natural-pdf 0.2.12__py3-none-any.whl → 0.2.13__py3-none-any.whl

temp/test_draw_guides_interactive.py

@@ -0,0 +1,30 @@
+"""Test the interactive guide drawing functionality"""
+
+from natural_pdf.core.pdf import PDF
+from natural_pdf.analyzers.guides import Guides
+
+# Load a sample PDF
+pdf = PDF("tests/sample_pdfs/simple_table.pdf")
+page = pdf.pages[0]
+
+# Create guides
+guides = Guides(page)
+
+# Add some initial guides for testing
+guides.vertical.from_content()
+guides.horizontal.from_lines(n=5)
+
+print("Initial vertical guides:", list(guides.vertical))
+print("Initial horizontal guides:", list(guides.horizontal))
+
+# This would open the interactive widget in Jupyter
+# guides.vertical.draw()
+
+# For non-Jupyter testing, we can check the method exists
+assert hasattr(guides.vertical, 'draw')
+assert callable(guides.vertical.draw)
+
+print("\nSuccess! The draw() method is available on GuidesList objects.")
+print("To use it interactively, run this in a Jupyter notebook:")
+print("  guides.vertical.draw()")
+print("  guides.horizontal.draw(width=600)")

temp/test_guide_draw_notebook.py

@@ -0,0 +1,47 @@
+"""Test script to verify the draw() method works"""
+
+import sys
+sys.path.insert(0, '.')
+
+from natural_pdf.analyzers.guides import GuidesList, Guides
+
+# Create a mock context for testing
+class MockContext:
+    def __init__(self):
+        self.width = 600
+        self.height = 800
+        
+    def render(self, resolution=150):
+        # Create a simple test image
+        from PIL import Image
+        img = Image.new('RGB', (int(self.width * resolution/72), int(self.height * resolution/72)), 'white')
+        return img
+
+# Test that the draw method exists
+mock_context = MockContext()
+guides = Guides(mock_context)
+
+# Add some test guides
+guides.vertical.data = [100, 200, 300, 400, 500]
+guides.horizontal.data = [150, 350, 550, 750]
+
+print("Initial vertical guides:", list(guides.vertical))
+print("Initial horizontal guides:", list(guides.horizontal))
+
+# Check that draw method exists
+assert hasattr(guides.vertical, 'draw')
+assert callable(guides.vertical.draw)
+assert hasattr(guides.horizontal, 'draw')
+assert callable(guides.horizontal.draw)
+
+print("\nSuccess! The draw() method is available.")
+print("\nIn a Jupyter notebook, you would use:")
+print("  guides.vertical.draw()      # Interactive vertical guide editor")
+print("  guides.horizontal.draw()    # Interactive horizontal guide editor")
+print("\nFeatures:")
+print("  - Click to add new guides")
+print("  - Click existing guides to select them")
+print("  - Drag to move guides")
+print("  - Delete key to remove selected guide")
+print("  - Arrow keys to fine-tune position")
+print("  - Enter to apply, Escape to cancel")

temp/test_inline_js.py

@@ -0,0 +1,22 @@
+"""Test inline JavaScript in HTML widget"""
+
+import ipywidgets as widgets
+from IPython.display import display
+
+# Create an HTML widget with inline JavaScript
+html_content = '''
+<div id="test-div">Click me!</div>
+<script type="text/javascript">
+document.getElementById('test-div').addEventListener('click', function() {
+    alert('Clicked!');
+    this.innerHTML = 'Clicked at ' + new Date().toLocaleTimeString();
+});
+console.log('JavaScript is running!');
+</script>
+'''
+
+# Display using widgets.HTML
+html_widget = widgets.HTML(value=html_content)
+display(html_widget)
+
+print("If you see 'Click me!' above and can click it, JavaScript is working.")

