From 45880b17e8c192bbd0c5b9003d226ce88533a163 Mon Sep 17 00:00:00 2001
From: daxid <david.rouquet@tetras-libre.fr>
Date: Thu, 22 Jun 2023 16:26:29 +0000
Subject: [PATCH] Update config to use config_dict as parameter of the config
constructor
---
tenet/__init__.py | 1 +
tenet/extraction/config.py | 170 ++++++++++++++++-------------
tenet/extraction/process.py | 10 +-
tenet/extraction/structure.py | 2 +-
tenet/main.py | 176 ++++++++++++++++++++++---------
tenet/scheme/owl_amr_scheme_1.py | 153 +++++++++++++++++++++++++++
6 files changed, 383 insertions(+), 129 deletions(-)
diff --git a/tenet/__init__.py b/tenet/__init__.py
index 3665b4dc..bd883646 100644
--- a/tenet/__init__.py
+++ b/tenet/__init__.py
@@ -8,6 +8,7 @@ sys.path.insert(0, os.path.abspath(LIB_PATH))
# -- Main Methods
from tenet.main import create_ontology_from_amrld_file
from tenet.main import create_ontology_from_amrld_dir
+from tenet.main import create_ontology_from_amrld_dir_multi_cpu
from tenet.main import generate_odrl_from_amrld_file
from tenet.main import generate_odrl_from_amrld_dir
#from main import create_ontology_from_unlrdf_file
\ No newline at end of file
diff --git a/tenet/extraction/config.py b/tenet/extraction/config.py
index 304f04cb..851484c8 100644
--- a/tenet/extraction/config.py
+++ b/tenet/extraction/config.py
@@ -36,13 +36,26 @@ class Config:
# Constructor
#-------------------------------------------------
- def __init__(self,
- config_file,
- uuid_str, source_corpus, target_ref='base',
- base_dir=None,
- base_output_dir=None,
- technical_dir_path=None):
+ # def __init__(self,
+ # config_file,
+ # uuid_str, source_corpus, target_ref='base',
+ # base_dir=None,
+ # base_output_dir=None,
+ # technical_dir_path=None,
+ # source_type=None
+ # ):
+
+ def __init__(self, config_dict):
+ config_file = config_dict['config_file_path']
+ uuid_str = config_dict['onto_prefix']
+ source_corpus = config_dict['source_corpus']
+ base_dir = config_dict['base_dir'] if 'base_dir' in config_dict.keys() else None
+ target_ref = config_dict['target_ref'] if 'target_ref' in config_dict.keys() else 'base'
+ base_output_dir = config_dict['base_output_dir'] if 'base_output_dir' in config_dict.keys() else None
+ technical_dir_path = config_dict['technical_dir_path'] if 'technical_dir_path' in config_dict.keys() else None
+ source_type = config_dict['source_type'] if 'source_type' in config_dict.keys() else None
+
# -- Config XML Tree
config_tree = etree.parse(config_file)
@@ -54,7 +67,11 @@ class Config:
self.source_corpus = source_corpus
self.target_ref = target_ref
self._process_level = c_base.get("process_level")
- self.source_type = c_base.get("source_type")
+ #self.source_type = c_base.get("source_type")
+ if source_type == None:
+ self.source_type = c_dir.get("source_type")
+ else:
+ self.source_type = source_type
self.extraction_scheme = c_base.get("extraction_scheme")
# # -- CTS Reference
@@ -227,11 +244,17 @@ class Config:
config_tree = etree.parse(self.config_file)
c_file = config_tree.xpath("file")[0]
self._schema_file = self.structure_dir
+
if self.source_type == 'amr':
self._schema_file += c_file.get("amr_input_data_schema")
if self.source_type == 'unl':
self._schema_file += c_file.get("unl_input_data_schema")
- self._schema_file += schema_file_cmpl + ".ttl"
+
+ if not schema_file_cmpl.startswith("./structure"):
+ self._schema_file += schema_file_cmpl
+
+ if not self._schema_file.endswith(".ttl"):
+ self._schema_file += ".ttl"
schema_file = property(_get_schema_file, _set_schema_file)
@@ -243,7 +266,10 @@ class Config:
def _set_source_sentence_file(self, source_sentence_file_cmpl):
self._source_sentence_file = self.input_doc_dir + self.source_corpus
- self._source_sentence_file += source_sentence_file_cmpl + '.ttl'
+ self._source_sentence_file += source_sentence_file_cmpl
+
+ if not self._source_sentence_file.endswith(".ttl"):
+ self._source_sentence_file += ".ttl"
source_sentence_file = property(_get_source_sentence_file,
_set_source_sentence_file)
@@ -341,69 +367,69 @@ class Config:
return config_str
- def to_dict(self):
- config_dict = {
- "config_file": self.config_file,
- "uuid_str": self.uuid_str,
- "source_corpus": self.source_corpus,
- "target_ref": self.target_ref,
- "base_dir": self.base_dir,
- "structure_dir": self.structure_dir,
- "cts_dir": self.cts_dir,
- "target_frame_dir": self.target_frame_dir,
- "input_doc_dir": self.input_doc_dir,
- "base_output_dir": self.base_output_dir,
- "output_dir": self.output_dir,
- "technical_dir_path": self.technical_dir_path,
