academic-refchecker 1.2.65__py3-none-any.whl → 1.2.66__py3-none-any.whl

{academic_refchecker-1.2.65.dist-info → academic_refchecker-1.2.66.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 1.2.65
+Version: 1.2.66
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT
@@ -57,6 +57,16 @@ Provides-Extra: vllm
 Requires-Dist: vllm>=0.3.0; extra == "vllm"
 Requires-Dist: huggingface_hub>=0.17.0; extra == "vllm"
 Requires-Dist: torch>=2.0.0; extra == "vllm"
+Provides-Extra: webui
+Requires-Dist: fastapi>=0.100.0; extra == "webui"
+Requires-Dist: uvicorn[standard]>=0.22.0; extra == "webui"
+Requires-Dist: pydantic>=2.0.0; extra == "webui"
+Requires-Dist: aiosqlite>=0.19.0; extra == "webui"
+Requires-Dist: httpx>=0.24.0; extra == "webui"
+Requires-Dist: cryptography>=42.0.0; extra == "webui"
+Requires-Dist: pymupdf>=1.23.0; extra == "webui"
+Requires-Dist: Pillow>=9.0.0; extra == "webui"
+Requires-Dist: python-multipart>=0.0.6; extra == "webui"
 Dynamic: license-file
 
 # 📚 Academic Paper Reference Checker
@@ -176,9 +186,18 @@ Learn about RefChecker's design philosophy and development process in this detai
 
 RefChecker also includes a modern web interface with real-time progress updates, check history, and export options.
 
+### Prerequisites
+
+- **Python 3.8+** with RefChecker installed (`pip install academic-refchecker[webui]`)
+- **Node.js 18+** and npm
+
 ### Quick Start (Web UI)
 
 ```bash
+# Install Python dependencies (if not already done)
+pip install academic-refchecker[llm,webui]
+
+# Install Node.js dependencies
 cd web-ui
 npm install    # First time only
 npm start      # Starts both backend and frontend
@@ -186,6 +205,20 @@ npm start      # Starts both backend and frontend
 
 Then open **http://localhost:5173** in your browser.
 
+### Alternative: Start Servers Separately
+
+**Terminal 1 - Backend:**
+```bash
+refchecker-webui --port 8000
+# Or: python -m uvicorn backend.main:app --port 8000
+```
+
+**Terminal 2 - Frontend:**
+```bash
+cd web-ui
+npm run dev
+```
+
 ### Features
 
 - ✨ Real-time validation with live progress updates
@@ -284,24 +317,33 @@ You can debug vllm server issues by running refchecker with the `--debug` flag.
 
 ## 📦 Installation
 
+### Prerequisites
+
+- **Python 3.8+** (3.10+ recommended)
+- **Node.js 18+** and npm (only required for Web UI)
+
 ### Option 1: Install from PyPI (Recommended)
 
 For the latest stable release with all features:
 
 ```bash
-pip install academic-refchecker[llm,dev,optional]
+pip install academic-refchecker[llm,webui]
 ```
 
 This installs RefChecker with:
 - **llm**: Support for OpenAI, Anthropic, Google, Azure, and vLLM providers
-- **dev**: Development tools (pytest, black, flake8, mypy)
-- **optional**: Enhanced features (lxml, selenium, pikepdf, nltk, scikit-learn)
+- **webui**: Web interface dependencies (FastAPI, uvicorn, etc.)
 
-For a minimal installation:
+For a minimal installation (CLI only, no LLM or Web UI):
 ```bash
 pip install academic-refchecker
 ```
 
+Other optional extras:
+- **dev**: Development tools (pytest, black, flake8, mypy)
+- **optional**: Enhanced features (lxml, selenium, pikepdf, nltk, scikit-learn)
+- **vllm**: Local model inference with vLLM
+
 ### Option 2: Install from Source
 
 #### 1. Clone the Repository
@@ -311,13 +353,27 @@ git clone https://github.com/markrussinovich/refchecker.git
 cd refchecker
 ```
 
-#### 2. Install Dependencies
+#### 2. Create and Activate Virtual Environment (Recommended)
+
+```bash
+python -m venv .venv
+# On Windows:
+.venv\Scripts\activate
+# On macOS/Linux:
+source .venv/bin/activate
+```
+
+#### 3. Install Dependencies
 
 ```bash
+# Install all dependencies including LLM and Web UI support
+pip install -e ".[llm,webui]"
+
+# Or install from requirements.txt
 pip install -r requirements.txt
 ```
 
-#### 3. (Optional) Install Additional Dependencies
+#### 4. (Optional) Install Additional Dependencies
 
 For enhanced performance and LLM support, you can install optional dependencies:
 
@@ -337,6 +393,15 @@ pip install selenium
 pip install pikepdf
 ```
 
+### Web UI Installation
+
+The Web UI requires Node.js 18+ in addition to the Python dependencies:
+
+```bash
+cd web-ui
+npm install
+```
+
 ## 📖 Usage
 
 Check papers in various formats and online locations:

{academic_refchecker-1.2.65.dist-info → academic_refchecker-1.2.66.dist-info}/RECORD

@@ -1,16 +1,26 @@
-academic_refchecker-1.2.65.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+academic_refchecker-1.2.66.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+backend/__init__.py,sha256=TFVkOx5tSp3abty15RzUbaSwQ9ZD0kfUn7PDh63xkYY,521
+backend/__main__.py,sha256=74V7yUMsRSZaaRyXYm-rZVc3TVUcUgwsoTQTUbV5EqM,211
+backend/cli.py,sha256=SCwaLObaO9F-tiDCbPJF6DXwiamSsdDz50E1OX-6T08,1379
+backend/concurrency.py,sha256=2KY9I_8dDkyl_HTGx27ZxU4rFXx2vqbGOlo5RrRbPjA,3223
+backend/database.py,sha256=TP5wRt4wzQC8mk5CyTSmCVJQza9kUwNUuWpQarPYmbc,29794
+backend/main.py,sha256=hcY1lV82f1B-8Nu_IO3Y7Fqhb_4bH64n8FfGAtDv9x4,49594
+backend/models.py,sha256=El2F-RTHgxQ7-WODmiYCpjsTFDpjwF9PBt-JDa_XipE,2591
+backend/refchecker_wrapper.py,sha256=B8oERiF81Pbrv0bS9CWUiFIzUQyfXCv8k4dz_jojaYk,51935
+backend/thumbnail.py,sha256=wPFXp3RlmcL9jVKZmSBRB7Pfy9Ti7nCnzNtL4osfNtM,17618
+backend/websocket_manager.py,sha256=l-Wou-rKV6n7t6Gcf5fR6s_4G-mssSrba0davNnYS70,4247
 refchecker/__init__.py,sha256=Pg5MrtLxDBRcNYcI02N-bv3tzURVd1S3nQ8IyF7Zw7E,322
 refchecker/__main__.py,sha256=agBbT9iKN0g2xXtRNCoh29Nr7z2n5vU-r0MCVJKi4tI,232
-refchecker/__version__.py,sha256=-juWRtkS6KT5HfM6qutVTGGQhABXogbKSSl54kxuPBY,89
+refchecker/__version__.py,sha256=riI0sV8UuNdPwTFz-z5QxcMQEIeBO61ZM-kvhsyG3-Y,89
 refchecker/checkers/__init__.py,sha256=T0PAHTFt6UiGvn-WGoJU8CdhXNmf6zaHmcGVoWHhmJQ,533
-refchecker/checkers/crossref.py,sha256=5BeSCK8K_S_-iwgQaNAbxZGNsxaxOyBzUQ3AD0Rc6nU,20433
-refchecker/checkers/enhanced_hybrid_checker.py,sha256=c5I_h8w6xD7XkBNkbneffeAnrO8B-uXH99edWBJvDMo,27788
+refchecker/checkers/crossref.py,sha256=88moAyTudBqf9SKqTQkNAq1yyuRe95f8r4EpmJznupQ,20937
+refchecker/checkers/enhanced_hybrid_checker.py,sha256=2jIeUX7hankPok3M4de9o2bsJZ17ZomuLkdfdr9EV0s,28671
 refchecker/checkers/github_checker.py,sha256=YJ2sLj22qezw3uWjA0jhtDO0fOW4HUwcVbv2DQ4LjR0,14277
-refchecker/checkers/local_semantic_scholar.py,sha256=KuVL3LTtlN84t88nFuMSPBj3bUawEzdtBHFM0w3rFvw,21024
-refchecker/checkers/openalex.py,sha256=omMQbZOnkDndMJSl9SQVtiETzpv1w1pt93YjlFTq8WA,19616
+refchecker/checkers/local_semantic_scholar.py,sha256=wJtMwyu_PgLF0CGsyip42auTnRyObTRxCRiv_N8l78Q,21024
+refchecker/checkers/openalex.py,sha256=WEjEppQMbutPs8kWOSorCIoXWqpJ9o1CXUicThHSWYU,20120
 refchecker/checkers/openreview_checker.py,sha256=0IHZe4Nscy8fle28rmhy1hhsofR5g0FFSakk8FFH_0A,40540
 refchecker/checkers/pdf_paper_checker.py,sha256=lrg09poNJBz9FNMrUoEjQ6CJbdYZAVANw0bCaTSb5oo,19904
-refchecker/checkers/semantic_scholar.py,sha256=kCNn1hu2R9vQhUEn2wqQ9qgVfIRRQGzk7Z5sB1VyWlE,35506
+refchecker/checkers/semantic_scholar.py,sha256=T8PSJfyYP1BlbW9_hhZTlxVOeBMyGHJap989PMpDrEE,36012
 refchecker/checkers/webpage_checker.py,sha256=A_d5kg3OOsyliC00OVq_l0J-RJ4Ln7hUoURk21aO2fs,43653
 refchecker/config/__init__.py,sha256=r7sONsX2-ITviUJRU1KEz76uAuTRqZlzU-TVkvFRGYY,15
 refchecker/config/logging.conf,sha256=r1tP0ApLHtlz7rV-oKS1MVO7oXJOgahbZFTtYmKnf9U,687
@@ -18,7 +28,7 @@ refchecker/config/settings.py,sha256=-vODFoXbWbGPUElpmchE5zbCj_n4Vtxr8HU1hQDFp_c
 refchecker/core/__init__.py,sha256=1T2MSQyDk0u_PupbHvm4CvNNN--dxsw78fqKUrqoYrM,157
 refchecker/core/db_connection_pool.py,sha256=XRiOdehikkSz3obH4WKgf8woa3694if50Q15rBT-4XQ,4697
 refchecker/core/parallel_processor.py,sha256=HpVFEMwPBiP2FRjvGqlaXpjV5S0qP-hxdB_Wdl_lACo,17704
-refchecker/core/refchecker.py,sha256=UnsQ7odItgdqKtDVLVtniNJ8R29VnvlRPcZ5VJJBi0Q,286685
+refchecker/core/refchecker.py,sha256=rP5_-9eRhn6rxtoC7LCJyaOdNNGX5AS5K1S7ZNN3bo0,287343
 refchecker/database/__init__.py,sha256=mEuVHlEBuS44t_2ZT_JnvQQrlRCjo1SJq1NmaJ6r8OY,125
 refchecker/database/download_semantic_scholar_db.py,sha256=waN4I97KC_36YMiPbiBDUUmgfzu1nub5yeKdAsIR2aw,75276
 refchecker/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -28,22 +38,22 @@ refchecker/scripts/__init__.py,sha256=xJwo6afG8s7S888BK2Bxw2d7FX8aLkbl0l_ZoJOFib
 refchecker/scripts/start_vllm_server.py,sha256=ZepWp2y2cKFW0Kgsoima2RbmF02fTU29UFcLLpsBhFU,4213
 refchecker/services/__init__.py,sha256=jGi9S74Msak3YR-C4Qb68VU7HB4oLaX9o1rlVAFpOFI,187
 refchecker/services/pdf_processor.py,sha256=7i5x043qfnyzE5EQmytfy_uPjbeCJp4Ka5OPyH-bwOE,10577
-refchecker/utils/__init__.py,sha256=1RrGoIIn1_gVzxd56b6a7HeAS-wu7uDP-nxLbR3fJ-8,1199
-refchecker/utils/arxiv_utils.py,sha256=PvMBJGubvDvo9_WxrXUH4OWMNrEAD7z7NCcRl0la2iI,20601
+refchecker/utils/__init__.py,sha256=SKTEQeKpLOFFMIzZiakzctsW9zGe_J7LDNJlygWV6RY,1221
+refchecker/utils/arxiv_utils.py,sha256=C7wqoCy9FZUQpoF92vLeJyrK1-6XoMmmL6u_hfDV3ro,18031
 refchecker/utils/author_utils.py,sha256=DLTo1xsxef2wxoe4s_MWrh36maj4fgnvFlsDLpDE-qQ,5507
 refchecker/utils/biblatex_parser.py,sha256=IKRUMtRsjdXIktyk9XGArt_ms0asmqP549uhFvvumuE,25581
 refchecker/utils/bibliography_utils.py,sha256=d6kqDOQou_PX6WQkOzrGyN5GpzaOjhu54w9wGfBRQZw,11760
 refchecker/utils/bibtex_parser.py,sha256=xY0dEqT8lBZF-W21YRpG28lp_F2ikLan7nK70WiCU2o,15286
 refchecker/utils/config_validator.py,sha256=rxf7K3DYmJ-BNPsmtaCNipY2BTVT-pJZ7wN-M9Y3GC8,11167
 refchecker/utils/db_utils.py,sha256=_wSupfBlm0ILFvntQTvoj7tLDCbrYPRQrp9NDvphF_E,6281
-refchecker/utils/doi_utils.py,sha256=ezUiRnYRpoO0U_Rqgxv1FxqmeTwPh6X8gLgSDbqg5sY,4874
-refchecker/utils/error_utils.py,sha256=IT-5128mAEMdx4R7dtBOfCvGhTu1-UumM77m762Mcs4,12555
+refchecker/utils/doi_utils.py,sha256=_7YvQ0DTOQBMIujUE0SdJicjPiAR3VETLU668GIji24,6094
+refchecker/utils/error_utils.py,sha256=PbB9HP2eoiWTIvRqzyh1SDhEgCEc7ecN5hVB-dUFP5Q,13093
 refchecker/utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
-refchecker/utils/text_utils.py,sha256=d_X4r1nVvkL7i0DhxfLaVK3CzbMP2oZvqX3kxfDudQw,220978
+refchecker/utils/text_utils.py,sha256=v5beDt_fyx4ETfTXLYrDMp3CuUGoDoLs7-d1H2GdySE,228585
 refchecker/utils/unicode_utils.py,sha256=-WBKarXO756p7fd7gCeNsMag4ztDNURwFX5IVniOtwY,10366
 refchecker/utils/url_utils.py,sha256=7b0rWCQJSajzqOvD7ghsBZPejiq6mUIz6SGhvU_WGDs,9441
-academic_refchecker-1.2.65.dist-info/METADATA,sha256=k6dmILrrK9b2yKN56l1-gZFdPruDfRp0s7Us6TpdifU,24104
-academic_refchecker-1.2.65.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academic_refchecker-1.2.65.dist-info/entry_points.txt,sha256=kG6k2JwFIRvmKe0oZTr2RYStyfl79BirJxyaO6kjIxA,72
