commit 40e895a0be36a14480c8dbaff5de69bf43b33841
author Nils Diewald <nils@diewald-online.de> Fri Nov 15 14:14:43 2024 +0100
committer Gerrit Code Review <gerrit2@korap.ids-mannheim.de> Fri Nov 15 14:14:43 2024 +0100
tree 46b9d2358e0c57bfbc776c0ffdbd0e5fd51f8477
parent 8703f867969af04fba710fc17e86ab0e87d488eb
parent f4d6add8ef718b1665438a8017c73dc1cecfb7fd

Merge "Don't stop indexing on parsing errors"

Changes

diff --git a/Changes b/Changes
index a0e073c..8886337 100755
--- a/Changes
+++ b/Changes
@@ -1,3 +1,6 @@
+0.2.2 2024-11-14
+        - Don't stop on CSV parsing errors
+
 0.2.1 2024-05-02
         - Update dependencies
         - Add CITATION.cff

service.go

diff --git a/service.go b/service.go
index 3d2ecdc..d0d9769 100644
--- a/service.go
+++ b/service.go
@@ -99,7 +99,8 @@
 			break
 		}
 		if err != nil {
-			log.Fatal(err)
+			log.Println(err)
+			continue;
 		}
 
 		if err := txn.Set([]byte(record[0]), []byte(record[1]+","+record[2])); err == badger.ErrTxnTooBig {

testdata/sz_mapping_example1.csv

diff --git a/testdata/sz_mapping_example1.csv b/testdata/sz_mapping_example1.csv
index b64ca3a..67b3622 100644
--- a/testdata/sz_mapping_example1.csv
+++ b/testdata/sz_mapping_example1.csv
@@ -1,3 +1,4 @@
 "U92/JAN/00001","Süddeutsche Zeitung","https://archiv.szarchiv.de/Portal/restricted/Start.act?articleId=A800000"
 "U92/JAN/00002","Süddeutsche Zeitung","https://archiv.szarchiv.de/Portal/restricted/Start.act?articleId=A800001"
 "U92/JAN/00003","Süddeutsche Zeitung","https://archiv.szarchiv.de/Portal/restricted/Start.act?articleId=A800010"
+"WPD11/A16/05067","Wikipedia","http://de.wikipedia.org/wiki/Arbeitsgemeinschaft_industrieller_Forschungsvereinigungen_\"Otto_von_Guericke\""