Working on the refactoring of apex

.vscode/launch.json

@@ -38,8 +38,8 @@
                      //"../apex/InGaN_nanowires_linescan.edaxh5",
                      //"../apex/InGaN_nanowires_map.edaxh5",
                      //"../apex/InGaN_nanowires_spectra.edaxh5",
-                     //"../apex/2023-08-16_Ni_NFDI.edaxh5",
-                     "tests/data/173_0057.h5oina",
+                     "tests/data/2023-08-16_Ni_NFDI.edaxh5",
+                     //"tests/data/173_0057.h5oina",
                      "--reader",
                      "em",
                      "--nxdl",
@@ -57,7 +57,8 @@
                      //"--output=pynxtools_em/dbg/zeiss.nxs",
                      //"--output=pynxtools_em/dbg/tfs.nxs",
                      //"--output=dbg/apex.nxs"
-                     "--output=dbg/hfive_oxford.nxs"],
+                     //"--output=dbg/hfive_oxford.nxs",
+                     "--output=dbg/hfive_apex.nxs"],
         }
     ]
 }

src/pynxtools_em/parsers/conventions.py

@@ -97,7 +97,7 @@ def parse(self, template) -> dict:
                     ]
                 )
             if not is_cartesian_cs_well_defined(handedness, directions):
-                raise ValueError(f"{csys_name}_reference_frame is not well defined!")
+                print(f"{csys_name}_reference_frame is not well defined!")
 
         # could add tests for gnomonic and pattern_centre as well
         return template

src/pynxtools_em/parsers/hfive_oxford.py

@@ -82,8 +82,7 @@ def check_if_supported(self):
             return
 
         with h5py.File(self.file_path, "r") as h5r:
-            req_fields = ["Manufacturer", "Software Version", "Format Version"]
-            for req_field in req_fields:
+            for req_field in ["Manufacturer", "Software Version", "Format Version"]:
                 if f"/{req_field}" not in h5r:
                     return
 
@@ -130,6 +129,7 @@ def parse(self, template: dict) -> dict:
                         ebsd_roi_overview(self.ebsd, self.id_mgn, template)
                         ebsd_roi_phase_ipf(self.ebsd, self.id_mgn, template)
                         self.id_mgn["roi_id"] += 1
+                        self.ebsd = EbsdPointCloud()
 
                     # TODO:Vitesh example
         return template
@@ -145,7 +145,7 @@ def parse_and_normalize_slice_ebsd_header(self, fp):
         self.ebsd.dimensionality = 2
         # the next two lines encode the typical assumption that is not reported in tech partner file!
 
-        dims = ["X", "Y"]
+        dims = ["X", "Y"]  # TODO::1d example
         for dim in dims:
             for req_field in [f"{dim} Cells", f"{dim} Step"]:
                 if f"{grp_name}/{req_field}" not in fp:
@@ -188,14 +188,13 @@ def parse_and_normalize_slice_ebsd_phases(self, fp):
             self.ebsd.phases[phase_idx] = {}
             sub_grp_name = f"{grp_name}/{phase_id}"
 
-            req_fields = [
+            for req_field in [
                 "Phase Name",
                 "Reference",
                 "Lattice Angles",
                 "Lattice Dimensions",
                 "Space Group",
-            ]
-            for req_field in req_fields:
+            ]:
                 if f"{sub_grp_name}/{req_field}" not in fp:
                     print(f"Unable to parse {sub_grp_name}/{req_field} !")
                     self.ebsd = EbsdPointCloud()
@@ -236,6 +235,14 @@ def parse_and_normalize_slice_ebsd_phases(self, fp):
                 )
                 self.ebsd = EbsdPointCloud()
                 return
+            latt = Lattice(
+                abc[0].magnitude,
+                abc[1].magnitude,
+                abc[2].magnitude,
+                angles[0].magnitude,
+                angles[1].magnitude,
+                angles[2].magnitude,
+            )
 
             # Space Group, no, H5T_NATIVE_INT32, (1, 1), Space group index.
             # The attribute Symbol contains the string representation, for example P m -3 m.
@@ -246,45 +253,21 @@ def parse_and_normalize_slice_ebsd_phases(self, fp):
             else:
                 self.ebsd.space_group = [space_group]
 
