adjustements to include .rod downloads and parsing other rod files

src/download_rod_files/README.md

@@ -0,0 +1,34 @@
+# Downloading multiple .rod files
+
+## download_rods_script.sh
+
+Adjust the file `download_rods_script.sh`to the range of download you want.
+Default start is `1` and default end is `3`.
+Be careful: Do not trigger unneccsary amounts of downloads.
+
+Take a look [here](https://solsa.crystallography.net/rod/1000679.html), to get valid .rod IDs. For this example its e.g. `1000679`.
+
+## Add the command as script
+
+`chmod +x download_rods_script.sh`
+
+## Exectutute the script
+
+`./download_rods_script.sh`
+
+
+## Convert the downloaded .rod files
+
+via the pynxtools-raman command:
+
+`dataconverter <PATH_TO>/1000679.rod src/pynxtools_raman/config/config_file_rod.json --reader raman --nxdl NXraman --output rod_example_neuxs.nxs`
+
+
+# Automatec conversion of all .rod files to .nxs files
+
+## Add the command as script
+`chmod +x convert_all_rod_to_nxs.sh`
+
+## Call the script
+`./src/download_rod_files/convert_all_rod_to_nxs.sh`
+

src/download_rod_files/convert_all_rod_to_nxs.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+
+# Define the folder containing the .rod files
+folder_path="./src/download_rod_files"
+
+# Loop over all .rod files in the folder
+for file in "$folder_path"/*.rod; do
+    # Extract the base name (without extension)
+    base_name=$(basename "$file" .rod)
+
+    # Execute the command with the base name
+    dataconverter "$file" src/pynxtools_raman/config/config_file_rod.json \
+      --reader raman --nxdl NXraman --output "${base_name}.nxs"
+done

src/download_rod_files/download_rods_script.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+#for X in {1..3}; do
+for X in {1000004..1000005}; do
+  download_rod_file "$X"
+done

src/pynxtools_raman/config/config_file_rod.json

@@ -18,7 +18,7 @@
   "/ENTRY[entry]/INSTRUMENT[instrument]/LENS_OPT[objective_lens]/numerical_aperture": "@data:_raman_measurement_device.microscope_numerical_aperture",
   "/ENTRY[entry]/INSTRUMENT[instrument]/MONOCHROMATOR[monochromator]/grating/period": "@data:_raman_measurement_device.diffraction_grating",
   "/ENTRY[entry]/INSTRUMENT[instrument]/MONOCHROMATOR[monochromator]/grating/period/@units": "lines/mm",
-  "/ENTRY[entry]/SAMPLE[sample]/name":"@data:_chemical_name_systematic",
+  "/ENTRY[entry]/SAMPLE[sample]/name":"@data:_chemical_name_mineral",
   "/ENTRY[entry]/SAMPLE[sample]/physical_form":"@data:_[local]_chemical_compound_state",
   "/ENTRY[entry]/SAMPLE[sample]/chemical_formula":"@data:_chemical_formula_structural",
   "/ENTRY[entry]/SAMPLE[sample]/ENVIRONMENT[medium]/sample_medium":"@data:_raman_measurement.environment",
@@ -31,7 +31,7 @@
   "/ENTRY[entry]/definition/@url": "Remove_this_if_pynxtools_issue_#469_is_solved",
   "/ENTRY[entry]/experiment_type": "Raman spectroscopy",
   "/ENTRY[entry]/raman_experiment_type": "other",
-  "/ENTRY[entry]/title": "@data:_chemical_name_mineral",
+  "/ENTRY[entry]/title": "@data:_cod_original_formula_sum",
   "/ENTRY[entry]/start_time": "@data:_raman_measurement.datetime_initiated",
   "/ENTRY[entry]/@default": "data",
   "/ENTRY[entry]/DATA[data]/@signal": "y_values",

src/pynxtools_raman/reader.py

@@ -90,6 +90,12 @@ def handle_rod_file(self, filepath) -> Dict[str, Any]:
         # get the key and value pairs from the rod file
         self.raman_data = rod.extract_keys_and_values_from_cif()
 
+        # replace the [ and ] to avoid confliucts in processing with pynxtools NXclass assignments
+        self.raman_data = {
+            key.replace("_[local]_", "_local_"): value
+            for key, value in self.raman_data.items()
+        }
+
         self.missing_meta_data = copy.deepcopy(self.raman_data)
 
         # This changes all uppercase string elements to lowercase string elements for the given key, within a given key value pair
@@ -101,16 +107,17 @@ def handle_rod_file(self, filepath) -> Dict[str, Any]:
         # transform the string into a datetime object
         time_key = "_raman_measurement.datetime_initiated"
         date_time_str = self.raman_data.get(time_key)
-        date_time_obj = datetime.datetime.strptime(date_time_str, "%Y-%m-%d")
-        # assume UTC for .rod data, as this is not specified in detail
-        tzinfo = datetime.timezone.utc
-        if isinstance(date_time_obj, datetime.datetime):
-            if tzinfo is not None:
-                # Apply the specified timezone to the datetime object
-                date_time_obj = date_time_obj.replace(tzinfo=tzinfo)
-
-            # assign the dictionary the corrrected date format
-            self.raman_data[time_key] = date_time_obj.isoformat()
+        if date_time_str is not None:
+            date_time_obj = datetime.datetime.strptime(date_time_str, "%Y-%m-%d")
+            # assume UTC for .rod data, as this is not specified in detail
+            tzinfo = datetime.timezone.utc
+            if isinstance(date_time_obj, datetime.datetime):
+                if tzinfo is not None:
+                    # Apply the specified timezone to the datetime object
+                    date_time_obj = date_time_obj.replace(tzinfo=tzinfo)
+
+                # assign the dictionary the corrrected date format
+                self.raman_data[time_key] = date_time_obj.isoformat()
 
         # remove capitalization
         objective_type_key = "_raman_measurement_device.optics_type"
@@ -199,7 +206,10 @@ def get_data(self, key: str, path: str) -> Any:
         # this filters out the meta data, which is up to now only created for .rod files
 
         if self.missing_meta_data:
-            del self.missing_meta_data[path]
+            # this if condition is required, to only delete keys which are abaialble by the data.
+            # e.g. is defined to extract it via config.json, but there is no value in meta data
+            if path in self.missing_meta_data.keys():
+                del self.missing_meta_data[path]
 
         if value is not None:
             try: