fix(cv): resolve infinite page duplication bug caused by playback cursor

scripts/debug/dump_measure_numbers.py

@@ -0,0 +1,50 @@
+import cv2
+import numpy as np
+import os
+
+pdf_path = r"C:\Users\Certes\Desktop\guitar_score\output\shintakarajima_perfect.pdf"
+out_dir = r"C:\Users\Certes\Desktop\guitar_score\scripts\debug"
+
+img_path = os.path.join(out_dir, "verify_chunk_0.jpg") # from previous sessions
+if not os.path.exists(img_path):
+    print("verify_chunk_0.jpg not found. extracting a page from PDF...")
+    import fitz
+    doc = fitz.open(pdf_path)
+    page = doc.load_page(0)
+    pix = page.get_pixmap(dpi=150)
+    pix.save(os.path.join(out_dir, "pdf_test_page.png"))
+    img_path = os.path.join(out_dir, "pdf_test_page.png")
+
+img = cv2.imread(img_path)
+gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+_, bin_inv = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY_INV)
+
+h, w = img.shape[:2]
+staff_y_top = int(h * 0.3)
+row_sums = np.sum(bin_inv[:, :min(w, 1000)], axis=1) / 255.0
+staff_rows = np.where(row_sums > min(w, 1000) * 0.4)[0]
+if len(staff_rows) >= 6: staff_y_top = staff_rows[0]
+
+# locate measure bars
+col_sums = np.sum(bin_inv[staff_y_top:staff_y_top+100, :], axis=0) / 255.0
+bar_xs = np.where(col_sums > 30)[0]
+bars = []
+if len(bar_xs) > 0:
+    curr = [bar_xs[0]]
+    for x in bar_xs[1:]:
+        if x - curr[-1] < 10: curr.append(x)
+        else:
+            bars.append(int(np.mean(curr)))
+            curr = [x]
+    bars.append(int(np.mean(curr)))
+
+# Crop first 5 measure numbers
+for i, x in enumerate(bars[:5]):
+    box_y1 = max(0, staff_y_top - 40)
+    box_y2 = staff_y_top
+    box_x1 = x
+    box_x2 = min(w, x + 60)
+    crop = img[box_y1:box_y2, box_x1:box_x2]
+    out_file = os.path.join(out_dir, f"measure_num_{i}.png")
+    cv2.imwrite(out_file, crop)
+    print(f"Saved measure number crop to {out_file}")

