aboutsummaryrefslogtreecommitdiffstats
path: root/sql/dump_unextracted_pdf.sql
diff options
context:
space:
mode:
Diffstat (limited to 'sql/dump_unextracted_pdf.sql')
-rw-r--r--sql/dump_unextracted_pdf.sql5
1 files changed, 4 insertions, 1 deletions
diff --git a/sql/dump_unextracted_pdf.sql b/sql/dump_unextracted_pdf.sql
index 4d264b9..5c7e7a7 100644
--- a/sql/dump_unextracted_pdf.sql
+++ b/sql/dump_unextracted_pdf.sql
@@ -8,8 +8,11 @@ COPY (
SELECT row_to_json(cdx)
FROM grobid
LEFT JOIN cdx ON grobid.sha1hex = cdx.sha1hex
+ --LEFT JOIN fatcat_file ON grobid.sha1hex = fatcat_file.sha1hex
+ WHERE cdx.sha1hex IS NOT NULL
+ --AND fatcat_file.sha1hex IS NOT NULL
)
--- TO '/grande/snapshots/dump_unextracted_pdf.2020-06-25.json';
+--TO '/grande/snapshots/dump_unextracted_pdf.2020-06-25.json';
TO STDOUT
WITH NULL '';