def check_config_xml(self, contents):
"""
Check whether the given XML config file contents
is well-formed and it has all the required parameters.
:param string contents: the XML config file contents or XML config string
:param bool is_config_string: if ``True``, contents is a config string
:rtype: :class:`~aeneas.validator.ValidatorResult`
"""
self.log(u"Checking contents XML config file")
self.result = ValidatorResult()
if self._are_safety_checks_disabled(u"check_config_xml"):
return self.result
contents = gf.safe_bytes(contents)
self.log(u"Checking that contents is well formed")
self.check_raw_string(contents, is_bstring=True)
if not self.result.passed:
return self.result
self.log(u"Checking required parameters for job")
job_parameters = gf.config_xml_to_dict(contents, self.result, parse_job=True)
self._check_required_parameters(self.XML_JOB_REQUIRED_PARAMETERS, job_parameters)
if not self.result.passed:
return self.result
self.log(u"Checking required parameters for task")
tasks_parameters = gf.config_xml_to_dict(contents, self.result, parse_job=False)
for parameters in tasks_parameters:
self.log([u"Checking required parameters for task: '%s'", parameters])
self._check_required_parameters(self.XML_TASK_REQUIRED_PARAMETERS, parameters)
if not self.result.passed:
return self.result
return self.result
def test_config_xml_to_dict_task(self):
tests = [
(None, []),
(u"", []),
(u"<job></job>", []),
(u"<job><k1>v1</k1></job>", []),
(u"<job><k1>v1</k1><k2></k2></job>", []),
(u"<job><tasks></tasks></job>", []),
(u"<job><tasks><foo></foo></tasks></job>", []),
(u"<job><tasks><task></task></tasks></job>", [{}]),
(u"<job><tasks><task></task><foo></foo></tasks></job>", [{}]),
(u"<job><tasks><task></task><foo></foo><task></task></tasks></job>", [{}, {}]),
(u"<job><tasks><task><k1></k1></task><foo></foo></tasks></job>", [{}]),
(u"<job><tasks><task><k1>v1</k1></task></tasks></job>", [{u"k1": u"v1"}]),
(u"<job><tasks><task><k1>v1</k1><k2>v2</k2></task></tasks></job>", [{u"k1": u"v1", u"k2": u"v2"}]),
(u"<job><tasks><task><k1>v1</k1><k2> v2</k2></task></tasks></job>", [{u"k1": u"v1", u"k2": u"v2"}]),
(u"<job><tasks><task><k1>v1</k1><k2> v2 </k2></task></tasks></job>", [{u"k1": u"v1", u"k2": u"v2"}]),
(u"<job><tasks><task><k1>v1</k1><k2>v2 </k2></task></tasks></job>", [{u"k1": u"v1", u"k2": u"v2"}]),
(
u"<job><tasks><task><k1>v1</k1></task><task><k2>v2</k2></task></tasks></job>",
[{u"k1": u"v1"}, {u"k2": u"v2"}],
),
(
u"<job><tasks><task><k1>v1</k1></task><task><k2>v2</k2></task><task></task></tasks></job>",
[{u"k1": u"v1"}, {u"k2": u"v2"}, {}],
),
]
for test in tests:
self.assertEqual(gf.config_xml_to_dict(test[0], result=None, parse_job=False), test[1])
def test_config_xml_to_dict_job(self):
tests = [
(None, {}),
(u"", {}),
(u"<job></job>", {}),