scripts/debug/fast_verify.py

@@ -1,78 +0,0 @@
-import cv2
-from video_cv_tracker import TemporalTracker
-from youtube_tab_to_pdf import extract_unique_scroll, generate_long_image, generate_pdf, download_video, extract_frames
-import sys
-import os
-from pathlib import Path
-
-# Run verification specifically on Shintakarajima
-url = "https://youtu.be/tJq1n8TofM0"
-video_path = Path("output/サカナクション／新宝島(エレキギターTAB) 難易度★★★ sakanaction shintakarajima.mp4")
-
-print("Extracting full video for final 142-measure verification...")
-cap = cv2.VideoCapture(str(video_path))
-
-# PRE-CALCULATE Dynamic Crop
-# Just like extract_unique_scroll does automatically, we detect the white band.
-ret, initial = cap.read()
-scale = 1280 / initial.shape[1]
-resized_init = cv2.resize(initial, (1280, int(initial.shape[0] * scale)))
-
-from youtube_tab_to_pdf import _find_white_tab_strip
-crop_top = 0
-crop_bottom = resized_init.shape[0]
-
-cap.set(cv2.CAP_PROP_POS_FRAMES, 500)
-ret, check_frame = cap.read()
-if ret:
-    resized_check = cv2.resize(check_frame, (1280, int(check_frame.shape[0] * scale)))
-    bounds = _find_white_tab_strip(resized_check)
-    if bounds:
-        crop_top, crop_bottom = bounds
-        # Preserve D.S. al Coda, ┌─ 1., ┌─ 2., and measure numbers drawn in the black abyss!
-        crop_top = max(0, crop_top - 60)
-        
-print(f"Dynamically Cropping to: Y={crop_top} to {crop_bottom}")
-
-cap.set(cv2.CAP_PROP_POS_FRAMES, 0)
-frames = []
-idx = 0
-tracker = TemporalTracker(diff_threshold=0.05)
-
-while True:
-    ret, frame = cap.read()
-    if not ret: break
-    
-    frame_resized = cv2.resize(frame, (1280, int(frame.shape[0] * scale)))
-    clean_ribbon = frame_resized[crop_top:crop_bottom, :]
-    frames.append(clean_ribbon)
-    idx += 1
-
-cap.release()
-
-cv2.imwrite("C:/Users/Certes/.gemini/antigravity/brain/975cea00-dd68-4689-9ee3-f1a2408b4ee6/raw_frame_check.png", frames[30])
-
-print(f"Extracted {len(frames)} frames. Running sequential page extraction...")
-try:
-    final_chunks = extract_unique_scroll(frames)
-    print("DEBUG: final_chunks len =", len(final_chunks))
-    if final_chunks:
-        print("DEBUG: final_chunks[0].shape =", final_chunks[0].shape)
-        cv2.imwrite("C:/Users/Certes/.gemini/antigravity/brain/975cea00-dd68-4689-9ee3-f1a2408b4ee6/debug_chunk_0.png", final_chunks[0])
-    
-    # Save the chunks to artifact directory to literally look at it
-    artifact_path = Path(os.environ.get('APPDATA', '')) / '..' / 'Local' / 'Google' / 'AndroidStudio2024.1' # Just using relative artifact manually? No, I'll save it to C:\Users\Certes\.gemini\antigravity\brain\975cea00-dd68-4689-9ee3-f1a2408b4ee6\
-    artifact_path = Path(r"C:\Users\Certes\.gemini\antigravity\brain\975cea00-dd68-4689-9ee3-f1a2408b4ee6")
-    output_png = artifact_path / "final_check_100_sec.png"
-    
-    generate_long_image(final_chunks, output_png)
-    print(f"Saved successful verification image to: {output_png}")
-
-    if final_chunks:
-        generate_pdf(final_chunks, Path("output/shintakarajima_perfect.pdf"))
-        print("✨ Successfully generated output/shintakarajima_perfect.pdf ✨")
-    else:
-        print("Failed to produce rows.")
-except Exception as e:
-    import traceback
-    traceback.print_exc()

scripts/debug/print_ascii.py

@@ -0,0 +1,24 @@
+import cv2
+import numpy as np
+import sys
+
+def print_ascii(img_path):
+    img = cv2.imread(img_path, cv2.IMREAD_GRAYSCALE)
+    if img is None: return
+    _, bin_inv = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY_INV)
+    
+    # Trim empty borders
+    coords = cv2.findNonZero(bin_inv)
+    if coords is not None:
+        x,y,w,h = cv2.boundingRect(coords)
+        bin_inv = bin_inv[y:y+h, x:x+w]
+        
+    print(f"\nImage: {img_path}")
+    for row in range(0, bin_inv.shape[0], 2):
+        line = ""
+        for col in range(0, bin_inv.shape[1], 1):
+            line += "##" if bin_inv[row, col] > 127 else "  "
+        print(line)
+
+for i in range(5):
+    print_ascii(rf"C:\Users\Certes\Desktop\guitar_score\scripts\debug\measure_num_{i}.png")

scripts/debug/render_pdf.py

@@ -0,0 +1,36 @@
+import os
+import sys
+
+try:
+    import fitz  # PyMuPDF
+except ImportError:
+    print("fitz not found, trying to install PyMuPDF...")
+    os.system(f"{sys.executable} -m pip install PyMuPDF")
+    import fitz
+
+pdf_path = r"C:\Users\Certes\Desktop\guitar_score\output\shintakarajima_perfect.pdf"
+out_dir = r"C:\Users\Certes\.gemini\antigravity\brain\5805a1e3-c776-4325-8538-351d54b5e0a0"
+
+try:
+    doc = fitz.open(pdf_path)
+    md_content = "# PDF Visual Inspection\n\n```carousel\n"
+    
+    for i in range(min(5, len(doc))): # First 5 pages are enough to see the tangling
+        page = doc.load_page(i)
+        pix = page.get_pixmap(dpi=150)
+        out_file = os.path.join(out_dir, f"pdf_page_{i}.png")
+        pix.save(out_file)
+        
+        if i > 0:
+            md_content += "<!-- slide -->\n"
+        md_content += f"![Page {i+1}]({out_file})\n"
+        
+    md_content += "```\n"
+
+    with open(os.path.join(out_dir, "PDF_Inspection.md"), "w", encoding="utf-8") as f:
+        f.write(md_content)
+        
+    print("PDF successfully rendered to images and markdown generated.")
+
+except Exception as e:
+    print(f"Error rendering PDF: {e}")

