#!/usr/bin/env python3 """Generate EXTREMELY hard OCR documents — embedded images + heavy degradation: 1. extreme_receipt_photo — thermal receipt PHOTOGRAPHED on a desk: perspective warp, uneven lighting, shadow, crinkle lines, faded thermal band, printed logo. 2. extreme_po_collage — image-heavy purchase order: product THUMBNAIL IMAGES in table rows, QR code, barcode, rotated APPROVED stamp over the table, signature scribble, misaligned columns. 3. extreme_contract_fax — dense two-column contract received BY FAX: low contrast, salt-and-pepper noise, skew, scanline streaks, punch-hole shadows, handwritten blue margin note, red RECEIVED stamp. Each writes .png + .gt.json + .txt (sidecar reference text, drawn from the SAME strings as the image so CER/WER is fair). All are tagged skip_eval so the main eval harness is unchanged; the OCR quality benchmark picks them up. """ from __future__ import annotations import json import math import random from pathlib import Path import numpy as np from PIL import Image, ImageDraw, ImageFilter, ImageFont ROOT = Path(__file__).resolve().parent.parent OUT = ROOT / "backend" / "evals" / "datasets" rng = random.Random(42) def font(sz, bold=False, mono=False): paths = (["/System/Library/Fonts/Supplemental/Courier New Bold.ttf", "/System/Library/Fonts/Supplemental/Courier New.ttf"] if mono else []) + [ "/System/Library/Fonts/Supplemental/Arial Bold.ttf" if bold else "/System/Library/Fonts/Supplemental/Arial.ttf", "/System/Library/Fonts/Helvetica.ttc", "/Library/Fonts/Arial.ttf", ] for p in paths: try: return ImageFont.truetype(p, sz) except Exception: continue return ImageFont.load_default() def _find_coeffs(dst, src): """Perspective coefficients so that src corners land on dst corners.""" A, B = [], [] for (x, y), (u, v) in zip(dst, src): A.append([x, y, 1, 0, 0, 0, -u * x, -u * y]) A.append([0, 0, 0, x, y, 1, -v * x, -v * y]) B.extend([u, v]) res, *_ = np.linalg.lstsq(np.array(A, float), np.array(B, float), rcond=None) return res.tolist() def stamp(text, color, angle, size=(360, 120), fsz=34): im = Image.new("RGBA", size, (0, 0, 0, 0)) d = ImageDraw.Draw(im) d.rounded_rectangle([4, 4, size[0] - 4, size[1] - 4], radius=16, outline=color + (190,), width=5) f = font(fsz, bold=True) tw = d.textlength(text, font=f) d.text(((size[0] - tw) / 2, (size[1] - fsz) / 2 - 6), text, font=f, fill=color + (190,)) return im.rotate(angle, expand=True, resample=Image.BICUBIC) def signature(w=220, h=60, color=(25, 30, 120)): im = Image.new("RGBA", (w, h), (0, 0, 0, 0)) d = ImageDraw.Draw(im) pts = [] for i in range(60): t = i / 59 x = 8 + t * (w - 16) y = h / 2 + math.sin(t * 14 + 1.3) * (h / 3) * (1 - 0.5 * t) + rng.uniform(-2, 2) pts.append((x, y)) d.line(pts, fill=color + (230,), width=3, joint="curve") return im # ── 1. extreme_receipt_photo ────────────────────────────────────────────────── R_LINES = [ "BREW & BEAN COFFEE Co.", "412 Harbor Lane, Portland OR", "Receipt #R-88341 Reg 02", "Date: 2026-06-02 14:37", "Currency: USD", "--------------------------------", "Flat White 2 x 4.75 9.50", "Butter Croissant 3 x 3.25 9.75", "Cold Brew Growler 1 x 14.00 14.00", "Loyalty discount -2.50", "--------------------------------", "Subtotal 30.75", "Tax 8.8% 2.71", "TOTAL 33.46", "Payment: VISA ****4421", "--------------------------------", "Thank you! brewandbean.example", ] R_GT = { "doc_type": "receipt", "merchant": "BREW & BEAN COFFEE Co.", "date": "2026-06-02", "currency": "USD", "subtotal": 30.75, "tax_amount": 2.71, "total": 33.46, "payment_method": "VISA ****4421", "line_items": [ {"description": "Flat White", "quantity": 2, "unit_price": 4.75, "line_total": 9.50}, {"description": "Butter Croissant", "quantity": 3, "unit_price": 3.25, "line_total": 9.75}, {"description": "Cold Brew Growler", "quantity": 1, "unit_price": 14.00, "line_total": 14.00}, ], "_meta": {"doc_type": "receipt", "channel": "photo", "difficulty": "extreme", "skip_eval": True}, } def gen_receipt(): pw, ph = 560, 1010 paper = Image.new("RGBA", (pw, ph), (250, 248, 242, 255)) d = ImageDraw.Draw(paper) # printed logo: filled coffee-cup glyph in a ring cx, cy = pw // 2, 64 d.ellipse([cx - 44, cy - 44, cx + 44, cy + 44], outline=(60, 50, 45), width=4) d.rounded_rectangle([cx - 20, cy - 14, cx + 14, cy + 22], radius=5, fill=(60, 50, 45)) d.arc([cx + 8, cy - 8, cx + 30, cy + 14], 270, 90, fill=(60, 50, 45), width=4) fm = font(24, mono=True) y = 130 for ln in R_LINES: w = d.textlength(ln, font=fm) x = (pw - w) / 2 if not ln.startswith(("Flat", "Butter", "Cold", "Loyal", "Subt", "Tax", "TOTAL", "Paym")) else 28 d.text((x, y), ln, font=fm, fill=(40, 38, 36)) y += 36 d.line([(0, ph - 14), (pw, ph - 6)], fill=(250, 248, 242, 0)) # keep bottom edge clean # crinkle lines for _ in range(7): x0 = rng.randint(0, pw) d.line([(x0, 0), (x0 + rng.randint(-90, 90), ph)], fill=(208, 204, 196, 90), width=2) # faded thermal band (blend toward white) arr = np.asarray(paper).astype(np.float32) y0, y1 = 430, 560 fade = arr[y0:y1, :, :3] arr[y0:y1, :, :3] = fade + (255 - fade) * 0.55 paper = Image.fromarray(arr.astype(np.uint8)) # desk background with wood grain + vignette W, H = 1000, 1400 desk = Image.new("RGB", (W, H), (96, 74, 54)) dd = ImageDraw.Draw(desk) for yy in range(0, H, 7): dd.line([(0, yy), (W, yy + rng.randint(-3, 3))], fill=(96 + rng.randint(-10, 8), 74 + rng.randint(-8, 6), 54 + rng.randint(-6, 6)), width=3) # shadow under receipt sh = Image.new("RGBA", (W, H), (0, 0, 0, 0)) ImageDraw.Draw(sh).polygon([(232, 152), (798, 198), (742, 1292), (172, 1232)], fill=(0, 0, 0, 110)) desk.paste(Image.new("RGB", (W, H), 0), (0, 0), sh.filter(ImageFilter.GaussianBlur(18))) # perspective-warp the receipt onto the desk dst = [(248, 138), (786, 186), (730, 1276), (188, 1218)] coeffs = _find_coeffs(dst, [(0, 0), (pw, 0), (pw, ph), (0, ph)]) warped = paper.transform((W, H), Image.PERSPECTIVE, coeffs, Image.BICUBIC) desk.paste(warped, (0, 0), warped) # uneven lighting: bright top-left, dim bottom-right + vignette a = np.asarray(desk).astype(np.float32) yy, xx = np.mgrid[0:H, 0:W] light = 1.12 - 0.32 * ((xx / W) * 0.6 + (yy / H) * 0.4) r2 = ((xx - W / 2) / (W / 2)) ** 2 + ((yy - H / 2) / (H / 2)) ** 2 light *= 1 - 0.18 * np.clip(r2 - 0.45, 0, 1) a *= light[..., None] a += np.random.default_rng(7).normal(0, 4.5, a.shape) img = Image.fromarray(np.clip(a, 0, 255).astype(np.uint8)).filter(ImageFilter.GaussianBlur(0.6)) img.save(OUT / "extreme_receipt_photo.png") (OUT / "extreme_receipt_photo.txt").write_text("\n".join(R_LINES) + "\n") (OUT / "extreme_receipt_photo.gt.json").write_text(json.dumps(R_GT, indent=2)) # ── 2. extreme_po_collage ───────────────────────────────────────────────────── PO_ITEMS = [ ("SHELF UNIT S-200 heavy gauge", 24, 189.00, 4536.00), ("LED STRIP 2m retail white", 60, 22.40, 1344.00), ("ENDCAP DISPLAY birch finish", 12, 310.00, 3720.00), ] PO_GT = { "doc_type": "purchase_order", "order_number": "PO-77RX-3309", "order_date": "2026-05-21", "delivery_date": "2026-06-15", "vendor_name": "Nordic Fixture Works AB", "buyer_name": "Aperture Retail Group", "ship_to": "DC-7, 4420 Logistics Pkwy, Columbus OH", "currency": "USD", "payment_terms": "Net 45", "subtotal": 9600.00, "tax_amount": 792.00, "total": 10392.00, "line_items": [{"description": d_, "quantity": q, "unit_price": u, "line_total": t} for d_, q, u, t in PO_ITEMS], "_meta": {"doc_type": "purchase_order", "channel": "scanned", "difficulty": "extreme", "skip_eval": True}, } def _thumb(kind): im = Image.new("RGB", (76, 76), (235, 238, 242)) d = ImageDraw.Draw(im) if kind == 0: # shelf unit for i in range(4): d.rectangle([10, 12 + i * 15, 66, 18 + i * 15], fill=(120, 128, 140)) d.line([(12, 12), (12, 66)], fill=(80, 86, 96), width=3) d.line([(64, 12), (64, 66)], fill=(80, 86, 96), width=3) elif kind == 1: # LED strip d.rounded_rectangle([8, 30, 68, 46], radius=8, fill=(60, 64, 70)) for x in range(14, 66, 9): d.ellipse([x, 34, x + 6, 42], fill=(255, 240, 160)) else: # endcap display d.polygon([(14, 64), (26, 14), (50, 14), (62, 64)], fill=(196, 164, 120)) d.rectangle([20, 40, 56, 46], fill=(160, 128, 88)) d.rectangle([24, 26, 52, 32], fill=(160, 128, 88)) d.rectangle([0, 0, 75, 75], outline=(150, 150, 150)) return im def _qr(d, x, y, n=21, cell=5): g = random.Random(9) for r in range(n): for c in range(n): if g.random() < 0.45: d.rectangle([x + c * cell, y + r * cell, x + c * cell + cell - 1, y + r * cell + cell - 1], fill=0) for fx, fy in [(0, 0), (n - 7, 0), (0, n - 7)]: # finder squares d.rectangle([x + fx * cell, y + fy * cell, x + (fx + 7) * cell, y + (fy + 7) * cell], outline=0, width=3) d.rectangle([x + (fx + 2) * cell, y + (fy + 2) * cell, x + (fx + 5) * cell, y + (fy + 5) * cell], fill=0) def gen_po(): W, H = 1240, 1600 im = Image.new("RGB", (W, H), (252, 252, 250)) d = ImageDraw.Draw(im) h1, h2, h3, body, small = font(40, True), font(22, True), font(18, True), font(19), font(15) # header: drawn logo + vendor (left), meta box (right), QR top-right corner d.rectangle([40, 40, 120, 120], fill=(30, 90, 160)) d.polygon([(52, 108), (80, 52), (108, 108)], fill=(252, 252, 250)) d.text((136, 