Bio::Tools WWW
SummaryIncluded librariesPackage variablesSynopsisDescriptionGeneral documentationMethods
Toolbar
WebCvsRaw content
Summary
Bio::Tools::WWW - Bioperl manager for web resources related to biology.
Package variables
Globals (from "use vars" definitions)
$BioWWW
%EXPORT_TAGS
$AUTHORITY = 'nobody@localhost'
@EXPORT_OK = qw($BioWWW)
$VERSION
$Revision
$ID
Privates (from "my" definitions)
%Home_url = ( 'bioperl' =>'http://bio.perl.org/', 'bioperl-stanford'=>'http://genome-www.stanford.edu/perlOOP/bioperl/', 'bioperl-schema' =>'http://bio.perl.org/Projects/Schema/', 'biomoo' =>'http://bioinformatics.weizmann.ac.il/BioMOO/', 'blast_ncbi' =>'http://www.ncbi.nlm.nih.gov/BLAST/', 'blast_wu' =>'http://blast.wustl.edu/', 'bsm' =>'http://www.biochem.ucl.ac.uk/bsm/', 'clustal' =>'http://www.csc.fi/molbio/progs/clustalw/clustalw.html', 'ebi' =>'http://www.ebi.ac.uk/', 'emotif' =>'http://motif.Stanford.EDU/emotif', 'entrez' =>'http://www3.ncbi.nlm.nih.gov/Entrez/', 'expasy' =>'http://www.expasy.ch/', 'gdb' =>'http://www.gdb.org/', 'mips' =>'http://speedy.mips.biochem.mpg.de/', 'mmdb' =>'http://www.ncbi.nlm.nih.gov/Structure/', 'modbase' =>'http://guitar.rockefeller.edu/', 'ncbi' =>'http://www.ncbi.nlm.nih.gov/', 'pedant' =>'http://pedant.mips.biochem.mpg.de', 'phylip' =>'http://evolution.genetics.washington.edu/phylip.html', 'pir' =>'http://www-nbrf.georgetown.edu/pir/', 'pfam' =>'http://pfam.wustl.edu/', 'pfam_uk' =>'http://www.sanger.ac.uk/Software/Pfam/', 'pfam_us' =>'http://pfam.wustl.edu/', 'pdb' =>'http://www.pdb.bnl.gov/', 'presage' =>'http://presage.stanford.edu/', 'geneQuiz' =>'http://www.sander.ebi.ac.uk/genequiz/genomes/sc/', 'molMov' =>'http://bioinfo.mbb.yale.edu/MolMovDB/', 'pubmed' =>'http://www.ncbi.nlm.nih.gov/PubMed/', 'sacch3d' =>'http://genome-www.stanford.edu/Sacch3D/', 'sgd' =>'http://genome-www.stanford.edu/Saccharomyces/', 'scop' =>'http://scop.stanford.edu/scop/', 'swissProt' =>'http://www.expasy.ch/sprot/sprot-top.html', 'webmol' =>'http://genome-www.stanford.edu/structure/webmol/', 'ypd' =>'http://quest7.proteome.com/YPDhome.html', )
%SGD_url = ('home' =>$Home_url{'sgd'}, 'help' =>$Home_url{'sgd'}.'help/', 'mammal' =>$Home_url{'sgd'}.'mammal/', 'worm' =>$Home_url{'sgd'}.'worm/', 'gene' =>$SGD_stem_url{'sacchdb'}.'find+Locus+', 'locus' =>$SGD_stem_url{'sacchdb'}.'find+Locus+', 'orf' =>$SGD_stem_url{'sacchdb'}.'find+Locus+', 'mipsorf' =>$SGD_stem_url{'sgd'}."mips-orfs?", 'gene_info' =>$SGD_stem_url{'sacchdb'}.'find+Gene_Info+', 'prot_info' =>$SGD_stem_url{'sacchdb'}.'find+Protein_Info+', 'seq' =>$SGD_stem_url{'sgd'}.'seqDisplay?seq=', 'gi' =>$SGD_stem_url{'sacchdb'}.'find+Sequence+Database+=+GenPept+AND+NEXT+=+', 'chr' =>$SGD_stem_url{'sgd2'}.'seqTools?chr=', 'chr_old' =>$SGD_stem_url{'sgd'}.'dnaredir?chr=', 'seq_an' =>$SGD_stem_url{'sgd2'}.'seqTools?seqname=', 'seq_an_old' =>$SGD_stem_url{'sgd'}.'dnaredir?seqname=', 'map_chr' =>$SGD_stem_url{'sgd'}.'ORFMAP/ORFmap?chr=', 'map_orf' =>$SGD_stem_url{'sgd'}.'ORFMAP/ORFmap?seq=', 'feature' =>$SGD_stem_url{'sgd2'}.'featureform?chr=', 'search' =>$SGD_stem_url{'sgd'}.'search?', 'images' =>$SGD_stem_url{'stanford'}.'images/', 'suggest' =>$SGD_stem_url{'stanford'}.'forms/sgd-suggestion.html', 'tmp' =>$SGD_stem_url{'stanford'}.'tmp/', )