-academic_refchecker-1.2.65.dist-info/top_level.txt,sha256=ZdIg_PFHiATpVT5Uvp4L17Q0d8mk8ZBsINXKf1tE0bo,11
-academic_refchecker-1.2.65.dist-info/RECORD,,
+academic_refchecker-1.2.66.dist-info/METADATA,sha256=Qb0y3NPV9VPdNDEICSvkfLHoYE3n6Hl4kBXbN4RO3O8,25778
+academic_refchecker-1.2.66.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academic_refchecker-1.2.66.dist-info/entry_points.txt,sha256=9cREsaKwlp05Ql0CBIjKrNHk5IG2cHY5LvJPsV2-SxA,108
+academic_refchecker-1.2.66.dist-info/top_level.txt,sha256=FfNvrvpj25gfpUBjW0epvz7Qrdejhups5Za_DBiSRu4,19
+academic_refchecker-1.2.66.dist-info/RECORD,,

{academic_refchecker-1.2.65.dist-info → academic_refchecker-1.2.66.dist-info}/entry_points.txt

@@ -1,2 +1,3 @@
 [console_scripts]
 academic-refchecker = refchecker.core.refchecker:main
+refchecker-webui = backend.cli:main

{academic_refchecker-1.2.65.dist-info → academic_refchecker-1.2.66.dist-info}/top_level.txt

@@ -1 +1,2 @@
+backend
 refchecker

backend/__init__.py

@@ -0,0 +1,21 @@
+# Backend package for RefChecker Web UI
+"""
+RefChecker Web UI Backend
+
+This package provides the FastAPI backend for the RefChecker Web UI,
+including WebSocket support for real-time progress updates.
+
+Usage:
+    # As a command line tool (after pip install):
+    refchecker-webui --host 0.0.0.0 --port 8000
+    
+    # As a Python module:
+    python -m backend --host 0.0.0.0 --port 8000
+    
+    # With uvicorn directly:
+    uvicorn backend.main:app --host 0.0.0.0 --port 8000
+"""
+
+from .main import app
+
+__all__ = ["app"]

backend/__main__.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python3
+"""
+Allow running backend as a module: python -m backend
+
+This provides a clean entry point for the WebUI backend server.
+"""
+
+from .cli import main
+
+if __name__ == "__main__":
+    main()

backend/cli.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""
+CLI entry point for RefChecker Web UI backend server.
+
+This module provides the console script entry point for the refchecker-webui command.
+"""
+
+import sys
+import argparse
+
+
+def main():
+    """Main entry point for the refchecker-webui command."""
+    parser = argparse.ArgumentParser(
+        description="Start the RefChecker Web UI backend server"
+    )
+    parser.add_argument(
+        "--host", 
+        default="0.0.0.0", 
+        help="Host to bind to (default: 0.0.0.0)"
+    )
+    parser.add_argument(
+        "--port", 
+        type=int, 
+        default=8000, 
+        help="Port to listen on (default: 8000)"
+    )
+    parser.add_argument(
+        "--reload",
+        action="store_true",
+        help="Enable auto-reload for development"
+    )
+    
+    args = parser.parse_args()
+    
+    try:
+        import uvicorn
+    except ImportError:
+        print("Error: uvicorn is not installed.")
+        print("Install it with: pip install 'academic-refchecker[webui]'")
+        sys.exit(1)
+    
+    print(f"Starting RefChecker Web UI backend on http://{args.host}:{args.port}")
+    print("Make sure to start the frontend separately (cd web-ui && npm run dev)")
+    print()
+    
+    uvicorn.run(
+        "backend.main:app",
+        host=args.host,
+        port=args.port,
+        reload=args.reload
+    )
+
+
+if __name__ == "__main__":
+    main()

backend/concurrency.py

@@ -0,0 +1,100 @@
+"""
+Global concurrency limiter for reference checking across all papers.
+
+This module provides a system-wide semaphore that limits the total number
+of concurrent reference checks, regardless of how many papers are being
+checked simultaneously.
+"""
+import asyncio
+from typing import Optional
+import logging
+
+logger = logging.getLogger(__name__)
+
+# Default max concurrent reference checks
+DEFAULT_MAX_CONCURRENT = 6
+
+class GlobalConcurrencyLimiter:
+    """
+    System-wide concurrency limiter for reference checks.
+    
+    Uses a semaphore to limit total concurrent operations across
+    all paper checks.
+    """
+    
+    def __init__(self, max_concurrent: int = DEFAULT_MAX_CONCURRENT):
+        self._max_concurrent = max_concurrent
+        self._semaphore = asyncio.Semaphore(max_concurrent)
+        self._active_count = 0
+        self._lock = asyncio.Lock()
+    
+    @property
+    def max_concurrent(self) -> int:
+        return self._max_concurrent
+    
+    @property
+    def active_count(self) -> int:
+        return self._active_count
+    
+    async def set_max_concurrent(self, value: int):
+        """
+        Update the max concurrent limit.
+        
+        Note: This recreates the semaphore, so it should only be called
+        when no operations are in progress, or the caller should be aware
+        that current limits may temporarily exceed the new value.
+        """
+        if value < 1:
+            value = 1
+        if value > 50:
+            value = 50
+        
+        async with self._lock:
+            old_value = self._max_concurrent
+            self._max_concurrent = value
+            self._semaphore = asyncio.Semaphore(value)
+            logger.info(f"Global concurrency limit changed from {old_value} to {value}")
+    
+    async def acquire(self):
+        """Acquire a slot in the concurrency pool."""
+        await self._semaphore.acquire()
+        async with self._lock:
+            self._active_count += 1
+            logger.debug(f"Acquired slot, active: {self._active_count}/{self._max_concurrent}")
+    
+    def release(self):
+        """Release a slot back to the concurrency pool."""
+        self._semaphore.release()
+        # Note: can't use async lock in sync context, so we do best-effort count
+        self._active_count = max(0, self._active_count - 1)
+        logger.debug(f"Released slot, active: {self._active_count}/{self._max_concurrent}")
+    
+    async def __aenter__(self):
+        await self.acquire()
+        return self
+    
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        self.release()
+        return False
+
+
+# Global singleton instance
+_limiter: Optional[GlobalConcurrencyLimiter] = None
+
+
+def get_limiter() -> GlobalConcurrencyLimiter:
+    """Get the global concurrency limiter instance."""
+    global _limiter
+    if _limiter is None:
+        _limiter = GlobalConcurrencyLimiter()
+    return _limiter
+
+
+async def init_limiter(max_concurrent: int = DEFAULT_MAX_CONCURRENT):
+    """Initialize or reinitialize the global limiter with a specific limit."""
+    global _limiter
+    if _limiter is None:
+        _limiter = GlobalConcurrencyLimiter(max_concurrent)
+    else:
+        await _limiter.set_max_concurrent(max_concurrent)
+    return _limiter