crossword-app/backend-py/test-integration/test_visual_analysis.py

#!/usr/bin/env python3
"""
Test to analyze the visual representation issue that might cause words to appear extended.
"""

import sys
from pathlib import Path

# Add project root to path
project_root = Path(__file__).parent.parent  # Go up from test-integration to backend-py
sys.path.insert(0, str(project_root))

from src.services.crossword_generator_fixed import CrosswordGeneratorFixed

def analyze_visual_word_extensions():
    """Analyze how visual word extensions might occur in the crossword grid."""
    
    print("🔍 Analyzing Visual Word Extension Issues\n")
    
    generator = CrosswordGeneratorFixed(vector_service=None)
    
    # Create a scenario that might produce the "visual extension" effect
    # Based on the crossword images, it seems like words are appearing to extend
    # when they shouldn't
    
    grid = [["." for _ in range(15)] for _ in range(15)]
    placed_words = []
    
    print("=" * 60)
    print("SCENARIO 1: Creating potential visual extension")
    print("=" * 60)
    
    # Step 1: Place MACHINE
    if generator._can_place_word(grid, "MACHINE", 7, 3, "horizontal"):
        generator._place_word(grid, "MACHINE", 7, 3, "horizontal")
        placed_words.append({
            "word": "MACHINE", "row": 7, "col": 3, "direction": "horizontal", "number": 1
        })
        print("✅ Placed MACHINE at (7, 3) horizontal")
    
    # Step 2: Place a word that intersects at the end of MACHINE
    # This might create the visual illusion of extension
    if generator._can_place_word(grid, "EXPERT", 5, 9, "vertical"):  # E intersects with E in MACHINE
        generator._place_word(grid, "EXPERT", 5, 9, "vertical")
        placed_words.append({
            "word": "EXPERT", "row": 5, "col": 9, "direction": "vertical", "number": 2
        })
        print("✅ Placed EXPERT at (5, 9) vertical")
    
    # Step 3: Place another intersecting word that might create confusion
    if generator._can_place_word(grid, "TYPOGRAPHY", 7, 10, "horizontal"):  # Starts right after MACHINE
        generator._place_word(grid, "TYPOGRAPHY", 7, 10, "horizontal")
        placed_words.append({
            "word": "TYPOGRAPHY", "row": 7, "col": 10, "direction": "horizontal", "number": 3
        })
        print("✅ Placed TYPOGRAPHY at (7, 10) horizontal")
    
    print("\nCurrent grid state:")
    print_detailed_grid(grid, placed_words)
    
    # Analyze what the human eye might see
    print("\n" + "=" * 60)
    print("VISUAL ANALYSIS")
    print("=" * 60)
    
    analyze_row_sequences(grid, placed_words, 7)  # Analyze row 7 specifically
    analyze_column_sequences(grid, placed_words, 9)  # Analyze column 9 specifically
    
    # Test another scenario
    print("\n" + "=" * 60)
    print("SCENARIO 2: Adjacent word placement")
    print("=" * 60)
    
    grid2 = [["." for _ in range(15)] for _ in range(15)]
    placed_words2 = []
    
    # Place words that are adjacent but should be separate
    if generator._can_place_word(grid2, "SCIENCE", 6, 2, "horizontal"):
        generator._place_word(grid2, "SCIENCE", 6, 2, "horizontal")
        placed_words2.append({
            "word": "SCIENCE", "row": 6, "col": 2, "direction": "horizontal", "number": 1
        })
    
    # Try to place a word immediately after with no gap
    if generator._can_place_word(grid2, "TECHNOLOGY", 6, 9, "horizontal"):
        generator._place_word(grid2, "TECHNOLOGY", 6, 9, "horizontal")
        placed_words2.append({
            "word": "TECHNOLOGY", "row": 6, "col": 9, "direction": "horizontal", "number": 2
        })
        print("⚠️ Placed TECHNOLOGY immediately after SCIENCE")
    else:
        print("✅ Correctly prevented TECHNOLOGY placement immediately after SCIENCE")
    
    print("\nGrid 2 state:")
    print_detailed_grid(grid2, placed_words2)
    
    # Check what boundary checking should prevent
    print("\n" + "=" * 60)
    print("BOUNDARY VALIDATION TEST")
    print("=" * 60)
    
    test_boundary_edge_cases(generator)

def print_detailed_grid(grid, placed_words, highlight_rows=None):
    """Print grid with detailed analysis."""
    print("Grid with word boundaries marked:")
    print("   ", end="")
    for c in range(min(15, len(grid[0]))):
        print(f"{c:2d}", end="")
    print()
    
    for r in range(min(15, len(grid))):
        print(f"{r:2d}: ", end="")
        for c in range(min(15, len(grid[0]))):
            cell = grid[r][c]
            if cell == ".":
                print(" .", end="")
            else:
                print(f" {cell}", end="")
        print()
    
    print("\nPlaced words:")
    for i, word_info in enumerate(placed_words):
        print(f"  {i+1}. {word_info['word']} at ({word_info['row']}, {word_info['col']}) {word_info['direction']}")

def analyze_row_sequences(grid, placed_words, row):
    """Analyze letter sequences in a specific row."""
    print(f"\nAnalyzing row {row} sequences:")
    
