def parseXML(self, file, naam):
Log.log.startTimer("parseXML")
xml = None
try:
xml = etree.parse(file)
bericht = Log.log.endTimer("parseXML")
Database().log_actie('xml_parse', naam, bericht)
except (Exception), e:
bericht = Log.log.error("fout %s in XML parsen, bestand=%s" % (str(e), str(naam) ))
Database().log_actie('xml_parse', naam, bericht, True)
def parseXML(self, file, naam):
Log.log.startTimer("parseXML")
xml = None
try:
xml = etree.parse(file)
bericht = Log.log.endTimer("parseXML")
Database().log_actie('xml_parse', naam, bericht)
except (Exception), e:
bericht = Log.log.error("fout %s in XML parsen, bestand=%s" %
(str(e), str(naam)))
Database().log_actie('xml_parse', naam, bericht, True)
def process_xml(self, file_resource, filenaam):
Log.log.info("process_xml: verwerk %s " % filenaam)
try:
# XML doc parsen naar etree object
Log.log.startTimer("parseXML")
parsed_xml = etree.parse(file_resource)
bericht = Log.log.endTimer("parseXML")
self.database.log_actie("xml_parse", filenaam, bericht)
except (Exception), e:
bericht = Log.log.error("fout %s in XML parsen, bestand=%s" % (str(e), filenaam))
self.database.log_actie("xml_parse", filenaam, bericht, True)
return
def process_xml(self, file_resource, filenaam):
Log.log.info("process_xml: verwerk %s " % filenaam)
try:
# XML doc parsen naar etree object
Log.log.startTimer("parseXML")
parsed_xml = etree.parse(file_resource)
bericht = Log.log.endTimer("parseXML")
self.database.log_actie('xml_parse', filenaam, bericht)
except (Exception), e:
bericht = Log.log.error("fout %s in XML parsen, bestand=%s" % (str(e), filenaam))
self.database.log_actie('xml_parse', filenaam, bericht, True)
return
def parse_gemeentelijke_indeling(args):
if not os.access(args.input, os.R_OK):
if args.verbose:
print("Error: Cannot read file: "+ args.input)
return
if args.verbose:
print("Parsing XML file: "+ args.input)
try:
# XML doc parsen naar etree object
parsed_xml = etree.parse(args.input)
except (Exception), e:
print("Error: Failed to parse file: %s (%s)" % (args.input, str(e)))
return
def parse_gemeentelijke_indeling(args):
if not os.access(args.input, os.R_OK):
if args.verbose:
print("Error: Cannot read file: " + args.input)
return
if args.verbose:
print("Parsing XML file: " + args.input)
try:
# XML doc parsen naar etree object
parsed_xml = etree.parse(args.input)
except (Exception), e:
print("Error: Failed to parse file: %s (%s)" % (args.input, str(e)))
return
def parse(fn, out = None):
"""
Reads XML from the file name or object 'fn' and returns
a 'Unit' instance. Rewrites the XML to out, if not None.
