Created
May 3, 2012 14:09
-
-
Save orenhe/2585891 to your computer and use it in GitHub Desktop.
mediawiki2rst
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl | |
# | |
# mediawiki2rst - converts mediawiki markup to Restructured Text format | |
# | |
# python-docutils provide rst2<whatever> tools, thus it can be one hop towards converting to html, odt, latex etc | |
# | |
# License: BSD-style | |
# | |
# Author: Oren Held | |
# | |
# Note: this is a very incomplete implementation | |
# | |
while (<>) { | |
chomp; | |
# Sections | |
if (/====\s*([^=]+)\s*====/) { | |
$len=length($1); | |
print "\n".$1."\n"; print "-"x$len."\n\n"; | |
next; | |
} | |
elsif (/===\s*([^=]+)\s*===/) { | |
$len=length($1); | |
print "\n".$1."\n"; print "="x$len."\n\n"; | |
next; | |
} | |
elsif (/==\s*([^=]+)\s*==/) { | |
$len=length($1); | |
print "\n"."-"x $len."\n"; print $1."\n"; print "-"x$len."\n\n"; | |
next; | |
}; | |
# Bullets and enumerations | |
if (/^*/ || /^#/) { | |
s/^#/#./; | |
s/^\*\*\*/ \*/; | |
s/^\*\*/ \*/; | |
print $_; | |
print "\n\n"; | |
next; | |
}; | |
# Emphasis - TODO - this part needs to be run after all output, because some lines won't reach this stage due to | |
# 'next' statements earlier | |
s/\'\'\'([^\']+)\'\'\'/**$1**/g; | |
s/\'\'([^\']+)\'\'/*$1*/g; | |
print $_; | |
print "\n"; | |
}; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment