def read_source()

in pelican/plugins/gfm.py [0:0]

• 32 lines of code
• 10 McCabe index (conditional complexity)

    def read_source(self, source_path):
        "Read metadata and content from the source."

        # Prepare the "slug", which is the target file name. It will be the
        # same as the source file, minus the leading ".../content/(articles|pages)"
        # and with the extension removed (Pelican will add .html)
        relpath = os.path.relpath(source_path, self.settings['PATH'])
        parts = relpath.split(os.sep)
        parts[-1] = os.path.splitext(parts[-1])[0]  # split off ext, keep base
        slug = os.sep.join(parts[1:])

        metadata = {
            'slug': slug,
        }
        # Fetch the source content, with a few appropriate tweaks
        with pelican.utils.pelican_open(source_path) as text:

            # Extract the metadata from the header of the text
            lines = text.splitlines()
            i = 0 # See https://github.com/apache/infrastructure-pelican/issues/70
            for i in range(len(lines)):
                line = lines[i]
                match = GFMReader.RE_METADATA.match(line)
                if match:
                    name = match.group(1).strip().lower()
                    if name != 'slug':
                        value = match.group(2).strip()
                        if name == 'date':
                            value = pelican.utils.get_date(value)
                    metadata[name] = value
                    #if name != 'title':
                    #  print 'META:', name, value
                elif not line.strip():
                    # blank line
                    continue
                else:
                    # reached actual content
                    break

            # Redo the slug for articles.
            # depending on pelicanconf.py this will change the output filename
            if parts[0] == 'articles' and 'title' in metadata:
                metadata['slug'] = pelican.utils.slugify(
                    metadata['title'],
                    self.settings.get('SLUG_SUBSTITUTIONS', ()))

            # Reassemble content, minus the metadata
            text = '\n'.join(lines[i:])

            return text, metadata