v1.17.1 (AR500 fix cleaning func)

Alban-Peyrat · Mar 14, 2024 · 82d268d · 82d268d
1 parent 6d573de
commit 82d268d
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,14 @@ _Some previous changes will be added_
 
 ## [Unreleased]
 
+## [1.17.1] - 2024-03-14
+
+### Fixed
+
+* Added `UN` to the lsit of empty words deleted
+* Added `+` to the list of deleted noise
+* Logs now properly write the target database value instead of the origin database twice
+
 ## [1.17.0] - 2024-02-28
 
 ### Changed

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"\.|\,|\?|\!|\;|\/|\:|\=|\[|\]|\'|\-|\(|\)|\||\"|\<|\>", " ", _str, flags=re.IGNORECASE)
+        _str = re.sub(r"\.|\,|\?|\!|\;|\/|\:|\=|\[|\]|\'|\-|\(|\)|\||\"|\<|\>|\+", " ", _str, flags=re.IGNORECASE)
     # replace multiple spaces by ine in string if requested (default yes)
     if _multiplespaces:
         _str = re.sub("\s+", " ", _str).strip()
@@ -114,7 +114,7 @@ def delete_CBS_boolean_operators(txt:str) -> str:
 
 def delete_Sudoc_empty_words(txt:str) -> str:
     """Deletes all Sudoc empty keywords (index TOUT) to simplify the query"""
-    txt = re.sub(r"\b(A|BIS|DI|IL|OF|THE|AB|BY|DIE|IM|ON|THEIR|ABOUT|C|DONT|IMPR|OU|THIS|ACCORDING|CE|DR|IN|OVER|TO|ACROSS|CETTE|DU|INTO|P|UEBER|AD|CEUX|DURANT|E|PAR|UM|AGAINST|CHEZ|DURANTE|ITS|PER|UND|AINSI|CO|DURCH|J|PLUS|UNDER|AL|COMME|DURING|L|POR|UNE|ALL|COMO|E|LA|POUR|UNLESS|ALLA|CUM|ED|LAS|QU|UNTER|ALLE|D|EIN|LE|QUAE|UPON|ALS|DAL|EINE|LES|QUE|VOM|ALSO|DALL|EINEM|LEUR|R|VON|ALTRE|DALLA|EINER|LEURS|S|VOR|AM|DANS|EINES|LO|SANS|VOS|AMONG|DAS|EL|LOS|SE|VOTRE|AN|DE|EN|M|SELON|VOUS|AND|DEGLI|ES|MES|SES|W|ASI|DEL|ET|MIT|SIC|WAS|AT|DELL|F|N|SINCE|WE|ATQUE|DELLA|FOR|NACH|SIVE|WHITCH|AU|DELLE|FROM|NE|SN|WITH|AUF|DELLO|FUER|NEAR|SO|Y|AUPRES|DEM|G|NEL|SOME|ZU|AUS|DEN|GLI|NO|SOUS|ZUR|AUSSI|DEPUIS|H|NOS|ST|AUX|DER|HIS|NOTRE|SUL|AVEC|DEREN|I|NOUS|SUR|B|DES|IHRE|O|TE|BEI|DESDE|IHRER|ODER|THAT)\b", "", txt, flags=re.IGNORECASE)
+    txt = re.sub(r"\b(A|BIS|DI|IL|OF|THE|AB|BY|DIE|IM|ON|THEIR|ABOUT|C|DONT|IMPR|OU|THIS|ACCORDING|CE|DR|IN|OVER|TO|ACROSS|CETTE|DU|INTO|P|UEBER|AD|CEUX|DURANT|E|PAR|UM|AGAINST|CHEZ|DURANTE|ITS|PER|UND|AINSI|CO|DURCH|J|PLUS|UNDER|AL|COMME|DURING|L|POR|UNE|ALL|COMO|E|LA|POUR|UNLESS|ALLA|CUM|ED|LAS|QU|UNTER|ALLE|D|EIN|LE|QUAE|UPON|ALS|DAL|EINE|LES|QUE|VOM|ALSO|DALL|EINEM|LEUR|R|VON|ALTRE|DALLA|EINER|LEURS|S|VOR|AM|DANS|EINES|LO|SANS|VOS|AMONG|DAS|EL|LOS|SE|VOTRE|AN|DE|EN|M|SELON|VOUS|AND|DEGLI|ES|MES|SES|W|ASI|DEL|ET|MIT|SIC|WAS|AT|DELL|F|N|SINCE|WE|ATQUE|DELLA|FOR|NACH|SIVE|WHITCH|AU|DELLE|FROM|NE|SN|WITH|AUF|DELLO|FUER|NEAR|SO|Y|AUPRES|DEM|G|NEL|SOME|ZU|AUS|DEN|GLI|NO|SOUS|ZUR|AUSSI|DEPUIS|H|NOS|ST|AUX|DER|HIS|NOTRE|SUL|AVEC|DEREN|I|NOUS|SUR|B|DES|IHRE|O|TE|BEI|DESDE|IHRER|ODER|THAT|UN)\b", "", txt, flags=re.IGNORECASE)
     return re.sub(r"\s+", " ", txt)
 
 def delete_for_sudoc(txt:str) -> str:

diff --git a/main.py b/main.py
@@ -64,7 +64,7 @@ def main(es: fcr.Execution_Settings):
     if es.processing.enum_member == fcr.Processing_Names.MARC_FILE_IN_KOHA_SRU:
         es.log.simple_info("Koha URL", es.target_url)
     es.log.simple_info("Origin database", es.processing.origin_database.name)
-    es.log.simple_info("Target database", es.processing.origin_database.name)
+    es.log.simple_info("Target database", es.processing.target_database.name)
     es.log.simple_info("Origin database mapping", es.origin_database_mapping)
     es.log.simple_info("Target database mapping", es.target_database_mapping)