From fa3101e506ffbe9947880cbe679edf90b4e71940 Mon Sep 17 00:00:00 2001
From: Ian Longden <ianl@sanger.ac.uk>
Date: Tue, 2 Sep 2008 10:02:10 +0000
Subject: [PATCH] -verbose option added which also need to change run
subroutine to get the file/s via a ref to and array then an array
---
.../XrefParser/AedesGenBankParser.pm | 15 +-
.../xref_mapping/XrefParser/AgilentParser.pm | 18 +-
.../XrefParser/AnophelesSymbolParser.pm | 16 +-
.../xref_mapping/XrefParser/BaseParser.pm | 249 ++++++++++--------
.../xref_mapping/XrefParser/CeleraParser.pm | 15 +-
.../xref_mapping/XrefParser/CodelinkParser.pm | 16 +-
.../xref_mapping/XrefParser/DBASSParser.pm | 42 ++-
.../xref_mapping/XrefParser/DirectParser.pm | 2 +-
.../XrefParser/EntrezGeneParser.pm | 15 +-
.../xref_mapping/XrefParser/FastaParser.pm | 17 +-
.../xref_mapping/XrefParser/FlybaseParser.pm | 23 +-
.../XrefParser/Flybase_dmel_GFFv3_Parser.pm | 27 +-
.../xref_mapping/XrefParser/GOParser.pm | 25 +-
.../xref_mapping/XrefParser/HGNCParser.pm | 43 +--
.../xref_mapping/XrefParser/HPAParser.pm | 28 +-
.../xref_mapping/XrefParser/IPIParser.pm | 16 +-
.../xref_mapping/XrefParser/IlluminaParser.pm | 16 +-
.../XrefParser/IlluminaWGParser.pm | 17 +-
.../XrefParser/InterproGoParser.pm | 14 +-
.../xref_mapping/XrefParser/InterproParser.pm | 47 ++--
.../xref_mapping/XrefParser/JGI_Parser.pm | 19 +-
.../xref_mapping/XrefParser/MGDParser.pm | 8 +-
.../xref_mapping/XrefParser/MIMParser.pm | 14 +-
.../xref_mapping/XrefParser/RGDParser.pm | 10 +-
.../XrefParser/RefSeqGPFFParser.pm | 30 ++-
.../xref_mapping/XrefParser/RefSeqParser.pm | 21 +-
.../xref_mapping/XrefParser/SGDParser.pm | 14 +-
.../xref_mapping/XrefParser/SegmentParser.pm | 13 +-
.../xref_mapping/XrefParser/UCSCParser.pm | 11 +-
.../xref_mapping/XrefParser/UniGeneParser.pm | 22 +-
.../xref_mapping/XrefParser/UniProtParser.pm | 44 ++--
.../UniProtParser_descriptions_only.pm | 37 +--
.../XrefParser/UniProtVarSplicParser.pm | 20 +-
.../xref_mapping/XrefParser/VbDirectParser.pm | 14 +-
.../xref_mapping/XrefParser/VbGFF3Parser.pm | 16 +-
.../xref_mapping/XrefParser/VegaParser.pm | 32 ++-
.../XrefParser/Vega_TranParser.pm | 6 +-
.../XrefParser/WilsonAffyParser.pm | 29 +-
.../xref_mapping/XrefParser/WormPepParser.pm | 16 +-
.../WormbaseDatabaseStableIDParser.pm | 5 +-
.../XrefParser/XenopusJamboreeParser.pm | 15 +-
.../xref_mapping/XrefParser/ZFINParser.pm | 30 ++-
.../xref_mapping/XrefParser/ncRNAParser.pm | 8 +-
43 files changed, 668 insertions(+), 427 deletions(-)
diff --git a/misc-scripts/xref_mapping/XrefParser/AedesGenBankParser.pm b/misc-scripts/xref_mapping/XrefParser/AedesGenBankParser.pm
index ed24106d2c..3699a7e221 100644
--- a/misc-scripts/xref_mapping/XrefParser/AedesGenBankParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/AedesGenBankParser.pm
@@ -13,7 +13,16 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
+
my $cpt = 0 ;
next if (/^File:/); # skip header
@@ -38,7 +47,7 @@ sub run {
if ($header eq "") {
$header = "Aedes_GenBank".$cpt ;
- print STDERR "One sequence with a random name ... \n" ;
+ print STDERR "One sequence with a random name ... \n" if($verbose);
$cpt++ ;
}
@@ -74,7 +83,7 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " AedesGenBank xrefs succesfully parsed\n";
+ print scalar(@xrefs) . " AedesGenBank xrefs succesfully parsed\n" if($verbose);
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
diff --git a/misc-scripts/xref_mapping/XrefParser/AgilentParser.pm b/misc-scripts/xref_mapping/XrefParser/AgilentParser.pm
index 4fdbee3847..3ee69d8651 100644
--- a/misc-scripts/xref_mapping/XrefParser/AgilentParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/AgilentParser.pm
@@ -13,16 +13,22 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
- my @xrefs;
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
-# local $/ = "\n>";
+ my @xrefs;
my $ag_io = $self->get_filehandle($file);
if ( !defined $ag_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -59,11 +65,11 @@ sub run {
$ag_io->close();
- print scalar(@xrefs) . " Agilent xrefs succesfully parsed\n";
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
+ print scalar(@xrefs) . " Agilent xrefs succesfully parsed\n" if($verbose);
+
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/AnophelesSymbolParser.pm b/misc-scripts/xref_mapping/XrefParser/AnophelesSymbolParser.pm
index 76294ccfa7..59e24b7f3e 100644
--- a/misc-scripts/xref_mapping/XrefParser/AnophelesSymbolParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/AnophelesSymbolParser.pm
@@ -14,7 +14,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
next if (/^File:/); # skip header
@@ -25,7 +33,7 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -56,11 +64,11 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " AnophelesSymbol xrefs succesfully parsed\n";
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
+ print scalar(@xrefs) . " AnophelesSymbol xrefs succesfully parsed\n" if($verbose);
+
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/BaseParser.pm b/misc-scripts/xref_mapping/XrefParser/BaseParser.pm
index e7723647f3..93383a7075 100644
--- a/misc-scripts/xref_mapping/XrefParser/BaseParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/BaseParser.pm
@@ -38,7 +38,8 @@ my %xref_dependent_mapped;
my ( $host, $port, $dbname, $user,
$pass, $create, $release, $cleanup,
$deletedownloaded, $drop_db, $checkdownload, $dl_path,
- $unzip, $stats );
+ $unzip, $stats, $verbose);
+
# --------------------------------------------------------------------------------
# Get info about files to be parsed from the database
@@ -51,7 +52,7 @@ sub run {
my $sourcesr, $checkdownload, $create,
$release, $cleanup, $drop_db,
$deletedownloaded, $dl_path, my $notsourcesr,
- $unzip, $stats
+ $unzip, $stats, $verbose
) = @_;
$base_dir = $dl_path if $dl_path;
@@ -140,7 +141,7 @@ sub run {
while ( my @row = $sth->fetchrow_array() ) {
- print '-' x 4, "{ $name }", '-' x ( 72 - length($name) ), "\n";
+ print '-' x 4, "{ $name }", '-' x ( 72 - length($name) ), "\n" if ($verbose);
my $cs;
my $file_cs = "";
@@ -176,21 +177,32 @@ sub run {
# Database parsing
if ( $file =~ /^mysql:/i ) {
$dsn = $file;
- print "Parsing $dsn with $parser\n";
+ print "Parsing $dsn with $parser\n" if ($verbose);
eval "require XrefParser::$parser";
my $new = "XrefParser::$parser"->new();
if (
$new->run( $dsn, $source_id, $species_id,
- $name, undef ) )
+ $name, undef, $verbose ) )
{
++$summary{$name}->{$parser};
}
next;
}
-
-
- if ( $unzip && ( $file =~ /\.(gz|Z)$/ ) ) {
- printf( "Uncompressing '%s' using 'gunzip'\n", $file );
+ if ( $file =~ /^script:/i ) {
+ print "Parsing $file with $parser\n" if ($verbose);
+ eval "require XrefParser::$parser";
+ my $new = "XrefParser::$parser"->new();
+ if (
+ $new->run_script( $file, $source_id, $species_id, $verbose ) )
+ {
+ ++$summary{$name}->{$parser};
+ }
+ next;
+ }
+
+
+ if ( $unzip && ( $file =~ /\.(gz|Z)$/ ) ) {
+ printf( "Uncompressing '%s' using 'gunzip'\n", $file ) if ($verbose);
system( "gunzip", "-f", $file );
}
if ($unzip) { $file =~ s/\.(gz|Z)$// }
@@ -199,7 +211,7 @@ sub run {
# check file size as some .SPC files can be of zero length
if ( !defined( $cs = md5sum($file) ) ) {
- printf( "Download '%s'\n", $file );
+ printf( "Download '%s'\n", $file ) if($verbose);
++$summary{$name}->{$parser};
} else {
$file_cs .= ':' . $cs;
@@ -209,7 +221,7 @@ sub run {
if ( -s $file ) {
$parse = 1;
print "Checksum for '$file' does not match, "
- . "will parse...\n";
+ . "will parse...\n" if ($verbose);
# Files from sources "Uniprot/SWISSPROT" and
# "Uniprot/SPTREMBL" are all parsed with the
@@ -223,7 +235,7 @@ sub run {
$empty = 1;
printf(
"The file '%s' has zero length, skipping\n",
- $file );
+ $file ) if ($verbose);
}
}
} ## end else [ if ( !defined( $cs = md5sum...
@@ -237,7 +249,7 @@ sub run {
if ( $parse and @files_to_parse and defined $file_cs ) {
print "Parsing '"
. join( "', '", @files_to_parse )
- . "' with $parser\n";
+ . "' with $parser\n" if ($verbose);
eval "require XrefParser::$parser";
$@ && warn( "[ERROR] Cannot require $parser: $@" );
@@ -247,7 +259,7 @@ sub run {
# Run with $release_url.
if (
$new->run( $source_id, $species_id,
- @files_to_parse, $release_url ) )
+ \@files_to_parse, $release_url, $verbose ) )
{
++$summary{$name}->{$parser};
}
@@ -255,7 +267,7 @@ sub run {
# Run without $release_url.
if (
$new->run( $source_id, $species_id,
- @files_to_parse ) )
+ \@files_to_parse, undef, $verbose ) )
{
++$summary{$name}->{$parser};
}
@@ -273,12 +285,12 @@ sub run {
} elsif ( !$dsn && !$empty && @files_to_parse ) {
print( "Ignoring '"
. join( "', '", @files_to_parse )
- . "' as checksums match\n" );
+ . "' as checksums match\n" ) if ($verbose);
}
if ($cleanup) {
foreach my $file (@files_to_parse) {
- printf( "Deleting '%s'\n", $file );
+ printf( "Deleting '%s'\n", $file ) if($verbose);
unlink($file);
}
}
@@ -410,7 +422,7 @@ sub run {
print join("\t",@{$sum_line{$sum_name}})."\n";
}
- }
+ } # if ($stats)
} ## end while ( my @row = $sth->fetchrow_array...
@@ -418,20 +430,21 @@ sub run {
print "\n", '=' x 80, "\n";
print "Summary of status\n";
print '=' x 80, "\n";
-
+
+
foreach my $source_name ( sort keys %summary ) {
- foreach my $parser_name ( keys %{ $summary{$source_name} } ) {
- printf( "%30s %-20s\t%s\n",
- $source_name,
- $parser_name, (
- defined $summary{$source_name}->{$parser_name}
- && $summary{$source_name}->{$parser_name}
- ? 'FAILED'
- : 'OKAY'
- ) );
- }
+ foreach my $parser_name ( keys %{ $summary{$source_name} } ) {
+ printf( "%30s %-20s\t%s\n",
+ $source_name,
+ $parser_name, (
+ defined $summary{$source_name}->{$parser_name}
+ && $summary{$source_name}->{$parser_name}
+ ? 'FAILED'
+ : 'OKAY'
+ ) );
+ }
}
-
+
if($stats){
my %sum_line;
@@ -555,7 +568,11 @@ sub fetch_files {
# Change old-style 'LOCAL:' URIs into 'file:'.
$user_uri =~ s#^LOCAL:#file:#i;
my $uri = URI->new($user_uri);
- if ( $uri->scheme() eq 'file' ) {
+
+# print "\n*******$user_uri\n*********\n";
+ if ( $uri->scheme() eq 'script'){
+ push( @processed_files, $user_uri );
+ }elsif ( $uri->scheme() eq 'file' ) {
# Deal with local files.
my @local_files;
@@ -574,7 +591,7 @@ sub fetch_files {
catfile( $dest_dir, basename( $uri->path() ) );
if ( $deletedownloaded && -f $file_path ) {
- printf( "Deleting '%s'\n", $file_path );
+ printf( "Deleting '%s'\n", $file_path ) if ($verbose);
unlink($file_path);
}
@@ -584,12 +601,12 @@ sub fetch_files {
# used (for globbing FTP URIs, we always need to connect
# to a FTP site to see what files are there).
- printf( "File '%s' already exists\n", $file_path );
+ printf( "File '%s' already exists\n", $file_path ) if ($verbose);
push( @processed_files, $file_path );
next;
}
- printf( "Connecting to FTP host '%s'\n", $uri->host() );
+ printf( "Connecting to FTP host '%s'\n", $uri->host() ) if ($verbose);
my $ftp = Net::FTP->new( $uri->host(), 'Debug' => 0 );
if ( !defined($ftp) ) {
@@ -624,17 +641,17 @@ sub fetch_files {
catfile( $dest_dir, basename($remote_file) );
if ( $deletedownloaded && -f $file_path ) {
- printf( "Deleting '%s'\n", $file_path );
+ printf( "Deleting '%s'\n", $file_path ) if($verbose);
unlink($file_path);
}
if ( $checkdownload && -f $file_path ) {
- printf( "File '%s' already exists\n", $file_path );
+ printf( "File '%s' already exists\n", $file_path ) if ($verbose);
} else {
if ( !-d dirname($file_path) ) {
printf( "Creating directory '%s'\n",
- dirname($file_path) );
+ dirname($file_path) ) if($verbose);
if ( !mkdir( dirname($file_path) ) ) {
printf(
"==> Can not create directory '%s': %s",
@@ -645,8 +662,8 @@ sub fetch_files {
printf( "Fetching '%s' (size = %s)\n",
$remote_file,
- $ftp->size($remote_file) || '(unknown)' );
- printf( "Local file is '%s'\n", $file_path );
+ $ftp->size($remote_file) || '(unknown)' ) if ($verbose);
+ printf( "Local file is '%s'\n", $file_path ) if($verbose);
if ( !$ftp->get( $remote_file, $file_path ) ) {
printf( "==> Could not get '%s': %s\n",
@@ -667,7 +684,7 @@ sub fetch_files {
catfile( $dest_dir, basename( $uri->path() ) );
if ( $deletedownloaded && -f $file_path ) {
- printf( "Deleting '%s'\n", $file_path );
+ printf( "Deleting '%s'\n", $file_path ) if($verbose);
unlink($file_path);
}
@@ -675,14 +692,14 @@ sub fetch_files {
# The file is already there, no need to connect to a
# HTTP server.
- printf( "File '%s' already exists\n", $file_path );
+ printf( "File '%s' already exists\n", $file_path ) if ($verbose);
push( @processed_files, $file_path );
next;
}
if ( !-d dirname($file_path) ) {
printf( "Creating directory '%s'\n",
- dirname($file_path) );
+ dirname($file_path) ) if($verbose);
if ( !mkdir( dirname($file_path) ) ) {
printf( "==> Can not create directory '%s': %s",
dirname($file_path), $! );
@@ -690,14 +707,14 @@ sub fetch_files {
}
}
- printf( "Connecting to HTTP host '%s'\n", $uri->host() );
- printf( "Fetching '%s'\n", $uri->path() );
+ printf( "Connecting to HTTP host '%s'\n", $uri->host() ) if($verbose);
+ printf( "Fetching '%s'\n", $uri->path() ) if($verbose);
if ( $checkdownload && -f $file_path ) {
- printf( "File '%s' already exists\n", $file_path );
+ printf( "File '%s' already exists\n", $file_path ) if($verbose);
} else {
- printf( "Local file is '%s'\n", $file_path );
+ printf( "Local file is '%s'\n", $file_path ) if($verbose);
my $ua = LWP::UserAgent->new();
$ua->env_proxy();
@@ -766,7 +783,7 @@ sub get_filehandle
if ( !defined $io ) { return undef }
- print "Reading from '$file_name'...\n";
+ print "Reading from '$file_name'...\n" if($verbose);
return $io;
}
@@ -787,7 +804,7 @@ sub new
sub get_source_id_for_filename {
my ($self, $file) = @_;
- print STDERR "FILE $file\n" ;
+ print "FILE $file\n" if($verbose) ;
my $sql = "SELECT s.source_id FROM source s, source_url su WHERE su.source_id=s.source_id AND su.url LIKE '%/" . $file . "%'";
my $sth = dbi()->prepare($sql);
$sth->execute();
@@ -1065,7 +1082,7 @@ sub get_existing_mappings {
#print "mgi_to_uniprot{" . $row[1] . "} = " . $row[2] . "\n";
}
- print "Got " . scalar(keys(%mappings)) . " $from_source_name -> $to_source_name mappings\n";
+ print "Got " . scalar(keys(%mappings)) . " $from_source_name -> $to_source_name mappings\n" if($verbose);
return \%mappings;
@@ -1078,7 +1095,7 @@ sub upload_xref_object_graphs {
my ($self, $rxrefs) = @_;
my $dbi = dbi();
- print "count = ".$#$rxrefs."\n";
+ print "count = ".$#$rxrefs."\n" if($verbose);
if ($#$rxrefs > -1) {
@@ -1086,7 +1103,7 @@ sub upload_xref_object_graphs {
# $self->delete_by_source($rxrefs);
# upload new ones
- print "Uploading xrefs\n";
+ print "Uploading xrefs\n" if($verbose);
my $xref_sth = $dbi->prepare("INSERT INTO xref (accession,version,label,description,source_id,species_id) VALUES(?,?,?,?,?,?)");
my $pri_insert_sth = $dbi->prepare("INSERT INTO primary_xref VALUES(?,?,?,?)");
my $pri_update_sth = $dbi->prepare("UPDATE primary_xref SET sequence=? WHERE xref_id=?");
@@ -1106,30 +1123,30 @@ sub upload_xref_object_graphs {
return undef;
}
# Create entry in xref table and note ID
- if(! $xref_sth->execute($xref->{ACCESSION},
+ if(! $xref_sth->execute($xref->{ACCESSION},
$xref->{VERSION} || 0,
$xref->{LABEL},
$xref->{DESCRIPTION},
$xref->{SOURCE_ID},
$xref->{SPECIES_ID})){
- if(!defined($xref->{SOURCE_ID})){
- print "your xref: $xref->{ACCESSION} does not have a source-id\n";
- return undef;
- }
- $xref_id = insert_or_select($xref_sth, $dbi->err, $xref->{ACCESSION}, $xref->{SOURCE_ID}, $xref->{SPECIES_ID});
- $xref_update_label_sth->execute($xref->{LABEL},$xref_id) if (defined($xref->{LABEL}));
- $xref_update_descr_sth->execute($xref->{DESCRIPTION},$xref_id,) if (defined($xref->{DESCRIPTION}));
- }
- else{
- $xref_id = insert_or_select($xref_sth, $dbi->err, $xref->{ACCESSION}, $xref->{SOURCE_ID}, $xref->{SPECIES_ID});
- }
-
+ if(!defined($xref->{SOURCE_ID})){
+ print "your xref: $xref->{ACCESSION} does not have a source-id\n";
+ return undef;
+ }
+ $xref_id = $self->insert_or_select($xref_sth, $dbi->err, $xref->{ACCESSION}, $xref->{SOURCE_ID}, $xref->{SPECIES_ID});
+ $xref_update_label_sth->execute($xref->{LABEL},$xref_id) if (defined($xref->{LABEL}));
+ $xref_update_descr_sth->execute($xref->{DESCRIPTION},$xref_id,) if (defined($xref->{DESCRIPTION}));
+ }
+ else{
+ $xref_id = $self->insert_or_select($xref_sth, $dbi->err, $xref->{ACCESSION}, $xref->{SOURCE_ID}, $xref->{SPECIES_ID});
+ }
+
# create entry in primary_xref table with sequence; if this is a "cumulative"
- # entry it may already exist, and require an UPDATE rather than an INSERT
+ # entry it may already exist, and require an UPDATE rather than an INSERT
if(defined($xref->{SEQUENCE})){
if(!(defined($xref_id) and $xref_id)){
- print STDERR "xref_id is not set for :\n$xref->{ACCESSION}\n$xref->{LABEL}\n$xref->{DESCRIPTION}\n$xref->{SOURCE_ID}\n";
+ print STDERR "xref_id is not set for :\n$xref->{ACCESSION}\n$xref->{LABEL}\n$xref->{DESCRIPTION}\n$xref->{SOURCE_ID}\n$xref->{SPECIES_ID}\n";
}
if ( primary_xref_id_exists($xref_id) ) {
$pri_update_sth->execute( $xref->{SEQUENCE}, $xref_id )
@@ -1161,7 +1178,7 @@ sub upload_xref_object_graphs {
$dep{SOURCE_ID},
$xref->{SPECIES_ID});
- my $dep_xref_id = insert_or_select($xref_sth, $dbi->err, $dep{ACCESSION}, $dep{SOURCE_ID}, $xref->{SPECIES_ID});
+ my $dep_xref_id = $self->insert_or_select($xref_sth, $dbi->err, $dep{ACCESSION}, $dep{SOURCE_ID}, $xref->{SPECIES_ID});
if($dbi->err){
print STDERR "dbi\t$dbi->err \n$dep{ACCESSION} \n $dep{SOURCE_ID} \n";
@@ -1194,8 +1211,8 @@ sub upload_xref_object_graphs {
sub upload_direct_xrefs{
my ($self, $direct_xref) = @_;
for my $dr(@$direct_xref) {
- # print "having now direct-XREF : $dr->{ENSEMBL_STABLE_ID} \n" ;
- my $general_xref_id = get_xref_id_by_accession_and_source($dr->{ACCESSION},$dr->{SOURCE_ID});
+# print "having now direct-XREF : ".$dr->{ENSEMBL_STABLE_ID}."\t".$dr->{SPECIES_ID}." \n" ;
+ my $general_xref_id = get_xref($dr->{ACCESSION},$dr->{SOURCE_ID},$dr->{SPECIES_ID});
if ($general_xref_id){
# print "direct_xref:\n$general_xref_id\n$dr->{ENSEMBL_STABLE_ID}\n$dr->{ENSEMBL_TYPE}\t$dr->{LINKAGE_XREF}\n\n";
$self->add_direct_xref($general_xref_id, $dr->{ENSEMBL_STABLE_ID},$dr->{ENSEMBL_TYPE},$dr->{LINKAGE_XREF});
@@ -1387,6 +1404,28 @@ sub update_source
}
+# --------------------------------------------------------------------------------
+sub dbi2{
+
+ my $self = shift;
+ my ($host, $port, $user, $dbname, $pass) = @_;
+ my $dbi2;
+
+ if ( !defined $dbi2 || !$dbi2->ping() ) {
+ my $connect_string =
+ sprintf( "dbi:mysql:host=%s;port=%s;database=%s",
+ $host, $port, $dbname );
+
+ $dbi2 =
+ DBI->connect( $connect_string, $user, $pass,
+ { 'RaiseError' => 1 } )
+ or croak( "Can't connect to database: " . $DBI::errstr );
+ $dbi2->{'mysql_auto_reconnect'} = 1; # Reconnect on timeout
+ }
+
+ return $dbi2;
+}
+
# --------------------------------------------------------------------------------
sub dbi
@@ -1432,7 +1471,7 @@ sub md5sum
# --------------------------------------------------------------------------------
-sub get_xref_id_by_accession_and_source {
+sub get_xref_id_by_accession_and_source_OLD {
my ($acc, $source_id, $species_id ) = @_;
@@ -1460,15 +1499,14 @@ SELECT xref_id FROM xref WHERE accession=? AND source_id=?';
sub insert_or_select {
- my ($sth, $error, $acc, $source, $species) = @_;
+ my ($self, $sth, $error, $acc, $source, $species) = @_;
my $id;
# TODO - check for specific error code rather than for just any error
if ($error) {
- $id = get_xref_id_by_accession_and_source($acc, $source, $species);
-# print STDERR "Got existing xref id " . $id . " for " . $acc . " " . $source . "\n";
+ $id = $self->get_xref($acc, $source, $species);
} else {
@@ -1535,17 +1573,17 @@ sub delete_by_source {
# now delete them
foreach my $source (keys %source_ids) {
- print "Deleting pairs with source ID $source \n";
+ print "Deleting pairs with source ID $source \n" if($verbose);
$pairs_sth->execute($source);
- print "Deleting direct xrefs with source ID $source \n";
+ print "Deleting direct xrefs with source ID $source \n" if($verbose);
$direct_sth->execute($source);
- print "Deleting synonyms of xrefs with source ID $source \n";