temp/test_widget_functionality.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python
+"""Test the guide widget functionality"""
+
+import sys
+import os
+
+# Add parent directory to path
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+# Test importing and basic functionality
+try:
+    from natural_pdf.analyzers.guides import InteractiveGuideWidget, GuidesList, _GUIDE_WIDGET_AVAILABLE
+    print("✓ Successfully imported InteractiveGuideWidget")
+    
+    if _GUIDE_WIDGET_AVAILABLE:
+        print("✓ ipywidgets is available")
+        
+        # Create a mock GuidesList for testing
+        class MockPage:
+            def __init__(self):
+                self.bbox = (0, 0, 595, 842)  # A4 page size in points
+                
+            def render(self, resolution=150):
+                # Mock render method
+                from PIL import Image
+                width = int(595 * resolution / 72)
+                height = int(842 * resolution / 72)
+                return Image.new('RGB', (width, height), color='white')
+                
+        class MockGuides:
+            def __init__(self):
+                self.context = MockPage()
+                
+        class MockGuidesList:
+            def __init__(self):
+                self.data = [100, 200, 300]
+                self._axis = 'vertical'
+                self._parent = MockGuides()
+        
+        # Test creating the widget
+        mock_guides = MockGuidesList()
+        try:
+            widget = InteractiveGuideWidget(mock_guides)
+            print("✓ Successfully created InteractiveGuideWidget instance")
+            print(f"  - Widget ID: {widget.widget_id}")
+            print(f"  - Widget base classes: {InteractiveGuideWidget.__bases__}")
+            
+            # Check if the widget has the expected methods
+            expected_methods = ['_generate_content', 'update_guides']
+            for method in expected_methods:
+                if hasattr(widget, method):
+                    print(f"  - Has method: {method}")
+                else:
+                    print(f"  - Missing method: {method}")
+                    
+        except Exception as e:
+            print(f"✗ Error creating widget: {e}")
+            
+    else:
+        print("⚠ ipywidgets not available - widget functionality disabled")
+        
+except ImportError as e:
+    print(f"✗ Import error: {e}")
+    
+except Exception as e:
+    print(f"✗ Unexpected error: {e}")
+    
+print("\nWidget implementation test complete!")

temp/test_widget_simple.py

@@ -0,0 +1,41 @@
+#!/usr/bin/env python
+"""Simple test for the guide widget"""
+
+import sys
+import os
+
+# Add parent directory to path
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
+
+# Test importing the module
+try:
+    from natural_pdf.analyzers.guides import InteractiveGuideWidget, _GUIDE_WIDGET_AVAILABLE
+    print(f"✓ Module imported successfully")
+    print(f"✓ Widget available: {_GUIDE_WIDGET_AVAILABLE}")
+    
+    if _GUIDE_WIDGET_AVAILABLE:
+        print("✓ ipywidgets is installed and InteractiveGuideWidget is available")
+    else:
+        print("✗ ipywidgets is not installed")
+        
+except ImportError as e:
+    print(f"✗ Import error: {e}")
+    sys.exit(1)
+
+# Check if we can create the widget class
+if _GUIDE_WIDGET_AVAILABLE:
+    try:
+        # We can't actually instantiate it without a GuidesList, but we can check the class exists
+        print(f"✓ InteractiveGuideWidget class: {InteractiveGuideWidget}")
+        print(f"✓ Widget base classes: {InteractiveGuideWidget.__bases__}")
+        
+        # Check methods
+        methods = [m for m in dir(InteractiveGuideWidget) if not m.startswith('_')]
+        print(f"✓ Public methods: {methods}")
+        
+    except Exception as e:
+        print(f"✗ Error checking widget class: {e}")
+else:
+    print("⚠ Skipping widget checks as ipywidgets is not available")
+
+print("\nAll checks passed!")

temp/debug_cell_extraction.py

@@ -1,42 +0,0 @@
-"""Debug cell text extraction with exclusions"""
-from natural_pdf import PDF
-from natural_pdf.analyzers.guides import Guides
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Add exclusions
-pdf.add_exclusion(lambda page: page.find(text="PREMISE").above(), label="header")
-
-# Check exclusions are registered
-print("Exclusions on page:")
-exclusions = page._get_exclusion_regions(debug=True)
-
-# Create guides and build grid
-headers = page.find(text="NUMBER").right(include_source=True).expand(top=3, bottom=3).find_all('text')
-guides = Guides(page)
-guides.vertical.from_content(headers, align='left')
-guides.horizontal.from_stripes()
-
-# Build grid and get cells
-grid_result = guides.build_grid(include_outer_boundaries=True)
-cells = grid_result["regions"]["cells"]
-
-print(f"\nTotal cells: {len(cells)}")
-
-# Check first row cells (these should be in excluded area)
-first_row_cells = [c for c in cells if c.bbox[1] < 90]  # y < 90
-print(f"\nFirst row cells: {len(first_row_cells)}")
-
-for i, cell in enumerate(first_row_cells[:3]):
-    print(f"\nCell {i}:")
-    print(f"  Bbox: {cell.bbox}")
-    print(f"  Raw text: {repr(cell.extract_text(apply_exclusions=False))}")
-    print(f"  With exclusions: {repr(cell.extract_text(apply_exclusions=True))}")
-
-# Now test the full table extraction
-print("\n\nFull table extraction:")
-result = guides.extract_table(include_outer_boundaries=True, apply_exclusions=True, header=False)
-df = result.to_df()
-print("\nFirst row of dataframe:")
-print(df.iloc[0].to_dict() if not df.empty else "Empty")

