From 476c887ea8b7f85751b3cdc0447931a583077aa0 Mon Sep 17 00:00:00 2001
From: eiglesias34 <eiglesias34@gmail.com>
Date: Fri, 4 Oct 2024 12:23:22 +0200
Subject: [PATCH] Fixing issue with XML namespace

---
 README.md                    |  2 +-
 VERSION                      |  2 +-
 rdfizer/rdfizer/__init__.py  |  1 -
 rdfizer/rdfizer/functions.py | 38 ++++++++++++++++++++++++++++++------
 rdfizer/rdfizer/semantify.py |  1 -
 5 files changed, 34 insertions(+), 10 deletions(-)

diff --git a/README.md b/README.md
index a014546..4143a41 100644
--- a/README.md
+++ b/README.md
@@ -84,7 +84,7 @@ You can easily customize your own configurations from the set of features that S
 
 ## Version 
 ```
-4.7.4.11
+4.7.4.12
 ```
 
 ## RML-Test Cases
diff --git a/VERSION b/VERSION
index e1f202d..6314e65 100644
--- a/VERSION
+++ b/VERSION
@@ -1 +1 @@
-4.7.4.11
\ No newline at end of file
+4.7.4.12
\ No newline at end of file
diff --git a/rdfizer/rdfizer/__init__.py b/rdfizer/rdfizer/__init__.py
index 3384b03..1ce765a 100755
--- a/rdfizer/rdfizer/__init__.py
+++ b/rdfizer/rdfizer/__init__.py
@@ -2333,7 +2333,6 @@ def semantify_xml(triples_map, triples_map_list, output_file_descriptor):
     for child in root.iterfind(level, namespace):
         create_subject = True
         global generated_subjects
-
         if mapping_partitions == "yes":
             if "_" in triples_map.triples_map_id:
                 componets = triples_map.triples_map_id.split("_")[:-1]
diff --git a/rdfizer/rdfizer/functions.py b/rdfizer/rdfizer/functions.py
index aa57b68..096b1b1 100644
--- a/rdfizer/rdfizer/functions.py
+++ b/rdfizer/rdfizer/functions.py
@@ -1212,6 +1212,24 @@ def string_substitution_xml(string, pattern, row, term, iterator, parent_map, na
 
 						else:
 							return None
+					elif namespace != {}:
+						if row.find("{"+namespace[""]+"}"+match) is not None:
+							if re.search("^[\s|\t]*$", row.find("{"+namespace[""]+"}"+match).text) is None:
+								new_string = new_string[:start + offset_current_substitution] + encode_char(row.find("{"+namespace[""]+"}"+match).text.strip()) + new_string[ end + offset_current_substitution:]
+								offset_current_substitution = offset_current_substitution + len(encode_char(row.find("{"+namespace[""]+"}"+match).text.strip())) - (end - start)
+
+							else:
+								return None
+						else:
+							if match in row.attrib:
+								if row.attrib[match] is not None:
+									if re.search("^[\s|\t]*$", row.attrib[match]) is None:
+										new_string = new_string[:start + offset_current_substitution] + encode_char(row.attrib[match].strip()) + new_string[end + offset_current_substitution:]
+										offset_current_substitution = offset_current_substitution + len(encode_char(row.attrib[match].strip())) - (end - start)
+									else:
+										return None
+							else:
+								return None
 					else:
 						if match in row.attrib:
 							if row.attrib[match] is not None:
@@ -1272,12 +1290,20 @@ def string_substitution_xml(string, pattern, row, term, iterator, parent_map, na
 								temp_list[i] = {"string":new_string,"offset_current_substitution":offset_current_substitution}
 								i += 1
 						else:
-							for child in row.findall(match, namespace):
-								if re.search("^[\s|\t]*$", child.text) is None:
-									new_string = temp_list[i]["string"][:start + temp_list[i]["offset_current_substitution"]] + encode_char(child.text.strip()) + temp_list[i]["string"][ end + temp_list[i]["offset_current_substitution"]:]
-									offset_current_substitution = temp_list[i]["offset_current_substitution"] + len(encode_char(child.text.strip())) - (end - start)
-									temp_list[i] = {"string":new_string,"offset_current_substitution":offset_current_substitution}
-									i += 1
+							if namespace != {}:
+								for child in row.findall("{"+namespace[""]+"}"+match, namespace):
+									if re.search("^[\s|\t]*$", child.text) is None:
+										new_string = temp_list[i]["string"][:start + temp_list[i]["offset_current_substitution"]] + encode_char(child.text.strip()) + temp_list[i]["string"][ end + temp_list[i]["offset_current_substitution"]:]
+										offset_current_substitution = temp_list[i]["offset_current_substitution"] + len(encode_char(child.text.strip())) - (end - start)
+										temp_list[i] = {"string":new_string,"offset_current_substitution":offset_current_substitution}
+										i += 1
+							else:
+								for child in row.findall(match, namespace):
+									if re.search("^[\s|\t]*$", child.text) is None:
+										new_string = temp_list[i]["string"][:start + temp_list[i]["offset_current_substitution"]] + encode_char(child.text.strip()) + temp_list[i]["string"][ end + temp_list[i]["offset_current_substitution"]:]
+										offset_current_substitution = temp_list[i]["offset_current_substitution"] + len(encode_char(child.text.strip())) - (end - start)
+										temp_list[i] = {"string":new_string,"offset_current_substitution":offset_current_substitution}
+										i += 1
 				else:
 					match = reference_match.group(1).split("[")[0]
 					if "@" in match:
diff --git a/rdfizer/rdfizer/semantify.py b/rdfizer/rdfizer/semantify.py
index 1de27f8..8c569e9 100755
--- a/rdfizer/rdfizer/semantify.py
+++ b/rdfizer/rdfizer/semantify.py
@@ -2333,7 +2333,6 @@ def semantify_xml(triples_map, triples_map_list, output_file_descriptor):
     for child in root.iterfind(level, namespace):
         create_subject = True
         global generated_subjects
-
         if mapping_partitions == "yes":
             if "_" in triples_map.triples_map_id:
                 componets = triples_map.triples_map_id.split("_")[:-1]