Bulk OCR + GPS push: process multiple GPS photos, match assets, push coordinates to DB with Leaflet map

server.py

@@ -1,5 +1,5 @@
 """EXIF + OCR test backend — validate that GPS survives upload pipeline."""
-import io, json, re, uuid
+import io, json, re, uuid, sqlite3
 from pathlib import Path
 
 from fastapi import FastAPI, File, Form, HTTPException, UploadFile
@@ -14,10 +14,20 @@ except ImportError:
 
 UPLOADS = Path(__file__).parent / "uploads"
 UPLOADS.mkdir(exist_ok=True)
+CANTEEN_DB = Path(__file__).parent.parent / "canteen-asset-tracker" / "assets.db"
 
 app = FastAPI(title="EXIF Test")
 
 
+def _get_canteen_db():
+    """Get a read/write connection to the canteen assets database."""
+    if not CANTEEN_DB.exists():
+        return None
+    conn = sqlite3.connect(str(CANTEEN_DB))
+    conn.row_factory = sqlite3.Row
+    return conn
+
+
 def _dms_to_decimal(dms, ref):
     """Convert EXIF DMS tuple to decimal degrees."""
     try:
@@ -39,10 +49,8 @@ def extract_exif(image_bytes: bytes) -> dict:
         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]
@@ -50,7 +58,6 @@ def extract_exif(image_bytes: bytes) -> dict:
         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")
@@ -87,7 +94,6 @@ def run_ocr(image_bytes: bytes) -> dict:
         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 {
@@ -100,13 +106,47 @@ def run_ocr(image_bytes: bytes) -> dict:
         tmp_path.unlink(missing_ok=True)
 
 
+def lookup_machine_id(machine_id: str) -> dict | None:
+    """Look up an asset by machine_id. Returns asset dict or None."""
+    conn = _get_canteen_db()
+    if not conn:
+        return None
+    try:
+        row = conn.execute(
+            "SELECT id, machine_id, name, category, status, address, building_name, "
+            "floor, room, latitude, longitude, make, model, description, photo_path "
+            "FROM assets WHERE machine_id = ?",
+            (machine_id.strip(),),
+        ).fetchone()
+        if row:
+            return {
+                "id": row["id"],
+                "machine_id": row["machine_id"],
+                "name": row["name"],
+                "category": row["category"],
+                "status": row["status"],
+                "address": row["address"],
+                "building_name": row["building_name"],
+                "floor": row["floor"],
+                "room": row["room"],
+                "latitude": row["latitude"],
+                "longitude": row["longitude"],
+                "make": row["make"],
+                "model": row["model"],
+                "description": row["description"],
+                "photo_path": row["photo_path"],
+            }
+    finally:
+        conn.close()
+    return None
+
+
 @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"
@@ -116,10 +156,11 @@ async def analyze_photo(file: UploadFile = File(...)):
     exif_result = extract_exif(contents)
     ocr_result = run_ocr(contents) if HAS_TESSERACT else {"available": False, "text": ""}
 
-    # Extract machine ID from OCR for auto-lookup
     machine_id = None
+    asset = None
     if ocr_result.get("match_5dash6"):
         machine_id = re.sub(r"\D", "", ocr_result["match_5dash6"])[-5:]
+        asset = lookup_machine_id(machine_id)
 
     return {
         "filename": file.filename,
@@ -129,57 +170,125 @@ async def analyze_photo(file: UploadFile = File(...)):
         "exif": exif_result,
         "ocr": ocr_result,
         "machine_id": machine_id,
+        "asset": asset,
     }
 
 
+@app.post("/api/bulk-process")
+async def bulk_process(files: list[UploadFile] = File(...)):
+    """Process multiple photos: OCR each, extract EXIF GPS, look up matching assets.
+
+    Returns a list of results, each with:
+      - filename, exif (gps), ocr match, matched asset (if found)
+      - needs_gps: true if asset exists AND has no coordinates AND photo has GPS
+    """
+    if not files:
+        return {"results": [], "summary": {"total": 0, "has_gps": 0, "matched": 0, "needs_gps": 0}}
+
+    results = []
+    summary = {"total": len(files), "has_gps": 0, "matched": 0, "needs_gps": 0}
+
+    for file in files:
+        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": ""}
+
+        has_gps = exif_result.get("gps") is not None
+        if has_gps:
+            summary["has_gps"] += 1
+
+        machine_id = None
+        asset = None
+        needs_gps = False
+
+        if ocr_result.get("match_5dash6"):
+            machine_id = re.sub(r"\D", "", ocr_result["match_5dash6"])[-5:]
+            asset = lookup_machine_id(machine_id)
+            if asset:
+                summary["matched"] += 1
+                # Check if asset needs GPS
+                if (asset["latitude"] is None or asset["longitude"] is None) and has_gps:
+                    needs_gps = True
+                    summary["needs_gps"] += 1
+
+        results.append({
+            "filename": file.filename,
+            "saved_as": fname,
+            "file_size_kb": round(file_size / 1024, 1),
+            "exif": exif_result,
+            "ocr": ocr_result,
+            "machine_id": machine_id,
+            "asset": asset,
+            "needs_gps": needs_gps,
+        })
+
+    return {"results": results, "summary": summary}
+
+
 @app.get("/api/lookup")
 async def lookup_asset(machine_id: str = ""):
     """Look up an asset by machine_id in the canteen assets database."""
     if not machine_id or not machine_id.strip():
         return {"found": False, "reason": "No machine_id provided"}
 
-    import sqlite3
-    from pathlib import Path as _Path
+    asset = lookup_machine_id(machine_id.strip())
+    if asset:
+        return {"found": True, "asset": asset}
+    return {"found": False, "reason": f"No asset with machine_id '{machine_id}'"}
 
-    db_path = _Path(__file__).parent.parent / "canteen-asset-tracker" / "assets.db"
-    if not db_path.exists():
-        return {"found": False, "reason": f"Database not found at {db_path}"}
+
+@app.post("/api/push-gps")
+async def push_gps(request: dict):
+    """Update an asset's GPS coordinates from photo EXIF data.
+
+    Body: {"asset_id": 123, "latitude": 40.7417, "longitude": -73.9292}
+    Only updates assets that currently have NULL lat/lng.
+    """
+    asset_id = request.get("asset_id")
+    latitude = request.get("latitude")
+    longitude = request.get("longitude")
+
+    if not asset_id or latitude is None or longitude is None:
+        raise HTTPException(400, "asset_id, latitude, and longitude are required")
+
+    conn = _get_canteen_db()
+    if not conn:
+        raise HTTPException(500, "Database not available")
 
     try:
-        conn = sqlite3.connect(str(db_path))
-        conn.row_factory = sqlite3.Row
+        # Only update if currently NULL
         row = conn.execute(
-            "SELECT id, machine_id, name, category, status, address, building_name, "
-            "floor, room, latitude, longitude, make, model, description, photo_path "
-            "FROM assets WHERE machine_id = ?",
-            (machine_id.strip(),),
+            "SELECT latitude, longitude FROM assets WHERE id = ?", (int(asset_id),)
         ).fetchone()
-        conn.close()
+        if not row:
+            conn.close()
+            raise HTTPException(404, f"Asset {asset_id} not found")
+        if row["latitude"] is not None and row["longitude"] is not None:
+            conn.close()
+            return {"updated": False, "reason": "Asset already has GPS coordinates", "asset_id": asset_id}
 
-        if row:
-            return {
-                "found": True,
-                "asset": {
-                    "id": row["id"],
-                    "machine_id": row["machine_id"],
-                    "name": row["name"],
-                    "category": row["category"],
-                    "status": row["status"],
-                    "address": row["address"],
-                    "building_name": row["building_name"],
-                    "floor": row["floor"],
-                    "room": row["room"],
-                    "latitude": row["latitude"],
-                    "longitude": row["longitude"],
-                    "make": row["make"],
-                    "model": row["model"],
-                    "description": row["description"],
-                    "photo_path": row["photo_path"],
-                },
-            }
-        return {"found": False, "reason": f"No asset with machine_id '{machine_id}'"}
+        conn.execute(
+            "UPDATE assets SET latitude = ?, longitude = ?, updated_at = datetime('now') WHERE id = ?",
+            (float(latitude), float(longitude), int(asset_id)),
+        )
+        conn.commit()
+        conn.close()
+        return {"updated": True, "asset_id": asset_id, "latitude": float(latitude), "longitude": float(longitude)}
     except Exception as e:
-        return {"found": False, "reason": str(e)}
+        try:
+            conn.close()
+        except Exception:
+            pass
+        raise HTTPException(500, str(e))
 
 
 @app.get("/api/uploads")

static/index.html

@@ -5,6 +5,8 @@
 <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no, viewport-fit=cover">
 <title>EXIF Scanner — Find GPS Photos</title>
 <script src="https://cdn.jsdelivr.net/npm/exifr@7/dist/lite.umd.js"></script>
+<link rel="stylesheet" href="https://unpkg.com/leaflet@1.9.4/dist/leaflet.css" />
+<script src="https://unpkg.com/leaflet@1.9.4/dist/leaflet.js"></script>
 <style>
   :root {
     --bg: #0f172a; --card: #1e293b; --card2: #334155;
@@ -184,6 +186,35 @@
     max-height: 120px; overflow-y: auto; color: var(--text2);
     margin-top: 6px;
   }
+
+  /* Bulk results */
+  #mapContainer { height: 250px; border-radius: var(--radius-sm); margin-bottom: 10px; display: none; }
+  .bulk-card {
+    background: var(--card); border-radius: var(--radius-sm); padding: 10px;
+    margin-bottom: 8px; display: flex; align-items: center; gap: 10px;
+    border-left: 3px solid var(--border);
+  }
+  .bulk-card.gps-ready { border-left-color: var(--green); }
+  .bulk-card .bulk-thumb { width: 48px; height: 48px; border-radius: 6px; object-fit: cover; flex-shrink: 0; }
+  .bulk-card .bulk-info { flex: 1; min-width: 0; }
+  .bulk-card .bulk-name { font-size: 13px; font-weight: 600; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
+  .bulk-card .bulk-meta { font-size: 11px; color: var(--text2); }
+  .bulk-card .bulk-action { flex-shrink: 0; }
+  .btn-push {
+    font-size: 11px; font-weight: 700; padding: 6px 12px; border-radius: 14px;
+    border: none; cursor: pointer; -webkit-tap-highlight-color: transparent;
+    background: var(--green); color: #000;
+  }
+  .btn-push:disabled { opacity: 0.4; }
+  .btn-push.done { background: var(--card2); color: var(--text3); }
+
+  .match-badge {
+    display: inline-block; font-size: 10px; padding: 2px 8px; border-radius: 10px; font-weight: 600;
+  }
+  .match-badge.matched { background: var(--green); color: #000; }
+  .match-badge.no-match { background: var(--border); color: var(--text2); }
+  .match-badge.no-gps { background: var(--amber); color: #000; }
+  .match-badge.has-gps { background: var(--card2); color: var(--text2); }
 </style>
 </head>
 <body>
@@ -226,12 +257,26 @@
   </div>
 </div>
 
-<!-- Server results for uploaded photo -->
+<!-- Server results for single upload -->
 <div class="section" id="serverSection" style="display:none;">
   <div class="detail-section">🖥️ Server Results <span class="badge badge-info">PIL + OCR</span></div>
   <div id="serverResults"></div>
 </div>
 
+<!-- Bulk process button -->
+<button class="btn btn-primary" id="bulkBtn" style="display:none;margin-top:12px;" onclick="startBulkProcess()">
+  🔍 Bulk Process GPS Photos
+</button>
+
+<!-- Bulk results -->
+<div class="section" id="bulkSection" style="display:none;">
+  <div class="detail-section">📊 Bulk Results
+    <span class="match-badge" id="bulkSummary" style="margin-left:auto;"></span>
+  </div>
+  <div id="mapContainer"></div>
+  <div id="bulkResults"></div>
+</div>
+
 <div class="btn-row" style="margin-top:8px;">
   <button class="btn btn-outline btn-sm" id="clearBtn" style="display:none;" onclick="resetAll()">🔄 Clear All & Re-select</button>
 </div>
@@ -309,6 +354,8 @@ function updateSummary() {
   document.getElementById('sumGps').textContent = gps;
   document.getElementById('sumNoGps').textContent = nogps;
   document.getElementById('summary').style.display = 'block';
+  // Show bulk button if we have GPS photos
+  document.getElementById('bulkBtn').style.display = gps > 0 ? 'block' : 'none';
 }
 
 function setFilter(f) {
@@ -480,10 +527,210 @@ async function lookupAsset(machineId) {
   }
 }
 
