pdf-file-renamer 0.6.0__py3-none-any.whl → 0.6.1__py3-none-any.whl

pdf_file_renamer/__init__.py

@@ -1,3 +1,3 @@
 """PDF Renamer - Intelligent PDF file renaming using LLMs."""
 
-__version__ = "0.6.0"
+__version__ = "0.6.1"

pdf_file_renamer/application/pdf_rename_workflow.py

@@ -5,7 +5,7 @@ import contextlib
 from collections.abc import Callable
 from pathlib import Path
 
-from pdf_file_renamer.domain.models import FileRenameOperation
+from pdf_file_renamer.domain.models import ConfidenceLevel, FileRenameOperation
 from pdf_file_renamer.domain.ports import (
     DOIExtractor,
     FilenameGenerator,
@@ -103,12 +103,18 @@ class PDFRenameWorkflow:
 
             # Mark complete
             if status_callback:
+                # result.confidence is already a string due to use_enum_values=True
+                confidence_str = (
+                    result.confidence.value
+                    if isinstance(result.confidence, ConfidenceLevel)
+                    else result.confidence
+                )
                 status_callback(
                     filename,
                     {
                         "status": "Complete",
                         "stage": "✓",
-                        "confidence": result.confidence.value,
+                        "confidence": confidence_str,
                     },
                 )
 

pdf_file_renamer/infrastructure/doi/pdf2doi_extractor.py

@@ -31,16 +31,14 @@ class PDF2DOIExtractor(DOIExtractor):
         try:
             # Run pdf2doi in executor to avoid blocking
             loop = asyncio.get_event_loop()
-            results = await loop.run_in_executor(
+            result = await loop.run_in_executor(
                 None, pdf2doi.pdf2doi, str(pdf_path)
             )
 
-            if not results or len(results) == 0:
+            # pdf2doi returns a dict (not a list)
+            if not result or not isinstance(result, dict):
                 return None
 
-            # Get the first result
-            result = results[0]
-
             # Check if DOI was found
             identifier = result.get("identifier")
             if not identifier:
@@ -50,15 +48,51 @@ class PDF2DOIExtractor(DOIExtractor):
             if identifier_type.lower() not in ("doi", "arxiv"):
                 return None
 
-            # Extract metadata from validation_info (bibtex)
+            # Extract metadata from validation_info (JSON string from CrossRef API)
             validation_info = result.get("validation_info", "")
 
-            # Parse bibtex for metadata
-            title = self._extract_bibtex_field(validation_info, "title")
-            authors = self._extract_bibtex_authors(validation_info)
-            year = self._extract_bibtex_field(validation_info, "year")
-            journal = self._extract_bibtex_field(validation_info, "journal")
-            publisher = self._extract_bibtex_field(validation_info, "publisher")
+            # Parse JSON metadata
+            import json
+
+            metadata = {}
+            if validation_info:
+                try:
+                    metadata = json.loads(validation_info)
+                except json.JSONDecodeError:
+                    pass
+
+            # Extract title
+            title = metadata.get("title")
+
+            # Extract authors (list of dicts with 'given' and 'family' fields)
+            authors = None
+            if "author" in metadata:
+                author_list = metadata["author"]
+                authors = []
+                for author in author_list:
+                    if isinstance(author, dict):
+                        family = author.get("family", "")
+                        given = author.get("given", "")
+                        if family:
+                            full_name = f"{given} {family}".strip() if given else family
+                            authors.append(full_name)
+                if not authors:
+                    authors = None
+
+            # Extract year from published-online or published
+            year = None
+            for date_field in ["published-online", "published", "created"]:
+                if date_field in metadata and "date-parts" in metadata[date_field]:
+                    date_parts = metadata[date_field]["date-parts"]
+                    if date_parts and len(date_parts) > 0 and len(date_parts[0]) > 0:
+                        year = str(date_parts[0][0])
+                        break
+
+            # Extract journal (container-title)
+            journal = metadata.get("container-title")
+
+            # Extract publisher
+            publisher = metadata.get("publisher")
 
             return DOIMetadata(
                 doi=identifier,

pdf_file_renamer/presentation/formatters.py

@@ -7,7 +7,7 @@ from rich.prompt import Prompt
 from rich.table import Table
 from rich.text import Text
 
-from pdf_file_renamer.domain.models import FileRenameOperation
+from pdf_file_renamer.domain.models import ConfidenceLevel, FileRenameOperation
 
 
 class ProgressDisplay:
@@ -146,7 +146,13 @@ class InteractivePrompt:
             info_text.append("Suggested: ", style="bold green")
             info_text.append(f"{operation.new_filename}\n", style="green")
             info_text.append("Confidence: ", style="bold yellow")
-            info_text.append(f"{operation.confidence.value}\n", style="yellow")
+            # Handle both enum and string confidence
+            conf_str = (
+                operation.confidence.value
+                if isinstance(operation.confidence, ConfidenceLevel)
+                else operation.confidence
+            )
+            info_text.append(f"{conf_str}\n", style="yellow")
             info_text.append("Reasoning: ", style="bold white")
             info_text.append(operation.reasoning, style="dim white")
 
@@ -206,10 +212,16 @@ class ResultsTable:
             reasoning = op.reasoning
             if len(reasoning) > 100:
                 reasoning = reasoning[:100] + "..."
+            # Handle both enum and string confidence
+            conf_str = (
+                op.confidence.value
+                if isinstance(op.confidence, ConfidenceLevel)
+                else op.confidence
+            )
             table.add_row(
                 op.original_path.name,
                 op.new_filename,
-                op.confidence.value,
+                conf_str,
                 reasoning,
             )
 

{pdf_file_renamer-0.6.0.dist-info → pdf_file_renamer-0.6.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pdf-file-renamer
-Version: 0.6.0
+Version: 0.6.1
 Summary: Intelligent PDF renaming using LLMs
 License-File: LICENSE
 Requires-Python: >=3.11

