remove the redundant metadata parser code

src/depiction/persistence/imzml/metadata.py

@@ -0,0 +1,10 @@
+from pydantic import BaseModel
+
+from depiction.persistence.pixel_size import PixelSize
+
+
+class Metadata(BaseModel):
+    pixel_size: PixelSize
+    data_processing: list[str]
+    software: list[str]
+    ibd_checksums: dict[str, str]

src/depiction/persistence/imzml/parser/parse_metadata.py

@@ -1,5 +1,9 @@
+from __future__ import annotations
+
+from pathlib import Path
 from xml.etree.ElementTree import ElementTree
 
+from depiction.persistence.imzml.metadata import Metadata
 from depiction.persistence.pixel_size import PixelSize
 
 
@@ -8,6 +12,18 @@ def __init__(self, etree: ElementTree) -> None:
         self._etree = etree
         self._ns = "{http://psi.hupo.org/ms/mzml}"
 
+    @classmethod
+    def from_file(cls, path: Path) -> ParseMetadata:
+        return cls(ElementTree(file=path))
+
+    def parse(self) -> Metadata:
+        return Metadata(
+            pixel_size=self.pixel_size,
+            data_processing=self.data_processing,
+            software=self.software,
+            ibd_checksums=self.ibd_checksums,
+        )
+
     @property
     def ibd_checksums(self) -> dict[str, str]:
         elements = self._etree.findall(f".//{self._ns}fileDescription/{self._ns}fileContent/{self._ns}cvParam")
@@ -46,3 +62,16 @@ def pixel_size(self) -> PixelSize | None:
             return PixelSize(size_x=pixel_size_x, size_y=pixel_size_x, unit=unit)
         [pixel_size_y] = collect["pixel_size_y"]
         return PixelSize(size_x=pixel_size_x, size_y=pixel_size_y, unit=unit)
+
+    @property
+    def data_processing(self) -> list[str]:
+        # each method will have some child accessions, for now we just parse it all into a flat string
+        # this should probably be improved in the future!! (but then we will simply upgrade to a different type that
+        # can hold the extra information, so it should be obvious whether the new code is used)
+        items = self._etree.findall(f".//{self._ns}processingMethod/{self._ns}cvParam")
+        return [item.attrib["name"] for item in items]
+
+    @property
+    def software(self) -> list[str]:
+        items = self._etree.findall(f".//{self._ns}software/{self._ns}cvParam")
+        return [item.attrib["name"] for item in items]

src/depiction_targeted_preproc/workflow/proc/export_raw_metadata.py

@@ -5,7 +5,8 @@
 from loguru import logger
 from pydantic import ValidationError
 
-from depiction.persistence.imzml.extract_metadata import ExtractMetadata, Metadata
+from depiction.persistence.imzml.metadata import Metadata
+from depiction.persistence.imzml.parser.parse_metadata import ParseMetadata
 from depiction.persistence.pixel_size import PixelSize
 
 
@@ -14,7 +15,7 @@ def proc_export_raw_metadata(
     output_json_path: Annotated[Path, typer.Option()],
 ) -> None:
     try:
-        metadata = ExtractMetadata.extract_file(input_imzml_path)
+        metadata = ParseMetadata.from_file(input_imzml_path).parse()
     except ValidationError:
         logger.error("Failed to extract metadata from {input_imzml_path}", input_imzml_path=input_imzml_path)
         logger.info("Using dummy metadata instead!")

src/depiction_targeted_preproc/workflow/vis/images_ome_tiff.py

@@ -4,7 +4,7 @@
 
 from depiction.image import MultiChannelImage
 from depiction.persistence.format_ome_tiff import OmeTiff
-from depiction.persistence.imzml.extract_metadata import Metadata
+from depiction.persistence.imzml.metadata import Metadata
 
 app = cyclopts.App()