aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2020-06-25 18:18:39 -0700
committerBryan Newbold <bnewbold@archive.org>2020-06-25 18:18:39 -0700
commitb8db6fb555b8d29900015d9829bce1c372b8b1b9 (patch)
treecec4bcd11f1feffe0cc7e853eab4f7325ec0ce08
parent6f382a4c07ccac68896f75d55835a8876981edbd (diff)
downloadsandcrawler-b8db6fb555b8d29900015d9829bce1c372b8b1b9.tar.gz
sandcrawler-b8db6fb555b8d29900015d9829bce1c372b8b1b9.zip
commented special modes for 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 '';