#!/usr/bin/perl -w ###################################################################### # # # Code2HTML # # --------- # # # # Code2Html, version 0.7.1, Aug 1999, ppalfrad@cosy.sbg.ac.at # # # # AUTHOR # # Peter Palfrader, computer science student at the # # University of Salzburg/Austria. Written in 1999. # # # # DESCRIPTION # # code2html.pl is a perlscript which converts a program # # source code to syntax highlighted HTML by applying a set # # of regular expressions depending on the language # # the source code is written. # # # # LICENSE # # Copyright (c) 1999 by Peter Palfrader. # # Not derived from licensed software. # # # # Permission is granted to anyone to use this software for # # any purpose on any computer system, and to redistribute it # # in any way, subject to the following restrictions: # # # # 1. The author is not responsible for the consequences of # # use of this software, no matter how awful, even if they # # arise from defects in it. # # 2. The origin of this software must not be misrepresented, # # either by explicit claim or by omission. # # 3. Altered versions must be plainly marked as such, and # # must not be misrepresented (by explicit claim or # # omission) as being the original software. # # 3a. It would be nice if I got a copy of your improved # # version sent to ppalfrad@cosy.sbg.ac.at. However this # # is not obligatory. # # 4. This notice must not be removed or altered. # # # # Thanks to Henry Spencer for this wonderful license :). # # # # # # The regular expressions found in the default database are # # are not subject to this license. They have been taken # # from NEdit and were then slightly modified by me. # # # # According to Mark Edel who does the support # # of NEdit they are public domain and so you may do with # # them whatever you want. # # # ###################################################################### # # # HISTORY # # # # 0.7.1 - August 1999 # # * corrected (hopefully) a gotcha in the perl patterns (again...) # # * added one item to the changelog of 0.7.0 # # * --replace_tabs no longer replaces every tab with the given # # amount of spaces but instead it now replaces it with the right # # number to go to the next tabstop. the parameter given to # # replace_tabs gives the width of tabstops. # # TNX to T. Jahn for providing an example # # of how to do this in one of his programs. If I had known it # # was that easy I'ld have done it earlier :) # # # # 0.7.0 - August 1999 # # * No longer need for that stupid fatal_error sub. I now use perl's # # handlers for __DIE__ and __WARN__ # # * complete rewrite of the option and parameter fetching sub. I # # now use Getopt::Long. TNX to Barrie for the pointer. As a # # the number for --replace_tabs / -t is no longer optional. # # * Added HTML patching: code2html now also allows you to have # # inline source code in an html file. It can then take this html # # file and insert the syntax highlighted code. # # Look in the help. It's very usefull ( at least for me ) # # * the CGI mode got a forth way to pass the input file. If the # # input_selector parameter is set to REDIRECT_URL the file is # # taken from ENV{'DOCUMENT_ROOT'}.$ENV{'REDIRECT_URL'}. # # Kevin Burton suggested this so that # # it is possible to configure Apache with an action directive # # to automatically print java files syntax highlighted. # # # # 0.6.6 - July 1999 # # * added sql - it is still very poor since I don't know all the # # keywords etc. If you know, tell me. # # * Martynov Andrew pointed me to the qq, qx, # # etc operators in perl. They should now no longer cause problems # # * Wayne Roberts # # reported a problem with C strings like "\\". It should be fixed # # too. # # * I changed the operator with which the default language base # # is assigned to a variable, so there's no need for \\\\\\\\\\ # # quotes anymore :) # # # # 0.6.5 - June 1999 # # * tweaking Perl regular expressions (TNX to Barrie Slaymaker # # ) # # * if a language mode cannot be found the error message now tells # # you which lang you requested. # # * new --fallback option. This language mode is used if the # # given mode by parameter #1 is not available. This feature was # # requested by Barrie Slaymaker # # * changed 'is called as CGI' heuristics. # # # # 0.6.4 - May 1999 # # * the name attribute in the line numbers was wrong. there should # # be no # in it. TNX to # # * linking to line numbers now works from the command line too # # # # 0.6.3 - May 1999 # # * fixed C character constant regex. TNX to Jesse # # # # * line numbers now can link to themselves # # * line numbers now have a constant width # # # # 0.6.2 - May 1999 # # * fixed something in HTML lang # # # # 0.6.1 - May 1999 # # * added 'plain' language mode # # * cgi support improoved. should now also handle # # enctype="multipart/form-data" forms # # # # 0.6.0 - May 1999 # # * fixed Substitution loop at ./code2html.pl (5.2) line 627 # # * changed string regular expressions: \" is no longer a problem # # * default locations for the language files have changed: # # first all the files listed in the enviroment variable # # CODE2HTML_CONFIG (seperated by colons (:)) will be checked, # # then, if HOME set, $HOME/.code2html.config and finally # # /etc/code2html.config # # TNX to Eric Brandwine for the hint. # # * new: --no_header does not print the ... stuff # # * new: --content_type prints Content-Type: text/html; # # * C/C++: in preprocessor lines: strings are highlighted now # # * -n now also names the lines with .. # # * script may now be run as a CGI script. see the CGI section # # in the help # # * get_config_file was rewritten because it was _ugly_ # # # # 0.5.2 - May 1999 # # * fixed Makefile dependency line bug. (a * in regexp instead a +) # # # # 0.5.1 - May 1999 # # * clarified copyright questions on regular expressions # # * changed -dumb_default_lang to -dump_default_lang :) # # # # 0.5.0 - Apr 1999 # # * changed find_all_matches__create_taglist__insert_placeholders # # so that it works around a bug in earlier perl versions, in which # # pos() is not set if the return value of m//g is not used. # # * changed a regex in get_config_file # # # # 0.4.1 - Mar 1999 # # * changed JavaScript regexps slightly # # * changed find_all_matches_.. slightly # # # # 0.4.0 - Mar 1999 # # * script no longer needs $' and $` thus beeing faster. $& is still # # needed # # * regexps for perl changed slightly # # * find_all_matches has been completly rewritten. verify is no # # longer needed. taglist is built while searching. # # May take a bit longer now, but otherwhise a bug could not have # # been fixed. # # * changed (fixed?) start of language_def_block pos evaluation # # # # 0.3.3 - Feb 1999 # # * fixed STDIN/STDOUT parameters when passed a - the scrpit though # # options would follow and didn't tread this as a handle for STDIN # # * added -V as shortcut to --version # # # # 0.3.2 - Feb 1999 # # * removed -T from 1st line so activePerl will run the script # # without any modifications # # * changed perl string regexps. run now faster and better # # (and run at all under win) # # * added --replace_tabs # # # # 0.3.1 - Feb 1999 # # * fixed language files bug (lang_mode no longer # # starts langmode) # # * fixed empty html tag bug when reading lang specs # # * added languages: Makefile, Java, JavaScript, Perl # # * added --modes # # # # 0.3.0 - Feb 1999 # # * added linenumbers # # * added and tag in html output # # * fixed crlf switch works now # # # # 0.2.0 - Feb 1999 # # * first official release # # # ###################################################################### use strict; use Getopt::Long; my $FILES_DISALLOWED_IN_CGI = 0; # you may set this to true to disallow file reading from your hd in # cgi mode. This may be good if your httpd runs as 'root' (yes, I've # seen this!) and so any user could with some knowledge easily read # your /etc/shadow for example! my $FILES_REDIRECT_DISALLOWED = 0; my $vernr = "0.7.1"; my $monthshort = "Aug"; my $monthlong = "August"; my $pure_version_message = "Code2Html, version $vernr, $monthshort 1999, ppalfrad\@cosy.sbg.ac.at"; my $version_message = "\$pure_version_message\n\n"; my $help_message = " $pure_version_message NAME code2html.pl - Converts a program source code to HTML SYNOPSIS (1) code2html.pl [options] language_mode [input_file [output_file]] (2) code2html.pl -p [file] (3) code2html.pl (as a CGI script: see CGI section below) DESCRIPTION code2html.pl is a perlscript which converts a program source code to syntax highlighted HTML by applying a set of regular expressions depending on the language the source code is written. EXAMPLE USAGE assuming code2html.pl is in the current directory, you may type code2html.pl perl code2html.pl code2html.html to convert the script into a html file. (1) OPTIONS language_mode Specify the set of regular expressions to use. These have to be defined in a langugage file (see FILES below). To find out which language modes are defined, issue a code2html.pl --modes. This input is treated case-insensitive. input_file Is the file which contains the program source code to be formatted. If not specified or a minus (-) is given, the code will be read from STDIN. output_file Is the file ro write the formatted code to. If not specified or a minus (-) is given, the code will be written to STDOUT. -v, --verbose Prints progress information to STDERR. You will not need this. -n, --linenumbers Print out the source code with line numbers. -N, --linknumbers Print out the source code with line numbers. The linenumbers will link to themselves, which makes it easy to send links to lines. -t, --replace_tabs <TABSTOP WIDTH> Replace each occurence of a <TAB> character with the right amount of spaces to get to the next TABSTOP. can be changed by an optional argument. -l, --language_file <FILE> Specify an alternate languages file to take the regular expressions from (see FILES below). -m, --modes Print all defined modes currently defined to STDOUT and exit succesfully. Also prints modes from a given language_file if applicable. --fallback <LANG> If the language mode givin with the first parameter (language_mode) cannot be found then use this mode. Usefull when code2html is called from a script to ensure output is created: --fallback plain --dump_default_lang Write default language file to STDOUT and exit succesfully. -h, -? --help Print this text and exit succesfully. -V --version Print the program version and exit succesfully. -c --content_type Prints \"Content-Type: text/html\\n\\n\" prior to the html file. Usefull if the script is ivoked as a cgi script. -H --no_header do not print the <html>, <head>, <body>, <pre> stuff. Usefull if this script is only a part in a bigger program. (2) code2html.pl -p [file] code2html now also allows you to have inline source code in an html file. It can then take this html file and insert the syntax highlighted code. If no file is given, code2html reads from STDIN and writes to STDOUT. To use this feature, just insert a like like this into your html file: <!-- code2html add [options] lang_mode <file> --> the syntax highlighted file will be inserted at this position enclosed in <pre> tags. All options that can be given on the commandline like --linenumbers etc. work. --help, --version and --dump_default_lang work too however it is not very intelligent to use them :). --content_type is ignored. You may also write the program's source code directly in the html file with the following syntax: <!-- code2html add [options] lang_mode <your program source code here> --> This is a very new feature, so if you have problems or questions, please let me know. An example can be found at my homepage: http://www.cosy.sbg.ac.at/~ppalfrad (3) CGI If the the script is used as a CGI script (GATEWAY_INTERFACE envoriment set and no command line arguments given) code2html reads the arguments either from the query string or from stdin. (methods POST and GET). --content_type is switched on automatically and the output always goes to STDOUT. The following parameters/options are accepted: language_mode - required 'c', 'cc', 'pas', etc. fallback - optional 'plain', 'c', etc. if language_mode cannot be found, use this one input_selector - optional either 'file', 'cgi_input1', 'cgi_input2', or 'REDIRECT_URL' default: file filename file to read from if input_selector is 'file' cgi_input1 the source code to syntax highlight for example from a <textarea> or from a upload. see input_selector cgi_input2 the source code to syntax highlight for example from a <textarea> or from a upload. see input_selector line_numbers - optional 'yes', 'no' or 'link' default: no replace_tabs - optional if 0 then tabs are not replaced, if larger then each tab is replaced by that many spaces. default: 0 Why two cgi_inputs you may ask: This is to allow your users to choose vie a <form> interface whether they want to insert their file into a <textarea> or user a <browse> button to select their file. See the example on my home- page. Note that by default it is possbile for your users to read all the files the httpd can read (if you don't run a cgi- wrapper or something like this . You may disallow file reading via cgi with setting FILES_DISALLOWED_IN_CGI to 1 at the top of the script. The input selector REDIRECT_URL needs a special explaination. The file name is formed from the two enviroment variables DOCUMENT_ROOT and REDIRECET_URL. Kevin Burton <burton\@relativity.yi.org> will tell you what you need this for: > So I had a problem where I wanted all my Java files > automatically converted to html and displayed. But I > didn't want to write any crazy web interface for > code2html. > So what I did was this. > > Configured Apache with an \"Action\" directive in srm.conf > like this: > > Action text/java > /cgi-bin/code2html?language_mode=java&input_selector=REDIRECT_URL > > Works great! > > It is more powerfull if you use it in an Apache > <Directory> tag > > <Directory /source> > > #with your Action tag here... this way you can > #still have regular .java files on your server. > > </Directory> > BUGS If the input file contains all 256 possible characters then all character values of 255 will be changed to values of 254. I don't think this is a problem and so I will not try to find a other way to code this stuff. If however this is a problem for you, let me know and I will rethink my strategy. Please report bugs to ppalfrad\@cosy.sbg.ac.at. This program is still in beta so you might find some. Also have a look at my web-site, perhaps a new version is available already: http://www.cosy.sbg.ac.at/~ppalfrad/ FILES file specified by -l or --language_file if any files specified in \$CODE2HTML_CONFIG, seperated by colons \$HOME/.code2html.config /etc/code2html.config built in default languages These databases will be searched in that order for the set of regular expressions specified by the language_mode parameter. The first set of regular expression which is found will be taken. The files must have the following structure: Empty lines are ignored. Every line beginning with a pound sign (#) is a comment. Note that a line actually must start with this character (apart from tabs and spaces) in order to be a comment. A language starts with the name of it's section in brackets. Aliases may be defined withing the same brackets seperated by a comma (,). Examples: [c] [c++,cpp,cc] Then the default background and text colours may be set. If not defined they default to #ffffff (white) for the background and #000000 (black) for the text. bgcolor=#ffffff textcolor=#000000 Spaces and Tabs before and after the equals-sign (=) are allowed. The first non whitespace after the = sign until the end of line will then be copied to the bgcolor and the text options in the HTMLs body tag. As a third step the regular expressions must be defined: A line defining this consist of three parts: The html tag to insert at the start of the pattern's occurance, one to insert at the end and the pattern itself. All three parts must be enclosed in double quotes(\") and are seperated by commas (,). If one of those parts contains a double quote, this must be escaped with a backshlash (\\). Example: \"<i>\", \"</i>\", \"\\\".*?\\\"\" This line prints all strings enclosed by double quotes italic. If a line starts with a minus (-) then this pattern is applied to the matched part of the previos line that had no minus in front. So you can highlight for example escape characters in strings. - \"<strong>\", \"</strong>\", \"\\\\.\" If you ever write languages files yourself, I'ld be happy if you could send be them, so I put them on my homepage with full credits of course. Before you do so you might also have a look at my site to check wheter someone has written the file for your language already. web-site: http://www.cosy.sbg.ac.at/~ppalfrad/ AUTHOR Peter Palfrader, computer science student at the University of Salzburg/Austria. Written in $monthlong 1999. LICENSE Copyright (c) 1999 by Peter Palfrader. Not derived from licensed software. Permission is granted to anyone to use this software for any purpose on any computer system, and to redistribute it in any way, subject to the following restrictions: 1. The author is not responsible for the consequences of use of this software, no matter how awful, even if they arise from defects in it. 2. The origin of this software must not be misrepresented, either by explicit claim or by omission. 3. Altered versions must be plainly marked as such, and must not be misrepresented (by explicit claim or omission) as being the original software. 3a. It would be nice if I got a copy of your improved version sent to ppalfrad\@cosy.sbg.ac.at. However this is not obligatory. 4. This notice must not be removed or altered. Thanks to Henry Spencer for this wonderful license :). The regular expressions found in the default database are are not subject to this license. They have been taken from NEdit and were then slightly modified by me. According to Mark Edel <edel\@ltx.com> who does the support of NEdit they are public domain and so you may do with them whatever you want. "; my $short_help = " $pure_version_message NAME code2html.pl - Converts a program source code to HTML SYNOPSIS code2html.pl language_mode [input_file [output_file]] [options] DESCRIPTION code2html.pl is a perlscript which converts a program source code to syntax highlighted HTML by applying a set of regular expressions depending on the language the source code is written. "; my $USE_CGI_FOR_ERRORS = 0; $SIG{'__DIE__'} = sub { if ($USE_CGI_FOR_ERRORS) { print "Content-Type: text/plain\n\n$_[0]\n"; } else { print STDERR $_[0]; }; exit 1; }; $SIG{'__WARN__'} = sub { if (!$USE_CGI_FOR_ERRORS) { print STDERR $_[0]; }; }; my %params = &parse_params; if ($params{'what_to_do'} eq 'patch_html') { &patch_html(\%params) } elsif ($params{'what_to_do'} eq 'normal' ) { &main(\%params) } else { die("I don't know what to do :(\n") }; sub main { my %params = %{shift()}; my $hidechar = ""; # a character that must not exist in the code and which is used as a placeholder will be set in $code; my $bgcolor = "#ffffff"; #default value only. will be set in parse_config_part my $textcolor = "#000000"; #default value only. will be set in parse_config_part my @CONFIG_FILES = []; push @CONFIG_FILES, split(/:/,$params{'langfile'}) if defined($params{'langfile'}); push @CONFIG_FILES, split(/:/,$ENV{'CODE2HTML_CONFIG'}) if ($ENV{'CODE2HTML_CONFIG'}); push @CONFIG_FILES, $ENV{'HOME'}."/.code2html.config" if (defined($ENV{'HOME'})); push @CONFIG_FILES, "/etc/code2html.config"; print STDERR "parsing config file...\n" if ($params{'verbose'}); my @regexps = &parse_config_part( &get_config_file(\@CONFIG_FILES, \%params) , $bgcolor, $textcolor); print STDERR "loading input file...\n" if ($params{'verbose'}); my $code = &get_input_file(\%params, $hidechar); print STDERR "finding all matches, inserting placeholders, creating taglist...\n" if ($params{'verbose'}); my @taglist = &find_all_matches__create_taglist__insert_placeholders(\@regexps, $code, $hidechar); print STDERR "converting source code to HTML...\n" if ($params{'verbose'}); $code = &convert_code_2_html($code); print STDERR "replacing placeholders with appropriate HTML tags...\n" if ($params{'verbose'}); $code = &insert_tags(\@taglist, $code, $hidechar); print STDERR "outputting file...\n" if ($params{'verbose'}); return &put_output(\%params, $code, $bgcolor, $textcolor); } sub patch_html { my %params = %{shift()}; my $code; open(FILEHANDLE, $params{'infile'}) || die("Error while opening inputfile.\n"); undef $/; $code = <FILEHANDLE>; close(FILEHANDLE); $code =~ s/<!-- code2html delete start -->.*?<!-- code2html delete stop -->//gs; my $counter=0; my @chunks = split ( /(<!-- code2html add.*?-->)/s , $code); $code = ''; for (@chunks) { $code .= $_; if ($_ =~ /<!-- code2html add(.*?)(\n.*?)?-->/s) { my $cmdline = $1; my $input = $2; $cmdline =~ s/^[ \t]*//g; $cmdline =~ s/[ \t]*$//g; @ARGV = split ( / / , $cmdline); my %new_params = &parse_params; $new_params{'input'} = $input if ($new_params{'infile'} eq "-"); undef $new_params{'outfile'}; $new_params{'line_number_prefix'} = ++$counter; $new_params{'verbose'} = $params{'verbose'}; my $no_header = $new_params{'noheader'}; $new_params{'noheader'} = 1; if ($no_header) { $code .= '<!-- code2html delete start -->'.. &main(\%new_params). '<!-- code2html delete stop -->'; } else { $code .= '<!-- code2html delete start --><pre>'. &main(\%new_params). '</pre><!-- code2html delete stop -->'; }; }; }; open(FILEHANDLE, '>'.$params{'infile'}) || die("Error while opening outputfile.\n"); print FILEHANDLE $code; close(FILEHANDLE); }; ##################################################################### ################### get_input_data ################################## ##################################################################### # Reads the input data for the cgi script. # in : nothing # out: a hash with the input data sub get_input_data { my $input_data; my %f; if($ENV{'REQUEST_METHOD'} eq 'GET') { $input_data = $ENV{'QUERY_STRING'}; } else { read(STDIN, $input_data, $ENV{'CONTENT_LENGTH'}); }; if ($ENV{'CONTENT_TYPE'} =~ m/^multipart\/form-data; boundary=(.