Changeset 22642 for main/trunk

Timestamp:

2010-08-17T12:24:42+12:00 (14 years ago)

Author:

kjdon

Message:

removed all open office stuff. Haven't tested it properly as am at home

File:

• main/trunk/greenstone2/bin/script/gsConvert.pl (modified) (12 diffs)

main/trunk/greenstone2/bin/script/gsConvert.pl

@@ -67 +67 @@
 my $pdf_allow_images_only;
 my $windows_scripting;
-my $openoffice_scripting;
 
 sub print_usage
@@ -75 +74 @@
     print STDERR "              or text using third-party programs.\n\n";
     print STDERR "  usage: $0 [options] filename\n";
-    if ($openoffice_scripting) {
-    print STDERR "  options:\n\t-type\tdoc|dot|docx|odf|pdf|ps|ppt|rtf|xls\t(input file type)\n";
-    }
-    else {
-    print STDERR "  options:\n\t-type\tdoc|dot|pdf|ps|ppt|rtf|xls\t(input file type)\n";
-    }
+    print STDERR "  options:\n\t-type\tdoc|dot|pdf|ps|ppt|rtf|xls\t(input file type)\n";
     print STDERR "\t-errlog\t<filename>\t(append err messages)\n";
     print STDERR "\t-output\tauto|html|text|pagedimg_jpg|pagedimg_gif|pagedimg_png\t(output file type)\n";
@@ -86 +80 @@
     print STDERR "\t-use_strings\tuse strings to extract text if conversion fails\n";
     print STDERR "\t-windows_scripting\tuse windows VB script (if available) to convert Microsoft Word and PPT documents\n";
-    print STDERR "\t-openoffice_scripting\tuse OpenOffice (if available) to convert Microsoft Office documents \n";
     print STDERR "\t-pdf_complex\tuse complex output when converting PDF to HTML\n";
     print STDERR "\t-pdf_nohidden\tDon't attempt to extract hidden text from PDF files\n";
@@ -106 +99 @@
 
     
-    # scan for -openoffice_scripting as it effects the permissible
-    # values for -type
-
-    foreach my $a (@ARGV) {
-    if ($a =~ m/^-openoffice_scripting$/) {
-        $openoffice_scripting = 1;
-        last;
-    }
-    }
-
-    my $parse_type;
-    if ($openoffice_scripting) {
-    $parse_type = 'type/(doc|dot|docx|odf|pdf|ps|ppt|rtf|xls)/';
-    }
-    else {
-    $parse_type = 'type/(doc|dot|pdf|ps|ppt|rtf|xls)/';
-    }
-
     # read command-line arguments
     if (!parsargv::parse(\@ARGV,
-             $parse_type, \$input_type,
+             'type/(doc|dot|pdf|ps|ppt|rtf|xls)/', \$input_type,
              '/errlog/.*/', \$faillogfile,
              'output/(auto|html|text|pagedimg).*/', \$output_type,
@@ -132 +107 @@
              'verbose/\d+/0', \$verbose,
              'windows_scripting',\$windows_scripting,
-             'openoffice_scripting',\$openoffice_scripting,
              'use_strings', \$use_strings,
              'pdf_complex', \$pdf_complex,
@@ -173 +147 @@
     print STDERR "Error: No filename extension or input type defined\n";
     exit(1);
-    } 
-    elsif ($openoffice_scripting && (($input_type eq "docx") || ($input_type eq "odf"))) {
-    print &convertDOC($input_filename, $output_filestem, $output_type);
-    print "\n";
     } 
     elsif ($input_type eq "doc" || $input_type eq "dot") {
@@ -230 +200 @@
     my ($input_filename, $output_filestem, $output_type) = @_;
 
-    if (($openoffice_scripting) && ($input_filename =~ m/\.docx?$/i)) {
-    # Jump right in and process with Open Office
-        if (openoffice_doc_to_html($input_filename, $output_filestem)) {
-        return "html";
-    }
-    else {
-        return "fail";
-    }
-    }
-
     # Many .doc files are not in fact word documents!
     my $realtype = &find_docfile_type($input_filename);
@@ -262 +222 @@
         $success = &native_doc_to_html($input_filename, $output_filestem);
     }
-    elsif ($openoffice_scripting) {
-        $success = &openoffice_doc_to_html($input_filename, $output_filestem);
-    }
     else {
         $success = &doc_to_html($input_filename, $output_filestem);    
@@ -288 +245 @@
     if ($windows_scripting) {
         $success = &native_doc_to_html($input_filename, $output_filestem);
-    }
-    elsif ($openoffice_scripting) {
-        $success = &openoffice_doc_to_html($input_filename, $output_filestem);
     }
     else {
@@ -402 +356 @@
     my $ppt_convert_type = "";
 
-    if ($openoffice_scripting) {
-    # Jump right in and process with Open Office
-        if (openoffice_doc_to_html($input_filename, $output_filestem)) {
-        return "html";
-    }
-    else {
-        return "fail";
-    }
-    }
-    
     #if (!$output_type || $windows_scripting || ($output_type !~ m/html/i) || ($output_type !~ m/text/i)){
     if ($windows_scripting && ($output_type !~ m/html/i) && ($output_type !~ m/text/i)){
@@ -475 +419 @@
     my $success = 0;
 
-    if ($openoffice_scripting) {
-    # Jump right in and process with Open Office
-        if (openoffice_doc_to_html($input_filename, $output_filestem)) {
-        return "html";
-    }
-    else {
-        return "fail";
-    }
-    }
-    
     # Attempt conversion to HTML
     if (!$output_type || ($output_type =~ m/html/i)) {
@@ -897 +831 @@
 }
 
-# Attempt to convert a word document to html with JODConvert scripting program
-sub openoffice_doc_to_html {
-    my ($input_filename, $output_filestem) = @_;
-
-    if (-e "$output_filestem.html") {
-    print STDERR "    The conversion file:\n";
-    print STDERR "      $output_filestem.html\n";
-    print STDERR "    ... skipping\n";
-    return 1;
-    }
-
-    my $oo_script_dir = &util::filename_cat($ENV{'GEXT_OPENOFFICE'}, "bin", "script");
-    my $oo2html = &util::filename_cat($oo_script_dir,"oo2html");
-    if (!-e $oo2html) {
-    print STDERR "Error: Unable to find 'oo2html' in: \n";
-    print STDERR "       $oo_script_dir\n";
-    print STDERR "       Is the OpenOffice extension to Greenstone installed?\n";
-    return 0;
-    }
-
-    my $cmd = "";
-    if ($timeout) {$cmd = "ulimit -t $timeout;";}
-    $cmd .=  "$oo2html \"$input_filename\" \"$output_filestem.html\"";
-
-    # redirecting STDERR
-    $cmd .= " 2> \"$output_filestem.err\""
-    if ($ENV {'GSDLOS'} !~ m/^windows$/i || $is_winnt_2000);
-    
-    # execute the command
-    $!=0;
-    if (system($cmd)!=0)
-    {
-    print STDERR "Error executing oo2html converter: $!\n";
-    print STDERR "Command was: $cmd\n";
-
-    if (-s "$output_filestem.err") {
-        open (ERRFILE, "<$output_filestem.err");
-        
-        my $write_to_fail_log=0;
-        if ($faillogfile ne "" && defined(open(FAILLOG,">>$faillogfile")))
-        {$write_to_fail_log=1;}
-
-        my $line;
-        while ($line=<ERRFILE>) {
-        if ($line =~ m/\w/) {
-            print STDERR "$line";
-            print FAILLOG "$line" if ($write_to_fail_log);
-        }
-        if ($line !~ m/startup error/) {next;}
-        print STDERR " (given an invalid .DOC file?)\n";
-        print FAILLOG " (given an invalid .DOC file?)\n"
-        if ($write_to_fail_log);
-        
-        } # while ERRFILE
-        close FAILLOG if ($write_to_fail_log);
-    }
-    return 0; # we can try any_to_text
-    }
-
-    # Was the conversion successful?
-    if (-s "$output_filestem.html") {
-    open(TMP, "$output_filestem.html");
-    my $line = <TMP>;
-    close(TMP);
-    if ($line && $line =~ m/html/i) {
-        &util::rm("$output_filestem.err") if -e "$output_filestem.err";
-        return 1;
-    }
-    }
-    
-    # If here, an error of some sort occurred
-    
-    &util::rm("$output_filestem.html") if -e "$output_filestem.html";
-    if (-e "$output_filestem.err") {
-    if ($faillogfile ne "" && defined(open(FAILLOG,">>$faillogfile"))) {
-        open (ERRLOG,"$output_filestem.err");
-        while (<ERRLOG>) {print FAILLOG $_;}
-        close FAILLOG;
-        close ERRLOG;
-    }
-    &util::rm("$output_filestem.err");
-    }
-    return 0;
-}
-
 # Attempt to convert an RTF document to html with rtftohtml
 sub rtf_to_html {