%SGD_stem_url = ('stanford' =>'http://genome-www.stanford.edu/', 'sgd' =>'http://genome-www.stanford.edu/cgi-bin/SGD/', 'sgd2' =>'http://genome-www2.stanford.edu/cgi-bin/SGD/', 's3d' =>'http://genome-www.stanford.edu/cgi-bin/SGD/Sacch3D/', 's3d2' =>'http://genome-www2.stanford.edu/cgi-bin/SGD/Sacch3D/', 's3d3' =>'http://genome-www3.stanford.edu/cgi-bin/SGD/Sacch3D/', 'sacchdb' =>'http://genome-www.stanford.edu/cgi-bin/dbrun/SacchDB?', )
%Stem_url = ( 'emotif' =>'http://dna.Stanford.EDU/cgi-bin/emotif/', 'entrez' =>'http://www3.ncbi.nlm.nih.gov/htbin-post/Entrez/query?', 'pdb' =>'http://www.pdb.bnl.gov/pdb-bin/', 'pfam_uk' =>'http://www.sanger.ac.uk/cgi-bin/Pfam/', 'pfam_us' =>'http://pfam.wustl.edu/cgi-bin/', 'pir' =>'http://www-nbrf.georgetown.edu/cgi-bin/nbrfget?', )
%Search_url = ( '3db' =>$Stem_url{'pdb'}.'opdbshort?oPDBid=', 'embl' =>$Home_url{'ebi'}.'htbin/emblfetch?', 'expasy' =>$Home_url{'expasy'}.'cgi-bin/', 'cath' =>$Home_url{'bsm'}.'cath/CATHSrch.pl?type=PDB&query=', 'cog_seq' =>$Home_url{'ncbi'}.'cgi-bin/COG/nph-cognitor?seq=', 'cog_orf' =>$Home_url{'ncbi'}.'cgi-bin/COG/cogeseq?', 'ec1' =>$Home_url{'gdb'}.'bin/bio/wais_q-bio?object_class_key=30&jhu_id=', 'ec2' =>$Home_url{'bsm'}.'enzymes/', 'ec3' =>$Home_url{'expasy'}.'cgi-bin/get-enzyme-entry?', 'emotif_id' =>$Stem_url{'emotif'}.'nph-identify?sequence=', 'entrez' =>$Stem_url{'entrez'}."db=p_r?db=1&choseninfo=ORF_NAME%20[Gene%20Name]\@1\@1&form=4&field=Gene%20Name&mode=0&retrievestring=ORF_NAME%20[Gene%20Name]", 'gb_n' =>$Stem_url{'entrez'}."db=n&form=6&dopt=g&uid=", 'gb_p' =>$Stem_url{'entrez'}."db=p&form=6&dopt=g&uid=", 'gb_struct' =>$Stem_url{'entrez'}."db=t&form=6&dopt=s&uid=", 'pdb' =>$Stem_url{'pdb'}.'send-text?filename=', 'medline' =>$Stem_url{'entrez'}.'form=6&db=m&Dopt=r&uid=', 'mmdb' =>$Stem_url{'entrez'}.'db=t&form=6&Dopt=s&uid=', 'modbase_orf' =>$Home_url{'modbase'}.'gm-cgi-bin/orf_page.cgi?pg1=0.5&pg2=1.0&orf=', 'modbase_model' =>$Home_url{'modbase'}.'gm-cgi-bin/model_page.cgi?pg1=0.5&pg2=1.0&orf=', 'molMov' =>$Home_url{'molMov'}.'search.cgi?pdb=', 'pdb' =>$Stem_url{'pdb'}.'opdbshort?oPDBid=', 'pdb_coord' =>$Stem_url{'pdb'}.'send-pdb?filename=', 'pfam' =>$Home_url{'pfam'}.'cgi-bin/nph-hmm_search?evalue=1.0&protseq=', 'pfam_sp_uk' =>$Stem_url{'pfam_uk'}.'swisspfamget.pl?name=', 'pfam_seq_uk' =>$Stem_url{'pfam_uk'}.'nph-search.cgi?evalue=1.0&type=normal&protseq=', 'pfam_sp_us' =>$Stem_url{'pfam_us'}.'getswisspfam?key=', 'pfam_seq_us' =>$Stem_url{'pfam_us'}.'nph-hmm_search?evalue=1.0&protseq=', 'pfam_form' =>$Home_url{'pfam'}.'cgi-bin/hmm_page.cgi', 'pir_id' =>$Stem_url{'pir'}.'fmt=c&xref=0&id=', 'pir_acc' =>$Stem_url{'pir'}.'fmt=c&xref=1&id=', 'pir_uid' =>$Stem_url{'pir'}.'uid=', 'pdbSum' =>$Home_url{'bsm'}.'cath/GetPDBSUMCODE.pl?code=', 'presage_sp' =>$Home_url{'presage'}.'search.cgi?spac=', 'swpr' =>$Home_url{'expasy'}.'cgi-bin/get-sprot-entry?', 'swModel' =>$Home_url{'expasy'}.'cgi-bin/sprot-swmodel-sub?', 'swprSearch' =>$Home_url{'expasy'}.'cgi-bin/sprot-search-ful?', 'scop' =>$Home_url{'scop'}.'search.cgi?pdb=', 'scop_pdb' =>$Home_url{'scop'}.'search.cgi?pdb=', 'scop_data' =>$Home_url{'scop'}.'data/scop.', 'wormpep' =>'http://www.sanger.ac.uk/cgi-bin/wormpep_fetch.pl?entry=', 'wormace' =>'http://webace.sanger.ac.uk/cgi-bin/webace?db=wormace&class=Sequence&text=yes&object=', 'ypd' =>'http://quest7.proteome.com/YPD/', )
$Not_found_url = 'http://genome-www.stanford.edu/Sacch3D/notfound.html'
