From af140307a025738767e740fea8da8d15e20fb983 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 5 Aug 2020 13:10:56 -0700 Subject: grobid+pdftext missing catch-up commands --- sql/dump_ungrobid_pdf_petabox.sql | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 sql/dump_ungrobid_pdf_petabox.sql (limited to 'sql/dump_ungrobid_pdf_petabox.sql') diff --git a/sql/dump_ungrobid_pdf_petabox.sql b/sql/dump_ungrobid_pdf_petabox.sql new file mode 100644 index 0000000..f758ec2 --- /dev/null +++ b/sql/dump_ungrobid_pdf_petabox.sql @@ -0,0 +1,17 @@ + +-- Run like: +-- psql sandcrawler < dump_ungrobid_pdf_petabox.sql + +BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE; + +COPY ( + SELECT DISTINCT ON (petabox.sha1hex) row_to_json(petabox) + FROM petabox + WHERE NOT EXISTS (SELECT grobid.sha1hex FROM grobid WHERE petabox.sha1hex = grobid.sha1hex AND grobid.status IS NOT NULL) + -- uncomment/comment this to control whether only fatcat files are included + AND EXISTS (SELECT fatcat_file.sha1hex FROM fatcat_file WHERE petabox.sha1hex = fatcat_file.sha1hex) +) +TO '/grande/snapshots/dump_ungrobided_pdf_petabox.2020-08-04.json' +WITH NULL ''; + +ROLLBACK; -- cgit v1.2.3