def pre_cleanup(self):
manipulate = TeiManipulate(self.gv)
tree = manipulate.load_dom_tree()
# make sure that head elements are not encapsulated within any elements that will stop them from being
# correctly transformed by the XSL
allowed = ['{http://www.tei-c.org/ns/1.0}div', '{http://www.tei-c.org/ns/1.0}body']
head_elements = tree.xpath('//tei:div[tei:head]', namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
count = 0
for element in head_elements:
current = element
while current is not None:
current = current.getparent()
if current is not None:
if current.tag and current.tag not in allowed:
current.tag = 'REMOVE'
count += 1
elif current.tag and current.tag in allowed:
break
else:
break
if count > 0:
etree.strip_tags(tree, 'REMOVE')
manipulate.save_tree(tree)
self.debug.print_debug(self, u'Extracted {0} headings from inside invalid elements'.format(count))
# split any p tags with sub-tags hi rend="Indent" into new elements
biblio_elements = tree.xpath('//tei:p'
'[tei:hi[contains(@rend, "Indent") or contains(@rend, "Default Style") or '
'contains(@rend, "Text Body")]]',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
for parent in biblio_elements:
add_position = parent
for element in parent.xpath('tei:hi[contains(@rend, "Indent") or contains(@rend, "Default Style") or '
'contains(@rend, "Text Body")]',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'}):
new_p = etree.Element('p')
if 'rend' in parent.attrib:
new_p.attrib['rend'] = parent.attrib['rend']
add_position.addnext(new_p)
new_p.append(element)
add_position = new_p
manipulate.save_tree(tree)
self.debug.print_debug(self, u'Separated out p {0}'.format(manipulate.get_stripped_text(parent)))
def pre_clean(self):
self.extract_metadata_fields()
manipulate = TeiManipulate(self.gv)
tree = manipulate.load_dom_tree()
# get all elements in the body
section = tree.xpath('//tei:body//*', namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
items_to_match = ['{http://www.tei-c.org/ns/1.0}head', '{http://www.tei-c.org/ns/1.0}p',
'{http://www.tei-c.org/ns/1.0}cit']
count = 0
matched_authors = []
for item in section:
if count > 2:
break
if item.tag in items_to_match:
count += 1
text = self.get_stripped_text(item)
processed = False
for author in self.authors:
if not author in matched_authors:
has_all = True
for component in author:
if not component in text:
has_all = False
break
if has_all:
# found a metadata line
matched_authors.append(author)
count -= 1
item.getparent().remove(item)
self.debug.print_debug(self, u'Removed line "{0}" '
u'because it appears to be author metadata'.format(text))
processed = True
break
if not processed:
for metadata in self.metadata:
if metadata in text:
# found a metadata line
count -= 1
item.getparent().remove(item)
self.debug.print_debug(self, u'Removed line "{0}" '
u'because it appears to be duplicated metadata'.format(text))
manipulate.save_tree(tree)
def pre_cleanup(self):
manipulate = TeiManipulate(self.gv)
tree = manipulate.load_dom_tree()
# make sure that head elements are not encapsulated within any elements that will stop them from being
# correctly transformed by the XSL
allowed = [
'{http://www.tei-c.org/ns/1.0}div',
'{http://www.tei-c.org/ns/1.0}body'
]
head_elements = tree.xpath(
'//tei:div[tei:head]',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
count = 0
for element in head_elements:
current = element
while current is not None:
current = current.getparent()
if current is not None:
if current.tag and current.tag not in allowed:
current.tag = 'REMOVE'
count += 1
elif current.tag and current.tag in allowed:
break
else:
break
if count > 0:
etree.strip_tags(tree, 'REMOVE')
manipulate.save_tree(tree)
self.debug.print_debug(
self,
u'Extracted {0} headings from inside invalid elements'.format(
count))
# split any p tags with sub-tags hi rend="Indent" into new elements
biblio_elements = tree.xpath(
'//tei:p'
'[tei:hi[contains(@rend, "Indent") or contains(@rend, "Default Style") or '
'contains(@rend, "Text Body")]]',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
for parent in biblio_elements:
add_position = parent
for element in parent.xpath(
'tei:hi[contains(@rend, "Indent") or contains(@rend, "Default Style") or '
'contains(@rend, "Text Body")]',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'}):
new_p = etree.Element('p')
if 'rend' in parent.attrib:
new_p.attrib['rend'] = parent.attrib['rend']
add_position.addnext(new_p)
new_p.append(element)
add_position = new_p
manipulate.save_tree(tree)
self.debug.print_debug(
self, u'Separated out p {0}'.format(
manipulate.get_stripped_text(parent)))
def pre_clean(self):
self.extract_metadata_fields()
manipulate = TeiManipulate(self.gv)
tree = manipulate.load_dom_tree()
# get all elements in the body
section = tree.xpath('//tei:body//*',
namespaces={'tei': 'http://www.tei-c.org/ns/1.0'})
items_to_match = [
'{http://www.tei-c.org/ns/1.0}head',
'{http://www.tei-c.org/ns/1.0}p',
'{http://www.tei-c.org/ns/1.0}cit'
]
count = 0
matched_authors = []
for item in section:
if count > 2:
break
if item.tag in items_to_match:
count += 1
text = self.get_stripped_text(item)
processed = False
for author in self.authors:
if not author in matched_authors:
has_all = True
for component in author:
if not component in text:
has_all = False
break
if has_all:
# found a metadata line
matched_authors.append(author)
count -= 1
item.getparent().remove(item)
self.debug.print_debug(
self, u'Removed line "{0}" '
u'because it appears to be author metadata'.
format(text))
processed = True
break
if not processed:
for metadata in self.metadata:
if metadata in text:
# found a metadata line
count -= 1
item.getparent().remove(item)
self.debug.print_debug(
self, u'Removed line "{0}" '
u'because it appears to be duplicated metadata'
.format(text))
manipulate.save_tree(tree)