(u"<job><k1>v1</k1></job>", {
u"k1": u"v1"
}),
(u"<job><k1>v1</k1><k2></k2></job>", {
u"k1": u"v1"
}),
(u"<job><k1>v1</k1><k2> </k2></job>", {
u"k1": u"v1"
}),
(u"<job><k1>v1</k1><k2>v2</k2></job>", {
u"k1": u"v1",
u"k2": u"v2"
}),
(u"<job><k1>v1</k1><k2> v2</k2></job>", {
u"k1": u"v1",
u"k2": u"v2"
}),
(u"<job><k1>v1</k1><k2> v2 </k2></job>", {
u"k1": u"v1",
u"k2": u"v2"
}),
(u"<job><k1>v1</k1><k2>v2 </k2></job>", {
u"k1": u"v1",
u"k2": u"v2"
}),
]
for test in tests:
self.assertEqual(
gf.config_xml_to_dict(test[0], result=None, parse_job=True),
test[1])
def test_config_xml_to_dict_task(self):
tests = [
(None, []),
(u"", []),
(u"<job></job>", []),
(u"<job><k1>v1</k1></job>", []),
(u"<job><k1>v1</k1><k2></k2></job>", []),
(u"<job><tasks></tasks></job>", []),
(u"<job><tasks><foo></foo></tasks></job>", []),
(u"<job><tasks><task></task></tasks></job>", [{}]),
(u"<job><tasks><task></task><foo></foo></tasks></job>", [{}]),
(u"<job><tasks><task></task><foo></foo><task></task></tasks></job>",
[{}, {}]),
(u"<job><tasks><task><k1></k1></task><foo></foo></tasks></job>",
[{}]),
(u"<job><tasks><task><k1>v1</k1></task></tasks></job>", [{
u"k1":
u"v1"
}]),
(u"<job><tasks><task><k1>v1</k1><k2>v2</k2></task></tasks></job>",
[{
u"k1": u"v1",
u"k2": u"v2"
}]),
(u"<job><tasks><task><k1>v1</k1><k2> v2</k2></task></tasks></job>",
[{
u"k1": u"v1",
u"k2": u"v2"
}]),
(u"<job><tasks><task><k1>v1</k1><k2> v2 </k2></task></tasks></job>",
[{
u"k1": u"v1",
u"k2": u"v2"
}]),
(u"<job><tasks><task><k1>v1</k1><k2>v2 </k2></task></tasks></job>",
[{
u"k1": u"v1",
u"k2": u"v2"
}]),
(u"<job><tasks><task><k1>v1</k1></task><task><k2>v2</k2></task></tasks></job>",
[{
u"k1": u"v1"
}, {
u"k2": u"v2"
}]),
(u"<job><tasks><task><k1>v1</k1></task><task><k2>v2</k2></task><task></task></tasks></job>",
[{
u"k1": u"v1"
}, {
u"k2": u"v2"
}, {}]),
]
for test in tests:
self.assertEqual(
gf.config_xml_to_dict(test[0], result=None, parse_job=False),
test[1])
def test_config_xml_to_dict_job(self):
tests = [
(None, {}),
(u"", {}),
(u"<job></job>", {}),
(u"<job><k1>v1</k1></job>", {u"k1": u"v1"}),
(u"<job><k1>v1</k1><k2></k2></job>", {u"k1": u"v1"}),
(u"<job><k1>v1</k1><k2> </k2></job>", {u"k1": u"v1"}),
(u"<job><k1>v1</k1><k2>v2</k2></job>", {u"k1": u"v1", u"k2": u"v2"}),
(u"<job><k1>v1</k1><k2> v2</k2></job>", {u"k1": u"v1", u"k2": u"v2"}),
(u"<job><k1>v1</k1><k2> v2 </k2></job>", {u"k1": u"v1", u"k2": u"v2"}),
(u"<job><k1>v1</k1><k2>v2 </k2></job>", {u"k1": u"v1", u"k2": u"v2"}),
]
for test in tests:
self.assertEqual(gf.config_xml_to_dict(test[0], result=None, parse_job=True), test[1])
def _analyze_xml_config(self, config_contents=None):
"""
Analyze the given container and return the corresponding job.
If ``config_contents`` is ``None``,
try reading it from the XML config file inside the container.