+ print "Deleting synonyms of xrefs with source ID $source \n" if($verbose);
$syn_sth->execute($source);
- print "Deleting dependent xrefs of xrefs with source ID $source \n";
+ print "Deleting dependent xrefs of xrefs with source ID $source \n" if($verbose);
$dep_sth->execute($source);
- print "Deleting primary xrefs with source ID $source \n";
+ print "Deleting primary xrefs with source ID $source \n" if($verbose);
# $p_xref_sth->execute($source);
- print "Deleting xrefs with source ID $source \n";
+ print "Deleting xrefs with source ID $source \n" if($verbose);
$xref_sth->execute($source);
}
@@ -1569,7 +1607,7 @@ sub validate_sources {
my $rv = $sth->execute(lc($source));
if ( $rv > 0 ) {
- print "Source $source is valid\n";
+ print "Source $source is valid\n" if($verbose);
} else {
print "\nSource $source is not valid; valid sources are:\n";
show_valid_sources();
@@ -1603,18 +1641,19 @@ sub validate_species {
my @species_ids;
my $dbi = dbi();
- my $sth = $dbi->prepare("SELECT species_id, name FROM species WHERE LOWER(name)=? OR LOWER(aliases) LIKE ?");
+ my $sth = $dbi->prepare("SELECT species_id, name FROM species WHERE LOWER(name)=? OR LOWER(aliases) REGEXP ?");
my ($species_id, $species_name);
foreach my $sp (@species) {
- $sth->execute(lc($sp), "%" . lc($sp) . "%");
+# $sth->execute(lc($sp), "%" . lc($sp) . "%"); # no longer allow % as this generates tomany possible errors
+ $sth->execute(lc($sp), "^".lc($sp).",|[ ]".lc($sp)."[,]|^".lc($sp)."\$|[,] ".lc($sp)."\$" );
$sth->bind_columns(\$species_id, \$species_name);
if (my @row = $sth->fetchrow_array()) {
- print "Species $sp is valid (name = " . $species_name . ", ID = " . $species_id . ")\n";
+ print "Species $sp is valid (name = " . $species_name . ", ID = " . $species_id . ")\n" if($verbose);
push @species_ids, $species_id;
} else {
- print "Species $sp is not valid; valid species are:\n";
+ print STDERR "Species $sp is not valid; valid species are:\n";
show_valid_species();
exit(1);
}
@@ -1631,7 +1670,7 @@ sub show_valid_species() {
$sth->execute();
while (my @row = $sth->fetchrow_array()) {
- print $row[0] . " (aliases: " . $row[1] . ")\n";
+ print STDERR $row[0] . " (aliases: " . $row[1] . ")\n";
}
}
@@ -1669,14 +1708,14 @@ sub get_direct_xref{
sub get_xref{
- my ($self,$acc,$source) = @_;
+ my ($self,$acc,$source, $species_id) = @_;
if(!defined($get_xref_sth)){
- my $sql = "select xref_id from xref where accession = ? and source_id = ?";
+ my $sql = "select xref_id from xref where accession = ? and source_id = ? and species_id = ?";
$get_xref_sth = $dbi->prepare($sql);
}
- $get_xref_sth->execute( $acc, $source ) or croak( $dbi->errstr() );
+ $get_xref_sth->execute( $acc, $source, $species_id ) or croak( $dbi->errstr() );
if(my @row = $get_xref_sth->fetchrow_array()) {
return $row[0];
}
@@ -1688,6 +1727,10 @@ sub add_xref {
$species_id )
= @_;
+ my $xref_id = $self->get_xref($acc,$source_id, $species_id);
+ if(defined($xref_id)){
+ return $xref_id;
+ }
if ( !defined($add_xref_sth) ) {
$add_xref_sth =
dbi->prepare( "INSERT INTO xref "
@@ -1733,14 +1776,14 @@ VALUES
}
- my $direct_id = $self->get_xref($acc, $source_id);
+ my $direct_id = $self->get_xref($acc, $source_id, $species_id);
if(!defined($direct_id)){
$add_xref_sth->execute(
$acc, $version || 0, $label,
$description, $source_id, $species_id
) or croak("$acc\t$label\t\t$source_id\t$species_id\n");
}
- $direct_id = $self->get_xref($acc, $source_id);
+ $direct_id = $self->get_xref($acc, $source_id, $species_id);
$self->add_direct_xref($direct_id, $direct_xref, $type, "");
}
@@ -1772,14 +1815,14 @@ VALUES
(?,?,?,?)");
}
- my $dependent_id = $self->get_xref($acc, $source_id);
+ my $dependent_id = $self->get_xref($acc, $source_id, $species_id);
if(!defined($dependent_id)){
$add_xref_sth->execute(
$acc, $version || 0, $label,
$description, $source_id, $species_id
) or croak("$acc\t$label\t\t$source_id\t$species_id\n");
}
- $dependent_id = $self->get_xref($acc, $source_id);
+ $dependent_id = $self->get_xref($acc, $source_id, $species_id);
if(!defined($dependent_id)){
croak("$acc\t$label\t\t$source_id\t$species_id\n");
}
@@ -1793,14 +1836,14 @@ VALUES
}
sub add_to_syn_for_mult_sources{
- my ($self, $acc, $sources, $syn) = @_;
+ my ($self, $acc, $sources, $syn, $species_id) = @_;
if(!defined($add_synonym_sth)){
$add_synonym_sth = $dbi->prepare("INSERT INTO synonym VALUES(?,?)");
}
my $found =0;
foreach my $source_id (@$sources){
- my $xref_id = $self->get_xref($acc, $source_id);
+ my $xref_id = $self->get_xref($acc, $source_id, $species_id);
if(defined($xref_id)){
$add_synonym_sth->execute( $xref_id, $syn )
or croak( $dbi->errstr() . "\n $xref_id\n $syn\n" );
@@ -1816,19 +1859,19 @@ sub add_to_syn_for_mult_sources{
sub add_to_syn{
- my ($self, $acc, $source_id, $syn) = @_;
+ my ($self, $acc, $source_id, $syn, $species_id) = @_;
if(!defined($add_synonym_sth)){
$add_synonym_sth = $dbi->prepare("INSERT INTO synonym VALUES(?,?)");
}
- my $xref_id = $self->get_xref($acc, $source_id);
+ my $xref_id = $self->get_xref($acc, $source_id, $species_id);
if(defined($xref_id)){
$add_synonym_sth->execute( $xref_id, $syn )
or croak( $dbi->errstr() . "\n $xref_id\n $syn\n" );
}
else {
croak( "Could not find acc $acc in "
- . "xref table source = $source_id\n" );
+ . "xref table source = $source_id of species $species_id\n" );
}
}
@@ -1910,7 +1953,7 @@ sub create {
$ini_file, $metadata_file );
if ( system($cmd) == 0 ) {
- print("==> Done.\n");
+ print("==> Done.\n") if($verbose);
} else {
if ( $? == -1 ) {
croak("Failed to execute: $!\n");
@@ -1935,7 +1978,7 @@ sub create {
if ( $drop_db ) {
$dbh->do( "DROP DATABASE $dbname" );
- print "Database $dbname dropped\n" ;
+ print "Database $dbname dropped\n" if($verbose) ;
}
if ( $create && !$drop_db ) {
@@ -1944,7 +1987,7 @@ sub create {
chomp $p;
if ($p eq "yes") {
$dbh->do( "DROP DATABASE $dbname" );
- print "Removed existing database $dbname\n";
+ print "Removed existing database $dbname\n" if($verbose);
} else {
print "$dbname NOT removed\n";
exit(1);
@@ -1959,7 +2002,7 @@ sub create {
my $table_file = catfile( $sql_dir, 'sql', 'table.sql' );
- printf( "Creating %s from %s\n", $dbname, $table_file );
+ printf( "Creating %s from %s\n", $dbname, $table_file ) if($verbose);
if ( !-e $table_file ) {
croak( "Cannot open " . $table_file );
}
@@ -1970,7 +2013,7 @@ sub create {
or croak("Cannot execute the following command (exit $?):\n$cmd\n");
printf( "Populating metadata in %s from %s\n",
- $dbname, $metadata_file );
+ $dbname, $metadata_file ) if($verbose);
if ( !-e $metadata_file ) {
croak( "Cannot open " . $metadata_file );
}
@@ -2042,7 +2085,7 @@ sub set_release
$dbi->prepare(
"UPDATE source SET source_release=? WHERE source_id=?");
- print "Setting release to '$release' for source ID '$source_id'\n";
+ print "Setting release to '$release' for source ID '$source_id'\n" if($verbose);
$sth->execute( $release, $source_id );
}
diff --git a/misc-scripts/xref_mapping/XrefParser/CeleraParser.pm b/misc-scripts/xref_mapping/XrefParser/CeleraParser.pm
index 29eee0286f..d2e38ad5b2 100644
--- a/misc-scripts/xref_mapping/XrefParser/CeleraParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/CeleraParser.pm
@@ -16,7 +16,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my $celera_gene_source_id = $self->get_source_id_for_source_name('Celera_Gene');
@@ -27,7 +35,7 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -70,11 +78,10 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " Celera xrefs succesfully parsed\n";
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
+ print scalar(@xrefs) . " Celera xrefs succesfully parsed\n" if($verbose);
- print "Done\n";
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/CodelinkParser.pm b/misc-scripts/xref_mapping/XrefParser/CodelinkParser.pm
index e6fd95fe60..e314556b60 100644
--- a/misc-scripts/xref_mapping/XrefParser/CodelinkParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/CodelinkParser.pm
@@ -14,7 +14,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my @xrefs;
@@ -22,7 +30,7 @@ sub run {
my $codelink_io = $self->get_filehandle($file);
if ( !defined $codelink_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 = error
}
@@ -52,11 +60,11 @@ sub run {
$codelink_io->close();
- print scalar(@xrefs) . " Codelink xrefs succesfully parsed\n";
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
+ print scalar(@xrefs) . " Codelink xrefs succesfully parsed\n" if($verbose);
+
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/DBASSParser.pm b/misc-scripts/xref_mapping/XrefParser/DBASSParser.pm
index 6086efb561..8c630c9891 100644
--- a/misc-scripts/xref_mapping/XrefParser/DBASSParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/DBASSParser.pm
@@ -18,32 +18,28 @@ my $dbi;
my $xref_id;
my $source_id;
-sub new {
- my $proto = shift;
- my $class = ref $proto || $proto;
- my $self = bless {}, $class;
-
- return $self;
-}
+sub run {
+ my $self = shift if (defined(caller(1)));
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $rel_url = shift;
+ my $verbose = shift;
-sub run {
- my $self = shift;
+ my $filename = @{$files}[0];
- my ( $source_id, $species_id, $filename ) = @_;
+# my ( $source_id, $species_id, $filename, $rel_url,$verbose ) = @_;
my $file_io = $self->get_filehandle($filename);
if ( !defined($file_io) ) {
return 1;
}
- my $parsed_count = 0;
+ my $parsed_count = 0;
- printf( STDERR "source = %d\t species = %d\n",
- $source_id, $species_id );
-
- $file_io->getline();
+ $file_io->getline();
while ( defined( my $line = $file_io->getline() ) ) {
@@ -53,14 +49,14 @@ sub run {
my ( $dbass_gene_id, $dbass_gene_name, $ensembl_id) = split( /,/, $line );
if ( !defined($dbass_gene_id) || !defined($ensembl_id) ) {
- printf( "Line %d contains has less than two columns.\n",
+ printf STDERR ( "Line %d contains has less than two columns.\n",
1 + $parsed_count );
- print ("The parsing failed\n");
+ print STDERR ("The parsing failed\n");
return 1;
}
- my $first_gene_name;
+ my $first_gene_name = $dbass_gene_name;
my $second_gene_name;
@@ -71,11 +67,10 @@ sub run {
if ($dbass_gene_name =~ /(.*)\((.*)\)/){
$first_gene_name = $1;
$second_gene_name = $2;
- print $first_gene_name, "\n", $second_gene_name, "\n";
+# print $first_gene_name, "\n", $second_gene_name, "\n" if($verbose);
}
-
my $label = $first_gene_name;
my $type = 'gene';
my $description = '';
@@ -84,7 +79,7 @@ sub run {
++$parsed_count;
- my $xref_id = XrefParser::BaseParser->get_xref( $dbass_gene_id, $source_id );
+ my $xref_id = XrefParser::BaseParser->get_xref( $dbass_gene_id, $source_id, $species_id );
if ( !defined($xref_id) || $xref_id eq '' ) {
$xref_id = XrefParser::BaseParser->add_xref($dbass_gene_id, $version, $label, $description, $source_id, $species_id);
@@ -96,7 +91,7 @@ sub run {
XrefParser::DBASSParser->add_synonym($xref_id, $synonym);
}
elsif ($synonym =~ /^\s/){
- print "There is white space! \n";
+ print "There is white space! \n" if($verbose);
}
else {
next;
@@ -105,11 +100,10 @@ sub run {
} ## end while ( defined( my $line...
