diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-08-05 13:08:10 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-08-05 13:08:10 -0700 |
| commit | 049b94db33de00338ce37e32286c24888fc81fae (patch) | |
| tree | d850a87f1e09fbcf3afc9722f2f7c4c66cfde0a7 | |
| parent | c5409c04ec7f08fbdc059a6813ef3202e995ff36 (diff) | |
| download | sandcrawler-049b94db33de00338ce37e32286c24888fc81fae.tar.gz sandcrawler-049b94db33de00338ce37e32286c24888fc81fae.zip | |
sql stats commands updates
| -rw-r--r-- | sql/stats/README.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/sql/stats/README.md b/sql/stats/README.md index 52642f6..89deec2 100644 --- a/sql/stats/README.md +++ b/sql/stats/README.md @@ -53,7 +53,7 @@ Processed or not: Counts: - SELECT COUNT(DISTINCT fatcat_release) AS unique_releases, COUNT(*) AS total FROM grobid; + SELECT COUNT(*) AS total_files, COUNT(DISTINCT fatcat_release) AS unique_releases FROM grobid; Status? @@ -101,7 +101,7 @@ Results by source: ON ingest_request.base_url = ingest_file_result.base_url AND ingest_request.ingest_type = ingest_file_result.ingest_type AND ingest_file_result.ingest_type IS NOT NULL - GROUP BY ingest_request.ingest_type, ingest_request.link_source ORDER BY attempts DESC LIMIT 25; + GROUP BY ingest_request.ingest_type, ingest_request.link_source ORDER BY attempts DESC LIMIT 35; Ingest result by status: |