:param string config_contents: the contents of the XML config file
:rtype: :class:`~aeneas.job.Job`
"""
self.log(u"Analyzing container with XML config string")
if config_contents is None:
self.log(u"Analyzing container with XML config file")
config_entry = self.container.entry_config_xml
self.log([u"Found XML config entry '%s'", config_entry])
config_dir = os.path.dirname(config_entry)
self.log([u"Directory of XML config entry: '%s'", config_dir])
self.log([u"Reading XML config entry: '%s'", config_entry])
config_contents = self.container.read_entry(config_entry)
else:
self.log(u"Analyzing container with XML config contents")
config_dir = ""
self.log(u"Converting config contents into job config dict")
job_parameters = gf.config_xml_to_dict(
config_contents,
result=None,
parse_job=True
)
self.log(u"Converting config contents into tasks config dict")
tasks_parameters = gf.config_xml_to_dict(
config_contents,
result=None,
parse_job=False
)
self.log(u"Calculating the path of the sync map root directory")
sync_map_root_directory = gf.norm_join(
config_dir,
job_parameters[gc.PPN_JOB_OS_HIERARCHY_PREFIX]
)
job_os_hierarchy_type = job_parameters[gc.PPN_JOB_OS_HIERARCHY_TYPE]
self.log([u"Path of the sync map root directory: '%s'", sync_map_root_directory])
self.log(u"Converting job config dict into job config string")
config_string = gf.config_dict_to_string(job_parameters)
job = Job(config_string)
for task_parameters in tasks_parameters:
self.log(u"Converting task config dict into task config string")
config_string = gf.config_dict_to_string(task_parameters)
self.log([u"Creating task with config string '%s'", config_string])
try:
custom_id = task_parameters[gc.PPN_TASK_CUSTOM_ID]
except KeyError:
custom_id = ""
task_info = [
custom_id,
gf.norm_join(
config_dir,
task_parameters[gc.PPN_TASK_IS_TEXT_FILE_XML]
),
gf.norm_join(
config_dir,
task_parameters[gc.PPN_TASK_IS_AUDIO_FILE_XML]
)
]
self.log([u"Creating task: '%s'", str(task_info)])
task = self._create_task(
task_info,
config_string,
sync_map_root_directory,
job_os_hierarchy_type
)
job.add_task(task)
return job
def _analyze_xml_config(self, config_contents=None):
"""
Analyze the given container and return the corresponding job.
If ``config_contents`` is ``None``,
try reading it from the XML config file inside the container.
:param config_contents: the contents of the XML config file
:type config_contents: string
:rtype: :class:`aeneas.job.Job`
"""
# TODO break this function down into smaller functions
self._log("Analyzing container with XML config string")
if config_contents is None:
self._log("Analyzing container with XML config file")
config_entry = self.container.entry_config_xml
self._log(["Found XML config entry '%s'", config_entry])
config_dir = os.path.dirname(config_entry)
self._log(["Directory of XML config entry: '%s'", config_dir])
self._log(["Reading XML config entry: '%s'", config_entry])
config_contents = self.container.read_entry(config_entry)
else:
self._log("Analyzing container with XML config contents")
config_dir = ""
# remove BOM
#self._log("Removing BOM")
#config_contents = gf.remove_bom(config_contents)
# get the job parameters and tasks parameters
self._log("Converting config contents into job config dict")
job_parameters = gf.config_xml_to_dict(
config_contents,
result=None,
parse_job=True
)
self._log("Converting config contents into tasks config dict")
tasks_parameters = gf.config_xml_to_dict(
config_contents,
result=None,
parse_job=False
)
# compute the root directory for the sync map files
self._log("Calculating the path of the sync map root directory")
sync_map_root_directory = gf.norm_join(
config_dir,
job_parameters[gc.PPN_JOB_OS_HIERARCHY_PREFIX]
)
job_os_hierarchy_type = job_parameters[gc.PPN_JOB_OS_HIERARCHY_TYPE]
self._log(["Path of the sync map root directory: '%s'", sync_map_root_directory])
# create the Job object to be returned
self._log("Converting job config dict into job config string")
config_string = gf.config_dict_to_string(job_parameters)
job = Job(config_string)
# create the Task objects
for task_parameters in tasks_parameters:
self._log("Converting task config dict into task config string")
config_string = gf.config_dict_to_string(task_parameters)
self._log(["Creating task with config string '%s'", config_string])
try:
custom_id = task_parameters[gc.PPN_TASK_CUSTOM_ID]
except KeyError:
custom_id = ""
task_info = [
custom_id,
gf.norm_join(
config_dir,
task_parameters[gc.PPN_TASK_IS_TEXT_FILE_XML]
),
gf.norm_join(
config_dir,
task_parameters[gc.PPN_TASK_IS_AUDIO_FILE_XML]
)
]
self._log(["Creating task: '%s'", str(task_info)])
task = self._create_task(
task_info,
config_string,
sync_map_root_directory,
job_os_hierarchy_type
)
job.add_task(task)
# return the Job
return job
def check_contents_xml_config_file(self, config_contents):
"""
Check whether the given XML config contents
is well formed and contains all the requested parameters.
