#!/usr/bin/env python3
"""Debug script: analyze text line slopes on deskewed image to determine true residual shear."""
import sys, math, asyncio
sys.path.insert(0, "/app/backend")

import cv2
import numpy as np
import pytesseract
from ocr_pipeline_session_store import get_session_db

SESSION_ID = "3dcb1897-09a6-4b80-91b5-7e4207980bf3"

async def main():
    s = await get_session_db(SESSION_ID)
    if not s:
        print("Session not found")
        return

    deskewed_png = s.get("deskewed_png")
    if not deskewed_png:
        print("No deskewed_png stored")
        return

    arr = np.frombuffer(deskewed_png, dtype=np.uint8)
    img = cv2.imdecode(arr, cv2.IMREAD_COLOR)
    h, w = img.shape[:2]
    print(f"Deskewed image: {w}x{h}")

    # Detect text line slopes using Tesseract word positions
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    data = pytesseract.image_to_data(gray, output_type=pytesseract.Output.DICT, config="--psm 6")

    lines = {}
    for i in range(len(data["text"])):
        txt = (data["text"][i] or "").strip()
        if len(txt) < 2 or data["conf"][i] < 30:
            continue
        key = (data["block_num"][i], data["par_num"][i], data["line_num"][i])
        cx = data["left"][i] + data["width"][i] / 2
        cy = data["top"][i] + data["height"][i] / 2
        if key not in lines:
            lines[key] = []
        lines[key].append((cx, cy))

    slopes = []
    for key, pts in lines.items():
        if len(pts) < 3:
            continue
        pts.sort(key=lambda p: p[0])
        xs = np.array([p[0] for p in pts])
        ys = np.array([p[1] for p in pts])
        if xs[-1] - xs[0] < w * 0.2:
            continue
        A = np.vstack([xs, np.ones(len(xs))]).T
        result = np.linalg.lstsq(A, ys, rcond=None)
        slope = result[0][0]
        angle_deg = math.degrees(math.atan(slope))
        slopes.append(angle_deg)

    if not slopes:
        print("No text lines detected")
        return

    median_slope = sorted(slopes)[len(slopes) // 2]
    mean_slope = sum(slopes) / len(slopes)
    print(f"Text lines found: {len(slopes)}")
    print(f"Median slope: {median_slope:.4f} deg")
    print(f"Mean slope:   {mean_slope:.4f} deg")
    print(f"Range: [{min(slopes):.4f}, {max(slopes):.4f}]")
    print()
    print("Individual line slopes:")
    for s in sorted(slopes):
        print(f"  {s:+.4f}")

    # Also test the 4 dewarp methods directly
    print("\n--- Dewarp method results on deskewed image ---")
    from cv_vocab_pipeline import (
        _detect_shear_angle, _detect_shear_by_projection,
        _detect_shear_by_hough, _detect_shear_by_text_lines,
    )
    for name, fn in [
        ("vertical_edge", _detect_shear_angle),
        ("projection", _detect_shear_by_projection),
        ("hough_lines", _detect_shear_by_hough),
        ("text_lines", _detect_shear_by_text_lines),
    ]:
        r = fn(img)
        print(f"  {name}: shear={r['shear_degrees']:.4f} conf={r['confidence']:.3f}")

    # The user says "right side needs to come down 3mm"
    # For a ~85mm wide image (1002px at ~300DPI), 3mm ~ 35px
    # shear angle = atan(35 / 1556) ~ 1.29 degrees
    # Let's check: what does the image look like if we apply 0.5, 1.0, 1.5 deg shear?
    print("\n--- Pixel shift at right edge for various shear angles ---")
    for deg in [0.5, 0.8, 1.0, 1.3, 1.5, 2.0]:
        shift_px = h * math.tan(math.radians(deg))
        shift_mm = shift_px / (w / 85.0)  # approximate mm
        print(f"  {deg:.1f} deg -> {shift_px:.0f}px shift -> ~{shift_mm:.1f}mm")

asyncio.run(main())