def resolve_xinclude(source_folder, source_ext):
""""""
# Process all files in the source folder with the give extension
pattern = "{}/**/*{}".format(source_folder, source_ext)
matches = glob.glob(pattern, recursive=True)
for filepath in matches:
# print("Parsing", filepath)
tree = ET.parse(filepath)
root = tree.getroot()
EI.include(root, loader=loader) # resolves xi:include elements
# Write output file
filename = os.path.basename(filepath)
basename, ext = os.path.splitext(filename)
out_filename = "{}.sbt".format(basename)
output_folder = os.path.dirname(filepath)
out_filepath = os.path.join(output_folder, out_filename)
with open(out_filepath, "wb") as f:
s = ET.tostring(root)
# TODO: would be good to clean up trailing whitespace
# however, we'd have to do some str-bytes conversion
# s = "\n".join([ln.strip() for ln in s.splitlines()])
f.write(s)
print("Wrote", out_filepath)
return
def parseAndroidAudioPolicyEngineConfigurationFile(
audiopolicyengineconfigurationfile):
logging.info("Checking Audio Policy Engine Configuration file {}".format(
audiopolicyengineconfigurationfile))
#
# extract all product strategies name from audio policy engine configuration file
#
strategy_names = []
oldWorkingDir = os.getcwd()
print "Current working directory %s" % oldWorkingDir
newDir = os.path.join(oldWorkingDir,
audiopolicyengineconfigurationfile.name)
policy_engine_in_tree = ET.parse(audiopolicyengineconfigurationfile)
os.chdir(os.path.dirname(os.path.normpath(newDir)))
print "new working directory %s" % os.getcwd()
policy_engine_root = policy_engine_in_tree.getroot()
EI.include(policy_engine_root)
os.chdir(oldWorkingDir)
for strategy in policy_engine_root.iter('ProductStrategy'):
strategy_names.append(strategy.get('name'))
return strategy_names
def parse(self, file, baseUrl="", ownerDoc=None):
absUrl = convertToAbsUrl(file, baseUrl)
fp = urllib.request.urlopen(absUrl)
try:
tree = ElementTreeExtension()
treeWrapper = self.treeWrapperClass(self, tree, self.useCaching)
parser = ExtXMLTreeBuilder(file, absUrl, self, treeWrapper)
treeWrapper.getTree().parse(fp, parser)
fp.close()
# XInclude support
if self.processXInclude:
loaderInst = ExtXIncludeLoader(self.parse, absUrl, ownerDoc)
try:
ElementInclude.include(
treeWrapper.getTree().getroot(),
loaderInst.loader)
except IOError as errInst:
raise GenXmlIfError(
"%s: IOError: %s" %
(file, str(errInst)))
except ExpatError as errstr:
fp.close()
raise GenXmlIfError("%s: ExpatError: %s" % (file, str(errstr)))
except ElementInclude.FatalIncludeError as errInst:
fp.close()
raise GenXmlIfError("%s: XIncludeError: %s" % (file, str(errInst)))
return treeWrapper
def main():
parser = argparse.ArgumentParser(description='Create text with wrapping directives from rtt.')
parser.add_argument("rtt_file", help="RTT file.")
parser.add_argument("-r", "--heading_regexp", default="", help="Regexp to identify a chapter heading")
parser.add_argument("-b", "--heading_blocks", type=int, choices=[1, 2],
default=1, help="The number of blocks in a chapter heading.")
args = parser.parse_args()
rtt_file = os.path.abspath(args.rtt_file)
if not os.path.isfile(rtt_file):
print(rtt_file, "is not a file\n", file="stderr")
parser.print_help()
sys.exit(-1)
rtt = et.parse(rtt_file)
pages = rtt.find("pages")
os.chdir(os.path.dirname(rtt_file))
ei.include(pages)
open_mf = pages.attrib["microformatting-open"]
close_mf = pages.attrib["microformatting-close"]
pages_text = []
first_page_text = pages.find("page/text")
if first_page_text.text[0] != "\n":
first_page_text.text = "\n" + first_page_text.text
for p in pages.findall("page"):
pages_text.append(process_page(p, open_mf, close_mf,
args.heading_regexp, args.heading_blocks))
sys.stdout.write("\n".join(pages_text))
def loader(href, parse, encoding=None):
if parse == "xml":
with open(href, "rb") as file:
data = ET.parse(file).getroot()
EI.include(data, loader=loader)
else:
raise RuntimeError("Unable to handle recursive include.")
