__filename__ = "markdown.py" __author__ = "Bob Mottram" __license__ = "AGPL3+" __version__ = "1.5.0" __maintainer__ = "Bob Mottram" __email__ = "bob@libreserver.org" __status__ = "Production" __module_group__ = "Web Interface" def _markdown_get_sections(markdown: str) -> []: """Returns a list of sections for markdown """ if '' not in markdown: return [markdown] lines = markdown.split('\n') sections = [] section_text = '' section_active = False ctr = 0 for line in lines: if ctr > 0: section_text += '\n' if not section_active: if '' in line: section_active = True sections.append(section_text) section_text = '' else: if '' in line: section_active = False sections.append(section_text) section_text = '' section_text += line ctr += 1 if section_text.strip(): sections.append(section_text) return sections def _markdown_emphasis_html(markdown: str) -> str: """Add italics and bold html markup to the given markdown """ replacements = { ' **': ' ', '** ': ' ', '**.': '.', '**:': ':', '**;': ';', '?**': '?', '\n**': '\n', '**,': ',', '**\n': '\n', '(**': '()', '**)': ')', '>**': '>', '**<': '<', '>*': '>', '*<': '<', ' *': ' ', '* ': ' ', '?*': '?', '\n*': '\n', '*.': '.', '*:': ':', '*;': ';', '(*': '()', '*)': ')', '*,': ',', '*\n': '\n', '(_': '(', '_)': ')', ' _': ' ', '_ ': ' ', '_.': '.', '_:': ':', '_;': ';', '_,': ',', '_\n': '\n', ' `': ' ', '`.': '.', '`:': ':', "`'": "'", "(`": "(", "`)": ")", '`;': ';', '`,': ',', '`\n': '\n', '` ': ' ' } sections = _markdown_get_sections(markdown) markdown = '' for section_text in sections: if '' in section_text: markdown += section_text continue for md_str, html in replacements.items(): section_text = section_text.replace(md_str, html) if section_text.startswith('**'): section_text = section_text[2:] + '' elif section_text.startswith('*'): section_text = section_text[1:] + '' elif section_text.startswith('_'): section_text = section_text[1:] + '' if section_text.endswith('**'): section_text = section_text[:len(section_text) - 2] + '' elif section_text.endswith('*'): section_text = section_text[:len(section_text) - 1] + '' elif section_text.endswith('_'): section_text = section_text[:len(section_text) - 1] + '' if section_text.strip(): markdown += section_text return markdown def _markdown_replace_quotes(markdown: str) -> str: """Replaces > quotes with html blockquote """ if '> ' not in markdown: return markdown lines = markdown.split('\n') result = '' prev_quote_line = None code_section = False for line in lines: # avoid code sections if not code_section: if '' in line: code_section = True else: if '' in line: code_section = False if code_section: result += line + '\n' continue if '> ' not in line: result += line + '\n' prev_quote_line = None continue line_str = line.strip() if not line_str.startswith('> '): result += line + '\n' prev_quote_line = None continue line_str = line_str.replace('> ', '', 1).strip() if prev_quote_line: new_prev_line = prev_quote_line.replace('\n', '') result = result.replace(prev_quote_line, new_prev_line) + ' ' line_str += '\n' else: line_str = '
' + line_str + '
\n' result += line_str prev_quote_line = line_str if '\n' in result: result = result.replace('\n', '') if result.endswith('\n') and \ not markdown.endswith('\n'): result = result[:len(result) - 1] return result def _markdown_replace_links(markdown: str) -> str: """Replaces markdown links with html Optionally replace image links """ sections = _markdown_get_sections(markdown) result = '' for section_text in sections: if '' in section_text or \ '](' not in section_text: result += section_text continue sections_links = section_text.split('](') ctr = 0 for link_section in sections_links: if ctr == 0: ctr += 1 continue if not ('[' in sections_links[ctr - 1] and ')' in link_section): ctr += 1 continue link_text = sections_links[ctr - 1].split('[')[-1] link_url = link_section.split(')')[0] replace_str = '[' + link_text + '](' + link_url + ')' link_text = link_text.replace('`', '') if '!' + replace_str in section_text: html_link = \ '' + link_text + '' section_text = \ section_text.replace('!' + replace_str, html_link) if replace_str in section_text: if not link_url.startswith('#'): # external link html_link = \ '' + \ link_text + '' else: # bookmark html_link = \ '' + link_text + '' section_text = \ section_text.replace(replace_str, html_link) ctr += 1 result += section_text return result def _markdown_replace_bullet_points(markdown: str) -> str: """Replaces bullet points """ lines = markdown.split('\n') bullet_style = ('* ', ' * ', '- ', ' - ') bullet_matched = '' start_line = -1 line_ctr = 0 changed = False code_section = False for line in lines: if not line.strip(): # skip blank lines line_ctr += 1 continue # skip over code sections if not code_section: if '' in line: code_section = True else: if '' in line: code_section = False if code_section: line_ctr += 1 continue if not bullet_matched: for test_str in bullet_style: if line.startswith(test_str): bullet_matched = test_str start_line = line_ctr break else: if not line.startswith(bullet_matched): for index in range(start_line, line_ctr): line_text = lines[index].replace(bullet_matched, '', 1) if index == start_line: lines[index] = \ '
    \n
  • ' + line_text + '
    • ' elif index == line_ctr - 1: lines[index] = '
  • ' + line_text + '
    • \n
' else: lines[index] = '
  • ' + line_text + '
    • ' changed = True start_line = -1 bullet_matched = '' line_ctr += 1 if not changed: return markdown markdown = '' for line in lines: markdown += line + '\n' return markdown def _markdown_replace_code(markdown: str) -> str: """Replaces code sections within markdown """ lines = markdown.split('\n') start_line = -1 line_ctr = 0 changed = False section_active = False url_encode = False html_escape_table = { "&": "&", '"': """, "'": "'", ">": ">", "<": "<" } for line in lines: if not line.strip(): # skip blank lines line_ctr += 1 continue if line.startswith('```'): if not section_active: if 'html' in line or 'xml' in line or 'rdf' in line: url_encode = True start_line = line_ctr section_active = True else: lines[start_line] = '' lines[line_ctr] = '' if url_encode: lines[start_line] = '
    \n'
                    lines[line_ctr] = '\n
    ' for line_num in range(start_line + 1, line_ctr): lines[line_num] = \ "".join(html_escape_table.get(char, char) for char in lines[line_num]) section_active = False changed = True url_encode = False line_ctr += 1 if not changed: return markdown markdown = '' for line in lines: markdown += line + '\n' return markdown def markdown_example_numbers(markdown: str) -> str: """Ensures that example numbers in the ActivityPub specification document are sequential """ lines = markdown.split('\n') example_number = 1 line_ctr = 0 for line in lines: if not line.strip(): # skip blank lines line_ctr += 1 continue if line.startswith('##') and '## Example ' in line: header_str = line.split(' Example ')[0] lines[line_ctr] = header_str + ' Example ' + str(example_number) example_number += 1 line_ctr += 1 markdown = '' for line in lines: markdown += line + '\n' return markdown def markdown_to_html(markdown: str) -> str: """Converts markdown formatted text to html """ markdown = _markdown_replace_code(markdown) markdown = _markdown_replace_bullet_points(markdown) markdown = _markdown_replace_quotes(markdown) markdown = _markdown_emphasis_html(markdown) markdown = _markdown_replace_links(markdown) # replace headers lines_list = markdown.split('\n') html_str = '' ctr = 0 code_section = False titles = { "h6": '######', "h5": '#####', "h4": '####', "h3": '###', "h2": '##', "h1": '#' } for line in lines_list: if ctr > 0: if not code_section: html_str += '
    \n' else: html_str += '\n' # avoid code sections if not code_section: if '' in line: code_section = True else: if '' in line: code_section = False if code_section: html_str += line ctr += 1 continue for hsh, hashes in titles.items(): if line.startswith(hashes): bookmark_str = line.split(' ', 1)[1].lower().replace(' ', '-') line = line.replace(hashes, '').strip() line = '<' + hsh + ' id="' + bookmark_str + '">' + \ line + '\n' ctr = -1 break html_str += line ctr += 1 replacements = ( ('
    ', ''), ('
    ', '    '), ('

      ', '
        '), ('
        ', '') ) for pair in replacements: html_str = html_str.replace(pair[0], pair[1]) return html_str