This is an automated email from the ASF dual-hosted git repository.
tilman pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git
The following commit(s) were added to refs/heads/main by this push:
new 78bd4b29e TIKA-4278: colon delimiter detection is unreliable, use the
next one if same confidence
78bd4b29e is described below
commit 78bd4b29eaf685eab678cf6e211274292657a30f
Author: Tilman Hausherr <[email protected]>
AuthorDate: Tue Jul 16 09:31:44 2024 +0200
TIKA-4278: colon delimiter detection is unreliable, use the next one if
same confidence
---
.../src/main/java/org/apache/tika/parser/csv/CSVSniffer.java | 5 +++++
1 file changed, 5 insertions(+)
diff --git
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
index 1a772c22d..6eb53eb14 100644
---
a/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
+++
b/tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/csv/CSVSniffer.java
@@ -93,6 +93,11 @@ class CSVSniffer {
if (bestResult.getConfidence() < minConfidence) {
return CSVResult.TEXT;
}
+ // TIKA-4278: colon isn't reliable, e.g. govdocs1/242/242970.txt
+ if (results.size() > 1 && bestResult.getDelimiter().equals(':') &&
+ results.get(1).getConfidence() == bestResult.getConfidence()) {
+ return results.get(1);
+ }
return bestResult;
}