return data
def create_project(project_dir, rtt_file):
project_file = project_dir + "/project"
data = project_data.ProjectData(project_file, True)
rtt = et.parse(rtt_file).getroot()
ei.include(rtt)
process_metadata(rtt, data)
process_pages(rtt, data, project_dir)
data.save() #also unlocks
os.chmod(project_file, 0660)
def get_bocca_objects(element):
objs = []
ElementInclude.include(element)
for child in element.getchildren():
if child.tag == 'project':
objs.extend(get_bocca_objects(child))
elif child.tag in bocca_object_names:
objs.append(child)
return objs
def parse_xml( fname ):
"""Returns a parsed xml tree"""
# handle deprecation warning for XMLParsing a file with DOCTYPE
class DoctypeSafeCallbackTarget( ElementTree.TreeBuilder ):
def doctype( *args ):
pass
tree = ElementTree.ElementTree()
root = tree.parse( fname, parser=ElementTree.XMLParser( target=DoctypeSafeCallbackTarget() ) )
ElementInclude.include( root )
return tree
def parse_xml( fname ):
"""Returns a parsed xml tree"""
# handle deprecation warning for XMLParsing a file with DOCTYPE
class DoctypeSafeCallbackTarget( ElementTree.TreeBuilder ):
def doctype( *args ):
pass
tree = ElementTree.ElementTree()
root = tree.parse( fname, parser=ElementTree.XMLParser( target=DoctypeSafeCallbackTarget() ) )
ElementInclude.include( root )
return tree
def testURLInvocation_XInclude_ETINCLUDE(self):
#Reset the server back to "0"
r = requests.get(self._URL_+"/reset")
r = requests.get(self._URL_ +"/getCounter")
request_content = r.text.replace("\r\n","")
self.assertEqual("0", request_content)
with self.assertRaises(IOError):
root = self.helperParse('../../xml_files_windows/url_invocation_xinclude.xml')
# Resolve xi:include references
_ETINCLUDE.include(root)
def testXInclude_ETINCLUDE(self):
root = self.helperParse('../../xml_files_windows/xinclude.xml')
# Resolve xi:include references
_ETINCLUDE.include(root)
# The Inclusion of xi:include should now have happened.
# Therefore we can get an iterator over the newly included element
# 'content'
elem_data = root.iter('content')
for elem in elem_data:
self.assertEqual("it_works", elem.text)
self.assertEqual("content", elem.tag)
def testXInclude_ETINCLUDE(self):
root = self.helperParse('../../xml_files_windows/xinclude.xml')
# Resolve xi:include references
_ETINCLUDE.include(root)
# The Inclusion of xi:include should now have happened.
# Therefore we can get an iterator over the newly included element
# 'content'
elem_data = root.iter('content')
for elem in elem_data:
self.assertEqual("it_works", elem.text)
self.assertEqual("content", elem.tag)
def testURLInvocation_XInclude_ETINCLUDE(self):
#Reset the server back to "0"
r = requests.get(self._URL_ + "/reset")
r = requests.get(self._URL_ + "/getCounter")
request_content = r.text.replace("\r\n", "")
self.assertEqual("0", request_content)
with self.assertRaises(IOError):
root = self.helperParse(
'../../xml_files_windows/ssrf/url_invocation_xinclude.xml')
# Resolve xi:include references
_ETINCLUDE.include(root)
def test_include_xml(self):
from xml.etree import ElementTree, ElementInclude
tree = ElementTree.parse("files/document.xml")
root = tree.getroot()
ElementInclude.include(root)
tree.write("files/tree_created.xml")
fo = open("files/tree_created.xml", "r+")
lines = fo.readlines()
self.assertEqual([
'<document>\n', ' <document>\n',
' <para>This is a paragraph.</para>\n', '</document>\n',
'</document>'
], lines)
def load(self, filename):
try:
doc = etree.parse(filename)
root = doc.getroot()
einclude.include(root)
self.logger.info("Parsing sources.")
