From 52967e05d2c8febdaa0426634fa987eaf5f58577 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Fri, 1 Feb 2019 15:13:32 -0800 Subject: give sort way more RAM by default --- notes/crawl_cdx_merge.md | 4 ++-- notes/match_filter_enrich.txt | 6 +++--- notes/petabox_ia_metadata.txt | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'notes') diff --git a/notes/crawl_cdx_merge.md b/notes/crawl_cdx_merge.md index 1d744f5..d2cffee 100644 --- a/notes/crawl_cdx_merge.md +++ b/notes/crawl_cdx_merge.md @@ -11,7 +11,7 @@ Run script from scratch repo: Assuming we're just looking at PDFs: - zcat CRAWL-2000.cdx.gz | rg -i pdf | sort -u | gzip > CRAWL-2000.sorted.cdx.gz + zcat CRAWL-2000.cdx.gz | rg -i pdf | sort -S 4G -u | gzip > CRAWL-2000.sorted.cdx.gz ## Old Way @@ -22,7 +22,7 @@ Get all the CDX files and merge/sort: mkdir CRAWL-2000 && cd CRAWL-2000 cat ../CRAWL-2000.items | shuf | parallel --bar -j6 ia download {} {}.cdx.gz ls */*.cdx.gz | parallel --bar -j1 zcat {} > CRAWL-2000.unsorted.cdx - sort -u CRAWL-2000.unsorted.cdx > CRAWL-2000.cdx + sort -S 4G -u CRAWL-2000.unsorted.cdx > CRAWL-2000.cdx wc -l CRAWL-2000.cdx rm CRAWL-2000.unsorted.cdx diff --git a/notes/match_filter_enrich.txt b/notes/match_filter_enrich.txt index 0c9a2c3..0c1f7df 100644 --- a/notes/match_filter_enrich.txt +++ b/notes/match_filter_enrich.txt @@ -9,7 +9,7 @@ somewhere. Reduce down the scored matches to just {sha1, dois}, sorted: - zcat 2018-08-27-2352.17-matchcrossref.tsv.gz | ./filter_scored_matches.py | pv -l | sort > 2018-08-27-2352.17-matchcrossref.filtered.tsv + zcat 2018-08-27-2352.17-matchcrossref.tsv.gz | ./filter_scored_matches.py | pv -l | sort -S 8G > 2018-08-27-2352.17-matchcrossref.filtered.tsv # 5.79M 0:18:54 [5.11k/s] Join/merge the output: @@ -25,7 +25,7 @@ json2} columns from the regular match script. The filter_scored_matches.py doesn't know what to do with those columns at the moment, and the output isn't sorted by slug... need to tweak scripts to fix this. -In the meanwhile, as a work around just take the columns we want and resort: +In the meanwhile, as a work around just take the columns we want and re-sort: export LC_ALL=C - zcat 2018-12-18-2237.09-matchcrossref.insertable.tsv.gz | cut -f2-5 | sort -u | gzip > 2018-12-18-2237.09-matchcrossref.tsv.gz + zcat 2018-12-18-2237.09-matchcrossref.insertable.tsv.gz | cut -f2-5 | sort -S 8G -u | gzip > 2018-12-18-2237.09-matchcrossref.tsv.gz diff --git a/notes/petabox_ia_metadata.txt b/notes/petabox_ia_metadata.txt index df3bdc1..3a99805 100644 --- a/notes/petabox_ia_metadata.txt +++ b/notes/petabox_ia_metadata.txt @@ -14,7 +14,7 @@ Commands: ia-mine metamgr-journals-loose.20181218.items > journals.20181218.json export LC_ALL=C - cat journals-ia.20181218.json | jq 'select(.files) | .files[] | select(.format == "Text PDF") | .sha1' -r | sort -u > journals-ia.20181218.pdf-sha1.tsv + cat journals-ia.20181218.json | jq 'select(.files) | .files[] | select(.format == "Text PDF") | .sha1' -r | sort -S 4G -u > journals-ia.20181218.pdf-sha1.tsv Size/results: -- cgit v1.2.3