implementing default metadata omission/user metadata selection

src/auto_archiver/core/orchestrator.py

@@ -274,6 +274,14 @@ Here's how that would look: \n\nsteps:\n  extractors:\n  - [your_extractor_name_
             default=False,
         )
 
+        parser.add_argument(
+            "--metadata",
+            dest="requested_metadata",
+            help="An array of specific metadata fields to select from the collected content.",
+            default=[],
+            nargs="?",
+        )
+
     def add_individual_module_args(
         self, modules: list[LazyBaseModule] = None, parser: argparse.ArgumentParser = None
     ) -> None:

src/auto_archiver/modules/metadata_enricher/metadata_enricher.py

@@ -11,19 +11,21 @@ class MetadataEnricher(Enricher):
     Extracts metadata information from files using exiftool.
     """
 
-    def enrich(self, to_enrich: Metadata) -> None:
+    def enrich(self, to_enrich: Metadata, md_grocery_list=["author", "datetimes", "location"]) -> None:
         logger.debug("Extracting EXIF metadata")
 
         for i, m in enumerate(to_enrich.media):
             if len(md := self.get_metadata(m.filename)):
-                to_enrich.media[i].set("metadata", md)
+                # feature flag has this currently turned on
+                specified_md = self.select_metadata(md, md_grocery_list)
+                to_enrich.media[i].set("metadata", specified_md)
+                # to_enrich.media[i].set("metadata", md)
 
     def get_metadata(self, filename: str) -> dict:
         try:
             # Run ExifTool command to extract metadata from the file
             cmd = ["exiftool", filename]
             result = subprocess.run(cmd, capture_output=True, text=True)
-
             # Process the output to extract individual metadata fields
             metadata = {}
             for line in result.stdout.splitlines():
@@ -35,3 +37,33 @@ class MetadataEnricher(Enricher):
         except Exception as e:
             logger.error(f"Error occurred: {e}: {traceback.format_exc()}")
         return {}
+
+    def select_metadata(self, all_md, md_grocery_list):
+        """
+        coordinates the selection of metadata from the general exiftool output to the user-specified grocery list
+        """
+        # defining the batches of metadata that get pulled for special terms
+        author_key_terms = ["author", "producer", "creator"]
+        datetime_key_terms = ["date", "time"]
+        location_key_terms = ["gps", "latitude", "longitude"]
+
+        specified_md = {}
+        for md_key in all_md.keys():
+            md_key_lower = md_key.lower()
+            # checking for special baskets within the grocery list of requested metadata
+            if ("author" in md_grocery_list) and any(
+                term in md_key_lower and len(all_md[md_key]) for term in author_key_terms
+            ):
+                specified_md[md_key] = all_md[md_key]
+            if ("datetime" in md_grocery_list) and any(
+                term in md_key_lower and len(all_md[md_key]) for term in datetime_key_terms
+            ):
+                specified_md[md_key] = all_md[md_key]
+            if ("location" in md_grocery_list) and any(
+                term in md_key_lower and len(all_md[md_key]) for term in location_key_terms
+            ):
+                specified_md[md_key] = all_md[md_key]
+            # if the metadata value is requested directly
+            if md_key_lower in md_grocery_list or md_key in md_grocery_list and len(all_md[md_key]):
+                specified_md[md_key] = all_md[md_key]
+        return specified_md