From 08ae9f4c14feab9f9e77cfca8f9dcb17eb8ee78e Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Thu, 25 Jun 2020 16:31:22 -0700 Subject: unextracted PDF job dump command --- sql/dump_unextracted_pdf.sql | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 sql/dump_unextracted_pdf.sql diff --git a/sql/dump_unextracted_pdf.sql b/sql/dump_unextracted_pdf.sql new file mode 100644 index 0000000..4d264b9 --- /dev/null +++ b/sql/dump_unextracted_pdf.sql @@ -0,0 +1,16 @@ + +-- Run like: +-- psql sandcrawler < dump_unextracted_pdf.sql > dump_unextracted_pdf.2019-09-23.json + +BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE; + +COPY ( + SELECT row_to_json(cdx) + FROM grobid + LEFT JOIN cdx ON grobid.sha1hex = cdx.sha1hex +) +-- TO '/grande/snapshots/dump_unextracted_pdf.2020-06-25.json'; +TO STDOUT +WITH NULL ''; + +ROLLBACK; -- cgit v1.2.3