nabu 2024.2.13__py3-none-any.whl → 2025.1.0__py3-none-any.whl

nabu/testutils.py

@@ -1,3 +1,4 @@
+from dataclasses import dataclass
 from itertools import product
 import tarfile
 import os
@@ -5,6 +6,7 @@ import numpy as np
 from scipy.signal.windows import gaussian
 from silx.resources import ExternalResources
 from silx.io.dictdump import nxtodict, dicttonx
+from nxtomo.application.nxtomo import ImageKey
 
 utilstest = ExternalResources(
     project="nabu", url_base="http://www.silx.org/pub/nabu/data/", env_key="NABU_DATA", timeout=60
@@ -14,14 +16,14 @@ __big_testdata_dir__ = os.environ.get("NABU_BIGDATA_DIR")
 if __big_testdata_dir__ is None or not (os.path.isdir(__big_testdata_dir__)):
     __big_testdata_dir__ = None
 
-__do_long_tests__ = os.environ.get("NABU_LONG_TESTS", False)
+__do_long_tests__ = os.environ.get("NABU_LONG_TESTS", False)  # noqa: PLW1508
 if __do_long_tests__:
     try:
         __do_long_tests__ = bool(int(__do_long_tests__))
     except:
         __do_long_tests__ = False
 
-__do_large_mem_tests__ = os.environ.get("NABU_LARGE_MEM_TESTS", False)
+__do_large_mem_tests__ = os.environ.get("NABU_LARGE_MEM_TESTS", False)  # noqa: PLW1508
 if __do_large_mem_tests__:
     try:
         __do_large_mem_tests__ = bool(int(__do_large_mem_tests__))
@@ -56,6 +58,38 @@ def get_data(*dataset_path):
     return np.load(dataset_downloaded_path)
 
 
+@dataclass
+class SimpleNXTomoDescription:
+    n_darks: int = 0
+    n_flats1: int = 0
+    n_projs: int = 0
+    n_flats2: int = 0
+    n_align: int = 0
+    frame_shape: tuple = None
+    dtype: np.dtype = np.uint16
+
+
+def get_dummy_nxtomo_info():
+    nx_fname = utilstest.getfile("dummy_nxtomo.nx")
+    data_desc = SimpleNXTomoDescription(
+        n_darks=10, n_flats1=11, n_projs=100, n_flats2=11, n_align=12, frame_shape=(11, 10), dtype=np.uint16
+    )
+    image_key = np.concatenate(
+        [
+            np.zeros(data_desc.n_darks, dtype=np.int32) + ImageKey.DARK_FIELD.value,
+            np.zeros(data_desc.n_flats1, dtype=np.int32) + ImageKey.FLAT_FIELD.value,
+            np.zeros(data_desc.n_projs, dtype=np.int32) + ImageKey.PROJECTION.value,
+            np.zeros(data_desc.n_flats2, dtype=np.int32) + ImageKey.FLAT_FIELD.value,
+            np.zeros(data_desc.n_align, dtype=np.int32) + ImageKey.ALIGNMENT.value,
+        ]
+    )
+    projs_vals = np.arange(data_desc.n_projs) + data_desc.n_flats1 + data_desc.n_darks
+    darks_vals = np.arange(data_desc.n_darks)
+    flats1_vals = np.arange(data_desc.n_darks, data_desc.n_darks + data_desc.n_flats1)
+    flats2_vals = np.arange(data_desc.n_darks, data_desc.n_darks + data_desc.n_flats2)
+    return nx_fname, data_desc, image_key, projs_vals, darks_vals, flats1_vals, flats2_vals
+
+
 def get_array_of_given_shape(img, shape, dtype):
     """
     From a given image, returns an array of the wanted shape and dtype.
@@ -81,12 +115,34 @@ def get_big_data(filename):
 
 
 def uncompress_file(compressed_file_path, target_directory):
-    with tarfile.open(compressed_file_path) as f:
-        f.extractall(path=target_directory)
+    if not tarfile.is_tarfile(compressed_file_path):
+        raise ValueError(f"Invalid tar file: {compressed_file_path}")
+
+    def is_safe_member(member, target_directory):
+        """Ensure the member does not extract outside the target directory."""
+        if not isinstance(member, tarfile.TarInfo):
+            return False  # Reject any unexpected type
+
+        abs_target = os.path.abspath(target_directory)
+        member_path = os.path.abspath(os.path.join(target_directory, member.name))
+        return member_path.startswith(abs_target)
+
+    def get_valid_members(tar):
+        members = [m for m in tar.getmembers() if is_safe_member(m, target_directory)]
+        if not members:
+            raise ValueError("No valid files to extract or archive contains unsafe paths.")
+        for member in members:
+            if not is_safe_member(member, target_directory):
+                raise ValueError(f"Unsafe path detected: {member.name}")
+
+    with tarfile.open(compressed_file_path, "r") as tar:
+        tar.extractall(  # noqa: S202 - what can be done in addition of the above checks ?
+            path=target_directory, members=get_valid_members(tar)
+        )
 
 
 def get_file(fname):
-    downloaded_file = dataset_downloaded_path = utilstest.getfile(fname)
+    downloaded_file = utilstest.getfile(fname)
     if ".tar" in fname:
         uncompress_file(downloaded_file, os.path.dirname(downloaded_file))
         downloaded_file = downloaded_file.split(".tar")[0]
@@ -204,10 +260,7 @@ def generate_nx_dataset(out_fname, image_key, data_volume=None, rotation_angle=N
     nx_entry = nx_dict["entry"]
 
     def _get_field(dict_, path):
-        if path.startswith("/"):
-            path = path[1:]
-        if path.endswith("/"):
-            path = path[:-1]
+        path = path.strip("/")
         split_path = path.split("/")
         if len(split_path) == 1:
             return dict_[split_path[0]]

nabu/utils.py

@@ -1,7 +1,8 @@
+from bisect import bisect_left
 from fnmatch import fnmatch
 from functools import partial
 import os
-from functools import partial, lru_cache
+from functools import lru_cache
 from itertools import product
 import warnings
 from time import time
@@ -94,7 +95,7 @@ def indices_to_slices(indices):
     jumps = np.hstack([-1, jumps, len(indices) - 1])
     slices = []
     for i in range(len(jumps) - 1):
-        slices.append(slice(indices[jumps[i] + 1], indices[jumps[i + 1]] + 1))
+        slices.append(slice(indices[jumps[i] + 1], indices[jumps[i + 1]] + 1))  # noqa: PERF401
     return slices
 
 
@@ -180,10 +181,12 @@ def list_match_queries(available, queries):
     Given a list of strings, return all items matching any of one elements of "queries"
     """
     matches = []
+    if isinstance(queries, str):
+        queries = [queries]
     for a in available:
         for q in queries:
             if fnmatch(a, q):
-                matches.append(a)
+                matches.append(a)  # noqa: PERF401
     return matches
 
 
@@ -211,7 +214,7 @@ def _sizeof(Type):
     return np.dtype(Type).itemsize
 
 
-class _Default_format(dict):
+class _DefaultFormat(dict):
     """
     https://docs.python.org/3/library/stdtypes.html
     """
@@ -224,7 +227,7 @@ def safe_format(str_, **kwargs):
     """
     Alternative to str.format(), but does not throw a KeyError when fields are missing.
     """
-    return str_.format_map(_Default_format(**kwargs))
+    return str_.format_map(_DefaultFormat(**kwargs))
 
 
 def get_ftype(url):
@@ -296,7 +299,7 @@ def view_as_images_stack(img):
 
 
 def rescale_integers(items, new_tot):
-    """ "
+    """
     From a given sequence of integers, create a new sequence
     where the sum of all items must be equal to "new_tot".
     The relative contribution of each item to the new total is approximately kept.
@@ -329,6 +332,8 @@ def merged_shape(shapes, axis=0):
         return (shapes[0][0], n_img, shapes[0][2])
     elif axis == 2:
         return shapes[0][:2] + (n_img,)
+    else:
+        raise ValueError
 
 
 def is_device_backend(backend):
@@ -371,7 +376,7 @@ def generate_powers():
     powers = product(*valuations)
     res = []
     for pw in powers:
-        res.append(np.prod(list(map(lambda x: x[0] ** x[1], zip(primes, pw)))))
+        res.append(np.prod(list(map(lambda x: x[0] ** x[1], zip(primes, pw)))))  # noqa: PERF401
     return np.unique(res)
 
 
@@ -422,10 +427,14 @@ def partition_dict(dict_, n_partitions):
 
 
 def first_dict_item(dict_):
-    keys = sorted(list(dict_.keys()))
+    keys = sorted(dict_.keys())
     return dict_[keys[0]]
 
 
+def first_generator_item(gen):
+    return next(iter(gen))  # instead of list(gen)[0]
+
+
 def subsample_dict(dic, subsampling_factor):
     """
     Subsample a dict where keys are integers.
@@ -437,7 +446,7 @@ def subsample_dict(dic, subsampling_factor):
     return res
 
 
-def compare_dicts(dic1, dic2):
+def compare_dicts(dic1, dic2):  # noqa: PLR0911
     """
     Compare two dictionaries. Return None if and only iff the dictionaries are the same.
 
@@ -530,6 +539,18 @@ def restore_items_in_list(list_, removed_items):
         list_.insert(idx, val)
 
 
+def search_sorted(arr, val):
+    """
+    Binary search that returns the "nearest" index given a query,
+    i.e find "i" that minimizes   abs(arr[i] - val)
+    It does not return the "insersion point" contrarily to numpy.searchsorted() or bisect_left
+    """
+    pos = bisect_left(arr, val)
+    if pos == len(arr):
+        return len(arr) - 1
+    return pos - 1 if abs(val - arr[pos - 1]) < abs(arr[pos] - val) else pos
+
+
 def check_supported(param_value, available, param_desc):
     if param_value not in available:
         raise ValueError("Unsupported %s '%s'. Available are: %s" % (param_desc, param_value, str(available)))
@@ -629,7 +650,7 @@ def get_num_threads(n=None):
         return min(n_avail, n)
 
 
-class DictToObj(object):
+class DictToObj:
     """utility class to transform a dictionary into an object with dictionary items as members.
     Example:
 
@@ -646,14 +667,17 @@ def remove_parenthesis_or_brackets(input_str):
     """
     clear string from left and or roght parenthesis / braquets
     """
-    if input_str.startswith("(") and input_str.endswith(")") or input_str.startswith("[") and input_str.endswith("]"):
+    if (input_str.startswith("(") and input_str.endswith(")")) or (
+        input_str.startswith("[") and input_str.endswith("]")
+    ):
         input_str = input_str[1:-1]
     return input_str
 
 
 def filter_str_def(elmt):
     """clean elemt if is a string defined from a text file.
-    Remove some character that could have be put on left or right and some empty spaces"""
+    Remove some character that could have be put on left or right and some empty spaces
+    """
     if elmt is None:
         return None
     assert isinstance(elmt, str)
@@ -676,7 +700,7 @@ def convert_str_to_tuple(input_str: str, none_if_empty: bool = False):
     if isinstance(input_str, tuple):
         return input_str
     if not isinstance(input_str, str):
-        raise TypeError("input_str should be a string not {}, {}".format(type(input_str), input_str))
+        raise TypeError(f"input_str should be a string not {type(input_str)}, {input_str}")
     input_str = input_str.lstrip(" ").lstrip("(").lstrip("[").lstrip(" ").rstrip(" ")
     input_str = remove_parenthesis_or_brackets(input_str)
     input_str = input_str.replace("\n", ",")
@@ -702,9 +726,9 @@ def concatenate_dict(dict_1, dict_2) -> dict:
     return res
 