48), "Nordic Fixture Works AB", font=h2, fill=(20, 20, 30)) d.text((136, 80), "Industrigatan 14, Malmo SE · VAT SE5566778899", font=small, fill=(90, 90, 100)) d.text((40, 150), "PURCHASE ORDER", font=h1, fill=(30, 90, 160)) _qr(d, 1060, 40) meta = [("PO Number:", "PO-77RX-3309"), ("Order Date:", "2026-05-21"), ("Delivery Date:", "2026-06-15"), ("Payment Terms:", "Net 45"), ("Currency:", "USD")] d.rounded_rectangle([720, 150, 1200, 320], radius=10, outline=(30, 90, 160), width=2) for i, (k, v) in enumerate(meta): d.text((740, 165 + i * 30), k, font=h3, fill=(90, 90, 100)) d.text((920, 165 + i * 30), v, font=body, fill=(20, 20, 30)) d.text((40, 230), "Buyer: Aperture Retail Group", font=body, fill=(20, 20, 30)) d.text((40, 260), "Ship To: DC-7, 4420 Logistics Pkwy, Columbus OH", font=body, fill=(20, 20, 30)) # table with thumbnails + deliberately misaligned columns d.rectangle([40, 360, 1200, 404], fill=(30, 90, 160)) for x, t in [(56, "IMG"), (160, "DESCRIPTION"), (700, "QTY"), (840, "UNIT USD"), (1040, "AMOUNT")]: d.text((x, 370), t, font=h3, fill=(255, 255, 255)) y = 420 for i, (desc, qty, unit, tot) in enumerate(PO_ITEMS): off = [-14, 22, 6][i] # column misalignment per row im.paste(_thumb(i), (52, y)) d.text((160 + off, y + 24), desc, font=body, fill=(25, 25, 30)) d.text((706 + off // 2, y + 24), str(qty), font=body, fill=(25, 25, 30)) d.text((846 - off, y + 24), f"{unit:,.2f}", font=body, fill=(25, 25, 30)) d.text((1042 + off, y + 24), f"{tot:,.2f}", font=body, fill=(25, 25, 30)) d.line([(40, y + 88), (1200, y + 88)], fill=(210, 210, 215)) y += 96 # totals (right) + barcode (left) + signature d.text((840, y + 24), "Subtotal:", font=h3, fill=(90, 90, 100)); d.text((1042, y + 24), "9,600.00", font=body, fill=(20, 20, 30)) d.text((840, y + 58), "Tax 8.25%:", font=h3, fill=(90, 90, 100)); d.text((1042, y + 58), "792.00", font=body, fill=(20, 20, 30)) d.rectangle([820, y + 92, 1200, y + 134], fill=(240, 244, 250)) d.text((840, y + 100), "TOTAL:", font=h2, fill=(30, 90, 160)); d.text((1042, y + 100), "10,392.00 USD", font=h2, fill=(30, 90, 160)) bx = 40 g = random.Random(5) for _ in range(60): wbar = g.choice((2, 2, 3, 5)) d.rectangle([bx, y + 40, bx + wbar, y + 110], fill=0) bx += wbar + g.choice((2, 3)) d.text((40, y + 116), "*PO77RX3309*", font=small, fill=(60, 60, 60)) sig = signature() im.paste(sig, (760, H - 220), sig) d.line([(740, H - 160), (1010, H - 160)], fill=(60, 60, 60), width=2) d.text((740, H - 150), "Authorized — K. Lindqvist, Procurement", font=small, fill=(60, 60, 60)) # green APPROVED stamp overlapping the table st = stamp("APPROVED · OPS DESK", (20, 130, 60), 12) im.paste(st, (430, 560), st) # mild scan noise + tiny skew a = np.asarray(im).astype(np.float32) + np.random.default_rng(3).normal(0, 5, (H, W, 3)) im = Image.fromarray(np.clip(a, 0, 255).astype(np.uint8)).rotate(-0.7, expand=False, fillcolor=(252, 252, 250)) im.save(OUT / "extreme_po_collage.png") txt = ["PURCHASE ORDER", "Nordic Fixture Works AB", "Industrigatan 14, Malmo SE", "PO Number: PO-77RX-3309", "Order Date: 2026-05-21", "Delivery Date: 2026-06-15", "Payment Terms: Net 45", "Currency: USD", "Buyer: Aperture Retail Group", "Ship To: DC-7, 4420 Logistics Pkwy, Columbus OH", "IMG DESCRIPTION QTY UNIT USD AMOUNT"] + [ f"{desc} {q} {u:,.2f} {t:,.2f}" for desc, q, u, t in PO_ITEMS] + [ "Subtotal: 9,600.00", "Tax 8.25%: 792.00", "TOTAL: 10,392.00 USD", "*PO77RX3309*", "APPROVED · OPS DESK", "Authorized — K. Lindqvist, Procurement"] (OUT / "extreme_po_collage.txt").write_text("\n".join(txt) + "\n") (OUT / "extreme_po_collage.gt.json").write_text(json.dumps(PO_GT, indent=2)) # ── 3. extreme_contract_fax ─────────────────────────────────────────────────── C_GT = { "doc_type": "contract", "contract_number": "MSA-2026-0481", "title": "Master Services Agreement - Store Fit-Out Program", "party_a": "Aperture Retail Group", "party_b": "Halcyon Build Partners LLC", "effective_date": "2026-03-01", "expiration_date": "2029-02-28", "contract_value": 1250000.00, "currency": "USD", "governing_law": "State of Ohio", "auto_renew": False, "termination_notice_days": 60, "_meta": {"doc_type": "contract", "channel": "fax", "difficulty": "extreme", "skip_eval": True}, } C_HEAD = [ "MASTER SERVICES AGREEMENT - STORE FIT-OUT PROGRAM", "Contract No: MSA-2026-0481", "Party A: Aperture Retail Group Party B: Halcyon Build Partners LLC", "Effective Date: 2026-03-01 Expiration Date: 2029-02-28", "Total Contract Value: USD 1,250,000.00 Governing Law: State of Ohio", "Auto-Renewal: NO Termination Notice: 60 days written notice", ] C_BODY = [ "1. SCOPE. Contractor shall furnish all labor, materials, supervision and", "equipment required for the fit-out of retail premises identified in each", "Statement of Work executed under this Agreement.", "2. TERM. This Agreement commences on the Effective Date and continues", "until the Expiration Date unless terminated earlier per Section 9.", "3. COMPENSATION. Client shall pay Contractor fees not to exceed the", "Total Contract Value, payable per approved milestone invoices Net 30.", "4. CHANGE ORDERS. No variation is binding unless documented in a", "written change order signed by both parties' authorized representatives.", "5. WARRANTIES. Contractor warrants workmanship free of defects for", "twenty-four (24) months following practical completion of each site.", "6. INSURANCE. Contractor shall maintain commercial general liability", "coverage of not less than USD 5,000,000 per occurrence.", "7. CONFIDENTIALITY. Each party shall protect Confidential Information", "with no less than reasonable care and use it solely for this Agreement.", "8. LIABILITY. Neither party is liable for indirect or consequential", "damages; aggregate liability is capped at the Total Contract Value.", "9. TERMINATION. Either party may terminate for convenience upon sixty", "(60) days written notice, or immediately for uncured material breach.", "10. GOVERNING LAW. This Agreement is governed by the laws of the", "State of Ohio, excluding its conflict of law provisions.", ] def