updated markdown parsing and added scene breaks

novel_compiler/novel_compiler.py

@@ -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):
+class ParseTarget:
-    # Correct xml tags
+    TAGS = {'em':'italic', 'strong':'bold'}
-    pre = '<w:r><w:t xml:space="preserve">'
+    def __init__(self):
-    post = '</w:t></w:r>'
+        self.cur = {key: False for key in self.TAGS}
-    it_pre = '<w:r><w:rPr><w:i/></w:rPr><w:t xml:space="preserve">'
+        self.par = RichText()
-    bf_pre = '<w:r><w:rPr><w:b/></w:rPr><w:t xml:space="preserve">'
+    def start(self, tag, attrib):
-    bfit_pre = '<w:r><w:rPr><w:b/><w:i/></w:rPr><w:t xml:space="preserve">'
+        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)
+    target = ParseTarget()
-    html = html.replace('</p>', post)
+    parser = etree.XMLParser(target=target)
-    html = html.replace('<strong><em>', post+bfit_pre)
+    par = etree.XML(html, parser)
-    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)
     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()

setup.py

@@ -20,7 +20,7 @@ setup(
     ],
     packages=find_packages(),
     entry_points={"console_scripts": ["novel-compiler = novel_compiler.novel_compiler:main",]},
-    install_requires=('docxtpl','markdown','novel_stats','MarkdownPP'),
+    install_requires=('docxtpl','markdown','novel_stats','MarkdownPP', 'lxml'),
     include_package_data=True,
     python_requires='>3.7.0',
 )