diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 16:31:22 -0700 | 
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 16:31:22 -0700 | 
| commit | 08ae9f4c14feab9f9e77cfca8f9dcb17eb8ee78e (patch) | |
| tree | 99ba040c229906fdf601e5e0b954195d13dc62fe /sql | |
| parent | 155a4c9918cf052bed7b73165a7a9ed965e69c6e (diff) | |
| download | sandcrawler-08ae9f4c14feab9f9e77cfca8f9dcb17eb8ee78e.tar.gz sandcrawler-08ae9f4c14feab9f9e77cfca8f9dcb17eb8ee78e.zip  | |
unextracted PDF job dump command
Diffstat (limited to 'sql')
| -rw-r--r-- | sql/dump_unextracted_pdf.sql | 16 | 
1 files changed, 16 insertions, 0 deletions
diff --git a/sql/dump_unextracted_pdf.sql b/sql/dump_unextracted_pdf.sql new file mode 100644 index 0000000..4d264b9 --- /dev/null +++ b/sql/dump_unextracted_pdf.sql @@ -0,0 +1,16 @@ + +-- Run like: +--   psql sandcrawler < dump_unextracted_pdf.sql > dump_unextracted_pdf.2019-09-23.json + +BEGIN TRANSACTION ISOLATION LEVEL SERIALIZABLE READ ONLY DEFERRABLE; + +COPY ( +  SELECT row_to_json(cdx) +  FROM grobid +  LEFT JOIN cdx ON grobid.sha1hex = cdx.sha1hex +) +-- TO '/grande/snapshots/dump_unextracted_pdf.2020-06-25.json'; +TO STDOUT +WITH NULL ''; + +ROLLBACK;  | 
