Update threaded script, try to reduce multipolygons in geojson

shp-to-geojson.py

@@ -0,0 +1,95 @@
+import geopandas as gpd
+from shapely.geometry import LineString, MultiLineString, Polygon, MultiPolygon
+import pandas as pd
+
+df = gpd.read_file('original data/Sumter/RoadCenterlines_041125.shp.zip') #, crs=2237 NAD83 / Florida West (ftUS)
+df = df.to_crs(4326) # Convert to WGS 84
+
+def convert_to_linestrings(geom):
+    """Convert any geometry to a list of LineStrings"""
+    linestrings = []
+    
+    if geom is None or geom.is_empty:
+        return []
+    
+    # If it's already a LineString, just return it
+    if isinstance(geom, LineString):
+        linestrings.append(geom)
+    
+    # If it's a MultiLineString, extract all LineStrings
+    elif isinstance(geom, MultiLineString):
+        for line in geom.geoms:
+            linestrings.append(line)
+    
+    # If it's a Polygon, convert boundary to LineString(s)
+    elif isinstance(geom, Polygon):
+        # Exterior boundary
+        if not geom.exterior.is_empty:
+            linestrings.append(LineString(geom.exterior.coords))
+        # Interior boundaries (holes)
+        for interior in geom.interiors:
+            if not interior.is_empty:
+                linestrings.append(LineString(interior.coords))
+    
+    # If it's a MultiPolygon, process each polygon
+    elif isinstance(geom, MultiPolygon):
+        for poly in geom.geoms:
+            # Exterior boundary
+            if not poly.exterior.is_empty:
+                linestrings.append(LineString(poly.exterior.coords))
+            # Interior boundaries (holes)
+            for interior in poly.interiors:
+                if not interior.is_empty:
+                    linestrings.append(LineString(interior.coords))
+    
+    return linestrings
+
+def explode_linestring(linestring):
+    """Convert a LineString into individual segments"""
+    if linestring is None or linestring.is_empty:
+        return []
+    
+    coords = list(linestring.coords)
+    segments = []
+    
+    for i in range(len(coords) - 1):
+        segment = LineString([coords[i], coords[i + 1]])
+        segments.append(segment)
+    
+    return segments
+
+# Convert all geometries to LineStrings first
+df['linestrings'] = df.geometry.apply(convert_to_linestrings)
+
+# Explode to get one row per LineString
+df_exploded = df.explode('linestrings')
+
+# Filter out rows with empty linestrings
+df_exploded = df_exploded[df_exploded['linestrings'].notna()]
+df_exploded = df_exploded[~df_exploded['linestrings'].apply(lambda x: x.is_empty if x is not None else True)]
+
+# Now explode each LineString into segments
+df_exploded['segments'] = df_exploded['linestrings'].apply(explode_linestring)
+
+# Explode segments
+df_final = df_exploded.explode('segments')
+
+# Filter out empty segments
+df_final = df_final[df_final['segments'].notna()]
+df_final = df_final[~df_final['segments'].apply(lambda x: x.is_empty if x is not None else True)]
+
+# Create final GeoDataFrame with segments as geometry
+dfline = gpd.GeoDataFrame(
+    data=df_final.drop(['geometry', 'linestrings', 'segments'], axis=1), 
+    geometry=df_final['segments'],
+    crs=df.crs
+)
+
+# Reset index
+dfline = dfline.reset_index(drop=True)
+
+# Save to GeoJSON
+dfline.to_file('original data/Sumter/RoadCenterlines_041125.geojson', driver='GeoJSON')
+
+print(f"Converted {len(df)} original features to {len(dfline)} line segments")
+print(f"Geometry types in output: {dfline.geometry.geom_type.value_counts()}")

threaded.py

@@ -32,6 +32,13 @@ qgisfunctions = importlib.import_module("qgis-functions")
 # Suppress warnings for cleaner output
 warnings.filterwarnings('ignore')
 
+import re
+def titlecase(s):
+    return re.sub(
+        r"[A-Za-z]+('[A-Za-z]+)?",
+        lambda word: word.group(0).capitalize(),
+        s)
+
 class RoadComparator:
     def __init__(self, tolerance_feet: float = 50.0, min_gap_length_feet: float = 100.0, 
                  n_jobs: int = None, chunk_size: int = 1000):
@@ -308,11 +315,9 @@ class RoadComparator:
                             'surface': 'asphalt'
                         }
 
-                        print("Added: "+properties['name'])
-
                         for key, value in original_properties.items():
                             if key == 'NAME':
-                                properties['name'] = qgisfunctions.formatstreet(str(value)).title() if value is not None else None
+                                properties['name'] = titlecase(qgisfunctions.formatstreet(value,None,None)) if value is not None else None
                             elif key == 'SpeedLimit':
                                 properties['maxspeed'] = f"{value} mph" if value is not None else None
                             elif key == 'RoadClass':
@@ -333,6 +338,7 @@ class RoadComparator:
                         })
                         
             except Exception as e:
+                print(e)
                 continue  # Skip problematic geometries
         
         return added_roads