scripts/debug/rigorous_validator.py

@@ -0,0 +1,87 @@
+import fitz
+import cv2
+import numpy as np
+import os
+
+pdf_path = "output/shintakarajima_perfect.pdf"
+if not os.path.exists(pdf_path):
+    print("PDF not found!")
+    exit(1)
+
+doc = fitz.open(pdf_path)
+total_measures = 0
+measure_widths = []
+
+print("Running Rigorous Visual Validation against PDF...")
+
+for page_num in range(len(doc)):
+    page = doc.load_page(page_num)
+    pix = page.get_pixmap(dpi=150)
+    img = np.frombuffer(pix.samples, dtype=np.uint8).reshape(pix.h, pix.w, pix.n)
+    if img.shape[2] == 4:
+        img = cv2.cvtColor(img, cv2.COLOR_BGRA2BGR)
+    elif img.shape[2] == 1:
+        img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
+        
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    _, bin_inv = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY_INV)
+    
+    row_sums = np.sum(bin_inv, axis=1) / 255.0
+    staff_rows = np.where(row_sums > bin_inv.shape[1] * 0.4)[0]
+    
+    if len(staff_rows) == 0: continue
+    
+    staves = []
+    curr = [staff_rows[0]]
+    for y in staff_rows[1:]:
+        if y - curr[-1] < 100: curr.append(y)
+        else:
+            staves.append((curr[0], curr[-1]))
+            curr = [y]
+    staves.append((curr[0], curr[-1]))
+    
+    page_measures = 0
+    for i, (top, bottom) in enumerate(staves):
+        top = max(0, top - 20)
+        bottom = min(img.shape[0], bottom + 20)
+        
+        staff_region = bin_inv[top:bottom, :]
+        col_sums = np.sum(staff_region, axis=0) / 255.0
+        
+        expected_h = bottom - top
+        bar_xs = np.where(col_sums >= expected_h * 0.5)[0]
+        
+        grouped_bars = []
+        if len(bar_xs) > 0:
+            c = [bar_xs[0]]
+            for x in bar_xs[1:]:
+                if x - c[-1] < 10: c.append(x)
+                else:
+                    grouped_bars.append(int(np.mean(c)))
+                    c = [x]
+            grouped_bars.append(int(np.mean(c)))
+            
+        if len(grouped_bars) > 1:
+            diffs = np.diff(grouped_bars)
+            for d in diffs:
+                if d > 120: # filter out double bars ||
+                    measure_widths.append(d)
+                    page_measures += 1
+                    total_measures += 1
+                    
+    print(f"Page {page_num+1:02d}: Extracted {page_measures} measures.")
+
+print("\n--- Absolute Verdict ---")
+print(f"Total True Measures Counted: {total_measures}")
+if measure_widths:
+    print(f"Minimum Width: {np.min(measure_widths):.1f} px")
+    print(f"Maximum Width: {np.max(measure_widths):.1f} px")
+    print(f"Average Width: {np.mean(measure_widths):.1f} px")
+    
+    anomalies = [i for i, w in enumerate(measure_widths) if w > 1200 or w < 150]
+    if anomalies:
+        print(f"FAILED: Found {len(anomalies)} structural anomalies (broken or fused measures)!")
+    else:
+        print("PASS: 100% of measures have perfectly valid, biologically possible widths. No mangled Frankesteins.")
+else:
+    print("FAILED: No measures found!")

