--- loncom/interface/loncommon.pm	2001/12/13 01:31:39	1.16
+++ loncom/interface/loncommon.pm	2002/03/28 22:15:56	1.30
@@ -1,7 +1,7 @@
 # The LearningOnline Network with CAPA
 # a pile of common routines
 #
-# $Id: loncommon.pm,v 1.16 2001/12/13 01:31:39 harris41 Exp $
+# $Id: loncommon.pm,v 1.30 2002/03/28 22:15:56 albertel Exp $
 #
 # Copyright Michigan State University Board of Trustees
 #
@@ -27,7 +27,12 @@
 #
 # YEAR=2001
 # 2/13-12/7 Guy Albertelli
-# 12/11,12/12 Scott Harrison
+# 12/11,12/12,12/17 Scott Harrison
+# 12/21 Gerd Kortemeyer
+# 12/21 Scott Harrison
+# 12/25,12/28 Gerd Kortemeyer
+# YEAR=2002
+# 1/4 Gerd Kortemeyer
 
 # Makes a table out of the previous attempts
 # Inputs result_from_symbread, user, domain, course_id
@@ -36,17 +41,33 @@
 package Apache::loncommon;
 
 use strict;
+use Apache::lonnet();
 use POSIX qw(strftime);
 use Apache::Constants qw(:common);
 use Apache::lonmsg();
 
+my $readit;
+
+# ----------------------------------------------- Filetypes/Languages/Copyright
 my %language;
 my %cprtag;
 my %fe; my %fd;
 my %fc;
 
+# -------------------------------------------------------------- Thesaurus data
+my @therelated;
+my @theword;
+my @thecount;
+my %theindex;
+my $thetotalcount;
+my $thefuzzy=2;
+my $thethreshold=0.1/$thefuzzy;
+my $theavecount;
+
 # ----------------------------------------------------------------------- BEGIN
-sub BEGIN {
+BEGIN {
+
+    unless ($readit) {
 # ------------------------------------------------------------------- languages
     {
 	my $fh=Apache::File->new($Apache::lonnet::perlvar{'lonTabDir'}.
@@ -102,6 +123,87 @@ sub BEGIN {
 	    }
 	}
     }
+# -------------------------------------------------------------- Thesaurus data
+    {
+	my $fh=Apache::File->new($Apache::lonnet::perlvar{'lonTabDir'}.
+	       '/thesaurus.dat');
+	if ($fh) {
+            while (<$fh>) {
+               my ($tword,$tindex,$tcount,$trelated)=split(/\@/,$_);
+               $theindex{$tword}=$tindex;
+               $theword[$tindex]=$tword;
+               $thecount[$tindex]=$tcount;
+               $thetotalcount+=$tcount;
+               $therelated[$tindex]=$trelated;
+	   }
+        }
+        $theavecount=$thetotalcount/$#thecount;
+    }
+    &Apache::lonnet::logthis(
+              "<font color=yellow>INFO: Read file types and thesaurus</font>");
+    $readit=1;
+}
+
+}
+# ============================================================= END BEGIN BLOCK
+
+
+# ---------------------------------------------------------- Is this a keyword?
+
+sub keyword {
+    my $newword=shift;
+    $newword=~s/\W//g;
+    $newword=~tr/A-Z/a-z/;
+    my $tindex=$theindex{$newword};
+    if ($tindex) {
+        if ($thecount[$tindex]>$theavecount) {
+           return 1;
+        }
+    }
+    return 0;
+}
+# -------------------------------------------------------- Return related words
+
+sub related {
+    my $newword=shift;
+    $newword=~s/\W//g;
+    $newword=~tr/A-Z/a-z/;
+    my $tindex=$theindex{$newword};
+    if ($tindex) {
+        my %found=();
+        foreach (split(/\,/,$therelated[$tindex])) {
+# - Related word found
+            my ($ridx,$rcount)=split(/\:/,$_);
+# - Direct relation index
+            my $directrel=$rcount/$thecount[$tindex];
+            if ($directrel>$thethreshold) {
+               foreach (split(/\,/,$therelated[$ridx])) {
+                  my ($rridx,$rrcount)=split(/\:/,$_);
+                  if ($rridx==$tindex) {
+# - Determine reverse relation index
+                     my $revrel=$rrcount/$thecount[$ridx];
+# - Calculate full index
+                     $found{$ridx}=$directrel*$revrel;
+                     if ($found{$ridx}>$thethreshold) {
+                        foreach (split(/\,/,$therelated[$ridx])) {
+                            my ($rrridx,$rrrcount)=split(/\:/,$_);
+                            unless ($found{$rrridx}) {
+                               my $revrevrel=$rrrcount/$thecount[$ridx];
+                               if (
+                          $directrel*$revrel*$revrevrel>$thethreshold
+                               ) {
+                                  $found{$rrridx}=
+                                       $directrel*$revrel*$revrevrel;
+                               }
+                            }
+                        }
+                     }
+                  }
+               }
+            }
+        }
+    }
+    return ();
 }
 
 # ---------------------------------------------------------------- Language IDs
@@ -129,7 +231,7 @@ sub filecategories {
     return sort(keys(%fc));
 }
 
-# ------------------------------------------------------------- File Categories
+# -------------------------------------- File Types within a specified category
 sub filecategorytypes {
     return @{$fc{lc(shift(@_))}};
 }
@@ -165,9 +267,9 @@ sub get_previous_attempt {
       my %lasthash=();
       my $version;
       for ($version=1;$version<=$returnhash{'version'};$version++) {
-        map {
+        foreach (sort(split(/\:/,$returnhash{$version.':keys'}))) {
 	  $lasthash{$_}=$returnhash{$version.':'.$_};
-        } sort(split(/\:/,$returnhash{$version.':keys'}));
+        }
       }
       $prevattempts='<table border=2></tr><th>History</th>';
       foreach (sort(keys %lasthash)) {
@@ -256,16 +358,22 @@ sub get_student_answers {
 }
 
 sub get_unprocessed_cgi {
-  my ($query)= @_;
+  my ($query,$possible_names)= @_;
+  # $Apache::lonxml::debug=1;
   foreach (split(/&/,$query)) {
     my ($name, $value) = split(/=/,$_);
-    $value =~ tr/+/ /;
-    $value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C",hex($1))/eg;
-    if (!defined($ENV{'form.'.$name})) { $ENV{'form.'.$name}=$value; }
+    $name = &Apache::lonnet::unescape($name);
+    if (!defined($possible_names) || (grep {$_ eq $name} @$possible_names)) {
+      $value =~ tr/+/ /;
+      $value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C",hex($1))/eg;
+      &Apache::lonxml::debug("Seting :$name: to :$value:");
+      unless (defined($ENV{'form.'.$name})) { &add_to_env('form.'.$name,$value) };
+    }
   }
 }
 
 sub cacheheader {
+  unless ($ENV{'request.method'} eq 'GET') { return ''; }
   my $date=strftime("%a, %d %b %Y %H:%M:%S GMT",gmtime);
   my $output .='<meta HTTP-EQUIV="Expires" CONTENT="'.$date.'" />
                 <meta HTTP-EQUIV="Cache-control" CONTENT="no-cache" />
@@ -275,10 +383,139 @@ sub cacheheader {
 
 sub no_cache {
   my ($r) = @_;
-  my $date=strftime("%a, %d %b %Y %H:%M:%S GMT",gmtime);
+  unless ($ENV{'request.method'} eq 'GET') { return ''; }
+  #my $date=strftime("%a, %d %b %Y %H:%M:%S GMT",gmtime);
   $r->no_cache(1);
   $r->header_out("Pragma" => "no-cache");
-  $r->header_out("Expires" => $date);
+  #$r->header_out("Expires" => $date);
+}
+
+sub add_to_env {
+  my ($name,$value)=@_;
+  if (defined($ENV{$name})) {
+    if (ref($ENV{$name})) {
+      #already have multiple values
+      push(@{ $ENV{$name} },$value);
+    } else {
+      #first time seeing multiple values, convert hash entry to an arrayref
+      my $first=$ENV{$name};
+      undef($ENV{$name});
+      push(@{ $ENV{$name} },$first,$value);
+    }
+  } else {
+    $ENV{$name}=$value;
+  }
 }
 1;
 __END__;
+
+
+=head1 NAME
+
+Apache::loncommon - pile of common routines
+
+=head1 SYNOPSIS
+
+Referenced by other mod_perl Apache modules.
+
+Invocation:
+ &Apache::loncommon::SUBROUTINENAME(ARGUMENTS);
+
+=head1 INTRODUCTION
+
+Common collection of used subroutines.  This collection helps remove
+redundancy from other modules and increase efficiency of memory usage.
+
+Current things done:
+
+ Makes a table out of the previous homework attempts
+ Inputs result_from_symbread, user, domain, course_id
+ Reads in non-network-related .tab files
+
+This is part of the LearningOnline Network with CAPA project
+described at http://www.lon-capa.org.
+
+=head1 HANDLER SUBROUTINE
+
+There is no handler subroutine.
+
+=head1 OTHER SUBROUTINES
+
+=over 4
+
+=item *
+
+BEGIN() : initialize values from language.tab, copyright.tab, filetypes.tab,
+and filecategories.tab.
+
+=item *
+
+languageids() : returns list of all language ids
+
+=item *
+
+languagedescription() : returns description of a specified language id
+
+=item *
+
+copyrightids() : returns list of all copyrights
+
+=item *
+
+copyrightdescription() : returns description of a specified copyright id
+
+=item *
+
+filecategories() : returns list of all file categories
+
+=item *
+
+filecategorytypes() : returns list of file types belonging to a given file
+category
+
+=item *
+
+fileembstyle() : returns embedding style for a specified file type
+
+=item *
+
+filedescription() : returns description for a specified file type
+
+=item *
+
+filedescriptionex() : returns description for a specified file type with
+extra formatting
+
+=item *
+
+get_previous_attempt() : return string with previous attempt on problem
+
+=item *
+
+get_student_view() : show a snapshot of what student was looking at
+
+=item *
+
+get_student_answers() : show a snapshot of how student was answering problem
+
+=item *
+
+get_unprocessed_cgi() : get unparsed CGI parameters
+
+=item *
+
+cacheheader() : returns cache-controlling header code
+
+=item *
+
+nocache() : specifies header code to not have cache
+
+=item *
+
+add_to_env($name,$value) : adds $name to the %ENV hash with value
+$value, if $name already exists, the entry is converted to an array
+reference and $value is added to the array.
+
+=back
+
+=cut