Support extracting and storing snapshots from non-data mcd files

The IMC source folder may contain MCD files with no acquisition data which comprise snapshots need to be included in the converted Zarr folder. This fix implements the logic to check for such MCD files, and then extract and store their snapshot images within the same Zarr folder as "auxiliary" data.

imc2zarr/imclib/imcraw.py

@@ -12,16 +12,23 @@ from .metadefs import MetaDefinitions as defs
 
 class ImcRaw:
 
-    def __init__(self, input_dir, code=None):
-        self.input_dir = input_dir
+    def __init__(self, mcd_fn, code=None, txt_fns=None):
+        self.mcd_fn = mcd_fn
         self.code = code
-        self.mcd_fn = None
-        self.txt_fns = []  # text filenames
-        # parse files
-        self._find_files()
-        self._parse_files()
-        self._build_object_lists()
-        self._assign_imc_meta_summary()
+        self.txt_fns = txt_fns  # text filenames
+        self.panoramas = []
+        self.acquisitions = []
+        try:
+            self._parse_files()
+            self._build_object_lists()
+            self._assign_imc_meta_summary()
+            self.has_acquisitions = True
+        except Exception as e:
+            if self.panoramas and not self.acquisitions:
+                # seems to be an mcd file with snapshot content only, swallow the exception
+                self.has_acquisitions = False
+            else:
+                raise e
 
     def _assign_imc_meta_summary(self):
         # assign run timestamp from the first acquisition
@@ -29,7 +36,6 @@ class ImcRaw:
         # assign code
         if not self.code:
             self.code = self.timestamp.strftime('%Y%m%d-%H%M%S-%f')
-        self.rawmeta = self._parser.xml_str.replace("\n", "")
         self.mcd_sw_version = self.slides[0].get_property(defs.SWVERSION)
         # set meta summary
         self.meta_summary = OrderedDict()
@@ -74,28 +80,12 @@ class ImcRaw:
             _panoramas.append(panorama)
         self.meta_summary['panoramas'] = _panoramas
 
-    def _find_files(self):
-        # check whether the input_dir points to an mcd file
-        if self.input_dir.is_file():
-            if self.input_dir.suffix != '.mcd':
-                raise Exception('Input file does not seem to be a valid mcd file')
-            self.mcd_fn = self.input_dir
-        else:
-            # check if mcd file exists
-            files = list(self.input_dir.glob('*.mcd'))
-            if not files:
-                raise Exception('No mcd file was found in the input folder')
-            elif len(files) > 1:
-                raise Exception('More than one mcd files were found in the input folder')
-            self.mcd_fn = files[0]
-            # text files
-            self.txt_fns = list(self.input_dir.glob('*.txt'))
-
     def _parse_files(self):
         try:
             self._parser = ImcDataParser(self.mcd_fn, textfilenames=self.txt_fns)
             self._parser.read_mcd_xml()
             self._parser.parse_mcd_xml()
+            self.rawmeta = self._parser.xml_str.replace("\n", "")
         except Exception as e:
             raise Exception('Error parsing raw files: {}'.format(str(e)))
 
@@ -162,6 +152,7 @@ class ImcRaw:
             self._parser.save_snapshot_image(q, out_folder)
 
     def save_meta_xml(self, out_folder):
+        out_folder.mkdir(parents=True, exist_ok=True)
         fn = "mcd_schema.xml"
         fn = out_folder.joinpath(fn)
         with open(fn, "w") as f: