[BACK]Return to post_xml.pm CVS log [TXT] [DIR] Up to [LON-CAPA] / loncom / homework / cleanxml

Diff for /loncom/homework/cleanxml/post_xml.pm between versions 1.1 and 1.3

version 1.1, 2015/12/03 20:40:31 version 1.3, 2015/12/15 15:33:30
Line 42  use XML::LibXML; Line 42  use XML::LibXML;
 use HTML::TokeParser; # used to parse sty files  use HTML::TokeParser; # used to parse sty files
 use Tie::IxHash; # for ordered hashes  use Tie::IxHash; # for ordered hashes
   
 use Env qw(RES_DIR); # path of res directory parent (without the / at the end)  
   
 no warnings 'recursion'; # yes, fix_paragraph is using heavy recursion, I know  no warnings 'recursion'; # yes, fix_paragraph is using heavy recursion, I know
   
 # these are constants  # these are constants
Line 77  my $warnings; # 1 = print warnings Line 75  my $warnings; # 1 = print warnings
   
   
 # Parses the XML document and fixes many things to turn it into a document matching the schema.  # Parses the XML document and fixes many things to turn it into a document matching the schema.
 # Returns the text of the document as a byte string.  # @param {reference} textref - reference to the text of the document
   # @param {string} file_path - path of the file being processed (we only extract the directory path from it)
   # @param {string} res_dir - path of res directory parent (without the / at the end)
   # @param {boolean} warn - 1 to print warnings, 0 otherwise
   # @returns the text of the document as a byte string.
 sub post_xml {  sub post_xml {
   my ($textref, $file_path, $warn) = @_;    my ($textref, $file_path, $res_dir, $warn) = @_;
   $warnings = $warn;    $warnings = $warn;
       
   my $dom_doc = XML::LibXML->load_xml(string => $textref);    my $dom_doc = XML::LibXML->load_xml(string => $textref);
Line 92  sub post_xml { Line 94  sub post_xml {
       
   fix_attribute_case($root);    fix_attribute_case($root);
       
   my $fix_by_hand = replace_m($root);    replace_m($root);
       
   my @all_block = (@block_elements, @block_html);    my @all_block = (@block_elements, @block_html);
   add_sty_blocks($file_path, $root, \@all_block); # must come before the subs using @all_block    add_sty_blocks($file_path, $res_dir, $root, \@all_block); # must come before the subs using @all_block
   
   fix_block_styles($root, \@all_block);    fix_block_styles($root, \@all_block);
   $root->normalize();    $root->normalize();
Line 140  sub post_xml { Line 142  sub post_xml {
   
   replace_tm_dtm($root);    replace_tm_dtm($root);
       
   if ($fix_by_hand) {  
     die "The file has been converted but it should be fixed by hand.";  
   }  
   return $dom_doc->toString(); # byte string !    return $dom_doc->toString(); # byte string !
 }  }
   
Line 353  sub fix_attribute_case { Line 352  sub fix_attribute_case {
 # Replaces m by HTML, tm and/or dtm (which will be replaced by <m> later, but they are useful  # Replaces m by HTML, tm and/or dtm (which will be replaced by <m> later, but they are useful
 #   to know if the element is a block element or not).  #   to know if the element is a block element or not).
 # m might contain non-math LaTeX, while tm and dtm may only contain math.  # m might contain non-math LaTeX, while tm and dtm may only contain math.
 # Returns 1 if the file should be fixed by hand, 0 otherwise.  
 sub replace_m {  sub replace_m {
   my ($root) = @_;    my ($root) = @_;
   my $doc = $root->ownerDocument;    my $doc = $root->ownerDocument;
   my $fix_by_hand = 0;  
   # search for variable declarations    # search for variable declarations
   my @variables = ();    my @variables = ();
   my @scripts = $root->getElementsByTagName('script');    my @scripts = $root->getElementsByTagName('script');
Line 406  sub replace_m { Line 403  sub replace_m {
           if ($warnings) {            if ($warnings) {
             print "WARNING: <m> is used in a script, it should be converted by hand\n";              print "WARNING: <m> is used in a script, it should be converted by hand\n";
           }            }
           $fix_by_hand = 1;  
         }          }
       }        }
     }      }
Line 421  sub replace_m { Line 417  sub replace_m {
       if ($warnings) {        if ($warnings) {
         print "WARNING: m value is not simple text\n";          print "WARNING: m value is not simple text\n";
       }        }
       $fix_by_hand = 1;  
       next;        next;
     }      }
     my $text = $m->firstChild->nodeValue;      my $text = $m->firstChild->nodeValue;
Line 552  sub replace_m { Line 547  sub replace_m {
     $m->parentNode->replaceChild($fragment, $m);      $m->parentNode->replaceChild($fragment, $m);
           
   }    }
   return $fix_by_hand;  
 }  }
   
 # Returns the HTML equivalent of LaTeX input, using tth  # Returns the HTML equivalent of LaTeX input, using tth
Line 591  sub html_to_dom { Line 585  sub html_to_dom {
 # Use the linked sty files to guess which newly defined elements should be considered blocks.  # Use the linked sty files to guess which newly defined elements should be considered blocks.
 # Also adds to @containing_styles the sty elements that contain styles.  # Also adds to @containing_styles the sty elements that contain styles.
 # @param {string} fn - the file path (we only extract the directory path from it)  # @param {string} fn - the file path (we only extract the directory path from it)
   # @param {string} res_dir - path of res directory parent (without the / at the end)
   # @param {Element} root - the root element
 sub add_sty_blocks {  sub add_sty_blocks {
   my ($fn, $root, $all_block) = @_;    my ($fn, $res_dir, $root, $all_block) = @_;
   my $doc = $root->ownerDocument;    my $doc = $root->ownerDocument;
   my @parserlibs = $doc->getElementsByTagName('parserlib');    my @parserlibs = $doc->getElementsByTagName('parserlib');
   my @libs = ();    my @libs = ();
Line 608  sub add_sty_blocks { Line 604  sub add_sty_blocks {
   my ($name, $path, $suffix) = fileparse($fn);    my ($name, $path, $suffix) = fileparse($fn);
   foreach my $sty (@libs) {    foreach my $sty (@libs) {
     if (substr($sty, 0, 1) eq '/') {      if (substr($sty, 0, 1) eq '/') {
       $sty = $RES_DIR.$sty;        $sty = $res_dir.$sty;
     } else {      } else {
       $sty = $path.$sty;        $sty = $path.$sty;
     }      }
Removed from v.1.1  
changed lines
  Added in v.1.3

FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>