MAINT: Renamed sav -> spss

src/caoscrawler/__init__.py

 from . import converters
-from .conv_impl.sav import SAVConverter
+from .conv_impl.spss import SPSSConverter
 from .crawl import Crawler, SecurityMode
 from .version import CfoodRequiredVersionError, get_caoscrawler_version
 
 __version__ = get_caoscrawler_version()
 
 # Convenience members #########################################################
-converters.SAVConverter = SAVConverter
+# mypy: disable-error-code="attr-defined"
+converters.SPSSConverter = SPSSConverter

src/caoscrawler/cfood-schema.yml

@@ -31,6 +31,7 @@ cfood:
           - JSONFile
           - CSVTableConverter
           - XLSXTableConverter
+          - SPSSFile
           - H5File
           - H5Dataset
           - H5Group

src/caoscrawler/conv_impl/sav.py → src/caoscrawler/conv_impl/spss.py

@@ -18,20 +18,29 @@
 
 """Converter for SAV files (stored by SPSS)."""
 
-# import pyreadstat  # Maybe us this if we need more metadata
 import pandas as pd
+import pyreadstat
 
 from .. import converters
-from ..stores import GeneralStore, RecordStore
-from ..structure_elements import (BooleanElement, DictElement, Directory, File,
-                                  FloatElement, IntegerElement, JSONFile,
-                                  ListElement, NoneElement, StructureElement,
-                                  TextElement)
+from ..stores import GeneralStore
+from ..structure_elements import (File, StructureElement)
 
 
-class SAVConverter(converters.TableConverter):
+class SPSSConverter(converters.TableConverter):
     """Converter for SAV files (stored by SPSS)."""
 
-    def create_children(self, values: GeneralStore, element: StructureElement):
+    # def __init__(self, *args, **kwargs):
+    #     super().__init__(*args, **kwargs)
+    #     from IPython import embed
+    #     embed()
+
+    def create_children(self, values: GeneralStore, element: StructureElement) -> list:
+        assert isinstance(element, File)
         df = pd.io.spss.read_spss(element.path)
+
+        # if element.path.endswith(".sav"):
+        #     sav_df, meta = pyreadstat.read_sav(element.path, metadataonly=True)
+        # from IPython import embed
+        # embed()
+
         return self._children_from_dataframe(df)

src/caoscrawler/default_converters.yml

@@ -81,6 +81,10 @@ CSVTableConverter:
   converter: CSVTableConverter
   package: caoscrawler.converters
 
+SPSSFile:
+  converter: SPSSConverter
+  package: caoscrawler.converters
+
 XLSXTableConverter:
   converter: XLSXTableConverter
   package: caoscrawler.converters

unittests/test_sav_converter.py → unittests/test_spss_converter.py

@@ -16,7 +16,7 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program. If not, see <https://www.gnu.org/licenses/>.
 
-"""Testing converter for SAV files."""
+"""Testing converter for SPSS files."""
 
 import datetime
 import importlib
@@ -28,7 +28,7 @@ import pytest
 
 from caoscrawler.converters import (
     ConverterValidationError,
-    SAVConverter,
+    SPSSConverter,
 )
 from caoscrawler.structure_elements import (BooleanElement, DictElement,
                                             Directory, File, FloatElement,
@@ -52,8 +52,8 @@ def converter_registry():
     return converter_registry
 
 
-def test_sav_converter(converter_registry):
-    converter = SAVConverter({
+def test_spss_converter(converter_registry):
+    converter = SPSSConverter({
         "match": ("sample.sav")
     },
         "ThisConverterNameIsIrrelevant", converter_registry