aboutsummaryrefslogtreecommitdiffstats
path: root/sql/dump_reingest_quarterly.sql
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2022-04-04 15:27:02 -0700
committerBryan Newbold <bnewbold@archive.org>2022-04-04 15:27:02 -0700
commitc4caeaedc63c2bb2f9bb9f6be6826480aefc9caf (patch)
tree8cbf981a46afc8571ab3cc85f3eab5595afd426b /sql/dump_reingest_quarterly.sql
parent51193896a4958025f1bf045b0ba908ab5d4d0553 (diff)
downloadsandcrawler-c4caeaedc63c2bb2f9bb9f6be6826480aefc9caf.tar.gz
sandcrawler-c4caeaedc63c2bb2f9bb9f6be6826480aefc9caf.zip
sql: fix reingest query missing type on LEFT JOIN; wrap in read-only transaction
Diffstat (limited to 'sql/dump_reingest_quarterly.sql')
-rw-r--r--sql/dump_reingest_quarterly.sql7
1 files changed, 6 insertions, 1 deletions
diff --git a/sql/dump_reingest_quarterly.sql b/sql/dump_reingest_quarterly.sql
index c425a15..c377bf0 100644
--- a/sql/dump_reingest_quarterly.sql
+++ b/sql/dump_reingest_quarterly.sql
@@ -1,7 +1,11 @@
+BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE;
+
COPY (
SELECT row_to_json(ingest_request.*) FROM ingest_request
- LEFT JOIN ingest_file_result ON ingest_file_result.base_url = ingest_request.base_url
+ LEFT JOIN ingest_file_result ON
+ ingest_file_result.base_url = ingest_request.base_url
+ AND ingest_file_result.ingest_type = ingest_request.ingest_type
WHERE
(ingest_request.ingest_type = 'pdf'
OR ingest_request.ingest_type = 'html')
@@ -32,3 +36,4 @@ COPY (
-- AND (ingest_request.ingest_request_source != 'fatcat-changelog'
-- AND ingest_request.ingest_request_source != 'fatcat-ingest')
+ROLLBACK;