Normalize RasterSourceDataSource param names between python and SQL

Signed-off-by: Jason T. Brown <[email protected]>

Author: vpipkt

datasource/src/main/scala/org/locationtech/rasterframes/datasource/raster/RasterSourceDataSource.scala

@@ -44,12 +44,12 @@ object RasterSourceDataSource {
   final val SHORT_NAME = "raster"
   final val PATH_PARAM = "path"
   final val PATHS_PARAM = "paths"
-  final val BAND_INDEXES_PARAM = "bandIndexes"
-  final val TILE_DIMS_PARAM = "tileDimensions"
-  final val CATALOG_TABLE_PARAM = "catalogTable"
-  final val CATALOG_TABLE_COLS_PARAM = "catalogColumns"
-  final val CATALOG_CSV_PARAM = "catalogCSV"
-  final val LAZY_TILES_PARAM = "lazyTiles"
+  final val BAND_INDEXES_PARAM = "band_indexes"
+  final val TILE_DIMS_PARAM = "tile_dimensions"
+  final val CATALOG_TABLE_PARAM = "catalog_table"
+  final val CATALOG_TABLE_COLS_PARAM = "catalog_col_names"
+  final val CATALOG_CSV_PARAM = "catalog_csv"
+  final val LAZY_TILES_PARAM = "lazy_tiles"
 
   final val DEFAULT_COLUMN_NAME = PROJECTED_RASTER_COLUMN.columnName
 

pyrasterframes/src/main/python/docs/languages.pymd

@@ -97,9 +97,9 @@ sql("""
 CREATE OR REPLACE TEMPORARY VIEW red_nir_tiles_monthly_2017
 USING raster
 OPTIONS (
-    catalogTable='red_nir_monthly_2017',
-    catalogColumns='red,nir',
-    tileDimensions='256,256'
+    catalog_table='red_nir_monthly_2017',
+    catalog_col_names='red,nir',
+    tile_dimensions='256,256'
     )
 """)
 ```

pyrasterframes/src/main/python/pyrasterframes/__init__.py

@@ -153,9 +153,9 @@ def temp_name():
         band_indexes = [0]
 
     options.update({
-        "bandIndexes": to_csv(band_indexes),
-        "tileDimensions": to_csv(tile_dimensions),
-        "lazyTiles": lazy_tiles
+        "band_indexes": to_csv(band_indexes),
+        "tile_dimensions": to_csv(tile_dimensions),
+        "lazy_tiles": lazy_tiles
     })
 
     # Parse the `source` argument
@@ -166,11 +166,11 @@ def temp_name():
             catalog = None
             options.update(dict(paths='\n'.join([str(i) for i in source])))  # pass in "uri1\nuri2\nuri3\n..."
         if all([isinstance(i, list) for i in source]):
-            # list of lists; we will rely on pandas to
-            #   - coerce all data to str (possibly using objects' __str__ or __repr__\
+            # list of lists; we will rely on pandas to:
+            #   - coerce all data to str (possibly using objects' __str__ or __repr__)
             #   - ensure data is not "ragged": all sublists are same len
             path = None
-            catalog_col_names = ['proj_raster_{}'.format(i) for i in range(len(source[0]))]
+            catalog_col_names = ['proj_raster_{}'.format(i) for i in range(len(source[0]))]  # assign these names
             catalog = PdDataFrame(source,
                                   columns=catalog_col_names,
                                   dtype=str,
@@ -194,8 +194,8 @@ def temp_name():
 
         if isinstance(catalog, str):
             options.update({
-                "catalogCSV": catalog,
-                "catalogColumns": to_csv(catalog_col_names)
+                "catalog_csv": catalog,
+                "catalog_col_names": to_csv(catalog_col_names)
             })
         elif isinstance(catalog, DataFrame):
             # check catalog_col_names
@@ -205,8 +205,8 @@ def temp_name():
             tmp_name = temp_name()
             catalog.createOrReplaceTempView(tmp_name)
             options.update({
-                "catalogTable": tmp_name,
-                "catalogColumns": to_csv(catalog_col_names)
+                "catalog_table": tmp_name,
+                "catalog_col_names": to_csv(catalog_col_names)
             })
         elif isinstance(catalog, PdDataFrame):
             # check catalog_col_names
@@ -220,8 +220,8 @@ def temp_name():
             spark_catalog = session.createDataFrame(catalog)
             spark_catalog.createOrReplaceTempView(tmp_name)
             options.update({
-                "catalogTable": tmp_name,
-                "catalogColumns": to_csv(catalog_col_names)
+                "catalog_table": tmp_name,
+                "catalog_col_names": to_csv(catalog_col_names)
             })
 
     return df_reader \