diff options
author | Bryan Newbold <bnewbold@robocracy.org> | 2018-07-26 01:04:48 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@robocracy.org> | 2018-07-26 01:04:48 -0700 |
commit | 87099999ebf58b31e2fecd1e3b57bf6712f08b76 (patch) | |
tree | 635a15fcac8466e83c49ef732eb3cf0d175efe55 /python | |
parent | 20b3a58bf8dcd0e63ec6cfb8f13ebfb83d83c927 (diff) | |
download | fatcat-87099999ebf58b31e2fecd1e3b57bf6712f08b76.tar.gz fatcat-87099999ebf58b31e2fecd1e3b57bf6712f08b76.zip |
rename python scripts
Diffstat (limited to 'python')
-rw-r--r-- | python/README.md | 2 | ||||
-rw-r--r-- | python/README_import.md | 20 | ||||
-rwxr-xr-x | python/fatcat_import.py (renamed from python/client.py) | 0 | ||||
-rwxr-xr-x | python/fatcat_webface.py (renamed from python/run.py) | 0 |
4 files changed, 11 insertions, 11 deletions
diff --git a/python/README.md b/python/README.md index c7e33f0a..eebbbd9c 100644 --- a/python/README.md +++ b/python/README.md @@ -3,7 +3,7 @@ Use `pipenv` (which you can install with `pip`). - pipenv run run.py + pipenv run fatcat_webface.py Run tests: diff --git a/python/README_import.md b/python/README_import.md index ae9764e6..38c8406f 100644 --- a/python/README_import.md +++ b/python/README_import.md @@ -24,7 +24,7 @@ the others: From CSV file: export LC_ALL=C.UTF-8 - time ./client.py import-issn /srv/datasets/journal_extra_metadata.csv + time ./fatcat_import.py import-issn /srv/datasets/journal_extra_metadata.csv real 2m42.148s user 0m11.148s @@ -36,38 +36,38 @@ Pretty quick, a few minutes. Directly from compressed tarball; takes about 2 hours in production: - tar xf /srv/datasets/public_profiles_API-2.0_2017_10_json.tar.gz -O | jq -c . | grep '"person":' | time parallel -j12 --pipe --round-robin ./client.py import-orcid - + tar xf /srv/datasets/public_profiles_API-2.0_2017_10_json.tar.gz -O | jq -c . | grep '"person":' | time parallel -j12 --pipe --round-robin ./fatcat_import.py import-orcid - After tuning database, `jq` CPU seems to be bottleneck, so, from pre-extracted tarball: tar xf /srv/datasets/public_profiles_API-2.0_2017_10_json.tar.gz -O | jq -c . | rg '"person":' > /srv/datasets/public_profiles_1_2_json.all.json - time parallel --bar --pipepart -j8 -a /srv/datasets/public_profiles_1_2_json.all.json ./client.py import-orcid - + time parallel --bar --pipepart -j8 -a /srv/datasets/public_profiles_1_2_json.all.json ./fatcat_import.py import-orcid - Does not work: - ./client.py import-orcid /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3/0000-0001-5115-8623.json + ./fatcat_import.py import-orcid /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3/0000-0001-5115-8623.json Instead: - cat /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3/0000-0001-5115-8623.json | jq -c . | ./client.py import-orcid - + cat /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3/0000-0001-5115-8623.json | jq -c . | ./fatcat_import.py import-orcid - Or for many files: - find /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3 -iname '*.json' | parallel --bar jq -c . {} | rg '"person":' | ./client.py import-orcid - + find /data/orcid/partial/public_profiles_API-2.0_2017_10_json/3 -iname '*.json' | parallel --bar jq -c . {} | rg '"person":' | ./fatcat_import.py import-orcid - ### ORCID Performance for ~9k files: - (python-B2RYrks8) bnewbold@orithena$ time parallel --pipepart -j4 -a /data/orcid/partial/public_profiles_API-2.0_2017_10_json/all.json ./client.py import-orcid - + (python-B2RYrks8) bnewbold@orithena$ time parallel --pipepart -j4 -a /data/orcid/partial/public_profiles_API-2.0_2017_10_json/all.json ./fatcat_import.py import-orcid - real 0m15.294s user 0m28.112s sys 0m2.408s => 636/second - (python-B2RYrks8) bnewbold@orithena$ time ./client.py import-orcid /data/orcid/partial/public_profiles_API-2.0_2017_10_json/all.json + (python-B2RYrks8) bnewbold@orithena$ time ./fatcat_import.py import-orcid /data/orcid/partial/public_profiles_API-2.0_2017_10_json/all.json real 0m47.268s user 0m2.616s sys 0m0.104s @@ -94,11 +94,11 @@ After some simple database tuning: From compressed: - xzcat /srv/datasets/crossref-works.2018-01-21.json.xz | time parallel -j20 --round-robin --pipe ./client.py import-crossref - /srv/datasets/20180216.ISSN-to-ISSN-L.txt + xzcat /srv/datasets/crossref-works.2018-01-21.json.xz | time parallel -j20 --round-robin --pipe ./fatcat_import.py import-crossref - /srv/datasets/20180216.ISSN-to-ISSN-L.txt ## Manifest - time ./client.py import-manifest /srv/datasets/idents_files_urls.sqlite + time ./fatcat_import.py import-manifest /srv/datasets/idents_files_urls.sqlite [...] Finished a batch; row 284518671 of 9669646 (2942.39%). Total inserted: 6606900 diff --git a/python/client.py b/python/fatcat_import.py index 2804a210..2804a210 100755 --- a/python/client.py +++ b/python/fatcat_import.py diff --git a/python/run.py b/python/fatcat_webface.py index cfddad48..cfddad48 100755 --- a/python/run.py +++ b/python/fatcat_webface.py |