academic-refchecker 1.2.68__py3-none-any.whl → 1.2.69__py3-none-any.whl

{academic_refchecker-1.2.68.dist-info → academic_refchecker-1.2.69.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: academic-refchecker
-Version: 1.2.68
+Version: 1.2.69
 Summary: A comprehensive tool for validating reference accuracy in academic papers
 Author-email: Mark Russinovich <markrussinovich@hotmail.com>
 License-Expression: MIT
@@ -188,18 +188,45 @@ RefChecker also includes a modern web interface with real-time progress updates,
 
 ![RefChecker Web UI](assets/webui.png)
 
-### Prerequisites
-
-- **Python 3.8+** with RefChecker installed (`pip install academic-refchecker[webui]`)
-- **Node.js 18+** and npm
+### Option 1: Install from PyPI (Recommended)
 
-### Quick Start (Web UI)
+The simplest way to run the Web UI is using the pip-installed package:
 
 ```bash
-# Install Python dependencies (if not already done)
+# Install RefChecker with Web UI support
 pip install academic-refchecker[llm,webui]
 
-# Install Node.js dependencies
+# Start the web server
+refchecker-webui
+```
+
+Then open **http://localhost:8000** in your browser.
+
+The `refchecker-webui` command starts a complete web server with both the API backend and the pre-built frontend.
+
+**Options:**
+```bash
+refchecker-webui --port 8080      # Use a different port
+refchecker-webui --host 0.0.0.0   # Allow external connections
+```
+
+### Option 2: Run from Cloned Repository (Development)
+
+If you're developing or modifying the Web UI:
+
+**Prerequisites:**
+- **Python 3.8+** with dependencies installed
+- **Node.js 18+** and npm
+
+```bash
+# Clone the repository
+git clone https://github.com/markrussinovich/refchecker.git
+cd refchecker
+
+# Install Python dependencies
+pip install -e ".[llm,webui]"
+
+# Install and run the frontend development server
 cd web-ui
 npm install    # First time only
 npm start      # Starts both backend and frontend
@@ -207,15 +234,14 @@ npm start      # Starts both backend and frontend
 
 Then open **http://localhost:5173** in your browser.
 
-### Alternative: Start Servers Separately
+**Alternative: Start Servers Separately**
 
-**Terminal 1 - Backend:**
+*Terminal 1 - Backend:*
 ```bash
-refchecker-webui --port 8000
-# Or: python -m uvicorn backend.main:app --port 8000
+python -m uvicorn backend.main:app --reload --port 8000
 ```
 
-**Terminal 2 - Frontend:**
+*Terminal 2 - Frontend:*
 ```bash
 cd web-ui
 npm run dev

{academic_refchecker-1.2.68.dist-info → academic_refchecker-1.2.69.dist-info}/RECORD

