1.17.5 : bug fix

Alban-Peyrat · Apr 11, 2024 · 46386a0 · 46386a0
1 parent aa6e741
commit 46386a0
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,13 @@ _Some previous changes will be added_
 
 ## [Unreleased]
 
+## [1.17.5] - 2024-04-11
+
+### Fixed
+
+* `Universal_Data_Extractor.extract_list_of_strings` method does not crash anymore if some subfield had no values
+* ASCII range (hexadecimal) `21-2F`, `3A-40`, `5B-60`, `7B-7F` added to the noise list
+
 ## [1.17.4] - 2024-03-28
 
 ### Added

diff --git a/fcr_classes.py b/fcr_classes.py
@@ -2884,7 +2884,11 @@ def extract_list_of_strings(self,marc_field: Marc_Fields_Data, filter_value: Opt
         output = []
         extraction = self.extract_data_from_marc_field(marc_field, filter_value)
         for field_value in extraction:
-            output.append(" ".join(field_value))
+            valid_values = []
+            for value in field_value:
+                if value:
+                    valid_values.append(value)
+            output.append(" ".join(valid_values))
         return output
 
     def extract_list_of_lists(self,marc_field: Marc_Fields_Data, filter_value: Optional[str] = "") -> List[str]:

diff --git a/fcr_func.py b/fcr_func.py
@@ -16,7 +16,7 @@ def prep_string(_str:str, _noise = True, _multiplespaces = True) -> str:
     """
     # remove noise (punctuation) if asked (by default yes)
     if _noise:
-        _str = re.sub(r"\.|\,|\?|\!|\;|\/|\:|\=|\[|\]|\'|\-|\(|\)|\||\"|\<|\>|\+|\°|[\u2010-\u2015]", " ", _str, flags=re.IGNORECASE)
+        _str = re.sub(r"[\x21-\x2F]|[\x3A-\x40]|[\x5B-\x60]|[\x7B-\x7F]|[\u2010-\u2015]|\.|\,|\?|\!|\;|\/|\:|\=|\[|\]|\'|\-|\(|\)|\||\"|\<|\>|\+|\°", " ", _str, flags=re.IGNORECASE)
     # replace multiple spaces by ine in string if requested (default yes)
     if _multiplespaces:
         _str = re.sub("\s+", " ", _str).strip()