Merge pull request #929 from IGS/hotfix-927

Hotfix 927

www/api/resources/projectr.py

@@ -497,7 +497,10 @@ def projectr_callback(dataset_id, genecart_id, projection_id, session_id, scope,
                 , "num_dataset_genes": num_target_genes
             }
 
-    adata.close()
+    # Close adata so that we do not have a stale opened object
+    if adata.isbacked:
+        adata.file.close()
+
     if dedup_copy.exists():
         dedup_copy.unlink()
 

www/cgi/process_uploaded_expression_dataset.cgi

@@ -26,6 +26,7 @@ import pandas as pd
 import scanpy as sc
 from scipy import sparse
 import anndata
+import zipfile
 
 # This has a huge dependency stack of libraries. Occasionally, one of them has methods
 #  which prints debugging information on STDOUT, killing this CGI.  So here we redirect
@@ -305,48 +306,58 @@ def process_mex_3tab(upload_dir):
 
     files_extracted = []
 
-    with tarfile.open(filename) as tf:
-        for entry in tf:
-            tf.extract(entry, path=upload_dir)
-
-            # Nemo suffixes
-            nemo_suffixes = ['DataMTX.tab', 'COLmeta.tab', 'ROWmeta.tab']
-            suffix_found = None
+    if compression_format == 'tarball':
+        try:
+            with tarfile.open(filename) as tf:
+                for entry in tf:
+                    tf.extract(entry, path=upload_dir)
+
+                    # Nemo suffixes
+                    nemo_suffixes = ['DataMTX.tab', 'COLmeta.tab', 'ROWmeta.tab']
+                    suffix_found = None
+
+                    for suffix in nemo_suffixes:
+                        if entry.name.endswith(suffix):
+                            suffix_found = suffix
+                            # Rename the file to the appropriate name
+                            os.rename(os.path.join(upload_dir, entry.name), 
+                                    os.path.join(upload_dir, suffix))
+
+                    if suffix_found is not None:
+                        files_extracted.append(suffix_found)
+                    else:
+                        files_extracted.append(entry.name)
+        except tarfile.ReadError:
+            write_status(upload_dir, 'error', "Bad tarball file. Couldn't extract the tarball.")
+            return
 
-            for suffix in nemo_suffixes:
-                if entry.name.endswith(suffix):
-                    suffix_found = suffix
-                    # Rename the file to the appropriate name
-                    os.rename(os.path.join(upload_dir, entry.name), 
-                              os.path.join(upload_dir, suffix))
-
-            if suffix_found is not None:
-                files_extracted.append(suffix_found)
-            else:
-                files_extracted.append(entry.name)
-
-    with zipfile.ZipFile(filename) as zf:
-        for entry in zf.infolist():
-            zf.extract(entry, path=upload_dir)
-
-            # Nemo suffixes
-            nemo_suffixes = ['DataMTX.tab', 'COLmeta.tab', 'ROWmeta.tab']
-            suffix_found = None
-
-            for suffix in nemo_suffixes:
-                if entry.filename.endswith(suffix):
-                    suffix_found = suffix
-                    # Rename the file to the appropriate name
-                    os.rename(os.path.join(upload_dir, entry.filename), 
-                              os.path.join(upload_dir, suffix))
-
-            if suffix_found is not None:
-                files_extracted.append(suffix_found)
-            else:
-                files_extracted.append(entry.filename)
+    if compression_format == 'zip':
+        try:
+            with zipfile.ZipFile(filename) as zf:
+                for entry in zf.infolist():
+                    zf.extract(entry, path=upload_dir)
+
+                    # Nemo suffixes
+                    nemo_suffixes = ['DataMTX.tab', 'COLmeta.tab', 'ROWmeta.tab']
+                    suffix_found = None
+
+                    for suffix in nemo_suffixes:
+                        if entry.filename.endswith(suffix):
+                            suffix_found = suffix
+                            # Rename the file to the appropriate name
+                            os.rename(os.path.join(upload_dir, entry.filename), 
+                                    os.path.join(upload_dir, suffix))
+
+                    if suffix_found is not None:
+                        files_extracted.append(suffix_found)
+                    else:
+                        files_extracted.append(entry.filename)
+        except zipfile.BadZipFile:
+            write_status(upload_dir, 'error', "Bad zip file. Couldn't extract the zip file.")
+            return
 
     # Determine the dataset type
-    dataset_type = tarball_content_type(files_extracted)
+    dataset_type = package_content_type(files_extracted)
 
     if dataset_type is None:
         write_status(upload_dir, 'error', "Unsupported dataset format. Couldn't tell type from file names within the tarball")
@@ -363,7 +374,7 @@ def write_status(upload_dir, status_name, message):
     with open(os.path.join(upload_dir, 'status.json'), 'w') as f:
         f.write(json.dumps(status))
 
-def tarball_content_type(filenames):
+def package_content_type(filenames):
         print("DEBUG: filenames", file=sys.stderr, flush=True)
         print(filenames, file=sys.stderr, flush=True)
         """

www/js/upload_dataset.js

@@ -269,7 +269,6 @@ const populateMetadataFormFromFile = async () => {
     if (data.success) {
         document.getElementsByName('metadata-title')[0].value = data.metadata.title.value;
         document.getElementsByName('metadata-summary')[0].value = data.metadata.summary.value;
-        document.getElementsByName('metadata-dataset-type')[0].value = data.metadata.dataset_type.value;
         document.getElementsByName('metadata-annotation-source')[0].value = data.metadata.annotation_source.value;
         document.getElementsByName('metadata-annotation-version')[0].value = data.metadata.annotation_release_number.value;
         document.getElementsByName('metadata-geo-id')[0].value = data.metadata.geo_accession.value;
@@ -285,6 +284,16 @@ const populateMetadataFormFromFile = async () => {
         document.getElementsByName('metadata-library-source')[0].value = data.metadata.library_source.value;
         document.getElementsByName('metadata-library-strategy')[0].value = data.metadata.library_strategy.value;
         document.getElementsByName('metadata-pubmed-id')[0].value = data.metadata.pubmed_id.value;
+
+        // Handle the metadata-dataset-type select box
+        let dataset_type_select = document.getElementsByName('metadata-dataset-type')[0];
+        for (let i = 0; i < dataset_type_select.options.length; i++) {
+            if (dataset_type_select.options[i].value === data.metadata.dataset_type.value) {
+                dataset_type_select.selectedIndex = i;
+                break;
+            }
+        }
+
         document.getElementById('metadata-upload-status-message').textContent = "Form populated with uploaded metadata";
         button.disabled = false;
 

www/upload_dataset.html

@@ -225,8 +225,8 @@ <h1>Step - Enter metadata (via form OR upload)</h1>
                           <div class="select">
                             <select name="metadata-dataset-type">
                               <option value="">Select one</option>
-                              <option value="sc-rna-seq">Single-cell RNA-seq</option>
-                              <option value="bulk-rna-seq">Bulk RNA-seq</option>
+                              <option value="single-cell-rnaseq">Single-cell RNA-seq</option>
+                              <option value="bulk-rnaseq">Bulk RNA-seq</option>
                               <option value="microarray">Microarray</option>
                             </select>
                           </div>