- def get_statistics(self):
- def count_text(text, counter, in_fn=False):
- if text:
- text = re.sub(r'\s+', ' ', text)
-
- chars = len(text) if text.strip() else 0
- words = len(text.split()) if text.strip() else 0
-
- counter['chars'] += chars
- counter['words'] += words
- if not in_fn:
- counter['chars_with_fn'] += chars
- counter['words_with_fn'] += words
-
- def count(elem, counter, in_fn=False):
- if elem.tag in (RDFNS('RDF'), 'nota_red', 'abstrakt', 'uwaga', 'ekstra'):
- return
- if not in_fn and elem.tag in ('pa', 'pe', 'pr', 'pt', 'motyw'):
- in_fn = True
- count_text(elem.text, counter, in_fn=in_fn)
- for child in elem:
- count(child, counter, in_fn=in_fn)
- count_text(child.tail, counter, in_fn=in_fn)
-
-
- data = {
- "self": Counter(),
- "parts": [],
- "total": {
- }
- }
-
- count(self.edoc.getroot(), data['self'])
- for k, v in data['self'].items():
- data['total'][k] = v
-
- for part in self.parts(pass_part_errors=True):
- if isinstance(part, Exception):
- data['parts'].append((None, {}))
- else:
- data['parts'].append((part, part.get_statistics()))
- for k, v in data['parts'][-1][1]['total'].items():
- data['total'][k] = data['total'].get(k, 0) + v
-
- return data
-