*)$/i) { my $boundary = quotemeta($1); my @blocks = split(/$boundary/, $input_data); for (@blocks) { if (my $dummy = m/name="(.*?)"/i) { my $name = $1; $_ =~ s/\r\n/\n/g; m/\n\n(.*)\n/s; my $value = $1; $f{$name}=$value; }; }; } elsif ($ENV{'CONTENT_TYPE'} =~ m/^multipart\/form-data;$/i) # if the boundary is not in the enviroment variable we'll guess { my $dummy = $input_data =~ m/^(.*?)(\n|\r)/; my $boundary = $1; my @blocks = split(/$boundary/, $input_data); for (@blocks) { if (my $dummy = m/name="(.*?)"/i) { my $name = $1; $_ =~ s/\r\n/\n/g; m/\n\n(.*)\n/s; my $value = $1; $f{$name}=$value; }; }; } else { my @form_fields = split(/&/, $input_data); for (@form_fields) { my ($name, $value) = split(/=/, $_); $value =~ tr/+/ /; $value =~ s/%([a-fA-F0-9][a-fA-F0-9])/pack("C", hex($1))/eg; $f{$name} = $value; } }; return %f; }; ################################################################################ ####################### parse_params ########################################### ################################################################################ sub parse_params { my %RESULT; if (defined($ENV{'GATEWAY_INTERFACE'}) && (!scalar(@ARGV))) # if there is a CGI enviroment and no parameters/options given { $USE_CGI_FOR_ERRORS = 1; $RESULT{'content-type'} = 1; $RESULT{'what_to_do'} = 'normal'; my %input = &get_input_data; if (!defined($input{'language_mode'})) {die('CGI parse error: language mode not given!')}; $RESULT{'langmode'} = $input{'language_mode'}; if ($input{'input_selector'} eq "cgi_input1") { if (!defined($input{'cgi_input1'})) {die('CGI parse error: cgi_input1 does not exist!')}; $RESULT{'input'} = $input{'cgi_input1'}; } elsif ($input{'input_selector'} eq "cgi_input2") { if (!defined($input{'cgi_input2'})) {die('CGI parse error: cgi_input2 does not exist!')}; $RESULT{'input'} = $input{'cgi_input2'}; } elsif ($input{'input_selector'} eq "file") { if ($FILES_DISALLOWED_IN_CGI) {die('CGI parse error: option not supported due to security reasons!')}; if (!defined($input{'filename'})) {die('CGI parse error: filename not defined!')}; $RESULT{'infile'} = $input{'filename'}; } elsif ($input{'input_selector'} eq "REDIRECT_URL") { if ($FILES_REDIRECT_DISALLOWED) {die('CGI parse error: option not supported due to security reasons!')}; if (!defined($ENV{'REDIRECT_URL'})) {die('CGI parse error: ENV: REDIRECT_URL not defined!')}; $RESULT{'infile'} = $ENV{'DOCUMENT_ROOT'}.$ENV{'REDIRECT_URL'}; } else { die('CGI parse error: input selector not given!'); }; if ($input{'line_numbers'} eq "yes") { $RESULT{'linenumbers'} = 'yes'; }; if ($input{'line_numbers'} eq "link") { $RESULT{'linenumbers'} = 'link'; }; if (defined($input{'replace_tabs'})) { $RESULT{'replacetabs'} = $input{'replace_tabs'} }; if (defined($input{'fallback'})) { $RESULT{'alt_langmode'} = $input{'fallback'} }; $RESULT{'content_type'} = 1; $RESULT{'outfile'} = '-'; } else { my $verbose = 0; my $linenumbers = 0; my $linknumbers = 0; my $replace_tabs = 0; my $language_file = ''; my $modes = 0; my $fallback = ''; my $dump_default_lang = 0; my $help = 0; my $version = 0; my $content_type = 0; my $no_header = 0; my $patch_html; Getopt::Long::config('bundling'); if (! GetOptions( "--verbose" , \$verbose , "-v" , \$verbose , "--linenumbers" , \$linenumbers , "-n" , \$linenumbers , "--linknumbers" , \$linknumbers , "-N" , \$linknumbers , "--replace_tabs=i" , \$replace_tabs , "-t=i" , \$replace_tabs , "--language_file=s" , \$language_file , "-l=s" , \$language_file , "--modes" , \$modes , "-m" , \$modes , "--fallback=s" , \$fallback , "--dump_default_lang" , \$dump_default_lang , "--help" , \$help , "-s" , \$help , "-h" , \$help , "--version" , \$version , "-V" , \$version , "--content_type" , \$content_type , "-c" , \$content_type , "--no_header" , \$no_header , "-H" , \$no_header , "--patch_html" , \$patch_html , "-p" , \$patch_html ) ) { print STDERR $short_help; print STDERR "\n\nrun code2html --help for furhter help\n"; exit 1; }; if ($help) { print $help_message; exit 0; }; if ($version) { print $version_message; exit 0; }; if ($dump_default_lang) { print &get_default_database; exit 0; }; if ($patch_html) { $RESULT{'what_to_do'} = 'patch_html'; $RESULT{'verbose'} = $verbose; if (!defined ($RESULT{'infile'} = shift(@ARGV))) { $RESULT{'infile'} = '-' }; $RESULT{'outfile'} = $RESULT{'infile'}; } else { $RESULT{'what_to_do'} = 'normal'; $RESULT{'verbose'} = $verbose; if ($linknumbers) { $RESULT{'linenumbers'} = 'link' } elsif ($linenumbers) { $RESULT{'linenumbers'} = 'yes' } else { $RESULT{'linenumbers'} = 'no' }; $RESULT{'replacetabs'} = $replace_tabs; $RESULT{'langfile'} = $language_file; $RESULT{'modes'} = $modes; $RESULT{'alt_langmode'} = $fallback; $RESULT{'content_type'} = $content_type; $RESULT{'noheader'} = $no_header; if (!defined ($RESULT{'langmode'} = shift(@ARGV))) { print STDERR "no language mode given!\n"; print STDERR $short_help; print STDERR "\n\nrun code2html --help for furhter help\n"; exit 1; }; if (!defined ($RESULT{'infile'} = shift(@ARGV))) { $RESULT{'infile'} = '-'}; if (!defined ($RESULT{'outfile'} = shift(@ARGV))) { $RESULT{'outfile'} = '-'}; if (defined (shift(@ARGV))) { print STDERR "too many parameters!\n"; print STDERR $short_help; print STDERR "\n\nrun code2html --help for furhter help\n"; exit 1; }; }; }; return %RESULT; }; ################################################################################ ####################### get_config_lines ####################################### ################################################################################ sub get_config_lines { #in : \@lines #in : metaquoted $langmode #in : $modes #returns config file as string my @lines = @{shift()}; my ($lm, $modes) = @_; my $result = ""; if ($modes) { for (@lines) { $_ =~ s/\n|\r//g; $_ =~ s/^[ \t]*(.*)[ \t]*/$1/; #remove beginning and trailing spaces / tabs print " ".$_."\n" if (substr($_,0,1) eq "["); } } else { my $waiting = 1; for (@lines) { if ($waiting) { $_ =~ s/\n|\r//g; $_ =~ s/^[ \t]*(.*)[ \t]*/$1/; #remove beginning and trailing spaces / tabs if ($_ =~ m/^\[(.*?[, ])?$lm([, ].*?)?\]/i) {$waiting = 0;}; } else { $_ =~ s/\n|\r//g; $_ =~ s/^[ \t]*(.*)[ \t]*/$1/; #remove beginning and trailing spaces / tabs last if (substr($_,0,1) eq "["); #new language mode if (($_ ne "")&&(substr($_, 0, 1) ne "#")) { $_ =~ /^(.*)$/; # untaint input $result .= $1."\n"; } } }; }; return $result; }; ################################################################################ ####################### get_one_config_file #################################### ################################################################################ sub get_one_config_file { #in: filename #in: langmode already meta quoted. #in: modes; #returns config file as string my ($filename, $langmode, $modes) = @_; open(FILEHANDLE, "<$filename") || return ""; my @lines = <FILEHANDLE>; my $result = get_config_lines(\@lines, $langmode, $modes); close FILEHANDLE; return $result; }; ################################################################################ ####################### get_config_file ######################################## ################################################################################ sub get_config_file { #in : @config_files #in : %params #returns config file as string my @CONFIG_FILES = @{shift()}; my %PARAMS = %{shift()}; #Apply language mode my $result = ""; if ($PARAMS{'modes'}) { print "\n\nDefined language modes:\n"; print "-----------------------\n"; print "(You may use any of the names seperated\n"; print "by commas to refer to a certain mode.)\n\n"; }; for (@CONFIG_FILES) { print "in file $_:\n" if $PARAMS{'modes'}; $result = &get_one_config_file($_, quotemeta($PARAMS{'langmode'}), $PARAMS{'modes'}); if ($result ne "") {last;}; }; if ($result eq "") { print "in default database:\n" if $PARAMS{'modes'}; my @lines = split(/\n/,&get_default_database); $result = &get_config_lines(\@lines, quotemeta($PARAMS{'langmode'}), $PARAMS{'modes'}); } if ($PARAMS{'modes'}) { print "-----------------------\n"; print "That's it\n\n\n"; exit; }; if ($result eq "") { if ($PARAMS{'alt_langmode'} ne "") { warn("Given language mode '".$PARAMS{'langmode'}."' was not found in config files. Falling back to '".$PARAMS{'alt_langmode'}."'.\n"); $PARAMS{'langmode' } = $PARAMS{'alt_langmode'}; $PARAMS{'alt_langmode'} = ""; $result = get_config_file(\@CONFIG_FILES, \%PARAMS); } else { die("Given language mode '".$PARAMS{'langmode'}."' was not found in config files.\n"); }; } return $result; }; ################################################################################ ####################### parse_config_part ###################################### ################################################################################ sub parse_config_part { #in: string: config data #in: string: bgcolor #in: string: textcolor #returns @regexps my ($configdata, $bgcolor, $textcolor) = @_; my @regexps = (); while ($configdata =~ /(^[^\-].*?$)/gms) # ) { my $us = $1; my $after = substr($configdata, pos($configdata)); if ($us =~ /^"/) #";# xemacs :) { my %t = (); my $tmp = ""; my @child = (); $us =~ s/([ \t]*("([^"]|\\")*")[ \t]*,)//m; $tmp = $1; $tmp =~ m/("(.*[^\\])?")/; $tmp = $1; $tmp =~ s/"(.*)"/$1/g; $tmp =~ s/\\"/"/g; $t{"html1"} = $tmp; $us =~ s/([ \t]*("([^"]|\\")*")[ \t]*,)//m; $tmp = $1; $tmp =~ m/("(.*[^\\])?")/; $tmp = $1; $tmp =~ s/"(.*)"/$1/g; $tmp =~ s/\\"/"/g; $t{"html2"} = $tmp; $us =~ s/([ \t]*("([^"]|\\")*")[ \t]*$)//m; $tmp = $1; $tmp =~ m/("(.*[^\\])?")/; $tmp = $1; $tmp =~ s/"(.*)"/$1/g; $tmp =~ s/\\"/"/g; $t{"regex"} = $tmp; if ($after =~ /(^\n\-.*?($|\n[^\-]))/s) { $tmp = $1; $tmp =~ s/^\n//; $tmp =~ s/\n.$//; $tmp =~ s/^-[ \t]*//mg; @child = &parse_config_part($tmp."\n"); }; $t{"childregex"} = \@child; push @regexps, \%t; } else { if ($us =~ s/^bgcolor[ \t]*=[ \t]*//i) { $_[1] = $us; } elsif ($us =~ s/^textcolor[ \t]*=[ \t]*//i) { $_[2] = $us; } }; }; return @regexps; }; ################################################################################ ####################### checkTabulator ######################################### ################################################################################ sub checkTabulator { my ($line, $TABSTOP) = @_; while ((my $at = index($line, "\t")) != -1) { my $cnt = ($TABSTOP - ($at % $TABSTOP)); my $replace_with = ' ' x $cnt if ($cnt); $line =~ s/\t/$replace_with/; }; return $line; } ################################################################################ ####################### get_input_file ######################################### ################################################################################ sub get_input_file { # in : \%params # out : hidechar # returns: input file my %PARAMS = %{$_[0]}; my $code; my $hidechar = ""; if (defined($PARAMS{'input'}) && ($PARAMS{'input'} ne "")) { $code = $PARAMS{'input'}; $code =~ s/\r//g; } else { open(FILEHANDLE, $PARAMS{'infile'}) || die("Error while opening inputfile.\n"); undef $/; $code = <FILEHANDLE>; close(FILEHANDLE); }; if ($PARAMS{'replacetabs'} != 0) { my @lines = split(/\n/, $code); for (@lines) { $_ = &checkTabulator($_, $PARAMS{'replacetabs'}); }; $code = join("\n", @lines); # my $replacewith = " " x $PARAMS{'replacetabs'}; # $code =~ s/\t/$replacewith/g; }; #find a character that does not exist in $code foreach $a (0..255) { my $n = quotemeta(chr($a)); if (!($code =~ s/$n/$n/g)) { $_[1] = chr($a); last; }; }; if ($_[1] eq "") # if no character - which does not exist in $code - was found then be brute { $code =~ s/\xff/\xfe/g; $_[1] = "\xff"; } return $code; }; ################################################################################ ####################### find_all_matches__create_taglist__insert_placeholders ## ################################################################################ sub find_all_matches__create_taglist__insert_placeholders { # in: regexps # in/out: code # in : hidechar # returns: @taglist; my @regexps = @{$_[0]}; my $code = $_[1]; my $hidechar = $_[2]; my @taglist; if (!@regexps) {return @taglist}; #if there are no regexps, then there are not hits. my $over_length = length($code)+1; my $index=0; my @regexps_occurence; for (@regexps) { my %t; $t{"index"} = $index; $t{"regex"} = $$_{"regex"}; $t{"html1"} = $$_{"html1"}; $t{"html2"} = $$_{"html2"}; pos($code) = 0; if ($code =~ /$t{"regex"}/gms) { $t{"first_occurence"} = pos($code) - length($&) } else { $t{"first_occurence"} = $over_length; }; push @regexps_occurence, \%t; $index++; }; @regexps_occurence = sort { $$a{"first_occurence"} <=> $$b{"first_occurence"} || $$a{"index"} <=> $$b{"index"} } @regexps_occurence; while (${$regexps_occurence[0]}{"first_occurence"} < $over_length) { my %t; pos($code) = ${$regexps_occurence[0]}{"first_occurence"} + scalar(@taglist); my $dummy = $code =~ /${$regexps_occurence[0]}{"regex"}/gms; my $match = $&; my $matchend = pos($code); my $matchlength = length($match); my $delta_offset = 0; push @taglist, ${$regexps_occurence[0]}{"html1"}; #push beginning html tag my @m = @{ ${ %{$regexps[${$regexps_occurence[0]}{"index"}]} }{"childregex"} }; if (@m) { my @newtaglist = &find_all_matches__create_taglist__insert_placeholders( \@m, $match, $hidechar); $delta_offset = scalar(@newtaglist); push @taglist, @newtaglist; }; $code = substr($code, 0, $matchend-$matchlength) . $hidechar . $match . $hidechar . substr($code, $matchend); push @taglist, ${$regexps_occurence[0]}{"html2"}; #push ending html tag for (@regexps_occurence) { if (${$_}{"first_occurence"} < $matchend+2+$delta_offset - scalar(@taglist)) { pos($code) = $matchend+2+$delta_offset; if ($code =~ /${$_}{"regex"}/gms) { ${$_}{"first_occurence"} = pos($code) - length($&) - scalar(@taglist); } else { ${$_}{"first_occurence"} = $over_length; }; } else { last; } } @regexps_occurence = sort { $$a{"first_occurence"} <=> $$b{"first_occurence"} || $$a{"index"} <=> $$b{"index"} } @regexps_occurence; }; $_[1] = $code; return @taglist; }; ################################################################################ ####################### convert_code_2_html #################################### ################################################################################ sub convert_code_2_html { # in: code # returns: code my $code = $_[0]; $code =~ s/&/&/g; $code =~ s/>/>/g; $code =~ s/</</g; $code =~ s/"/"/g; # "# just because xemacs syntax highlighting messes things up return $code; }; ################################################################################ ####################### insert_tags ############################################ ################################################################################ sub insert_tags { # in: taglist # in: code # in: hidechar # returns: code my @taglist = @{$_[0]}; my $tmp = $_[1]; my $hidechar = $_[2]; my $newcode = ""; for (@taglist) # go for all tags { # This goes must faster than # $code =~ s/$hidechar/$_/; $tmp =~ m/(^.*?)$hidechar(.*)/s; $newcode .= $1.$_; $tmp = $2; }; return $newcode.$tmp; }; ################################################################################ ####################### put_output ############################################# ################################################################################ sub prettyprint { # don't ask me what happens if $nr does not fit into $lengthofnr chars! my ($nr, $lengthofnr) = @_; my $result = " " x $lengthofnr; substr($result, -length($nr)) = $nr; return $result; } sub put_output { my %PARAMS = %{shift()}; my ($code, $bgcolor, $textcolor) = @_; my $text = ''; $text .= "Content-Type: text/html;\n\n" if ($PARAMS{'content_type'}); $text .= "<html><head><title>". ($PARAMS{'outfile'} eq '-' ? 'STDIN' : $PARAMS{'outfile'} eq '-'). "
\n"         if (!$PARAMS{'noheader'});


	
      my @lines = split(/\n/,$code);
      my $nr = 1;

      my $nr_of_lines = scalar(@lines);
      my $lengthofnr = 0;
      while ($nr_of_lines>1)
	{
	    $lengthofnr++;
	    $nr_of_lines = $nr_of_lines / 10;
	};
 
      my $prefix = '';
      $prefix = $PARAMS{'line_number_prefix'}.'_' if defined $PARAMS{'line_number_prefix'};
      for (@lines)
	{
	    if ($PARAMS{'linenumbers'} eq 'link')
	      { $text .= ''.&prettyprint($nr, $lengthofnr).'  '.$_."\n"; }
	    elsif ($PARAMS{'linenumbers'} eq 'yes')
	      { $text .= ''.&prettyprint($nr, $lengthofnr).'  '.$_."\n"; }
	    else
	      { $text .= ''.$_."\n"; };
	    $nr++;
	}

      
      $text .= "
\n" if (!$PARAMS{'no_header'}); if (defined($PARAMS{'outfile'})) { open (FILEHANDLE, ">".$PARAMS{'outfile'}) || die("Error while opening outputfile.\n"); print FILEHANDLE $text; close (FILEHANDLE); }; return $text; }; ################################################################################ ####################### get_default_database ################################### ################################################################################ sub get_default_database { # last evaluated value will be returned my $tmp = <<'EODB'; ###################################################################### ################################# Plain ############################## ###################################################################### [plain] bgcolor=#ffffff textcolor=#000000 ###################################################################### ################################# Ada 95 ############################# ###################################################################### [ada,ada95] bgcolor=#ffffff textcolor=#000000 #Comments "", "", "--.*?$" #String Literals "", "", "\".*?(\"|$)" #Character Literals "", "", "'.'" #Ada Attibutes "", "", "'[a-zA-Z][a-zA-Z_]+\b" #Numeric Literals "", "", "(((2|8|10|16)#[_0-9a-fA-F]*#)|[0-9.]+)" #Withs Pragmas Use "", "", "\b(([wW]ith|WITH|[pP]ragma|PRAGMA|[uU]se|USE)[ \t\n\f\r]+[a-zA-Z0-9_.]+;)+\b" #Predefined Types "", "", "\b([bB]oolean|BOOLEAN|[cC]haracter|CHARACTER|[cC]ount|COUNT|[dD]uration|DURATION|[fF]loat|FLOAT|[iI]nteger|INTEGER|[lL]ong_[fF]loat|LONG_FLOAT|[lL]ong_[iI]nteger|LONG_INTEGER|[pP]riority|PRIORITY|[sS]hort_[fF]loat|SHORT_FLOAT|[sS]hort_[iI]nteger|SHORT_INTEGER|[sS]tring|STRING)\b" #Predefined Subtypes "", "", "\b([fF]ield|FIELD|[nN]atural|NATURAL|[nN]umber_[bB]ase|NUMBER_BASE|[pP]ositive|POSITIVE|[pP]riority|PRIORITY)\b" #Reserved Words "", "", "\b([aA]bort|ABORT|[aA]bs|ABS|[aA]ccept|ACCEPT|[aA]ccess|ACCESS|[aA]nd|AND|[aA]rray|ARRAY|[aA][tT]|[bB]egin|BEGIN|[bB]ody|BODY|[cC]ase|CASE|[cC]onstant|CONSTANT|[dD]eclare|DECLARE|[dD]elay|DELAY|[dD]elta|DELTA|[dD]igits|DIGITS|[dD][oO]|[eE]lse|ELSE|[eE]lsif|ELSIF|[eE]nd|END|[eE]ntry|ENTRY|[eE]xception|EXCEPTION|[eE]xit|EXIT|[fF]or|FOR|[fF]unction|FUNCTION|[gG]eneric|GENERIC|[gG]oto|GOTO|[iI][fF]|[iI][nN]|[iI][sS]|[lL]imited|LIMITED|[lL]oop|LOOP|[mM]od|MOD|[nN]ew|NEW|[nN]ot|NOT|[nN]ull|NULL|[oO][fF]|[oO][rR]|[oO]thers|OTHERS|[oO]ut|OUT|[pP]ackage|PACKAGE|[pP]ragma|PRAGMA|[pP]rivate|PRIVATE|[pP]rocedure|PROCEDURE|[rR]aise|RAISE|[rR]ange|RANGE|[rR]ecord|RECORD|[rR]em|REM|[rR]enames|RENAMES|[rR]eturn|RETURN|[rR]everse|REVERSE|[sS]elect|SELECT|[sS]eparate|SEPARATE|[sS]ubtype|SUBTYPE|[tT]ask|TASK|[tT]erminate|TERMINATE|[tT]hen|THEN|[tT]ype|TYPE|[uU]se|USE|[wW]hen|WHEN|[wW]hile|WHILE|[wW]ith|WITH|[xX]or|XOR)\b" #Ada 95 Only "", "", "\b([aA]bstract|ABSTRACT|[tT]agged|TAGGED|[aA]ll|ALL|[pP]rotected|PROTECTED|[aA]liased|ALIASED|[rR]equeue|REQUEUE|[uU]ntil|UNTIL)\b" #Identifiers "", "", "\b[a-zA-Z][a-zA-Z0-9_]*\b" #Dot All "", "", "\.[aA][lL][lL]\b" ###################################################################### ################################# C ################################## ###################################################################### [c] bgcolor=#ffffff textcolor=#000000 #comment "", "", "/\*.*?\*/" #string "", "", "((\"\")|(\"\\\\\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character - "", "", "\\." #preprocessor line "", "", "^[ \t]*#.*?$" #string - "", "", "((\"\")|(\"\\\\\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character -- "", "", "\\." # - "", "", "<.*?>" #comment - "", "", "[^/]/\*.*?\*/" #character constant "", "", "'(\\)?.'" #esc character - "", "", "\\." #numeric constant "", "", "\b((0(x|X)[0-9a-fA-F]*)|(([0-9]+\.?[0-9]*)|(\.[0-9]+))((e|E)(\+|-)?[0-9]+)?)(L|l|UL|ul|u|U|F|f)?\b" #storage keyword "", "", "\b(const|extern|auto|register|static|unsigned|signed|volatile|char|double|float|int|long|short|void|typedef|struct|union|enum)\b" #keyword "", "", "\b(return|goto|if|else|case|default|switch|break|continue|while|do|for|sizeof)\b" #braces "", "", "[\{\}]" #symbols "", "", "([\*\-\+=:;%&\|<>\(\)\[\]!])" #identifiers "", "", "([a-zA-Z_][a-zA-Z_0-9]*)" ###################################################################### ################################# C ++ ############################### ###################################################################### [c++,cpp,cc] bgcolor=#ffffff textcolor=#000000 #comment "", "", "/\*.*?\*/" #cplus comment "", "", "//.*?$" #string "", "", "((\"\")|(\"\\\\\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character - "", "", "\\." #preprocessor line "", "", "^[ \t]*#.*?$" #string - "", "", "((\"\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character -- "", "", "\\." # - "", "", "<.*?>" #comment - "", "", "[^/]/\*.*?\*/" #cplus comment - "", "", "//.*?$" #character constant "", "", "'(\\)?.'" #esc character - "", "", "\\." #numeric constant "", "", "\b((0(x|X)[0-9a-fA-F]*)|(([0-9]+\.?[0-9]*)|(\.[0-9]+))((e|E)(\+|-)?[0-9]+)?)(L|l|UL|ul|u|U|F|f)?\b" #storage keyword "", "", "\b(class|typename|typeid|template|friend|virtual|inline|explicit|operator|overload|public|private|protected|const|extern|auto|register|static|mutable|unsigned|signed|volatile|char|double|float|int|long|short|bool|wchar_t|void|typedef|struct|union|enum)\b" #keyword "", "", "\b(new|delete|this|return|goto|if|else|case|default|switch|break|continue|while|do|for|catch|throw|sizeof|true|false|namespace|using|dynamic_cast|static_cast|reinterpret_cast)\b" #braces "", "", "[\{\}]" #symbols "", "", "([\*\-\+=:;%&\|<>\(\)\[\]!])" #identifiers "", "", "([a-zA-Z_][a-zA-Z_0-9]*)" ###################################################################### ################################# HTML ############################### ###################################################################### [html] bgcolor=#ffffff textcolor=#000000 #comment "", "", "" #special chars "", "", "\&[-.a-zA-Z0-9#]*;?" #tag "", "", "<(/|!)?[-.a-zA-Z0-9]*.*?>" #double quote string - "", "", "\".*?\"" #single quote string - "", "", "'.*?'" #brackets - "", "", "[<>]" #attribute - "", "", "[^'\"]+?" ###################################################################### ################################# Java ############################### ###################################################################### [java] bgcolor=#ffffff textcolor=#000000 #doc comment "", "", "/\*\*.*?\*/" #comment "", "", "/\*.*?\*/" #cplus comment "", "", "//.*?$" #string "", "", "((\"\")|(\"\\\\\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character - "", "", "\\." #single quoted "", "", "'([^\\]|\\[^'])*?'" #numeric constant "", "", "\b((0(x|X)[0-9a-fA-F]*)|(([0-9]+\.?[0-9]*)|(\.[0-9]+))((e|E)(\+|-)?[0-9]+)?)(L|l|UL|ul|u|U|F|f)?\b" #include "", "", "\b(import|package)\b.*?$" #esc character - "", "", "\\(.|\n)" #comment - "", "", "[^/]/\*.*?\*/" #storage keyword "", "", "\b(abstract|boolean|byte|char|class|double|extends|final|float|int|interface|long|native|private|protected|public|short|static|transient|synchronized|void|volatile|implements)\b" #keyword "", "", "\b(break|case|catch|continue|default|do|else|false|finally|for|if|instanceof|new|null|return|super|switch|this|throw|throws|true|try|while)\b" #braces and parens "", "", "[\{\}\(\)\[\]]" #Identifiers "", "", "\b[a-zA-Z_][a-zA-Z0-9_]*\b" #symbols "", "", "([\*\-\+=:;%&\|<>!])" ###################################################################### ################################# JavaScript ######################### ###################################################################### [js,javascipt] bgcolor=#ffffff textcolor=#000000 #comment "", "", "/\*.*?\*/" #cplus comment "", "", "//.*?$" #numeric constant "", "", "\b((0(x|X)[0-9a-fA-F]*)|(([0-9]+\.?[0-9]*)|(\.[0-9]+))((e|E)(\+|-)?[0-9]+)?)(L|l|UL|ul|u|U|F|f)?\b" #events "", "", "\b(onAbort|onBlur|onClick|onChange|onDblClick|onDragDrop|onError|onFocus|onKeyDown|onKeyPress|onLoad|onMouseDown|onMouseMove|onMouseOut|onMouseOver|onMouseUp|onMove|onResize|onSelect|onSubmit|onUnload)\b" #braces "", "", "[\{\}]" #statements "", "", "\b(break|continue|else|for|if|in|new|return|this|typeof|var|while|with)\b" #function "", "", "function[\t ]+([a-zA-Z0-9_]+)[\t \(]+.*?[\n{]" #function args - "", "", "\(.*?\)" #function name - "", "", "[\t ][a-zA-Z0-9_]+" #built in object type "", "", "\b(anchor|Applet|Area|Array|button|checkbox|Date|document|elements|FileUpload|form|frame|Function|hidden|history|Image|link|location|Math|navigator|Option|password|Plugin|radio|reset|select|string|submit|text|textarea|window)\b" #string "", "", "\".*?(\"|$)" #Colors - "", "", "(aliceblue|antiquewhite|aqua|aquamarine|azure|beige|bisque|black|blanchedalmond|blue|blueviolet|brown|burlywood|cadetblue|chartreuse|chocolate|coral|cornflowerblue|cornsilk|crimson|cyan|darkblue|darkcyan|darkgoldenrod|darkgray|darkgreen|darkkhaki|darkmagenta|darkolivegreen|darkorange|darkorchid|darkred|darksalmon|darkseagreen|darkslateblue|darkslategray|darkturquoise|darkviolet|deeppink|deepskyblue|dimgray|dodgerblue|firebrick|floralwhite|forestgreen|fuchsia|gainsboro|ghostwhite|gold|goldenrod|gray|green|greenyellow|honeydew|hotpink|indianred|indigo|ivory|khaki|lavender|lavenderblush|lawngreen|lemonchiffon|lightblue|lightcoral|lightcyan|lightgoldenrodyellow|lightgreen|lightgrey|lightpink|lightsalmon|lightseagreen|lightskyblue|lightslategray|lightsteelblue|lightyellow|lime|limegreen|linen|magenta|#008000|mediumaquamarine|mediumblue|mediumorchid|mediumpurple|mediumseagreen|mediumslateblue|mediumspringgreen|mediumturquoise|mediumvioletred|midnightblue|mintcream|mistyrose|moccasin|navajowhite|navy|oldlace|olive|olivedrab|orange|orangered|orchid|palegoldenrod|palegreen|paleturquoise|palevioletred|papayawhip|peachpuff|peru|pink|plum|powderblue|purple|red|rosybrown|royalblue|saddlebrown|salmon|sandybrown|seagreen|seashell|sienna|silver|skyblue|slateblue|slategray|snow|springgreen|steelblue|tan|teal|thistle|tomato|turquoise|violet|wheat|white|whitesmoke|yellow|yellowgreen|#[A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9])" #string "", "", "'.*?('|$)" #Colors - "", "", "(aliceblue|antiquewhite|aqua|aquamarine|azure|beige|bisque|black|blanchedalmond|blue|blueviolet|brown|burlywood|cadetblue|chartreuse|chocolate|coral|cornflowerblue|cornsilk|crimson|cyan|darkblue|darkcyan|darkgoldenrod|darkgray|darkgreen|darkkhaki|darkmagenta|darkolivegreen|darkorange|darkorchid|darkred|darksalmon|darkseagreen|darkslateblue|darkslategray|darkturquoise|darkviolet|deeppink|deepskyblue|dimgray|dodgerblue|firebrick|floralwhite|forestgreen|fuchsia|gainsboro|ghostwhite|gold|goldenrod|gray|green|greenyellow|honeydew|hotpink|indianred|indigo|ivory|khaki|lavender|lavenderblush|lawngreen|lemonchiffon|lightblue|lightcoral|lightcyan|lightgoldenrodyellow|lightgreen|lightgrey|lightpink|lightsalmon|lightseagreen|lightskyblue|lightslategray|lightsteelblue|lightyellow|lime|limegreen|linen|magenta|#008000|mediumaquamarine|mediumblue|mediumorchid|mediumpurple|mediumseagreen|mediumslateblue|mediumspringgreen|mediumturquoise|mediumvioletred|midnightblue|mintcream|mistyrose|moccasin|navajowhite|navy|oldlace|olive|olivedrab|orange|orangered|orchid|palegoldenrod|palegreen|paleturquoise|palevioletred|papayawhip|peachpuff|peru|pink|plum|powderblue|purple|red|rosybrown|royalblue|saddlebrown|salmon|sandybrown|seagreen|seashell|sienna|silver|skyblue|slateblue|slategray|snow|springgreen|steelblue|tan|teal|thistle|tomato|turquoise|violet|wheat|white|whitesmoke|yellow|yellowgreen|#[A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9][A-Fa-f0-9])" #event capturing "", "", "\b(captureEvents|releaseEvents|routeEvent|handleEvent)\b.*?(\)|$)" #predefined methods "", "", "\b(abs|acos|alert|anchor|asin|atan|atan2|back|big|blink|blur|bold|ceil|charAt|clear|clearTimeout|click|close|confirm|cos|escape|eval|exp|fixed|floor|focus|fontcolor|fontsize|forward|getDate|getDay|getHours|getMinutes|getMonth|getSeconds|getTime|getTimezoneOffset|getYear|go|indexOf|isNaN|italics|javaEnabled|join|lastIndexOf|link|log|max|min|open|parse|parseFloat|parseInt|pow|prompt|random|reload|replace|reset|reverse|round|scroll|select|setDate|setHours|setMinutes|setMonth|setSeconds|setTimeout|setTime|setYear|sin|small|sort|split|sqrt|strike|sub|submit|substring|sup|taint|tan|toGMTString|toLocaleString|toLowerCase|toString|toUpperCase|unescape|untaint|UTC|write|writeln)\b" #properties "", "", "\b(action|alinkColor|anchors|appCodeName|appName|appVersion|bgColor|border|checked|complete|cookie|defaultChecked|defaultSelected|defaultStatus|defaultValue|description|E|elements|enabledPlugin|encoding|fgColor|filename|forms|frames|hash|height|host|hostname|href|hspace|index|lastModified|length|linkColor|links|LN2|LN10|LOG2E|LOG10E|lowsrc|method|name|opener|options|parent|pathname|PI|port|protocol|prototype|referrer|search|selected|selectedIndex|self|SQRT1_2|SQRT2|src|status|target|text|title|top|type|URL|userAgent|value|vlinkColor|vspace|width|window)\b" #operators "", "", "([=;->/&|])" ###################################################################### ################################# Makefile ########################### ###################################################################### [make,makefile] bgcolor=#ffffff textcolor=#000000 #comment "", "", "#.*?$" #Assignment "", "", "^( *| [ \t]*)[A-Za-z0-9_+]*[ \t]*(\+|:)?=" #Dependency Line "", "", "^ *([A-Za-z0-9./$(){} _%+-]|\n)*::?" #Dependency Target - "", "", "[A-Za-z0-9./$(){} _%+-]+" #Dependency continuation - "", "", "\\\n" #comment - "", "", "#.*?$" #macro - "", "", "\$([A-Za-z0-9_]|\([^)]*\)|{[^}]*})" #int macro - "", "", "\$([<@*?%]|\$@)" #Continuation "", "", "\\$" #Macro "", "", "\$([A-Za-z0-9_]|\([^)]*\)|{[^}]*})" #Internal Macro "", "", "\$([<@*?%]|\$@)" #Escaped Dollar "", "", "\$\$" #Include "", "", "^include[ \t]" ###################################################################### ################################# Pascal ############################# ###################################################################### [pas,pascal] bgcolor=#ffffff textcolor=#000000 #comment1 (* *) "", "", "\(\*.*?\*\)" #comment1 { } "", "", "\{.*?\}" #string "", "", "'.*?('|$)" #preprocessor line "", "", "^[ \t]*#.*?$" #comment1 (* *) - "", "", "\(\*.*?\*\)" #comment1 { } - "", "", "\{.*?\}" #character constant "", "", "'.'" #numeric constant "", "", "\b((0(x|X)[0-9a-fA-F]*)|[0-9.]+((e|E)(\+|-)?)?[0-9]*)(L|l|UL|ul|u|U|F|f)?\b" #storage and ops "", "", "\b(and|AND|array|const|div|export|file|function|import|in|IN|label|mod|module|nil|not|NOT|only|or|OR|packed|pow|pragma|procedure|program|protected|qualified|record|restricted|set|type|var)\b" #keywords "", "", "\b(begin|case|do|downto|else|end|for|goto|if|of|otherwise|repeat|then|to|until|while|with)\b" #symbols "", "", "([\*\-\+=:;<>\(\)\[\]!]|[^/]/[^/])" #identifiers "", "", "([a-zA-Z_][a-zA-Z_0-9.^]*[a-zA-Z_0-9]|[a-zA-Z_][a-zA-Z_0-9]*)" #dot, carret(sp?) - "", "", "(\.|\^)+" ###################################################################### ################################# Perl ############################### ###################################################################### [perl] bgcolor=#ffffff textcolor=#000000 #comment "", "", "#.*?$" #variables "", "", "[$@%]\$?({[^}]*}|[^a-zA-Z0-9_/\t\n\.,\\[\\{\\(]|[0-9]+|[a-zA-Z_][a-zA-Z0-9_]*)?" #string; so this part realy is weird, but it works! "", "", "((\"\")|(\"\\\\\")|(\"[^\"\\]\")|(\"[^\"].*?[^\\]\"))" #esc character - "", "", "\\." #variables - "", "", "[$@%]\$?({[^}]*}|[^a-zA-Z0-9_/\t\n\.,\\[\\{\\(]|[0-9]+|[a-zA-Z_][a-zA-Z0-9_]*)?" #string; so this part realy is weird, but it works! "", "", "(('')|('\\\\')|('[^'\\]')|('[^'].*?[^\\]'))" #esc character - "", "", "\\." #more strings - q// qw// "", "", "(?:\b| )(?:q|qw)(\W)(\\\1|[^\1\n])*(\1)" #esc character - "", "", "\\." #more strings qq// qx// "", "", "(?:\b| )(?:qq|qx)(\W)(\\\1|[^\1\n])*(\1)" #esc character - "", "", "\\." #variables - "", "", "[$@%]\$?({[^}]*}|[^a-zA-Z0-9_/\t\n\.,\\[\\{\\(]|[0-9]+|[a-zA-Z_][a-zA-Z0-9_]*)?" #subroutine header "", "", "sub[\t ]+([a-zA-Z0-9_]+)[\t \n]*(\{|\n)" #subr header coloring - "", "", "[\t ]([a-zA-Z0-9_]+)" #ignore escaped chars # "", "", "\\[#"'\$msytq]" #regex matching # "", "", "(\b| )((m|q|qq)?/)(\\/|[^/\n])*(/[gimsox]*)" "", "", "(\b| )?(/)(\\/|[^/\n])*(/[gimsox]*)" "", "", "(?:\b| )(?:(?:m|q|qq)(\W))(\\\1|[^\1\n])*(\1[gimsox]*)" #regex substitution # "", "", "(\b| )((s|y|tr)/)(\\/|[^/\n])*(/)[^/\n]*(/[gimsox]*)" "", "", "(?:\b| )?(?:s(\W))(?:\\\1|[^\1\n])*?(\1)[^(\1)\n]*?(\1[gimsox]*)" #translate "", "", "(?:\b| )(?:(?:tr|y)(\W))(?:\\\1|[^\1\n])*?(\1)[^(\1)\n]*?(\1[gimsox]*)" #keywords "", "", "\b(my|local|new|if|until|while|elsif|else|eval|unless|for|foreach|continue|exit|die|last|goto|next|redo|return|local|exec|do|use|require|package|eval|BEGIN|END|eq|ne|not|\|\||\&\&|and|or)\b" #library fns "", "", "\b(abs|accept|alarm|atan2|bind|binmode|bless|caller|chdir|chmod|chomp|chop|chr|chroot|chown|closedir|close|connect|cos|crypt|dbmclose|dbmopen|defined|delete|die|dump|each|endgrent|endhostent|endnetent|endprotoent|endpwent|endservent|eof|exec|exists|exp|fctnl|fileno|flock|fork|format|formline|getc|getgrent|getgrgid|getgrnam|gethostbyaddr|gethostbyname|gethostent|getlogin|getnetbyaddr|getnetbyname|getnetent|getpeername|getpgrp|getppid|getpriority|getprotobyname|getprotobynumber|getprotoent|getpwent|getpwnam|getpwuid|getservbyname|getservbyport|getservent|getsockname|getsockopt|glob|gmtime|grep|hex|import|index|int|ioctl|join|keys|kill|lcfirst|lc|length|link|listen|log|localtime|lstat|map|mkdir|msgctl|msgget|msgrcv|no|oct|opendir|open|ord|pack|pipe|pop|pos|printf|print|push|quotemeta|rand|readdir|read|readlink|recv|ref|rename|reset|reverse|rewinddir|rindex|rmdir|scalar|seekdir|seek|select|semctl|semget|semop|send|setgrent|sethostent|setnetent|setpgrp|setpriority|setprotoent|setpwent|setsockopt|shift|shmctl|shmget|shmread|shmwrite|shutdown|sin|sleep|socket|socketpair|sort|splice|split|sprintf|sqrt|srand|stat|study|substr|symlink|syscall|sysopen|sysread|system|syswrite|telldir|tell|tie|tied|time|times|truncate|uc|ucfirst|umask|undef|unlink|unpack|unshift|untie|utime|values|vec|wait|waitpid|wantarray|warn|write|qw|-[rwxoRWXOezsfdlpSbctugkTBMAC])\b" #braces and parens "", "", "[\[\]\{\}\(\)]" #<< stuff "", "", "<<'([^\n]*)';.*?^\1$" "", "", "<<([^\n]*).*?^\1$" ###################################################################### ################################# sql ################################ ###################################################################### [sql] bgcolor=#ffffff textcolor=#000000 #keywords "", "", ",|%|<|>|:=|=|\(|\)|\b(SELECT|ON|FROM|ORDER BY|DESC|WHERE|AND|OR|NOT|NULL|TRUE|FALSE|select|on|from|order by|desc|where|and|or|not|null|true|false|Select|On|From|Order By|Desc|Where|And|Or|Not|Null|True|False)\b" #comment "", "", "--.*?$" #comment "", "", "/\*.*?\*/" #string; so this part realy is weird, but it works! "", "", "(('')|('[^'\\]')|('[^'].*?[^\\]'))" #keywords "", "", "END IF;|End If;|end if;|\b(CREATE|REPLACE|BEGIN|END|FUNCTION|RETURN|FETCH|OPEN|CLOSE|INTO|IS|IN|WHEN|OTHERS|GRANT|ON|TO|EXCEPTION|SHOW|SET|OUT|PRAGMA|AS|PACKAGE|create|replace|begin|end|function|return|fetch|open|close|into|is|in|when|others|grant|on|to|exception|show|set|out|pragma|as|package|Create|Replace|Begin|End|Function|Return|Fetch|Open|Close|Into|Is|In|When|Others|Grant|On|To|Exception|Show|Set|Out|Pragma|As|Package)\b" #keywords "", "", "\b(ALTER|Alter|alter)\b" #datatypes "", "", "\b(INTEGER|Integer|integer|BLOB|Blob|blobl|DATE|Date|date|NUMERIC|Numeric|numeric|CHARACTER|Character|character|VARYING|Varying|varying|VARCHAR|Varchar|varchar|CHAR|Char|char)\b" #st "", "", "\b(CONSTRAINT|Constraint|constraint|KEY|Key|key|CONSTRAINT|Constraint|constraint|REFERENCES|References|references|PRIMARY|Primary|primary|TABLE|Table|table|FOREIGN|Foreign|foreign|ADD|Add|add|INSERT|Insert|insert|GROUP BY|Group By|group by)\b" ###################################################################### EODB ; };