:param config_contents:
:type config_contents: string
:rtype: :class:`aeneas.validator.ValidatorResult`
"""
self._log("Checking contents XML config file")
result = ValidatorResult()
# remove BOM, if any
#self._log("Removing BOM")
#config_contents = gf.remove_bom(config_contents)
# check if it is well encoded
result = self.check_string_well_encoded(config_contents)
if not result.passed:
self._log("Failed")
return result
# check required parameters for the job section
self._log("Checking required parameters for job")
required_parameters = [
gc.PPN_JOB_OS_FILE_NAME,
gc.PPN_JOB_OS_CONTAINER_FORMAT,
gc.PPN_JOB_OS_HIERARCHY_TYPE,
gc.PPN_JOB_OS_HIERARCHY_PREFIX
]
job_parameters = gf.config_xml_to_dict(
config_contents,
result,
parse_job=True
)
self._check_required_parameters(
required_parameters,
job_parameters,
result
)
if not result.passed:
self._log("Failed")
return result
# check required parameters for each task section
self._log("Checking required parameters for task")
required_parameters = [
gc.PPN_TASK_LANGUAGE,
gc.PPN_TASK_IS_TEXT_FILE_FORMAT,
gc.PPN_TASK_IS_TEXT_FILE_XML,
gc.PPN_TASK_IS_AUDIO_FILE_XML,
gc.PPN_TASK_OS_FILE_NAME,
gc.PPN_TASK_OS_FILE_FORMAT,
]
tasks_parameters = gf.config_xml_to_dict(
config_contents,
result,
parse_job=False
)
for parameters in tasks_parameters:
self._log(["Checking required parameters for task: '%s'", parameters])
self._check_required_parameters(
required_parameters,
parameters,
result
)
if not result.passed:
self._log("Failed")
return result
# return result
self._log(["Checking contents XML config file: returning %s", result.passed])
return result
def check_contents_xml_config_file(self, config_contents):
"""
Check whether the given XML config contents
is well formed and contains all the requested parameters.
:param config_contents:
:type config_contents: string
:rtype: :class:`aeneas.validator.ValidatorResult`
"""
self._log("Checking contents XML config file")
result = ValidatorResult()
# remove BOM, if any
#self._log("Removing BOM")
#config_contents = gf.remove_bom(config_contents)
# check if it is well encoded
result = self.check_string_well_encoded(config_contents)
if not result.passed:
self._log("Failed")
return result
# check required parameters for the job section
self._log("Checking required parameters for job")
required_parameters = [
gc.PPN_JOB_OS_FILE_NAME, gc.PPN_JOB_OS_CONTAINER_FORMAT,
gc.PPN_JOB_OS_HIERARCHY_TYPE, gc.PPN_JOB_OS_HIERARCHY_PREFIX
]
job_parameters = gf.config_xml_to_dict(config_contents,
result,
parse_job=True)
self._check_required_parameters(required_parameters, job_parameters,
result)
if not result.passed:
self._log("Failed")
return result
# check required parameters for each task section
self._log("Checking required parameters for task")
required_parameters = [
gc.PPN_TASK_LANGUAGE,
gc.PPN_TASK_IS_TEXT_FILE_FORMAT,
gc.PPN_TASK_IS_TEXT_FILE_XML,
gc.PPN_TASK_IS_AUDIO_FILE_XML,
gc.PPN_TASK_OS_FILE_NAME,
gc.PPN_TASK_OS_FILE_FORMAT,
]
tasks_parameters = gf.config_xml_to_dict(config_contents,
result,
parse_job=False)
for parameters in tasks_parameters:
self._log(
["Checking required parameters for task: '%s'", parameters])
self._check_required_parameters(required_parameters, parameters,
result)
if not result.passed:
self._log("Failed")
return result
# return result
self._log(
["Checking contents XML config file: returning %s", result.passed])
return result
def _analyze_xml_config(self, config_contents=None):
"""
Analyze the given container and return the corresponding job.
If ``config_contents`` is ``None``,
try reading it from the XML config file inside the container.
