[hdf5tomoscan] move get_compacted_projections to tomoscan.esrf.utils

tomoscan/esrf/hdf5scan.py

@@ -41,6 +41,7 @@ from silx.utils.enum import Enum as _Enum
 from tomoscan.utils import docstring
 from silx.io.utils import get_data
 from ..unitsystem import metricsystem
+from .utils import get_compacted_dataslices
 import logging
 import typing
 
@@ -615,80 +616,6 @@ class HDF5TomoScan(TomoScanBase):
         else:
             return None
 
-    @staticmethod
-    def _get_compacted_projections(projections):
-        """
-        Regroup urls to get the data more efficiently.
-        Build a structure mapping projections indices to information on
-        how to load the data: `{indices_set: data_location}`
-        where `data_location` contains contiguous indices.
-
-        Parameters
-        -----------
-        projections: dict
-            Dictionary where the key is an integer and the value is a silx `DataUrl`.
-
-        Returns
-        --------
-        merged_projections: dict
-            Dictionary where the key is a list of indices, and the value
-            is the corresponding `silx.io.url.DataUrl` with merged data_slice
-
-        """
-        def _convert_to_slice(idx):
-            if numpy.isscalar(idx):
-                return slice(idx, idx+1)
-            # otherwise, assume already slice object
-            return idx
-
-        def is_contiguous_slice(slice1, slice2):
-            if numpy.isscalar(slice1):
-                slice1 = slice(slice1, slice1+1)
-            if numpy.isscalar(slice2):
-                slice2 = slice(slice2, slice2+1)
-            return slice2.start == slice1.stop
-
-        def merge_slices(slice1, slice2):
-            return slice(slice1.start, slice2.stop)
-
-        sorted_files_indices = sorted(projections.keys())
-        idx0 = sorted_files_indices[0]
-        first_url = projections[idx0]
-
-        merged_indices = [
-            [idx0]
-        ]
-        data_location = [
-            [
-                first_url.file_path(),
-                first_url.data_path(),
-                _convert_to_slice(first_url.data_slice())
-            ]
-        ]
-        pos = 0
-        curr_fp, curr_dp, curr_slice = data_location[pos]
-        for idx in sorted_files_indices[1:]:
-            url = projections[idx]
-            next_slice = _convert_to_slice(url.data_slice())
-            if (url.file_path() == curr_fp) and (url.data_path() == curr_dp) and is_contiguous_slice(curr_slice, next_slice):
-                merged_indices[pos].append(idx)
-                merged_slices = merge_slices(curr_slice, next_slice)
-                data_location[pos][-1] = merged_slices
-                curr_slice = merged_slices
-            else: # "jump"
-                pos += 1
-                merged_indices.append([idx])
-                data_location.append([
-                    url.file_path(), url.data_path(), _convert_to_slice(url.data_slice())
-                ])
-                curr_fp, curr_dp, curr_slice = data_location[pos]
-
-        # Format result
-        res = {}
-        for ind, dl in zip(merged_indices, data_location):
-            res[tuple(ind)] = DataUrl(file_path=dl[0], data_path=dl[1], data_slice=dl[2])
-        return res
-
     @property
     def projections_compacted(self):
         """
@@ -701,7 +628,7 @@ class HDF5TomoScan(TomoScanBase):
             is the corresponding `silx.io.url.DataUrl` with merged data_slice
         """
         if self._projections_compacted is None:
-            self._projections_compacted = self._get_compacted_projections(self.projections)
+            self._projections_compacted = get_compacted_dataslices(self.projections)
         return self._projections_compacted
 
     def __str__(self):

tomoscan/esrf/utils.py

@@ -32,6 +32,7 @@ import os
 import fabio
 from silx.io.url import DataUrl
 from typing import Union
+import numpy
 
 
 def get_parameters_frm_par_or_info(file_: str) -> dict:
@@ -86,3 +87,77 @@ def extract_urls_from_edf(file_: str, start_index: Union[None, int], n_frames: U
                              data_slice=[i_frame, ])
         index += 1
     return res
+
+
+def get_compacted_dataslices(urls):
+    """
+    Regroup urls to get the data more efficiently.
+    Build a structure mapping files indices to information on
+    how to load the data: `{indices_set: data_location}`
+    where `data_location` contains contiguous indices.
+
+    Parameters
+    -----------
+    urls: dict
+        Dictionary where the key is an integer and the value is a silx `DataUrl`.
+
+    Returns
+    --------
+    merged_urls: dict
+        Dictionary where the key is a list of indices, and the value
+        is the corresponding `silx.io.url.DataUrl` with merged data_slice
+
+    """
+    def _convert_to_slice(idx):
+        if numpy.isscalar(idx):
+            return slice(idx, idx+1)
+        # otherwise, assume already slice object
+        return idx
+
+    def is_contiguous_slice(slice1, slice2):
+        if numpy.isscalar(slice1):
+            slice1 = slice(slice1, slice1+1)
+        if numpy.isscalar(slice2):
+            slice2 = slice(slice2, slice2+1)
+        return slice2.start == slice1.stop
+
+    def merge_slices(slice1, slice2):
+        return slice(slice1.start, slice2.stop)
+
+    sorted_files_indices = sorted(urls.keys())
+    idx0 = sorted_files_indices[0]
+    first_url = urls[idx0]
+
+    merged_indices = [
+        [idx0]
+    ]
+    data_location = [
+        [
+            first_url.file_path(),
+            first_url.data_path(),
+            _convert_to_slice(first_url.data_slice())
+        ]
+    ]
+    pos = 0
+    curr_fp, curr_dp, curr_slice = data_location[pos]
+    for idx in sorted_files_indices[1:]:
+        url = urls[idx]
+        next_slice = _convert_to_slice(url.data_slice())
+        if (url.file_path() == curr_fp) and (url.data_path() == curr_dp) and is_contiguous_slice(curr_slice, next_slice):
+            merged_indices[pos].append(idx)
+            merged_slices = merge_slices(curr_slice, next_slice)
+            data_location[pos][-1] = merged_slices
+            curr_slice = merged_slices
+        else: # "jump"
+            pos += 1
+            merged_indices.append([idx])
+            data_location.append([
+                url.file_path(), url.data_path(), _convert_to_slice(url.data_slice())
+            ])
+            curr_fp, curr_dp, curr_slice = data_location[pos]
+
+    # Format result
+    res = {}
+    for ind, dl in zip(merged_indices, data_location):
+        res[tuple(ind)] = DataUrl(file_path=dl[0], data_path=dl[1], data_slice=dl[2])
+    return res