index
:
sandcrawler
bnewbold-args
bnewbold-backfill
bnewbold-persist-grobid-errors
bnewbold-refactor-loggging
master
trawler
[no description]
about
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
sql
Mode
Name
Size
-rw-r--r--
README.md
5429
log
stats
plain
d---------
backfill
332
log
stats
plain
-rw-r--r--
dump_file_meta.sql
233
log
stats
plain
-rw-r--r--
dump_regrobid_pdf.sql
460
log
stats
plain
-rw-r--r--
dump_regrobid_pdf_petabox.sql
567
log
stats
plain
-rw-r--r--
dump_reingest_bulk.sql
1494
log
stats
plain
-rw-r--r--
dump_reingest_old.sql
1858
log
stats
plain
-rw-r--r--
dump_reingest_quarterly.sql
2413
log
stats
plain
-rw-r--r--
dump_reingest_spn.sql
1766
log
stats
plain
-rw-r--r--
dump_reingest_terminalstatus.sql
1474
log
stats
plain
-rw-r--r--
dump_reingest_weekly.sql
2103
log
stats
plain
-rw-r--r--
dump_unextracted_pdf.sql
728
log
stats
plain
-rw-r--r--
dump_unextracted_pdf_petabox.sql
506
log
stats
plain
-rw-r--r--
dump_ungrobid_pdf.sql
637
log
stats
plain
-rw-r--r--
dump_ungrobid_pdf_petabox.sql
625
log
stats
plain
-rw-r--r--
dump_unmatched_glutton_pdf.sql
459
log
stats
plain
-rw-r--r--
example.env
62
log
stats
plain
-rw-r--r--
ingest_again.md
9240
log
stats
plain
d---------
ingest_stats
139
log
stats
plain
d---------
migrations
111
log
stats
plain
-rw-r--r--
monitoring_queries.md
8098
log
stats
plain
-rw-r--r--
pdftrio_queries.md
2062
log
stats
plain
-rw-r--r--
random_queries.md
6024
log
stats
plain
-rwxr-xr-x
reingest_bulk.sh
641
log
stats
plain
-rwxr-xr-x
reingest_old.sh
638
log
stats
plain
-rwxr-xr-x
reingest_quarterly.sh
661
log
stats
plain
-rwxr-xr-x
reingest_spn.sh
615
log
stats
plain
-rwxr-xr-x
reingest_terminalstatus_forcerecrawl.sh
697
log
stats
plain
-rwxr-xr-x
reingest_weekly.sh
648
log
stats
plain
l---------
sandcrawler_schema.sql
->
migrations/2019-12-19-060141_init/up.sql
40
log
stats
plain
d---------
stats
868
log
stats
plain
-rw-r--r--
table_sizes.md
851
log
stats
plain