From 4974246522906c5763a08d96ac8992251b7c3e9d Mon Sep 17 00:00:00 2001
From: Florez Ospina Juan Felipe <juan.florez-ospina@psi.ch>
Date: Fri, 13 Sep 2024 14:59:11 +0200
Subject: [PATCH] move def get_parent_child_relationships(file: h5py.File) from
 ..._vis.py to ..._ops.py

---
 src/hdf5_ops.py | 32 ++++++++++++++++++++++++++++++++
 src/hdf5_vis.py | 33 ++-------------------------------
 2 files changed, 34 insertions(+), 31 deletions(-)

diff --git a/src/hdf5_ops.py b/src/hdf5_ops.py
index 0906c87..133f0f3 100644
--- a/src/hdf5_ops.py
+++ b/src/hdf5_ops.py
@@ -196,3 +196,35 @@ def list_datasets_in_hdf5file(hdf5_file_path):
     dataset_df['parent_file'] = dataset_df['dataset_name'].apply(lambda x: x.split('/')[-2])
 
     return dataset_df
+
+def get_parent_child_relationships(file: h5py.File):
+
+    nodes = ['/']
+    parent = ['']
+    #values = [file.attrs['count']]
+    # TODO: maybe we should make this more general and not dependent on file_list attribute? 
+    #if 'file_list' in file.attrs.keys():
+    #    values = [len(file.attrs['file_list'])]
+    #else:
+    #    values = [1]
+    values = [len(file.keys())]
+
+    def node_visitor(name,obj):
+        if name.count('/') <=2:
+            nodes.append(obj.name)
+            parent.append(obj.parent.name)
+            #nodes.append(os.path.split(obj.name)[1])
+            #parent.append(os.path.split(obj.parent.name)[1])
+            
+            if isinstance(obj,h5py.Dataset):# or not 'file_list' in obj.attrs.keys():
+                values.append(1)
+            else:
+                print(obj.name)
+                try:
+                    values.append(len(obj.keys()))
+                except:
+                    values.append(0)
+
+    file.visititems(node_visitor)
+
+    return nodes, parent, values 
\ No newline at end of file
diff --git a/src/hdf5_vis.py b/src/hdf5_vis.py
index f09cede..cebab9e 100644
--- a/src/hdf5_vis.py
+++ b/src/hdf5_vis.py
@@ -13,38 +13,9 @@ from plotly.subplots import make_subplots
 import plotly.graph_objects as go
 import plotly.express as px
 #import plotly.io as pio
+from hdf5_ops import get_parent_child_relationships
 
-def get_parent_child_relationships(file: h5py.File):
-
-    nodes = ['/']
-    parent = ['']
-    #values = [file.attrs['count']]
-    # TODO: maybe we should make this more general and not dependent on file_list attribute? 
-    #if 'file_list' in file.attrs.keys():
-    #    values = [len(file.attrs['file_list'])]
-    #else:
-    #    values = [1]
-    values = [len(file.keys())]
-
-    def node_visitor(name,obj):
-        if name.count('/') <=2:
-            nodes.append(obj.name)
-            parent.append(obj.parent.name)
-            #nodes.append(os.path.split(obj.name)[1])
-            #parent.append(os.path.split(obj.parent.name)[1])
-            
-            if isinstance(obj,h5py.Dataset):# or not 'file_list' in obj.attrs.keys():
-                values.append(1)
-            else:
-                print(obj.name)
-                try:
-                    values.append(len(obj.keys()))
-                except:
-                    values.append(0)
-
-    file.visititems(node_visitor)
-
-    return nodes, parent, values    
+ 
 
 def display_group_hierarchy_on_a_treemap(filename: str):