+            strct = Structure(title=phase_name, atoms=None, lattice=latt)
             if len(self.ebsd.phase) > 0:
-                self.ebsd.phase.append(
-                    Structure(
-                        title=phase_name,
-                        atoms=None,
-                        lattice=Lattice(
-                            abc[0],
-                            abc[1],
-                            abc[2],
-                            angles[0],
-                            angles[1],
-                            angles[2],
-                        ),
-                    )
-                )
+                self.ebsd.phase.append(strct)
             else:
-                self.ebsd.phase = [
-                    Structure(
-                        title=phase_name,
-                        atoms=None,
-                        lattice=Lattice(
-                            abc[0],
-                            abc[1],
-                            abc[2],
-                            angles[0],
-                            angles[1],
-                            angles[2],
-                        ),
-                    )
-                ]
+                self.ebsd.phase = [strct]
 
     def parse_and_normalize_slice_ebsd_data(self, fp):
         # https://github.com/oinanoanalysis/h5oina/blob/master/H5OINAFile.md
         grp_name = f"{self.prfx}/EBSD/Data"
         if f"{grp_name}" not in fp:
-            raise ValueError(f"Unable to parse {grp_name} !")
+            print(f"Unable to parse {grp_name} !")
+            self.ebsd = EbsdPointCloud()
+            return
 
-        req_fields = ["Euler", "Phase", "X", "Y", "Band Contrast"]
-        for req_field in req_fields:
+        for req_field in ["Euler", "Phase", "X", "Y", "Band Contrast"]:
             if f"{grp_name}/{req_field}" not in fp:
                 print(f"Unable to parse {grp_name}/{req_field} !")
                 self.ebsd = EbsdPointCloud()

src/pynxtools_em/parsers/image_base.py

@@ -31,7 +31,8 @@ def __init__(self, file_path: str = "", verbose=False):
         if file_path is not None and file_path != "":
             self.file_path = file_path
         else:
-            raise ValueError(f"{__name__} needs proper instantiation !")
+            print(f"{__name__} needs proper instantiation !")
+            return
         self.tmp: Dict = {}
         self.verbose = verbose
         self.file_path_sha256 = None
@@ -43,4 +44,5 @@ def init_named_cache(self, ckey: str):
             self.tmp[ckey] = {}
             return ckey
         else:
-            raise ValueError(f"Existent named cache {ckey} must not be overwritten !")
+            print(f"Existent named cache {ckey} must not be overwritten !")
+            return

src/pynxtools_em/parsers/image_png_protochips.py

@@ -183,7 +183,7 @@ def get_xml_metadata(self, file, fp):
                                                 string_to_number(v)
                                             )
                                         else:
-                                            raise KeyError(
+                                            print(
                                                 "Trying to register a duplicated key {key}"
                                             )
                                     if k.endswith(".Value"):

src/pynxtools_em/parsers/image_tiff_jeol.py

@@ -107,7 +107,7 @@ def check_if_tiff_jeol(self):
                         else:
                             self.flat_dict_meta[tmp[0]] = ureg.Quantity(tmp[1])
                     else:
-                        raise KeyError(f"Found duplicated key {tmp[0]} !")
+                        print(f"Found duplicated key {tmp[0]} !")
                 else:
                     print(f"WARNING::{line} is currently ignored !")
 

src/pynxtools_em/parsers/image_tiff_point_electronic.py

@@ -67,7 +67,7 @@ def xmpmeta_to_flat_dict(self, meta: fd.FlatDict):
                     if key not in self.flat_metadata:
                         self.flat_metadata[key] = string_to_number(obj)
                     else:
-                        raise KeyError(f"Duplicated key {key} !")
+                        print(f"Duplicated key {key} !")
 
     def check_if_tiff_point_electronic(self):
         """Check if resource behind self.file_path is a TaggedImageFormat file.

src/pynxtools_em/parsers/image_tiff_tfs.py

@@ -123,7 +123,7 @@ def get_metadata(self):
                     # TODO::better use official convention to not read beyond the end of file
                 idx += 1
                 if pos_s is None or pos_e is None:
-                    raise ValueError(
+                    print(
                         f"Definition of byte boundaries for reading childs of [{parent}] was unsuccessful !"
                     )
                 # print(f"Search for [{parent}] in between byte offsets {pos_s} and {pos_e}")
@@ -150,7 +150,7 @@ def get_metadata(self):
                                 else:
                                     self.flat_dict_meta[f"{parent}/{term}"] = value
                         else:
-                            raise ValueError(
+                            print(
                                 f"Detected an unexpected case {parent}/{term}, type: {type(value)} !"
                             )
                     else:

src/pynxtools_em/parsers/rsciio_velox.py

@@ -157,9 +157,7 @@ def process_event_data_em_metadata(self, obj: dict, template: dict) -> dict:
         flat_orig_meta = fd.FlatDict(obj["original_metadata"], "/")
 
         if (len(identifier) != 3) or (not all(isinstance(x, int) for x in identifier)):
-            raise ValueError(
-                f"Argument identifier {identifier} needs three int values!"
-            )
+            print(f"Argument identifier {identifier} needs three int values!")
         trg = (
             f"/ENTRY[entry{identifier[0]}]/measurement/event_data_em_set/EVENT_DATA_EM"
             f"[event_data_em{identifier[1]}]/em_lab/ebeam_column"

src/pynxtools_em/reader.py

@@ -25,8 +25,8 @@
 
 from pynxtools_em.concepts.nxs_concepts import NxEmAppDef
 from pynxtools_em.parsers.conventions import NxEmConventionParser
+from pynxtools_em.parsers.hfive_apex import HdfFiveEdaxApexParser
 