"""
e = etree.parse(fn).getroot()
u = unit.Unit()
u.lang = e.get('language')
u.filename = e.get('filename')
if out:
open(out + os.path.basename(u.filename) + '.lh', 'w').write(etree.tostring(e))
u.source = e.find('raw-source').text
for t in e.find('referenced-types').getchildren():
tt = types.aggregate_from_xml(t)
assert tt.id not in u.types
u.types[tt.id] = tt
for f in e.find('function-bodies').getchildren():
u.functions += [ functions.Function.from_xml(f) ]
u.finalise()
return u
def process_xml(self, file_resource, filenaam):
Log.log.info("process_xml: verwerk %s " % filenaam)
try:
# XML doc parsen naar etree object
Log.log.startTimer("parseXML")
parsed_xml = etree.parse(file_resource)
bericht = Log.log.endTimer("parseXML")
self.database.log_actie('xml_parse', filenaam, bericht)
except (Exception) as e:
bericht = Log.log.error("fout %s in XML parsen, bestand=%s" %
(str(e), filenaam))
self.database.log_actie('xml_parse', filenaam, bericht, True)
return
if filenaam == 'gemeentelijke-indeling.xml':
try:
self.processor.processGemeentelijkeIndeling(
parsed_xml.getroot(), filenaam)
self.database.log_actie('xml_processing', filenaam,
'verwerkt OK')
except (Exception) as e:
bericht = Log.log.error(
"fout %s in XML DOM processing, bestand=%s" %
(str(e), filenaam))
self.database.log_actie('xml_processing', filenaam, bericht,
True)
else:
try:
# Verwerken parsed xml: de Processor bepaalt of het een extract of een mutatie is
self.processor.processDOM(parsed_xml.getroot(), filenaam)
self.database.log_actie('verwerkt', filenaam, 'verwerkt OK')
except (Exception) as e:
bericht = Log.log.error(
"fout %s in XML DOM processing, bestand=%s" %
(str(e), filenaam))
self.database.log_actie('xml_processing', filenaam, bericht,
True)
def __init__(self, elem, parent=None, index=0, parse_remote_metadata=False):
if elem.tag != "Layer":
raise ValueError("%s should be a Layer" % (elem,))
self.parent = parent
if parent:
self.index = "%s.%d" % (parent.index, index)
else:
self.index = str(index)
self.id = self.name = testXMLValue(elem.find("Name"))
# layer attributes
self.queryable = int(elem.attrib.get("queryable", 0))
self.cascaded = int(elem.attrib.get("cascaded", 0))
self.opaque = int(elem.attrib.get("opaque", 0))
self.noSubsets = int(elem.attrib.get("noSubsets", 0))
self.fixedWidth = int(elem.attrib.get("fixedWidth", 0))
self.fixedHeight = int(elem.attrib.get("fixedHeight", 0))
# title is mandatory property
self.title = None
title = testXMLValue(elem.find("Title"))
if title is not None:
self.title = title.strip()
self.abstract = testXMLValue(elem.find("Abstract"))
# bboxes
b = elem.find("BoundingBox")
self.boundingBox = None
if b is not None:
try: # sometimes the SRS attribute is (wrongly) not provided
srs = b.attrib["SRS"]
except KeyError:
srs = None
self.boundingBox = (
float(b.attrib["minx"]),
float(b.attrib["miny"]),
float(b.attrib["maxx"]),
float(b.attrib["maxy"]),
srs,
)
elif self.parent:
if hasattr(self.parent, "boundingBox"):
self.boundingBox = self.parent.boundingBox
# ScaleHint
sh = elem.find("ScaleHint")
self.scaleHint = None
if sh is not None:
self.scaleHint = {"min": sh.attrib["min"], "max": sh.attrib["max"]}
attribution = elem.find("Attribution")
if attribution is not None:
self.attribution = dict()
title = attribution.find("Title")
url = attribution.find("OnlineResource")
logo = attribution.find("LogoURL")
if title is not None:
self.attribution["title"] = title.text
if url is not None:
self.attribution["url"] = url.attrib["{http://www.w3.org/1999/xlink}href"]
if logo is not None:
self.attribution["logo_size"] = (int(logo.attrib["width"]), int(logo.attrib["height"]))
self.attribution["logo_url"] = logo.find("OnlineResource").attrib["{http://www.w3.org/1999/xlink}href"]
b = elem.find("LatLonBoundingBox")
if b is not None:
self.boundingBoxWGS84 = (
float(b.attrib["minx"]),
float(b.attrib["miny"]),
float(b.attrib["maxx"]),
float(b.attrib["maxy"]),
)
elif self.parent:
self.boundingBoxWGS84 = self.parent.boundingBoxWGS84
else:
self.boundingBoxWGS84 = None
# SRS options
self.crsOptions = []
# Copy any parent SRS options (they are inheritable properties)
if self.parent:
self.crsOptions = list(self.parent.crsOptions)
# Look for SRS option attached to this layer
if elem.find("SRS") is not None:
## some servers found in the wild use a single SRS
## tag containing a whitespace separated list of SRIDs
## instead of several SRS tags. hence the inner loop
for srslist in map(lambda x: x.text, elem.findall("SRS")):
if srslist:
for srs in srslist.split():
self.crsOptions.append(srs)
# Get rid of duplicate entries
self.crsOptions = list(set(self.crsOptions))
# Set self.crsOptions to None if the layer (and parents) had no SRS options
if len(self.crsOptions) == 0:
# raise ValueError('%s no SRS available!?' % (elem,))
# Comment by D Lowe.
# Do not raise ValueError as it is possible that a layer is purely a parent layer and does not have SRS specified. Instead set crsOptions to None
# Comment by Jachym:
# Do not set it to None, but to [], which will make the code
# work further. Fixed by anthonybaxter
self.crsOptions = []
# Styles
self.styles = {}
# Copy any parent styles (they are inheritable properties)
if self.parent:
self.styles = self.parent.styles.copy()
# Get the styles for this layer (items with the same name are replaced)
for s in elem.findall("Style"):
name = s.find("Name")
title = s.find("Title")
if name is None or title is None:
raise ValueError("%s missing name or title" % (s,))
style = {"title": title.text}
# legend url
legend = s.find("LegendURL/OnlineResource")
if legend is not None:
style["legend"] = legend.attrib["{http://www.w3.org/1999/xlink}href"]
self.styles[name.text] = style
# keywords
self.keywords = [f.text for f in elem.findall("KeywordList/Keyword")]
# timepositions - times for which data is available.
self.timepositions = None
for extent in elem.findall("Extent"):
if extent.attrib.get("name").lower() == "time":
if extent.text:
self.timepositions = extent.text.split(",")
break
# Elevations - available vertical levels
self.elevations = None
for extent in elem.findall("Extent"):
if extent.attrib.get("name").lower() == "elevation":
if extent.text:
self.elevations = extent.text.split(",")
break
# MetadataURLs
self.metadataUrls = []
for m in elem.findall("MetadataURL"):
metadataUrl = {
"type": testXMLValue(m.attrib["type"], attrib=True),
"format": testXMLValue(m.find("Format")),
"url": testXMLValue(m.find("OnlineResource").attrib["{http://www.w3.org/1999/xlink}href"], attrib=True),
}
if metadataUrl["url"] is not None and parse_remote_metadata: # download URL
try:
content = urllib2.urlopen(metadataUrl["url"])
doc = etree.parse(content)
if metadataUrl["type"] is not None:
if metadataUrl["type"] == "FGDC":
metadataUrl["metadata"] = Metadata(doc)
if metadataUrl["type"] == "TC211":
metadataUrl["metadata"] = MD_Metadata(doc)
except Exception, err:
metadataUrl["metadata"] = None
self.metadataUrls.append(metadataUrl)
def __init__(self, elem, parent=None, index=0, parse_remote_metadata=False):
if elem.tag != 'Layer':
raise ValueError('%s should be a Layer' % (elem,))
self.parent = parent
if parent:
self.index = "%s.%d" % (parent.index, index)
else:
self.index = str(index)
self.id = self.name = testXMLValue(elem.find('Name'))
# title is mandatory property
self.title = testXMLValue(elem.find('Title')).strip()
self.abstract = testXMLValue(elem.find('Abstract'))
# bboxes
b = elem.find('BoundingBox')
self.boundingBox = None
if b is not None:
try: #sometimes the SRS attribute is (wrongly) not provided
srs=b.attrib['SRS']
except KeyError:
srs=None
self.boundingBox = (
float(b.attrib['minx']),
float(b.attrib['miny']),
float(b.attrib['maxx']),
float(b.attrib['maxy']),
srs,
)
elif self.parent:
if hasattr(self.parent, 'boundingBox'):
self.boundingBox = self.parent.boundingBox
# ScaleHint
sh = elem.find('ScaleHint')
self.scaleHint = None
if sh is not None:
self.scaleHint = {'min': sh.attrib['min'], 'max': sh.attrib['max']}
attribution = elem.find('Attribution')
if attribution is not None:
self.attribution = dict()
title = attribution.find('Title')
url = attribution.find('OnlineResource')
logo = attribution.find('LogoURL')
if title is not None:
self.attribution['title'] = title.text
if url is not None:
self.attribution['url'] = url.attrib['{http://www.w3.org/1999/xlink}href']
if logo is not None:
self.attribution['logo_size'] = (int(logo.attrib['width']), int(logo.attrib['height']))
self.attribution['logo_url'] = logo.find('OnlineResource').attrib['{http://www.w3.org/1999/xlink}href']
b = elem.find('LatLonBoundingBox')
if b is not None:
self.boundingBoxWGS84 = (
float(b.attrib['minx']),
float(b.attrib['miny']),
float(b.attrib['maxx']),
float(b.attrib['maxy']),
)
elif self.parent:
self.boundingBoxWGS84 = self.parent.boundingBoxWGS84
else:
self.boundingBoxWGS84 = None
#SRS options
self.crsOptions = []
#Copy any parent SRS options (they are inheritable properties)
if self.parent:
self.crsOptions = list(self.parent.crsOptions)
#Look for SRS option attached to this layer
if elem.find('SRS') is not None:
## some servers found in the wild use a single SRS
## tag containing a whitespace separated list of SRIDs
## instead of several SRS tags. hence the inner loop
for srslist in map(lambda x: x.text, elem.findall('SRS')):
if srslist:
for srs in srslist.split():
self.crsOptions.append(srs)
#Get rid of duplicate entries
self.crsOptions = list(set(self.crsOptions))
#Set self.crsOptions to None if the layer (and parents) had no SRS options
if len(self.crsOptions) == 0:
#raise ValueError('%s no SRS available!?' % (elem,))
#Comment by D Lowe.
#Do not raise ValueError as it is possible that a layer is purely a parent layer and does not have SRS specified. Instead set crsOptions to None
self.crsOptions=None
#Styles
self.styles = {}
#Copy any parent styles (they are inheritable properties)
if self.parent:
self.styles = self.parent.styles.copy()
#Get the styles for this layer (items with the same name are replaced)
for s in elem.findall('Style'):
name = s.find('Name')
title = s.find('Title')
if name is None or title is None:
raise ValueError('%s missing name or title' % (s,))
style = { 'title' : title.text }
# legend url
legend = s.find('LegendURL/OnlineResource')
if legend is not None:
style['legend'] = legend.attrib['{http://www.w3.org/1999/xlink}href']
self.styles[name.text] = style
# keywords
self.keywords = extract_xml_list(elem.findall('KeywordList/Keyword'))
# timepositions - times for which data is available.
self.timepositions=None
for extent in elem.findall('Extent'):
if extent.attrib.get("name").lower() =='time':
if extent.text:
self.timepositions=extent.text.split(',')
break
# MetadataURLs
self.metadataUrls = []
for m in elem.findall('MetadataURL'):
metadataUrl = {
'type': testXMLValue(m.attrib['type'], attrib=True),
'format': testXMLValue(m.find('Format')),
'url': testXMLValue(m.find('OnlineResource').attrib['{http://www.w3.org/1999/xlink}href'], attrib=True)
}
if metadataUrl['url'] is not None and parse_remote_metadata: # download URL
try:
content = urllib2.urlopen(metadataUrl['url'])
doc = etree.parse(content)
if metadataUrl['type'] is not None:
if metadataUrl['type'] == 'FGDC':
metadataUrl['metadata'] = Metadata(doc)
if metadataUrl['type'] == 'TC211':
metadataUrl['metadata'] = MD_Metadata(doc)
except Exception, err:
metadataUrl['metadata'] = None
self.metadataUrls.append(metadataUrl)
def parse_gemeentelijke_indeling(args):
if not os.access(args.input, os.R_OK):
if args.verbose:
print("Error: Cannot read file: " + args.input)
return
if args.verbose:
print("Parsing XML file: " + args.input)
try:
