading
 - **Bibliography Search**: CryptoBib database search for cryptography papers
+- **PDF Reading**: Read and extract text from local and online PDF files
 
 ### Paper Search Capabilities
 

all_in_mcp-0.2.3.dist-info/RECORD

@@ -0,0 +1,12 @@
+all_in_mcp/__init__.py,sha256=REDwcbifpuUnsFAhNowIKCZ-8g6irIzUFTI_f8Aunxk,215
+all_in_mcp/paper.py,sha256=vSJyC_ehfZX5-ASYG048z8gaD1LKafFdJvR13iQcJRw,7104
+all_in_mcp/server.py,sha256=pMGyRbgr_kwC_ZNsxMUwXcoEQ8fW4NZx3Sns7uRRa8I,15140
+all_in_mcp/academic_platforms/__init__.py,sha256=2KgWMc38NBhRkiLYwqyKi43u-Wm5vWK8i-es3fQFlN0,210
+all_in_mcp/academic_platforms/base.py,sha256=VYMp8_tnp7YzXKAXLfr7uUxgvJBNKRyC_NT1uVhBOwY,673
+all_in_mcp/academic_platforms/cryptobib.py,sha256=F9N23eojfyAIjnFDPrJAYOpZ_Vi9iHOqNHGtKC6O16c,17360
+all_in_mcp/academic_platforms/iacr.py,sha256=MUPxFycVS0eMsJok71y12RUqjxbRrCReG33V5ORAbfU,15450
+all_in_mcp-0.2.3.dist-info/METADATA,sha256=43FE07lBZ-f92fi1AemtCEQO_IVXyKD1d_keztjtcYI,5750
+all_in_mcp-0.2.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+all_in_mcp-0.2.3.dist-info/entry_points.txt,sha256=FbQOtUQzOIfkMNp4qQV1NTU9K4J7C0XGH9wKKhfK1VM,47
+all_in_mcp-0.2.3.dist-info/licenses/LICENSE,sha256=idExTHItK7AC5FVo4H9HKnr6h51Z8BKCEztZPyP8nK8,1062
+all_in_mcp-0.2.3.dist-info/RECORD,,

all_in_mcp-0.2.2.dist-info/RECORD

@@ -1,12 +0,0 @@
-all_in_mcp/__init__.py,sha256=REDwcbifpuUnsFAhNowIKCZ-8g6irIzUFTI_f8Aunxk,215
-all_in_mcp/paper.py,sha256=QVH2BQpQT3I14T2IaZs1ZeC-MJVoFNVYZXSs1iHlGLY,2293
-all_in_mcp/server.py,sha256=CDiHXXMPlNPMLcpnjrZ5zoKrujNxZLryf8ecgtYt-bg,13971
-all_in_mcp/academic_platforms/__init__.py,sha256=-Asc2WpmfyvCCF0s-Ni6kcz8dkyyV7n3gjhhD2Oq1BA,210
-all_in_mcp/academic_platforms/base.py,sha256=VYMp8_tnp7YzXKAXLfr7uUxgvJBNKRyC_NT1uVhBOwY,673
-all_in_mcp/academic_platforms/cryptobib.py,sha256=4vLVNQdWBw6YLHPlw6bJVEGlsoihPE9rUfNCiAdu5Ic,17399
-all_in_mcp/academic_platforms/iacr.py,sha256=MUPxFycVS0eMsJok71y12RUqjxbRrCReG33V5ORAbfU,15450
-all_in_mcp-0.2.2.dist-info/METADATA,sha256=tHh2ZAZkW_mRnk44Arz06bn0xxyMV4xoAtJKuf7_rXs,5677
-all_in_mcp-0.2.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-all_in_mcp-0.2.2.dist-info/entry_points.txt,sha256=FbQOtUQzOIfkMNp4qQV1NTU9K4J7C0XGH9wKKhfK1VM,47
-all_in_mcp-0.2.2.dist-info/licenses/LICENSE,sha256=idExTHItK7AC5FVo4H9HKnr6h51Z8BKCEztZPyP8nK8,1062
-all_in_mcp-0.2.2.dist-info/RECORD,,