abstractmethod

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

@@ -4,8 +4,9 @@ from typing import Dict
 
 from kedro.framework.session import KedroSession
 
-from actesdataset import EtreeXMLDataSet, BsXMLDataSet
+from actesdataset import EtreeXMLDataSet, BsXMLDataSet, JSONDataSet
-from actesdataset import XMLDataSetCollection, JSONDataSetCollection
+from actesdataset import (XMLDataSetCollection, JSONDataSetCollection)
+#                         FullJSONDataSetCollection)
 
 logger = logging.getLogger(__name__)
 
@@ -61,4 +62,15 @@ def parse_json_collection(datasetcol: JSONDataSetCollection) -> Dict[str, BsXMLD
         output_datasets[dataset_filenamestem] = output_xmldataset
     return output_datasets
 
-#def add_xmlcontent_tojson(jsondoc: JSONDataSetCollection, xmlcontent: XMLDataSetCollection) -> 
+#def add_xmlcontent_tojson(jsondoc: JSONDataSetCollection, xmlcontent: XMLDataSetCollection) -> Dict[str, JSONDataSet]:
+
+#    logger.info("9999999999999999999999" + str(xmlcontent.datasets.keys()))
+#    json_datasets = jsondoc.datasets
+##    xmlcontent._load()
+#    logger.info(str(xmlcontent))
+#    xmlcontent = xmlcontent.datasets
+#    for dataset_filenamestem, dataset in json_datasets.items():
+#        document = dataset._load()
+#        document['xmlcontent'] = xmlcontent[dataset_filenamestem].source_doc
+#    return json_datasets
+#    

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

@@ -1,7 +1,8 @@
 
 from kedro.pipeline import Pipeline, node, pipeline
 
-from .nodes import parse_xml_collection, parse_json_collection
+from .nodes import (parse_xml_collection, parse_json_collection)
+#                   add_xmlcontent_tojson)
 
 
 def create_pipeline(**kwargs) -> Pipeline:
@@ -21,7 +22,7 @@ def create_pipeline(**kwargs) -> Pipeline:
             ),
 #            node(
 #                func=add_xmlcontent_tojson,
-#                inputs=["bourbon_jsonoutput", "bourbon_xmlcontent"],
+#                inputs=["bourbon_json", "bourbon_xmlcontent"],
 #                outputs="bourbon_fulljson",
 #                name="bourbon_fulljson_ds_collection",
 #            ),

actes-princiers/src/actesdataset.py

@@ -2,6 +2,8 @@ import logging
 import json
 from typing import Dict, Any
 from pathlib import Path
+from abc import ABC, abstractmethod
+
 
 from lxml import etree
 from bs4 import BeautifulSoup
@@ -25,7 +27,7 @@ def _xslt(xsltstylesheet):
 
 xslt_transformer = _xslt(xlststylesheet)
 
-class XMLDataSet:
+class XMLDataSet(ABC):
     "Abstract base class for an XML dataset loader"
         
     def __init__(self, filepath: str) -> None:
@@ -40,6 +42,12 @@ class XMLDataSet:
         "kedro's API-like repr()"
         return dict(filepath=self._filepath)
 
+    @abstractmethod
+    def _load(self):
+        pass
+
+    def _save(self, data:str) -> None:
+        pass
 
 class EtreeXMLDataSet(XMLDataSet):
     "XMLDataSet loader with lxml.etree (lxml.etree._ElementTree)"
@@ -159,7 +167,7 @@ class JSONDataSetCollection(DataSetCollection):
         return self
 
 
-class JSONDataSet(AbstractDataSet):
+class JSONDataSet: #(AbstractDataSet):
     def __init__(self, filepath: str):
         self._filepath = filepath
 
@@ -179,12 +187,11 @@ class FullJSONDataSetCollection(DataSetCollection):
     def _load(self) -> dict[str, JSONDataSet]:
         "kedro's API loader method"
         self.datasets = dict()
-        for filepath in sorted(self._folderpath.glob("*.xml")):
+        for filepath in sorted(self._folderpath.glob("*.json")):
             self.datasets[filepath.stem] = JSONDataSet(
                 filepath=str(filepath))
         return self
 
-
 #class TextDataSet:
 #    """loads/saves data from/to a text file using an underlying filesystem
 #    example usage