scripts/debug/slice_for_ai.py

@@ -0,0 +1,31 @@
+import cv2
+import os
+
+img_path = r"C:\Users\Certes\.gemini\antigravity\brain\975cea00-dd68-4689-9ee3-f1a2408b4ee6\final_check_100_sec.png"
+out_dir = r"C:\Users\Certes\.gemini\antigravity\brain\5805a1e3-c776-4325-8538-351d54b5e0a0"
+
+img = cv2.imread(img_path)
+h, w = img.shape[:2]
+
+slice_h = 1000
+num_slices = (h + slice_h - 1) // slice_h
+
+md_content = "# Visual Inspection of final_check_100_sec.png\n\n```carousel\n"
+
+for i in range(num_slices):
+    y_start = i * slice_h
+    y_end = min((i + 1) * slice_h, h)
+    slice_img = img[y_start:y_end, :]
+    out_file = os.path.join(out_dir, f"ai_slice_{i}.png")
+    cv2.imwrite(out_file, slice_img)
+    
+    if i > 0:
+        md_content += "<!-- slide -->\n"
+    md_content += f"![Slice {i}]({out_file})\n"
+
+md_content += "```\n"
+
+with open(os.path.join(out_dir, "visual_inspection.md"), "w", encoding="utf-8") as f:
+    f.write(md_content)
+
+print(f"Generated {num_slices} slices and artifact visual_inspection.md")

scripts/debug/test_full_ocr.py

@@ -0,0 +1,32 @@
+import cv2
+import easyocr
+import numpy as np
+
+img_path = r"C:\Users\Certes\.gemini\antigravity\brain\5805a1e3-c776-4325-8538-351d54b5e0a0\ai_slice_3.png"
+img = cv2.imread(img_path)
+gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+_, bin_inv = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY_INV)
+
+row_sums = np.sum(bin_inv, axis=1) / 255.0
+staff_rows = np.where(row_sums > bin_inv.shape[1] * 0.4)[0]
+staff_top = staff_rows[0]
+
+upper_band = gray[max(0, staff_top - 60) : staff_top + 10, :] # Include slightly below top line
+cv2.imwrite(r"C:\Users\Certes\Desktop\guitar_score\scripts\debug\upper_band.png", upper_band)
+
+reader = easyocr.Reader(['en'], gpu=False)
+
+# Test 1: Original
+print("Testing Original Upper Band...")
+results = reader.readtext(upper_band, allowlist='0123456789')
+for r in results: print(r)
+
+# Test 2: Upscaled
+print("\nTesting Upscaled x2...")
+lg2 = cv2.resize(upper_band, (upper_band.shape[1]*2, upper_band.shape[0]*2), interpolation=cv2.INTER_CUBIC)
+for r in reader.readtext(lg2, allowlist='0123456789'): print(r)
+
+# Test 3: Binarized
+print("\nTesting Binarized Upscaled...")
+_, bin_lg = cv2.threshold(lg2, 180, 255, cv2.THRESH_BINARY_INV)
+for r in reader.readtext(bin_lg, allowlist='0123456789'): print(r)

