Add OCR naming and PNG-to-PDF export (modules 5-7, single-page only)

- ocr/: Tesseract-based vendor/date/total extraction. PSM 6 (single
  uniform text block) instead of the default fixes receipts where
  item-name/price columns were otherwise split into separate blocks and
  dropped. Vendor line picked by median (not max) word height within the
  top fraction of the crop, breaking ties by topmost line - max() was
  fooled by single descender/ascender glyphs (commas, parens) inflating
  one word's bounding box.
- naming/: merge OCR metadata into YYYY-MM-DD_vendor.pdf filenames,
  degrading gracefully to UNSORTED_<timestamp>.pdf; per-run dedup.
- pdf/: img2pdf-based multi-page-capable assembly (images_to_pdf).
- pipeline.run_export(): OCR + name + PDF each detected crop from a
  detect() report, writes pdf/ and export_summary.csv.
- New `paperpod export <video>` CLI command.
- Verified against synthetic Home Depot/Metro/Petro-Canada receipts:
  3/3 correct vendor, date, and total after tuning.

Known limitation (documented in README): no page-flip/multi-page
grouping yet (that's events/, still unbuilt) - every detected document
becomes its own single-page PDF.

paperpod/pipeline.py

@@ -10,6 +10,7 @@ from __future__ import annotations
 
 import csv
 import json
+from datetime import datetime, timedelta
 from pathlib import Path
 from typing import Any
 
@@ -18,6 +19,9 @@ import numpy as np
 
 from paperpod.capture.video import iter_frames, probe_video
 from paperpod.config import Config, config_to_dict
+from paperpod.naming.filename import build_name, dedupe_stem
+from paperpod.ocr.extract import run_ocr
+from paperpod.pdf.build import images_to_pdf
 from paperpod.vision.document import detect_document, warp_document
 from paperpod.vision.enhance import enhance_for_ocr
 from paperpod.vision.motion import Segment, find_segments, motion_score, prepare_gray
@@ -160,3 +164,83 @@ def run_detection(video_path: str | Path, cfg: Config, out_dir: str | Path) -> d
     with open(out_dir / "report.json", "w") as f:
         json.dump(report, f, indent=2)
     return report
+
+
+def run_export(report: dict[str, Any], cfg: Config, out_dir: str | Path) -> dict[str, Any]:
+    """OCR-name and PDF-export every detected crop from a detect() report.
+
+    NOTE: there is no page-grouping yet (module 3 / events/ is not built),
+    so every detected crop becomes its own single-page PDF, even if it was
+    physically one side of a multi-page stack. pod_id == window_id for now.
+
+    Writes:
+      pdf/<name>.pdf         one PDF per detected document
+      export_summary.csv     timestamp, pod_id, page_count, source_of_name,
+                              ocr_vendor, ocr_date, ocr_total, final_filename
+    Returns the summary rows (also embedded back for programmatic use).
+    """
+    out_dir = Path(out_dir)
+    pdf_dir = out_dir / "pdf"
+    pdf_dir.mkdir(parents=True, exist_ok=True)
+
+    video_path = Path(report["video"])
+    duration_s = report["video_meta"]["duration_s"]
+    try:
+        recording_start = datetime.fromtimestamp(video_path.stat().st_mtime) - timedelta(
+            seconds=duration_s
+        )
+    except FileNotFoundError:
+        recording_start = datetime.now() - timedelta(seconds=duration_s)
+
+    used_stems: set[str] = set()
+    rows: list[dict[str, Any]] = []
+
+    for window in report["stable_windows"]:
+        if not window.get("document_found"):
+            continue
+
+        crop_path = out_dir / window["crop_path"]
+        image = cv2.imread(str(crop_path))
+        if image is None:
+            continue
+
+        ocr = run_ocr(
+            image,
+            lang=cfg.ocr.lang,
+            vendor_top_fraction=cfg.ocr.vendor_top_fraction,
+            min_word_confidence=cfg.ocr.min_word_confidence,
+            psm=cfg.ocr.psm,
+        )
+        event_time = recording_start + timedelta(seconds=window["t_start"])
+        naming = build_name(ocr.date, ocr.vendor, event_time, cfg.naming.max_vendor_len)
+        stem = dedupe_stem(naming.stem, used_stems)
+
+        pdf_path = pdf_dir / f"{stem}.pdf"
+        images_to_pdf([crop_path], pdf_path, title=stem)
+
+        rows.append(
+            {
+                "timestamp": event_time.isoformat(timespec="seconds"),
+                "pod_id": window["window_id"],
+                "page_count": 1,
+                "source_of_name": naming.source,
+                "ocr_vendor": ocr.vendor or "",
+                "ocr_date": ocr.date or "",
+                "ocr_total": ocr.total or "",
+                "ocr_confidence": round(ocr.mean_confidence, 1),
+                "final_filename": pdf_path.name,
+                "pdf_path": str(pdf_path.relative_to(out_dir)),
+            }
+        )
+
+    with open(out_dir / "export_summary.csv", "w", newline="") as f:
+        fieldnames = [
+            "timestamp", "pod_id", "page_count", "source_of_name",
+            "ocr_vendor", "ocr_date", "ocr_total", "ocr_confidence",
+            "final_filename", "pdf_path",
+        ]
+        writer = csv.DictWriter(f, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(rows)
+
+    return {"rows": rows, "pdf_dir": str(pdf_dir)}