# XML doc parsen naar etree object
parsed_xml = etree.parse(args.input)
except (Exception) as e:
print("Error: Failed to parse file: %s (%s)" % (args.input, str(e)))
return
gemeentelijke_indeling = hash()
root = parsed_xml.getroot()
if stripschema(root.tag) == 'gemeentelijke_indeling':
if len(root.attrib):
gemeentelijke_indeling['attributes'] = root.attrib
if len(root.nsmap):
gemeentelijke_indeling['nsmap'] = root.nsmap
for indelingNode in root:
if stripschema(indelingNode.tag) == 'indeling':
jaar = indelingNode.get('jaar')
indeling = hash()
indeling['attributes']['jaar'] = jaar
for provincieNode in indelingNode:
if stripschema(provincieNode.tag) == 'provincie':
provinciecode = provincieNode.get('code')
provincienaam = provincieNode.get('naam')
provincie = hash()
provincie['attributes']['code'] = provinciecode
provincie['attributes']['naam'] = provincienaam
for gemeenteNode in provincieNode:
if stripschema(gemeenteNode.tag) == 'gemeente':
gemeentecode = gemeenteNode.get('code')
gemeentenaam = gemeenteNode.get('naam')
begindatum = gemeenteNode.get('begindatum')
einddatum = gemeenteNode.get('einddatum')
gemeente = hash()
gemeente['attributes']['code'] = gemeentecode
gemeente['attributes']['naam'] = gemeentenaam
gemeente['attributes'][
'begindatum'] = begindatum
gemeente['attributes']['einddatum'] = einddatum
provincie['gemeente'][gemeentecode] = gemeente
indeling['provincie'][provinciecode] = provincie
gemeentelijke_indeling['indeling'][jaar] = indeling
return gemeentelijke_indeling
def __init__(self,
elem,
parent=None,
index=0,
parse_remote_metadata=False):
if elem.tag != 'Layer':
raise ValueError('%s should be a Layer' % (elem, ))
self.parent = parent
if parent:
self.index = "%s.%d" % (parent.index, index)
else:
self.index = str(index)
self.id = self.name = testXMLValue(elem.find('Name'))
# layer attributes
self.queryable = int(elem.attrib.get('queryable', 0))
self.cascaded = int(elem.attrib.get('cascaded', 0))
self.opaque = int(elem.attrib.get('opaque', 0))
self.noSubsets = int(elem.attrib.get('noSubsets', 0))
self.fixedWidth = int(elem.attrib.get('fixedWidth', 0))
self.fixedHeight = int(elem.attrib.get('fixedHeight', 0))
# title is mandatory property
self.title = None
title = testXMLValue(elem.find('Title'))
if title is not None:
self.title = title.strip()
self.abstract = testXMLValue(elem.find('Abstract'))
# bboxes
b = elem.find('BoundingBox')
self.boundingBox = None
if b is not None:
try: #sometimes the SRS attribute is (wrongly) not provided
srs = b.attrib['SRS']
except KeyError:
srs = None
self.boundingBox = (
float(b.attrib['minx']),
float(b.attrib['miny']),
float(b.attrib['maxx']),
float(b.attrib['maxy']),
srs,
)
elif self.parent:
if hasattr(self.parent, 'boundingBox'):
self.boundingBox = self.parent.boundingBox
# ScaleHint
sh = elem.find('ScaleHint')
self.scaleHint = None
if sh is not None:
self.scaleHint = {'min': sh.attrib['min'], 'max': sh.attrib['max']}
attribution = elem.find('Attribution')
if attribution is not None:
self.attribution = dict()
title = attribution.find('Title')
url = attribution.find('OnlineResource')
logo = attribution.find('LogoURL')
if title is not None:
self.attribution['title'] = title.text
if url is not None:
self.attribution['url'] = url.attrib[
'{http://www.w3.org/1999/xlink}href']
if logo is not None:
self.attribution['logo_size'] = (int(logo.attrib['width']),
int(logo.attrib['height']))
self.attribution['logo_url'] = logo.find(
'OnlineResource'
