feature/pdct 1441 Add family_import_id and import_id to GCF document parser

.trunk/configs/cspell.json

@@ -36,7 +36,11 @@
     "iterrows",
     "notna",
     "conftest",
-    "capsys"
+    "capsys",
+    "dtypes",
+    "isin",
+    "pydantic",
+    "getfixturevalue"
   ],
   "flagWords": ["hte"],
   "suggestionsTimeout": 5000

.trunk/trunk.yaml

@@ -41,7 +41,6 @@ lint:
       paths:
         - .trunk/configs/cspell.json
         - .gitignore
-        - tests/unit_tests/parsers/document/conftest.py
     - linters: [pre-commit-hooks, prettier]
       paths:
         - tests/unit_tests/fixtures/malformed_data.json

gcf_data_mapper/cli.py

@@ -92,7 +92,7 @@ def wrangle_to_json(
     return {
         "collections": collection(debug),
         "families": family(project_info, debug),
-        "documents": document(doc_info, debug),
+        "documents": document(project_info, doc_info, debug),
         "events": event(project_info, debug),
     }
 

gcf_data_mapper/enums/document.py

@@ -0,0 +1,34 @@
+from enum import Enum
+
+
+class RequiredDocumentColumns(Enum):
+    TITLE = "Title"
+    TYPE = "Type"
+    ID = "ID (Unique ID from our CMS for the document)"
+    SOURCE_URL = "Document page permalink"
+
+
+class TranslatedDocumentColumns(Enum):
+    TRANSLATED_FILES = "Translated files"
+    TRANSLATED_TITLES = "Translated titles"
+
+
+class RequiredFamilyDocumentColumns(Enum):
+    APPROVED_REF = "ApprovedRef"
+    PROJECTS_ID = "ProjectsID"
+
+
+class IgnoreDocumentTypes(Enum):
+    """Filter the following columns out of the GCF document data.
+
+    TODO: Phase 2 GCF/MCF we will need to parse these document types too
+    but for now, we will omit them.
+    """
+
+    POLICIES_STRATEGIES_GUIDELINES = "Policies, strategies, and guidelines"
+    COUNTRY_PROGRAMME = "Country programme"
+
+
+class DocumentVariantNames(Enum):
+    ORIGINAL = "Original Translation"
+    TRANSLATION = "Translated"