X-Git-Url: https://git.mdrn.pl/redakcja.git/blobdiff_plain/4395564bb09e6b7d74cae3421f6342dd546b5619..9bfbdb0f7175d3902ed63bd33e53aadff4f44d88:/apps/catalogue/xml_tools.py diff --git a/apps/catalogue/xml_tools.py b/apps/catalogue/xml_tools.py index 242714b6..75cb2d8c 100644 --- a/apps/catalogue/xml_tools.py +++ b/apps/catalogue/xml_tools.py @@ -14,7 +14,7 @@ class ParseError(BaseException): def _trim(text, trim_begin=True, trim_end=True): - """ + """ Cut off everything before RE_TRIM_BEGIN and after RE_TRIM_END, so that eg. one big XML file can be compiled from many small XML files. """ @@ -26,7 +26,7 @@ def _trim(text, trim_begin=True, trim_end=True): def compile_text(parts): - """ + """ Compiles full text from an iterable of parts, trimming where applicable. """ @@ -103,7 +103,7 @@ def split_xml(text): name_elem = deepcopy(element) for tag in 'extra', 'motyw', 'pa', 'pe', 'pr', 'pt', 'uwaga': for a in name_elem.findall('.//' + tag): - a.text='' + a.text = '' del a[:] name = etree.tostring(name_elem, method='text', encoding='utf-8').strip() @@ -123,15 +123,11 @@ def split_xml(text): while parent[0] is not element: del parent[0] element, parent = parent, parent.getparent() - chunks[:0] = [[name, - unicode(etree.tostring(copied, encoding='utf-8'), 'utf-8') - ]] + chunks[:0] = [[name, unicode(etree.tostring(copied, encoding='utf-8'), 'utf-8')]] parts = src.findall('.//naglowek_rozdzial') - chunks[:0] = [[u'początek', - unicode(etree.tostring(src, encoding='utf-8'), 'utf-8') - ]] + chunks[:0] = [[u'początek', unicode(etree.tostring(src, encoding='utf-8'), 'utf-8')]] for ch in chunks[1:]: ch[1] = add_trim_begin(ch[1])