temp/debug_exclusion_overlap.py

@@ -1,43 +0,0 @@
-"""Debug how exclusions work with overlapping regions"""
-from natural_pdf import PDF
-from natural_pdf.analyzers.guides import Guides
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Add exclusion
-pdf.add_exclusion(lambda page: page.find(text="PREMISE").above(), label="header")
-
-# Get the exclusion region
-exclusions = page._get_exclusion_regions()
-excl_region = exclusions[0]
-print(f"Exclusion region: {excl_region.bbox}")
-print(f"Exclusion bottom: {excl_region.bbox[3]}")
-
-# Create a test cell that overlaps the exclusion
-# Cell 1 from before: (32.06, 0.5, 73.18288, 79.53999999999996)
-test_cell = page.region(32.06, 0.5, 73.18288, 79.53999999999996)
-
-print(f"\nTest cell: {test_cell.bbox}")
-print(f"Cell overlaps exclusion: top={test_cell.bbox[1]} < excl_bottom={excl_region.bbox[3]}")
-
-# Extract text from different y-ranges
-print("\nText in different parts of the cell:")
-
-# Part above exclusion line (should be empty)
-upper_part = page.region(32.06, 0.5, 73.18288, 59.12)
-print(f"Upper part (0.5 to 59.12): '{upper_part.extract_text(apply_exclusions=True)}'")
-
-# Part below exclusion line (should have text)  
-lower_part = page.region(32.06, 59.12, 73.18288, 79.54)
-print(f"Lower part (59.12 to 79.54): '{lower_part.extract_text()}'")
-
-# The whole cell
-print(f"Whole cell with exclusions: '{test_cell.extract_text(apply_exclusions=True)}'")
-print(f"Whole cell without exclusions: '{test_cell.extract_text(apply_exclusions=False)}'")
-
-# Check what text elements are in this region
-print("\nText elements in cell:")
-cell_texts = test_cell.find_all('text')
-for t in cell_texts[:5]:
-    print(f"  '{t.text}' at y={t.top:.2f}-{t.bottom:.2f}")

temp/debug_exclusions_guides.py

@@ -1,67 +0,0 @@
-"""Debug why exclusions aren't working with guides.extract_table()"""
-from natural_pdf import PDF
-from natural_pdf.analyzers.guides import Guides
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Check initial text
-print("Initial text:")
-print(page.extract_text()[:200])
-print()
-
-# Add exclusions
-pdf.add_exclusion(lambda page: page.find(text="PREMISE").above())
-pdf.add_exclusion(lambda page: page.find("text:regex(Page \d+ of)").expand())
-
-# Check text after exclusions
-print("Text after exclusions:")
-print(page.extract_text()[:100])
-print()
-
-# Debug exclusion regions
-print("Checking exclusion regions:")
-exclusions = page._get_exclusion_regions(debug=True)
-print(f"\nTotal exclusions: {len(exclusions)}")
-for i, exc in enumerate(exclusions):
-    print(f"  {i}: {exc.bbox}")
-print()
-
-# Create guides
-headers = (
-    page
-    .find(text="NUMBER")
-    .right(include_source=True)
-    .expand(top=3, bottom=3)
-    .find_all('text')
-)
-
-guides = Guides(page)
-guides.vertical.from_content(headers, align='left')
-guides.horizontal.from_stripes()
-
-# Build grid to see what regions are created
-print("\nBuilding grid...")
-grid_result = guides.build_grid(include_outer_boundaries=True)
-table_region = grid_result["regions"]["table"]
-print(f"Table region: {table_region}")
-print(f"Table bbox: {table_region.bbox if table_region else 'None'}")
-
-# Check if table region respects exclusions
-if table_region:
-    print("\nExtracting text from table region directly:")
-    table_text = table_region.extract_text()[:200]
-    print(f"Table text: {table_text}")
-    
-    # Now extract table
-    print("\nExtracting table with apply_exclusions=True:")
-    result = guides.extract_table(include_outer_boundaries=True, apply_exclusions=True, header=False)
-    df = result.to_df()
-    print(df.head())
-    
-    # Check if excluded content is in the table
-    table_str = df.to_string()
-    has_feb = "FEBRUARY 2014" in table_str or "FEBR" in table_str
-    has_alphabetic = "ALPHABETIC LISTING" in table_str
-    print(f"\nContains 'FEBRUARY': {has_feb}")
-    print(f"Contains 'ALPHABETIC LISTING': {has_alphabetic}")

