annotate scripts/migration/versions_source_ @ 10:a50cf11e5178

Rewrite LGDataverse completely upgrading to dataverse4.0
author Zoe Hong <zhong@mpiwg-berlin.mpg.de>
date Tue, 08 Sep 2015 17:00:21 +0200
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
10
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
1 #!/usr/bin/perl
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
2
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
3 # TODO:
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
4 # the script still has the namespaces "1902.1" and "10.7910" hard-coded,
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
5 # to identifies the "local" studies.
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
6
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
7 my $url = shift @ARGV;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
8
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
9 use DBI;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
10
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
11 my $username = "xxxxx";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
12 my $password = 'xxxxx';
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
13 my $database = "xxxxx";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
14
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
15 my $dbh = DBI->connect("DBI:Pg:dbname=$database;host=$host",$username,$password);
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
16
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
17 unless ( -d "ddi" )
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
18 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
19 mkdir "ddi";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
20 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
21
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
22 my $sth;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
23
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
24 $sth = $dbh->prepare(qq {SELECT s.id, s.authority, s.studyid, v.alias FROM study s, vdc v WHERE s.owner_id = v.id});
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
25
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
26 $sth->execute();
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
27
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
28 my $sid;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
29
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
30 $studycounter = 0;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
31 $extraversioncounter = 0;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
32 $versioncounter = 0;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
33
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
34 while ( @foo = $sth->fetchrow() )
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
35 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
36 $sid = $foo[0];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
37 $authority = $foo[1];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
38 $studyid = $foo[2];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
39 $dvalias = $foo[3];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
40
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
41 unless ($authority eq "1902.1" || $authority =~/^10\.7910/ ) {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
42 next;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
43 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
44
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
45 unless ( -d "ddi/$dvalias" )
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
46 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
47 mkdir "ddi/$dvalias";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
48 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
49
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
50 my $sth1;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
51
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
52 $sth1 = $dbh->prepare(qq {SELECT versionnumber,versionstate FROM studyversion v WHERE study_id=$sid});
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
53 $sth1->execute();
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
54
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
55 my $vn;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
56
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
57 $localcounter = 0;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
58
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
59 while ( @bar = $sth1->fetchrow() )
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
60 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
61 $vn = $bar[0];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
62 $vstate = $bar[1];
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
63
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
64 if ($vstate eq "RELEASED")
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
65 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
66 print $dvalias . "\t" . $sid . "\t" . $authority . "/" . $studyid . "/export_ddi.xml\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
67 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
68 else
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
69 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
70 print STDERR "executing: wget -O ddi/" . $dvalias . "/" . $sid . "-" . $vn . ".xml '" . $url . "?studyId=" . $sid . "&versionNumber=" . $vn . "'\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
71 system "wget -O ddi/" . $dvalias . "/" . $sid . "-" . $vn . ".xml '" . $url . "?studyId=" . $sid . "&versionNumber=" . $vn . "'\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
72 $versioncounter++;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
73 $localcounter++;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
74 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
75 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
76
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
77 $sth1->finish;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
78 $studycounter++;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
79 $extraversioncounter++ if $localcounter;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
80
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
81 unless ($studycounter % 1000)
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
82 {
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
83 print STDERR "\n" . $studycounter . " studies processed.\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
84 print STDERR $extraversioncounter . " had versions other than released;\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
85 print STDERR "Total " . $versioncounter . " versions processed.\n";
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
86 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
87 }
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
88
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
89 $sth->finish;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
90
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
91 $dbh->disconnect;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
92
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
93 exit 0;
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
94
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
95
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
96
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
97
a50cf11e5178 Rewrite LGDataverse completely upgrading to dataverse4.0
Zoe Hong <zhong@mpiwg-berlin.mpg.de>
parents:
diff changeset
98