diff options
Diffstat (limited to 'sql/dump_unextracted_pdf_petabox.sql')
-rw-r--r-- | sql/dump_unextracted_pdf_petabox.sql | 18 |
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..bb9f162 --- /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 '/srv/sandcrawler/tasks/dump_unextracted_pdf_petabox.2020-07-22.json' +WITH NULL ''; + +ROLLBACK; |