From 55815b2e62a3ce53d5e71d0c6fd676b6cbf5baca Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 3 Nov 2020 11:31:38 -0800 Subject: SQL: unmatched glutton query (old) --- sql/dump_unmatched_glutton_pdf.sql | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) create mode 100644 sql/dump_unmatched_glutton_pdf.sql (limited to 'sql') diff --git a/sql/dump_unmatched_glutton_pdf.sql b/sql/dump_unmatched_glutton_pdf.sql new file mode 100644 index 0000000..d089c7e --- /dev/null +++ b/sql/dump_unmatched_glutton_pdf.sql @@ -0,0 +1,19 @@ + +-- Run like: +-- psql sandcrawler < THING.sql > THING.2019-09-23.json + +BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE; + +COPY ( + SELECT row_to_json(grobid) + FROM grobid + LEFT JOIN fatcat_file ON grobid.sha1hex = fatcat_file.sha1hex + WHERE fatcat_file.sha1hex IS NULL + AND grobid.fatcat_release IS NOT NULL + LIMIT 1000 +) +TO '/grande/snapshots/dump_unmatched_glutton_pdf.2020-06-30.json'; +--TO STDOUT +--WITH NULL ''; + +ROLLBACK; -- cgit v1.2.3