- printf( "%d direct xrefs succesfully parsed\n", $parsed_count );
+ printf( "%d direct xrefs succesfully parsed\n", $parsed_count ) if($verbose);
$file_io->close();
- print "Done\n";
return 0;
} ## end sub run
diff --git a/misc-scripts/xref_mapping/XrefParser/DirectParser.pm b/misc-scripts/xref_mapping/XrefParser/DirectParser.pm
index 5b3686ac38..02ace4883f 100644
--- a/misc-scripts/xref_mapping/XrefParser/DirectParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/DirectParser.pm
@@ -63,7 +63,7 @@ sub run {
++$parsed_count;
my $xref_id =
- XrefParser::BaseParser->get_xref( $accession, $source_id );
+ XrefParser::BaseParser->get_xref( $accession, $source_id, $species_id );
if ( !defined($xref_id) || $xref_id eq '' ) {
$xref_id =
diff --git a/misc-scripts/xref_mapping/XrefParser/EntrezGeneParser.pm b/misc-scripts/xref_mapping/XrefParser/EntrezGeneParser.pm
index aae8c38d93..74dbf7e761 100644
--- a/misc-scripts/xref_mapping/XrefParser/EntrezGeneParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/EntrezGeneParser.pm
@@ -23,9 +23,16 @@ if (!defined(caller())) {
sub run {
my $self = shift if (defined(caller(1)));
+
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
+
+
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
@@ -39,7 +46,7 @@ sub run {
my $eg_io = $self->get_filehandle($file);
if ( !defined $eg_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 is an error
}
@@ -111,7 +118,7 @@ sub run {
my (@syn) = split(/\|/ ,$arr[$gene_synonyms_index]);
foreach my $synonym (@syn){
if($synonym ne "-"){
- $self->add_to_syn($acc, $source_id, $synonym);
+ $self->add_to_syn($acc, $source_id, $synonym, $species_id);
$syn_count++;
}
}
@@ -119,7 +126,7 @@ sub run {
$eg_io->close();
- print $xref_count." EntrezGene Xrefs added with $syn_count synonyms\n";
+ print $xref_count." EntrezGene Xrefs added with $syn_count synonyms\n" if($verbose);
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/FastaParser.pm b/misc-scripts/xref_mapping/XrefParser/FastaParser.pm
index 9c2bade8a4..4cbc9c369e 100644
--- a/misc-scripts/xref_mapping/XrefParser/FastaParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/FastaParser.pm
@@ -14,7 +14,16 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
+
my $sio = Bio::SeqIO->new(-format=>'fasta' , -file=>$file );
my %species_tax_id = %{$self->get_taxonomy_from_species_id($species_id)};
@@ -44,11 +53,13 @@ sub run {
}
- print scalar(@xrefs) . " Fasta xrefs succesfully parsed\n";
+ print scalar(@xrefs) . " Fasta xrefs succesfully parsed\n" if($verbose);
$self->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
+ print scalar(@xrefs) . " Fasta xrefs succesfully loaded\n" if($verbose);
+
+
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/FlybaseParser.pm b/misc-scripts/xref_mapping/XrefParser/FlybaseParser.pm
index c63fc84941..606b58a169 100644
--- a/misc-scripts/xref_mapping/XrefParser/FlybaseParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/FlybaseParser.pm
@@ -8,6 +8,7 @@ use warnings;
use Carp;
use base qw( XrefParser::BaseParser );
+my $verbose;
# The object types we'd like to parse.
our %object_types = ( gene => 1,
@@ -106,7 +107,7 @@ sub get_source_id_for_source_name {
$self->SUPER::get_source_id_for_source_name(@_);
printf( "source_id for source '%s' is %d\n",
- $source_name, $source_id{$source_name} );
+ $source_name, $source_id{$source_name} ) if ($verbose);
}
if ( !defined( $source_id{$source_name} )
@@ -121,8 +122,18 @@ sub get_source_id_for_source_name {
}
sub run {
- my $self = shift;
- my ( $source_id, $species_id, $data_file, $release_file ) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ $verbose = shift;
+
+ my $data_file = @{$files}[0];
+
+# my $self = shift;
+# my ( $source_id, $species_id, $data_file, $release_file ) = @_;
# Fetch hashes of already stored Uniprot and Interpro accessions.
my %pre_xref_ids = (
@@ -141,7 +152,7 @@ sub run {
printf( "%d lines read, %d skipped, %d parsed; %d lines/s\n",
$count_read, $count_skipped,
$count_read - $count_skipped,
- ( $count_read - $last_count_read )/$status_interval );
+ ( $count_read - $last_count_read )/$status_interval ) if($verbose);
$last_count_read = $count_read;
alarm($status_interval);
};
@@ -359,10 +370,10 @@ sub run {
} ## end while ( defined( my $line...
$data_io->close();
- print("FlybaseParser Summary:\n");
+ print("FlybaseParser Summary:\n") if($verbose);
foreach my $label ( sort( keys(%xref_ids) ) ) {
my $accessions = $xref_ids{$label};
- printf( "\t%-32s %6d\n", $label, scalar( keys( %{$accessions} ) ) );
+ printf( "\t%-32s %6d\n", $label, scalar( keys( %{$accessions} ) ) ) if($verbose);
}
} ## end sub run
diff --git a/misc-scripts/xref_mapping/XrefParser/Flybase_dmel_GFFv3_Parser.pm b/misc-scripts/xref_mapping/XrefParser/Flybase_dmel_GFFv3_Parser.pm
index 3c5119b000..3beecdac6b 100644
--- a/misc-scripts/xref_mapping/XrefParser/Flybase_dmel_GFFv3_Parser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/Flybase_dmel_GFFv3_Parser.pm
@@ -44,6 +44,7 @@ use base qw( XrefParser::BaseParser );
my %cache_source =();
+my $verbose;
# --------------------------------------------------------------------------------
# Parse command line and run if being run directly
@@ -175,10 +176,20 @@ sub get_source{
}
sub run {
+
my $self = shift if (defined(caller(1)));
+
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ $verbose = shift;
+
+ my $file = @{$files}[0];
+# my $self = shift if (defined(caller(1)));
+# my $source_id = shift;
+# my $species_id = shift;
+# my $file = shift;
my $species_name;
@@ -202,14 +213,14 @@ sub run {
# delete previous if running directly rather than via BaseParser
if (!defined(caller(1))) {
- print "Deleting previous xrefs for these sources\n";
+ print "Deleting previous xrefs for these sources\n" if($verbose);
XrefParser::BaseParser->delete_by_source(\@xrefs);
}
- print "... parsed.\n";
- print STDERR "uploading ".scalar(@xrefs)." xrefs's\n";
+ print "... parsed.\n" if($verbose);
+ print STDERR "uploading ".scalar(@xrefs)." xrefs's\n" if($verbose);
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print STDERR "uploading ".scalar(@direct_xrefs)." direct-xrefs's\n";
+ print STDERR "uploading ".scalar(@direct_xrefs)." direct-xrefs's\n" if($verbose);
XrefParser::BaseParser->upload_direct_xrefs(\@direct_xrefs);
return 0;
@@ -232,12 +243,12 @@ sub relink_synonyms_to_xrefs{
sub create_xrefs {
my ($self, $flybase_source_id, $file) = @_;
- print STDERR "starting to parse $file...." ;
+ print STDERR "starting to parse $file...." if($verbose);
my $gff_io = $self->get_filehandle($file);
if ( !defined $gff_io ) {
- print "ERROR: Can't open the GFF file $file\n";
+ print STDERR "ERROR: Can't open the GFF file $file\n";
return 0;
}
@@ -1079,7 +1090,7 @@ sub get_species {
$sth->finish;
if (defined $species_name) {
- print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n";
+ print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n" if($verbose);
} else {
throw("Cannot find species corresponding to taxonomy ID " . $species_id . " - check species table\n");
}
diff --git a/misc-scripts/xref_mapping/XrefParser/GOParser.pm b/misc-scripts/xref_mapping/XrefParser/GOParser.pm
index a5d98fdc71..2c7df6aef8 100644
--- a/misc-scripts/xref_mapping/XrefParser/GOParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/GOParser.pm
@@ -25,16 +25,17 @@ if (!defined(caller())) {
sub run {
my $self = shift if (defined(caller(1)));
+
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
- my $release_file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
- my %wrongtype;
+ my $file = @{$files}[0];
-# if(!defined($source_id)){
-# $source_id = $self->get_source_id_for_filename($file);
-# }
+
+ my %wrongtype;
#get the "main" GO source id.
$source_id = $self->get_source_id_for_source_name("GO","main");
@@ -80,11 +81,11 @@ sub run {
my $go_io = $self->get_filehandle($file);
if ( !defined $go_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 error
}
- print "processing for taxon: $tax_id\n";
+ print "processing for taxon: $tax_id\n" if($verbose);
my $taxon_line = "taxon:".$tax_id;
my $miss =0;
while ( $_ = $go_io->getline() ) {
@@ -142,7 +143,7 @@ sub run {
if(defined($worm{$worm_acc})){
my ($xref_id, $stable_id, $type, $link) = split(/::/,$worm{$worm_acc});
- my $new_xref_id=$self->get_xref($array[4],$source_id);
+ my $new_xref_id=$self->get_xref($array[4],$source_id, $species_id);
if(!defined($new_xref_id)){
$new_xref_id = $self->add_xref($array[4],undef,$array[4],"", $source_id, $species_id);
@@ -181,7 +182,7 @@ sub run {
}
elsif(!defined($wrongtype{$array[0]})){
- print STDERR "WARNING: unknown type ".$array[0]."\n";
+ print STDERR "WARNING: unknown type ".$array[0]."\n" if($verbose);
$wrongtype{$array[0]} = 1;
}
}
@@ -189,7 +190,7 @@ sub run {
$go_io->close();
- print "\t$count GO dependent xrefs added $refseq_miss refseq not found and $swiss_miss Swissprot not found \n";
+ print "\t$count GO dependent xrefs added $refseq_miss refseq not found and $swiss_miss Swissprot not found \n" if($verbose);
}
if ( defined $release_file ) {
# Parse and set release information from $release_file.
@@ -205,7 +206,7 @@ sub run {
s#.*The following table describes.*?of (GOA.*?)<ul>.*#$1#;
$release =~ s#<[^>]+>##g;
- print "GO release: '$release'\n";
+ print "GO release: '$release'\n" if($verbose);
$self->set_release( $source_id, $release );
}
diff --git a/misc-scripts/xref_mapping/XrefParser/HGNCParser.pm b/misc-scripts/xref_mapping/XrefParser/HGNCParser.pm
index fc919c9e3a..3b7e93e605 100644
--- a/misc-scripts/xref_mapping/XrefParser/HGNCParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/HGNCParser.pm
@@ -15,7 +15,7 @@ my $syn_sth;
if (!defined(caller())) {
if (scalar(@ARGV) != 1) {
- print "\nUsage: HGNCParser.pm file <source_id> <species_id>\n\n";
+ print STDERR "\nUsage: HGNCParser.pm file <source_id> <species_id>\n\n";
exit(1);
}
@@ -28,9 +28,12 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files_ref}[0];
- print STDERR "source = $source_id\tspecies = $species_id\n";
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
}
@@ -68,7 +71,6 @@ sub run {
push @list, "refseq_dna";
my (%entrezgene) = %{XrefParser::BaseParser->get_valid_xrefs_for_dependencies("EntrezGene",@list)};
- my $swiss_count = 0;
my $refseq_count = 0;
my $entrezgene_count = 0;
my $ensembl_count = 0;
@@ -112,14 +114,14 @@ sub run {
if (defined($array[3])) { # dead name, add to synonym
my @array2 = split(',\s*', $array[3]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_ensembl_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_ensembl_mapped, $arr, $species_id);
}
}
if (defined($array[4])) { # alias, add to synonym
my @array2 = split(',\s*', $array[4]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_ensembl_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_ensembl_mapped, $arr, $species_id);
}
}
@@ -133,14 +135,14 @@ sub run {
if (defined($array[3])) { # dead name, add to synonym
my @array2 = split(',\s*', $array[3]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_manual, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_manual, $arr, $species_id);
}
}
if (defined($array[4])) { # alias, add to synonym
my @array2 = split(',\s*', $array[4]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_manual, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_manual, $arr, $species_id);
}
}
}
@@ -154,14 +156,14 @@ sub run {
if (defined($array[3])) { # dead name, add to synonym
my @array2 = split(',\s*', $array[3]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_mapped, $arr, $species_id);
}
}
if (defined($array[4])) { # alias, add to synonym
my @array2 = split(',\s*', $array[4]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_refseq_mapped, $arr, $species_id);
}
}
}
@@ -176,17 +178,17 @@ sub run {
if (defined($array[3])) { # dead name, add to synonym
my @array2 = split(',\s*', $array[3]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_manual, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_manual, $arr, $species_id);
}
}
if (defined($array[4])) { # alias, add to synonym
my @array2 = split(',\s*', $array[4]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_manual, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_manual, $arr, $species_id);
}
}
- }
+ }
}
if(defined($array[7])){
@@ -198,30 +200,31 @@ sub run {
if (defined($array[3])) { # dead name, add to synonym
my @array2 = split(',\s*', $array[3]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_mapped, $arr, $species_id);
}
}
if (defined($array[4])) { # alias, add to synonym
my @array2 = split(',\s*', $array[4]);
foreach my $arr (@array2){
- XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_mapped, $arr);
+ XrefParser::BaseParser->add_to_syn($array[0], $hgnc_entrezgene_mapped, $arr, $species_id);
}
}
}
}
if(!$seen){ # Store to keep descriptions etc
$self->add_xref($array[0], "", $array[1], $array[2], $source_id, $species_id);
+ $mismatch++;
}
} # while HGNC
- $hugo_io->getline();
-
- print "Loaded a total of " . ($refseq_count + $entrezgene_count) . " HGNC xrefs, $refseq_count from RefSeq curated mappings and $entrezgene_count from EntrezGene mappings\n";
-
- print "$mismatch xrefs could not be associated via RefSeq or EntrezGene\n";
+ $hugo_io->close();
+
+ print "Loaded a total of " . ($refseq_count + $entrezgene_count) . " HGNC xrefs, $refseq_count from RefSeq curated mappings and $entrezgene_count from EntrezGene mappings and $ensembl_count from ensembl_mapping\n" if($verbose);
+
+ print "$mismatch xrefs could not be associated via RefSeq, EntrezGene or ensembl\n" if($verbose);
return 0; # successful
diff --git a/misc-scripts/xref_mapping/XrefParser/HPAParser.pm b/misc-scripts/xref_mapping/XrefParser/HPAParser.pm
index 38465320ea..e77da82af1 100644
--- a/misc-scripts/xref_mapping/XrefParser/HPAParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/HPAParser.pm
@@ -14,19 +14,16 @@ use base qw( XrefParser::BaseParser);
# 4) Link (URL)
-sub new {
- my $proto = shift;
-
- my $class = ref $proto || $proto;
- my $self = bless {}, $class;
-
- return $self;
-}
-
sub run {
- my $self = shift;
+ my $self = shift if (defined(caller(1)));
- my ( $source_id, $species_id, $filename ) = @_;
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $rel_url = shift;
+ my $verbose = shift;
+
+ my $filename = @{$files}[0];
my $file_io = $self->get_filehandle($filename);
if ( !defined($file_io) ) {
@@ -35,9 +32,6 @@ sub run {
my $parsed_count = 0;
- printf( STDERR "source = %d\t species = %d\n",
- $source_id, $species_id );
-
$file_io->getline();
while ( defined( my $line = $file_io->getline() ) ) {
@@ -61,7 +55,7 @@ sub run {
++$parsed_count;
- my $xref_id = XrefParser::BaseParser->get_xref( $antibody_id, $source_id );
+ my $xref_id = XrefParser::BaseParser->get_xref( $antibody_id, $source_id, $species_id );
if ( !defined($xref_id) || $xref_id eq '' ) {
$xref_id = XrefParser::BaseParser->add_xref($antibody_id, $version, $label, $description, $source_id, $species_id);
@@ -72,12 +66,10 @@ sub run {
} ## end while ( defined( my $line...
- printf( "%d direct xrefs succesfully parsed\n", $parsed_count );
+ printf( "%d direct xrefs succesfully parsed\n", $parsed_count ) if($verbose);
$file_io->close();
- print "Done\n";
-
return 0;
} ## end sub run
diff --git a/misc-scripts/xref_mapping/XrefParser/IPIParser.pm b/misc-scripts/xref_mapping/XrefParser/IPIParser.pm
index 75f70a6ff1..05b59025e2 100644
--- a/misc-scripts/xref_mapping/XrefParser/IPIParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/IPIParser.pm
@@ -13,7 +13,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my @xrefs;
@@ -22,7 +30,7 @@ sub run {
my $ipi_io = $self->get_filehandle($file);
if ( !defined $ipi_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 = error
}
@@ -65,11 +73,11 @@ sub run {
$ipi_io->close();
- print scalar(@xrefs) . " IPI xrefs succesfully parsed\n";
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
+ print scalar(@xrefs) . " IPI xrefs succesfully parsed\n" if($verbose);
+
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/IlluminaParser.pm b/misc-scripts/xref_mapping/XrefParser/IlluminaParser.pm
index 55beefae90..b0a1d86724 100644
--- a/misc-scripts/xref_mapping/XrefParser/IlluminaParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/IlluminaParser.pm
@@ -14,14 +14,22 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my @xrefs;
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -63,10 +71,10 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " Illumina V2 xrefs succesfully parsed\n";
-
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
+ print scalar(@xrefs) . " Illumina V2 xrefs succesfully parsed\n" if($verbose);
+
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/IlluminaWGParser.pm b/misc-scripts/xref_mapping/XrefParser/IlluminaWGParser.pm
index 12bb2fdf9b..56236e9d76 100644
--- a/misc-scripts/xref_mapping/XrefParser/IlluminaWGParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/IlluminaWGParser.pm
@@ -7,14 +7,23 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
+
my @xrefs;
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -85,11 +94,11 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " Illumina V2 xrefs succesfully parsed\n";
-
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
+ print scalar(@xrefs) . " Illumina V2 xrefs succesfully parsed\n" if($verbose);
+
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/InterproGoParser.pm b/misc-scripts/xref_mapping/XrefParser/InterproGoParser.pm
index 02ad1bf478..ac3e9abdde 100644
--- a/misc-scripts/xref_mapping/XrefParser/InterproGoParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/InterproGoParser.pm
@@ -6,14 +6,22 @@ use vars qw(@ISA);
@ISA = qw(XrefParser::BaseParser);
sub run {
- my( $self, $source_id, $species_id, $file ) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my $file_io = $self->get_filehandle($file)
|| ( print( "ERROR: Cannot open $file\n" ) && return 1 );
my %interpros = %{$self->get_valid_codes("interpro",$species_id)};
scalar( keys %interpros )
- || ( print( "ERROR: No InterPro xrefs found in DB" ) && return 1 );
+ || ( print STDERR "ERROR: No InterPro xrefs found in DB" && return 1 );
#get the "main" GO source id.
$source_id = $self->get_source_id_for_source_name("GO","main");
@@ -49,7 +57,7 @@ sub run {
}
print "Parsed identifiers from $file\n".
"\tadded $dependent_xref_count GO xrefs dependent on InterPro\n".
- "\tskipped $skip_count GO terms due to missing InterPros\n";
+ "\tskipped $skip_count GO terms due to missing InterPros\n" if($verbose);
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/InterproParser.pm b/misc-scripts/xref_mapping/XrefParser/InterproParser.pm
index 69a26cbb9c..e4deab7fa5 100644
--- a/misc-scripts/xref_mapping/XrefParser/InterproParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/InterproParser.pm
@@ -30,10 +30,13 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files_ref = shift;
my $release_file = shift;
+ my $verbose = shift;
+
+
+ my $file = @{$files_ref}[0];
- print STDERR "source = $source_id\tspecies = $species_id\n";
if(!defined($source_id)){
$source_id = $self->get_source_id_for_filename($file);
}
@@ -56,10 +59,10 @@ sub run {
. "(accession,version,label,description,source_id,species_id) "
. "VALUES(?,?,?,?,?,?)" );
- my $get_xref_sth =
- $self->dbi()
- ->prepare( "SELECT xref_id FROM xref "
- . "WHERE accession = ? AND source_id = ?" );
+# my $get_xref_sth =
+# $self->dbi()
+# ->prepare( "SELECT xref_id FROM xref "
+# . "WHERE accession = ? AND source_id = ?" );
my $dir = dirname($file);
@@ -70,7 +73,7 @@ sub run {
my $xml_io = $self->get_filehandle($file);
if ( !defined $xml_io ) {
- print "ERROR: Can't open hugo interpro file $dir/interpro.xml\n";
+ print "ERROR: Can't open hugo interpro file $file\n";
return 1; # 1= error
}
@@ -92,7 +95,7 @@ sub run {
if ($interpro) {
# print $interpro."\n";
- if ( !get_xref( $get_xref_sth, $interpro, $source_id ) ) {
+ if ( !$self->get_xref( $interpro, $source_id, $species_id ) ) {
$count{INTERPRO}++;
if (
!$add_xref_sth->execute(
@@ -101,7 +104,7 @@ sub run {
)
)
{
- print "Problem adding '$interpro'\n";
+ print STDERR "Problem adding '$interpro'\n";
return 1; # 1 is an error
}
}
@@ -115,7 +118,7 @@ sub run {
my ( $db_type, $id ) = ( $1, $2 );
if( $db_type eq 'SSF' ){ $id =~ s/^SSF// } # Strip SSF prefix
- if ( !get_xref( $get_interpro_sth, $interpro, $id ) ) {
+ if ( !$self->get_xref( $interpro, $id, $species_id ) ) {
$add_interpro_sth->execute( $interpro, $id );
$count{$db_type}++;
}
@@ -126,7 +129,7 @@ sub run {
$xml_io->close();
for my $db ( keys %count ) {
- print "\t" . $count{$db} . " $db loaded.\n";
+ print "\t" . $count{$db} . " $db loaded.\n" if($verbose);
}
if ( defined $release_file ) {
@@ -145,24 +148,24 @@ sub run {
$release_io->close();
if ( defined $release ) {
- print "Interpro release is '$release'\n";
+ print "Interpro release is '$release'\n" if($verbose);
$self->set_release( $source_id, $release );
} else {
- print "Did not find release info in '$release_file'\n";
+ print "Did not find release info in '$release_file'\n" if($verbose);
}
}
return 0;
}
-sub get_xref{
- my ($get_xref_sth, $acc, $source) = @_;
-
- $get_xref_sth->execute($acc, $source) || die "FAILED $acc $source\n";
- if(my @row = $get_xref_sth->fetchrow_array()) {
- return $row[0];
- }
- return 0;
-}
+#sub get_xref{
+# my ($get_xref_sth, $acc, $source) = @_;
+#
+# $get_xref_sth->execute($acc, $source) || die "FAILED $acc $source\n";
+# if(my @row = $get_xref_sth->fetchrow_array()) {
+# return $row[0];
+# }
+# return 0;
+#}
1;
diff --git a/misc-scripts/xref_mapping/XrefParser/JGI_Parser.pm b/misc-scripts/xref_mapping/XrefParser/JGI_Parser.pm
index f76003ffcc..cb32def5a1 100644
--- a/misc-scripts/xref_mapping/XrefParser/JGI_Parser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/JGI_Parser.pm
@@ -13,7 +13,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my $source_name = $self->get_source_name_for_source_id ($source_id) ;
@@ -50,7 +58,7 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 is an error
}
@@ -88,7 +96,7 @@ sub run {
$version = "JGI 2.0" ;
}else {
- print "WARNING : The source-name specified in the populate_metatable.sql file is\n" .
+ print STDERR "WARNING : The source-name specified in the populate_metatable.sql file is\n" .
"WARNING : not matching the differnt cases specified in JGI_Parser.pm - plese\n" .
