From e0ad2e3be5286b2703df8f0a98b450658e28d28b Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 12 Nov 2019 13:22:18 -0800 Subject: SQL stats and commands (mostly from sept 2019) --- sql/dump_regrobid_pdf.sql | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100644 sql/dump_regrobid_pdf.sql (limited to 'sql/dump_regrobid_pdf.sql') diff --git a/sql/dump_regrobid_pdf.sql b/sql/dump_regrobid_pdf.sql new file mode 100644 index 0000000..b846834 --- /dev/null +++ b/sql/dump_regrobid_pdf.sql @@ -0,0 +1,15 @@ + +-- Run like: +-- psql sandcrawler < dump_regrobid_pdf.sql | sort -S 4G | uniq -w 40 | cut -f2 > dump_regrobid_pdf.2019-11-12.json + +BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE; + +COPY ( + SELECT cdx.sha1hex, row_to_json(cdx) FROM cdx + WHERE cdx.mimetype = 'application/pdf' + AND EXISTS (SELECT grobid.sha1hex FROM grobid WHERE cdx.sha1hex = grobid.sha1hex AND grobid.grobid_version IS NULL) +) +TO STDOUT +WITH NULL ''; + +ROLLBACK; -- cgit v1.2.3