@@ -1,4 +1,4 @@
-academic_refchecker-1.2.68.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
+academic_refchecker-1.2.69.dist-info/licenses/LICENSE,sha256=Kwrx3fePVCeEFDCZvCW4OuoTNBiSoYbpGBI6qzGhWF0,1067
 backend/__init__.py,sha256=TFVkOx5tSp3abty15RzUbaSwQ9ZD0kfUn7PDh63xkYY,521
 backend/__main__.py,sha256=74V7yUMsRSZaaRyXYm-rZVc3TVUcUgwsoTQTUbV5EqM,211
 backend/cli.py,sha256=xV3l9M5OdNQQYOcrzj2d_7RmCgj7CXP_1oi0TPe6zNo,1672
@@ -6,7 +6,7 @@ backend/concurrency.py,sha256=2KY9I_8dDkyl_HTGx27ZxU4rFXx2vqbGOlo5RrRbPjA,3223
 backend/database.py,sha256=1jLP1m9vNk5sEs4bh_xmX0T5ilZkUTX1c7nOVz5XnNc,30681
 backend/main.py,sha256=ntz5PbEfG65ENFTHVQlY-c8hP5UPM_hdFjl60YMNh78,54371
 backend/models.py,sha256=El2F-RTHgxQ7-WODmiYCpjsTFDpjwF9PBt-JDa_XipE,2591
-backend/refchecker_wrapper.py,sha256=B8oERiF81Pbrv0bS9CWUiFIzUQyfXCv8k4dz_jojaYk,51935
+backend/refchecker_wrapper.py,sha256=cgJpPFNGAKHaNKxnLY3r3RxlJVT-yRyr3rJFeMxoxAo,51873
 backend/thumbnail.py,sha256=wPFXp3RlmcL9jVKZmSBRB7Pfy9Ti7nCnzNtL4osfNtM,17618
 backend/websocket_manager.py,sha256=l-Wou-rKV6n7t6Gcf5fR6s_4G-mssSrba0davNnYS70,4247
 backend/static/favicon.svg,sha256=R0oQauh16Uy0D7JlT27k-zdjJtrvfPKOe9La5vKYwuM,395
@@ -16,16 +16,16 @@ backend/static/assets/index-2P6L_39v.css,sha256=KC3Wa6jfD1qwmEoVpqTovlzf8fsn5oHY
 backend/static/assets/index-hk21nqxR.js,sha256=z2agP8ZFYw4AfYi-GJ5E_8_k-lPF-frXOJtPk-I0hDs,369533
 refchecker/__init__.py,sha256=Pg5MrtLxDBRcNYcI02N-bv3tzURVd1S3nQ8IyF7Zw7E,322
 refchecker/__main__.py,sha256=agBbT9iKN0g2xXtRNCoh29Nr7z2n5vU-r0MCVJKi4tI,232
-refchecker/__version__.py,sha256=kEtpfBysPxr3KR4tVgxInHiaiLaH_24ip16viUv_rkA,89
+refchecker/__version__.py,sha256=cloSFZI6gJtk10frg47j2b9FYBRIoN_5QQ4lFZq639o,65
 refchecker/checkers/__init__.py,sha256=T0PAHTFt6UiGvn-WGoJU8CdhXNmf6zaHmcGVoWHhmJQ,533
 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=wJtMwyu_PgLF0CGsyip42auTnRyObTRxCRiv_N8l78Q,21024
+refchecker/checkers/local_semantic_scholar.py,sha256=c-KUTh99s-Di71h-pzdrwlPgoSTwB-tgVAZnCrMFXmw,21011
 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=T8PSJfyYP1BlbW9_hhZTlxVOeBMyGHJap989PMpDrEE,36012
+refchecker/checkers/semantic_scholar.py,sha256=yvatQM5fXdW0qagqrTUpgotd0RbT7N_pqaRNGfmQjJs,35613
 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
@@ -33,7 +33,7 @@ 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=rP5_-9eRhn6rxtoC7LCJyaOdNNGX5AS5K1S7ZNN3bo0,287343
+refchecker/core/refchecker.py,sha256=nX8guDXFL1ZdT-K6KUJT_3iZjuoYsWj4e0rKrqd5VZA,287117
 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
@@ -52,13 +52,13 @@ refchecker/utils/bibtex_parser.py,sha256=xY0dEqT8lBZF-W21YRpG28lp_F2ikLan7nK70Wi
 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=_7YvQ0DTOQBMIujUE0SdJicjPiAR3VETLU668GIji24,6094
-refchecker/utils/error_utils.py,sha256=PbB9HP2eoiWTIvRqzyh1SDhEgCEc7ecN5hVB-dUFP5Q,13093
+refchecker/utils/error_utils.py,sha256=8TcfRUD6phZ7viPJrezQ4jKf_vE65lqEXZq5707eU6s,15425
 refchecker/utils/mock_objects.py,sha256=QxU-UXyHSY27IZYN8Sb8ei0JtNkpGSdMXoErrRLHXvE,6437
 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-1.2.68.dist-info/METADATA,sha256=WKwHwxJAnbiMawTop8ZabanE8Egti7CBUpZyG8xM85U,25818
-academic_refchecker-1.2.68.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-academic_refchecker-1.2.68.dist-info/entry_points.txt,sha256=9cREsaKwlp05Ql0CBIjKrNHk5IG2cHY5LvJPsV2-SxA,108
-academic_refchecker-1.2.68.dist-info/top_level.txt,sha256=FfNvrvpj25gfpUBjW0epvz7Qrdejhups5Za_DBiSRu4,19
-academic_refchecker-1.2.68.dist-info/RECORD,,
+academic_refchecker-1.2.69.dist-info/METADATA,sha256=vdhMaYS48pa0U9rLKlZiU4U1V9eTKmCOqB511WOkEQQ,26478
+academic_refchecker-1.2.69.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+academic_refchecker-1.2.69.dist-info/entry_points.txt,sha256=9cREsaKwlp05Ql0CBIjKrNHk5IG2cHY5LvJPsV2-SxA,108
+academic_refchecker-1.2.69.dist-info/top_level.txt,sha256=FfNvrvpj25gfpUBjW0epvz7Qrdejhups5Za_DBiSRu4,19
+academic_refchecker-1.2.69.dist-info/RECORD,,