scripts/debug/test_ocr_band.py

@@ -0,0 +1,65 @@
+import cv2
+import numpy as np
+import easyocr
+import sys
+
+# Initialize EasyOCR reader
+reader = easyocr.Reader(['en'], gpu=False)
+
+def extract_measure_numbers(img_path):
+    img = cv2.imread(img_path)
+    if img is None: return
+    
+    # We find the rows of the staff
+    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    _, bin_inv = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY_INV)
+    
+    # To find the first measure of this chunk, let's find the vertical measure bar
+    col_sums = np.sum(bin_inv, axis=0) / 255.0
+    # a measure bar is a tall black line
+    bar_xs = np.where(col_sums > 30)[0]
+    
+    if len(bar_xs) == 0: return
+    
+    # Group the xs into distinct bars
+    bars = []
+    curr = [bar_xs[0]]
+    for x in bar_xs[1:]:
+        if x - curr[-1] < 10:
+            curr.append(x)
+        else:
+            bars.append(int(np.mean(curr)))
+            curr = [x]
+    bars.append(int(np.mean(curr)))
+    
+    print(f"File: {img_path}")
+    for bar_x in bars[:5]: # Check first 5 bars
+        # The measure number is usually right after the bar, slightly above the staff.
+        # Let's crop a box [bar_x : bar_x + 50] horizontally, and [staff_top - 30 : staff_top] vertically
+        
+        # approximate staff_top
+        slice_cols = bin_inv[:, bar_x:bar_x+10]
+        row_sums = np.sum(slice_cols, axis=1) / 255.0
+        staff_rows = np.where(row_sums > 2)[0]
+        if len(staff_rows) == 0: continue
+        staff_top = staff_rows[0]
+        
+        y1 = max(0, staff_top - 40)
+        y2 = staff_top
+        x1 = bar_x
+        x2 = min(img.shape[1], bar_x + 60)
+        
+        crop = gray[y1:y2, x1:x2]
+        if crop.shape[0] < 10 or crop.shape[1] < 10: continue
+        
+        # Upscale for OCR
+        crop_lg = cv2.resize(crop, (crop.shape[1]*3, crop.shape[0]*3), interpolation=cv2.INTER_CUBIC)
+        
+        results = reader.readtext(crop_lg, allowlist='0123456789')
+        for (bbox, text, prob) in results:
+            if prob > 0.5:
+                print(f"  Bar at x={bar_x}: Measure {text} (conf: {prob:.2f})")
+                
+if __name__ == "__main__":
+    extract_measure_numbers(r"C:\Users\Certes\.gemini\antigravity\brain\5805a1e3-c776-4325-8538-351d54b5e0a0\ai_slice_0.png")
+    extract_measure_numbers(r"C:\Users\Certes\.gemini\antigravity\brain\5805a1e3-c776-4325-8538-351d54b5e0a0\ai_slice_3.png")

scripts/debug/verify_structure.py

@@ -0,0 +1,55 @@
+import cv2
+import numpy as np
+import os
+
+img_path = r"C:\Users\Certes\.gemini\antigravity\brain\975cea00-dd68-4689-9ee3-f1a2408b4ee6\final_check_100_sec.png"
+if not os.path.exists(img_path):
+    print("final_check_100_sec.png not found!")
+    exit(1)
+
+img = cv2.imread(img_path)
+gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+_, bin_inv = cv2.threshold(gray, 200, 255, cv2.THRESH_BINARY_INV)
+
+h, w = img.shape[:2]
+
+row_sums = np.sum(bin_inv[:, :1000], axis=1) / 255.0
+staff_rows = np.where(row_sums > 1000 * 0.4)[0]
+if len(staff_rows) < 6:
+    print("Cannot find staff lines")
+    exit(1)
+staff_y_top = staff_rows[0]
+staff_y_bottom = staff_rows[-1]
+
+expected_h = staff_y_bottom - staff_y_top
+print(f"Staff height: {expected_h}px (from Y={staff_y_top} to {staff_y_bottom})")
+
+col_sums = np.sum(bin_inv[staff_y_top:staff_y_bottom, :], axis=0) / 255.0
+bar_xs = np.where(col_sums >= expected_h * 0.6)[0]
+
+grouped_bars = []
+if len(bar_xs) > 0:
+    curr = [bar_xs[0]]
+    for x in bar_xs[1:]:
+        if x - curr[-1] < 10: curr.append(x)
+        else:
+            grouped_bars.append(int(np.mean(curr)))
+            curr = [x]
+    grouped_bars.append(int(np.mean(curr)))
+
+diffs = np.diff(grouped_bars)
+print(f"Total measures: {len(grouped_bars) - 1}")
+
+def get_stats(arr):
+    if not len(arr): return "N/A"
+    return f"Min: {np.min(arr)}, Max: {np.max(arr)}, Mean: {np.mean(arr):.1f}"
+
+print("Measure width stats:", get_stats(diffs))
+
+anomalies = [i for i, d in enumerate(diffs) if d < 180 or d > 1200]
+if anomalies:
+    print(f"\n[FAIL] ANOMALIES DETECTED! Mangled measures at indices: {anomalies}")
+    for i in anomalies[:20]:
+        print(f"  Measure {i}: width {diffs[i]}px (Starts at X={grouped_bars[i]})")
+else:
+    print("\n[SUCCESS] NO ANOMALIES. All measures have consistent beat widths. No overlapping mangles detected!")