def ETIteratorFromObj(obj, events=None, parser=None):
"""obj can be
1) a string that ends with .xml -> the file is parsed and the resulting ElementTree returned
2) a string that ends with .xml.gz -> the file is unzipped, parsed, and the resulting ElementTree is returned
3) an open input stream -> the input is parsed and the resulting ElementTree is returned
4) an ElementTree or an Element -> obj is returned as-is, nothing is done"""
if isinstance(obj, str) or isinstance(obj, unicode):
if obj.endswith(".gz"):
fStream = GzipFile(obj, "rt")
#fStream = codecs.getreader("utf-8")(GzipFile(obj,"rt"))
else:
fStream = open(obj, "rt")
#fStream=codecs.open(obj, "rt", "utf-8")
for rv in iterparse2(fStream, events):
yield rv
elif isinstance(obj,
ElementTree.ElementTree) or ElementTree.iselement(obj):
if ElementTree.iselement(obj):
root = obj
else:
root = obj.getroot()
#if events == None:
# events = ["END"]
for element in root.getiterator():
yield ("memory", element)
else:
#not a string, not a tree, not an element, should be a stream
#let's parse it
for rv in ElementTree.iterparse(obj, events):
yield rv
def ETIteratorFromObj(obj, events=None, parser=None):
"""obj can be
1) a string that ends with .xml -> the file is parsed and the resulting ElementTree returned
2) a string that ends with .xml.gz -> the file is unzipped, parsed, and the resulting ElementTree is returned
3) an open input stream -> the input is parsed and the resulting ElementTree is returned
4) an ElementTree or an Element -> obj is returned as-is, nothing is done"""
if isinstance(obj,str) or isinstance(obj,unicode):
if obj.endswith(".gz"):
fStream=GzipFile(obj,"rt")
#fStream = codecs.getreader("utf-8")(GzipFile(obj,"rt"))
else:
fStream=open(obj,"rt")
#fStream=codecs.open(obj, "rt", "utf-8")
for rv in iterparse2(fStream, events):
yield rv
elif isinstance(obj,ElementTree.ElementTree) or ElementTree.iselement(obj):
if ElementTree.iselement(obj):
root = obj
else:
root = obj.getroot()
#if events == None:
# events = ["END"]
for element in root.getiterator():
yield ("memory", element)
else:
#not a string, not a tree, not an element, should be a stream
#let's parse it
for rv in ElementTree.iterparse(obj, events):
yield rv
def __init__(self, key, name, force_=False):
#didn't i read somwhere that variable reuse is bad like this? :)
#sys.stdout.write('Got key: %s\n' % (key,))
x = 'http://isbndb.com/api/books.xml?access_key=%s&index1=isbn'
x += '&value1=foo&results=keystats'
x %= key
a = urllib.urlopen(x).read()
sys.stdout.write('Got from isbndb:\n %s\n' % (a, ))
y = ElementTree.fromstring(a)
if ElementTree.iselement(y.find('ErrorMessage')):
sys.stdout.write('Found error...')
if force_:
sys.stdout.write('forcing\n')
self.active = False
self.granted = 0
self.limit = 0
return
else:
sys.stdout.write('erroring\n')
raise ValueError, 'either bad key or something'
else:
self.active = True
y = y.find('KeyStats')
self.granted = int(y.get('granted'))
self.limit = int(y.get('limit'))
self.name = name
def __init__(self, key, name, force_=False):
#didn't i read somwhere that variable reuse is bad like this? :)
#sys.stdout.write('Got key: %s\n' % (key,))
x = 'http://isbndb.com/api/books.xml?access_key=%s&index1=isbn'
x += '&value1=foo&results=keystats'
x %=key
a = urllib.urlopen(x).read()
sys.stdout.write('Got from isbndb:\n %s\n' % (a,))
y = ElementTree.fromstring(a)
if ElementTree.iselement(y.find('ErrorMessage')):
sys.stdout.write('Found error...')
if force_:
sys.stdout.write('forcing\n')
self.active = False
self.granted = 0
self.limit = 0
return
else:
sys.stdout.write('erroring\n')
raise ValueError, 'either bad key or something'
else:
self.active = True
y = y.find('KeyStats')
self.granted = int(y.get('granted'))
self.limit = int(y.get('limit'))
self.name = name
def ETFromObj(obj):
"""obj can be
1) a string that ends with .xml -> the file is parsed and the resulting ElementTree returned
2) a string that ends with .xml.gz -> the file is unzipped, parsed, and the resulting ElementTree is returned
3) an open input stream -> the input is parsed and the resulting ElementTree is returned
4) an ElementTree or an Element -> obj is returned as-is, nothing is done"""
if isinstance(obj, str) or isinstance(obj, unicode):
if obj.endswith(".xml.gz"):
fStream = GzipFile(obj, "rt")
#fStream = codecs.getreader("utf-8")(GzipFile(obj,"rt"))
elif obj.endswith(".xml") or obj.endswith(".svg") or obj.endswith(
".nxml") or obj.endswith(".csml"):
fStream = open(obj, "rt")
#fStream=codecs.open(obj, "rt", "utf-8")
else:
raise ValueError(
"%s: File format not recognized (expected .xml or .xml.gz)" %
obj)
return ElementTree.parse(fStream)
elif isinstance(obj,
ElementTree.ElementTree) or ElementTree.iselement(obj):
return obj
else:
#not a string, not a tree, not an element, should be a stream
#let's parse it
return ElementTree.parse(obj)
def fetch(param):
a = urllib.urlopen(param.url)
x = unicode(a.read(), 'ascii', errors='ignore')
tree = ElementTree.fromstring(x)
err = tree.find('ErrorMessage')
if ElementTree.iselement(err):
raise Exception, 'an error occurred'
stats = tree.find('KeyStats')
list = tree.find('BookList')
param.key.update(stats)
return list
def fetch(param):
a = urllib.urlopen(param.url)
x = unicode(a.read(),'ascii',errors='ignore')
tree = ElementTree.fromstring(x)
err = tree.find('ErrorMessage')
if ElementTree.iselement(err):
raise Exception, 'an error occurred'
stats = tree.find('KeyStats')
list = tree.find('BookList')
param.key.update(stats)
return list
def extractMarks(srcGpx, dstGpx=None):
if ET.iselement(srcGpx):
sroot = srcGpx
else:
src = ET.parse(srcGpx)
sroot = src.getroot()
root = ET.Element("gpx")
root.attrib = sroot.attrib.copy()
root.set("xmlns", GPX_NS)
root.set("{%s}dummy"%GPX_NS, "true") # dummy to force ns insertion
root.set("{%s}dummy"%MY_NS, "true") # dummy to force ns insertion
root.text = "\n "
all = sroot.findall(mkpath("trk/trkseg/trkpt"))
trk = seg = None
ctr = []
open = None
for tpt in all:
mark = tpt.find(mkpath("extensions/gpslog:mark")) # extensions/gpslog:mark"))
if mark != None and mark.get("in") == "true":
trk = ET.SubElement(root, "trk")
tnm = ET.SubElement(trk, "name")
tdsc = ET.SubElement(trk, "desc")
seg = ET.SubElement(trk, "trkseg")
tnm.text = mark.text
tdsc.text = mark.text + " - " + tpt.findtext(mkpath("time"))
# Formatting in DOM :-(
tnm.tail = "\n "; seg.text = "\n "; seg.tail = "\n ";
trk.text = "\n "; trk.tail = "\n "
open = tpt
if seg != None:
seg.append(killNs(tpt))
if mark != None and mark.get("in") != "true":
assert open != None, "Found closing trackpoint without opener"
ctr += [ center(open, tpt) ]
trk = seg = open = None
if open != None:
ctr += [ center(open, tpt) ]
addCenterpoints(root, ctr)
return root
def fauxFetch(params):
"""This is a simple fetch for testing cursor functionality"""
page = os.path.join(prependdir,'xml','%s.xml'%(params.pageNum,))
sys.stdout.write('OPENING PAGE: %s\n' % (page,))
#f = open(page)
#a = f.read()
#r = ElementTree.fromstring(unicode(a,'ascii',errors='ignore'))
try:
r = ElementTree.parse(page)
except:
raise SyntaxError, 'page was: %s' % (page,)
r = r.find('BookList')
if ElementTree.iselement(r):
return r
else:
raise Exception, 'not getting a page...'
def fauxFetch(params):
"""This is a simple fetch for testing cursor functionality"""
page = os.path.join(prependdir, 'xml', '%s.xml' % (params.pageNum, ))
sys.stdout.write('OPENING PAGE: %s\n' % (page, ))
#f = open(page)
#a = f.read()
#r = ElementTree.fromstring(unicode(a,'ascii',errors='ignore'))
try:
r = ElementTree.parse(page)
except:
raise SyntaxError, 'page was: %s' % (page, )
r = r.find('BookList')
if ElementTree.iselement(r):
return r
else:
raise Exception, 'not getting a page...'
def check_element(element):
if not ElementTree.iselement(element):
print "not an element"
if not hasattr(element, "tag"):
print "no tag member"
if not hasattr(element, "attrib"):
print "no attrib member"
if not hasattr(element, "text"):
print "no text member"
if not hasattr(element, "tail"):
print "no tail member"
check_string(element.tag)
check_mapping(element.attrib)
if element.text != None:
check_string(element.text)
if element.tail != None:
check_string(element.tail)
def check_element(element):
if not ElementTree.iselement(element):
print "not an element"
if not hasattr(element, "tag"):
print "no tag member"
if not hasattr(element, "attrib"):
print "no attrib member"
if not hasattr(element, "text"):
print "no text member"
if not hasattr(element, "tail"):
print "no tail member"
check_string(element.tag)
check_mapping(element.attrib)
if element.text != None:
check_string(element.text)
if element.tail != None:
check_string(element.tail)
def ETFromObj(obj):
"""obj can be
1) a string that ends with .xml -> the file is parsed and the resulting ElementTree returned
2) a string that ends with .xml.gz -> the file is unzipped, parsed, and the resulting ElementTree is returned
3) an open input stream -> the input is parsed and the resulting ElementTree is returned
4) an ElementTree or an Element -> obj is returned as-is, nothing is done"""
if isinstance(obj,str) or isinstance(obj,unicode):
if obj.endswith(".xml.gz"):
fStream=GzipFile(obj,"rt")
elif obj.endswith(".xml"):
fStream=open(obj,"rt")
else:
raise ValueError("%s: File format not recognized (expected .xml or .xml.gz)"%obj)
return ElementTree.parse(fStream)
elif isinstance(obj,ElementTree.ElementTree) or ElementTree.iselement(obj):
return obj
else:
#not a string, not a tree, not an element, should be a stream
#let's parse it
return ElementTree.parse(obj)
def test_fetchReturnType(self):
print "Testing return type is an Element and BookList...",
x = fetch(self.p)
self.assert_(ElementTree.iselement(x),"FAILED (fetch didnt get elem)")
self.assert_(x.tag == 'BookList', "FAILED (fetched elem not BookList)")
print "OK"
def check_type(self, c):
return ElementTree.iselement(c)
def check_type(self, c):
return ElementTree.iselement(c)
