def _execute_logical_form_on_table(logical_form: str, table: str):
"""
The parameters are written out to files which the jar file reads and then executes the
logical form.
"""
logical_form_filename = os.path.join(SEMPRE_DIR, 'logical_forms.txt')
with open(logical_form_filename, 'w') as temp_file:
temp_file.write(logical_form + '\n')
table_dir = os.path.join(SEMPRE_DIR, 'tsv/')
os.makedirs(table_dir, exist_ok=True)
# The .tsv file extension is important here since the table string parameter is in tsv format.
# If this file was named with suffix .csv then Sempre would interpret it as comma separated
# and return the wrong denotation.
table_filename = 'context.tsv'
with open(os.path.join(table_dir, table_filename),
'w',
encoding='utf-8') as temp_file:
temp_file.write(table)
# The id, target, and utterance are ignored, we just need to get the
# table filename into sempre's lisp format.
test_record = (
'(example (id nt-0) (utterance none) (context (graph tables.TableKnowledgeGraph %s))'
'(targetValue (list (description "6"))))' % (table_filename))
test_data_filename = os.path.join(SEMPRE_DIR, 'data.examples')
with open(test_data_filename, 'w') as temp_file:
temp_file.write(test_record)
# TODO(matt): The jar that we have isn't optimal for this use case - we're using a
# script designed for computing accuracy, and just pulling out a piece of it. Writing
# a new entry point to the jar that's tailored for this use would be cleaner.
if not check_for_java():
raise RuntimeError('Java is not installed properly.')
command = ' '.join([
'java', '-jar',
cached_path(DEFAULT_EXECUTOR_JAR), test_data_filename,
logical_form_filename, table_dir
])
run(command, shell=True)
denotations_file = os.path.join(SEMPRE_DIR,
'logical_forms_denotations.tsv')
with open(denotations_file) as temp_file:
line = temp_file.readline().split('\t')
# Clean up all the temp files generated from this function.
# Take care to not remove the auxiliary sempre files
os.remove(logical_form_filename)
shutil.rmtree(table_dir)
os.remove(denotations_file)
os.remove(test_data_filename)
return line[1] if len(line) > 1 else line[0]
def _create_sempre_executor(self) -> None:
"""
Creates a server running SEMPRE that we can send logical forms to for evaluation. This
uses inter-process communication, because SEMPRE is java code. We also need to be careful
to clean up the process when our program exits.
"""
if self._executor_process:
return
# It'd be much nicer to just use `cached_path` for these files. However, the SEMPRE jar
# that we're using expects to find these files in a particular location, so we need to make
# sure we put the files in that location.
os.makedirs(SEMPRE_DIR, exist_ok=True)
abbreviations_path = os.path.join(SEMPRE_DIR, 'abbreviations.tsv')
grammar_path = os.path.join(SEMPRE_DIR, 'grow.grammar')
with session_with_backoff() as session:
if not os.path.exists(abbreviations_path):
result = session.get(ABBREVIATIONS_FILE)
with open(abbreviations_path, 'wb') as downloaded_file:
downloaded_file.write(result.content)
if not os.path.exists(grammar_path):
result = session.get(GROW_FILE)
with open(grammar_path, 'wb') as downloaded_file:
downloaded_file.write(result.content)
if not check_for_java():
raise RuntimeError('Java is not installed properly.')
args = [
'java', '-jar',
cached_path(SEMPRE_EXECUTOR_JAR), 'serve', self._table_directory
]
self._executor_process = subprocess.Popen(args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
bufsize=1)
lines = []
for _ in range(6):
# SEMPRE outputs six lines of stuff when it loads that I can't disable. So, we clear
# that here.
lines.append(str(self._executor_process.stdout.readline()))
assert 'Parser' in lines[
-1], "SEMPRE server output unexpected; the server may have changed"
logger.info("Started SEMPRE server for evaluating logical forms")
# This is supposed to ensure that the subprocess gets killed when python exits.
atexit.register(self._stop_sempre_executor)
def _create_sempre_executor(self) -> None:
"""
Creates a server running SEMPRE that we can send logical forms to for evaluation. This
uses inter-process communication, because SEMPRE is java code. We also need to be careful
to clean up the process when our program exits.
"""
if self._executor_process:
return
# It'd be much nicer to just use `cached_path` for these files. However, the SEMPRE jar
# that we're using expects to find these files in a particular location, so we need to make
# sure we put the files in that location.
os.makedirs(SEMPRE_DIR, exist_ok=True)
abbreviations_path = os.path.join(SEMPRE_DIR, 'abbreviations.tsv')
if not os.path.exists(abbreviations_path):
result = requests.get(ABBREVIATIONS_FILE)
with open(abbreviations_path, 'wb') as downloaded_file:
downloaded_file.write(result.content)
grammar_path = os.path.join(SEMPRE_DIR, 'grow.grammar')
if not os.path.exists(grammar_path):
result = requests.get(GROW_FILE)
with open(grammar_path, 'wb') as downloaded_file:
downloaded_file.write(result.content)
if not check_for_java():
raise RuntimeError('Java is not installed properly.')
args = ['java', '-jar', cached_path(SEMPRE_EXECUTOR_JAR), 'serve', self._table_directory]
self._executor_process = subprocess.Popen(args,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
bufsize=1)
lines = []
for _ in range(6):
# SEMPRE outputs six lines of stuff when it loads that I can't disable. So, we clear
# that here.
lines.append(str(self._executor_process.stdout.readline()))
assert 'Parser' in lines[-1], "SEMPRE server output unexpected; the server may have changed"
logger.info("Started SEMPRE server for evaluating logical forms")
# This is supposed to ensure that the subprocess gets killed when python exits.
atexit.register(self._stop_sempre_executor)