root/trunk/freewrt/scripts/roff2htm

# $FreeWRT$
# $MirOS: src/scripts/roff2htm,v 1.55 2007/10/23 11:09:38 tg Exp $
# $ekkoBSD: catman2html.sh,v 1.2 2004/03/07 03:02:53 stephen Exp $
#-
# Copyright (c) 2004, 2005, 2006, 2007
#       Thorsten “mirabilos” Glaser <tg@mirbsd.de>
# Original version for ekkoBSD by:
# Copyright (c) 2004
#       Stephen Paskaluk <sap@mirbsd.org>
# Parts of the regular expression set below are based upon work by:
# Copyright (c) 1995
#       Panagiotis J. Christias <christia@theseas.ntua.gr>
#
# Provided that these terms and disclaimer and all copyright notices
# are retained or reproduced in an accompanying document, permission
# is granted to deal in this work without restriction, including un-
# limited rights to use, publicly perform, distribute, sell, modify,
# merge, give away, or sublicence.
#
# Advertising materials mentioning features or use of this work must
# display the following acknowledgement:
#       This product includes material provided by Thorsten Glaser.
#
# This work is provided “AS IS” and WITHOUT WARRANTY of any kind, to
# the utmost extent permitted by applicable law, neither express nor
# implied; without malicious intent or gross negligence. In no event
# may a licensor, author or contributor be held liable for indirect,
# direct, other damage, loss, or other issues arising in any way out
# of dealing in the work, even if advised of the possibility of such
# damage or existence of a defect, except proven that it results out
# of said person's immediate fault when using the work as intended.
#-
# Routines for converting catman pages and nrcon(1)d papers to HTML.
# ATTENTION: this file contains embedded white-, backspace and high-
#            bit-on control characters! Use “jupp --asis $0” to edit
# Note: this file contains magic and can’t be edited as UTF-8 either.
# Note: this script assumes MirBSD filesystem interna: ino_t=uint32_t

# check if mksh R31:2007/10/18 or up
if [[ $KSH_VERSION = @(\@\(#\)MIRBSD KSH R)@(3[2-9]|[4-9][0-9]|[1-9][0-9][0-9])\ +([0-9])/+([0-9])/+([0-9])?(\ *) ]]; then
        i=0
elif [[ $KSH_VERSION = @(\@\(#\)MIRBSD KSH R31)* ]]; then
        eval $(print "$KSH_VERSION" | sed 's#^.*R31 \([0-9]*\)/\([0-9]*\)/\([0-9]*\)\( .*\)*$#y=\1 m=\2 d=\3#')
        (( i = y < 2007 ? 1 :
            y > 2007 ? 0 :
            m < 10 ? 1 :
            m > 10 ? 0 :
            d < 18 ? 1 : 0 ))
        unset y m d
else
        i=1
fi
# we need an mksh version with uint32_t array indicēs
if (( i )); then
        print -u2 Error: your mksh is not recent enough.
        print -u2 Please upgrade to at least mksh R32.
        exit 1
fi
unset i

# initialise globals
roff2htm_gendate=$(date +"%F %T")               # current time
set -A roff2htm_inodecache                      # inode cache (empty)
if stat --help >/dev/null 2>&1; then
        roff2htm_statarg=-Lc                    # GNU stat (coreutils)
else
        roff2htm_statarg=-Lf                    # BSD stat (base system)
fi
unset LANGUAGE                                  # GNU locale (LC_MESSAGES)
export LC_ALL=C                                 # SUSv3 locale (override)

function do_convert {
        typeset -i ws=0
        col -x | sed -e 's/[     ]*$//g'                                \
            -e '/-$/N
{
s/\([0-9A-z][-.,0-9A-z]*\)-\n\(  *\)\([0-9A-z][-.,0-9A-z]*([1-9n][A-z]*)\)\([^ ]*\) /\1\3\4\
\2/
}'                                                                      \
            -e '/-$/N
{
s/\([0-9A-z][-.,0-9A-z]*\)-\n\(  *\)\([0-9A-z][-.,0-9A-z]*([1-9n][A-z]*)\)\([^ ]*\) /\1\3\4\
\2/
}'                                                                      \
            -e 'y#&<>#��#'                                              \
                                                                        \
            -e '/^[A-Z]/s#.##g'                                       \
            -e 's#^[A-Z][ ,A-Z0-9]*$#</pre><h2>&</h2><pre>#'            \
            -e 's#^  \([A-Z][ ,A-Z0-9]*\)$#</pre><h3>\1</h3><pre>#'    \
                                                                        \
            -e 's#_\([^�-�][�-�]*\)#<i>\1</i>#g'                       \
            -e 's#[^�-�][�-�]*\([^�-�][�-�]*\)#<b>\1</b>#g'            \
                                                                        \
            -e 's#</\([bi]\)><\1>##g'                                   \
            -e 's#</b><b>[^�-�][�-�]*##g'                              \
            -e 's#</b>[^�-�][�-�]*<b>##g'                              \
            -e 's#[^�-�][�-�]*##g'                                     \
            -e 's#_</i<b><</b>i>##g'                                    \
                                                                        \
            -e 's#^\( \{2,3\}\)\([A-Z][ ,0-9A-z]*\)$#\1<b>\2</b>#'      \
                                                                        \
            -e '/^   /s#\(\([0-9A-z][-.,0-9A-z]*\)(\([1-9n]\)[/0-9A-Za-z]*)\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
            -e '/^   /s#\(<i>\([0-9A-z][-.,0-9A-z]*\)</i>(\([1-9n]\)[/0-9A-Za-z]*)\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
            -e '/^   /s#\(\([0-9A-z][-.,0-9A-z]*\)(\([PSU][MS][DM]\))\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
            -e '/^   /s#\(<i>\([0-9A-z][-.,0-9A-z]*\)</i>(\([PSU][MS][DM]\))\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
            -e '/^   /s#\(\([0-9A-z][-.,0-9A-z]*\)(\(PAPERS\))\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
            -e '/^   /s#\(<i>\([0-9A-z][-.,0-9A-z]*\)</i>(\(PAPERS\))\)#<a href=\"../man\3/\2.htm\">\1</a>#g' \
                                                                        \
            -e 's#<b>+</b>\( *\)<b>o</b># \1•#'                         \
            -e 's#<b>+</b>#•#'                                          \
            -e 's#</\([bi]\)><\1>##g'                                   \
            -e 's#</\([bi]\)>\([[:punct:][:space:]]*\)<\1>#\2#g'        \
            -e 's#\([^[:punct:]]\)\([-!"#$%&'\''()*+,./:;=?@[\]^_`{|}~]*\)\(<[bi]>\)#\1\3\2#g'  \
            -e 's#\(<i>[fh]t*p:[^<]*\)</i>/#\1/</i>#g'                  \
            -e 's#\(<i>/[^<]*\)</i>/#\1/</i>#g'                         \
            -e 's#<h3>*<b>*>#<h3>#g' -e 's#</b></h3>#</h3>#g'           \
                                                                        \
            -e 's/�\&#38;/g'                                            \
            -e 's/�/\&#60;/g'                                           \
            -e 's/�/\&#62;/g'                                           \
                                                                        \
            -e '1s#^#<pre>#'                                            \
            -e '$s#$#</pre>#'                                           \
            -e 's#<pre></pre>##g'                                       \
            -e 's#</pre><pre>##g'                                       \
            -e 's#<a href="../man'${1:-0}'/#<a href="#g'                \
        | while IFS= read -r line; do
                if [[ -n $line ]]; then
                        print -r -- "$line"
                        ws=0
                else
                        (( !ws++ )) && print
                fi
        done
}

function output_header {
        print '<?xml version="1.0" encoding="utf-8" ?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
 "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en"><head>
 <meta http-equiv="content-type" content="text/html; charset=utf-8" />
 <title>RTFM '$1\($2')</title>
 <meta name="robots" content="index, follow" />
</head><body>
<p>• <a href="../">Index</a> or by <a href="../pkgs/">package</a> or section
 <a href="../man1/">1</a> <a href="../man2/">2</a> <a href="../man3/">3</a>
 <a href="../man3p/">3p</a> <a href="../man4/">4</a> <a href="../man5/">5</a>
 <a href="../man6/">6</a> <a href="../man7/">7</a> <a href="../man8/">8</a>
 <a href="../man9/">9</a> <a href="../mann/">n</a>
 • <a href="https://www.freewrt.org/trac/">Homepage</a> •</p><hr />
<h1>FreeWRT Manual: <a href="../man'$2/$1'.htm">'$1\($2')</a></h1>'
}

function output_footer {
        print '<hr /><p style="font-size:xx-small;">Generated on' \
            $roff2htm_gendate 'by
 <tt>$Id$</tt></p>
<p>These manual pages are <a href="http://www.freewrt.org/licence">copyrighted</a>
 by their respective writers; their source is available at our <a
 href="http://www.freewrt.org/downloads/">download area</a> and other mirrors.
 The rest is Copyright © 2006-2007 <a href="https://www.freewrt.org/">The
 FreeWRT/OpenADK Project</a>, Germany. <br /><i style="font-size:3pt;">
 This product includes material provided by Thorsten Glaser. The manpage→HTML
 converter is from ekkoBSD and <a href="http://mirbsd.de/">MirBSD</a>.</i></p>
<p style="font-size:x-small;">This manual page’s HTML representation
 is supposed to be <a href="http://validator.w3.org/check/referer">valid
 XHTML/1.1</a>; if not, please send a bug report – diffs preferred.</p>
</body></html>'
}

function do_conversion {
        output_header ${1:-missing-pagename} ${2:-0}
        do_convert ${2:-0}
        output_footer
}

# do_conversion_verbose title section infile outfile
function do_conversion_verbose {
        print -nru2 -- $3 → $4
        do_conversion $1 $2 <$3 >$4
        print -u2
}

# convert_page /path/to/man.cat1 /targetpath
function convert_page {
        typeset fn=$1 page sect tn
        typeset -Uui ino=$(stat $roff2htm_statarg %i $fn 2>/dev/null)
        page=${fn##*/}                  # basename
        page=${page%.0}                 # manual page name
        sect=${fn%/*}                   # dirname
        sect=${sect##*/cat}             # archsection
        sect=${sect%%/*}                # section
        tn=man${sect}/${page}.htm       # target file

        if (( ino )) && [[ -n ${roff2htm_inodecache[ino]} ]]; then
                # source file is linked to a file we know
                print -ru2 -- $tn ← ${roff2htm_inodecache[ino]}
                ln -f $2/${roff2htm_inodecache[ino]} $2/$tn
                # patch in the additional name(s)
                ed -s $2/$tn <<-EOF
                        /<title>/s#</title>#, $page($sect)&#
                        /<h1>/s#</h1>#, <a href="../$tn">$page($sect)</a>&#
                        wq
                EOF
        else
                # store target filename in the inode cache
                roff2htm_inodecache[ino]=$tn
                do_conversion_verbose $page $sect $fn $2/$tn
        fi
}

# output_htaccess >…/.htaccess
function output_htaccess {
        print DirectoryIndex /dev/null
        print "AddType 'text/html; charset=utf-8' htm"
}

# convert_all /path/to/share/man /targetpath
function convert_all {
        typeset tp=${2:-$(pwd)/mbsdman}         # target basepath
        typeset x f

        (find ${1:-/usr/share/man}/cat{[1-9n],3p} -name \*.0 2>&- | sort -f) |&
        for x in 1 2 3 3p 4 5 6 7 8 9 n; do
                mkdir -p $tp/man$x      # one per section
                output_htaccess >$tp/man$x/.htaccess
        done
        while read -p f; do
                convert_page $f $tp     # any subpages
        done
}