self.__parse_sources(root)
self.logger.info("Parsing servers.")
self.__parse_servers(root)
self.logger.info("Parsing rules.")
self.__parse_rules(root)
except ExpatError, e:
self.logger.error("The XML file is invalid; %s." % (e))
self.errors += 1
def parseString (self, text, baseUrl="", ownerDoc=None):
absUrl = convertToAbsUrl ("", baseUrl)
tree = ElementTreeExtension()
treeWrapper = self.treeWrapperClass(self, tree, self.useCaching)
parser = ExtXMLTreeBuilder("", absUrl, self, treeWrapper)
parser.feed(text)
treeWrapper.getTree()._setroot(parser.close())
# XInclude support
if self.processXInclude:
loaderInst = ExtXIncludeLoader (self.parse, absUrl, ownerDoc)
ElementInclude.include(treeWrapper.getTree().getroot(), loaderInst.loader)
return treeWrapper
def main():
if len(sys.argv) != 2 or not os.path.isfile(sys.argv[1]):
print("Usage: ", sys.argv[0], "rtt_file")
sys.exit(-1)
rtt = et.parse(sys.argv[1])
pages = rtt.find("pages")
os.chdir(os.path.dirname(sys.argv[1]))
ei.include(pages)
open_mf = pages.attrib["microformatting-open"]
close_mf = pages.attrib["microformatting-close"]
pages_text = []
first_page_text = pages.find("page/text")
if first_page_text.text[0] != "\n":
first_page_text.text = "\n" + first_page_text.text
for p in pages.findall("page"):
pages_text.append(process_page(p, open_mf, close_mf, heading_regexp))
sys.stdout.write("\n".join(pages_text))
def __load_target_xml(archtype: QL_ARCH,
ostype: QL_OS) -> ElementTree.ElementTree:
filename, base_url = QlGdbFeatures.__get_xml_path(archtype)
tree = ElementTree.parse(filename)
# NOTE: this is needed to load xinclude hrefs relative to the main xml file. starting
# from python 3.9 ElementInclude.include has an argument for that called 'base_url'.
# this is a workaround for earlier python versions such as 3.8
# <WORKAROUND>
def my_loader(base: PurePath):
def __wrapped(href: str, parse, encoding=None):
abshref = base / href
return ElementInclude.default_loader(str(abshref), parse,
encoding)
return __wrapped
# </WORKAROUND>
# inline all xi:include elements
ElementInclude.include(tree.getroot(), loader=my_loader(base_url))
# patch xml osabi element with the appropriate abi tag
osabi = tree.find('osabi')
if osabi is not None:
# NOTE: the 'Windows' abi tag is supported starting from gdb 10.
# earlier gdb versions use 'Cygwin' instead
abitag = {
QL_OS.LINUX: 'GNU/Linux',
QL_OS.FREEBSD: 'FreeBSD',
QL_OS.MACOS: 'Darwin',
QL_OS.WINDOWS: 'Windows',
QL_OS.UEFI: 'Windows',
QL_OS.DOS: 'Windows',
QL_OS.QNX: 'QNX-Neutrino'
}.get(ostype, 'unknown')
osabi.text = abitag
return tree
def parseAndroidAudioPolicyConfigurationFile(audiopolicyconfigurationfile):
logging.info("Checking Audio Policy Configuration file {}".format(
audiopolicyconfigurationfile))
#
# extract all devices addresses from audio policy configuration file
#
address_criteria_mapping_table = {
'sink': "OutputDevicesAddressesType",
'source': "InputDevicesAddressesType"
}
address_criteria = {
'OutputDevicesAddressesType': [],
'InputDevicesAddressesType': []
}
old_working_dir = os.getcwd()
print("Current working directory %s" % old_working_dir)
new_dir = os.path.join(old_working_dir, audiopolicyconfigurationfile.name)
policy_in_tree = ET.parse(audiopolicyconfigurationfile)
os.chdir(os.path.dirname(os.path.normpath(new_dir)))
print("new working directory %s" % os.getcwd())
policy_root = policy_in_tree.getroot()
EI.include(policy_root)
os.chdir(old_working_dir)
for device in policy_root.iter('devicePort'):
for key in address_criteria_mapping_table.keys():
if device.get('role') == key and device.get('address'):
logging.info("{}: <{}>".format(key, device.get('address')))
address_criteria[address_criteria_mapping_table[key]].append(
device.get('address'))
for criteria in address_criteria:
values = ','.join(address_criteria[criteria])
logging.info("{}: <{}>".format(criteria, values))
return address_criteria
def parse (self, file, baseUrl="", ownerDoc=None):
absUrl = convertToAbsUrl (file, baseUrl)
fp = urllib.urlopen (absUrl)
try:
tree = ElementTreeExtension()
treeWrapper = self.treeWrapperClass(self, tree, self.useCaching)
parser = ExtXMLTreeBuilder(file, absUrl, self, treeWrapper)
treeWrapper.getTree().parse(fp, parser)
fp.close()
# XInclude support
if self.processXInclude:
loaderInst = ExtXIncludeLoader (self.parse, absUrl, ownerDoc)
try:
ElementInclude.include(treeWrapper.getTree().getroot(), loaderInst.loader)
except IOError, errInst:
raise GenXmlIfError, "%s: IOError: %s" %(file, str(errInst))
except ExpatError, errstr:
fp.close()
raise GenXmlIfError, "%s: ExpatError: %s" %(file, str(errstr))
def fromFile(self, filename):
r"""
Following is the header as given in zend-config::
/**
* fromFile(): defined by Reader interface.
*
* @see ReaderInterface::fromFile()
* @param string $filename
* @return array
* @throws Exception\RuntimeException
*/
"""
if not os.path.isfile(filename) and not os.access(filename, os.R_OK):
raise RuntimeException(
"Xml: File %s Doesn't Exist or Not Readable" % filename)
self.directory = os.path.dirname(filename.rstrip(os.sep)) or '.'
try:
xmlcontent = ''
with open(filename, "r") as file:
for line in file:
if "@include" in line:
include = line.split(":")[1].strip()
with open(os.path.join(self.directory, include),
"r") as includedfile:
for includedline in includedfile:
xmlcontent += includedline
else:
xmlcontent += line
self.root = ElementTree.fromstring(xmlcontent)
ElementInclude.include(self.root, self.loader)
except ElementTree.ParseError as e:
raise RuntimeException("Xml: Error Reading XML file \"%s\": %s" %
(filename, e))
return self.process(self.root)
def orca_et_loader(uFile, parse, encoding=None,aReplacementVars={}):
'''Custom Loader for ElementTree Include to add definition path to includes
and to make make bulk include using placeholder possible
'''
if uFile.endswith('*'):
uRet=[]
uFile2=ReplaceVars(uFile)
uDir=AdjustPathToOs(os.path.dirname(uFile2))
uPattern=uFile2[len(uDir):]
uPattern=uPattern[1:-1]
aFiles=GetFileList(uDir)
for uFile in aFiles:
if uFile.startswith(uPattern):
uLoadFile=AdjustPathToOs(uDir+u'/'+uFile)
uLoadFileRedirect=oORCA.oTheScreen.aSkinRedirects.get(uLoadFile)
if uLoadFileRedirect:
uLoadFile=AdjustPathToOs(ReplaceVars(uLoadFileRedirect))
Logger.debug (u'XML: Bulk-Loading XML Include:'+uLoadFile)
uRaw= ElementInclude.default_loader(uLoadFile, "text", encoding)
uRaw2 = ReplaceDefVars(uRaw,aReplacementVars)
