Analyser optimisations (#781)

* Updated Context names and removed deprecated logic for parsing XML metadata from the TomographyContext
* Separate the bulk of the '_analyse' logic from the while loop it is in
* Added brackets around the 'or' clauses in the 'if self._limited' block of logic
* Disentangled the processing logic for the 4 SPA- and Tomography-related contexts
* Replaced matching Contexts using 'str(self._context)' with 'self._context.name'
* Replaced giant if-else blocks with match-case logic
* Updated Analyser tests after rewrite

Author: tieneupin

src/murfey/client/analyser.py

@@ -3,7 +3,7 @@
 import logging
 from importlib.metadata import entry_points
 from pathlib import Path
-from typing import Any, List, NamedTuple
+from typing import Any, NamedTuple, OrderedDict
 
 import xmltodict
 
@@ -209,12 +209,6 @@ def ensure_dcg_exists(
     return dcg_tag
 
 
-class ProcessingParameter(NamedTuple):
-    name: str
-    label: str
-    default: Any = None
-
-
 def detect_acquisition_software(dir_for_transfer: Path) -> str:
     glob = dir_for_transfer.glob("*")
     for f in glob:
@@ -225,9 +219,15 @@ def detect_acquisition_software(dir_for_transfer: Path) -> str:
     return ""
 
 
+class ProcessingParameter(NamedTuple):
+    name: str
+    label: str
+    default: Any = None
+
+
 class Context:
-    user_params: List[ProcessingParameter] = []
-    metadata_params: List[ProcessingParameter] = []
+    user_params: list[ProcessingParameter] = []
+    metadata_params: list[ProcessingParameter] = []
 
     def __init__(self, name: str, acquisition_software: str, token: str):
         self._acquisition_software = acquisition_software
@@ -256,7 +256,7 @@ def post_first_transfer(
 
     def gather_metadata(
         self, metadata_file: Path, environment: MurfeyInstanceEnvironment | None = None
-    ):
+    ) -> OrderedDict | None:
         raise NotImplementedError(
             f"gather_metadata must be declared in derived class to be used: {self}"
         )

src/murfey/client/context.py

@@ -20,7 +20,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("Atlas", acquisition_software, token)
+        super().__init__("AtlasContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
 

src/murfey/client/contexts/atlas.py

@@ -87,7 +87,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("CLEM", acquisition_software, token)
+        super().__init__("CLEMContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
         # CLEM contexts for "auto-save" acquisition mode

src/murfey/client/contexts/clem.py

@@ -81,7 +81,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("FIB", acquisition_software, token)
+        super().__init__("FIBContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
         self._milling: dict[int, list[MillingProgress]] = {}
@@ -189,7 +189,7 @@ def post_transfer(
                 sites = metadata["AutoTEM"]["Project"]["Sites"]["Site"]
                 for site in sites:
                     number = _number_from_name(site["Name"])
-                    milling_angle = site["Workflow"]["Recipe"][0]["Activites"][
+                    milling_angle = site["Workflow"]["Recipe"][0]["Activities"][
                         "MillingAngleActivity"
                     ].get("MillingAngle")
                     if self._lamellae.get(number) and milling_angle:

src/murfey/client/contexts/fib.py

@@ -82,7 +82,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("SPA", acquisition_software, token)
+        super().__init__("SPAContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
         self._processing_job_stash: dict = {}

src/murfey/client/contexts/spa.py

@@ -81,7 +81,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("SPA_metadata", acquisition_software, token)
+        super().__init__("SPAMetadataContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
 

src/murfey/client/contexts/spa_metadata.py

@@ -28,7 +28,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("SXT", acquisition_software, token)
+        super().__init__("SXTContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
 

src/murfey/client/contexts/sxt.py

@@ -5,8 +5,6 @@
 from threading import RLock
 from typing import Callable, Dict, List, OrderedDict
 
-import xmltodict
-
 import murfey.util.eer
 from murfey.client.context import Context, ProcessingParameter, ensure_dcg_exists
 from murfey.client.instance_environment import (
@@ -84,7 +82,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("Tomography", acquisition_software, token)
+        super().__init__("TomographyContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config
         self._tilt_series: Dict[str, List[Path]] = {}
@@ -550,46 +548,14 @@ def post_first_transfer(
     def gather_metadata(
         self, metadata_file: Path, environment: MurfeyInstanceEnvironment | None = None
     ) -> OrderedDict:
-        if metadata_file.suffix not in (".mdoc", ".xml"):
+        if metadata_file.suffix != ".mdoc":
             raise ValueError(
                 f"Tomography gather_metadata method expected xml or mdoc file not {metadata_file.name}"
             )
         try:
             if not metadata_file.is_file():
                 logger.debug(f"Metadata file {metadata_file} not found")
                 return OrderedDict({})
-            if metadata_file.suffix == ".xml":
-                with open(metadata_file, "r") as xml:
-                    try:
-                        for_parsing = xml.read()
-                    except Exception:
-                        logger.warning(
-                            f"Failed to parse file {metadata_file}", exc_info=True
-                        )
-                        return OrderedDict({})
-                    data = xmltodict.parse(for_parsing)
-                try:
-                    metadata: OrderedDict = OrderedDict({})
-                    metadata["experiment_type"] = "tomography"
-                    metadata["voltage"] = 300
-                    metadata["image_size_x"] = data["Acquisition"]["Info"]["ImageSize"][
-                        "Width"
-                    ]
-                    metadata["image_size_y"] = data["Acquisition"]["Info"]["ImageSize"][
-                        "Height"
-                    ]
-                    metadata["pixel_size_on_image"] = float(
-                        data["Acquisition"]["Info"]["SensorPixelSize"]["Height"]
-                    )
-                    metadata["motion_corr_binning"] = 1
-                    metadata["gain_ref"] = None
-                    metadata["dose_per_frame"] = (
-                        environment.dose_per_frame if environment else None
-                    )
-                    metadata["source"] = str(self._basepath)
-                except KeyError:
-                    return OrderedDict({})
-                return metadata
             with open(metadata_file, "r") as md:
                 mdoc_data = get_global_data(md)
                 num_blocks = get_num_blocks(md)

src/murfey/client/contexts/tomo.py

@@ -26,7 +26,7 @@ def __init__(
         machine_config: dict,
         token: str,
     ):
-        super().__init__("Tomography_metadata", acquisition_software, token)
+        super().__init__("TomographyMetadataContext", acquisition_software, token)
         self._basepath = basepath
         self._machine_config = machine_config