-# from pynxtools_em.parsers.hfive_apex import HdfFiveEdaxApexParser
 # from pynxtools_em.parsers.hfive_bruker import HdfFiveBrukerEspritParser
 # from pynxtools_em.parsers.hfive_dreamthreed import HdfFiveDreamThreedParser
 # from pynxtools_em.parsers.hfive_ebsd import HdfFiveEbsdCommunityParser
@@ -113,7 +113,7 @@ def read(
         print("Parse and map pieces of information within files from tech partners...")
         if len(case.dat) == 1:  # no sidecar file
             parsers: List[type] = [
-                # HdfFiveEdaxApexParser,
+                HdfFiveEdaxApexParser,
                 # HdfFiveBrukerEspritParser,
                 # HdfFiveDreamThreedParser,
                 # HdfFiveEbsdCommunityParser,

src/pynxtools_em/utils/gatan_utils.py

@@ -41,11 +41,9 @@ def gatan_image_spectrum_or_generic_nxdata(list_of_dict) -> str:
                     else:
                         token.append(obj["units"])
                 else:
-                    raise ValueError(
-                        f"{obj.keys()} are not exactly the expected keywords!"
-                    )
+                    print(f"{obj.keys()} are not exactly the expected keywords!")
             else:
-                raise ValueError(f"{obj} is not a dict!")
+                print(f"{obj} is not a dict!")
         if len(token) >= 1:
             print("_".join(token))
             unit_categories = []
@@ -61,7 +59,7 @@ def gatan_image_spectrum_or_generic_nxdata(list_of_dict) -> str:
                         elif base_unit == "kilogram * meter ** 2 / second ** 2":
                             unit_categories.append("eV")
                         else:
-                            raise ValueError(
+                            print(
                                 f"Hitting an undefined case for base_unit {base_unit} !"
                             )
                     except UndefinedUnitError:

src/pynxtools_em/utils/nion_utils.py

@@ -50,11 +50,9 @@ def nion_image_spectrum_or_generic_nxdata(list_of_dict) -> str:
                     else:
                         token.append(obj["units"])
                 else:
-                    raise ValueError(
-                        f"{obj.keys()} are not exactly the expected keywords!"
-                    )
+                    print(f"{obj.keys()} are not exactly the expected keywords!")
             else:
-                raise ValueError(f"{obj} is not a dict!")
+                print(f"{obj} is not a dict!")
         if len(token) >= 1:
             return "_".join(token)
     return ""

src/pynxtools_em/utils/rsciio_hspy_utils.py

@@ -38,12 +38,12 @@ def get_named_axis(axes_metadata, dim_name):
             if isinstance(axis, dict):
                 if "name" in axis:
                     if axis["name"] == dim_name:
-                        reqs = ["offset", "scale", "size", "units"]
                         # "index_in_array" and "navigate" are currently not required
                         # and ignored but might become important
-                        for req in reqs:
+                        for req in ["offset", "scale", "size", "units"]:
                             if req not in axis:
-                                raise ValueError(f"{req} not in {axis}!")
+                                print(f"{req} not in {axis}!")
+                                return None
                         retval = (
                             np.asarray(
                                 axis["offset"]

src/pynxtools_em/utils/string_conversions.py

@@ -35,7 +35,7 @@ def string_to_number(arg: str):
         raise TypeError(f"Input argument arg needs to be a string!")
 
 
-def rchop(s, suffix):
+def rchop(s: str, suffix: str) -> str:
     if suffix and s.endswith(suffix):
         return s[: -len(suffix)]
     return s

src/pynxtools_em/utils/velox_utils.py

@@ -39,11 +39,9 @@ def velox_image_spectrum_or_generic_nxdata(list_of_dict) -> str:
                     else:
                         token.append(obj["units"])
                 else:
-                    raise ValueError(
-                        f"{obj.keys()} are not exactly the expected keywords!"
-                    )
+                    print(f"{obj.keys()} are not exactly the expected keywords!")
             else:
-                raise ValueError(f"{obj} is not a dict!")
+                print(f"{obj} is not a dict!")
         if len(token) >= 1:
             print("_".join(token))
             unit_categories = []