Editorial Workflows

#coding: utf-8
# Markdown to PDF workflow
# by Mason Phillips

## This is a wrapper script for sending documents to Docverter
## for conversion from markdown to PDF using Pandoc. Typically
## Docverter calls are made with cURL; this script uses httplib.
## It is intended for use with Editorial on iOS, so output file
## is uploaded to Dropbox after document conversion.
## For more information, see: http://www.docverter.com/api.html
## Much of the concept and portions of code are from W. Caleb McDaniel's'
## iMDtoPDF.py for Pythonista http://wcm1.web.rice.edu/pandoc-on-ios.html

import httplib
import mimetypes
import re
import StringIO
import editor
import workflow
import os

## Helper functions for posting multipart/form-data request
## using standard libraries. Updated to reflect changes to
## httplib in Python 2.0.
## {{{ http://code.activestate.com/recipes/146306/ (r1)
 
def post_multipart(host, selector, fields, files):
    """
    Post fields and files to an http host as multipart/form-data.
    fields is a sequence of (name, value) elements for regular form fields.
    files is a sequence of (name, filename, value) elements for data to be uploaded as files
    Return the server's response page.
    """
    content_type, body = encode_multipart_formdata(fields, files)
    h = httplib.HTTPConnection(host)
    h.putrequest('POST', selector)
    h.putheader('content-type', content_type)
    h.putheader('content-length', str(len(body)))
    h.endheaders()
    h.send(body)
    response = h.getresponse()
    output = response.read()
    return output
    # return h.file.read()
 
def encode_multipart_formdata(fields, files):
    """
    fields is a sequence of (name, value) elements for regular form fields.
    files is a sequence of (name, filename, value) elements for data to be uploaded as files
    Return (content_type, body) ready for httplib.HTTP instance
    """
    BOUNDARY = '----------ThIs_Is_tHe_bouNdaRY_$'
    CRLF = '\r\n'
    L = []
    for (key, value) in fields:
        L.append('--' + BOUNDARY)
        L.append('Content-Disposition: form-data; name="%s"' % key)
        L.append('')
        L.append(value)
    for (key, filename, value) in files:
        L.append('--' + BOUNDARY)
        L.append('Content-Disposition: form-data; name="%s"; filename="%s"' % (key, filename))
        L.append('Content-Type: %s' % get_content_type(filename))
        L.append('')
        L.append(value)
    L.append('--' + BOUNDARY + '--')
    L.append('')
    body = CRLF.join(L)
    content_type = 'multipart/form-data; boundary=%s' % BOUNDARY
    return content_type, body
 
def get_content_type(filename):
    return mimetypes.guess_type(filename)[0] or 'application/octet-stream'
 
## end of http://code.activestate.com/recipes/146306/ }}}
 
## Put editor contents in a file to send to Docverter.
text = editor.get_text()

#Check if the document starts with mmd metadata:
if re.match('^\\w+:', text):
	#Find the first empty line:
	empty_line_match = re.search('^\\s*$', text, re.MULTILINE)
	if empty_line_match:
		#Remove the metadata block from the text:
		input_text = text[empty_line_match.end(0):]
else: 
	input_text = text

f = open("docverterin.txt", "w").write(input_text.encode('utf-8'))

## Use CSS to style your output.
css = """
body{color:#222;font:normal normal 400 100%/1.5em georgia,serif;width:40em;margin:3em auto;}a:link{color:#36C;}a:visited{color:#248;}blockquote,ol,p,ul{display:block;margin:0 0 1.5em;}blockquote{border-left:solid .1em #E4E4E4;color:#515151;padding:0 1.5em 0 1.4em;}code{font:normal normal 87.5%/1.71428571em monospace,sans-serif;}img{display:block;margin:1.5em auto;}pre{display:block;font:normal normal 87.5%/1.71428571em monospace,sans-serif;margin:1.71428571em;}h1{font-size:225%;line-height:1.3334em;margin:0 0 .1666em;}h2{font-size:175%;line-height:1.28571429em;margin:0 0 .35714286em;}h3{font-size:137.5%;line-height:1.3636em;margin:0 0 .5em;}h4,h5,h6{font-size:112.5%;line-height:1.3334em;margin:0 0 .7778em;}ol,ul{list-style-position:outside;padding:0;}ol ol,ol ul,ul ol,ul ul{margin:0 0 .75em 2em;}table{border-collapse:collapse;width:100%;margin:1.5em 0;}td,th{border:solid .1em #000;font-family:sans-serif;font-size:87.5%;line-height:1.71428571em;text-align:center;}.footnote{font-size:.8em;vertical-align:super;}.footnotes ol{font-weight:700;}h1,h2,h3,h4,h5,h6,.footnotes ol li p{font-weight:400;}.proclaim{color: #335E0F;}.explain{color: #3A81AA;}.illustration{color:#E0A51B}@media only screen and (max-device-width: 480px) {body{width:90%;}}
"""

# Use CSS3 Paged Media Module to number pages of PDF, set margins.
page_info = "@page {margin: 1in; @bottom-center{content: counter(page)}}"
c = open("docverter.css", "w").write(css + page_info)

## Set Docverter options and define fields using lists.
## Other options available at http://www.docverter.com/api.html#toc_2
fields = [("from", "markdown"), ("to", "pdf"), ("css", "docverter.css")]
files = [("input_files[]", "docverterin.txt", open("docverterin.txt", "r").read()), ("other_files[]", "docverter.css", open("docverter.css","r").read())]
 
## Post to Docverter using post_multipart()
output = post_multipart("c.docverter.com", "/convert", fields, files)
 
## Write output to a PDF file. 
outfile = workflow.get_variable('newTitle')+'.pdf'
buffer = StringIO.StringIO(output)
data = buffer.getvalue()
editor.set_file_contents(outfile, data, 'dropbox')

## Send the filename to the workflow.
workflow.set_output(outfile)