def update_by_re(config_path, conf_d = {'datanucleus.schema.validateConstraints': None}):
with codecs.open(config_path, 'r', 'utf-8') as fp:
xml = fp.read()
for k0,v0 in conf_d.items():
re_str = "<name>(?P<key>{})</name>\s+<value>(?P<value>\w+)</value>".format(k0)
m1 = regex.search(re_str, xml, regex.M)
re_str = "<name>(?P<key>{})</name>\s+<value />".format(k0)
m2 = regex.search(re_str, xml, regex.M)
re_str = "<name>(?P<key>{})</name>\s+(?P<value><value.+?>)".format(k0)
m3 = regex.search(re_str, xml, regex.M)
if m1 and v0:
target_dict = m1.groupdict()
target_str = m1.group()
target_str_new = target_str.replace(target_dict['value'], v0)
xml = xml.replace(target_str, target_str_new)
elif m2 and v0:
target_str = m2.group()
target_str_new = target_str.replace('<value />', '<value>{}</value>'.format(v0))
xml = xml.replace(target_str, target_str_new)
elif m3 and v0 is None:
target_dict = m3.groupdict()
xml = xml.replace(target_dict['value'], '<value />')
with codecs.open(config_path, 'w', 'utf-8') as fp:
fp.write(xml)
def remove_plurals_xml(xml):
pluralizeds = [
'Actecos', 'Detalles', 'Referencias', 'DscRcgGlobals', 'ImptoRetens'
]
for k in pluralizeds:
xml = xml.replace('<%s>' % k, '').replace('</%s>' % k, '')
return xml
def __init__(self,wp='wp.xml',testing=False,do_images=True):
self.wp = wp
self.testing = testing
self.do_images = do_images
self.xml = None
self.pivot_items_xml = ''
self.images = []
self.dzc_output = 'dzc_output'
self.blurb_max_len = 500
if self.testing:
doc = minidom.parseString(testentry)
else:
f = codecs.open(self.wp, 'r', 'utf-8')
xml = f.read()
f.close()
if xml.find('xmlns:atom="http://www.w3.org/2005/Atom"') == -1:
xml = xml.replace('xmlns:wp="http://wordpress.org/export/1.0/"', 'xmlns:wp="http://wordpress.org/export/1.0/" xmlns:atom="http://www.w3.org/2005/Atom"')
f = codecs.open(self.wp, 'w', 'utf-8')
f.write(xml)
f.close()
doc = minidom.parse(self.wp)
self.items = doc.getElementsByTagName('item')
def main(argv):
argc = len(argv)
if (argc is not 1):
print '\nWarning: incorrect argument(s) to knn.py. Expected arguments:\n\n' \
'\t- directory (required)\t: directory containing *.fts files with SIFT features.\n'
sys.exit(1)
dir = argv[0]
xmls = []
xmls.extend(glob.glob1(dir, '*.xml'))
print '{} .xml files found in directory {}'.format(len(xmls), dir)
deleted = 0
for xml in xmls:
xml1 = open(dir + '/' + xml)
xml2 = minidom.parse(xml1)
itemlist = xml2.getElementsByTagName('Type')
xml1.close()
if itemlist[0].firstChild.nodeValue == 'photograph' or itemlist[
0].firstChild.nodeValue == 'pseudoscan':
deleted += 1
fts = dir + '/' + xml.replace('.xml', '.fts')
jpg = dir + '/' + xml.replace('.xml', '.jpg')
# If text file exists, delete it.
if (os.path.isfile(fts)):
os.remove(fts)
if (os.path.isfile(jpg)):
os.remove(jpg)
os.remove(dir + '/' + xml)
print '*.fts files of {} "photograph" and "pseudoscan" images deleted.'.format(
deleted)
def main(argv):
argc = len(argv)
if (argc is not 1):
print '\nWarning: incorrect argument(s) to knn.py. Expected arguments:\n\n' \
'\t- directory (required)\t: directory containing *.fts files with SIFT features.\n'
sys.exit(1)
dir = argv[0]
xmls = []
xmls.extend(glob.glob1(dir, '*.xml'))
print '{} .xml files found in directory {}'.format(len(xmls), dir)
deleted = 0
for xml in xmls:
xml1 = open(dir + '/' + xml)
xml2 = minidom.parse(xml1)
itemlist = xml2.getElementsByTagName('Type')
xml1.close()
if itemlist[0].firstChild.nodeValue == 'photograph' or itemlist[0].firstChild.nodeValue == 'pseudoscan':
deleted += 1
fts = dir + '/' + xml.replace('.xml','.fts')
jpg = dir + '/' + xml.replace('.xml','.jpg')
# If text file exists, delete it.
if (os.path.isfile(fts)):
os.remove(fts)
if (os.path.isfile(jpg)):
os.remove(jpg)
os.remove(dir + '/' + xml)
print '*.fts files of {} "photograph" and "pseudoscan" images deleted.'.format(deleted)
'Ulmus minor', 'Phillyrea angustifolia', 'Buxus sempervirens',
'Quercus ilex', 'Olea europaea', 'Viburnum tinus', 'Pittosporum tobira',
'Hedera helix', 'Ruscus aculeatus', 'Celtis australis',
'Cercis siliquastrum', 'Populus nigra', 'Nerium oleander',
'Euphorbia characias', 'Corylus avellana', 'Pistacia lentiscus',
'Acer campestre', 'Rhus coriaria', 'Acer monspessulanum',
'Cotinus coggygria', 'Crataegus monogyna', 'Juniperus oxycedrus',
'Ginkgo biloba', 'Daphne cneorum', 'Populus alba', 'Platanus x hispanica',
'Arbutus unedo', 'Fraxinus angustifolia', 'Robinia pseudoacacia',
'Laurus nobilis', 'Diospyros kaki', 'Punica granatum'
]
count = len(xmls)
for xml in xmls:
xml1 = open(os.path.abspath(os.path.dirname(__file__)) + '/' + xml)
xml2 = minidom.parse(xml1)
itemlist = xml2.getElementsByTagName('ClassId')
if itemlist[0].firstChild.nodeValue not in top32classes:
count -= 1
jpg = xml.replace('.xml', '.jpg')
fts = xml.replace('.xml', '.fts')
hst = xml.replace('.xml', '.hst')
if (os.path.isfile(jpg)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + jpg)
if (os.path.isfile(fts)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + fts)
if (os.path.isfile(hst)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + hst)
print '{} items deleted'.format(count)
'Ginkgo biloba',
'Daphne cneorum',
'Populus alba',
'Platanus x hispanica',
'Arbutus unedo',
'Fraxinus angustifolia',
'Robinia pseudoacacia',
'Laurus nobilis',
'Diospyros kaki',
'Punica granatum'
]
count = len(xmls)
for xml in xmls:
xml1 = open(os.path.abspath(os.path.dirname(__file__)) + '/' + xml)
xml2 = minidom.parse(xml1)
itemlist = xml2.getElementsByTagName('ClassId')
if itemlist[0].firstChild.nodeValue not in top32classes:
count -= 1
jpg = xml.replace('.xml','.jpg')
fts = xml.replace('.xml','.fts')
hst = xml.replace('.xml','.hst')
if (os.path.isfile(jpg)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + jpg)
if(os.path.isfile(fts)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + fts)
if(os.path.isfile(hst)):
os.remove(os.path.abspath(os.path.dirname(__file__)) + '/' + hst)
print '{} items deleted'.format(count)
