def replace(self, pos: int, new_step: Step):
if pos >= len(self):
logMsg(
self,
'insert position is greater than the current length of steps. Append to the end instead.'
)
self.append(new_step)
elif pos < 0:
logMsg(
self,
'The position to delete is greater than the current length of steps. Ignore this command.'
)
return
else:
old_name = self.steps[pos].name
self.steps[pos] = new_step
new_step.pos_id = pos
new_step.setWorkflow(self)
if pos > 0:
self.steps[pos - 1].setNextStep(self.steps[pos])
self.steps[pos].setPreviousStep(self.steps[pos - 1])
if pos < len(self) - 1:
self.steps[pos].setNextStep(self.steps[pos + 1])
self.steps[pos + 1].setPreviousStep(self.steps[pos])
del self.name_dict[old_name]
self.name_dict[new_step.name] = pos
pass
def remove(self, pos: int):
if pos >= len(self):
logMsg(
self,
'The position to delete is greater than the current length of steps. Ignore this command.'
)
return
elif pos < 0:
logMsg(
self,
'The position to delete is greater than the current length of steps. Ignore this command.'
)
return
else:
self.steps.__delitem__(pos)
if pos > 0:
self.steps[pos - 1].setNextStep(self.steps[pos])
for step_id in range(pos, len(self)):
step = self.steps[step_id]
step.pos_id = step_id
step.setPreviousStep(self.steps[pos - 1])
if step_id < len(self) - 1:
step.setNextStep(self.steps[pos + 1])
self.name_dict[step.name] = step_id
pass
def load(self, config_file):
if not os.path.isfile(config_file):
current_dir = os.getcwd()
logMsg('current_dir=' + current_dir)
root_pos = current_dir.rfind(os.sep + 'SmartAnno' + os.sep)
root = current_dir[:root_pos + 11] if root_pos > 0 else current_dir
self.root = root
logMsg('root=' + root)
config_file = os.path.join(root, config_file)
if os.path.isfile(config_file):
with open(config_file, 'r') as f:
ConfigReader.configurations = json.load(f)
else:
if not os.path.exists(os.path.join(root, 'conf')):
os.makedirs(os.path.join(root, 'conf'))
file_name = 'smartanno_conf.json'
conf_path = os.path.join(self.root, 'conf')
if not os.path.exists(os.path.join(conf_path, file_name)):
shutil.copyfile(self.getDefaultResourceFile(file_name + '.bk'),
config_file)
with open(config_file, 'r') as f:
ConfigReader.configurations = json.load(f)
logError('File "' + config_file + '" doesn\'t exist, create ' +
os.path.abspath(config_file) + ' using default settings.')
ConfigReader.config_file = config_file
self.setUpDirs()
self.dumpDefaultRules()
def saveToWhoosh(self, df, dataset_id, overwrite=False):
# use whoosh search engine to enable full text search
if not os.path.exists(self.whoosh_root):
os.mkdir(self.whoosh_root)
ws_path = os.path.join(self.whoosh_root, dataset_id)
if not os.path.exists(ws_path):
os.mkdir(ws_path)
logMsg(
str(os.path.abspath(ws_path)) +
' does not exist, create it to store whoosh index')
overwrite = True
elif overwrite:
shutil.rmtree(ws_path)
os.mkdir(ws_path)
schema = Schema(DOC_ID=NUMERIC(stored=True), TEXT=TEXT)
if overwrite:
ix = create_in(ws_path, schema)
else:
ix = open_dir(ws_path)
writer = AsyncWriter(ix)
with self.workflow.dao.create_session() as session:
doc_iter = session.query(Document).filter(
Document.DATASET_ID == dataset_id)
for doc in doc_iter:
writer.add_document(DOC_ID=doc.DOC_ID, TEXT=doc.TEXT)
writer.commit()
pass
def complete(self):
clear_output(True)
if self.next_step is not None:
logMsg((self, 'workflow complete'))
if isinstance(self.next_step, Step):
if self.workflow is not None:
self.workflow.updateStatus(self.next_step.pos_id)
self.next_step.start()
else:
raise TypeError(
'Type error for ' + self.name +
'\'s next_step. Only Step can be the next_step, where its next_step is '
+ str(type(self.next_step)))
else:
print("next step hasn't been set.")
pass
def insert(self, pos: int, new_step: Step):
if pos >= len(self):
logMsg(
self,
'insert position is greater than the current length of steps. Append to the end instead.'
)
self.append(new_step)
else:
self.steps.insert(pos, new_step)
self.steps[pos].setWorkflow(self)
if pos > 0:
self.steps[pos - 1].setNextStep(self.steps[pos])
for step_id in range(pos, len(self)):
step = self.steps[step_id]
step.pos_id = step_id
step.setPreviousStep(self.steps[pos - 1])
if step_id < len(self) - 1:
step.setNextStep(self.steps[pos + 1])
self.name_dict[step.name] = step_id
pass
def append(self, new_step):
# if not isinstance(new_step, type(Step)):
# raise TypeError(
# 'Type error for ' + new_step + 'th steps. Only Step can be the next_step, where its next_step is '
# + str(type(new_step)))
previous_step = None
if len(self.steps) > 0:
previous_step = self.steps[-1]
step_id = len(self.steps)
new_step.pos_id = step_id
new_step.setWorkflow(self)
self.steps.append(new_step)
self.name_dict[new_step.name] = step_id
if previous_step is not None:
logMsg((self,
'attache new step ' + new_step.name + ' ' + str(step_id)))
new_step.setPreviousStep(previous_step)
previous_step.setNextStep(new_step)
pass
def train(self, x, y):
logMsg('error, abstract method called')
# [] to return Documents, dict() to return grouping information
pass