Beefy Boxes and Bandwidth Generously Provided by pair Networks
Keep It Simple, Stupid
 
PerlMonks  

Re: XML::Twig n00b

by Anonymous Monk
on Oct 23, 2009 at 03:42 UTC ( #802830=note: print w/ replies, xml ) Need Help??


in reply to XML::Twig n00b

#!/usr/bin/perl -- use strict; use warnings; use XML::Twig; my $xml = <<'__XML__'; <?xml version="1.0" encoding="UTF-8"?> <authenticationReports> <generatedTime>Tue Sep 29 07:07:34 PDT 2009</generatedTime> <appDeploymentFile name="app-deployment.properties.hklcp.trading"> <application name="hk"> <urlInfo> <url>e/t/hk/accts_subscription</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/accts_forms</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/custtradingpage</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/accts_userinfo</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/headermain</url> </urlInfo> <urlInfo> <url>e/t/hk/custservicepage</url> </urlInfo> <urlInfo> <url>e/t/hk/accts_transfermoney</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/userprereq</url> </urlInfo> <urlInfo> <url>e/t/hk/indices_us</url> </urlInfo> <urlInfo> <url>e/t/hk/homeloggedmessage</url> </urlInfo> <urlInfo> <url>e/t/hk/lead</url> </urlInfo> <urlInfo> <url>e/t/hk/orderviewmin</url> </urlInfo> <urlInfo> <url>e/t/hk/accts_changelogin</url> <otherPrereq>SessionPreReq</otherPrereq> </urlInfo> </application> <application name="intl"> <urlInfo> <url>e/t/intl/quotesandresearch</url> </urlInfo> <urlInfo> <url>e/t/intl/intltablesubnavviewcomponent</url> </urlInfo> <urlInfo> <url>e/t/intl/intltablemetaviewcomponent</url> </urlInfo> <urlInfo> <url>e/t/intl/disclaimer</url> </urlInfo> <urlInfo> <url>e/t/intl/headermain</url> </urlInfo> <urlInfo> <url>e/t/intl/indices_us</url> </urlInfo> <urlInfo> <url>e/t/intl/lead</url> </urlInfo> <urlInfo> <url>e/t/intl/selectlanguage</url> </urlInfo> <urlInfo> <url>e/t/intl/get-screen</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/intl/page_f</url> </urlInfo> <urlInfo> <url>e/t/intl/basicprereq</url> </urlInfo> <urlInfo> <url>e/t/intl/page</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> </application> </appDeploymentFile> </authenticationReports> __XML__ { my $name = ""; my %apps; my %urls; my $t = new XML::Twig( start_tag_handlers => { 'appDeploymentFile/application' => sub { my ( $twig, $tag, %att ) = @_; #~ %att is only defined when twig_roots #~ $_ is only defined when twig_handlers #~ twig_handlers is uses less memory $name = $att{name} || $_->{'att'}->{name}; return; }, }, twig_handlers => { #~ twig_roots => { 'appDeploymentFile/application/urlInfo/url' => sub { #~ warn "root _ = $_ |||| @_ "; warn $_->text;; $apps{$name}{ "/" . $_->text }++; $urls{ "/" . $_->text } = $name; return; }, }, ); $t->parse($xml); undef $t; use Data::Dumper(); print Data::Dumper->new([ \%apps, \%urls ])->Indent(1)->Dump; } __END__ $VAR1 = { 'intl' => { '/e/t/intl/lead' => 1, '/e/t/intl/page_f' => 1, '/e/t/intl/get-screen' => 1, '/e/t/intl/basicprereq' => 1, '/e/t/intl/indices_us' => 1, '/e/t/intl/intltablesubnavviewcomponent' => 1, '/e/t/intl/selectlanguage' => 1, '/e/t/intl/page' => 1, '/e/t/intl/quotesandresearch' => 1, '/e/t/intl/intltablemetaviewcomponent' => 1, '/e/t/intl/disclaimer' => 1, '/e/t/intl/headermain' => 1 }, 'hk' => { '/e/t/hk/orderviewmin' => 1, '/e/t/hk/indices_us' => 1, '/e/t/hk/accts_subscription' => 1, '/e/t/hk/userprereq' => 1, '/e/t/hk/custtradingpage' => 1, '/e/t/hk/custservicepage' => 1, '/e/t/hk/accts_changelogin' => 1, '/e/t/hk/accts_transfermoney' => 1, '/e/t/hk/homeloggedmessage' => 1, '/e/t/hk/lead' => 1, '/e/t/hk/accts_forms' => 1, '/e/t/hk/accts_userinfo' => 1, '/e/t/hk/headermain' => 1 } }; $VAR2 = { '/e/t/intl/lead' => 'intl', '/e/t/intl/page_f' => 'intl', '/e/t/hk/userprereq' => 'hk', '/e/t/hk/custservicepage' => 'hk', '/e/t/intl/indices_us' => 'intl', '/e/t/intl/selectlanguage' => 'intl', '/e/t/intl/intltablemetaviewcomponent' => 'intl', '/e/t/intl/quotesandresearch' => 'intl', '/e/t/intl/headermain' => 'intl', '/e/t/intl/disclaimer' => 'intl', '/e/t/hk/accts_forms' => 'hk', '/e/t/hk/accts_userinfo' => 'hk', '/e/t/hk/accts_subscription' => 'hk', '/e/t/hk/indices_us' => 'hk', '/e/t/hk/orderviewmin' => 'hk', '/e/t/intl/get-screen' => 'intl', '/e/t/hk/custtradingpage' => 'hk', '/e/t/intl/basicprereq' => 'intl', '/e/t/hk/accts_changelogin' => 'hk', '/e/t/hk/accts_transfermoney' => 'hk', '/e/t/hk/homeloggedmessage' => 'hk', '/e/t/intl/intltablesubnavviewcomponent' => 'intl', '/e/t/intl/page' => 'intl', '/e/t/hk/lead' => 'hk', '/e/t/hk/headermain' => 'hk' };


Comment on Re: XML::Twig n00b
Download Code
Re^2: XML::Twig n00b
by Anonymous Monk on Oct 23, 2009 at 03:45 UTC
Re^2: XML::Twig n00b
by Binford (Sexton) on Oct 23, 2009 at 04:24 UTC
    I've got to study that more, but can I put the otherPrereq tag in the hash? THANKS though...
      Sure, but you'll have to decide on a data structure
      #!/usr/bin/perl -- use strict; use warnings; use XML::Twig; my $xml = <<'__XML__'; <?xml version="1.0" encoding="UTF-8"?> <authenticationReports> <generatedTime>Tue Sep 29 07:07:34 PDT 2009</generatedTime> <appDeploymentFile name="app-deployment.properties.hklcp.trading"> <application name="hk"> <urlInfo> <url>e/t/hk/accts_subscription</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/accts_forms</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/custtradingpage</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/accts_userinfo</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/headermain</url> </urlInfo> <urlInfo> <url>e/t/hk/custservicepage</url> </urlInfo> <urlInfo> <url>e/t/hk/accts_transfermoney</url> <otherPrereq>HKPwdPreReq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/hk/userprereq</url> </urlInfo> <urlInfo> <url>e/t/hk/indices_us</url> </urlInfo> <urlInfo> <url>e/t/hk/homeloggedmessage</url> </urlInfo> <urlInfo> <url>e/t/hk/lead</url> </urlInfo> <urlInfo> <url>e/t/hk/orderviewmin</url> </urlInfo> <urlInfo> <url>e/t/hk/accts_changelogin</url> <otherPrereq>SessionPreReq</otherPrereq> </urlInfo> </application> <application name="intl"> <urlInfo> <url>e/t/intl/quotesandresearch</url> </urlInfo> <urlInfo> <url>e/t/intl/intltablesubnavviewcomponent</url> </urlInfo> <urlInfo> <url>e/t/intl/intltablemetaviewcomponent</url> </urlInfo> <urlInfo> <url>e/t/intl/disclaimer</url> </urlInfo> <urlInfo> <url>e/t/intl/headermain</url> </urlInfo> <urlInfo> <url>e/t/intl/indices_us</url> </urlInfo> <urlInfo> <url>e/t/intl/lead</url> </urlInfo> <urlInfo> <url>e/t/intl/selectlanguage</url> </urlInfo> <urlInfo> <url>e/t/intl/get-screen</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> <urlInfo> <url>e/t/intl/page_f</url> </urlInfo> <urlInfo> <url>e/t/intl/basicprereq</url> </urlInfo> <urlInfo> <url>e/t/intl/page</url> <otherPrereq>BasicPrereq</otherPrereq> </urlInfo> </application> </appDeploymentFile> </authenticationReports> __XML__ # REUSING $xml # SEE http://search.cpan.org/perldoc?XML::Twig#xparse # $xml = appDeploymentFile('xmlexample.xml'); $xml = appDeploymentFile($xml); use Data::Dumper(); print Data::Dumper->new([ $xml ])->Indent(1)->Dump; sub appDeploymentFile { my( $xml ) = @_; my $url = ""; my %urls; my $appFileName = ""; my $t = new XML::Twig( start_tag_handlers => { 'appDeploymentFile' => sub { my ( $twig, $tag, %att ) = @_; #~ %att is only defined when twig_handlers #~ $_ is only defined when twig_roots #~ twig_handlers is uses less memory $appFileName = $att{name} || $_->{'att'}->{name}; return; }, }, twig_handlers => { 'appDeploymentFile/application/urlInfo/url' => sub { $url = "/" . $_->text ; $urls{ $url } = ""; return; }, 'appDeploymentFile/application/urlInfo/otherPrereq' => sub { $urls{ $url } = $_->text ; return; }, }, ); $t->xparse($xml); undef $t; # REUSING $url $url = join ":", "prd" , $1 , "web" , $2 if $appFileName =~ /\.([^\. +]+?)\.([^\.]+?)$/; return [ $appFileName , $url, \%urls ]; } __END__ $VAR1 = [ 'app-deployment.properties.hklcp.trading', 'prd:hklcp:web:trading', { '/e/t/intl/lead' => '', '/e/t/intl/page_f' => '', '/e/t/hk/userprereq' => '', '/e/t/hk/custservicepage' => '', '/e/t/intl/indices_us' => '', '/e/t/intl/selectlanguage' => '', '/e/t/intl/intltablemetaviewcomponent' => '', '/e/t/intl/quotesandresearch' => '', '/e/t/intl/headermain' => '', '/e/t/intl/disclaimer' => '', '/e/t/hk/accts_forms' => 'HKPwdPreReq', '/e/t/hk/accts_userinfo' => 'HKPwdPreReq', '/e/t/hk/accts_subscription' => 'HKPwdPreReq', '/e/t/hk/indices_us' => '', '/e/t/hk/orderviewmin' => '', '/e/t/intl/get-screen' => 'BasicPrereq', '/e/t/hk/custtradingpage' => 'BasicPrereq', '/e/t/intl/basicprereq' => '', '/e/t/hk/accts_changelogin' => 'SessionPreReq', '/e/t/hk/accts_transfermoney' => 'HKPwdPreReq', '/e/t/hk/homeloggedmessage' => '', '/e/t/intl/intltablesubnavviewcomponent' => '', '/e/t/intl/page' => 'BasicPrereq', '/e/t/hk/lead' => '', '/e/t/hk/headermain' => '' } ];
        No still not working :( There are MULTIPLE AppDeployMentFile entries each with 1 to N application entries, each with 1 to N urlInfo sections. I somehow need to call this multiple times on each appDeploymentFile "chunk"? Thanks for your help though! Appreciate it. NEver mind, I just used xml_split on the appDeploymentFile tag and will prcoess each file from that.

Log In?
Username:
Password:

What's my password?
Create A New User
Node Status?
node history
Node Type: note [id://802830]
help
Chatterbox?
and the web crawler heard nothing...

How do I use this? | Other CB clients
Other Users?
Others chanting in the Monastery: (9)
As of 2014-10-23 10:08 GMT
Sections?
Information?
Find Nodes?
Leftovers?
    Voting Booth?

    For retirement, I am banking on:










    Results (125 votes), past polls