add output datasets

actes-princiers/conf/base/catalog.yml

@@ -4,12 +4,12 @@ bourbon:
   type: actesdataset.XMLDataSetCollection
   housename: bourbon
   folderpath: data/01_raw/houses/bourbon
+  outputfolderpath: data/02_intermediate/houses/bourbon/xml 
 
-# FIXME change the path to data/02_intermediate/houses/bourbon/xml 
 bourbon_content:
   type: actesdataset.XMLDataSetCollection
   housename: bourbon
-  folderpath: data/02_intermediate/houses/bourbon
+  folderpath: data/02_intermediate/houses/bourbon/xml
 
 #bourbon_json:
 #  type: actesdataset.XMLDataSetCollection

actes-princiers/src/actes_princiers/pipelines/xml_processing/nodes.py

@@ -7,7 +7,7 @@ from actesdataset import EtreeXMLDataSet
 logger = logging.getLogger(__name__)
 
 
-def parse_xml_collection(datasets: Dict[str, EtreeXMLDataSet], param: str) -> Dict[str, EtreeXMLDataSet]:
+def parse_xml_collection(datasets: Dict[str, EtreeXMLDataSet]) -> Dict[str, EtreeXMLDataSet]:
     "node function entry point, performs batch processing"
     output_datasets = dict()
     for dataset_filenamestem, dataset in datasets.items():
@@ -18,6 +18,7 @@ def parse_xml_collection(datasets: Dict[str, EtreeXMLDataSet], param: str) -> Di
         logger.info(f"dataset {descr} loaded")
         output_source_doc = dataset.transform() 
         # set dataset's output filepath
+#        output_filepath = _outputfolderpath
         output_filepath = dataset.filepath.replace("01_raw", "02_intermediate")
         output_xmldataset = EtreeXMLDataSet(output_filepath)
         # let's create subfolders now, if they don't exist

actes-princiers/src/actes_princiers/pipelines/xml_processing/pipeline.py

@@ -8,19 +8,19 @@ def create_pipeline(**kwargs) -> Pipeline:
         [
             node(
                 func=parse_xml_collection,
-                inputs=["bourbon", "params:xsltstylesheet"],
+                inputs=["bourbon"],
                 outputs="bourbon_content",
                 name="bourbon_ds_collection",
             ),
             node(
                 func=parse_xml_collection,
-                inputs=["berry", "params:xsltstylesheet"],
+                inputs=["berry"],
                 outputs="berry_content",
                 name="berry_ds_collection",
             ),
             node(
                 func=parse_xml_collection,
-                inputs=["anjou", "params:xsltstylesheet"],
+                inputs=["anjou"],
                 outputs="anjou_content",
                 name="anjou_ds_collection",
             ),

actes-princiers/src/actesdataset.py

@@ -1,6 +1,6 @@
 import logging
 import json
-from typing import Dict, Any
+from typing import Dict, Any, Optional
 from pathlib import Path
 
 from lxml import etree
@@ -121,9 +121,11 @@ class XMLDataSetCollection(AbstractDataSet):
     """
     def __init__(self, 
         housename: str,
-        folderpath: str) -> None:
+        folderpath: str,
+        outputfolderpath: Optional[str]=None) -> None:
         self._housename = housename
         self._folderpath = Path(folderpath)
+        self._outputfolderpath = outputfolderpath
             
     def _load(self) -> dict[str, EtreeXMLDataSet]:
         "kedro's API loader method"