aboutsummaryrefslogtreecommitdiffstats
path: root/sql/dump_regrobid_pdf.sql
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2019-11-12 13:22:18 -0800
committerBryan Newbold <bnewbold@archive.org>2019-11-12 13:22:18 -0800
commite0ad2e3be5286b2703df8f0a98b450658e28d28b (patch)
tree4f2781af5cffe42531b8585b1d5e79607c613d28 /sql/dump_regrobid_pdf.sql
parent2e3611f0e66615ae007d4e46bb5905e2220fb690 (diff)
downloadsandcrawler-e0ad2e3be5286b2703df8f0a98b450658e28d28b.tar.gz
sandcrawler-e0ad2e3be5286b2703df8f0a98b450658e28d28b.zip
SQL stats and commands (mostly from sept 2019)
Diffstat (limited to 'sql/dump_regrobid_pdf.sql')
-rw-r--r--sql/dump_regrobid_pdf.sql15
1 files changed, 15 insertions, 0 deletions
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;