correct handling of namespaces in xml

map_generator/utils/implant_annotations.py

+import logging
+import argparse
+import pandas as pd
+import xml.etree.ElementTree as ET
+from . import utils
+
+
+
+
+
+def implant(map_path: str, variants_path: str) -> str:
+
+    df_vars = pd.read_csv(variants_path, sep='\t', skiprows=4)
+    gene_uniprot = {}
+    for name, g in df_vars.groupby('gene_name')['identifier_uniprot']:
+        gene_uniprot[name] = set(g)
+
+    utils.register_namespaces(map_path)
+    tree = ET.parse(map_path)
+    root = tree.getroot()
+
+    for elem in root.iter('species'):
+        atts = elem.attrib
+        # if 'name' in atts:
+        #     print(elem.tag, atts)
+        for k, v in atts.items():
+            if len(v) > 250:
+                logging.warning("Trimming {} (key {} too long)".format(elem, k))
+                if "resource" in k:
+                    #  We want to keep the RDF resource still a valid resource otherwise MINERVA will fail during import
+                    atts[k] = atts[k].split(";")[0]
+                else:
+                    atts[k] = ""
+
+    return ET.tostring(root, encoding='utf8').decode('utf8')
+
+if __name__ == '__main__':
+
+    logging.basicConfig(
+        level=logging.INFO,
+        format='%(asctime)s [%(levelname)s] %(module)s - %(message)s',
+        datefmt='%H:%M:%S')
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-m", "--map_path",
+                        required=True,
+                        help="Input map XML file")
+    parser.add_argument("-v", "--variants_path",
+                        required=True,
+                        help="MINERVA variant file")
+    args = parser.parse_args()
+    print(implant(args.map_path, args.variants_path))
\ No newline at end of file

map_generator/utils/trim_long_strings.py

 import logging
 import argparse
 import xml.etree.ElementTree as ET
-
+import utils
 
 def trim(path: str) -> str:
+
+    utils.register_namespaces(path)
+
     tree = ET.parse(path)
     root = tree.getroot()
 

map_generator/utils/utils.py

+import xml.etree.ElementTree as ET
+import re
+
+def register_namespaces(path):
+    with open(path) as f:
+        content = f.read()
+        sbml_tag = re.search(r'<sbml([^>]*)>', content).group(1)
+        for ns in re.finditer(r'xmlns:*([^=]*)="([^"]*)"', sbml_tag ):
+            ET.register_namespace(ns.group(1), ns.group(2))
\ No newline at end of file