pyWebLayout/tests/test_long_word_fix.py

#!/usr/bin/env python3
"""
Test script specifically for verifying the long word fix.
"""

from PIL import Image, ImageDraw
from pyWebLayout.concrete.text import Text, Line
from pyWebLayout.style import Font, FontStyle, FontWeight
from pyWebLayout.style.layout import Alignment

def test_supercalifragilisticexpialidocious():
    """Test the specific long word that was causing issues"""
    
    print("Testing long word handling...")
    
    font_style = Font(
        font_path=None,
        font_size=12,
        colour=(0, 0, 0, 255)
    )
    
    # The problematic sentence
    sentence = "This sentence has some really long words like supercalifragilisticexpialidocious that might need hyphenation."
    
    # Test with the same constraints that were failing
    line_width = 150
    line_height = 25
    
    words = sentence.split()
    
    # Create lines and track all the text
    lines = []
    words_remaining = words.copy()
    all_rendered_text = []
    
    print(f"Original sentence: {sentence}")
    print(f"Line width: {line_width}px")
    print()
    
    line_number = 1
    while words_remaining:
        print(f"Creating line {line_number}...")
        
        # Create a new line
        current_line = Line(
            spacing=(3, 8),
            origin=(0, (line_number-1) * line_height),
            size=(line_width, line_height),
            font=font_style,
            halign=Alignment.LEFT
        )
        
        lines.append(current_line)
        
        # Add words to current line until it's full
        words_added_to_line = []
        while words_remaining:
            word = words_remaining[0]
            print(f"  Trying to add word: '{word}'")
            
            result = current_line.add_word(word)
            
            if result is None:
                # Word fit in the line
                words_added_to_line.append(word)
                words_remaining.pop(0)
                print(f"    ✓ Added '{word}' to line {line_number}")
            else:
                # Word didn't fit, or only part of it fit
                if result == word:
                    # Whole word didn't fit
                    print(f"    ✗ Word '{word}' didn't fit, moving to next line")
                    break
                else:
                    # Part of word fit, remainder is in result
                    words_added_to_line.append(word)  # The original word
                    words_remaining[0] = result  # Replace with remainder
                    print(f"    ⚡ Part of '{word}' fit, remainder: '{result}'")
                    break
        
        # Show what's on this line
        line_words = [word.text for word in current_line.text_objects]
        line_text = ' '.join(line_words)
        all_rendered_text.extend(line_words)
        print(f"  Line {line_number} contains: \"{line_text}\"")
        print(f"  Line {line_number} width usage: {current_line._current_width}/{line_width}px")
        print()
        
        # If no words were added to this line, we have a problem
        if not line_words:
            print(f"ERROR: No words could be added to line {line_number}")
            break
            
        line_number += 1
        
        # Safety check to prevent infinite loops
        if line_number > 10:
            print("Safety break: too many lines")
            break
    
    # Check if all words were rendered
    original_words = sentence.split()
    rendered_text_combined = ' '.join(all_rendered_text)
    
    print("="*60)
    print("VERIFICATION")
    print("="*60)
    print(f"Original text: {sentence}")
    print(f"Rendered text: {rendered_text_combined}")
    print()
    
    # Check for the problematic word
    long_word = "supercalifragilisticexpialidocious"
    if long_word in rendered_text_combined:
        print(f"✓ SUCCESS: Long word '{long_word}' was rendered!")
    elif "supercalifragilisticexpialidocious" in rendered_text_combined:
        print(f"✓ SUCCESS: Long word was rendered (possibly hyphenated)!")
    else:
        # Check if parts of the word are there
        found_parts = []
        for rendered_word in all_rendered_text:
            if long_word.startswith(rendered_word.replace('-', '')):
                found_parts.append(rendered_word)
            elif rendered_word.replace('-', '') in long_word:
                found_parts.append(rendered_word)
        
        if found_parts:
            print(f"✓ PARTIAL SUCCESS: Found parts of long word: {found_parts}")
        else:
            print(f"✗ FAILURE: Long word '{long_word}' was not rendered at all!")
    
    print(f"Total lines used: {len(lines)}")
    
    # Create combined image showing all lines
    total_height = len(lines) * line_height
    combined_image = Image.new('RGBA', (line_width, total_height), (255, 255, 255, 255))
    
    for i, line in enumerate(lines):
        line_img = line.render()
        y_pos = i * line_height
        combined_image.paste(line_img, (0, y_pos), line_img)
        
        # Add a border for visualization
        draw = ImageDraw.Draw(combined_image)
        draw.rectangle([(0, y_pos), (line_width-1, y_pos + line_height-1)], outline=(200, 200, 200), width=1)
    
    # Save the result
    output_filename = "test_long_word_fix.png"
    combined_image.save(output_filename)
    print(f"Result saved as: {output_filename}")
    
    return len(lines), all_rendered_text

if __name__ == "__main__":
    print("Testing long word fix for 'supercalifragilisticexpialidocious'...\n")
    
    lines_used, rendered_words = test_supercalifragilisticexpialidocious()
    
    print(f"\nTest completed!")
    print(f"- Lines used: {lines_used}")
    print(f"- Total words rendered: {len(rendered_words)}")
    print(f"- Check test_long_word_fix.png for visual verification")