%S3d_url = ('home' =>$Home_url{'sacch3d'}, 'search' =>$Home_url{'sacch3d'}.'search.html', 'help' =>$Home_url{'sacch3d'}.'help/', 'new' =>$Home_url{'sacch3d'}.'new/', 'chrm' =>$Home_url{'sacch3d'}.'data/chr', 'domains' =>$Home_url{'sacch3d'}.'domains/', 'genequiz' =>$Home_url{'sacch3d'}.'genequiz/', 'analysis' =>$Home_url{'sacch3d'}.'analysis/', 'scop' =>$SGD_stem_url{'s3d3'}.'getscop?data=', 'scop_fold' =>$SGD_stem_url{'s3d3'}.'getscop?type=fold&data=', 'scop_class' =>$SGD_stem_url{'s3d3'}.'getscop?type=class&data=', 'scop_gene' =>$SGD_stem_url{'s3d3'}.'getscop?type=gene&data=', 'gene' =>$SGD_stem_url{'s3d'}.'get?class=gene&item=', 'orf' =>$SGD_stem_url{'s3d'}.'get?class=orf&item=', 'text' =>$SGD_stem_url{'s3d'}.'get?class=text&item=', 'pdb' =>$SGD_stem_url{'s3d'}.'get?class=pdb&item=', 'pdb_coord' =>$SGD_stem_url{'s3d'}.'pdbcoord.pl?id=', 'dsc' =>$SGD_stem_url{'s3d'}.'dsc.pl?gene=', 'emotif' =>$SGD_stem_url{'s3d'}.'seq_search.pl?db=emotif&gene=', 'pfam' =>$SGD_stem_url{'s3d'}.'seq_search.pl?db=pfam&gene=', 'pfam_uk' =>$SGD_stem_url{'s3d'}.'seq_search.pl?db=pfam&loc=uk&gene=', 'pfam_us' =>$SGD_stem_url{'s3d'}.'seq_search.pl?db=pfam&loc=us&gene=', 'blast_pdb' =>$SGD_stem_url{'s3d'}.'getblast?db=pdb&name=', 'blast_nr' =>$SGD_stem_url{'s3d'}.'getblast?db=nr&name=', 'blast_est' =>$SGD_stem_url{'s3d'}.'getblast?db=est&name=', 'blast_mammal' =>$SGD_stem_url{'s3d'}.'getblast?db=mammal&name=', 'blast_human' =>$SGD_stem_url{'s3d'}.'getblast?db=human&name=', 'blast_worm' =>$SGD_stem_url{'s3d'}.'getblast?db=worm&name=', 'blast_yeast' =>$SGD_stem_url{'s3d'}.'getblast?db=yeast&name=', 'blast_worm_yeast'=>$SGD_stem_url{'s3d'}.'getblast?db=worm&query=worm&name=', 'patmatch' =>$SGD_stem_url{'s3d2'}.'grepmatch?', 'grepmatch' =>$SGD_stem_url{'s3d2'}.'grepmatch?', 'pdb_neighbors' =>$SGD_stem_url{'s3d'}.'pdb_neighbors?id=CHAIN&gene=ORF_NAME', )
%Html = ('authority' =>qq|<A HREF="mailto:$AUTHORITY"><b>$AUTHORITY</b></A>|, 'trouble' => <<"QQ_TROUBLE_QQ",<p>If this problem persists, <A HREF="mailto:$AUTHORITY"><b>please notify us.</b></A>Include a copy of this error page with your message. Thanks.<p>QQ_TROUBLE_QQ 'notify' => <<"QQ_NOTIFY_QQ",<A HREF="mailto:$AUTHORITY"><b>Please notify us.</b></A>Include a copy of this error page with your message. Thanks.<p>QQ_NOTIFY_QQ 'ourFault' => <<"QQ_FAULT_QQ",<p><b>This is our fault!</b> There is apparently a problem with our software that we may not know about. <A HREF="mailto:$AUTHORITY"><b>Please notify us!</b></A>Include a copy of this error page with your message. Thanks.<p>QQ_FAULT_QQ 'techDiff' => <<"QQ_TECH_QQ",<p><big>We are experiencing technical difficulties now.<br>We will have the problem fixed soon. Sorry for any inconvenience.</big><p> QQ_TECH_QQ )
$Tmp_url = 'http://genome-www.stanford.edu/tmp/'
%Viewer_url = ( 'java' =>$SGD_stem_url{'sgd'}.'Sacch3D/pdbViewer.pl?pdbCode=', 'webmol' =>$SGD_stem_url{'sgd'}.'Sacch3D/pdbViewer.pl?pdbCode=', 'codebase' =>$SGD_stem_url{'stanford'}.'structure/webmol/lib', 'rasmol' =>$Stem_url{'pdb'}.'send-ras?filename=', 'chime' =>$Stem_url{'pdb'}.'ccpeek?id=', 'cn3d' =>$Stem_url{'entrez'}.'db=t&form=6&Dopt=i&Complexity=Cn3D+Subset&uid=', 'kinemage' =>'http://prosci.org/Kinemage', )
Included modules
Bio::Root::Root
Exporter ( )
Inherit
Bio::Root::Root Exporter
Synopsis
    use Bio::Tools qw(:obj);