gen_contract(): W, H = 1240, 1600 im = Image.new("RGB", (W, H), (255, 255, 255)) d = ImageDraw.Draw(im) fh, fb, fs = font(26, True), font(17), font(14) d.text((30, 18), "FAX TX 06/12/2026 14:22 FROM HALCYON BUILD +1 614 555 0188 P.01/07", font=fs, fill=(60, 60, 60)) d.line([(30, 44), (1210, 44)], fill=(60, 60, 60), width=2) tw = d.textlength(C_HEAD[0], font=fh) d.text(((W - tw) / 2, 70), C_HEAD[0], font=fh, fill=(15, 15, 15)) y = 130 for ln in C_HEAD[1:]: d.text((80, y), ln, font=fb, fill=(20, 20, 20)) y += 30 d.line([(60, y + 8), (1180, y + 8)], fill=(120, 120, 120), width=2) # dense two-column body half = (len(C_BODY) + 1) // 2 for col, lines in enumerate((C_BODY[:half], C_BODY[half:])): x = 70 + col * 590 yy = y + 34 for ln in lines: d.text((x, yy), ln, font=fs, fill=(25, 25, 25)) yy += 24 for extra in range(14): # filler legalese to densify d.text((x, yy), f"{'WHEREAS the parties acknowledge the recitals set forth herein;'[: 58 - (extra % 3) * 4]}", font=fs, fill=(45, 45, 45)) yy += 24 # signature block sy = H - 300 for col, (name, role) in enumerate([("M. Okafor — Aperture Retail Group", "Chief Procurement Officer"), ("D. Reyes — Halcyon Build Partners LLC", "Managing Partner")]): x = 90 + col * 600 sig = signature(color=(20, 20, 20)) im.paste(sig, (x, sy), sig) d.line([(x, sy + 70), (x + 420, sy + 70)], fill=(40, 40, 40), width=2) d.text((x, sy + 80), name, font=fs, fill=(30, 30, 30)) d.text((x, sy + 102), role, font=fs, fill=(90, 90, 90)) # handwritten blue margin note + red stamp note = Image.new("RGBA", (430, 60), (0, 0, 0, 0)) ImageDraw.Draw(note).text((0, 8), "legal OK -> route to CFO (June 5)", font=font(24), fill=(28, 40, 160, 220)) note = note.rotate(-3, expand=True, resample=Image.BICUBIC) im.paste(note, (700, 360), note) st = stamp("RECEIVED JUN 05 2026", (180, 30, 30), -14, size=(420, 110), fsz=30) im.paste(st, (90, 430), st) # fax degradation: low contrast, salt & pepper, scanline streaks, skew, punch holes g = im.convert("L") a = np.asarray(g).astype(np.float32) a = 255 - (255 - a) * 0.62 # washed-out toner nz = np.random.default_rng(11) a += nz.normal(0, 9, a.shape) pepper = nz.random(a.shape) a[pepper < 0.004] = 30 # pepper a[pepper > 0.997] = 245 # salt for yy in range(0, H, 90): # scanline streaks a[yy:yy + 2, :] = np.clip(a[yy:yy + 2, :] * 1.25, 0, 255) img = Image.fromarray(np.clip(a, 0, 255).astype(np.uint8)).rotate(1.3, expand=False, fillcolor=235) d2 = ImageDraw.Draw(img) for hy in (H // 4, 3 * H // 4): # punch-hole shadows d2.ellipse([18, hy - 22, 62, hy + 22], fill=246, outline=140, width=3) img.convert("RGB").save(OUT / "extreme_contract_fax.png") (OUT / "extreme_contract_fax.txt").write_text("\n".join(C_HEAD + C_BODY) + "\n") (OUT / "extreme_contract_fax.gt.json").write_text(json.dumps(C_GT, indent=2)) if __name__ == "__main__": OUT.mkdir(parents=True, exist_ok=True) gen_receipt() gen_po() gen_contract() for sid in ("extreme_receipt_photo", "extreme_po_collage", "extreme_contract_fax"): print(f" wrote {OUT / sid}.png (+ .gt.json + .txt)")