.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.16) .\" .\" Standard preamble: .\" ======================================================================== .de Sp \" Vertical space (when we can't use .PP) .if t .sp .5v .if n .sp .. .de Vb \" Begin verbatim text .ft CW .nf .ne \\$1 .. .de Ve \" End verbatim text .ft R .fi .. .\" Set up some character translations and predefined strings. \*(-- will .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left .\" double quote, and \*(R" will give a right double quote. \*(C+ will .\" give a nicer C++. Capital omega is used to do unbreakable dashes and .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff, .\" nothing in troff, for use with C<>. .tr \(*W- .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' .ie n \{\ . ds -- \(*W- . ds PI pi . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch . ds L" "" . ds R" "" . ds C` "" . ds C' "" 'br\} .el\{\ . ds -- \|\(em\| . ds PI \(*p . ds L" `` . ds R" '' 'br\} .\" .\" Escape single quotes in literal strings from groff's Unicode transform. .ie \n(.g .ds Aq \(aq .el .ds Aq ' .\" .\" If the F register is turned on, we'll generate index entries on stderr for .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index .\" entries marked with X<> in POD. Of course, you'll have to process the .\" output yourself in some meaningful fashion. .ie \nF \{\ . de IX . tm Index:\\$1\t\\n%\t"\\$2" .. . nr % 0 . rr F .\} .el \{\ . de IX .. .\} .\" .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). .\" Fear. Run. Save yourself. No user-serviceable parts. . \" fudge factors for nroff and troff .if n \{\ . ds #H 0 . ds #V .8m . ds #F .3m . ds #[ \f1 . ds #] \fP .\} .if t \{\ . ds #H ((1u-(\\\\n(.fu%2u))*.13m) . ds #V .6m . ds #F 0 . ds #[ \& . ds #] \& .\} . \" simple accents for nroff and troff .if n \{\ . ds ' \& . ds ` \& . ds ^ \& . ds , \& . ds ~ ~ . ds / .\} .if t \{\ . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' .\} . \" troff and (daisy-wheel) nroff accents .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' .ds 8 \h'\*(#H'\(*b\h'-\*(#H' .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] .ds ae a\h'-(\w'a'u*4/10)'e .ds Ae A\h'-(\w'A'u*4/10)'E . \" corrections for vroff .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' . \" for low resolution devices (crt and lpr) .if \n(.H>23 .if \n(.V>19 \ \{\ . ds : e . ds 8 ss . ds o a . ds d- d\h'-1'\(ga . ds D- D\h'-1'\(hy . ds th \o'bp' . ds Th \o'LP' . ds ae ae . ds Ae AE .\} .rm #[ #] #H #V #F C .\" ======================================================================== .\" .IX Title "Bio::Biblio::IO 3pm" .TH Bio::Biblio::IO 3pm "2012-03-02" "perl v5.14.2" "User Contributed Perl Documentation" .\" For nroff, turn off justification. Always turn off hyphenation; it makes .\" way too many mistakes in technical documents. .if n .ad l .nh .SH "NAME" Bio::Biblio::IO \- Handling the bibliographic references .SH "SYNOPSIS" .IX Header "SYNOPSIS" .Vb 1 \& use Bio::Biblio::IO; \& \& # getting citations from a file \& $in = Bio::Biblio::IO\->new (\*(Aq\-file\*(Aq => \*(Aqmyfile.xml\*(Aq , \& \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& # \-\-\- OR \-\-\- \& \& # getting citations from a string \& $in = Bio::Biblio::IO\->new (\*(Aq\-data\*(Aq => \*(Aq...\*(Aq , \& \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& #\-\-\- OR \-\-\- \& \& # getting citations from a string if IO::String is installed \& use IO::String; \& $in = Bio::Biblio::IO\->new (\*(Aq\-fh\*(Aq => IO::String\->new ($citation), \& \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& \& $in = Bio::Biblio::IO\->new(\-fh => $io_handle , \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& \& #\-\-\- OR \-\-\- \& \& # getting citations from any IO handler \& $in = Bio::Biblio::IO\->new(\*(Aq\-fh\*(Aq => $io_handle , \& \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& \& \& # now, having $in, we can read all citations \& while ( my $citation = $in\->next_bibref() ) { \& &do_something_with_citation ($citation); \& } \& \& #\-\-\- OR \-\-\- \& \& # again reading all citation but now a callback defined in your \& # code is used (note that the reading starts already when new() \& # is called) \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq, \& \*(Aq\-file\*(Aq => $testfile, \& \*(Aq\-callback\*(Aq => \e&callback); \& sub callback { \& my $citation = shift; \& print $citation\->{\*(Aq_identifier\*(Aq} . "\en"; \& } \& \& #Now, to actually get a citation in an XML format, \& #use I module which returns an XML string: \& \& use Bio::Biblio; \& use Bio::Biblio::IO; \& my $xml = Bio::Biblio\->new\->get_by_id (\*(Aq12368254\*(Aq); \& my $reader = Bio::Biblio::IO\->new (\*(Aq\-data\*(Aq => $xml, \& \*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq); \& \& while (my $citation = $reader\->next_bibref()) { \& #... do something here with $citation \& } \& \& #And, finally, the resulting citation can be received in different \& #output formats: \& \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq, \& \*(Aq\-result\*(Aq => \*(Aqraw\*(Aq); \& #\-\-\- OR \-\-\- \& \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqmedlinexml\*(Aq, \& \*(Aq\-result\*(Aq => \*(Aqmedline2ref\*(Aq); \& \& #\-\-\- OR \-\-\- \& \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqpubmedxml\*(Aq, \& \*(Aq\-result\*(Aq => \*(Aqpubmed2ref\*(Aq); .Ve .SH "DESCRIPTION" .IX Header "DESCRIPTION" Bio::Biblio::IO is a handler module for accessing bibliographic citations. The citations can be in different formats \- assuming that there is a corresponding module knowing that format in Bio::Biblio::IO directory (e.g. Bio::Biblio::IO::medlinexml). The format (and the module name) is given by the argument \fI\-format\fR. .PP Once an instance of \f(CW\*(C`Bio::Biblio::IO\*(C'\fR class is available, the citations can be read by calling repeatedly method \fInext_bibref\fR: .PP .Vb 3 \& while (my $citation = $reader\->next_bibref()) { \& ... do something here with $citation \& } .Ve .PP However, this may imply that all citations were already read into the memory. If you expect a huge amount of citations to be read, you may choose a \fIcallback\fR option. Your subroutine is specified in the \&\f(CW\*(C`new()\*(C'\fR method and is called everytime a new citation is available (see an example above in \s-1SYNOPSIS\s0). .PP The citations returned by \fInext_bibref\fR or given to your callback routine can be of different formats depending on the argument \&\fI\-result\fR. One result type is \fIraw\fR and it is represented by a simple, not blessed hash table: .PP .Vb 1 \& $io = Bio::Biblio::IO\->new(\*(Aq\-result\*(Aq => \*(Aqraw\*(Aq); .Ve .PP What other result formats are available depends on the module who reads the citations in the first place. At the moment, the following ones are available: .PP .Vb 1 \& $io = Bio::Biblio::IO\->new(\*(Aq\-result\*(Aq => \*(Aqmedline2ref\*(Aq); .Ve .PP This is a default result format for reading citations by the \&\fImedlinexml\fR module. The \f(CW\*(C`medlinexml\*(C'\fR module is again the default one. Which means that you can almost omit arguments (you still need to say where the citations come from): .PP .Vb 1 \& $io = Bio::Biblio::IO\->new(\*(Aq\-file\*(Aq => \*(Aqdata/medline_data.xml\*(Aq); .Ve .PP Another result format available is for \s-1PUBMED\s0 citations (which is a super-set of the \s-1MEDLINE\s0 citations having few more tags): .PP .Vb 3 \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqpubmedxml\*(Aq, \& \*(Aq\-result\*(Aq => \*(Aqpubmed2ref\*(Aq, \& \*(Aq\-data\*(Aq => $citation); .Ve .PP Or, because \f(CW\*(C`pubmed2ref\*(C'\fR is a default one for \s-1PUBMED\s0 citations, you can say just: .PP .Vb 2 \& $io = Bio::Biblio::IO\->new(\*(Aq\-format\*(Aq => \*(Aqpubmedxml\*(Aq, \& \*(Aq\-data\*(Aq => $citation); .Ve .PP Both \f(CW\*(C`medline2ref\*(C'\fR and \f(CW\*(C`pubmed2ref\*(C'\fR results are objects defined in the directory \f(CW\*(C`Bio::Biblio\*(C'\fR. .SH "SEE ALSO" .IX Header "SEE ALSO" .IP "\(bu" 4 An example script \fIexamples/biblio.pl\fR. It has many options and its own help. The relevant options to this \s-1IO\s0 module are \fI\-f\fR (specifying what file to read) and \fI\-O\fR (specifying what result format to achieve). .IP "\(bu" 4 OpenBQS home page: http://www.ebi.ac.uk/~senger/openbqs .IP "\(bu" 4 Comments to the Perl client: http://www.ebi.ac.uk/~senger/openbqs/Client_perl.html .SH "FEEDBACK" .IX Header "FEEDBACK" .SS "Mailing Lists" .IX Subsection "Mailing Lists" 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. .PP .Vb 2 \& bioperl\-l@bioperl.org \- General discussion \& http://bioperl.org/wiki/Mailing_lists \- About the mailing lists .Ve .SS "Support" .IX Subsection "Support" Please direct usage questions or support issues to the mailing list: .PP \&\fIbioperl\-l@bioperl.org\fR .PP rather than to the module maintainer directly. Many experienced and reponsive experts will be able look at the problem and quickly address it. Please include a thorough description of the problem with code and data examples if at all possible. .SS "Reporting Bugs" .IX Subsection "Reporting Bugs" Report bugs to the Bioperl bug tracking system to help us keep track the bugs and their resolution. Bug reports can be submitted via the web: .PP .Vb 1 \& https://redmine.open\-bio.org/projects/bioperl/ .Ve .SH "AUTHOR" .IX Header "AUTHOR" Martin Senger (senger@ebi.ac.uk) .SH "COPYRIGHT" .IX Header "COPYRIGHT" Copyright (c) 2002 European Bioinformatics Institute. All Rights Reserved. .PP This module is free software; you can redistribute it and/or modify it under the same terms as Perl itself. .SH "DISCLAIMER" .IX Header "DISCLAIMER" This software is provided \*(L"as is\*(R" without warranty of any kind. .SH "APPENDIX" .IX Header "APPENDIX" The rest of the documentation details each of the object methods. Internal methods are preceded with a _ .SS "next_bibref" .IX Subsection "next_bibref" .Vb 6 \& Usage : $citation = stream\->next_bibref \& Function: Reads the next citation object from the stream and returns it. \& Returns : a Bio::Biblio::Ref citation object, or something else \& (depending on the \*(Aq\-result\*(Aq argument given in the \*(Aqnew()\*(Aq \& method). \& Args : none .Ve .SS "_load_format_module" .IX Subsection "_load_format_module" .Vb 4 \& Usage : $class\->_load_format_module ($format) \& Returns : 1 on success, undef on failure \& Args : \*(Aqformat\*(Aq should contain the last part of the \& name of a module who does the real implementation .Ve .PP It does (in run-time) a similar thing as .PP .Vb 1 \& require Bio::Biblio::IO::$format .Ve .PP It throws an exception if it fails to find and load the module (for example, because of the compilation errors in the module). .SS "_guess_format" .IX Subsection "_guess_format" .Vb 3 \& Usage : $class\->_guess_format ($filename) \& Returns : string with a guessed format of the input data (e.g. \*(Aqmedlinexml\*(Aq) \& Args : a file name whose extension can help to guess its format .Ve .PP It makes an expert guess what kind of data are in the given file (but be prepare that \f(CW$filename\fR may be empty).