aboutsummaryrefslogtreecommitdiffstats
path: root/sql/dump_ungrobid_pdf_petabox.sql
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2020-08-05 13:10:56 -0700
committerBryan Newbold <bnewbold@archive.org>2020-08-05 13:10:56 -0700
commitaf140307a025738767e740fea8da8d15e20fb983 (patch)
tree39b3413e2db69ea7568f45eff0eb228be040a59f /sql/dump_ungrobid_pdf_petabox.sql
parentec09418b88c0bf77fa2e8b4319529fa8044918c3 (diff)
downloadsandcrawler-af140307a025738767e740fea8da8d15e20fb983.tar.gz
sandcrawler-af140307a025738767e740fea8da8d15e20fb983.zip
grobid+pdftext missing catch-up commands
Diffstat (limited to 'sql/dump_ungrobid_pdf_petabox.sql')
-rw-r--r--sql/dump_ungrobid_pdf_petabox.sql17
1 files changed, 17 insertions, 0 deletions
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;