uRet.append(fromstring(uRaw2))
#uRet.append(ElementInclude.default_loader(uLoadFile, parse, encoding))
if len(uRet)==0:
return None
else:
return uRet
else:
uFile2=uFile
if FileExists(uFile2):
Logger.debug (u'XML: Loading XML Include:'+uFile2)
uRaw= ElementInclude.default_loader(uFile2, "text", encoding)
uRaw2 = ReplaceDefVars(uRaw,aReplacementVars)
bRet = fromstring(uRaw2)
#bRet= ElementInclude.default_loader(uFile2, parse, encoding)
else:
Logger.warning (u'XML: Skipping XML Include (File not found):'+uFile2)
bRet=None
return bRet
import defusedxml.ElementTree as _ET
import xml.etree.ElementInclude as _ETINCLUDE
tree = _ET.parse('../../xml_files_windows/standard.xml')
root = tree.getroot()
print root.tag
print root.text
'''
# for using XInclude
# This code helped a lot with troubeshooting ElementInclude.include:
# http://stackoverflow.com/questions/23684996/using-python-elementtree-elementinclude-and-xpointer-to-access-included-xml-file
import xml.etree.ElementTree as _ET
import xml.etree.ElementInclude as _ETINCLUDE
tree = _ET.parse('../../xml_files_windows/xinclude.xml')
root = tree.getroot()
_ETINCLUDE.include(root)
elem_data = root.iter('content')
for elem in elem_data:
print elem.tag
print elem.text
'''
def runCmds():
#1517 is VDSLR2 EqptType. This is demo. We should first get the EqptType from BID
if tstItem_name is not None:
if tstItem_name.upper() == "ALL":
print g_ERR_TBD
exit(0)
cmdMapFile = None
pCmdMapping = None
boardInfo = getBidEx()
if boardInfo is not None:
if arg_plat_sw_automation:
setPlatSwAutomation()
cmdMapFile = getCmdMapFile(boardInfo['EqptType'])
if cmdMapFile is not None:
pCmdMapping = ET.parse(cmdMapFile)
# ESA-760
depth = 0
while (depth < m_XINCLUDE_DEPTH):
EI.include(pCmdMapping.getroot())
depth += 1
# debug
#ET.dump(pCmdMapping.getroot())
else:
print g_ERR_CMD_MAPPING_FILE_NOT_FOUND
exit(-1)
else:
print g_ERR_USE_DEFAULT_CMD_MAP
cmdMapFile = getCmdMapFile('1517')
if cmdMapFile is not None:
pCmdMapping = ET.parse(cmdMapFile)
else:
print g_ERR_CMD_MAPPING_FILE_NOT_FOUND
exit(-1)
bTstItem = False
for tstKey, tstVal in getTstItemMapping(boardInfo['EqptType']):
testCmd = tstKey.upper()
if testCmd == tstItem_name:
bTstItem = True
cmdParse = None
testCmd = None
childNotEmpty = False
cmdMappingList = pCmdMapping.findall(tstVal)
# ESA-760
if not cmdMappingList:
itemXPath = m_XPATH_PATTERN + tstVal
cmdMappingList = pCmdMapping.findall(itemXPath)
# ESAA-523
milog = miLog()
passCnt = 0
failCnt = 0
summaryMsg = ""
detailMsg = ""
debugMsg = ""
tstNameFmtStr = "\nTestName:[{}] \n".format(tstItem_name)
tstNameEndFmtStr = "\nTestName:[/{}] \n".format(tstItem_name)
summaryMsg = tstNameFmtStr + summaryMsg
summaryMsg = summaryMsg + g_HEADERFMTSTR
startTime = time.strftime("%a, %d %b %Y %H:%M:%S",
time.localtime(time.time()))
tmpDebugStr = ""
tmpDetailStr = ""
if arg_dump_single_dbg:
milog.dumpTest(tstItem_name)
continue
if arg_dump_single_detail:
milog.dumpTest(tstItem_name, g_DUMP_DETAIL_STR)
continue
# ESA-1227
debugMsg = tstNameFmtStr
milog.prt_debug(debugMsg)
# ESA-747
if not cmdMappingList:
testResult = g_cmp_FAIL
tmpDebugStr = g_ERR_ITEM_NOT_FOUND_F(cmdMapFile)
else:
# # ESA-1227
detailMsg = tstNameFmtStr
milog.prt_detail(detailMsg)
