diff options
author | Bryan Newbold <bnewbold@archive.org> | 2020-10-21 12:24:13 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2020-10-21 12:24:13 -0700 |
commit | f1936476985231286ad1abc74318cc06e20e2627 (patch) | |
tree | ba51bf5a0c5d7085b2b5fa8ef38a3857d681ad3b /sql | |
parent | 71b8acdc564cc0d8cda9809d4c3cb3d91a4b8e21 (diff) | |
download | sandcrawler-f1936476985231286ad1abc74318cc06e20e2627.tar.gz sandcrawler-f1936476985231286ad1abc74318cc06e20e2627.zip |
sql stats: larger limits (more complete lists)
Diffstat (limited to 'sql')
-rw-r--r-- | sql/stats/README.md | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/sql/stats/README.md b/sql/stats/README.md index 2e9eae5..62e213c 100644 --- a/sql/stats/README.md +++ b/sql/stats/README.md @@ -29,7 +29,7 @@ Counts and total file size: Top mimetypes: - SELECT mimetype, COUNT(*) FROM file_meta GROUP BY mimetype ORDER BY COUNT DESC LIMIT 20; + SELECT mimetype, COUNT(*) FROM file_meta GROUP BY mimetype ORDER BY COUNT DESC LIMIT 30; Missing full metadata: @@ -43,7 +43,7 @@ Total and unique-by-sha1 counts: mimetype counts: - SELECT mimetype, COUNT(*) FROM cdx GROUP BY mimetype ORDER BY COUNT(*) DESC LIMIT 25; + SELECT mimetype, COUNT(*) FROM cdx GROUP BY mimetype ORDER BY COUNT(*) DESC LIMIT 30; ## GROBID @@ -53,11 +53,11 @@ Counts: Status? - SELECT status_code, COUNT(*) FROM grobid GROUP BY status_code ORDER BY COUNT DESC LIMIT 10; + SELECT status_code, COUNT(*) FROM grobid GROUP BY status_code ORDER BY COUNT DESC LIMIT 25; What version used? - SELECT grobid_version, COUNT(*) FROM grobid WHERE status_code = 200 GROUP BY grobid_version ORDER BY COUNT DESC LIMIT 10; + SELECT grobid_version, COUNT(*) FROM grobid WHERE status_code = 200 GROUP BY grobid_version ORDER BY COUNT DESC LIMIT 25; ## Petabox @@ -71,7 +71,7 @@ Requests by source: SELECT ingest_type, link_source, COUNT(*) FROM ingest_request GROUP BY ingest_type, link_source ORDER BY COUNT DESC LIMIT 25; - SELECT ingest_type, link_source, ingest_request_source, COUNT(*) FROM ingest_request GROUP BY ingest_type, link_source, ingest_request_source ORDER BY COUNT DESC LIMIT 25; + SELECT ingest_type, link_source, ingest_request_source, COUNT(*) FROM ingest_request GROUP BY ingest_type, link_source, ingest_request_source ORDER BY COUNT DESC LIMIT 35; Uncrawled requests by source: @@ -82,7 +82,7 @@ Uncrawled requests by source: ON ingest_request.base_url = ingest_file_result.base_url AND ingest_request.ingest_type = ingest_file_result.ingest_type WHERE ingest_file_result.base_url IS NULL - GROUP BY ingest_request.ingest_type, ingest_request.link_source ORDER BY COUNT DESC LIMIT 25; + GROUP BY ingest_request.ingest_type, ingest_request.link_source ORDER BY COUNT DESC LIMIT 35; Results by source: @@ -101,11 +101,11 @@ Results by source: Ingest result by status: - SELECT ingest_type, status, COUNT(*) FROM ingest_file_result GROUP BY ingest_type, status ORDER BY COUNT DESC LIMIT 25; + SELECT ingest_type, status, COUNT(*) FROM ingest_file_result GROUP BY ingest_type, status ORDER BY COUNT DESC LIMIT 50; Failed ingest by terminal status code: - SELECT ingest_type, terminal_status_code, COUNT(*) FROM ingest_file_result WHERE hit = false GROUP BY ingest_type, terminal_status_code ORDER BY COUNT DESC LIMIT 25; + SELECT ingest_type, terminal_status_code, COUNT(*) FROM ingest_file_result WHERE hit = false GROUP BY ingest_type, terminal_status_code ORDER BY COUNT DESC LIMIT 50; ## Fatcat Files |