    # Extract all letters in the row
    row_letters = []
    for c in range(len(grid[0])):
        if grid[row][c] != ".":
            row_letters.append((c, grid[row][c]))
    
    if not row_letters:
        print("  No letters in this row")
        return
    
    print(f"  Letters found: {row_letters}")
    
    # Find continuous sequences
    sequences = []
    current_seq = []
    
    for i, (col, letter) in enumerate(row_letters):
        if not current_seq or col == row_letters[i-1][0] + 1:
            current_seq.append((col, letter))
        else:
            if len(current_seq) > 1:
                sequences.append(current_seq)
            current_seq = [(col, letter)]
    
    if len(current_seq) > 1:
        sequences.append(current_seq)
    
    print(f"  Continuous sequences: {len(sequences)}")
    for i, seq in enumerate(sequences):
        word = "".join([letter for col, letter in seq])
        start_col = seq[0][0]
        print(f"    Sequence {i+1}: '{word}' starting at column {start_col}")
        
        # Check if this matches intended words
        intended = False
        for word_info in placed_words:
            if (word_info["direction"] == "horizontal" and 
                word_info["row"] == row and 
                word_info["col"] == start_col and
                word_info["word"] == word):
                intended = True
                print(f"      ✅ This is the intended word '{word_info['word']}'")
                break
        
        if not intended and len(word) > 1:
            print(f"      ❌ This appears to be an unintended word formation!")

def analyze_column_sequences(grid, placed_words, col):
    """Analyze letter sequences in a specific column."""
    print(f"\nAnalyzing column {col} sequences:")
    
    # Extract all letters in the column
    col_letters = []
    for r in range(len(grid)):
        if grid[r][col] != ".":
            col_letters.append((r, grid[r][col]))
    
    if not col_letters:
        print("  No letters in this column")
        return
    
    print(f"  Letters found: {col_letters}")
    
    # Find continuous sequences
    sequences = []
    current_seq = []
    
    for i, (row, letter) in enumerate(col_letters):
        if not current_seq or row == col_letters[i-1][0] + 1:
            current_seq.append((row, letter))
        else:
            if len(current_seq) > 1:
                sequences.append(current_seq)
            current_seq = [(row, letter)]
    
    if len(current_seq) > 1:
        sequences.append(current_seq)
    
    print(f"  Continuous sequences: {len(sequences)}")
    for i, seq in enumerate(sequences):
        word = "".join([letter for row, letter in seq])
        start_row = seq[0][0]
        print(f"    Sequence {i+1}: '{word}' starting at row {start_row}")
        
        # Check if this matches intended words
        intended = False
        for word_info in placed_words:
            if (word_info["direction"] == "vertical" and 
                word_info["col"] == col and 
                word_info["row"] == start_row and
                word_info["word"] == word):
                intended = True
                print(f"      ✅ This is the intended word '{word_info['word']}'")
                break
        
        if not intended and len(word) > 1:
            print(f"      ❌ This appears to be an unintended word formation!")

def test_boundary_edge_cases(generator):
    """Test specific boundary edge cases."""
    
    # Test case 1: Words that touch but shouldn't form a continuous sequence
    grid = [["." for _ in range(10)] for _ in range(10)]
    
    # Place first word
    generator._place_word(grid, "CAT", 5, 2, "horizontal")
    
    # Try to place second word immediately adjacent (should be blocked)
    can_place = generator._can_place_word(grid, "DOG", 5, 5, "horizontal")
    print(f"Can place 'DOG' immediately after 'CAT': {can_place}")
    
    if can_place:
        print("❌ PROBLEM: Adjacent words allowed - this could create visual extension!")
        print("Current grid after CAT:")
        for r in range(3, 8):
            print(f"Row {r}: ", end="")
            for c in range(8):
                print(f"{grid[r][c]} ", end="")
            print()
        
        generator._place_word(grid, "DOG", 5, 5, "horizontal") 
        print("After adding DOG:")
        for r in range(3, 8):
            print(f"Row {r}: ", end="")
            for c in range(8):
                print(f"{grid[r][c]} ", end="")
            print()
    else:
        print("✅ Correctly prevented adjacent word placement")
    
    # Test case 2: Check gap requirement
    can_place_with_gap = generator._can_place_word(grid, "DOG", 5, 6, "horizontal")
    print(f"Can place 'DOG' with 1-cell gap after 'CAT': {can_place_with_gap}")

if __name__ == "__main__":
    analyze_visual_word_extensions()