"WARNING : edit the parser \n" ;
return 1;
@@ -124,11 +132,10 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " JGI_ xrefs succesfully parsed\n";
+ print scalar(@xrefs) . " JGI_ xrefs succesfully parsed\n" if($verbose);
XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs);
- print "Done\n";
return 0; # successful
}
@@ -138,8 +145,6 @@ sub new
my $proto = shift;
my $self = $proto->SUPER::new(@_);
- print "\n\nhave new jp\n";
-
return $self;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/MGDParser.pm b/misc-scripts/xref_mapping/XrefParser/MGDParser.pm
index 7193a88c4d..709aa4c3f8 100644
--- a/misc-scripts/xref_mapping/XrefParser/MGDParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/MGDParser.pm
@@ -31,7 +31,11 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ $verbose = shift;
+
+ my $file = @{$files}[0];
die "No longer used. MGI is taken form the uniprot file\n";
@@ -92,7 +96,7 @@ sub run {
chomp ;
my ($key,$syn) = (split)[0,4];
if(defined($mgi_good{$key})){
- $self->add_to_syn($key, $source_id, $syn);
+ $self->add_to_syn($key, $source_id, $syn, $species_id);
$synonyms++;
}
}
diff --git a/misc-scripts/xref_mapping/XrefParser/MIMParser.pm b/misc-scripts/xref_mapping/XrefParser/MIMParser.pm
index b380b7b418..c951a70bd2 100644
--- a/misc-scripts/xref_mapping/XrefParser/MIMParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/MIMParser.pm
@@ -26,7 +26,11 @@ sub run {
my $general_source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my %old_to_new;
my %removed;
@@ -46,7 +50,7 @@ sub run {
my $morbid_source_id = XrefParser::BaseParser->get_source_id_for_source_name("MIM_MORBID");
push @sources, $morbid_source_id;
- print "sources are:- ".join(", ",@sources)."\n";
+ print "sources are:- ".join(", ",@sources)."\n" if($verbose);
local $/ = "*RECORD*";
@@ -115,12 +119,12 @@ sub run {
$new = $old_to_new{$new};
}
if(!defined($removed{$new})){
- $self->add_to_syn_for_mult_sources($new, \@sources, $old);
+ $self->add_to_syn_for_mult_sources($new, \@sources, $old, $species_id);
$syn_count++;
}
}
- print "$gene genemap and $phenotype phenotype MIM xrefs added\n";
- print "added $syn_count synonyms (defined by MOVED TO)\n";
+ print "$gene genemap and $phenotype phenotype MIM xrefs added\n" if($verbose);
+ print "added $syn_count synonyms (defined by MOVED TO)\n" if($verbose);
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/RGDParser.pm b/misc-scripts/xref_mapping/XrefParser/RGDParser.pm
index 6770c8f2e0..4c8d54fc73 100644
--- a/misc-scripts/xref_mapping/XrefParser/RGDParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/RGDParser.pm
@@ -30,7 +30,11 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
@@ -104,8 +108,8 @@ sub run {
$rgd_io->close();
- print "\t$count xrefs succesfully loaded and dependent on refseq\n";
- print "\t$mismatch xrefs added but with NO dependencies\n";
+ print "\t$count xrefs succesfully loaded and dependent on refseq\n" if($verbose);
+ print "\t$mismatch xrefs added but with NO dependencies\n" if($verbose);
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
index d67626acb0..179e5d4ff8 100644
--- a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
@@ -24,13 +24,20 @@ if (!defined(caller())) {
# --------------------------------------------------------------------------------
+my $verbose;
+
sub run {
my $self = shift if (defined(caller(1)));
my $source_id = shift;
my $species_id = shift;
- my @files = @_;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ $verbose = shift;
+
+ my @files = @{$files_ref};
+
my $release_file;
@@ -43,8 +50,8 @@ sub run {
my $dna_source_id =
$self->get_source_id_for_source_name('RefSeq_dna');
- print "RefSeq_peptide source ID = $peptide_source_id\n";
- print "RefSeq_dna source ID = $dna_source_id\n";
+ print "RefSeq_peptide source ID = $peptide_source_id\n" if($verbose);
+ print "RefSeq_dna source ID = $dna_source_id\n" if($verbose);
my $pred_peptide_source_id =
$self->get_source_id_for_source_name('RefSeq_peptide_predicted');
@@ -52,8 +59,8 @@ sub run {
$self->get_source_id_for_source_name('RefSeq_dna_predicted');
print "RefSeq_peptide_predicted source ID = "
- . "$pred_peptide_source_id\n";
- print "RefSeq_dna_predicted source ID = $pred_dna_source_id\n";
+ . "$pred_peptide_source_id\n" if($verbose);
+ print "RefSeq_dna_predicted source ID = $pred_dna_source_id\n" if($verbose);
my @xrefs;
foreach my $file (@files) {
@@ -96,7 +103,7 @@ sub run {
# Put a comma after the release number to make it more readable.
$release =~ s/Release (\d+)/Release $1,/;
- print "RefSeq release: '$release'\n";
+ print "RefSeq release: '$release'\n" if($verbose);
$self->set_release( $source_id, $release );
$self->set_release( $peptide_source_id, $release );
@@ -128,18 +135,13 @@ sub create_xrefs {
my @tax_ids = @{$species2tax{$species_id}};
my %name2species_id = map{ $_=>$species_id } @names;
my %taxonomy2species_id = map{ $_=>$species_id } @tax_ids;
- # my %name2species_id = $self->name2species_id();
- # my %taxonomy2species_id = $self->taxonomy2species_id();
my %dependent_sources = $self->get_dependent_xref_sources();
-# my (%genemap) = %{$self->get_valid_codes("mim_gene",$species_id)};
-# my (%morbidmap) = %{$self->get_valid_codes("mim_morbid",$species_id)};
-
my $refseq_io = $self->get_filehandle($file);
if ( !defined $refseq_io ) {
- print "ERROR: Can't open RefSeqGPFF file $file\n";
+ print STDERR "ERROR: Can't open RefSeqGPFF file $file\n";
return undef;
}
@@ -165,7 +167,7 @@ sub create_xrefs {
$type = 'peptide';
}else{
- print "Could not work out sequence type for $file\n";
+ print STDERR "Could not work out sequence type for $file\n";
return undef;
}
@@ -293,7 +295,7 @@ sub create_xrefs {
$refseq_io->close();
- print "Read " . scalar(@xrefs) ." xrefs from $file\n";
+ print "Read " . scalar(@xrefs) ." xrefs from $file\n" if($verbose);
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/RefSeqParser.pm b/misc-scripts/xref_mapping/XrefParser/RefSeqParser.pm
index 6132364af5..1f1c57799e 100644
--- a/misc-scripts/xref_mapping/XrefParser/RefSeqParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/RefSeqParser.pm
@@ -8,6 +8,8 @@ use File::Basename;
use base qw( XrefParser::BaseParser );
+
+my $verbose;
# --------------------------------------------------------------------------------
# Parse command line and run if being run directly
@@ -28,10 +30,13 @@ sub run {
my $self = shift if (defined(caller(1)));
- my $source_id = shift;
+ my $source_id = shift;
my $species_id = shift;
- my @files = @_;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ $verbose = shift;
+ my @files = @{$files_ref};
my $release_file;
if ( $files[-1] =~ /RefSeq-release/ ) {
@@ -43,8 +48,8 @@ sub run {
my $dna_source_id =
$self->get_source_id_for_source_name('RefSeq_dna');
- print "RefSeq_peptide source ID = $peptide_source_id\n";
- print "RefSeq_dna source ID = $dna_source_id\n";
+ print "RefSeq_peptide source ID = $peptide_source_id\n" if($verbose);
+ print "RefSeq_dna source ID = $dna_source_id\n" if($verbose);
my $pred_peptide_source_id =
$self->get_source_id_for_source_name('RefSeq_peptide_predicted');
@@ -52,8 +57,8 @@ sub run {
$self->get_source_id_for_source_name('RefSeq_dna_predicted');
print "RefSeq_peptide_predicted source ID = "
- . "$pred_peptide_source_id\n";
- print "RefSeq_dna_predicted source ID = $pred_dna_source_id\n";
+ . "$pred_peptide_source_id\n" if($verbose);
+ print "RefSeq_dna_predicted source ID = $pred_dna_source_id\n" if($verbose);
my @xrefs;
foreach my $file (@files) {
@@ -128,7 +133,7 @@ sub create_xrefs {
my $refseq_io = $self->get_filehandle($file);
if ( !defined $refseq_io ) {
- print "ERROR: Can't open RefSeq file $file\n";
+ print STDERR "ERROR: Can't open RefSeq file $file\n";
return undef;
}
@@ -205,7 +210,7 @@ sub create_xrefs {
$refseq_io->close();
- print "Read " . scalar(@xrefs) ." xrefs from $file\n";
+ print "Read " . scalar(@xrefs) ." xrefs from $file\n" if($verbose);
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/SGDParser.pm b/misc-scripts/xref_mapping/XrefParser/SGDParser.pm
index 5c20c87410..76fd234b89 100644
--- a/misc-scripts/xref_mapping/XrefParser/SGDParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/SGDParser.pm
@@ -26,7 +26,11 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files_ref}[0];
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
@@ -35,12 +39,12 @@ sub run {
$species_id = XrefParser::BaseParser->get_species_id_for_filename($file);
}
-
+
my $sgd_io = $self->get_filehandle($file);
if ( !defined $sgd_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 is an error
}
@@ -55,14 +59,14 @@ sub run {
$self->add_xref($sgd_id,"",$locus_name,$desc,$source_id,$species_id);
$xref_count++;
foreach my $synonym (@syn){
- $self->add_to_syn($sgd_id, $source_id, $synonym);
+ $self->add_to_syn($sgd_id, $source_id, $synonym, $species_id);
$syn_count++;
}
}
$sgd_io->close();
- print $xref_count." SGD Xrefs added with $syn_count synonyms\n";
+ print $xref_count." SGD Xrefs added with $syn_count synonyms\n" if($verbose);
return 0; #successful
}
diff --git a/misc-scripts/xref_mapping/XrefParser/SegmentParser.pm b/misc-scripts/xref_mapping/XrefParser/SegmentParser.pm
index 501f4f6322..24d33f5198 100644
--- a/misc-scripts/xref_mapping/XrefParser/SegmentParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/SegmentParser.pm
@@ -25,7 +25,12 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files_ref}[0];
+
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
@@ -40,7 +45,7 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open file $file\n";
+ print STDERR "ERROR: Could not open file $file\n";
return 1;
}
@@ -58,7 +63,7 @@ sub run {
}
$name_2_source_id{$source_name} = $tmp;
}
- my $xref_id = $self->get_xref($acc,$name_2_source_id{$source_name});
+ my $xref_id = $self->get_xref($acc,$name_2_source_id{$source_name}, $species_id);
if(!defined($xref_id)){
$xref_id = $self->add_xref($acc,"",$display_label,$description,$name_2_source_id{$source_name}, $species_id);
$added++;
@@ -72,7 +77,7 @@ sub run {
$file_io->close();
- print "Added $added Xrefs for Gene segments\n";
+ print "Added $added Xrefs for Gene segments\n" if($verbose);
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/UCSCParser.pm b/misc-scripts/xref_mapping/XrefParser/UCSCParser.pm
index 84258f5653..617ed75ca8 100644
--- a/misc-scripts/xref_mapping/XrefParser/UCSCParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/UCSCParser.pm
@@ -8,8 +8,15 @@ use warnings;
use base qw( XrefParser::CoordinateParser );
sub run {
- my $self = shift;
- my ( $source_id, $species_id, $data_file, $release_file ) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $data_file = @{$files}[0];
# Get the $source_id for the "UCSC" source.
$source_id = $self->get_source_id_for_source_name('UCSC');
diff --git a/misc-scripts/xref_mapping/XrefParser/UniGeneParser.pm b/misc-scripts/xref_mapping/XrefParser/UniGeneParser.pm
index d53e9fde3d..424d85cdec 100644
--- a/misc-scripts/xref_mapping/XrefParser/UniGeneParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/UniGeneParser.pm
@@ -8,6 +8,8 @@ use File::Basename;
use base qw( XrefParser::BaseParser );
+my $verbose;
+
# --------------------------------------------------------------------------------
# Parse command line and run if being run directly
@@ -30,13 +32,16 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $uniq_file = shift;
- my $data_file = shift;
- my $release_file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ $verbose = shift;
+
+ my $uniq_file = @{$files}[0];
+ my $data_file = @{$files}[1];
my $unigene_source_id = $self->get_source_id_for_source_name('UniGene');
- print "UniGene source ID = $unigene_source_id.\n";
+ print "UniGene source ID = $unigene_source_id.\n" if($verbose);
if ( !defined($species_id) ) {
$species_id =
@@ -83,8 +88,7 @@ sub run {
$release =~ s/\s{2,}/ /g;
$release =~ s/^(.*) UniGene/$1, UniGene/;
- print "UniGene release: '$release'\n";
- #$self->set_release( $source_id, $release );
+ print "UniGene release: '$release'\n" if($verbose);
$self->set_release( $unigene_source_id, $release );
}
}
@@ -107,7 +111,7 @@ sub get_desc{
my $desc_io = $self->get_filehandle( $data_file );
if ( !defined $desc_io ) {
- print "ERROR: Can't open $data_file\n";
+ print STDERR "ERROR: Can't open $data_file\n";
return undef;
}
@@ -149,7 +153,7 @@ sub create_xrefs {
my $unigene_io = $self->get_filehandle($uniq_file);
if ( !defined $unigene_io ) {
- print "Can't open RefSeq file $uniq_file\n";
+ print STDERR "Can't open RefSeq file $uniq_file\n";
return undef;
}
@@ -205,7 +209,7 @@ sub create_xrefs {
$unigene_io->close();
%geneid_2_desc=();
- print "Read " . scalar(@xrefs) ." xrefs from $uniq_file\n";
+ print "Read " . scalar(@xrefs) ." xrefs from $uniq_file\n" if($verbose);
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/UniProtParser.pm b/misc-scripts/xref_mapping/XrefParser/UniProtParser.pm
index e322b60b66..eba95aabb5 100644
--- a/misc-scripts/xref_mapping/XrefParser/UniProtParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/UniProtParser.pm
@@ -15,14 +15,17 @@ use File::Basename;
use base qw( XrefParser::BaseParser );
+
+my $verbose;
+
# --------------------------------------------------------------------------------
# Parse command line and run if being run directly
if (!defined(caller())) {
if (scalar(@ARGV) != 3) {
- print "\nUsage: UniProtParser.pm file.SPC <source_id> <species_id>\n\n";
- print scalar(@ARGV);
+ print STDERR "\nUsage: UniProtParser.pm file.SPC <source_id> <species_id>\n\n";
+ print STDERR scalar(@ARGV);
exit(1);
}
@@ -38,8 +41,11 @@ sub run {
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
- my $release_file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ $verbose = shift;
+
+ my $file = @{$files}[0];
my $species_name;
@@ -54,8 +60,8 @@ sub run {
$sptr_source_id =
$self->get_source_id_for_source_name('Uniprot/SPTREMBL');
- print "SwissProt source id for $file: $sp_source_id\n";
- print "SpTREMBL source id for $file: $sptr_source_id\n";
+ print "SwissProt source id for $file: $sp_source_id\n" if ($verbose);
+ print "SpTREMBL source id for $file: $sptr_source_id\n" if ($verbose);
my @xrefs =
@@ -68,7 +74,7 @@ sub run {
# delete previous if running directly rather than via BaseParser
if (!defined(caller(1))) {
- print "Deleting previous xrefs for these sources\n";
+ print "Deleting previous xrefs for these sources\n" if($verbose);
$self->delete_by_source(\@xrefs);
}
@@ -93,10 +99,10 @@ sub run {
while ( defined( my $line = $release_io->getline() ) ) {
if ( $line =~ m#(UniProtKB/Swiss-Prot Release .*)# ) {
$sp_release = $1;
- print "Swiss-Prot release is '$sp_release'\n";
+ print "Swiss-Prot release is '$sp_release'\n" if($verbose);
} elsif ( $line =~ m#(UniProtKB/TrEMBL Release .*)# ) {
$sptr_release = $1;
- print "SpTrEMBL release is '$sptr_release'\n";
+ print "SpTrEMBL release is '$sptr_release'\n" if($verbose);
}
}
$release_io->close();
@@ -133,11 +139,11 @@ sub get_species {
if (defined $species_name) {
- print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n";
+ print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n" if($verbose);
} else {
- print "Cannot find species corresponding to taxonomy ID " . $species_id . " - check species table\n";
+ print STDERR "Cannot find species corresponding to taxonomy ID " . $species_id . " - check species table\n";
exit(1);
}
@@ -178,10 +184,10 @@ sub create_xrefs {
# my $go_source_id = $self->get_source_id_for_source_name('GO');
my $embl_pred_source_id = $dependent_sources{'EMBL_predicted'};
my $protein_id_pred_source_id = $dependent_sources{'protein_id_predicted'};
- print "Predicted SwissProt source id for $file: $sp_pred_source_id\n";
- print "Predicted SpTREMBL source id for $file: $sptr_pred_source_id\n";
- print "Predicted EMBL source id for $file: $embl_pred_source_id\n";
- print "Predicted protein_id source id for $file: $protein_id_pred_source_id\n";
+ print "Predicted SwissProt source id for $file: $sp_pred_source_id\n" if($verbose);
+ print "Predicted SpTREMBL source id for $file: $sptr_pred_source_id\n" if($verbose);
+ print "Predicted EMBL source id for $file: $embl_pred_source_id\n" if($verbose);
+ print "Predicted protein_id source id for $file: $protein_id_pred_source_id\n" if($verbose);
# print "GO source id for $file: $go_source_id\n";
my (%genemap) =
@@ -424,12 +430,12 @@ sub create_xrefs {
$uniprot_io->close();
- print "Read $num_sp SwissProt xrefs and $num_sptr SPTrEMBL xrefs from $file\n";
- print "Found $num_sp_pred predicted SwissProt xrefs and $num_sptr_pred predicted SPTrEMBL xrefs\n" if ($num_sp_pred > 0 || $num_sptr_pred > 0);
+ print "Read $num_sp SwissProt xrefs and $num_sptr SPTrEMBL xrefs from $file\n" if($verbose);
+ print "Found $num_sp_pred predicted SwissProt xrefs and $num_sptr_pred predicted SPTrEMBL xrefs\n" if (($num_sp_pred > 0 || $num_sptr_pred > 0) and $verbose);
- print "Added the following dependent xrefs:-\n";
+ print "Added the following dependent xrefs:-\n" if($verbose);
foreach my $key (keys %dependent_xrefs){
- print $key."\t".$dependent_xrefs{$key}."\n";
+ print $key."\t".$dependent_xrefs{$key}."\n" if($verbose);
}
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/UniProtParser_descriptions_only.pm b/misc-scripts/xref_mapping/XrefParser/UniProtParser_descriptions_only.pm
index cae047405d..fe5e8cd13d 100644
--- a/misc-scripts/xref_mapping/XrefParser/UniProtParser_descriptions_only.pm
+++ b/misc-scripts/xref_mapping/XrefParser/UniProtParser_descriptions_only.pm
@@ -21,8 +21,8 @@ use base qw( XrefParser::BaseParser );
if (!defined(caller())) {
if (scalar(@ARGV) != 3) {
- print "\nUsage: UniProtParser.pm file.SPC <source_id> <species_id>\n\n";
- print scalar(@ARGV);
+ print STDERR "\nUsage: UniProtParser.pm file.SPC <source_id> <species_id>\n\n";
+ print STDERR scalar(@ARGV);
exit(1);
}
@@ -30,16 +30,21 @@ if (!defined(caller())) {
}
+my $verbose;
+
# --------------------------------------------------------------------------------
sub run {
my $self = shift if (defined(caller(1)));
- my $source_id = shift;
- my $species_id = shift;
- my $file = shift;
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
my $release_file = shift;
+ $verbose = shift;
+
+ my $file = @{$files}[0];
my $species_name;
@@ -54,8 +59,8 @@ sub run {
$sptr_source_id =
$self->get_source_id_for_source_name('Uniprot/SPTREMBL');
- print "SwissProt source id for $file: $sp_source_id\n";
- print "SpTREMBL source id for $file: $sptr_source_id\n";
+ print "SwissProt source id for $file: $sp_source_id\n" if($verbose);
+ print "SpTREMBL source id for $file: $sptr_source_id\n" if($verbose);
my @xrefs =
@@ -68,7 +73,7 @@ sub run {
# delete previous if running directly rather than via BaseParser
if (!defined(caller(1))) {
- print "Deleting previous xrefs for these sources\n";
+ print "Deleting previous xrefs for these sources\n" if($verbose);
$self->delete_by_source(\@xrefs);
}
@@ -93,10 +98,10 @@ sub run {
while ( defined( my $line = $release_io->getline() ) ) {
if ( $line =~ m#(UniProtKB/Swiss-Prot Release .*)# ) {
$sp_release = $1;
- print "Swiss-Prot release is '$sp_release'\n";
+ print "Swiss-Prot release is '$sp_release'\n" if($verbose);
} elsif ( $line =~ m#(UniProtKB/TrEMBL Release .*)# ) {
$sptr_release = $1;
- print "SpTrEMBL release is '$sptr_release'\n";
+ print "SpTrEMBL release is '$sptr_release'\n" if($verbose);
}
}
$release_io->close();
@@ -133,11 +138,11 @@ sub get_species {
if (defined $species_name) {
- print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n";
+ print "Taxonomy ID " . $taxonomy_id . " corresponds to species ID " . $species_id . " name " . $species_name . "\n" if($verbose);
} else {
- print "Cannot find species corresponding to taxonomy ID " . $species_id . " - check species table\n";
+ print STDERR "Cannot find species corresponding to taxonomy ID " . $species_id . " - check species table\n";
exit(1);
}
@@ -168,8 +173,8 @@ sub create_xrefs {
$self->get_source_id_for_source_name(
'Uniprot/SPTREMBL_predicted');
- print "Predicted SwissProt source id for $file: $sp_pred_source_id\n";
- print "Predicted SpTREMBL source id for $file: $sptr_pred_source_id\n";
+ print "Predicted SwissProt source id for $file: $sp_pred_source_id\n" if($verbose);
+ print "Predicted SpTREMBL source id for $file: $sptr_pred_source_id\n" if($verbose);
my $uniprot_io = $self->get_filehandle($file);
if ( !defined $uniprot_io ) { return undef }
@@ -295,8 +300,8 @@ sub create_xrefs {
$uniprot_io->close();
- print "Read $num_sp SwissProt xrefs and $num_sptr SPTrEMBL xrefs from $file\n";
- print "Found $num_sp_pred predicted SwissProt xrefs and $num_sptr_pred predicted SPTrEMBL xrefs\n" if ($num_sp_pred > 0 || $num_sptr_pred > 0);
+ print "Read $num_sp SwissProt xrefs and $num_sptr SPTrEMBL xrefs from $file\n" if($verbose);
+ print "Found $num_sp_pred predicted SwissProt xrefs and $num_sptr_pred predicted SPTrEMBL xrefs\n" if (($num_sp_pred > 0 || $num_sptr_pred > 0) and $verbose);
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/UniProtVarSplicParser.pm b/misc-scripts/xref_mapping/XrefParser/UniProtVarSplicParser.pm
index 9b3a6dad7d..2ac20eb65c 100644
--- a/misc-scripts/xref_mapping/XrefParser/UniProtVarSplicParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/UniProtVarSplicParser.pm
@@ -18,7 +18,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ( $self, $source_id, $species_id, $file, $release_file ) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my @xrefs;
@@ -27,12 +35,13 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 error
}
my %swiss = %{ $self->get_valid_codes( "uniprot", $species_id ) };
+ print scalar(%swiss)." uniprot entries will be used as tests\n" if($verbose);
my $missed = 0;
while ( $_ = $file_io->getline() ) {
my $xref;
@@ -68,8 +77,8 @@ sub run {
$file_io->close();
- print $missed." ignored as original uniprot not found in database\n";
- print scalar(@xrefs) . " UniProtVarSplic xrefs succesfully parsed\n";
+ print $missed." ignored as original uniprot not found in database\n" if($verbose);
+ print scalar(@xrefs) . " UniProtVarSplic xrefs succesfully parsed\n" if($verbose);
$self->upload_xref_object_graphs(\@xrefs);
@@ -79,7 +88,7 @@ sub run {
my $release_io = $self->get_filehandle($release_file);
while ( defined( my $line = $release_io->getline() ) ) {
if ( $line =~ m#(UniProtKB/Swiss-Prot Release .*)# ) {
- print "Swiss-Prot release is '$1'\n";
+ print "Swiss-Prot release is '$1'\n" if($verbose);
$self->set_release( $source_id, $1 );
}
}
@@ -87,7 +96,6 @@ sub run {
}
- print "Done\n";
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/VbDirectParser.pm b/misc-scripts/xref_mapping/XrefParser/VbDirectParser.pm
index 91e8ef7508..e9d3b88451 100644
--- a/misc-scripts/xref_mapping/XrefParser/VbDirectParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/VbDirectParser.pm
@@ -23,33 +23,25 @@ sub run {
my $i=0;
print STDERR "source: ".$source_id."\tspecies: ".$species_id."\n";
-# while ($ln = <INFILE>) {
-my $type = "transcript";
+ my $type = "transcript";
while (my $ln = <INFILE>) {
-# print STDERR $ln."\t!\n";
chomp($ln);
my ($probe,$id, $version, $description, $ensembl_id) = split("\t",$ln);
$i++;
- my $xref_id = XrefParser::BaseParser->get_xref($probe, $source_id);
+ my $xref_id = XrefParser::BaseParser->get_xref($probe, $source_id, $species_id);
if (!defined($xref_id) || $xref_id eq "") {
-# print STDERR "adding xref\n";
$xref_id = XrefParser::BaseParser->add_xref($probe, 1, $probe, $description, $source_id, $species_id);
}
-# else {
-# print "xref found in DB\t".$xref_id."\n";
-# }
-# print "xref = ".$xref_id."\n";
XrefParser::BaseParser->add_direct_xref($xref_id, $ensembl_id, $type, $probe);
}
- print $i." VB direct xrefs succesfully parsed\n";
+ print $i." VB direct xrefs succesfully parsed\n" if($verbose);
close(INFILE);
- print "Done\n";
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/VbGFF3Parser.pm b/misc-scripts/xref_mapping/XrefParser/VbGFF3Parser.pm
index f154b74399..950efaa284 100644
--- a/misc-scripts/xref_mapping/XrefParser/VbGFF3Parser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/VbGFF3Parser.pm
@@ -12,10 +12,18 @@ use base qw( XrefParser::CoordinateParser );
# Parser for GFF3-format probe mappings from Vectorbase
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
+
open (INFILE, "<$file");
my $i=0; my $type = "transcript";
- print STDERR "source: ".$source_id."\tspecies: ".$species_id."\n";
while (my $ln = <INFILE>) {
# # parse GFF line:
chomp($ln); $i++;
@@ -62,12 +70,12 @@ sub run {
'cdsEnd' => $end,
'exonStarts' => $start,
'exonEnds' => $end );
- print STDERR "$name, $start, $end\n";
+ print STDERR "$name, $start, $end\n" if($verbose);
$self->add_xref( $source_id, $species_id, \%xref );
}
}
}
- print STDERR $i." VB GFF3 xrefs succesfully parsed\n";
+ print STDERR $i." VB GFF3 xrefs succesfully parsed\n" if($verbose);
close(INFILE);
return 0;
diff --git a/misc-scripts/xref_mapping/XrefParser/VegaParser.pm b/misc-scripts/xref_mapping/XrefParser/VegaParser.pm
index 314a0911ea..2202b91874 100644
--- a/misc-scripts/xref_mapping/XrefParser/VegaParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/VegaParser.pm
@@ -22,17 +22,24 @@ use base qw( XrefParser::BaseParser );
sub run
{
- my $self = shift;
- my ( $source_id, $species_id, $file_name ) = @_;
-
- my $file_io = $self->get_filehandle($file_name);
-
- if ( !defined $file_io ) {
- return 1; # Failed.
- }
-
- my @xrefs;
- while ( defined( my $line = $file_io->getline() ) ) {
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files_ref = shift;
+ my $rel_file = shift;
+ my $verbose = shift;
+
+ my $file_name = @{$files_ref}[0];
+
+ my $file_io = $self->get_filehandle($file_name);
+
+ if ( !defined $file_io ) {
+ return 1; # Failed.
+ }
+
+ my @xrefs;
+ while ( defined( my $line = $file_io->getline() ) ) {
chomp $line;
if ( substr( $line, 0, 1 ) eq '>' ) {
@@ -62,11 +69,10 @@ sub run
}
}
- print scalar(@xrefs) . " Vega Fasta Xrefs successfully parsed\n";
$self->upload_xref_object_graphs( \@xrefs );
- print "Done\n";
+ print scalar(@xrefs) . " Vega Fasta Xrefs successfully parsed\n" if($verbose);
return 0; # Successful.
}
diff --git a/misc-scripts/xref_mapping/XrefParser/Vega_TranParser.pm b/misc-scripts/xref_mapping/XrefParser/Vega_TranParser.pm
index 4670b88c1f..5b7d3b6f55 100644
--- a/misc-scripts/xref_mapping/XrefParser/Vega_TranParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/Vega_TranParser.pm
@@ -13,6 +13,8 @@ sub run {
my ($self, $source_id, $species_id, $file) = @_;
+ die "No longer used try HGNC_curated_transcript\n";
+
my $vega_io = $self->get_filehandle($file);
my $clone_source_id =
@@ -21,7 +23,7 @@ sub run {
$self->get_source_id_for_source_name('HGNC_curated_transcript');
if ( !defined $vega_io ) {
- print "Could not open $file\n";
+ print STDERR "Could not open $file\n";
return 1;
}
@@ -55,7 +57,7 @@ sub run {
$self->add_direct_xref($xref_id, $stable_id, "transcript", "");
}
- print "Parsed $line_count lines from $file, added $xref_count xrefs and $xref_count direct_xrefs\n";
+ print "Parsed $line_count lines from $file, added $xref_count xrefs and $xref_count direct_xrefs\n" if($verbose);
$vega_io->close();
diff --git a/misc-scripts/xref_mapping/XrefParser/WilsonAffyParser.pm b/misc-scripts/xref_mapping/XrefParser/WilsonAffyParser.pm
index b2025e2850..9eb1ee65e6 100644
--- a/misc-scripts/xref_mapping/XrefParser/WilsonAffyParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/WilsonAffyParser.pm
@@ -10,9 +10,16 @@ my $syn_sth;
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
- my @xrefs = $self->create_xrefs($source_id, $species_id, $file);
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+# my ($self, $source_id, $species_id, $file) = @_;
+
+ my @xrefs = $self->create_xrefs($source_id, $species_id, @{$files}[0], $verbose);
if(!@xrefs){
return 1; # 1 error
@@ -27,7 +34,7 @@ sub run {
sub create_xrefs {
- my ($self, $source_id, $species_id, $file) = @_;
+ my ($self, $source_id, $species_id, $file, $verbose) = @_;
my ($count, $noseq, $direct) = (0,0,0);
@@ -38,7 +45,7 @@ sub create_xrefs {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 error
}
@@ -98,17 +105,15 @@ sub create_xrefs {
# Add description noting where the mapping came from
$xref->{DESCRIPTION} = $target . " used as mapping target";
- #print $xref->{ACCESSION} . " " . $target . " " . $? . "\n";
-
$count++;
- print "$count " if ($count % 100 == 0);
+ print "$count " if (($count % 100 == 0) and $verbose);
push @xrefs, $xref;
} else {
- print "Couldn't get sequence for $target\n";
+ print STDERR "Couldn't get sequence for $target\n";
$noseq++;
}
@@ -119,9 +124,11 @@ sub create_xrefs {
$file_io->close();
- print "\n\nParsed $count primary xrefs.\n";
- print "Couldn't get sequence for $noseq primary_xrefs\n" if ($noseq);
- print "Added $direct direct xrefs.\n";
+ if($verbose){
+ print "\n\nParsed $count primary xrefs.\n";
+ print "Couldn't get sequence for $noseq primary_xrefs\n" if ($noseq);
+ print "Added $direct direct xrefs.\n";
+ }
return \@xrefs;
diff --git a/misc-scripts/xref_mapping/XrefParser/WormPepParser.pm b/misc-scripts/xref_mapping/XrefParser/WormPepParser.pm
index 522c3544ed..e86d288af1 100644
--- a/misc-scripts/xref_mapping/XrefParser/WormPepParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/WormPepParser.pm
@@ -17,14 +17,20 @@ my $dep_sth;
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
- print STDERR "WORMPep source = $source_id\tspecies = $species_id\n";
my $worm_source_id = XrefParser::BaseParser->get_source_id_for_source_name('wormpep_id');
my $worm_locus_id = XrefParser::BaseParser->get_source_id_for_source_name('wormbase_locus');
- print STDERR "source = $worm_source_id, locus = $worm_locus_id.\n";
my $xref_sth = $self->dbi()->prepare("SELECT xref_id FROM xref WHERE accession=? AND source_id=$worm_source_id AND species_id=$species_id");
my $xref_sth2 = $self->dbi()->prepare("SELECT xref_id FROM xref WHERE accession=? AND source_id=$worm_locus_id AND species_id=$species_id");
@@ -32,7 +38,7 @@ sub run {
my $pep_io = $self->get_filehandle($file);
if ( !defined $pep_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 error
}
@@ -69,7 +75,7 @@ sub run {
$pep_io->close();
- print "Added $d_count direct xrefs and $x_count xrefs\n";
+ print "Added $d_count direct xrefs and $x_count xrefs\n" if($verbose);
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/WormbaseDatabaseStableIDParser.pm b/misc-scripts/xref_mapping/XrefParser/WormbaseDatabaseStableIDParser.pm
index 92d43cabed..a26e3f5b21 100644
--- a/misc-scripts/xref_mapping/XrefParser/WormbaseDatabaseStableIDParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/WormbaseDatabaseStableIDParser.pm
@@ -10,8 +10,7 @@ use strict;
use base qw( XrefParser::DatabaseParser );
sub run {
-
- my ($self, $dsn, $source_id, $species_id) = @_;
+ my ($self, $dsn, $source_id, $species_id, $verbose) = @_;
my $db = $self->connect($dsn); # source db (probably core)
my $xref_db = $self->dbi();
@@ -22,7 +21,7 @@ sub run {
# read stable IDs
foreach my $type ('gene', 'transcript') {
- print "Building xrefs from $type stable IDs\n";
+ print "Building xrefs from $type stable IDs\n" if($verbose);
my $wb_source_id = $self->get_source_id_for_source_name("wormbase_$type");
diff --git a/misc-scripts/xref_mapping/XrefParser/XenopusJamboreeParser.pm b/misc-scripts/xref_mapping/XrefParser/XenopusJamboreeParser.pm
index c9b1535209..38280dd582 100644
--- a/misc-scripts/xref_mapping/XrefParser/XenopusJamboreeParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/XenopusJamboreeParser.pm
@@ -15,7 +15,15 @@ use base qw( XrefParser::BaseParser );
sub run {
- my ($self, $source_id, $species_id, $file) = @_;
+ my $self = shift if (defined(caller(1)));
+
+ my $source_id = shift;
+ my $species_id = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
my @xrefs;
@@ -24,7 +32,7 @@ sub run {
my $file_io = $self->getline($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open $file\n";
+ print STDERR "ERROR: Could not open $file\n";
return 1; # 1 error
}
@@ -56,13 +64,12 @@ sub run {
$file_io->close();
- print scalar(@xrefs) . " XenopusJamboreeParser xrefs succesfully parsed\n";
+ print scalar(@xrefs) . " XenopusJamboreeParser xrefs succesfully parsed\n" if($verbose);
if(!defined(XrefParser::BaseParser->upload_xref_object_graphs(\@xrefs))){
return 1; #1 error
}
- print "Done\n";
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/ZFINParser.pm b/misc-scripts/xref_mapping/XrefParser/ZFINParser.pm
index 6dae3ce2b1..a235f1040a 100644
--- a/misc-scripts/xref_mapping/XrefParser/ZFINParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/ZFINParser.pm
@@ -13,7 +13,7 @@ use base qw( XrefParser::BaseParser );
if (!defined(caller())) {
if (scalar(@ARGV) != 1) {
- print "\nUsage: ZFINParser.pm file <source_id> <species_id>\n\n";
+ print STDERR "\nUsage: ZFINParser.pm file <source_id> <species_id>\n\n";
exit(1);
}
@@ -21,13 +21,18 @@ if (!defined(caller())) {
}
+
sub run {
my $self = shift if (defined(caller(1)));
my $source_id = shift;
my $species_id = shift;
- my $file = shift;
+ my $files = shift;
+ my $release_file = shift;
+ my $verbose = shift;
+
+ my $file = @{$files}[0];
if(!defined($source_id)){
$source_id = XrefParser::BaseParser->get_source_id_for_filename($file);
@@ -46,8 +51,7 @@ sub run {
$self->get_filehandle( catfile( $dir, 'uniprot.txt' ) );
if ( !defined $swissprot_io ) {
- print( "ERROR: Could not open " . catfile( $dir, 'uniprot.txt' ),
- "\n" );
+ print STDERR "ERROR: Could not open " . catfile( $dir, 'uniprot.txt' ). "\n" ;
return 1; # 1 error
}
@@ -78,8 +82,7 @@ sub run {
my $refseq_io = $self->get_filehandle( catfile( $dir, 'refseq.txt' ) );
if ( !defined $refseq_io ) {
- print( "ERROR: Could not open " . catfile( $dir, 'refseq.txt' ),
- "\n" );
+ print STDERR "ERROR: Could not open " . catfile( $dir, 'refseq.txt' ),"\n" ;
return 1;
}
@@ -106,8 +109,7 @@ sub run {
my $zfin_io = $self->get_filehandle( catfile( $dir, 'aliases.txt' ) );
if ( !defined $zfin_io ) {
- print( "ERROR: Could not open " . catfile( $dir, 'aliases.txt' ),
- "\n" );
+ print STDERR "ERROR: Could not open " . catfile( $dir, 'aliases.txt' ), "\n" ;
return 1;
}
@@ -120,17 +122,19 @@ sub run {
chomp;
my ($acc, undef, undef, $syn) = split (/\t/,$_);
if(defined($zfin{$acc})){
- XrefParser::BaseParser->add_to_syn($acc, $source_id, $syn);
+ XrefParser::BaseParser->add_to_syn($acc, $source_id, $syn, $species_id);
$syncount++;
}
}
$zfin_io->close();
- print "\t$spcount xrefs from UniProt and\n";
- print "\t$rscount xrefs from RefSeq succesfully loaded\n";
- print "\t$syncount synonyms loaded\n";
- print "\t$mismatch xrefs ignored\n";
+ if($verbose){
+ print "\t$spcount xrefs from UniProt and\n";
+ print "\t$rscount xrefs from RefSeq succesfully loaded\n";
+ print "\t$syncount synonyms loaded\n";
+ print "\t$mismatch xrefs ignored\n";
+ }
return 0;
}
diff --git a/misc-scripts/xref_mapping/XrefParser/ncRNAParser.pm b/misc-scripts/xref_mapping/XrefParser/ncRNAParser.pm
index a0478ba73a..9fc2ce5e67 100644
--- a/misc-scripts/xref_mapping/XrefParser/ncRNAParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/ncRNAParser.pm
@@ -12,7 +12,7 @@ use base qw( XrefParser::BaseParser );
if (!defined(caller())) {
if (scalar(@ARGV) != 1) {
- print "\nUsage: ncRNAParser.pm file <source_id> <species_id>\n\n";
+ print STDERR "\nUsage: ncRNAParser.pm file <source_id> <species_id>\n\n";
exit(1);
}
@@ -41,7 +41,7 @@ sub run {
my $file_io = $self->get_filehandle($file);
if ( !defined $file_io ) {
- print "ERROR: Could not open file $file\n";
+ print STDERR "ERROR: Could not open file $file\n";
return 1;
}
@@ -67,7 +67,7 @@ sub run {
}
$name_2_source_id{$source_name} = $tmp;
}
- my $xref_id = $self->get_xref($acc,$name_2_source_id{$source_name});
+ my $xref_id = $self->get_xref($acc,$name_2_source_id{$source_name}, $species_id);
if(!defined($xref_id)){
$xref_id = $self->add_xref($acc,"",$display_label,$description,$name_2_source_id{$source_name}, $species_id);
$added++;
@@ -82,7 +82,7 @@ sub run {
$file_io->close();
- print "Added $added Xrefs for ncRNAs\n";
+ print "Added $added Xrefs for ncRNAs\n" if($verbose);
return 0;
}
--
GitLab