{pdf_file_renamer-0.6.0.dist-info → pdf_file_renamer-0.6.1.dist-info}/RECORD

@@ -1,8 +1,8 @@
-pdf_file_renamer/__init__.py,sha256=yCEfy0jblhbUMNTSjJKPuW4zADXoI6IfICx8XvB4R8Q,85
+pdf_file_renamer/__init__.py,sha256=1hyyq0EM6vqGG8Gxxdkg3MuLU_4Mwj3mc812ikutUB8,85
 pdf_file_renamer/main.py,sha256=FTEEb-9QmOOsN9SE8L1SZvFVIkVpQDy8xZ5a8t8CWUs,145
 pdf_file_renamer/application/__init__.py,sha256=riSV7UXBenkDst7Nnf11N1_RuRtM7wpKdwugxOhumS4,363
 pdf_file_renamer/application/filename_service.py,sha256=IbeCNBwyhFlCMCZveq16nmQ2qvyTdtgLmr6PDWPckOs,4868
-pdf_file_renamer/application/pdf_rename_workflow.py,sha256=gd53KoR1aFrK__6TArm7Rtn1yNxylEI2ikmubDOByF4,5842
+pdf_file_renamer/application/pdf_rename_workflow.py,sha256=WLcGJ4ufEmAnGSxVQcOFDeGG8gXSccs11DaP521YDzo,6144
 pdf_file_renamer/application/rename_service.py,sha256=vviNQolk_w-qDQvOKTKj8ZhqYyyNWL-VJMfuUnL6WLw,2357
 pdf_file_renamer/domain/__init__.py,sha256=jxbH3h6xaCnSRuBxclFESl6ZE1pua_I1K4CRAaYxu_I,503
 pdf_file_renamer/domain/models.py,sha256=QwN79TzWmqvQvz-m9ymebvAx3pWlVpSWXNdSEAk4qq0,3186
@@ -10,7 +10,7 @@ pdf_file_renamer/domain/ports.py,sha256=ebOcHptiOK119NCmIwM32_fbRK5xkZP9K67vjL-4
 pdf_file_renamer/infrastructure/__init__.py,sha256=C3ZQ7WCPCa6PMfP00lu4wqb0r57GVyDdiD5EL2DhCeY,187
 pdf_file_renamer/infrastructure/config.py,sha256=baNL5_6_NNiS50ZNdql7fDwQbeAwf6f58HGYIWFQxQQ,2464
 pdf_file_renamer/infrastructure/doi/__init__.py,sha256=8N9ZEwfG7q5xomzh187YtP8t4CfEBHM334xNRblPeuI,153
-pdf_file_renamer/infrastructure/doi/pdf2doi_extractor.py,sha256=rAo0q5HTCqVTyyIXzW3D6riGS5Q9xlXhbT2AY0Hb7nk,3820
+pdf_file_renamer/infrastructure/doi/pdf2doi_extractor.py,sha256=mK2Z5oOwN-TgiEHLgoLM5yCSe_-G9kWXLr4Sw3nMkEM,5105
 pdf_file_renamer/infrastructure/llm/__init__.py,sha256=ToB8__mHvXwaIukGKPEAQ8SeC4ZLiH4auZI1P1yH5PQ,159
 pdf_file_renamer/infrastructure/llm/pydantic_ai_provider.py,sha256=kVsmj0NIawkj-1WWM0hZXbsNH09GabVZm9HPlYsxGuo,9217
 pdf_file_renamer/infrastructure/pdf/__init__.py,sha256=uMHqxSXNLZH5WH_e1kXrp9m7uTqPkiI2hXjNo6rCRoo,368
@@ -19,9 +19,9 @@ pdf_file_renamer/infrastructure/pdf/docling_extractor.py,sha256=auZrJpK7mMg1mUXK
 pdf_file_renamer/infrastructure/pdf/pymupdf_extractor.py,sha256=C61udZCqGqiVx7T0HWNyjvnhgv5AgMIcCYtrhgHOJwk,5465
 pdf_file_renamer/presentation/__init__.py,sha256=1VR44GoPGTixk3hG5YzhGyQf7a4BTKsJBd2VP3rHcFM,211
 pdf_file_renamer/presentation/cli.py,sha256=0t_59-utRWLNCYjFetU0ZHoF1DPTjdNiWM9Au0jFaOg,8013
-pdf_file_renamer/presentation/formatters.py,sha256=Yl-Et7OKMfthyLqTA5qEtSAqh0PfHKp3lNNBA_dn01c,8519
-pdf_file_renamer-0.6.0.dist-info/METADATA,sha256=6XmqT7jtJuqkWlks3FlPWCpNP_tKOGokhxy2Yju5R7k,9912
-pdf_file_renamer-0.6.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pdf_file_renamer-0.6.0.dist-info/entry_points.txt,sha256=0fEGYy60chGE9rECWeCVPxjxzz6vMtIAYdFvmH7xzbw,63
-pdf_file_renamer-0.6.0.dist-info/licenses/LICENSE,sha256=_w08V08WgoMpDMlGNlkIatC5QfQ_Ds_rXOBM8pl7ffE,1068
-pdf_file_renamer-0.6.0.dist-info/RECORD,,
+pdf_file_renamer/presentation/formatters.py,sha256=Es7pZoHw5bEPtNfa_s43eHXa_m0yrTmX6S2aU78JUE0,8978
+pdf_file_renamer-0.6.1.dist-info/METADATA,sha256=OyZKW601xnQFXR-SDLakLEnasq5rtfP7YO6IYn6f-z4,9912
+pdf_file_renamer-0.6.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pdf_file_renamer-0.6.1.dist-info/entry_points.txt,sha256=0fEGYy60chGE9rECWeCVPxjxzz6vMtIAYdFvmH7xzbw,63
+pdf_file_renamer-0.6.1.dist-info/licenses/LICENSE,sha256=_w08V08WgoMpDMlGNlkIatC5QfQ_Ds_rXOBM8pl7ffE,1068
+pdf_file_renamer-0.6.1.dist-info/RECORD,,