temp/debug_extra_guide.py

@@ -1,41 +0,0 @@
-"""Debug the extra guide issue."""
-from natural_pdf import PDF
-from natural_pdf.analyzers.guides import Guides
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Get headers
-headers = (
-    page
-    .find("text:contains(NUMBER)")
-    .right(include_source=True)
-    .expand(top=3, bottom=3)
-    .find_all('text')
-)
-
-print("Headers 3-5:")
-for i, h in enumerate(headers[3:5]):
-    print(f"  {i}: '{h.text}' bbox={h.bbox}")
-
-# Create guides with just these two headers
-guides = Guides(page)
-guides.vertical.from_content(headers[3:5], align='left', outer=False)
-
-print(f"\nResulting guides: {guides.vertical}")
-print(f"Expected: [328.32012, 539.63316]")
-
-# Let's also check what happens with each header individually
-print("\nTesting each header individually:")
-for i, h in enumerate(headers[3:5]):
-    g = Guides(page)
-    g.vertical.from_content([h], align='left', outer=False)
-    print(f"  Header {i} guides: {g.vertical}")
-
-# Check if it's related to the ElementCollection
-print("\nTesting with manual list of text:")
-text_list = [h.text for h in headers[3:5]]
-print(f"Text list: {text_list}")
-guides2 = Guides(page)
-guides2.vertical.from_content(text_list, align='left', outer=False)
-print(f"Guides from text list: {guides2.vertical}")

temp/debug_outer_boundaries.py

@@ -1,46 +0,0 @@
-"""Debug outer boundaries issue with exclusions"""
-from natural_pdf import PDF
-from natural_pdf.analyzers.guides import Guides
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Add exclusions
-pdf.add_exclusion(lambda page: page.find(text="PREMISE").above())
-
-# Create guides
-headers = (
-    page
-    .find(text="NUMBER")
-    .right(include_source=True)
-    .expand(top=3, bottom=3)
-    .find_all('text')
-)
-
-guides = Guides(page)
-guides.vertical.from_content(headers, align='left')
-guides.horizontal.from_stripes()
-
-print("Horizontal guides (sorted):")
-for i, h in enumerate(sorted(guides.horizontal)):
-    print(f"  {i}: {h:.2f}")
-
-print(f"\nFirst content guide: {sorted(guides.horizontal)[0]:.2f}")
-print(f"Page height: {page.height}")
-
-# Test without outer boundaries
-print("\n\nWithout outer boundaries:")
-result1 = guides.extract_table(include_outer_boundaries=False, apply_exclusions=True, header=False)
-df1 = result1.to_df()
-print(f"Shape: {df1.shape}")
-print("First row, first column:", df1.iloc[0, 0] if not df1.empty else "Empty")
-
-# Test with outer boundaries
-print("\n\nWith outer boundaries:")
-result2 = guides.extract_table(include_outer_boundaries=True, apply_exclusions=True, header=False)
-df2 = result2.to_df()
-print(f"Shape: {df2.shape}")
-print("First row, first column:", df2.iloc[0, 0] if not df2.empty else "Empty")
-
-# The issue: include_outer_boundaries adds guides at 0 and 612,
-# which creates cells that span into the exclusion zone

temp/debug_st_search.py

@@ -1,33 +0,0 @@
-"""Debug searching for 'ST' text."""
-from natural_pdf import PDF
-
-pdf = PDF("pdfs/m27.pdf")
-page = pdf.pages[0]
-
-# Get the original ST element
-headers = (
-    page
-    .find("text:contains(NUMBER)")
-    .right(include_source=True)
-    .expand(top=3, bottom=3)
-    .find_all('text')
-)
-original_st = headers[4]
-print(f"Original 'ST' element: '{original_st.text}' at {original_st.bbox}")
-
-# Search for 'ST' using find
-found_st = page.find('text:contains("ST")')
-print(f"\nFound 'ST' using find: '{found_st.text}' at {found_st.bbox}")
-
-# Find all elements containing 'ST'
-all_st = page.find_all('text:contains("ST")')
-print(f"\nAll elements containing 'ST':")
-for i, elem in enumerate(all_st[:10]):  # First 10
-    print(f"  {i}: '{elem.text}' at x={elem.x0:.2f}, bbox={elem.bbox}")
-
-# Check what's at position 332.88
-print(f"\nLooking for element at x≈332.88:")
-all_text = page.find_all('text')
-for elem in all_text:
-    if 332 < elem.x0 < 334:
-        print(f"  Found: '{elem.text}' at x={elem.x0:.5f}, bbox={elem.bbox}")