From: preecej <preecej@localhost>
Date: Mon, 25 Jul 2011 23:46:47 +0000 (+0000)
Subject: Began breaking out GAF from generic CSV, tab format.
X-Git-Url: http://gitweb.planteome.org/?a=commitdiff_plain;h=5eb66b93d0a37c6b0c2aa2a5df03ffd241a09b4c;p=old-jaiswallab-svn%2F.git

Began breaking out GAF from generic CSV, tab format.

svn path=/; revision=124
---

diff --git a/preecej/semantic_wiki/paw_TransformForImport.pl b/preecej/semantic_wiki/paw_TransformForImport.pl
index a6fbb62..92a4713 100644
--- a/preecej/semantic_wiki/paw_TransformForImport.pl
+++ b/preecej/semantic_wiki/paw_TransformForImport.pl
@@ -105,6 +105,7 @@ use XML::DOM;
 
 my %opts; # arg options
 my $file_type; # tab, csv, gaf
+my $file_del; # data delimeter
 my $input_file;
 my $output_file;
 my $verbose = 0; # flag for verbose output
@@ -157,9 +158,15 @@ sub init
         }
     }
     
-    # split data on either commas or tabs, if file type is generic
-    if ($file_type = "csv" || $file_type = "tab") {
-        my $file_del = ($file_type eq "csv") ? ',' : '\t';
+    # split data on either commas or tabs
+    switch ($file_type) {
+        case "csv" { $file_del = ','; }
+        case "tab" { $file_del = '\t'; }
+        case "gaf" { $file_del = '\t'; }
+        else {
+            die(uc($file_type) . " is not a valid file type. Please supply "
+                . "a tab, csv, or gaf file.\n");
+        }
     }
         
     system "clear";
@@ -190,12 +197,14 @@ sub import_data
     # open file
     open(INPUT_FILE,$input_file) or die("Could not open input file.");
 
+    my $line; # all-purpose line counter
+    
     # read in the source data
     my $count = 0;
     while (<INPUT_FILE>)
     {
        $count++;
-       my $line = $_;
+       $line = $_;
        chomp $line;
        my $data_val = (split('=',$line))[1];
        switch ($count) {
@@ -204,19 +213,38 @@ sub import_data
            case 4 { $source{'SourceVersion'} = $data_val; }
            case 5 { $source{'SourceURI'} = $data_val; }
            case 6 { $source{'SourceFile'} = $data_val; }
-           case 8 { $template_name = $data_val; }
-           case 9 { @field_names = split($file_del,$data_val); }
            else {;}
        }
-       if ($count == 10) { last; }
+       if ($count == 6) { last; }
     }
 
+    # read in "[Format] section if filetype is tab or csv"
+    $count++;
+    if ($file_type =~ /(csv)|(tab)/) { 
+
+        $count = 0;
+        while (<INPUT_FILE>)
+        {
+           $count++;
+           $line = $_;
+           chomp $line;
+           my $data_val = (split('=',$line))[1];
+           switch ($count) {
+               case 2 { $template_name = $data_val; }
+               case 3 { @field_names = split($file_del,$data_val); }
+               else {;}
+           }
+           if ($count == 3) { last; }
+        }
+    }
+   
     print "Reading data...\n\n";
+    $line = <INPUT_FILE>; # skip "[Data]"
     
     # loop through data rows and add all data fields to an array of hashes
     while (<INPUT_FILE>)
     {
-        my $line = $_;
+        $line = $_;
         chomp $line;
         
         my @tmp_data_ary = split($file_del, $line);
@@ -238,14 +266,17 @@ sub import_data
 # ---------------------------------------------------------------------------
 sub show_input
 {
-    print "[Source]\n";
+    print "\n[Source]\n";
     foreach my $key (keys %source) {
         print "$key: $source{$key}\n";
     }
     print "\n";
-    print "[Template]\n$template_name\n\n";
-    print "[Fields]\n" . join(', ',@field_names) . "\n\n";
-    
+
+    if ($file_type =~ /(csv)|(tab)/) { 
+        print "[Template]\n$template_name\n\n";
+        print "[Fields]\n" . join(', ',@field_names) . "\n\n";
+    }
+        
     print "[Data]\n";
     foreach my $row (@field_data) {
         foreach my $key (keys %$row) {
@@ -256,12 +287,11 @@ sub show_input
     print "\n";
 }
 
-
-# loop through the hash and build annotation data and source xml doc
+# xml transformation for generic tab or CSV-templated data
+# (currently uses XML::Smart)
 # ---------------------------------------------------------------------------
-sub write_xml
+sub transform_generic
 {
-    print "Transforming data...\n\n";
     my $curr_node; # placeholder for general node cursor
     my $curr_prov_node; # placeholder for node cursor in provenance pages
     my $curr_annot_node; # placeholder for node cursor in annotation pages
@@ -311,7 +341,7 @@ sub write_xml
         $curr_annot_node = $curr_annot_node->{Template};    
       
         # set up next provenance page
-        my $next_page = { Title => "Annotation:$next_page_title_id/Provenance" };
+        $next_page = { Title => "Annotation:$next_page_title_id/Provenance" };
         push(@{$curr_node->{Page}}, $next_page);
 
         $curr_prov_node = $curr_node->{Page}(
@@ -374,6 +404,28 @@ sub write_xml
     # write out xml doc to a single ImportXML file
     print "Writing data to output file...\n\n";
     $xml->save($output_file);
+    $output_data = $xml->data;
+}
+
+# xml transformation for GAF data
+# (currently uses XML::DOM)
+# ---------------------------------------------------------------------------
+sub transform_gaf
+{
+    $output_data = "hullo, gaf";
+}
+
+
+# loop through the hash and build annotation data and source xml doc
+# ---------------------------------------------------------------------------
+sub write_xml
+{
+    print "Transforming " . uc($file_type) . " data to SMW/SF XML...\n\n";
+
+    switch ($file_type) {
+        case ('csv' || 'tab') { transform_generic(); }
+        case 'gaf' { transform_gaf(); }
+    }
 }
 
 
@@ -382,7 +434,6 @@ sub write_xml
 sub show_output
 {
     print "[XML]\n";
-    $output_data = $xml->data;
     print $output_data;
     print "\n";
 }
@@ -394,7 +445,7 @@ sub show_output
 init;
 import_data;
 if ($verbose) { show_input; }
-write_xml;
+write_xml();
 if ($verbose) { show_output; }
 
 exit;