Add ruff linting and fix all 680 errors across codebase

advanced_methods/01_docling/01_basic_conversion.py

@@ -10,12 +10,13 @@
 
 uv pip install docling
 """
-import sys
+
 from pathlib import Path
 
 # Reference sample docs from the documents folder
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
 
+
 def convert_single_document():
     """Convert a single PDF to markdown using default settings."""
     from docling.document_converter import DocumentConverter
@@ -29,7 +30,7 @@ def convert_single_document():
     print("DOCLING: Basic PDF to Markdown")
     print("=" * 60)
     print(f"Status: {result.status}")
-    print(f"\n--- Markdown Output ---\n")
+    print("\n--- Markdown Output ---\n")
     print(result.document.export_to_markdown())
 
 
@@ -84,7 +85,6 @@ def export_formats():
     print(text[:300])
 
     # JSON (lossless serialization)
-    import json
     json_str = doc.model_dump_json(indent=2)
     print(f"\n--- JSON ({len(json_str)} chars) ---")
     print(json_str[:400] + "...")

advanced_methods/01_docling/02_pdf_advanced.py

@@ -15,22 +15,24 @@
 uv pip install "docling[tesserocr]"  # for Tesseract OCR
 uv pip install "docling[easyocr]"    # for EasyOCR
 """
-import sys
+
 from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
 
 
 def table_extraction_modes():
     """Compare FAST vs ACCURATE table detection on a table-heavy PDF."""
-    from docling.document_converter import DocumentConverter
     from docling.datamodel.base_models import InputFormat
     from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
-    from docling.document_converter import PdfFormatOption
+    from docling.document_converter import DocumentConverter, PdfFormatOption
 
     pdf_path = SAMPLES_DIR / "01_pdf" / "sample_docs" / "tables.pdf"
 
-    for mode_name, mode in [("FAST", TableFormerMode.FAST), ("ACCURATE", TableFormerMode.ACCURATE)]:
+    for mode_name, mode in [
+        ("FAST", TableFormerMode.FAST),
+        ("ACCURATE", TableFormerMode.ACCURATE),
+    ]:
         print(f"\n{'=' * 60}")
         print(f"TABLE DETECTION MODE: {mode_name}")
         print(f"{'=' * 60}")
@@ -41,9 +43,7 @@ def table_extraction_modes():
         )
 
         converter = DocumentConverter(
-            format_options={
-                InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
-            }
+            format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)}
         )
 
         result = converter.convert(str(pdf_path))
@@ -54,10 +54,9 @@ def table_extraction_modes():
 
 def ocr_configuration():
     """Configure OCR settings for scanned documents."""
-    from docling.document_converter import DocumentConverter
     from docling.datamodel.base_models import InputFormat
     from docling.datamodel.pipeline_options import PdfPipelineOptions
-    from docling.document_converter import PdfFormatOption
+    from docling.document_converter import DocumentConverter, PdfFormatOption
 
     pdf_path = SAMPLES_DIR / "01_pdf" / "sample_docs" / "simple_text.pdf"
 
@@ -70,11 +69,7 @@ def ocr_configuration():
         # ocr_options=TesseractCliOcrOptions(lang=["eng"])
     )
 
-    converter = DocumentConverter(
-        format_options={
-            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
-        }
-    )
+    converter = DocumentConverter(format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)})
 
     print("=" * 60)
     print("PDF WITH OCR ENABLED")

advanced_methods/01_docling/03_chunking.py

@@ -14,7 +14,7 @@
 
 uv pip install docling docling-core
 """
-import sys
+
 from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
@@ -37,9 +37,9 @@ def hierarchical_chunking():
     print("=" * 60)
 
     for i, chunk in enumerate(chunks[:5]):
-        print(f"\n--- Chunk {i+1} ---")
+        print(f"\n--- Chunk {i + 1} ---")
         print(f"Text: {chunk.text[:200]}...")
-        if hasattr(chunk, 'meta') and chunk.meta:
+        if hasattr(chunk, "meta") and chunk.meta:
             print(f"Metadata: {chunk.meta}")
         print()
 
