From 6a7aa2eeaeeee7f15a84dfeb2e1936bff0380218 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gr=C3=B6ne=2C=20Tjark=20Leon=20Raphael?=
<tjark.leon.raphael.groene@uni-hamburg.de>
Date: Mon, 16 Jun 2025 23:38:27 +0200
Subject: [PATCH] Update file maxwell_integrate_to_h5.py
---
maxwell_integrate_to_h5.py | 193 +++++++++++++++++++++++++++++++++----
1 file changed, 176 insertions(+), 17 deletions(-)
diff --git a/maxwell_integrate_to_h5.py b/maxwell_integrate_to_h5.py
index a79f9ec..9181d12 100644
--- a/maxwell_integrate_to_h5.py
+++ b/maxwell_integrate_to_h5.py
@@ -16,6 +16,7 @@ from watchdog.events import PatternMatchingEventHandler
from multiprocessing.pool import ThreadPool as Pool
import pandas as pd
from silx.io.dictdump import h5todict, dicttoh5
+import re
@@ -123,28 +124,186 @@ def integrate_ims_in_dir(path_im, path_int, dtype_im=".tif", dtype_int=".dat"):
subdir_name = os.path.basename(os.path.normpath(subdir_path_int))
results_df.to_csv(os.path.join(subdir_path_int, f"{subdir_name}.csv"), index=False)
- # Prepare data for HDF5 file using silx
- hdf5_data = {
- subdir_name: {
- "@NX_class": "NXroot",
- }
- }
# Sort results_data by filename
- results_data = sorted(results_data, key=lambda x: x["filename"].lower())
+ def natural_sort_key(item):
+ return [int(text) if text.isdigit() else text.lower() for text in re.split(r'(\d+)', item["filename"])]
- for idx, result in enumerate(results_data, start=1):
- group_name = f"{idx}.1"
- hdf5_data[subdir_name][group_name] = {
+ results_data = sorted(results_data, key=natural_sort_key)
+ # Prepare data for HDF5 file using silx
+ hdf5_data = {
+ subdir_name: {
"@NX_class": "NXentry",
- "description": os.path.basename(result["filename"]),
- "measurements": {
- "@NX_class": "NXcollection",
- "q": result["q"].tolist(),
- "I": result["I"].tolist(),
- "dI": result["dI"].tolist()
- }
+ "description": f"{subdir_name}",
+ "files": [
+ {
+ "name": f"{idx}.1",
+ "path": f"/{idx}.1",
+ "attributes": [
+ {
+ "name": "NX_class",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "NXentry"
+ },
+ {
+ "name": "default",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "measurement"
+ },
+ {
+ "name": "plotselect",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "q,I"
+ }
+ ],
+ "kind": "group",
+ "children": [
+ {
+ "name": "measurement",
+ "path": f"/{idx}.1/measurement",
+ "attributes": [
+ {
+ "name": "NX_class",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "NXcollection"
+ }
+ ],
+ "kind": "group",
+ "children": [
+ {
+ "name": "q",
+ "path": f"/{idx}.1/measurement/q",
+ "attributes": [],
+ "kind": "dataset",
+ "shape": [len(result["q"])],
+ "type": {
+ "class": "Float",
+ "endianness": "little-endian",
+ "size": 64
+ },
+ "chunks": [min(len(result["q"]), 1000)],
+ "filters": [],
+ "rawType": {
+ "signed": False,
+ "type": 1,
+ "vlen": False,
+ "littleEndian": True,
+ "size": 8,
+ "total_size": len(result["q"])
+ },
+ "value": result["q"]
+ },
+ {
+ "name": "I",
+ "path": f"/{idx}.1/measurement/I",
+ "attributes": [],
+ "kind": "dataset",
+ "shape": [len(result["I"])],
+ "type": {
+ "class": "Float",
+ "endianness": "little-endian",
+ "size": 64
+ },
+ "chunks": [min(len(result["I"]), 1000)],
+ "filters": [],
+ "rawType": {
+ "signed": False,
+ "type": 1,
+ "vlen": False,
+ "littleEndian": True,
+ "size": 8,
+ "total_size": len(result["I"])
+ },
+ "value": result["I"]
+ },
+ {
+ "name": "dI",
+ "path": f"/{idx}.1/measurement/dI",
+ "attributes": [],
+ "kind": "dataset",
+ "shape": [len(result["dI"])],
+ "type": {
+ "class": "Float",
+ "endianness": "little-endian",
+ "size": 64
+ },
+ "chunks": [min(len(result["dI"]), 1000)],
+ "filters": [],
+ "rawType": {
+ "signed": False,
+ "type": 1,
+ "vlen": False,
+ "littleEndian": True,
+ "size": 8,
+ "total_size": len(result["dI"])
+ },
+ "value": result["dI"]
+ }
+ ]
+ },
+ {
+ "name": "plotselect",
+ "path": f"/{idx}.1/plotselect",
+ "attributes": [
+ {
+ "name": "NX_class",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "NXcollection"
+ },
+ {
+ "name": "axes",
+ "shape": [1],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "q"
+ },
+ {
+ "name": "signal",
+ "shape": [],
+ "type": {
+ "class": "String",
+ "charSet": "UTF-8",
+ "strPad": "null-terminated"
+ },
+ "value": "I"
+ }
+ ],
+ "kind": "group"
+ }
+ ]
+ }
+ for idx, result in enumerate(results_data, start=1)
+ ]
}
+ }
# Save to HDF5 file using silx
hdf5_file_path = os.path.join(subdir_path_int, f"{subdir_name}.h5")
--
GitLab