:param string config_contents: the contents of the XML config file
:rtype: :class:`~aeneas.job.Job`
"""
self.log(u"Analyzing container with XML config string")
if config_contents is None:
self.log(u"Analyzing container with XML config file")
config_entry = self.container.entry_config_xml
self.log([u"Found XML config entry '%s'", config_entry])
config_dir = os.path.dirname(config_entry)
self.log([u"Directory of XML config entry: '%s'", config_dir])
self.log([u"Reading XML config entry: '%s'", config_entry])
config_contents = self.container.read_entry(config_entry)
else:
self.log(u"Analyzing container with XML config contents")
config_dir = ""
self.log(u"Converting config contents into job config dict")
job_parameters = gf.config_xml_to_dict(config_contents,
result=None,
parse_job=True)
self.log(u"Converting config contents into tasks config dict")
tasks_parameters = gf.config_xml_to_dict(config_contents,
result=None,
parse_job=False)
self.log(u"Calculating the path of the sync map root directory")
sync_map_root_directory = gf.norm_join(
config_dir, job_parameters[gc.PPN_JOB_OS_HIERARCHY_PREFIX])
job_os_hierarchy_type = job_parameters[gc.PPN_JOB_OS_HIERARCHY_TYPE]
self.log([
u"Path of the sync map root directory: '%s'",
sync_map_root_directory
])
self.log(u"Converting job config dict into job config string")
config_string = gf.config_dict_to_string(job_parameters)
job = Job(config_string)
for task_parameters in tasks_parameters:
self.log(u"Converting task config dict into task config string")
config_string = gf.config_dict_to_string(task_parameters)
self.log([u"Creating task with config string '%s'", config_string])
try:
custom_id = task_parameters[gc.PPN_TASK_CUSTOM_ID]
except KeyError:
custom_id = ""
task_info = [
custom_id,
gf.norm_join(config_dir,
task_parameters[gc.PPN_TASK_IS_TEXT_FILE_XML]),
gf.norm_join(config_dir,
task_parameters[gc.PPN_TASK_IS_AUDIO_FILE_XML])
]
self.log([u"Creating task: '%s'", str(task_info)])
task = self._create_task(task_info, config_string,
sync_map_root_directory,
job_os_hierarchy_type)
job.add_task(task)
return job
def _analyze_xml_config(self, config_contents=None):
"""
Analyze the given container and return the corresponding job.
If ``config_contents`` is ``None``,
try reading it from the XML config file inside the container.
:param config_contents: the contents of the XML config file
:type config_contents: string
:rtype: :class:`aeneas.job.Job`
"""
# TODO break this function down into smaller functions
self._log("Analyzing container with XML config string")
if config_contents is None:
self._log("Analyzing container with XML config file")
config_entry = self.container.entry_config_xml
self._log(["Found XML config entry '%s'", config_entry])
config_dir = os.path.dirname(config_entry)
self._log(["Directory of XML config entry: '%s'", config_dir])
self._log(["Reading XML config entry: '%s'", config_entry])
config_contents = self.container.read_entry(config_entry)
else:
self._log("Analyzing container with XML config contents")
config_dir = ""
# remove BOM
#self._log("Removing BOM")
#config_contents = gf.remove_bom(config_contents)
# get the job parameters and tasks parameters
self._log("Converting config contents into job config dict")
job_parameters = gf.config_xml_to_dict(config_contents,
result=None,
parse_job=True)
self._log("Converting config contents into tasks config dict")
tasks_parameters = gf.config_xml_to_dict(config_contents,
result=None,
parse_job=False)
# compute the root directory for the sync map files
self._log("Calculating the path of the sync map root directory")
sync_map_root_directory = gf.norm_join(
config_dir, job_parameters[gc.PPN_JOB_OS_HIERARCHY_PREFIX])
job_os_hierarchy_type = job_parameters[gc.PPN_JOB_OS_HIERARCHY_TYPE]
self._log([
"Path of the sync map root directory: '%s'",
sync_map_root_directory
])
# create the Job object to be returned
self._log("Converting job config dict into job config string")
config_string = gf.config_dict_to_string(job_parameters)
job = Job(config_string)
# create the Task objects
for task_parameters in tasks_parameters:
self._log("Converting task config dict into task config string")
config_string = gf.config_dict_to_string(task_parameters)
self._log(["Creating task with config string '%s'", config_string])
try:
custom_id = task_parameters[gc.PPN_TASK_CUSTOM_ID]
except KeyError:
custom_id = ""
task_info = [
custom_id,
gf.norm_join(config_dir,
task_parameters[gc.PPN_TASK_IS_TEXT_FILE_XML]),
gf.norm_join(config_dir,
task_parameters[gc.PPN_TASK_IS_AUDIO_FILE_XML])
]
self._log(["Creating task: '%s'", str(task_info)])
task = self._create_task(task_info, config_string,
sync_map_root_directory,
job_os_hierarchy_type)
job.add_task(task)
# return the Job
return job
