def command_upload(self):
'''upload XML_PATH IP_ID CONTENT_TYPE [XPATH]
pm dptext upload exon\source\rekeyed\converted\EXON-1-493.xhtml 1 transcription
'''
if len(self.args) < 4:
print 'upload requires 3 arguments'
return
xml_path, ip_id, content_type_name = self.args[1:4]
xpath = None
if len(self.args) > 4:
xpath = self.args[4]
# I find the TextContentXML record (or create it)
tcx = self.get_textcontentxml(ip_id, content_type_name)
if not tcx:
print 'ERROR: could not find record (%s, %s)' % (ip_id,
content_type_name)
return
# II load the file and convert it
from digipal.utils import read_file, get_xml_from_unicode
xml_string = read_file(xml_path)
# III get the XML into a string
if xpath:
xml = get_xml_from_unicode(xml_string, add_root=True)
els = xml.xpath(xpath)
if len(els) > 0:
root = els[0]
else:
raise Exception(u'No match for XPATH "%s"' % xpath)
from lxml import etree
#content = etree.tostring(root, encoding="UTF-8")
content = dputils.get_unicode_from_xml(etree, remove_root=True)
else:
content = xml_string
# print type(root)
# print dir(root)
# content = str(root)
if 'ũ' in content:
print 'Numeric entity'
exit()
# IV convert the xml tags and attribute to HTML-TEI
# content = self.get_xhtml_from_xml(content)
# save the content into the TextContentXML record
tcx.content = content
tcx.save()
from django.template.defaultfilters import filesizeformat
print 'Uploaded %s into record #%s' % (filesizeformat(
tcx.get_length()), tcx.id)
def command_upload(self):
'''upload XML_PATH IP_ID CONTENT_TYPE [XPATH]
pm dptext upload exon\source\rekeyed\converted\EXON-1-493.xhtml 1 transcription
'''
if len(self.args) < 4:
print 'upload requires 3 arguments'
return
xml_path, ip_id, content_type_name = self.args[1:4]
xpath = None
if len(self.args) > 4:
xpath = self.args[4]
# I find the TextContentXML record (or create it)
tcx = self.get_textcontentxml(ip_id, content_type_name)
if not tcx:
print 'ERROR: could not find record (%s, %s)' % (ip_id, content_type_name)
return
# II load the file and convert it
from digipal.utils import read_file, get_xml_from_unicode
xml_string = read_file(xml_path)
# III get the XML into a string
if xpath:
xml = get_xml_from_unicode(xml_string, add_root=True)
els = xml.xpath(xpath)
if len(els) > 0:
root = els[0]
else:
raise Exception(u'No match for XPATH "%s"' % xpath)
from lxml import etree
#content = etree.tostring(root, encoding="UTF-8")
content = dputils.get_unicode_from_xml(etree, remove_root=True)
else:
content = xml_string
# print type(root)
# print dir(root)
# content = str(root)
if 'ũ' in content:
print 'Numeric entity'
exit()
# IV convert the xml tags and attribute to HTML-TEI
# content = self.get_xhtml_from_xml(content)
# save the content into the TextContentXML record
tcx.content = content
tcx.save()
from django.template.defaultfilters import filesizeformat
print 'Uploaded %s into record #%s' % (filesizeformat(tcx.get_length()), tcx.id)
def get_tei_from_text_response(response, item_partid, content_type):
ret = response.get('content', '')
# decode entities (e.g. ’)
# TODO: make sure we keep core XML entities otherwise it may cause
# parsing errors down the line
from HTMLParser import HTMLParser
parser = HTMLParser()
ret = parser.unescape(ret)
# convert & back to & to keep XML well-formed
ret = ret.replace(u'&', u'&')
# convert to XML object
#xml = dputils.get_xml_from_unicode(ret, ishtml=True, add_root=True)
#print repr(response)
from digipal.models import ItemPart
itempart = ItemPart.objects.filter(id=item_partid).first()
tcx = TextContentXML.objects.filter(text_content__type__slug='translation', text_content__item_part__id=item_partid).first()
#
#print ret
from django.template.loader import render_to_string
context = {
'meta': {
'title': '%s of %s' % (content_type.title(), itempart),
'ms': {
'place': itempart.current_item.repository.place.name,
'repository': itempart.current_item.repository.name,
'shelfmark': itempart.current_item.shelfmark,
},
'edition': {
'date': tcx.modified
},
'project': settings.SITE_TITLE,
'authority': settings.SITE_TITLE,
},
}
template = render_to_string('digipal_text/tei_from_xhtml.xslt', context)
ret = dputils.get_xslt_transform('<root>%s</root>' % ret, template)
ret = dputils.get_unicode_from_xml(xmltree=ret).replace('xmlns=""', '')
# convert XML to string
#ret = dputils.get_unicode_from_xml(xml, remove_root=True)
return ret
def get_tei_from_text_response(response, item_partid, content_type):
ret = response.get('content', '')
# decode entities (e.g. ’)
# TODO: make sure we keep core XML entities otherwise it may cause
# parsing errors down the line
from HTMLParser import HTMLParser
parser = HTMLParser()
ret = parser.unescape(ret)
# convert & back to & to keep XML well-formed
ret = ret.replace(u'&', u'&')
# convert to XML object
#xml = dputils.get_xml_from_unicode(ret, ishtml=True, add_root=True)
from digipal.models import ItemPart
itempart = ItemPart.objects.filter(id=item_partid).first()
tcx = TextContentXML.objects.filter(
text_content__type__slug='translation',
text_content__item_part__id=item_partid).first()
#
from django.template.loader import render_to_string
context = {
'meta': {
'title': '%s of %s' % (content_type.title(), itempart),
'ms': {
'place': itempart.current_item.repository.place.name,
'repository': itempart.current_item.repository.name,
'shelfmark': itempart.current_item.shelfmark,
},
'edition': {
'date': tcx.modified
},
'project': settings.SITE_TITLE,
'authority': settings.SITE_TITLE,
},
}
template = render_to_string('digipal_text/tei_from_xhtml.xslt', context)
ret = dputils.get_xslt_transform('<root>%s</root>' % ret, template)
ret = dputils.get_unicode_from_xml(xmltree=ret).replace('xmlns=""', '')
# convert XML to string
#ret = dputils.get_unicode_from_xml(xml, remove_root=True)
return ret