#! /usr/bin/perl -w
# Copyright (C) 2005, 2007 Alex Schroeder
#
# Portions copyright (c) 2013, Peter Davis
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see .
sub ParseData {
my $data = shift;
my %result;
while ($data =~ /(\S+?): (.*?)(?=\n[^ \t]|\Z)/sg) {
my ($key, $value) = ($1, $2);
$value =~ s/\n\t/\n/g;
$result{$key} = $value;
}
return %result;
}
sub FixMarkUp {
my $data = shift;
my $orgout = "#+STARTUP: showeverything logdone\n#+options: num:nil\n\n";
my $csvMode = 0;
foreach (split /\n/, $data) {
if (length($_)) {
s/\r//g;
# csv tables
if ($_ =~ //) {
$csvMode = 1;
s//#+ATTR_HTML: :border 2 :rules all :frame border/g;
} elsif ($_ =~ /^\s*$/) {
$csvMode = 0;
} elsif ($csvMode) {
s/^/|/g;
s/,/|/g;
s/$/|/g;
}
# hyperlinks
s/\[\[([^]]*)\]\]/[[file:$1.org][$1]]/g;
# strike through
s/<\/?s>/+/g;
# verse
s/:::/#+BEGIN_VERSE/g;
# bold and italic
s/'''/*/g;
s/''/\//g;
# bullet lists
s/^\*\*\*\*/ */g;
s/^\*\*\*/ */g;
s/^\*\*/ */g;
s/^\*/ */g;
# headers
s/^\=\=\=\=/****/g;
s/^\=\=\=/***/g;
s/^\=\=/**/g;
s/^\=/*/g;
# s/ \=?$//g;
s/ \=\=\=\=$//g;
s/ \=\=\=$//g;
s/ \=\=$//g;
s/ \=$//g;
s/^# / 1. /g;
} else {
$csvMode = 0;
}
$orgout = $orgout . $_ . "\n";
}
return $orgout;
}
sub main {
my ($regexp, $PageDir, $OrgDir) = @_;
# include dotfiles!
local $/ = undef; # Read complete files
foreach my $file (glob("$PageDir/*/*.pg $PageDir/*/.*.pg")) {
next unless $file =~ m|/.*/(.+)\.pg$|;
my $page = $1;
next if $regexp && $page !~ m|$regexp|o;
$page = $page . ".org";
mkdir($OrgDir) or die "Cannot create $OrgDir directory: $!"
unless -d $OrgDir;
open(F, $file) or die "Cannot read $page file: $!";
my $data = ;
close(F);
my $ts = (stat("$OrgDir/$page"))[9];
my %result1 = ParseData($data);
my $result2 = FixMarkUp($result1{text});
if ($ts && $ts == $result1{ts}) {
print "skipping $page because it is up to date\n" if $verbose;
} else {
print "writing $page because $ts != $result{ts}\n" if $verbose;
open(F,"> $OrgDir/$page") or die "Cannot write $page org file: $!";
# print F $result1{text};
print F $result2;
close(F);
utime $result1{ts}, $result1{ts}, "$OrgDir/$page"; # touch file
}
}
}
use Getopt::Long;
my $regexp = undef;
my $page = 'page';
my $dir = 'org';
GetOptions ("regexp=s" => \$regexp,
"page=s" => \$page,
"dir=s" => \$dir,
"help" => \$help);
if ($help) {
print qq{
Usage: $0 [--regexp REGEXP] [--page DIR] [--dir DIR]
Writes the org wiki text into plain text files.
--regexp selects a subsets of pages whose names match the regular
expression. Note that spaces have been translated to underscores.
--page designates the page directory. By default this is 'page' in the
current directory. If you run this script in your data directory,
the default should be fine.
--dir designates an output directory. By default this is 'org' in the
current directory.
Example: $0 --regexp '\\.el\$' --dir elisp
}
} else {
main ($regexp, $page, $dir);
}