# debugMsg = tstNameFmtStr
# milog.prt_debug(debugMsg)
testResult = g_cmp_PASS
# ESA-1476. Only get the last item as the findall returns a list
# containing all matching elements in *document* order.
cmdMappingList = cmdMappingList[-1:]
for cmdMappingElem in cmdMappingList:
for child in cmdMappingElem.getchildren():
#print child.attrib['name'],':',child.text.strip()
if cmdParse is None:
childNotEmpty = True
cmdParse = testCmdParse(child)
else:
cmdParse.add(child)
if cmdParse:
if cmdParse.ready():
testCmdHandler = cmdParse.getCmdHandler()
if testCmdHandler is not None:
testCmdHandler.preProcess(verbose=arg_verbose, \
rstshown=arg_rstShown, killcard=arg_forced,\
repeated=arg_repeated)
testCmdHandler.process()
# ESAA-480
tmpResult = testCmdHandler.postProcess()
# ESA-1227
#tmpDetailStr = testCmdHandler.getDetailMsg()
# ESA-1283. Move log from the end to here since there
# is one case of hybrid(e.g. SGMIIKA2CPU test which is
# the combination of BCM and linux commands).
# EX-25985 does the same as debug log(add ending label)
# to get the detail information for the phyconn test
# if this test pass.
#tmpDetailStr = tmpDetailStr + tstNameEndFmtStr
#milog.prt_detail(tmpDetailStr)
if tmpResult == g_cmp_FAIL:
testResult = g_cmp_FAIL
# ESAA-523
#if testCmdHandler.getDebugMsg() is not None:
# tmpDebugStr = tmpDebugStr + testCmdHandler.getDebugMsg()
# EX-25985
#tmpDebugStr = tmpDebugStr + tstNameEndFmtStr
# ESA-1283 Put log there since there is one hybrid case.
#milog.prt_debug(tmpDebugStr)
cmdParse = None
else:
print g_ERR_HANDLER_NOT_FOUND
else:
print g_ERR_TEST_CMD_EMPTY
#The cmdParse should be None. If it's not, there is one possibility
#that the value of next in last command of config xml file(config/xxx.xml)
#is still yes. To cover this inadvertent incorrectness, add code below
if cmdParse is not None:
#No ready() invoked. Forced to run the handler
testCmdHandler = cmdParse.getCmdHandler()
if testCmdHandler is not None:
testCmdHandler.preProcess(verbose=arg_verbose, \
rstshown=arg_rstShown, killcard=arg_forced,\
repeated=arg_repeated)
testCmdHandler.process()
# ESAA-480
tmpResult = testCmdHandler.postProcess()
#tmpDetailStr = testCmdHandler.getDetailMsg()
# ESA-1283
# EX-25985 does the same as debug log(add ending label)
#tmpDetailStr = tmpDetailStr + tstNameEndFmtStr
#milog.prt_detail(tmpDetailStr)
if tmpResult == g_cmp_FAIL:
testResult = g_cmp_FAIL
# ESAA-523
#tmpDebugStr = tmpDebugStr + testCmdHandler.getDebugMsg()
# EX-25985
#tmpDebugStr = tmpDebugStr + tstNameEndFmtStr
# ESA-1283
#milog.prt_debug(tmpDebugStr)
cmdParse = None
else:
print g_ERR_HANDLER_NOT_FOUND
if childNotEmpty:
tmpDetailStr = testCmdHandler.getDetailMsg()
# ESA-1283. Move log from the end to here since there
# is one case of hybrid(e.g. SGMIIKA2CPU test which is
# the combination of BCM and linux commands).
# EX-25985 does the same as debug log(add ending label)
# to get the detail information for the phyconn test
# if this test pass.
tmpDetailStr = tmpDetailStr + tstNameEndFmtStr
milog.prt_detail(tmpDetailStr)
if testResult == g_cmp_FAIL:
tmpDebugStr = tmpDebugStr + testCmdHandler.getDebugMsg(
)
if testResult == g_cmp_FAIL:
# ESAA-523
#if testCmdHandler.getDebugMsg() is not None:
#tmpDebugStr = tmpDebugStr + testCmdHandler.getDebugMsg()
# EX-25985
tmpDebugStr = tmpDebugStr + tstNameEndFmtStr
# ESA-1283 Put log there since there is one hybrid case.
milog.prt_debug(tmpDebugStr)
# ESAA-523
endTime = time.strftime("%a, %d %b %Y %H:%M:%S",
time.localtime(time.time()))
if testResult == g_cmp_PASS:
passCnt += 1
else:
failCnt += 1
tmpStr = "| {:>4} | {:>4} | {} | {} |\n".format(
str(passCnt), str(failCnt), startTime, endTime)
summaryMsg = summaryMsg + tmpStr
summaryMsg = summaryMsg + g_FOOTERFMRSTR
milog.prt_summary(summaryMsg)
# ESAA-480
if arg_rstShown:
print testResult
if bTstItem == False:
if tstItem_name is None:
usage()
else:
print g_ERR_TEST_ITEM_NOT_FOUND
def XInclude_Tutorial(file):
tree = ET.parse(file)
root = tree.getroot()
EI.include(root)
tree.write('include.xml')
def parse_xml(fname):
"""Returns a parsed xml tree"""
tree = ElementTree.parse(fname)
root = tree.getroot()
ElementInclude.include(root)
return tree
def load_menus(path):
"""Load the file path."""
menus = ElementTree.parse(path)
ElementInclude.include(menus.getroot(), loader=Loader(path))
return menus
def __wrapped(href: str, parse, encoding=None):
abshref = base / href
return ElementInclude.default_loader(str(abshref), parse,
encoding)
def _loader(self, href, parse, encoding=None):
return ElementInclude.default_loader(self._path_map[href], parse,
encoding)
def LoadDocument(self, path: str) -> document.Document:
tree = ET.parse(path)
root = tree.getroot()
ElementInclude.include(root, self._loader)
return parser.ParseDocument(root)
def LoadNav(self, path: str) -> List[nav.NavItem]:
tree = ET.parse(path)
root = tree.getroot()
ElementInclude.include(root, self._loader)
return parser.ParseNav(root)
#!/usr/bin/python3
import xml.etree.ElementTree as et
import xml.etree.ElementInclude as ei
import sys
rtt = et.parse(sys.argv[1])
ei.include(rtt.getroot())
error_found = False
for page in rtt.findall(".//page"):
messages = []
img_lines = len(page.find("image/lines").text.split(","))
text = page.find("text").text
text_lines = len([X for X in text.splitlines() if len(X)])
if(img_lines != text_lines):
messages.append("Line count mismatch: image %d text %d" % (img_lines, text_lines))
if text.find("'") != -1:
messages.append("Single straight quote found")
if text.find('"') != -1:
messages.append("Double straight quote found")
if text.find("--") != -1:
messages.append("Double hyphen found")
if messages:
error_found = True
print(page.attrib["id"])
for m in messages:
print(" ", m)
if not error_found:
print("No errors found")
# -*- coding: utf-8 -*-
# Author: hkey
import xml.etree.ElementInclude as ET
tree = ET.parse('test.xml')
root = tree.getroot()
print(root.tag)
import defusedxml.ElementTree as _ET
import xml.etree.ElementInclude as _ETINCLUDE
tree = _ET.parse('../../xml_files_windows/standard.xml')
root = tree.getroot()
print root.tag
print root.text
'''
# for using XInclude
# This code helped a lot with troubeshooting ElementInclude.include:
# http://stackoverflow.com/questions/23684996/using-python-elementtree-elementinclude-and-xpointer-to-access-included-xml-file
import xml.etree.ElementTree as _ET
import xml.etree.ElementInclude as _ETINCLUDE
tree = _ET.parse('../../xml_files_windows/xinclude.xml')
root = tree.getroot()
_ETINCLUDE.include(root)
elem_data = root.iter('content')
for elem in elem_data:
print elem.tag
print elem.text
'''
class CommentedTreeBuilder(XmlET.TreeBuilder):
# Python 2.7 uses ElementTree 1.3.x.
def comment(self, data):
self.start(XmlET.Comment, {})
self.data(data)
self.end(XmlET.Comment)
def parse_xml(file_name, lh, include_comments=False):
"""Returns a parsed xml tree with comments intact."""
