|
|
|
@ -5,6 +5,7 @@ from novel_stats.novel_stats import count_words
|
|
|
|
|
import tempfile
|
|
|
|
|
import MarkdownPP
|
|
|
|
|
import json
|
|
|
|
|
from lxml import etree
|
|
|
|
|
|
|
|
|
|
TITLE_MARKER = '# '
|
|
|
|
|
AUTHOR_MARKER = '### '
|
|
|
|
@ -18,42 +19,41 @@ class Chapter:
|
|
|
|
|
self.heading = heading
|
|
|
|
|
self.paragraphs = []
|
|
|
|
|
|
|
|
|
|
def md_re_parser(md_paragraph):
|
|
|
|
|
# Correct xml tags
|
|
|
|
|
pre = '<w:r><w:t xml:space="preserve">'
|
|
|
|
|
post = '</w:t></w:r>'
|
|
|
|
|
it_pre = '<w:r><w:rPr><w:i/></w:rPr><w:t xml:space="preserve">'
|
|
|
|
|
bf_pre = '<w:r><w:rPr><w:b/></w:rPr><w:t xml:space="preserve">'
|
|
|
|
|
bfit_pre = '<w:r><w:rPr><w:b/><w:i/></w:rPr><w:t xml:space="preserve">'
|
|
|
|
|
class ParseTarget:
|
|
|
|
|
TAGS = {'em':'italic', 'strong':'bold'}
|
|
|
|
|
def __init__(self):
|
|
|
|
|
self.cur = {key: False for key in self.TAGS}
|
|
|
|
|
self.par = RichText()
|
|
|
|
|
def start(self, tag, attrib):
|
|
|
|
|
if tag in self.TAGS:
|
|
|
|
|
self.cur[tag] = True
|
|
|
|
|
def end(self, tag):
|
|
|
|
|
if tag in self.TAGS:
|
|
|
|
|
self.cur[tag] = False
|
|
|
|
|
def data(self, data):
|
|
|
|
|
tags = {self.TAGS[tag]:self.cur[tag] for tag in self.TAGS}
|
|
|
|
|
self.par.add(data, **tags)
|
|
|
|
|
def close(self):
|
|
|
|
|
return self.par
|
|
|
|
|
|
|
|
|
|
# Tag replacement
|
|
|
|
|
def md_re_parser(md_paragraph, break_mark):
|
|
|
|
|
if md_paragraph == break_mark:
|
|
|
|
|
return None
|
|
|
|
|
html = markdown.markdown(md_paragraph)
|
|
|
|
|
html = html.replace('<p>', pre)
|
|
|
|
|
html = html.replace('</p>', post)
|
|
|
|
|
html = html.replace('<strong><em>', post+bfit_pre)
|
|
|
|
|
html = html.replace('</strong></em>', post+pre)
|
|
|
|
|
html = html.replace('<em>', post+it_pre)
|
|
|
|
|
html = html.replace('</em>', post+pre)
|
|
|
|
|
html = html.replace('<strong>', post+bf_pre)
|
|
|
|
|
html = html.replace('</strong>', post+pre)
|
|
|
|
|
|
|
|
|
|
# xml cleanup
|
|
|
|
|
while pre+post in html:
|
|
|
|
|
html = html.replace(pre+post,'')
|
|
|
|
|
|
|
|
|
|
# convert to a rich text paragraph
|
|
|
|
|
par = RichText()
|
|
|
|
|
par.xml = html
|
|
|
|
|
if len(html) == 0:
|
|
|
|
|
print(md_paragraph)
|
|
|
|
|
target = ParseTarget()
|
|
|
|
|
parser = etree.XMLParser(target=target)
|
|
|
|
|
par = etree.XML(html, parser)
|
|
|
|
|
return par
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def novel_parser(source_file, context = None):
|
|
|
|
|
if not context:
|
|
|
|
|
context = {'author_address': 'Street\nTown, State ZIP\nCountry',
|
|
|
|
|
'author_email': 'name@email.com',
|
|
|
|
|
'author_phone': 'PhoneNumber(s)',
|
|
|
|
|
'author_website': 'https://www.author.com'}
|
|
|
|
|
'author_website': 'https://www.author.com',
|
|
|
|
|
'md_break_mark': '-*-',
|
|
|
|
|
'docx_break_mark': '#'}
|
|
|
|
|
context['chapters'] = []
|
|
|
|
|
|
|
|
|
|
wc = 0
|
|
|
|
@ -79,7 +79,7 @@ def novel_parser(source_file, context = None):
|
|
|
|
|
stripped = line.strip()
|
|
|
|
|
if stripped:
|
|
|
|
|
wc += count_words(stripped)
|
|
|
|
|
chapter.paragraphs.append(md_re_parser(stripped))
|
|
|
|
|
chapter.paragraphs.append(md_re_parser(stripped, context['md_break_mark']))
|
|
|
|
|
context['chapters'].append(chapter)
|
|
|
|
|
|
|
|
|
|
source_file.close()
|
|
|
|
|