| 1 | ##---------------------------------------------------------------------------## |
| 2 | ## File: |
| 3 | ## $Id: mhtxtenrich.pl,v 2.5 2001/08/25 19:57:59 ehood Exp $ |
| 4 | ## Author: |
| 5 | ## Earl Hood mhonarc@mhonarc.org |
| 6 | ## Description: |
| 7 | ## Library defines a routine for MHonArc to filter text/enriched |
| 8 | ## data. |
| 9 | ## |
| 10 | ## Filter routine can be registered with the following: |
| 11 | ## |
| 12 | ## <MIMEFILTERS> |
| 13 | ## text/enriched:m2h_text_enriched'filter:mhtxtenrich.pl |
| 14 | ## text/richtext:m2h_text_enriched'filter:mhtxtenrich.pl |
| 15 | ## </MIMEFILTERS> |
| 16 | ## |
| 17 | ##---------------------------------------------------------------------------## |
| 18 | ## MHonArc -- Internet mail-to-HTML converter |
| 19 | ## Copyright (C) 1997-2001 Earl Hood, mhonarc@mhonarc.org |
| 20 | ## |
| 21 | ## This program is free software; you can redistribute it and/or modify |
| 22 | ## it under the terms of the GNU General Public License as published by |
| 23 | ## the Free Software Foundation; either version 2 of the License, or |
| 24 | ## (at your option) any later version. |
| 25 | ## |
| 26 | ## This program is distributed in the hope that it will be useful, |
| 27 | ## but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 28 | ## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 29 | ## GNU General Public License for more details. |
| 30 | ## |
| 31 | ## You should have received a copy of the GNU General Public License |
| 32 | ## along with this program; if not, write to the Free Software |
| 33 | ## Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA |
| 34 | ## 02111-1307, USA |
| 35 | ##---------------------------------------------------------------------------## |
| 36 | |
| 37 | package m2h_text_enriched; |
| 38 | |
| 39 | ##--------------------------------------------------------------------------- |
| 40 | ## Filter routine. |
| 41 | ## |
| 42 | sub filter { |
| 43 | my($fields, $data, $isdecode, $args) = @_; |
| 44 | my($innofill, $chunk, $ret, $charset); |
| 45 | $ret = ""; |
| 46 | $args = "" unless defined($args); |
| 47 | $charset = ""; |
| 48 | |
| 49 | ## Grab charset parameter (if defined) |
| 50 | $ctype = $fields->{'content-type'}[0] || ""; |
| 51 | if ($ctype =~ /charset=(\S+)/) { |
| 52 | $charset = lc $1; |
| 53 | $charset =~ s/['"]//g; |
| 54 | } |
| 55 | |
| 56 | ## Convert specials |
| 57 | $$data =~ s|&|\&|gi; |
| 58 | $$data =~ s|<<|\<|gi; |
| 59 | |
| 60 | ## Translate text/enriched commands |
| 61 | $innofill = 0; |
| 62 | foreach $chunk (split(m|(</?nofill>)|i, $$data)) { |
| 63 | if ($chunk =~ m|<nofill>|i) { |
| 64 | $ret .= "<PRE>"; |
| 65 | $innofill = 1; |
| 66 | next; |
| 67 | } |
| 68 | if ($chunk =~ m|</nofill>|i) { |
| 69 | $ret .= "</PRE>"; |
| 70 | $innofill = 0; |
| 71 | next; |
| 72 | } |
| 73 | convert_tags(\$chunk); |
| 74 | if (!$innofill) { |
| 75 | $chunk =~ s|(\r?\n\s*)|&nl_seq_to_brs($1)|gie; |
| 76 | } |
| 77 | $ret .= $chunk; |
| 78 | } |
| 79 | |
| 80 | ## Translate 8-bit characters to entity refs based on charset |
| 81 | ## (we already did '<' and '&' characters) |
| 82 | if ($charset =~ /iso-8859-([2-9]|10)/i) { |
| 83 | require 'iso8859.pl'; |
| 84 | $ret = iso_8859::str2sgml($ret, $charset, 1); |
| 85 | } |
| 86 | |
| 87 | $ret; |
| 88 | } |
| 89 | |
| 90 | ##--------------------------------------------------------------------------- |
| 91 | ## convert_tags translates text/enriched commands to HTML tags. |
| 92 | ## |
| 93 | sub convert_tags { |
| 94 | my($str) = shift; |
| 95 | |
| 96 | $$str =~ s|<(/?)bold>|<$1B>|gi; |
| 97 | $$str =~ s|<(/?)italic>|<$1I>|gi; |
| 98 | $$str =~ s|<(/?)underline>|<$1U>|gi; |
| 99 | $$str =~ s|<(/?)fixed>|<$1TT>|gi; |
| 100 | $$str =~ s|<(/?)smaller>|<$1SMALL>|gi; |
| 101 | $$str =~ s|<(/?)bigger>|<$1BIG>|gi; |
| 102 | |
| 103 | $$str =~ s|<fontfamily>\s*<param>([^<]+)</param>|<FONT face="$1">|gi; |
| 104 | $$str =~ s|</fontfamily>|</FONT>|gi; |
| 105 | $$str =~ s|<color>\s*<param>\s*(\S+)\s*</param>|<FONT color="$1">|gi; |
| 106 | $$str =~ s|</color>|</FONT>|gi; |
| 107 | $$str =~ s|<center>|<P align="center">|gi; |
| 108 | $$str =~ s|</center>|</P>|gi; |
| 109 | $$str =~ s|<flushleft>|<P align="left">|gi; |
| 110 | $$str =~ s|</flushleft>|</P>|gi; |
| 111 | $$str =~ s|<flushright>|<P align="right">|gi; |
| 112 | $$str =~ s|</flushright>|</P>|gi; |
| 113 | $$str =~ s|<flushboth>|<P align="both">|gi; # Not supported in HTML |
| 114 | $$str =~ s|</flushboth>|</P>|gi; |
| 115 | $$str =~ s|<paraindent>\s*<param>([^<]*)</param>|<BLOCKQUOTE>|gi; |
| 116 | $$str =~ s|</paraindent>|</BLOCKQUOTE>|gi; |
| 117 | |
| 118 | $$str =~ s|<excerpt>\s*(<param>([^<]*)</param>)?|<BLOCKQUOTE>|gi; |
| 119 | $$str =~ s|</excerpt>|</BLOCKQUOTE>|gi; |
| 120 | |
| 121 | # Not supported commands |
| 122 | $$str =~ s|<lang>\s*<param>([^<]*)</param>||gi; |
| 123 | $$str =~ s|</lang>||gi; |
| 124 | } |
| 125 | |
| 126 | ##--------------------------------------------------------------------------- |
| 127 | ## nl_seq_to_brs returns a "<BR>" string based on the number |
| 128 | ## on eols in a string. |
| 129 | ## |
| 130 | sub nl_seq_to_brs { |
| 131 | my($str) = shift; |
| 132 | my($n); |
| 133 | $n = $str =~ tr/\n/\n/; |
| 134 | --$n; |
| 135 | if ($n <= 0) { |
| 136 | return " "; |
| 137 | } else { |
| 138 | return "<br>\n" x $n; |
| 139 | } |
| 140 | } |
| 141 | |
| 142 | ##--------------------------------------------------------------------------- |
| 143 | ## preserve_space returns a string with all spaces and tabs |
| 144 | ## converted to nbsps. |
| 145 | ## |
| 146 | sub preserve_space { |
| 147 | my($str) = shift; |
| 148 | 1 while |
| 149 | $str =~ s/^([^\t]*)(\t+)/$1 . ' ' x (length($2) * 8 - length($1) % 8)/e; |
| 150 | $str =~ s/ /\ /g; |
| 151 | $str; |
| 152 | } |
| 153 | |
| 154 | ##--------------------------------------------------------------------------- |
| 155 | 1; |