    $pdb = $BioWWW->home_url('pdb');
There is no need to create a new Bio::Tools::WWW.pm object when the
:obj tag is used. This tag will import the static $BioWWW object
created by Bio::Tools::WWW.pm into your name space. This saves you
from having to call new Bio::Tools::WWW.
You are free to not use the :obj tag and create the object as you
like, but a Bio::Tools::WWW object is not configurable; any given
script only needs a single copy.
Description
Bio::Tools::WWW is primarily a URL broker for a select set
of sites related to bioinformatics/genome analysis. It
definitely represents a biased, unexhaustive set.
It might be more accurate to call this module
"Bio::Tools::URL.pm". But this module does handle some non-URL
things and it may do more of this in the future. Having one
module to cover all biologically relevant web utilities
makes it more convenient, especially at this early stage
of development.
Maintaining accurate URLs over time can be challenging as
new web sites spring up and old sites are re-organized. Because
of this fact, the URLs in this module are not guaranteed to be
correct or exhaustive and will require periodic updating. By keeping URL management within Bio::Tools::WWW.pm, other generic
modules can easily access a variety of different web sites without
having to know about a potential multitude of specific modules
specialized for one database or another. An alternative approach would
be to have addresses defined within modules specialized for different
web sites. This, however, may create maintenance headaches when updating
these addresses. Websites with complex datasets may require special treatment
within this module. As an example,
URLs for the Saccharomyces Genome Database are clustered
separately in this module, due to (1) the different ways to
access information at this database and (2) the familiarity
of the developer with this database. The Bio::SGD::WWW.pm inherits from
Bio::Tools::WWW.pm to permit access to the URLs provided by Bio::Tools::WWW.pm
and to SGD-specific HTML and images.
The organization of Bio::Tools::WWW.pm is expected to evolve as
websites get born, die, and mutate their APIs.
Methods
home_urlDescriptionCode
htmlDescriptionCode
html_footer
No description
Code
not_found_urlDescriptionCode
preDescriptionCode
redirectDescriptionCode
s3d_linkDescriptionCode
s3d_urlDescriptionCode
search_linkDescriptionCode
search_urlDescriptionCode
sgd_linkDescriptionCode
sgd_stem_urlDescriptionCode
sgd_urlDescriptionCode
start_htmlDescriptionCode
stem_urlDescriptionCode
strip_htmlDescriptionCode
tmp_urlDescriptionCode
viewer_linkDescriptionCode
viewer_urlDescriptionCode
Methods description
home_urlcode    nextTop
 Usage     : $BioWWW->home_url(<string>)
 Purpose   : To obtain the homepage URL for a biological database or resource.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments are:
           :    bioperl  bioperl-schema  biomoo  bsm  ebi  emotif  entrez 
           :    expasy  mips  mmdb  ncbi  pir  pfam  pdb  geneQuiz  
           :    molMov  pubmed  sacch3d  sgd  scop  swissProt  webmol  ypd
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : The URLs listed here do not represent a complete list.
           : Expect this to evolve and grow with time.
See Also : search_url()
htmlcodeprevnextTop
 Usage     : $BioWWW->html(<string>)
 Purpose   : To obtain HTML-formatted text for frequently needed web-page messages.
 Returns   : String containing the HTML anchor ( qq|<A HREF="http://..."</A>|)
 Argument  : String.
           : Currently acceptable arguments are:
           :   authority  (mailto: link for webmaster; shows e-mail address as link)
           :   notify     (wraps mailto:authority link with text for link "please notify us")
           :   ourFault   ("this problem is our fault. If it persists <notify-link>")
           :   trouble    (same as ourFault but doesn't blame us for the problem)
           :   techDiff   ("we are experiencing technical difficulties. Please stand by.")
 Throws    : n/a
 Comments  : The authority (webmaster) is imported from the Bio::Root::Global.pm
           : module. The value for $AUTHORITY should be set there, or
           : customize this module so that it doesn't use Bio::Root::Global.pm.
not_found_urlcodeprevnextTop
 Usage     : $BioWWW->not_found_url()
 Purpose   : To obtain the URL for a web page to be shown in place of a 404 error.
 Returns   : String containing the URL (including "http://")
 Argument  : n/a
 Throws    : n/a
 Comments  : This URL should be customized as desired.
precodeprevnextTop
 Usage     : $BioWWW->pre("text to be pre-formatted");
 Purpose   : To produce HTML for text that is not to be formated by the brower.
 Returns   : String containing the "<pre>" formatted html.