@@ -66,9 +66,9 @@ def hybrid_chunking():
     print("=" * 60)
 
     for i, chunk in enumerate(chunks[:5]):
-        print(f"\n--- Chunk {i+1} ---")
+        print(f"\n--- Chunk {i + 1} ---")
         print(f"Text: {chunk.text[:200]}...")
-        if hasattr(chunk, 'meta') and chunk.meta:
+        if hasattr(chunk, "meta") and chunk.meta:
             print(f"Metadata: {chunk.meta}")
 
 
@@ -83,21 +83,23 @@ def compare_chunking_strategies():
 
     hier_chunks = list(HierarchicalChunker().chunk(result.document))
 
-    hybrid_chunks = list(HybridChunker(
-        tokenizer="sentence-transformers/all-MiniLM-L6-v2",
-        max_tokens=256,
-    ).chunk(result.document))
+    hybrid_chunks = list(
+        HybridChunker(
+            tokenizer="sentence-transformers/all-MiniLM-L6-v2",
+            max_tokens=256,
+        ).chunk(result.document)
+    )
 
     print("=" * 60)
     print("CHUNKING STRATEGY COMPARISON")
     print("=" * 60)
     print(f"\nHierarchical: {len(hier_chunks)} chunks")
     for i, c in enumerate(hier_chunks[:3]):
-        print(f"  [{i+1}] {len(c.text)} chars: {c.text[:80]}...")
+        print(f"  [{i + 1}] {len(c.text)} chars: {c.text[:80]}...")
 
     print(f"\nHybrid (256 tokens): {len(hybrid_chunks)} chunks")
     for i, c in enumerate(hybrid_chunks[:3]):
-        print(f"  [{i+1}] {len(c.text)} chars: {c.text[:80]}...")
+        print(f"  [{i + 1}] {len(c.text)} chars: {c.text[:80]}...")
 
 
 if __name__ == "__main__":

advanced_methods/01_docling/04_integrations.py

@@ -12,7 +12,7 @@
 uv pip install llama-index-readers-docling  # for LlamaIndex
 uv pip install langchain-docling            # for LangChain
 """
-import sys
+
 from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
@@ -48,7 +48,7 @@ def llamaindex_integration():
     print("DOCLING + LLAMAINDEX")
     print("=" * 60)
     for i, doc in enumerate(documents):
-        print(f"\nDocument {i+1}:")
+        print(f"\nDocument {i + 1}:")
         print(f"  Text length: {len(doc.text)}")
         print(f"  Preview: {doc.text[:200]}...")
 
@@ -85,7 +85,7 @@ def langchain_integration():
     print("DOCLING + LANGCHAIN")
     print("=" * 60)
     for i, doc in enumerate(documents):
-        print(f"\nDocument {i+1}:")
+        print(f"\nDocument {i + 1}:")
         print(f"  Content: {doc.page_content[:200]}...")
         print(f"  Metadata: {doc.metadata}")
 

advanced_methods/02_unstructured_io/01_auto_partition.py

@@ -9,7 +9,7 @@
 
 uv pip install "unstructured[all-docs]"
 """
-import sys
+
 from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
@@ -29,7 +29,7 @@ def auto_partition_pdf():
     for el in elements:
         print(f"\n[{type(el).__name__}]")
         print(f"  Text: {str(el)[:150]}")
-        if hasattr(el, 'metadata'):
+        if hasattr(el, "metadata"):
             if el.metadata.page_number:
                 print(f"  Page: {el.metadata.page_number}")
 
@@ -44,7 +44,10 @@ def auto_partition_multiple():
         ("HTML", SAMPLES_DIR / "04_html" / "sample_docs" / "article_page.html"),
         ("PPTX", SAMPLES_DIR / "03_pptx" / "sample_docs" / "presentation.pptx"),
         ("Email", SAMPLES_DIR / "07_email" / "sample_docs" / "plain_text.eml"),
-        ("Markdown", SAMPLES_DIR / "08_markdown_txt" / "sample_docs" / "technical_doc.md"),
+        (
+            "Markdown",
+            SAMPLES_DIR / "08_markdown_txt" / "sample_docs" / "technical_doc.md",
+        ),
         ("EPUB", SAMPLES_DIR / "09_epub" / "sample_docs" / "sample_book.epub"),
     ]
 
@@ -59,6 +62,7 @@ def auto_partition_multiple():
 
         # Show element type distribution
         from collections import Counter
+
         type_counts = Counter(type(el).__name__ for el in elements)
         for etype, count in type_counts.most_common():
             print(f"  {etype}: {count}")
@@ -97,6 +101,7 @@ def element_types_overview():
 """)
 
     from collections import Counter
+
     type_counts = Counter(type(el).__name__ for el in elements)
     print(f"Found in this document ({len(elements)} elements):")
     for etype, count in type_counts.most_common():
@@ -110,4 +115,8 @@ def element_types_overview():
     print("3. Element types overview")
     choice = input("Enter 1/2/3 (default=1): ").strip() or "1"
 
-    {"1": auto_partition_pdf, "2": auto_partition_multiple, "3": element_types_overview}[choice]()
+    {
+        "1": auto_partition_pdf,
+        "2": auto_partition_multiple,
+        "3": element_types_overview,
+    }[choice]()

advanced_methods/02_unstructured_io/02_pdf_strategies.py

@@ -12,17 +12,18 @@
 
 uv pip install "unstructured[pdf]"
 """
-import sys
+
 from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
 
 
 def compare_strategies():
     """Compare fast, hi_res, and ocr_only on the same PDF."""
-    from unstructured.partition.pdf import partition_pdf
-    from collections import Counter
     import time
+    from collections import Counter
+
+    from unstructured.partition.pdf import partition_pdf
 
     pdf_path = str(SAMPLES_DIR / "01_pdf" / "sample_docs" / "tables.pdf")
 
@@ -51,7 +52,7 @@ def compare_strategies():
                 print(f"  [{type(el).__name__}] {str(el)[:120]}")
         except Exception as e:
             print(f"  Error: {e}")
-            print(f"  (hi_res requires: uv pip install \"unstructured[pdf]\" and model downloads)")
+            print('  (hi_res requires: uv pip install "unstructured[pdf]" and model downloads)')
 
 
 def hi_res_with_options():
@@ -68,16 +69,16 @@ def hi_res_with_options():
         elements = partition_pdf(
             filename=pdf_path,
             strategy="hi_res",
-            infer_table_structure=True,   # Extract table HTML
-            include_page_breaks=True,      # Insert PageBreak elements
-            languages=["eng"],             # OCR language hints
+            infer_table_structure=True,  # Extract table HTML
+            include_page_breaks=True,  # Insert PageBreak elements
+            languages=["eng"],  # OCR language hints
         )
 
         for el in elements:
             if type(el).__name__ == "Table":
-                print(f"\n--- Table Found ---")
+                print("\n--- Table Found ---")
                 print(f"Text: {str(el)[:200]}")
-                if hasattr(el.metadata, 'text_as_html') and el.metadata.text_as_html:
+                if hasattr(el.metadata, "text_as_html") and el.metadata.text_as_html:
                     print(f"HTML: {el.metadata.text_as_html[:300]}")
                 break
         else:

advanced_methods/02_unstructured_io/03_specific_partitioners.py

@@ -17,9 +17,9 @@
 
 uv pip install "unstructured[all-docs]"
 """
-import sys
-from pathlib import Path
+
 from collections import Counter
+from pathlib import Path
 
 SAMPLES_DIR = Path(__file__).resolve().parent.parent.parent / "unstructured_documents"
 
@@ -82,11 +82,11 @@ def partition_email_demo():
     # Show email-specific metadata
     for el in elements[:1]:
         meta = el.metadata
-        if hasattr(meta, 'sent_from') and meta.sent_from:
+        if hasattr(meta, "sent_from") and meta.sent_from:
             print(f"  From: {meta.sent_from}")
-        if hasattr(meta, 'sent_to') and meta.sent_to:
+        if hasattr(meta, "sent_to") and meta.sent_to:
             print(f"  To: {meta.sent_to}")
-        if hasattr(meta, 'subject') and meta.subject:
+        if hasattr(meta, "subject") and meta.subject:
             print(f"  Subject: {meta.subject}")