 
-class BaseClassError:
+class BaseClassError(BaseException):
     def __init__(self, *args, **kwargs):
-        raise ValueError("Base class")
+        raise NotImplementedError("Base class")
 
 
 def MissingComponentError(msg):
@@ -767,7 +791,7 @@ def median2(img):
     Roughly same speed as scipy median filter, but more memory demanding.
     """
     img2 = extend_image_onepixel(img)
-    I = np.array(
+    img3 = np.array(
         [
             img2[0:-2, 0:-2],
             img2[0:-2, 1:-1],
@@ -780,13 +804,18 @@ def median2(img):
             img2[2:, 2:],
         ]
     )
-    return np.median(I, axis=0)
+    return np.median(img3, axis=0)
 
 
 # ------------------------------------------------------------------------------
 # ---------------------------- Decorators --------------------------------------
 # ------------------------------------------------------------------------------
 
+
+def no_decorator(func):
+    return func
+
+
 _warnings = {}
 
 
@@ -820,6 +849,7 @@ def warning(msg):
                 print(msg)
                 res = func(*args, **kwargs)
                 return res
+            return None
 
         return wrapper
 
@@ -840,7 +870,7 @@ def deprecated(msg, do_print=False):
 
 def deprecated_class(msg, do_print=False):
     def decorator(cls):
-        class wrapper:
+        class Wrapper:
             def __init__(self, *args, **kwargs):
                 deprecation_warning(msg, do_print=do_print, func_name=cls.__name__)
                 self.wrapped = cls(*args, **kwargs)
@@ -849,7 +879,7 @@ def deprecated_class(msg, do_print=False):
             def __getattr__(self, name):
                 return getattr(self.wrapped, name)
 
-        return wrapper
+        return Wrapper
 
     return decorator
 
@@ -905,7 +935,7 @@ from warnings import catch_warnings
 # catch_warnings() does not have "action=XX" kwarg for python < 3.11
 from sys import version_info
 
-if version_info.major == 3 and version_info.minor < 11:
+if version_info.major == 3 and version_info.minor < 11:  # noqa: YTT204 - not sure about this
 
     def dummy(*args, **kwargs):
         pass

{nabu-2024.2.13.dist-info → nabu-2025.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nabu
-Version: 2024.2.13
+Version: 2025.1.0
 Summary: Nabu - Tomography software
 Author-email: Pierre Paleo <pierre.paleo@esrf.fr>, Henri Payno <henri.payno@esrf.fr>, Alessandro Mirone <mirone@esrf.fr>, Jérôme Lesaint <jerome.lesaint@esrf.fr>
 Maintainer-email: Pierre Paleo <pierre.paleo@esrf.fr>
@@ -14,24 +14,25 @@ Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Environment :: Console
 Classifier: Operating System :: Unix
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: POSIX
 Classifier: Topic :: Scientific/Engineering :: Physics
 Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
-Requires-Python: >=3.7
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: numpy<2,>1.9.0
+Requires-Dist: numpy>1.9.0
 Requires-Dist: scipy
 Requires-Dist: h5py>=3.0
 Requires-Dist: silx>=0.15.0
-Requires-Dist: tomoscan>=2.1.5
+Requires-Dist: tomoscan>=2.2.2
 Requires-Dist: psutil
 Requires-Dist: pytest
 Requires-Dist: tifffile
@@ -41,7 +42,6 @@ Requires-Dist: scikit-image; extra == "full"
 Requires-Dist: PyWavelets; extra == "full"
 Requires-Dist: glymur; extra == "full"
 Requires-Dist: pycuda!=2024.1.1; extra == "full"
-Requires-Dist: scikit-cuda; extra == "full"
 Requires-Dist: pycudwt; extra == "full"
 Requires-Dist: sluurp>=0.3; extra == "full"
 Requires-Dist: pyvkfft; extra == "full"