 Argument  : n/a
 Throws    : n/a
 Status    : Experimental
redirectcodeprevnextTop
 Usage     : $BioWWW->redirect(<string>)
 Purpose   : Prints the header needed to redirect a web browser to a supplied URL. 
 Returns   : n/a; Prints the redirection header.
 Argument  : String containing the URL to be redirected to.
 Throws    : n/a
 Status    : Experimental
s3d_linkcodeprevnextTop
 Usage     : $BioWWW->s3d_link(<site>, <value>, <text>)
 Purpose   : Wrapper for s3d_url() that returns the complete URL within an HTML anchor.
 Returns   : String containing the URL (including "http://")
 Argument  : <site>  = string to be used as argument for s3d_url()
           : <value> = string to be appended to the s3d URL stem.
           : <text>  = string to be shown as the link text (default = <value>).
 Throws    : n/a
 Status    : Experimental
 Comments  : This accessor is specialized for the Saccharomyces Genome Database.
           : It is possible that it will be moved to SGD::WWW.pm in the future.
See Also : s3d_url(), sgd_link()
s3d_urlcodeprevnextTop
 Usage     : $BioWWW->s3d_url(<string>)
 Purpose   : To obtain the webpage URL or search stem for Sacch3D.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments (TODO).
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : This accessor is specialized for the Saccharomyces Genome Database.
           : It is possible that it will be moved to SGD::WWW.pm in the future.
See Also : search_url()
search_linkcodeprevnextTop
 Usage     : $BioWWW->search_link(<site>, <value>, <text>)
 Purpose   : Wrapper for search_url() that returns the URL within an HTML anchor.
 Returns   : String containing the HTML anchor ( qq|<A HREF="http://..."</A>|)
 Argument  : <site>  = string to be used as argument for search_url()
           : <value> = string to be appended to the search URL stem.
           : <text>  = string to be shown as the link text (default = <value>).
 Throws    : n/a
 Status    : Experimental
See Also : search_url()
search_urlcodeprevnextTop
 Usage     : $BioWWW->search_url(<string>)
 Purpose   : To provide a URL stem for a search engine at a biological database 
           : or resource.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments are:
           :   3db  embl  cath  ec1  ec2  ec3  emotif_id  entrez  gb1  gb2  
           :   gb3  gb4  gb5  pdb  medline  mmdb  pdb  pdb_coord  pfam  pir_acc  
           :   pdbSum  molMov  swpr  swModel  swprSearch  scop  scop_pdb  scop_data 
           :   ypd
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : Unlike the homepage URLs, this method does not return a complete
           : URL but a stem which must be further modified, typically by
           : appending data to it, before it can be used. The data appended
           : depends on the specific URL; typically, it is a database ID or
           : other unique identifier.
           : The requirements for each URL will be described here eventually.
           : 
           : The URLs listed here do not represent a complete list.
           : Expect this to evolve and grow with time.
           :
           : Given this complexity, it may be useful to provide special methods
           : for these different URLs. This would however result in an 
           : explosion of methods that might make this module less 
           : maintainable and harder to use.
See Also : home_url()
sgd_linkcodeprevnextTop
 Usage     : $BioWWW->sgd_link(<site>, <value>, <text>)
 Purpose   : Wrapper for sgd_url() that returns the complete URL within an HTML anchor.
 Returns   : String containing the URL (including "http://")
 Argument  : <site>  = string to be used as argument for sgd_url()
           : <value> = string to be appended to the sgd URL stem.
           : <text>  = string to be shown as the link text (default = <value>).
 Throws    : n/a
 Status    : Experimental
 Comments  : This accessor is specialized for the Saccharomyces Genome Database.
           : It is possible that it will be moved to SGD::WWW.pm in the future.
See Also : sgd_url(), s3d_link()
sgd_stem_urlcodeprevnextTop
 Usage     : $BioWWW->sgd_stem_url(<string>)
 Purpose   : To obtain the minimal stem URL for a SGD/Sacch3D CGI script.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments (TODO).
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : This accessor is specialized for the Saccharomyces Genome Database.
           : It is possible that it will be moved to SGD::WWW.pm in the future.
See Also : search_url()
sgd_urlcodeprevnextTop
 Usage     : $BioWWW->sgd_url(<string>)
 Purpose   : To obtain the webpage URL or search stem for SGD.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments (TODO).