fh = open(file_name, 'r')
try:
if include_comments:
tree = XmlET.parse(
fh, parser=XmlET.XMLParser(target=CommentedTreeBuilder()))
else:
tree = XmlET.parse(
fh, parser=XmlET.XMLParser(target=DoctypeSafeCallbackTarget()))
except Exception, e:
fh.close()
lh.write("Exception attempting to parse %s:\n%s\n\n" %
(file_name, str(e)))
return None
fh.close()
root = tree.getroot()
ElementInclude.include(root)
return tree
def _parse_xml(fname):
tree = ElementTree.parse(fname)
root = tree.getroot()
ElementInclude.include(root)
return tree
def doctype(*args):
pass
class CommentedTreeBuilder(XmlET.TreeBuilder):
# Python 2.7 uses ElementTree 1.3.x.
def comment(self, data):
self.start(XmlET.Comment, {})
self.data(data)
self.end(XmlET.Comment)
def parse_xml(file_name, lh, include_comments=False):
"""Returns a parsed xml tree with comments intact."""
fh = open(file_name, 'r')
try:
if include_comments:
tree = XmlET.parse(fh, parser=XmlET.XMLParser(target=CommentedTreeBuilder()))
else:
tree = XmlET.parse(fh, parser=XmlET.XMLParser(target=DoctypeSafeCallbackTarget()))
except Exception, e:
fh.close()
lh.write("Exception attempting to parse %s:\n%s\n\n" % (file_name, str(e)))
return None
fh.close()
root = tree.getroot()
ElementInclude.include(root)
return tree
def _parse_xml(fname):
tree = ElementTree.parse(fname)
root = tree.getroot()
ElementInclude.include(root)
return tree
def parse2tok(p, tmap, pel=False):
tree = ET.parse(p)
cwd=os.getcwd()
os.chdir(os.path.dirname(p))
root = tree.getroot()
EI.include(root)
parent_map = {c: p for p in root.iter() for c in p}
ls = root.findall(f'.//{tei_xmlns}line')
if len(ls) == 0:
ls = root.findall(f'.//{tei_xmlns}seg')
if len(ls) == 0:
ls = root.findall(f'.//{tei_xmlns}l')
if len(ls) == 0:
ls = root.findall(f'.//{tei_xmlns}p')
tok=[]
divs=[]
if ls[0].tag.endswith('p'):
tl=[]
for b in ls:
res=[]
p_content(b, res)
tl.append(res)
return tl, ["p"]
for b in ls:
p=parent_map[b]
if pel:
px = p.tag.replace(f'{tei_xmlns}', '') + "/"
else:
px = ""
if (p.tag == '{http://www.tei-c.org/ns/1.0}head'):
pdiv = parent_map[p]
if f'{xml_xmlns}id' in pdiv.attrib:
pdivid=pdiv.attrib[f'{xml_xmlns}id']
else:
pdivid=''
divs.append((len(tok), b.text, pdivid))
pm=[p]
while p in parent_map:
p=parent_map[p]
pm.append(p)
px="p"
for p in pm:
#print(p.tag)
if p.tag in tmap:
px = tmap[p.tag][1]
break
#tag = b.tag.replace(f'{tei_xmlns}', '')
tag=""
if "rend" in b.attrib:
tag = ";" + b.attrib["rend"]
if f'{xml_xmlns}id' in b.attrib:
id=b.attrib[f'{xml_xmlns}id']
else:
id="noid"
tx = linechildren(b)
tx = tx.replace("\n", "")
seq=line2arr(tx)
cnt = 0
for s in seq:
cnt += 1
tok.append((px + tag, id, cnt, s))
os.chdir(cwd)
return (tok, divs)
# 遍历xml文件
def traverseXml(element):
# print (len(element))
if len(element) > 0:
for child in element:
print(child.tag, "----", child.attrib)
traverseXml(child)
if __name__ == "__main__":
xmlFilePath = os.path.abspath(
"F:/Github/DL-data-processing-methods/XML/test.xml")
print(xmlFilePath)
try:
tree = ET.parse(xmlFilePath)
print("tree type:", type(tree))
# 获得根节点
root = tree.getroot()
except Exception as e: # 捕获除与程序退出sys.exit()相关之外的所有异常
print("parse test.xml fail!")
sys.exit()
print("root type:", type(root))
print(root.tag, "----", root.attrib)
# 遍历root的下一层
for child in root:
print("遍历root的下一层", child.tag, "----", child.attrib)
# 使用下标访问
def __call__(self, href, typ, encoding=None):
"""Fix relative references and call the default loader."""
return ElementInclude.default_loader(join(self.base, href), typ,
encoding)