).attrib['{http://www.w3.org/1999/xlink}href']
b = elem.find('LatLonBoundingBox')
if b is not None:
self.boundingBoxWGS84 = (
float(b.attrib['minx']),
float(b.attrib['miny']),
float(b.attrib['maxx']),
float(b.attrib['maxy']),
)
elif self.parent:
self.boundingBoxWGS84 = self.parent.boundingBoxWGS84
else:
self.boundingBoxWGS84 = None
#SRS options
self.crsOptions = []
#Copy any parent SRS options (they are inheritable properties)
if self.parent:
self.crsOptions = list(self.parent.crsOptions)
#Look for SRS option attached to this layer
if elem.find('SRS') is not None:
## some servers found in the wild use a single SRS
## tag containing a whitespace separated list of SRIDs
## instead of several SRS tags. hence the inner loop
for srslist in map(lambda x: x.text, elem.findall('SRS')):
if srslist:
for srs in srslist.split():
self.crsOptions.append(srs)
#Get rid of duplicate entries
self.crsOptions = list(set(self.crsOptions))
#Set self.crsOptions to None if the layer (and parents) had no SRS options
if len(self.crsOptions) == 0:
#raise ValueError('%s no SRS available!?' % (elem,))
#Comment by D Lowe.
#Do not raise ValueError as it is possible that a layer is purely a parent layer and does not have SRS specified. Instead set crsOptions to None
# Comment by Jachym:
# Do not set it to None, but to [], which will make the code
# work further. Fixed by anthonybaxter
self.crsOptions = []
#Styles
self.styles = {}
#Copy any parent styles (they are inheritable properties)
if self.parent:
self.styles = self.parent.styles.copy()
#Get the styles for this layer (items with the same name are replaced)
for s in elem.findall('Style'):
name = s.find('Name')
title = s.find('Title')
if name is None or title is None:
raise ValueError('%s missing name or title' % (s, ))
style = {'title': title.text}
# legend url
legend = s.find('LegendURL/OnlineResource')
if legend is not None:
style['legend'] = legend.attrib[
'{http://www.w3.org/1999/xlink}href']
self.styles[name.text] = style
# keywords
self.keywords = [f.text for f in elem.findall('KeywordList/Keyword')]
# timepositions - times for which data is available.
self.timepositions = None
self.defaulttimeposition = None
for extent in elem.findall('Extent'):
if extent.attrib.get("name").lower() == 'time':
if extent.text:
self.timepositions = extent.text.split(',')
self.defaulttimeposition = extent.attrib.get("default")
break
# Elevations - available vertical levels
self.elevations = None
for extent in elem.findall('Extent'):
if extent.attrib.get("name").lower() == 'elevation':
if extent.text:
self.elevations = extent.text.split(',')
break
# MetadataURLs
self.metadataUrls = []
for m in elem.findall('MetadataURL'):
metadataUrl = {
'type':
testXMLValue(m.attrib['type'], attrib=True),
'format':
testXMLValue(m.find('Format')),
'url':
testXMLValue(m.find('OnlineResource').
attrib['{http://www.w3.org/1999/xlink}href'],
attrib=True)
}
if metadataUrl[
'url'] is not None and parse_remote_metadata: # download URL
try:
content = urllib2.urlopen(metadataUrl['url'])
doc = etree.parse(content)
if metadataUrl['type'] is not None:
if metadataUrl['type'] == 'FGDC':
metadataUrl['metadata'] = Metadata(doc)
if metadataUrl['type'] == 'TC211':
metadataUrl['metadata'] = MD_Metadata(doc)
except Exception, err:
metadataUrl['metadata'] = None
self.metadataUrls.append(metadataUrl)
def parseXML(self,naam):
Log.log.startTimer("parseXML")
xml = etree.parse(naam)
Log.log.endTimer("parseXML")
return xml