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : This accessor is specialized for the Saccharomyces Genome Database.
           : It is possible that it will be moved to SGD::WWW.pm in the future.
See Also : search_url()
start_htmlcodeprevnextTop
 Usage     : $BioWWW->start_html()
 Purpose   : Prints the "Content-type: text/html\n\n<HTML>\n" header.
 Returns   : n/a; This method prints the Content-type string shown above.
 Argument  : n/a
 Throws    : n/a
 Status    : Experimental
 Comments  : This method prevents redundant invocations thus avoiding th
           : accidental printing of the "content-type..." on the page.
           : If using L. Stein's CGI.pm, this is similar to $query->header()
           : (Does CGI.pm prevent redundant invocation?)
stem_urlcodeprevnextTop
 Usage     : $BioWWW->stem_url(<string>)
 Purpose   : To obtain the minimal stem URL for searching a biological database or resource.
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments are:
           :    emotif  entrez  pdb
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : The URLs stems returned by this method are much more minimal than
           : this provided by search_url(). Use of these stems requires knowledge
           : of the CGI scripts which they invoke.
See Also : search_url()
strip_htmlcodeprevnextTop
 Usage     : $boolean = &strip_html( string_ref, [fast] );
 Purpose   : Removes HTML formatting from a supplied string.
 Returns   : Boolean: true if string was stripped, false if not.
 Argument  : string_ref = reference to a string containing the whole 
           :              web page to be stripped.
           : fast = a non-zero value. Optional. If set, a faster 
           :        but perhaps less thorough procedure is used for
           :        stripping. Default = not fast.
 Throws    : Exception if the argument is not a scalar reference.
 Comments  : Based on code originally written by Alex Dong Li
           : (ali@genet.sickkids.on.ca).
           : This is a more generic version of the function that appears 
           : in Bio::Tools::Blast::HTML.pm
           : This version does not perform any Blast-specific stripping.
           :
           : This employs a simple method for removing tags that
           : will fail under following conditions:
           :  1) if quoted > appears in a tag  (does this ever happen?)
           :  2) if a tag is split over multiple lines and this method is
           :     used to process one line at a time.
           :
           : Without fast mode, large HTML files can take exceedingly long times to
           : strip (e.g., 1Meg file with many tags can take 10 minutes versus 5 seconds
           : in fast mode. Try the swissprot yeast table). If you know the HTML to be
           : well-behaved (i.e., tags are not split across mutiple lines), use fast
           : mode for large, dense files.
tmp_urlcodeprevnextTop
 Usage     : $BioWWW->tmp_url()
 Purpose   : To obtain the URL for a temporary, web-accessible directory.
 Returns   : String containing the URL (including "http://")
 Argument  : n/a
 Throws    : n/a
 Comments  : This URL should be customized  as desired.
viewer_linkcodeprevnextTop
 Usage     : $BioWWW->viewer_link(<site>, <value>, <text>)
 Purpose   : Wrapper for viewer_url() that returns the complete URL within an HTML anchor.
 Returns   : String containing the HTML anchor ( qq|<A HREF="http://..."</A>|)
 Argument  : <site>  = string to be used as argument for viewer_url()
           : <value> = string to be appended to the viewer URL stem.
           : <text>  = string to be shown as the link text (default = <value>).
 Throws    : n/a
 Status    : Experimental
See Also : viewer_url()
viewer_urlcodeprevnextTop
 Usage     : $BioWWW->viewer_url(<string>)
 Purpose   : To obtain the stem URL for a 3D viewer (RasMol, WebMol, Cn3D)
 Returns   : String containing the URL (including "http://")
 Argument  : String
           : Currently acceptable arguments are:
           :    rasmol webmol cn3d java  (java is an alias for webmol)
 Throws    : Warns if argument cannot be resolved to a URL.
 Comments  : The 4-letter Brookhaven PDB identifier must be appended to the
           : URL provided by this method.
           : The URLs listed here do not represent a complete list.
           : Expect this to evolve and grow with time.
Methods code
home_urldescriptionprevnextTop
sub home_url {
 #-------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %Home_url;
    (exists $Home_url{$arg}) ? $Home_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
htmldescriptionprevnextTop
sub html {
 #----------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %Html;
    (exists $Html{$arg}) ? $Html{$arg} : "<pre>(missing HTML for\" $arg\")</pre>";
}


###
### Below are accessors specialized for the Saccharomyces Genome Database
### It is possible that they will be moved to Bio::SGD::WWW.pm in the future.
###
}
html_footerdescriptionprevnextTop
sub html_footer {
#----------------
    my( $self, @param ) = @_;  

    my( $linkTo, $linkText, $modified, $mail, $mailText, $top) = 
	$self->_rearrange([qw(LINKTO LINKTEXT MODIFIED MAIL MAILTEXT TOP)], @param);

    $modified = (scalar $modified) 
	? qq||<center><small><b>Last modified: $modified </b></small></center>| 
        : '';

    $linkTo ||= '';

#    $top = (defined $top) ? qq|<a href="top">Top</a><br>| : '';
    $top = qq||<a href="#top">Top</a>|;  ## Utilizing the HTML bug/feature wherein 
                                          ## a bogus name anchor defaults to the 
                                          ## top of the page. 

    return <<"HTML";	
<p>
<hr size=3 noshade width=95%>
$top | <a href="$linkTo"> $linkText</a><br>
$modified
<small><i><a href="mailto:$mail">$mailText</a></i></small>
</body></html>

HTML
}
not_found_urldescriptionprevnextTop
sub not_found_url {
  my $self = shift; $Not_found_url;
}
predescriptionprevnextTop
sub pre {
 #--------
    my $self = shift; 
    "<PRE>\n".shift()."\n</PRE>";
}


#----------------
}
redirectdescriptionprevnextTop
sub redirect {
#-------------
    my($self,$url) = @_;

    print "Location: $url\n";
    print "Content-type: text/html\n\n";
}
s3d_linkdescriptionprevnextTop
sub s3d_link {
 #--------------
    my($self,$arg,$value,$text) = @_; 
    my $url = $self->s3d_url($arg);
    $text ||= $value;
    qq||<A HREF="$url$value">$text</A>|;
}
s3d_urldescriptionprevnextTop
sub s3d_url {
 #-----------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %S3d_url;
    (exists $S3d_url{$arg}) ? $S3d_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
search_linkdescriptionprevnextTop
sub search_link {
 #---------------
    my($self,$arg,$value,$text) = @_; 
    my $url = $self->search_url($arg);
    $text ||= $value;
    qq||<A HREF="$url$value">$text</A>|;
}
search_urldescriptionprevnextTop
sub search_url {
 #--------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %Search_url;
    (exists $Search_url{$arg}) ? $Search_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
sgd_linkdescriptionprevnextTop
sub sgd_link {
 #--------------
    my($self,$arg,$value,$text) = @_; 
    my $url = $self->sgd_url($arg);
    $text ||= $value;
    qq||<A HREF="$url$value">$text</A>|;
}


#########################################################################
##                        INSTANCE METHODS                              
#########################################################################