+let bulkMap = null;
+let bulkData = [];
+
+async function startBulkProcess() {
+  const gpsPhotos = allPhotos.filter(p => p.hasGps);
+  if (!gpsPhotos.length) return;
+
+  const btn = document.getElementById('bulkBtn');
+  btn.disabled = true;
+  btn.innerHTML = '<span class="spinner"></span> Processing ' + gpsPhotos.length + ' photos...';
+
+  // Build FormData with all GPS photos
+  const fd = new FormData();
+  gpsPhotos.forEach(p => fd.append('files', p.file, p.file.name || 'photo.jpg'));
+
+  try {
+    const resp = await fetch('/api/bulk-process', { method: 'POST', body: fd });
+    const data = await resp.json();
+
+    // Merge thumbnails back into results
+    bulkData = data.results.map((r, i) => ({
+      ...r,
+      thumb: gpsPhotos[i]?.thumb || null,
+      clientLat: gpsPhotos[i]?.lat || null,
+      clientLng: gpsPhotos[i]?.lng || null,
+    }));
+
+    renderBulkResults(data.summary);
+  } catch (e) {
+    document.getElementById('bulkResults').innerHTML =
+      '<div class="empty">❌ Bulk process failed: ' + esc(e.message) + '</div>';
+  } finally {
+    btn.disabled = false;
+    btn.textContent = '🔍 Bulk Process GPS Photos';
+  }
+}
+
+function renderBulkResults(summary) {
+  const section = document.getElementById('bulkSection');
+  section.style.display = 'block';
+
+  // Summary badge
+  document.getElementById('bulkSummary').textContent =
+    summary.matched + ' matched, ' + summary.needs_gps + ' need GPS';
+  document.getElementById('bulkSummary').className =
+    'match-badge ' + (summary.matched > 0 ? 'matched' : 'no-match');
+
+  // Init map
+  const mapDiv = document.getElementById('mapContainer');
+  mapDiv.style.display = 'block';
+  if (bulkMap) bulkMap.remove();
+  bulkMap = L.map('mapContainer').setView([28.35, -81.55], 8);
+  L.tileLayer('https://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png', {
+    attribution: '© OSM', maxZoom: 19
+  }).addTo(bulkMap);
+
+  const markers = [];
+  let html = '';
+
+  bulkData.forEach((item, i) => {
+    const asset = item.asset;
+    const hasGps = item.exif?.gps;
+    const gpsLat = hasGps ? item.exif.gps.lat : null;
+    const gpsLng = hasGps ? item.exif.gps.lng : null;
+
+    // Map marker for every GPS photo
+    if (gpsLat && gpsLng) {
+      const marker = L.marker([gpsLat, gpsLng])
+        .addTo(bulkMap)
+        .bindPopup(
+          (asset ? esc(asset.name) : 'Unknown machine') +
+          '<br>📸 ' + esc(item.filename || 'photo') +
+          '<br>📍 ' + gpsLat.toFixed(5) + ', ' + gpsLng.toFixed(5)
+        );
+      markers.push([gpsLat, gpsLng]);
+    }
+
+    // Asset marker if it already has GPS in DB
+    if (asset && asset.latitude && asset.longitude) {
+      L.marker([asset.latitude, asset.longitude], {
+        icon: L.divIcon({
+          className: 'cat-pin-icon',
+          html: '<div style="width:22px;height:22px;border-radius:50%;background:#3b82f6;' +
+                'display:flex;align-items:center;justify-content:center;font-size:11px;' +
+                'box-shadow:0 2px 5px rgba(0,0,0,0.5);border:2px solid #fff;">🏠</div>',
+          iconSize: [24, 24], iconAnchor: [12, 12]
+        })
+      }).addTo(bulkMap)
+        .bindPopup('<b>' + esc(asset.name) + '</b><br>Existing location');
+    }
+
+    // Card
+    const isGpsReady = item.needs_gps;
+    html += '<div class="bulk-card' + (isGpsReady ? ' gps-ready' : '') + '">';
+
+    if (item.thumb) {
+      html += '<img class="bulk-thumb" src="' + item.thumb + '" alt="">';
+    }
+
+    html += '<div class="bulk-info">';
+
+    if (asset) {
+      html += '<div class="bulk-name">' + esc(asset.name) + '</div>';
+      html += '<div class="bulk-meta">';
+      html += '<span class="match-badge matched">🆔 ' + esc(asset.machine_id) + '</span> ';
+      html += '<span class="match-badge ' + (isGpsReady ? 'no-gps' : 'has-gps') + '">';
+      if (asset.latitude && asset.longitude) {
+        html += '📍 Has GPS in DB';
