EXIF scanner: multi-photo gallery with GPS detection

2026-05-25 00:32:16 -04:00
commit b079c9bf8f
8 changed files with 598 additions and 0 deletions
@@ -0,0 +1,144 @@
+"""EXIF + OCR test backend — validate that GPS survives upload pipeline."""
+import io, json, re, uuid
+from pathlib import Path
+
+from fastapi import FastAPI, File, Form, HTTPException, UploadFile
+from fastapi.staticfiles import StaticFiles
+from PIL import Image as PILImage
+
+try:
+    import pytesseract
+    HAS_TESSERACT = True
+except ImportError:
+    HAS_TESSERACT = False
+
+UPLOADS = Path(__file__).parent / "uploads"
+UPLOADS.mkdir(exist_ok=True)
+
+app = FastAPI(title="EXIF Test")
+
+
+def _dms_to_decimal(dms, ref):
+    """Convert EXIF DMS tuple to decimal degrees."""
+    try:
+        deg, minutes, sec = float(dms[0]), float(dms[1]), float(dms[2])
+        decimal = deg + minutes / 60.0 + sec / 3600.0
+        if ref in ("S", "W"):
+            decimal = -decimal
+        return round(decimal, 7)
+    except Exception:
+        return None
+
+
+def extract_exif(image_bytes: bytes) -> dict:
+    """Pull all useful EXIF fields + GPS from raw image bytes."""
+    result = {"has_exif": False, "tags": {}, "gps": None}
+    try:
+        img = PILImage.open(io.BytesIO(image_bytes))
+        exif = img.getexif()
+        if not exif:
+            return result
+
+        # Standard EXIF tags
+        for tag_id, value in exif.items():
+            tag_name = PILImage.ExifTags.TAGS.get(tag_id, f"0x{tag_id:04x}")
+            # Skip binary/thumbnail blobs
+            if tag_name in ("MakerNote", "UserComment", "PrintImageMatching"):
+                continue
+            result["tags"][tag_name] = str(value)[:300]
+
+        if result["tags"]:
+            result["has_exif"] = True
+
+        # GPS IFD
+        gps_ifd = exif.get_ifd(0x8825)
+        if gps_ifd:
+            lat_ref = gps_ifd.get(1, "N")
+            lat_dms = gps_ifd.get(2)
+            lng_ref = gps_ifd.get(3, "E")
+            lng_dms = gps_ifd.get(4)
+
+            if lat_dms and lng_dms:
+                lat = _dms_to_decimal(lat_dms, lat_ref)
+                lng = _dms_to_decimal(lng_dms, lng_ref)
+                if lat is not None and lng is not None:
+                    result["gps"] = {
+                        "lat": lat,
+                        "lng": lng,
+                        "lat_ref": str(lat_ref),
+                        "lng_ref": str(lng_ref),
+                        "raw_lat_dms": [float(v) for v in lat_dms],
+                        "raw_lng_dms": [float(v) for v in lng_dms],
+                    }
+    except Exception as e:
+        result["error"] = str(e)
+
+    return result
+
+
+def run_ocr(image_bytes: bytes) -> dict:
+    """Run Tesseract OCR on the image."""
+    if not HAS_TESSERACT:
+        return {"available": False, "text": "", "error": "pytesseract not installed"}
+
+    tmp_path = UPLOADS / f"ocr_{uuid.uuid4().hex}.jpg"
+    tmp_path.write_bytes(image_bytes)
+    try:
+        img = PILImage.open(tmp_path)
+        img_gray = img.convert("L")
+        text = pytesseract.image_to_string(img_gray, config="--psm 6")
+        # Extract machine ID patterns
+        match_5dash = re.search(r"(\d{5})[-\s]*(\d{6,})", text)
+        match_5plus = re.search(r"(\d{5,})", text)
+        return {
+            "available": True,
+            "raw_text": text.strip()[:500],
+            "match_5dash6": match_5dash.group(0) if match_5dash else None,
+            "match_5plus": match_5plus.group(0) if match_5plus else None,
+        }
+    finally:
+        tmp_path.unlink(missing_ok=True)
+
+
+@app.post("/api/analyze")
+async def analyze_photo(file: UploadFile = File(...)):
+    """Upload a photo, get back EXIF + OCR results."""
+    contents = await file.read()
+    file_size = len(contents)
+
+    # Save
+    ext = Path(file.filename or "photo.jpg").suffix.lower()
+    if ext not in {".jpg", ".jpeg", ".png", ".webp", ".bmp", ".tiff", ".tif", ".dng"}:
+        ext = ".jpg"
+    fname = f"{uuid.uuid4().hex}{ext}"
+    (UPLOADS / fname).write_bytes(contents)
+
+    exif_result = extract_exif(contents)
+    ocr_result = run_ocr(contents) if HAS_TESSERACT else {"available": False, "text": ""}
+
+    return {
+        "filename": file.filename,
+        "saved_as": fname,
+        "file_size": file_size,
+        "file_size_kb": round(file_size / 1024, 1),
+        "exif": exif_result,
+        "ocr": ocr_result,
+    }
+
+
+@app.get("/api/uploads")
+async def list_uploads():
+    """List previously uploaded files."""
+    files = sorted(UPLOADS.glob("*"), key=lambda p: p.stat().st_mtime, reverse=True)
+    return [
+        {"name": f.name, "size_kb": round(f.stat().st_size / 1024, 1)}
+        for f in files[:20]
+    ]
+
+
+# Mount static LAST
+app.mount("/", StaticFiles(directory="static", html=True), name="static")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8903)