Created
July 9, 2012 23:34
-
-
Save Gen2ly/3079785 to your computer and use it in GitHub Desktop.
Convert Markdown to Wordpress blogging format
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
#!/bin/bash | |
# Convert Markdown to Wordpress blogging format | |
# Required program(s) | |
req_progs=(ascii2uni pandoc) | |
for p in ${req_progs[@]}; do | |
hash "$p" 2>&- || \ | |
{ echo >&2 " Required program \"$p\" not installed."; exit 1; } | |
done | |
# Display usage if no parameters given | |
if [[ -z "$@" ]]; then | |
echo " ${0##*/} <file.md> - convert Markdown to Wordpress blogging format" | |
exit | |
fi | |
# Check if selection exists | |
for f in "$@"; do | |
[ ! -f "$f" ] && echo " Selection \""$f"\" does not exist." && exit | |
done | |
# Convert | |
for md in "$@"; do | |
file_html="${md%.*}".htm | |
file_wdpr="${md%.*}".wdp | |
## Convert to HTML | |
pandoc "$md" -o /tmp/"$file_html" && echo " Converted to HTML." | |
## Convert HTML entities to UTF8 | |
ascii2uni -a Y /tmp/"$file_html" -q > "$file_wdpr" && \ | |
echo " Converted HTML entities to UTF8." | |
# Clean up code | |
code_clnp () { | |
## Code blocks | |
# Remove four space after <code> and during code blocks (fix for Gedit | |
# having to use eight spaces for syntax recognition of code lines) | |
sed -i 's/<code> /<code>/g' "$file_wdpr" | |
sed -i 's/^ //g' "$file_wdpr" | |
# Only <pre> tags necessary (i.e. not <pre><code>) | |
sed -i 's|\(<pre*>\)<code>|\1|g' "$file_wdpr" | |
sed -i 's|</code></pre>|</pre>|g' "$file_wdpr" | |
# Use custom pre tag | |
#sed -i 's|<pre*>|<pre style="overflow:auto;width=auto;border:solid #A4DEA4;border-width:.1em .1em .1em .6em;padding:.2em .4em .2em .6em;background-color:#F0FAF0;font-size:1em;white-space:pre;">|g' "$file_wdpr" | |
## Newlines | |
# Newline after pre | |
#sed -i 's|</pre>|</pre>\n|g' "$file_wdpr" | |
# Ensure blankline after code blocks | |
sed -i -e ':a;N;$!ba;s|</pre>*\n\(.\{1\}\)|</pre>\n\n\1|g' "$file_wdpr" | |
# Newline after headers | |
sed -i 's/\(^<h[1-5].*\)/\1\n/g' "$file_wdpr" | |
# Remove paragraph tags, newline after | |
sed -i 's/<p>//g' "$file_wdpr" | |
sed -i 's|</p>|\n|g' "$file_wdpr" | |
# Remove breaks | |
sed -i 's/<br>//g' "$file_wdpr" | |
# Ensure blankline after lists | |
sed -i -e ':a;N;$!ba;s|</ol>*\n\(.\{1\}\)|</ol>\n\n\1|g' "$file_wdpr" | |
sed -i -e ':a;N;$!ba;s|</ul>*\n\(.\{1\}\)|</ul>\n\n\1|g' "$file_wdpr" | |
# Ensure blankline after tables | |
sed -i -e ':a;N;$!ba;s|</table>*\n\(.\{1\}\)|</table>\n\n\1|g' "$file_wdpr" | |
## Cleanup | |
# Remove vim settings | |
sed -i '/^<!-- vim:/d' "$file_wdpr" | |
# Delete first line if blank | |
sed -i '1{/^$/d}' "$file_wdpr" | |
# Remove trailing blank lines | |
while [ "$(tail -n 1 "$file_wdpr")" == "" ]; do | |
sed -i '$d' "$file_wdpr" | |
done | |
# Delete final newline | |
perl -i -e 'local $/; $_ = <>; s/\n$//; print' "$file_wdpr" | |
} | |
code_clnp && echo " Cleaned up formating." | |
done |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment