Created
April 18, 2011 01:56
-
-
Save morgant/924688 to your computer and use it in GitHub Desktop.
Convert MIME format wiki export (developed for PhpWiki exports) to Markdown
This file contains hidden or 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
#!/bin/bash | |
# | |
# mime2mdwn - Convert MIME format wiki export (developed for PhpWiki exports) to Markdown | |
# | |
# globals | |
debug=false | |
# the actual heavy lifting | |
function convert_mime_to_markdown() { | |
local in_header=true | |
local boundary='' | |
local version=0 | |
local data='' | |
local data_version=0 | |
while IFS=$IFS$'\r' read -r line; do | |
# process header lines | |
if $in_header; then | |
# in MIME formatting, a blank line signifies the end of the header | |
if [ "$line" = "" ]; then | |
if $debug; then printf "DEBUG: EOH\n"; fi | |
in_header=false | |
else | |
if $debug; then printf "DEBUG: HEADER: %s\n" "$line"; fi | |
# does the line contain a version number? | |
if [[ "$line" =~ version=([[:digit:]]+) ]]; then | |
version="${BASH_REMATCH[1]}" | |
if $debug; then printf "DEBUG: VERSION %s:\n" "$version"; fi | |
if (( $version >= $data_version )); then | |
data='' | |
data_version=$version | |
fi | |
fi | |
# does the line contain a boundary? | |
if [[ "$line" =~ boundary=\"(.*)\" ]]; then | |
boundary="^--${BASH_REMATCH[1]}(--)?" | |
if $debug; then printf "DEBUG: boundary = %s\n" "$boundary"; fi | |
fi | |
fi | |
else | |
# is this the beginning of another "part"? | |
if [[ "$line" =~ $boundary ]]; then | |
in_header=true | |
# otherwise, this is "part" content | |
else | |
if $debug; then printf "%s\n" "DEBUG: $line"; fi | |
if (( $version == $data_version )); then | |
data="${data}${line}"$'\n' | |
fi | |
fi | |
fi | |
done < "$1" | |
#printf "DATA (VERSION %s; pre-markup conversion):\n%s" "$data_version" "$data" | |
# convert CamelCase (starting w/capital; e.g. "NewtonNewbieGuide") to wiki links (e.g. "[[NewtonNewbieGuide]]") | |
data=$(echo -n "$data" | perl -pe "s/(^|\b|_)((?<![\[|])[A-Z][a-z]+[A-Z][A-Za-z]+(?![\]|]))($|\b|_)/\1\[\[\2\]\]\3/g") | |
# convert non-URI links in square brackets (e.g. "[NewtonConnectivityCD]") to wiki links (e.g. "[[NewtonConnectivityCD]]" | |
#data=$(echo -n "$data" | sed -E "s/([^[])\[([^\s]+)\]([^]])/\1\[\[\2\]\]\3/g") | |
data=$(echo -n "$data" | perl -pe "s/((?<!\[)\[[A-Za-z0-9]+\](?!\]))/\[\1\]/g") | |
# convert non-URI, named links in square brackets (e.g. "[BluetoothConnection|UsingBluetoothIndex]") to Markdown link format (e.g. "[BluetoothConnection](/UsingBluetoothIndex)") | |
data=$(echo -n "$data" | perl -pe "s/(?<!\[)\[(.+)\s?\|\s?([A-Za-z0-9]+)\](?!\])/[\1](\2)/g") | |
# convert URI, named links in square brackets (e.g. "[Newtontalk.net|http://www.newtontalk.net/]") to Markdown link format (e.g. "[Newtontalk.net](http://www.newtontalk.net/)") | |
data=$(echo -n "$data" | perl -pe "s/(?<!\[)\[(.+)\s?\|\s?([A-Za-z]+:(\/\/)?.+)\](?!\])/[\1](\2)/g") | |
# convert URI-only links in square brackets (e.g. "[http://tools.unna.org/glossary/]") to angle bracket format (e.g. "<http://tools.unna.org/glossary/>") | |
data=$(echo -n "$data" | perl -pe "s/(?<!\[)\[([A-Z-a-z]+:(\/\/)?.+)\](?!\])/<\1>/g") | |
# convert triple prime bold (e.g. "'''bold'''") to Markdown format (e.g. "__bold__") | |
data=$(echo -n "$data" | perl -pe "s/(?<!')'''(.+)'''(?!')/__\1__/g") | |
# convert double prime emphasis (e.g. "''emphasis''") to Markdown format (e.g. "_emphasis_") | |
data=$(echo -n "$data" | perl -pe "s/(?<!')''(.+)''(?!')/_\1_/g") | |
# convert headings (e.g. "!!Heading") to Markdown atk-style format (e.g. "## Heading") | |
data=$(echo -n "$data" | perl -pe "s/^!{1}([^!]+)$/# \1/g") | |
data=$(echo -n "$data" | perl -pe "s/^!{2}([^!]+)$/## \1/g") | |
data=$(echo -n "$data" | perl -pe "s/^!{3}([^!]+)$/### \1/g") | |
data=$(echo -n "$data" | perl -pe "s/^!{4}([^!]+)$/#### \1/g") | |
data=$(echo -n "$data" | perl -pe "s/^!{5}([^!]+)$/##### \1/g") | |
data=$(echo -n "$data" | perl -pe "s/^!{6}([^!]+)$/###### \1/g") | |
# printf "DATA (VERSION %s; post-markup conversion):\n%s" "$data_version" "$data" | |
# write the data back out to the file | |
echo -n "$data" > "$1" | |
} | |
# batch process a directory of files? | |
if [ -d "$1" ]; then | |
for file in $1/*; do | |
if [ ! -d "$file" ]; then | |
convert_mime_to_markdown "$file" | |
fi | |
done | |
# or just a single file? | |
elif [ -e "$1" ]; then | |
convert_mime_to_markdown "$1" | |
# if no file/directory, throw an error | |
else | |
printf "ERROR! %s not found!\n" "$1" | |
fi |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment