This is an automated email from the ASF dual-hosted git repository.
tballison 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 3a381e3fc6 TIKA-4997: tika-eval: index container_id on pipes_class*
and extract_… (#3410)
3a381e3fc6 is described below
commit 3a381e3fc66bcf9c020b8779c16125d28cff6c11
Author: Tim Allison <[email protected]>
AuthorDate: Mon Oct 26 08:26:26 2026 -0400
TIKA-4997: tika-eval: index container_id on pipes_class* and extract_…
(#3410)
* TIKA-4997: tika-eval: index container_id on pipes_class* and
extract_exceptions*
The crash-ledger reports and summary.md join extract_exceptions to
pipes_class,
which was built by create-table-as with no index, so H2 scanned
pipes_class once
per exception row: 9 h on a compare with 339k extract exceptions.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
* TIKA-4997: drop the EXPLAIN-based index tests; they break on H2 upgrades
---------
Co-authored-by: Claude Opus 5.5 <[email protected]>
---
tika-eval/tika-eval-app/src/main/resources/comparison-reports.xml | 4 ++++
tika-eval/tika-eval-app/src/main/resources/profile-reports.xml | 2 ++
2 files changed, 6 insertions(+)
diff --git a/tika-eval/tika-eval-app/src/main/resources/comparison-reports.xml
b/tika-eval/tika-eval-app/src/main/resources/comparison-reports.xml
index d1e126c8a6..6e9be4568a 100644
--- a/tika-eval/tika-eval-app/src/main/resources/comparison-reports.xml
+++ b/tika-eval/tika-eval-app/src/main/resources/comparison-reports.xml
@@ -37,6 +37,8 @@
end
from containers c
</sql>
+ <sql>create index pca_container_id on pipes_class_a (container_id)</sql>
+ <sql>create index if not exists eea_container_id on extract_exceptions_a
(container_id)</sql>
<!-- one classification per container; the crash-ledger reports and
summary.md join on it -->
<sql>drop table if exists pipes_class_b</sql>
<sql>create table pipes_class_b (container_id integer, pipes_status
varchar(64), classification varchar(64))
@@ -51,6 +53,8 @@
end
from containers c
</sql>
+ <sql>create index pcb_container_id on pipes_class_b (container_id)</sql>
+ <sql>create index if not exists eeb_container_id on extract_exceptions_b
(container_id)</sql>
<sql>drop index if exists pa_mime_id</sql>
<sql>drop index if exists pb_mime_id</sql>
<sql>create index pa_mime_id on profiles_a (mime_id);</sql>
diff --git a/tika-eval/tika-eval-app/src/main/resources/profile-reports.xml
b/tika-eval/tika-eval-app/src/main/resources/profile-reports.xml
index 3dfec034cc..875b4cde4a 100644
--- a/tika-eval/tika-eval-app/src/main/resources/profile-reports.xml
+++ b/tika-eval/tika-eval-app/src/main/resources/profile-reports.xml
@@ -36,6 +36,8 @@
end
from containers c
</sql>
+ <sql>create index pc_container_id on pipes_class (container_id)</sql>
+ <sql>create index if not exists ee_container_id on extract_exceptions
(container_id)</sql>
</before>