## Note that similar functions to those presented below are also availble 
## via L. Stein's CGI.pm. These are more experimental versions.
}
sgd_stem_urldescriptionprevnextTop
sub sgd_stem_url {
 #-----------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %SGD_stem_url;
    (exists $SGD_stem_url{$arg}) ? $SGD_stem_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
sgd_urldescriptionprevnextTop
sub sgd_url {
 #------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %SGD_url;
    (exists $SGD_url{$arg}) ? $SGD_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
start_htmldescriptionprevnextTop
sub start_html {
 #---------------
    my $self=shift; 
    if(!$self->{'_started_html'}) {
	print "Content-type: text/html\n\n<HTML>\n";
	$self->{'_started_html'} = 1;
    }
}
stem_urldescriptionprevnextTop
sub stem_url {
#--------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %Stem_url;
    (exists $Stem_url{$arg}) ? $Stem_url{$arg}
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
strip_htmldescriptionprevnextTop
sub strip_html {
#---------------
    my ($self, $string_ref, $fast) = @_;

    ref $string_ref eq 'SCALAR' or 
	$self->throw("Can't strip HTML: ".
		     "Argument is should be a SCALAR reference not a ${\ref $string_ref}");

    my $str = $$string_ref;
    my $stripped = 0;

    if($fast) {
	# MULTI-STRING-MODE: Much faster than single-string mode
	# but will miss tags that span multiple lines.
	# This is fine if you know the HTML to be "well-behaved".
	
	my @lines = split("\n", $str);
	foreach (@lines) {
	    s/<[^>]+>|&nbsp//gi and $stripped = 1;
	}
	
	# This regexp likely won't work properly in this mode.
	foreach (@lines) {
	    s/(\A|\n)>\s+/\n\n>/gi and $stripped = 1;
	}
	$$string_ref = join ("\n", @lines);

    } else {

	# SINGLE-STRING-MODE: Can be very slow for long strings with many substitutions.
	
	# Removing all "<>" tags. 
	$str =~ s/<[^>]+>|&nbsp//sgi and $stripped = 1;
	
	# Re-uniting any lone '>' characters. Not really necessary for functional HTML
	$str =~ s/(\A|\n)>\s+/\n\n>/sgi and $stripped = 1;
	
	$$string_ref = $str;
    }
    $stripped;
}


1;
__END__

########################################################################
##                            END OF CLASS                             
########################################################################
}
tmp_urldescriptionprevnextTop
sub tmp_url {
  my $self = shift; $Tmp_url;
}
viewer_linkdescriptionprevnextTop
sub viewer_link {
 #----------------
    my($self,$arg,$value,$text) = @_; 
    my $url = $self->viewer_url($arg);
    $text ||= $value;
    qq||<A HREF="$url$value">$text</A>|;
}
viewer_urldescriptionprevnextTop
sub viewer_url {
 #---------------
    my($self,$arg) = @_; 
    $arg eq 'all' and return %Viewer_url;
    (exists $Viewer_url{$arg}) ? $Viewer_url{$arg} 
                             : ($self->warn("Can't resolve argument to URL: $arg"), 
				$Not_found_url);
}
General documentation
INSTALLATIONTop
This module is included with the central Bioperl distribution:
   http://bio.perl.org/Core/Latest
   ftp://bio.perl.org/pub/DIST
You also need to define URLs for the following variables in this package:
  $Not_found_url : Generic page to show in place of a 404 error.
  $Tmp_url       : Web-accessible site that is Used for scripts that 
                   need to generate temporary, web-accessible files.
                   The files need not necessarily be HTML files, but 
                   being on the same disk as the server will permit 
                   faster IO from server scripts.
SEE ALSOTop
 http://bio.perl.org/Projects/modules.html  - Online module documentation
 http://bio.perl.org/                       - Bioperl Project Homepage
FEEDBACKTop
Mailing Lists Top
User feedback is an integral part of the evolution of this and other Bioperl modules.
Send your comments and suggestions preferably to one of the Bioperl mailing lists.
Your participation is much appreciated.
  bioperl-l@bioperl.org                  - General discussion
  http://www.bioperl.org/MailList.shtml  - About the mailing lists
Reporting BugsTop
Report bugs to the Bioperl bug tracking system to help us keep track the bugs and
their resolution. Bug reports can be submitted via email or the web:
    bioperl-bugs@bio.perl.org                   
    http://bugzilla.bioperl.org/
AUTHORTop
Steve Chervitz, sac@bioperl.org
VERSIONTop
Bio::Tools::WWW.pm, 0.014
COPYRIGHTTop
Copyright (c) 1996-98 Steve Chervitz. All Rights Reserved.
This module is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
APPENDIXTop
Methods beginning with a leading underscore are considered private
and are intended for internal use by this module. They are
not considered part of the public interface and are described here
for documentation purposes only.
FOR DEVELOPERS ONLYTop
Data MembersTop
An instance of Bio::Tools::WWW.pm is a blessed reference to a hash containing
all or some of the following fields:
 FIELD           VALUE
 --------------------------------------------------------------
 _started_html   Defined the on the initial invocation of start_html()
                 to avoid duplicate printing out the "Content-type..." header.