dd-l2-bangkok-multicrs-audit

Rerun

cd /work && python3 -c "
import geopandas as gpd
import fiona

# List layers in the GeoPackage
layers = fiona.list_layers('bangkok_contractor_delivery.gpkg')
print('Layers:', layers)
"

Traceback (most recent call last):
  File "<string>", line 6, in <module>
    layers = fiona.list_layers('bangkok_contractor_delivery.gpkg')
             ^^^^^^^^^^^^^^^^^
AttributeError: module 'fiona' has no attribute 'list_layers'. Did you mean: 'listlayers'?

cd /work && python3 -c "
import fiona
layers = fiona.listlayers('bangkok_contractor_delivery.gpkg')
print('Layers:', layers)
"

cd /work && python3 -c "
import geopandas as gpd
import fiona
import warnings
warnings.filterwarnings('ignore')

layers = fiona.listlayers('bangkok_contractor_delivery.gpkg')

for layer in layers:
    print(f'===== {layer} =====')
    gdf = gpd.read_file('bangkok_contractor_delivery.gpkg', layer=layer)
    print(f'CRS: {gdf.crs}')
    print(f'Geometry type: {gdf.geometry.geom_type.unique()}')
    print(f'Feature count: {len(gdf)}')
    print(f'Columns: {list(gdf.columns)}')
    print(f'Dtypes:\n{gdf.dtypes}')
    print(f'First few rows:')
    print(gdf.head(2).to_string())
    print()
    # Check text columns
    for col in gdf.select_dtypes(include='object').columns:
        if col == 'geometry':
            continue
        print(f'  Column {col}: unique sample values: {gdf[col].dropna().unique()[:5]}')
    print()
"

===== parcels =====
CRS: EPSG:24047
Geometry type: <ArrowStringArray>
['Polygon']
Length: 1, dtype: str
Feature count: 4000
Columns: ['id', 'name_th', 'owner_class', 'geometry']
Dtypes:
id                  str
name_th             str
owner_class         str
geometry       geometry
dtype: object
First few rows:
       id                                               name_th owner_class                                                                                                                            geometry
0  P00000     แปลงที่ดิน บางรัก     private    POLYGON ((657421.516 1509162.37, 657992.722 1509165.787, 657991.396 1509387.035, 657420.195 1509383.617, 657421.516 1509162.37))
1  P00001  แปลงที่ดิน ปทุมวัน       state  POLYGON ((658135.524 1509166.644, 658706.731 1509170.077, 658705.399 1509391.324, 658134.196 1509387.891, 658135.524 1509166.644))

  Column id: unique sample values: <ArrowStringArray>
['P00000', 'P00001', 'P00002', 'P00003', 'P00004']
Length: 5, dtype: str
  Column name_th: unique sample values: <ArrowStringArray>
[   'แปลงที่ดิน บางรัก',
 'แปลงที่ดิน ปทุมวัน',
       'แปลงที่ดิน วัฒนา',
 'แปลงที่ดิน คลองเตย',
    'แปลงที่ดิน ดินแดง']
Length: 5, dtype: str
  Column owner_class: unique sample values: <ArrowStringArray>
['private', 'state', 'religious']
Length: 3, dtype: str

===== roads =====
CRS: EPSG:32647
Geometry type: <ArrowStringArray>
['LineString']
Length: 1, dtype: str
Feature count: 5000
Columns: ['id', 'name', 'highway', 'geometry']
Dtypes:
id               str
name             str
highway          str
geometry    geometry
dtype: object
First few rows:
       id                               name    highway                                                     geometry
0  R00000  ถนนสุขุมวิท    primary  LINESTRING (656835.685 1509487.003, 657156.989 1509488.924)
1  R00001      ถนนพระราม 4  secondary   LINESTRING (657192.69 1509489.138, 657190.305 1509887.384)

  Column id: unique sample values: <ArrowStringArray>
['R00000', 'R00001', 'R00002', 'R00003', 'R00004']
Length: 5, dtype: str
  Column name: unique sample values: <ArrowStringArray>
[      'ถนนสุขุมวิท',
           'ถนนพระราม 4',
           'ถนนพระราม 9',
 'ถนนรัชดาภิเษก',
       'ถนนเพชรบุรี']
Length: 5, dtype: str
  Column highway: unique sample values: <ArrowStringArray>
['primary', 'secondary', 'tertiary', 'residential', 'service']
Length: 5, dtype: str

===== markets =====
CRS: EPSG:4326
Geometry type: <ArrowStringArray>
['Point']
Length: 1, dtype: str
Feature count: 1000
Columns: ['id', 'name_th', 'kind', 'geometry']
Dtypes:
id               str
name_th          str
kind             str
geometry    geometry
dtype: object
First few rows:
       id         name_th   kind                 geometry
0  M00000  ตลาดนัดจตุจักร  fresh  POINT (100.4533 13.655)
1  M00001      ตลาดอ.ต.ก.    wet  POINT (100.4599 13.655)

  Column id: unique sample values: <ArrowStringArray>
['M00000', 'M00001', 'M00002', 'M00003', 'M00004']
Length: 5, dtype: str
  Column name_th: unique sample values: <ArrowStringArray>
['ตลาดนัดจตุจักร', 'ตลาดอ.ต.ก.', 'ตลาดคลองเตย', 'ตลาดสะพานขาว', 'ตลาดบางรัก']
Length: 5, dtype: str
  Column kind: unique sample values: <ArrowStringArray>
['fresh', 'wet', 'night']
Length: 3, dtype: str

cd /work && python3 -c "
# Check if parcels name_th is mojibake
s = 'แปลงที่ดิน บางรัก'
# If these bytes are actually UTF-8 bytes stored as latin1, we can recover by:
# Take the text, encode as latin1 to get back the original bytes, then decode as UTF-8
recovered = s.encode('latin1').decode('utf-8')
print('Recovered:', repr(recovered))
print('Recovered text:', recovered)

# Check roads
s2 = 'ถนนสุขุมวิท'
recovered2 = s2.encode('latin1').decode('utf-8')
print('Roads recovered:', repr(recovered2))
print('Roads text:', recovered2)

# Check markets
s3 = 'ถนนเพชรบุรี'
recovered3 = s3.encode('latin1').decode('utf-8')
print('Market road name test recovered:', repr(recovered3))
"

Recovered: 'แปลงที่ดิน บางรัก'
Recovered text: แปลงที่ดิน บางรัก
Roads recovered: 'ถนนสุขุมวิท'
Roads text: ถนนสุขุมวิท
Market road name test recovered: 'ถนนเพชรบุรี'

cd /work && python3 -c "
import geopandas as gpd
import warnings
warnings.filterwarnings('ignore')

layers_info = []
layers = ['parcels', 'roads', 'markets']

for layer in layers:
    gdf = gpd.read_file('bangkok_contractor_delivery.gpkg', layer=layer)
    crs = gdf.crs
    # Format as EPSG:NNNN
    if crs is not None:
        epsg_code = crs.to_epsg()
        declared_crs = f'EPSG:{epsg_code}' if epsg_code else str(crs)
    else:
        declared_crs = 'None'
    
    geom_type = gdf.geometry.geom_type.iloc[0]
    feature_count = len(gdf)
    
    # Get sample coordinate from first feature
    geom = gdf.geometry.iloc[0]
    if geom.geom_type == 'Point':
        sample_x = geom.x
        sample_y = geom.y
    elif geom.geom_type == 'Polygon':
        # Get first point of exterior ring
        x, y = geom.exterior.coords[0]
        sample_x = x
        sample_y = y
    elif geom.geom_type == 'LineString':
        x, y = geom.coords[0]
        sample_x = x
        sample_y = y
    elif geom.geom_type == 'MultiPolygon':
        x, y = geom.geoms[0].exterior.coords[0]
        sample_x = x
        sample_y = y
    else:
        sample_x = None
        sample_y = None
    
    # Check encoding
    # Look at text columns for anomalies
    encoding_detected = 'utf-8'  # default
    for col in gdf.select_dtypes(include='object').columns:
        if col == 'geometry':
            continue
        for val in gdf[col].dropna().head(10):
            val_str = str(val)
            # Check if it looks like mojibake: characters like à, å, ç, é, etc.
            # If the string has characters in the latin1 range that could be UTF-8 bytes misinterpreted
            mojibake_chars = set('àáâãäåæçèéêëìíîïðñòóôõöøùúûüýþ')
            if any(c in mojibake_chars for c in val_str):
                encoding_detected = 'latin1-mojibake'
                break
        if encoding_detected == 'latin1-mojibake':
            break
    
    print(f'{layer}: CRS={declared_crs}, geom={geom_type}, count={feature_count}, x={sample_x}, y={sample_y}, encoding={encoding_detected}')
    layers_info.append([layer, declared_crs, geom_type, feature_count, sample_x, sample_y, encoding_detected])
"