+      } else if (isGpsReady) {
+        html += '📍 Photo GPS: ' + gpsLat.toFixed(4) + ', ' + gpsLng.toFixed(4);
+      } else {
+        html += '⚠️ No photo GPS';
+      }
+      html += '</span>';
+      html += '</div>';
+    } else if (item.machine_id) {
+      html += '<div class="bulk-name">Machine #' + esc(item.machine_id) + '</div>';
+      html += '<div class="bulk-meta"><span class="match-badge no-match">No DB match</span></div>';
+    } else {
+      html += '<div class="bulk-name">' + esc(item.filename || 'Photo') + '</div>';
+      html += '<div class="bulk-meta"><span class="match-badge no-match">No OCR match</span></div>';
+    }
+
+    html += '</div>'; // bulk-info
+
+    // Push button
+    html += '<div class="bulk-action">';
+    if (isGpsReady) {
+      html += '<button class="btn-push" id="pushBtn' + i + '" onclick="pushGpsToAsset(' + i + ')">📤 Push GPS</button>';
+    } else if (asset && asset.latitude && asset.longitude) {
+      html += '<button class="btn-push done">✓ In DB</button>';
+    }
+    html += '</div>';
+
+    html += '</div>'; // bulk-card
+  });
+
+  document.getElementById('bulkResults').innerHTML = html;
+
+  // Fit map to markers
+  if (markers.length) {
+    const bounds = L.latLngBounds(markers);
+    bulkMap.fitBounds(bounds, { padding: [30, 30], maxZoom: 15 });
+  }
+
+  // Invalidate map size after display
+  setTimeout(() => { if (bulkMap) bulkMap.invalidateSize(); }, 200);
+
+  section.scrollIntoView({ behavior: 'smooth' });
+}
+
+async function pushGpsToAsset(idx) {
+  const item = bulkData[idx];
+  if (!item || !item.asset || !item.needs_gps) return;
+
+  const btn = document.getElementById('pushBtn' + idx);
+  btn.disabled = true;
+  btn.textContent = '⏳ Pushing...';
+
+  const gps = item.exif.gps;
+  try {
+    const resp = await fetch('/api/push-gps', {
+      method: 'POST',
+      headers: { 'Content-Type': 'application/json' },
+      body: JSON.stringify({
+        asset_id: item.asset.id,
+        latitude: gps.lat,
+        longitude: gps.lng,
+      }),
+    });
+    const data = await resp.json();
+    if (data.updated) {
+      btn.className = 'btn-push done';
+      btn.textContent = '✓ Pushed!';
+      // Add marker to map for pushed location
+      if (bulkMap) {
+        L.marker([gps.lat, gps.lng], {
+          icon: L.divIcon({
+            className: 'cat-pin-icon',
+            html: '<div style="width:22px;height:22px;border-radius:50%;background:#22c55e;' +
+                  'display:flex;align-items:center;justify-content:center;font-size:11px;' +
+                  'box-shadow:0 2px 5px rgba(0,0,0,0.5);border:2px solid #fff;">✓</div>',
+            iconSize: [24, 24], iconAnchor: [12, 12]
+          })
+        }).addTo(bulkMap)
+          .bindPopup('<b>' + esc(item.asset.name) + '</b><br>📍 Pushed: ' + gps.lat.toFixed(5) + ', ' + gps.lng.toFixed(5))
+          .openPopup();
+      }
+    } else {
+      btn.textContent = data.reason || 'Failed';
+      btn.style.background = 'var(--red)';
+    }
+  } catch (e) {
+    btn.textContent = 'Error';
+    btn.style.background = 'var(--red)';
+  }
+}
+
 function resetAll() {
   allPhotos = [];
   selectedIdx = -1;
   currentFilter = 'all';
+  bulkData = [];
+  if (bulkMap) { bulkMap.remove(); bulkMap = null; }
   document.getElementById('fileInput').value = '';
   document.getElementById('uploadArea').style.display = '';
   document.getElementById('gallery').innerHTML = '';
@@ -491,6 +738,9 @@ function resetAll() {
   document.getElementById('filterBar').style.display = 'none';
   document.getElementById('detail').style.display = 'none';
   document.getElementById('serverSection').style.display = 'none';
+  document.getElementById('bulkSection').style.display = 'none';
+  document.getElementById('bulkBtn').style.display = 'none';
+  document.getElementById('mapContainer').style.display = 'none';
   document.getElementById('clearBtn').style.display = 'none';
 }