aboutsummaryrefslogtreecommitdiffstats
path: root/sql/dump_unextracted_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_unextracted_pdf_petabox.sql
parentec09418b88c0bf77fa2e8b4319529fa8044918c3 (diff)
downloadsandcrawler-af140307a025738767e740fea8da8d15e20fb983.tar.gz
sandcrawler-af140307a025738767e740fea8da8d15e20fb983.zip
grobid+pdftext missing catch-up commands
Diffstat (limited to 'sql/dump_unextracted_pdf_petabox.sql')
-rw-r--r--sql/dump_unextracted_pdf_petabox.sql18
1 files changed, 18 insertions, 0 deletions
diff --git a/sql/dump_unextracted_pdf_petabox.sql b/sql/dump_unextracted_pdf_petabox.sql
new file mode 100644
index 0000000..7db34fb
--- /dev/null
+++ b/sql/dump_unextracted_pdf_petabox.sql
@@ -0,0 +1,18 @@
+
+-- Run like:
+-- psql sandcrawler < dump_unextracted_pdf_petabox.sql
+
+BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE;
+
+COPY (
+ SELECT DISTINCT ON (petabox.sha1hex) row_to_json(petabox)
+ FROM grobid
+ LEFT JOIN petabox ON grobid.sha1hex = petabox.sha1hex
+ LEFT JOIN pdf_meta ON grobid.sha1hex = pdf_meta.sha1hex
+ WHERE petabox.sha1hex IS NOT NULL
+ AND pdf_meta.sha1hex IS NULL
+)
+TO '/grande/snapshots/dump_unextracted_pdf_petabox.2020-07-22.json'
+WITH NULL '';
+
+ROLLBACK;