From: Don Armstrong <don@donarmstrong.com>
Date: Tue, 13 Dec 2011 22:37:07 +0000 (-0800)
Subject:  * use rsync instead of lftp to download schemas and data
X-Git-Url: https://git.donarmstrong.com/?p=don.git;a=commitdiff_plain;h=3fd42e115725d33c75509e2fb9bbf03745ed6776

 * use rsync instead of lftp to download schemas and data
---

diff --git a/genetics/dbsnp_mirror.mdwn b/genetics/dbsnp_mirror.mdwn
index addc10e..9ffa841 100644
--- a/genetics/dbsnp_mirror.mdwn
+++ b/genetics/dbsnp_mirror.mdwn
@@ -8,10 +8,9 @@ download the databases and schemas for the current release of dbsnp.
 For humans, this is currently ≈60G, and takes a while to retrieve
 (about 24 hours or so).
 
-    for a in {organism,shared}_{data,schema}; do 
-        lftp -c "open ftp.ncbi.nlm.nih.gov; cd /snp/organisms/human_9606/database/; mirror $a";
-    done;
-
+   rsync -rvP --include 'organism_*' --exclude '**' rsync://ftp.ncbi.nlm.nih.gov/snp/organisms/human_9606/database/ .
+   rsync -rvP rsync://ftp.ncbi.nlm.nih.gov/snp/database/shared_data .
+   rsync -rvP rsync://ftp.ncbi.nlm.nih.gov/snp/database/shared_schema .
 
 Preparing SQL Schemas
 ---------------------