fio-l1-vienna-shapefile-recovery

Rerun

import pandas as pd
import geopandas as gpd
import json

def main():
    # 1. Load column map
    # The CSV format looks like: " 1\ttruncated,original" 
    # Wait, looking at the 'Read' output:
    #      1	truncated,original
    #      2	KATASTRALG,KATASTRALGEMEINDE_NAME
    # It seems it's a tab-separated file or similar. Let's check with pandas.
    
    # Let's try reading it as a CSV with a specific delimiter if needed.
    # Looking at the content: '     1\ttruncated,original'
    # It seems to be whitespace/tab delimited for the first column, 
    # then comma separated for the rest.
    
    # Actually, let's just read it as a simple text file and parse it manually 
    # to be safe, or use read_csv with sep='\t' if it's tab-separated.
    
    mapping = {}
    with open('column_map.csv', 'r', encoding='utf-8') as f:
        lines = f.readlines()
        for line in lines:
            if ',' in line and '\t' in line:
                # Split by tab
                parts = line.strip().split('\t')
                if len(parts) == 2:
                    # parts[1] is "truncated,original"
                    cols = parts[1].split(',')
                    if len(cols) == 2:
                        truncated = cols[0].strip()
                        original = cols[1].strip()
                        mapping[truncated] = original

    print(f"Loaded mapping: {mapping}")

    # 2. Load shapefile
    # The shapefile might have encoding issues. 
    # Let's try reading it.
    gdf = gpd.read_file('parcels.shp')
    
    # 3. Rename columns
    # We only rename columns that are in our mapping.
    # We MUST NOT rename 'geometry'
    
    # Create a dictionary for renaming
    rename_dict = {old: new for old, new in mapping.items() if old in gdf.columns}
    print(f"Renaming columns: {rename_dict}")
    gdf = gdf.rename(columns=rename_dict)

    # 4. Ensure geometry is Polygon or MultiPolygon
    # GeoPandas usually handles this, but let's ensure we don't have points/lines
    # if the user specifically asked for Polygon/MultiPolygon.
    # However, for a parcel file, it's almost certainly polygons.
    # We can filter if necessary, but let's stick to the request.
    
    # 5. Save to GeoJSON
    # GeoJSON requires WGS84 (EPSG:4326) for web viewers usually.
    # Let's check the current CRS.
    print(f"Current CRS: {gdf.crs}")
    
    if gdf.crs is not None and gdf.crs.to_epsg() != 4326:
        print("Reprojecting to EPSG:4326...")
        gdf = gdf.to_crs(epsg=4326)
    
    # Save
    output_filename = 'parcels.geojson'
    gdf.to_file(output_filename, driver='GeoJSON')
    print(f"Successfully saved to {output_filename}")

if __name__ == "__main__":
    main()

import pandas as pd
import geopandas as gpd
import json

def main():
    # 1. Load column map
    # The file content is:
    #      1	truncated,original
    #      2	KATASTRALG,KATASTRALGEMEINDE_NAME
    # It seems the first part is an index, and the second part is a tab-separated pair
    # where the pair itself is "truncated,original"
    
    mapping = {}
    with open('column_map.csv', 'r', encoding='utf-8') as f:
        lines = f.readlines()
        for line in lines:
            line = line.strip()
            if not line or 'truncated,original' in line:
                continue
            
            # The line looks like "2\tKATASTRALG,KATASTRALGEMEINDE_NAME"
            # or "     2\tKATASTRALG,KATASTRALGEMEINDE_NAME"
            if '\t' in line:
                parts = line.split('\t')
                if len(parts) == 2:
                    # parts[1] should be "truncated,original"
                    col_pair = parts[1].split(',')
                    if len(col_pair) == 2:
                        truncated = col_pair[0].strip()
                        original = col_pair[1].strip()
                        mapping[truncated] = original

    print(f"Loaded mapping: {mapping}")

    if not mapping:
        print("Error: Mapping is empty. Check parser logic.")
        return

    # 2. Load shapefile
    gdf = gpd.read_file('parcels.shp')
    print(f"Original columns: {gdf.columns.tolist()}")
    
    # 3. Rename columns
    # We only rename columns that are in our mapping.
    rename_dict = {old: new for old, new in mapping.items() if old in gdf.columns}
    print(f"Renaming columns: {rename_dict}")
    gdf = gdf.rename(columns=rename_dict)

    # 4. Ensure geometry is Polygon or MultiPolygon
    # Filter out any non-polygonal geometries if they exist
    gdf = gdf[gdf.geometry.type.isin(['Polygon', 'MultiPolygon'])]

    # 5. Save to GeoJSON
    # Reproject to EPSG:4326 for web compatibility
    print(f"Current CRS: {gdf.crs}")
    if gdf.crs is not None and gdf.crs.to_epsg() != 4326:
        print("Reprojecting to EPSG:4326...")
        gdf = gdf.to_crs(epsg=4326)
    
    output_filename = 'parcels.geojson'
    # Note: to_file with driver='GeoJSON' handles encoding automatically (UTF-8)
    gdf.to_file(output_filename, driver='GeoJSON')
    print(f"Successfully saved to {output_filename}")
    print(f"Final columns: {gdf.columns.tolist()}")

if __name__ == "__main__":
    main()

import geopandas as gpd
import pandas as pd

def main():
    # The cat -A output showed that it is actually a standard comma-separated file.
    # The "1  truncated,original" line I saw earlier might have been an artifact of my reading/thinking
    # or how the file was displayed.
    # Looking at cat -A:
    # truncated,original$
    # KATASTRALG,KATASTRALGEMEINDE_NAME$
    # ...
    
    # It's just a CSV.
    mapping_df = pd.read_csv('column_map.csv')
    print("Mapping DF head:")
    print(mapping_df.head())
    
    # The columns are likely named 'truncated' and 'original' (or whatever the first line is)
    # Let's check columns.
    mapping_dict = dict(zip(mapping_df.iloc[:, 0], mapping_df.iloc[:, 1]))
    print(f"Generated mapping: {mapping_dict}")

    # 2. Load shapefile
    gdf = gpd.read_file('parcels.shp')
    
    # 3. Rename columns
    rename_dict = {old: new for old, new in mapping_dict.items() if old in gdf.columns}
    print(f"Renaming columns: {rename_dict}")
    gdf = gdf.rename(columns=rename_dict)

    # 4. Ensure geometry is Polygon or MultiPolygon
    gdf = gdf[gdf.geometry.type.isin(['Polygon', 'MultiPolygon'])]

    # 5. Save to GeoJSON
    # Reproject to EPSG:4326 for web compatibility
    print(f"Current CRS: {gdf.crs}")
    if gdf.crs is not None and gdf.crs.to_epsg() != 4326:
        print("Reprojecting to EPSG:4326...")
        gdf = gdf.to_crs(epsg=4326)
    
    output_filename = 'parcels.geojson'
    gdf.to_file(output_filename, driver='GeoJSON')
    print(f"Successfully saved to {output_filename}")
    print(f"Final columns: {gdf.columns.tolist()}")

if __name__ == "__main__":
    main()