@mytec: iter1.6 ready for testing

backend/app/services/buildings_service.py

@@ -1,3 +1,4 @@
+import re
 import httpx
 import asyncio
 from typing import List, Optional
@@ -34,6 +35,33 @@ class BuildingsService:
         self._memory_cache: dict[str, List[Building]] = {}
         self._max_cache_size = 50  # bbox regions
 
+    @staticmethod
+    def _safe_int(value) -> Optional[int]:
+        """Safely parse int from OSM tag (handles '1а', '2-3', '5+', etc.)"""
+        if not value:
+            return None
+        try:
+            return int(value)
+        except (ValueError, TypeError):
+            match = re.search(r'\d+', str(value))
+            if match:
+                return int(match.group())
+            return None
+
+    @staticmethod
+    def _safe_float(value) -> Optional[float]:
+        """Safely parse float from OSM tag (handles '10 m', '~12', '10m')"""
+        if not value:
+            return None
+        try:
+            cleaned = str(value).lower().replace('m', '').replace('~', '').strip()
+            return float(cleaned)
+        except (ValueError, TypeError):
+            match = re.search(r'[\d.]+', str(value))
+            if match:
+                return float(match.group())
+            return None
+
     def _bbox_key(self, min_lat: float, min_lon: float, max_lat: float, max_lon: float) -> str:
         """Generate cache key for bbox"""
         # Round to 0.01 degree (~1km) grid for cache efficiency
@@ -157,7 +185,7 @@ class BuildingsService:
                 id=element["id"],
                 geometry=geometry,
                 height=height,
-                levels=int(tags.get("building:levels", 0)) or None,
+                levels=self._safe_int(tags.get("building:levels")),
                 building_type=tags.get("building"),
                 material=material_str,
                 tags=tags
@@ -169,22 +197,15 @@ class BuildingsService:
         """Estimate building height from OSM tags"""
         # Explicit height tag
         if "height" in tags:
-            try:
-                h = tags["height"]
-                # Handle "10 m" or "10m" format
-                if isinstance(h, str):
-                    h = h.replace("m", "").replace(" ", "")
-                return float(h)
-            except (ValueError, TypeError):
-                pass
+            h = self._safe_float(tags["height"])
+            if h is not None and h > 0:
+                return h
 
         # Calculate from levels
         if "building:levels" in tags:
-            try:
-                levels = int(tags["building:levels"])
+            levels = self._safe_int(tags["building:levels"])
+            if levels is not None and levels > 0:
                 return levels * self.DEFAULT_LEVEL_HEIGHT
-            except (ValueError, TypeError):
-                pass
 
         # Default based on building type
         building_type = tags.get("building", "yes")