From 15d5ba2907a3aab871f5eef8f5ca070f8735ca1a Mon Sep 17 00:00:00 2001
From: Elias Vitali <elias.vitali@kit.edu>
Date: Mon, 26 Jun 2023 12:59:28 +0200
Subject: [PATCH] added support for non-indexed acquisitions

---
 acquisitionMapper.py | 10 +++++++++-
 metaMapper.py        | 36 +++++++++++++++++++++++++++---------
 2 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/acquisitionMapper.py b/acquisitionMapper.py
index c71b12f..386ed89 100644
--- a/acquisitionMapper.py
+++ b/acquisitionMapper.py
@@ -64,13 +64,21 @@ def extract_values(addresses, data, dataset_num = 1):
     for key, address in addresses.items():
         levels = address.split('.')
         current_data = data
+        # print(levels)
         for level in levels:
             # emxml contains multiple instances of "Dataset", so it returns a list when asked. We need to tell it
             # which dataset we actually want. 1 is SEM Image, 2 is SEM Image 2, and 3 is the one we're not
             # interested in. We subtract 1 because indexing begins at zero
             # Still needed: check this against image folder name
+            # print(f"current level: {level}")
             if level == 'Dataset':
-                current_data = current_data[level][dataset_num - 1]
+                if isinstance(current_data[level], list):
+                    try:
+                        current_data = current_data[level][dataset_num - 1]
+                    except IndexError:
+                        print(f"There is no dataset at index {dataset_num}.")
+                else:
+                    current_data = current_data[level]
             else:
                 current_data = current_data[level]
         result[key] = current_data
diff --git a/metaMapper.py b/metaMapper.py
index 9b2e5f5..5e9436d 100644
--- a/metaMapper.py
+++ b/metaMapper.py
@@ -12,6 +12,7 @@
 
 def extract_zip_file(zip_file_path):
     temp_dir = tempfile.mkdtemp()
+    
 
     start_time = time.time()  # Start time
     logging.info("Extracting {zip_file_path}...")
@@ -19,8 +20,11 @@ def extract_zip_file(zip_file_path):
     target_dir = None
 
     with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
+        total_items = len(zip_ref.namelist())
 
         for index, file_name in enumerate(zip_ref.namelist(), start=1):
+            if index%10 == 0:
+                print(f"Extracting file {index}/{total_items}...")
             file_path = os.path.join(temp_dir, file_name)
             zip_ref.extract(file_name, temp_dir)
 
@@ -42,14 +46,24 @@ def extract_zip_file(zip_file_path):
 inputZip   = sys.argv[2]
 outputFile = sys.argv[3]
 
+def getExampleImage(directory):
+    for file in os.listdir(directory):
+        if file.endswith('.tif'):
+            return os.path.join(directory, file)
+
 mainDir, tempDir = extract_zip_file(inputZip)
-imgFile = os.path.join(mainDir, 'Images/SEM Image 2/SEM Image 2 - SliceImage - 001.tif') # uses the first image
+imgFile = getExampleImage(os.path.join(mainDir, 'Images/SEM Image'))
 imgDirectory = os.path.join(mainDir, 'Images')
 xmlFile = os.path.join(mainDir, 'EMproject.emxml')
 
 xmlMap, imgMap = extract_metadata_addresses(mapFile)
 xmlMetadata = xml_to_dict(xmlFile)
 
+# print('XML MAP:')
+# print(xmlMap)
+# print('xmlMetadata')
+# print(xmlMetadata)
+
 acqXmlMetadata = extract_values(xmlMap, xmlMetadata)
 
 # Read an image for acquisition metadata
@@ -65,7 +79,11 @@ def extract_zip_file(zip_file_path):
 # Read and format dataset metadata
 datasetXmlMap, datasetImgMap = extract_metadata_addresses_dataset(mapFile)
 datasets = xmlMetadata['EMProject']['Datasets']['Dataset']
-datasetNames = [d['Name'] for d in datasets]
+# print(f'len = {len(datasets)}, datasets: {datasets}')
+if isinstance(datasets, list):
+    datasetNames = [d['Name'] for d in datasets]
+else:
+    datasetNames = [datasets['Name']]
 def processDatasets(datasetNum, imageDirectory):
     # Extract xml data for this dataset
     mappedEMMetadata = extract_values(datasetXmlMap, xmlMetadata, datasetNum)
@@ -198,17 +216,17 @@ def combineMetadata(acquisition_metadata, dataset_metadata, image_metadata):
             metadata['acquisition']['dataset'][i]['images'].append(image_dict)
     return metadata
 
-def save_metadata_as_json(metadata, save_path):
-    with open(save_path, 'w') as file:
-        json.dump(metadata, file, indent=4)
-    logging.info(f"Metadata saved as {save_path}")
-
-# For local tests
 # def save_metadata_as_json(metadata, save_path):
-#     with open(os.path.join(save_path, 'output.json'), 'w') as file:
+#     with open(save_path, 'w') as file:
 #         json.dump(metadata, file, indent=4)
 #     logging.info(f"Metadata saved as {save_path}")
 
+# For local tests
+def save_metadata_as_json(metadata, save_path):
+    with open(os.path.join(save_path, 'output.json'), 'w') as file:
+        json.dump(metadata, file, indent=4)
+    logging.info(f"Metadata saved as {save_path}")
+
 combinedMetadata = combineMetadata(acqMetadata, datasetMetadata, imageMetadata)
 save_metadata_as_json(combinedMetadata, outputFile)
 shutil.rmtree(tempDir)