backend/refchecker_wrapper.py

@@ -171,18 +171,18 @@ class ProgressRefChecker:
                 "is_warning": is_warning,  # Preserve warning_type as warning flag
             })
 
-        # Determine status - items with warning_type or certain error types are warnings, not errors
-        warning_types = ['year', 'venue', 'author']
+        # Determine status - items originally from warning_type are warnings, items from error_type are errors
         # Items originally from info_type are suggestions, not errors
         # Items originally from warning_type are warnings, not errors
+        # Items with error_type (including year/venue/author when missing) are errors
         has_errors = any(
-            e.get('error_type') not in ['unverified', 'info'] + warning_types 
+            e.get('error_type') not in ['unverified', 'info'] 
             and not e.get('is_suggestion')
             and not e.get('is_warning')
             for e in sanitized
         )
         has_warnings = any(
-            (e.get('error_type') in warning_types or e.get('is_warning'))
+            e.get('is_warning')
             and not e.get('is_suggestion') 
             for e in sanitized
         )
@@ -252,8 +252,8 @@ class ProgressRefChecker:
                     "suggestion_type": err.get('error_type') or 'info',
                     "suggestion_details": err.get('error_details', '')
                 })
-            elif err.get('is_warning') or err.get('error_type') in ['year', 'venue', 'author']:
-                # Items with is_warning flag or known warning types go to warnings
+            elif err.get('is_warning'):
+                # Only items with is_warning flag (originally warning_type) go to warnings
                 formatted_warnings.append(err_obj)
             elif err.get('error_type') == 'unverified':
                 formatted_errors.append({**err_obj, "error_type": 'unverified'})

refchecker/__version__.py

@@ -1,5 +1,3 @@
 """Version information for RefChecker."""
 
-__version__ = "1.2.68"
-
-__version__ = "1.2.68"
+__version__ = "1.2.69"

refchecker/checkers/local_semantic_scholar.py

@@ -36,7 +36,7 @@ import os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 from refchecker.utils.doi_utils import extract_doi_from_url, compare_dois, construct_doi_url
-from refchecker.utils.error_utils import create_author_error, create_year_warning, create_doi_error
+from refchecker.utils.error_utils import create_author_error, create_doi_error
 from refchecker.utils.text_utils import normalize_author_name, normalize_paper_title, is_name_match, compare_authors, calculate_title_similarity
 from refchecker.utils.url_utils import extract_arxiv_id_from_url, get_best_available_url
 from refchecker.utils.db_utils import process_semantic_scholar_result, process_semantic_scholar_results
@@ -432,20 +432,24 @@ class LocalNonArxivReferenceChecker:
         
         # Verify year (with tolerance)
         paper_year = paper_data.get('year')
-        if year and paper_year:
-            # Get year tolerance from config (default to 1 if not available)
-            year_tolerance = 1  # Default tolerance
-            try:
-                from config.settings import get_config
-                config = get_config()
-                year_tolerance = config.get('text_processing', {}).get('year_tolerance', 1)
-            except (ImportError, Exception):
-                pass  # Use default if config not available
-            
-            # Only flag as mismatch if the difference is greater than tolerance
-            if abs(year - paper_year) > year_tolerance:
-                logger.debug(f"Local DB: Year mismatch - cited: {year}, actual: {paper_year}")
-                errors.append(create_year_warning(year, paper_year))
+        # Get year tolerance from config (default to 1 if not available)
+        year_tolerance = 1  # Default tolerance
+        try:
+            from config.settings import get_config
+            config = get_config()
+            year_tolerance = config.get('text_processing', {}).get('year_tolerance', 1)
+        except (ImportError, Exception):
+            pass  # Use default if config not available
+        
+        from refchecker.utils.error_utils import validate_year
+        year_warning = validate_year(
+            cited_year=year,
+            paper_year=paper_year,
+            year_tolerance=year_tolerance
+        )
+        if year_warning:
+            logger.debug(f"Local DB: Year issue - {year_warning.get('warning_details', '')}")
+            errors.append(year_warning)
         
         # Verify DOI
         paper_doi = None

refchecker/checkers/semantic_scholar.py

@@ -511,29 +511,25 @@ class NonArxivReferenceChecker:
         
         # Verify year using flexible validation
         paper_year = paper_data.get('year')
-        if year and paper_year:
-            # Check if we have an exact ArXiv ID match for additional context
-            arxiv_id_match = False
-            if url and 'arxiv.org/abs/' in url:
-                arxiv_match = re.search(r'arxiv\.org/abs/([^\s/?#]+)', url)
-                if arxiv_match:
-                    cited_arxiv_id = arxiv_match.group(1)
-                    external_ids = paper_data.get('externalIds', {})
-                    found_arxiv_id = external_ids.get('ArXiv')
-                    arxiv_id_match = (cited_arxiv_id == found_arxiv_id)
-            
-            # Use flexible year validation
-            from refchecker.utils.text_utils import is_year_substantially_different
-            context = {'arxiv_match': arxiv_id_match}
-            is_different, warning_message = is_year_substantially_different(year, paper_year, context)
-            
-            if is_different and warning_message:
-                from refchecker.utils.error_utils import format_year_mismatch
-                errors.append({
-                    'warning_type': 'year',
-                    'warning_details': format_year_mismatch(year, paper_year),
-                    'ref_year_correct': paper_year
-                })
+        # Check if we have an exact ArXiv ID match for additional context
+        arxiv_id_match = False
+        if url and 'arxiv.org/abs/' in url:
+            arxiv_match = re.search(r'arxiv\.org/abs/([^\s/?#]+)', url)
+            if arxiv_match:
+                cited_arxiv_id = arxiv_match.group(1)
+                external_ids = paper_data.get('externalIds', {})
+                found_arxiv_id = external_ids.get('ArXiv')
+                arxiv_id_match = (cited_arxiv_id == found_arxiv_id)
+        
+        from refchecker.utils.error_utils import validate_year
+        year_warning = validate_year(
+            cited_year=year,
+            paper_year=paper_year,
+            use_flexible_validation=True,
+            context={'arxiv_match': arxiv_id_match}
+        )
+        if year_warning:
+            errors.append(year_warning)
         
         # Verify venue
         cited_venue = reference.get('journal', '') or reference.get('venue', '')
@@ -573,10 +569,10 @@ class NonArxivReferenceChecker:
                 from refchecker.utils.error_utils import create_venue_warning
                 errors.append(create_venue_warning(cited_venue, paper_venue))
         elif not cited_venue and paper_venue:
-            # Reference has no venue but paper has one - always warn about missing venue
+            # Reference has no venue but paper has one - error for missing venue
             errors.append({
-                'warning_type': 'venue',
-                'warning_details': f"Venue missing: should include '{paper_venue}'",
+                'error_type': 'venue',
+                'error_details': f"Venue missing: should include '{paper_venue}'",
                 'ref_venue_correct': paper_venue
             })
 

refchecker/core/refchecker.py

@@ -1928,25 +1928,24 @@ class ArxivReferenceChecker:
         
         # Verify year (with tolerance)
         paper_year = paper_data.get('year')
-        if year and paper_year:
-            # Get year tolerance from config (default to 1 if not available)
-            year_tolerance = 1  # Default tolerance
-            try:
-                from config.settings import get_config
-                config = get_config()
-                year_tolerance = config.get('text_processing', {}).get('year_tolerance', 1)
-            except (ImportError, Exception):
-                pass  # Use default if config not available
-            
-            # Only flag as mismatch if the difference is greater than tolerance
-            if abs(year - paper_year) > year_tolerance:
-                logger.debug(f"DB Verification: Year mismatch - cited: {year}, actual: {paper_year}")
-                from refchecker.utils.error_utils import format_year_mismatch
-                errors.append({
-                    'warning_type': 'year',
-                    'warning_details': format_year_mismatch(year, paper_year),
-                    'ref_year_correct': paper_year
-                })
+        # Get year tolerance from config (default to 1 if not available)
+        year_tolerance = 1  # Default tolerance
+        try:
+            from config.settings import get_config
+            config = get_config()
+            year_tolerance = config.get('text_processing', {}).get('year_tolerance', 1)
+        except (ImportError, Exception):
+            pass  # Use default if config not available
+        
+        from refchecker.utils.error_utils import validate_year
+        year_warning = validate_year(
+            cited_year=year,
+            paper_year=paper_year,
+            year_tolerance=year_tolerance
+        )
+        if year_warning:
+            logger.debug(f"DB Verification: Year issue - {year_warning.get('warning_details', '')}")
+            errors.append(year_warning)
         
         # Verify DOI
         if doi and external_ids.get('DOI'):

refchecker/utils/error_utils.py

@@ -124,6 +124,67 @@ def create_year_warning(cited_year: int, correct_year: int) -> Dict[str, Any]:
     }
 
 
+def create_year_missing_error(correct_year: int) -> Dict[str, Any]:
+    """
+    Create a standardized error for missing year in reference.
+    
+    Args:
+        correct_year: Correct year from database
+        
+    Returns:
+        Standardized error dictionary
+    """
+    return {
+        'error_type': 'year',
+        'error_details': f"Year missing: should include '{correct_year}'",
+        'ref_year_correct': correct_year
+    }
+
+
+def validate_year(cited_year: Optional[int], paper_year: Optional[int], 
+                  year_tolerance: int = 1, use_flexible_validation: bool = False,
+                  context: Optional[Dict[str, Any]] = None) -> Optional[Dict[str, Any]]:
+    """
+    Validate year field and return appropriate warning if needed.
+    
+    This function handles:
+    - Year mismatch (with configurable tolerance)
+    - Missing year in reference
+    
+    Args:
+        cited_year: Year as cited in the reference (may be None)
+        paper_year: Correct year from database/API (may be None)
+        year_tolerance: Maximum allowed difference between years (default 1)
+        use_flexible_validation: If True, use is_year_substantially_different for more context-aware checking
+        context: Optional context dict for flexible validation (e.g., {'arxiv_match': True})
+        
+    Returns:
+        Warning dictionary if year issue found, None otherwise
+    """
+    if not paper_year:
+        # Can't validate without a known correct year
+        return None
+    
+    if cited_year and paper_year:
+        if use_flexible_validation:
+            # Use the more sophisticated validation from text_utils
+            from refchecker.utils.text_utils import is_year_substantially_different
+            is_different, warning_message = is_year_substantially_different(
+                cited_year, paper_year, context or {}
+            )
+            if is_different and warning_message:
+                return create_year_warning(cited_year, paper_year)
+        else:
+            # Simple tolerance-based validation
+            if abs(cited_year - paper_year) > year_tolerance:
+                return create_year_warning(cited_year, paper_year)
+    elif not cited_year and paper_year:
+        # Reference is missing a year but paper has one
+        return create_year_missing_error(paper_year)
+    
+    return None
+
+
 def create_doi_error(cited_doi: str, correct_doi: str) -> Optional[Dict[str, str]]:
     """
     Create a standardized DOI error or warning dictionary.
@@ -220,8 +281,8 @@ def create_venue_warning(cited_venue: str, correct_venue: str) -> Dict[str, str]
     # If cited venue cleans to empty, treat as missing venue instead of mismatch
     if not clean_cited and clean_correct:
         return {
-            'warning_type': 'venue',
-            'warning_details': format_missing_venue(clean_correct),
+            'error_type': 'venue',
+            'error_details': format_missing_venue(clean_correct),
             'ref_venue_correct': correct_venue
         }