- "sentence_output_dir": self.sentence_output_dir,
- "process_level": self.process_level,
- "source_type": self.source_type,
- "extraction_scheme": self.extraction_scheme,
- "config_param_file": self.config_param_file,
- "base_ontology_file": self.base_ontology_file,
- "cts_file": self.cts_file,
- "base_uri": self.base_uri,
- "onto_suffix": self.onto_suffix,
- "onto_seed_suffix": self.onto_seed_suffix,
- "source_sentence_file": self.source_sentence_file,
- "frame_ontology_file": self.frame_ontology_file,
- "frame_ontology_seed_file": self.frame_ontology_seed_file,
- "output_ontology_namespace": self.output_ontology_namespace,
- "output_file": self.output_file,
- "input_doc_dir": self.input_doc_dir,
- "schema_file": self.schema_file,
- }
- return config_dict
+ # def to_dict(self):
+ # config_dict = {
+ # "config_file": self.config_file,
+ # "uuid_str": self.uuid_str,
+ # "source_corpus": self.source_corpus,
+ # "target_ref": self.target_ref,
+ # "base_dir": self.base_dir,
+ # "structure_dir": self.structure_dir,
+ # "cts_dir": self.cts_dir,
+ # "target_frame_dir": self.target_frame_dir,
+ # "input_doc_dir": self.input_doc_dir,
+ # "base_output_dir": self.base_output_dir,
+ # "output_dir": self.output_dir,
+ # "technical_dir_path": self.technical_dir_path,
+ # "sentence_output_dir": self.sentence_output_dir,
+ # "process_level": self.process_level,
+ # "source_type": self.source_type,
+ # "extraction_scheme": self.extraction_scheme,
+ # "config_param_file": self.config_param_file,
+ # "base_ontology_file": self.base_ontology_file,
+ # "cts_file": self.cts_file,
+ # "base_uri": self.base_uri,
+ # "onto_suffix": self.onto_suffix,
+ # "onto_seed_suffix": self.onto_seed_suffix,
+ # "source_sentence_file": self.source_sentence_file,
+ # "frame_ontology_file": self.frame_ontology_file,
+ # "frame_ontology_seed_file": self.frame_ontology_seed_file,
+ # "output_ontology_namespace": self.output_ontology_namespace,
+ # "output_file": self.output_file,
+ # "input_doc_dir": self.input_doc_dir,
+ # "schema_file": self.schema_file,
+ # }
+ # return config_dict
- def update_from_dict(self, config_dict):
- self.config_file = config_dict.get("config_file")
- self.uuid_str = config_dict.get("uuid_str")
- self.source_corpus = config_dict.get("source_corpus")
- self.target_ref = config_dict.get("target_ref")
- self.base_dir = config_dict.get("base_dir")
- self.structure_dir = config_dict.get("structure_dir")
- self.cts_dir = config_dict.get("cts_dir")
- self.target_frame_dir = config_dict.get("target_frame_dir")
- self.input_doc_dir = config_dict.get("input_doc_dir")
- self.base_output_dir = config_dict.get("base_output_dir")
- self.output_dir = config_dict.get("output_dir")
- self.technical_dir_path = config_dict.get("technical_dir_path")
- self.sentence_output_dir = config_dict.get("sentence_output_dir")
- self.process_level = config_dict.get("process_level")
- self.source_type = config_dict.get("source_type")
- self.extraction_scheme = config_dict.get("extraction_scheme")
- self.config_param_file = config_dict.get("config_param_file")
- self.base_ontology_file = config_dict.get("base_ontology_file")
- self.cts_file = config_dict.get("cts_file")
- self.base_uri = config_dict.get("base_uri")
- self.onto_suffix = config_dict.get("onto_suffix")
- self.onto_seed_suffix = config_dict.get("onto_seed_suffix")
- self.source_sentence_file = config_dict.get("source_sentence_file")
- self.frame_ontology_file = config_dict.get("frame_ontology_file")
- self.frame_ontology_seed_file = config_dict.get("frame_ontology_seed_file")
- self.output_ontology_namespace = config_dict.get("output_ontology_namespace")
- self.output_file = config_dict.get("output_file")
- self.input_doc_dir = config_dict.get("input_doc_dir")
- self.schema_file = config_dict.get("schema_file")
+ # def update_from_dict(self, config_dict):
+ # self.config_file = config_dict.get("config_file")
+ # self.uuid_str = config_dict.get("uuid_str")
+ # self.source_corpus = config_dict.get("source_corpus")
+ # self.target_ref = config_dict.get("target_ref")
+ # self.base_dir = config_dict.get("base_dir")
+ # self.structure_dir = config_dict.get("structure_dir")
+ # self.cts_dir = config_dict.get("cts_dir")
+ # self.target_frame_dir = config_dict.get("target_frame_dir")
+ # self.input_doc_dir = config_dict.get("input_doc_dir")
+ # self.base_output_dir = config_dict.get("base_output_dir")
+ # self.output_dir = config_dict.get("output_dir")
+ # self.technical_dir_path = config_dict.get("technical_dir_path")
+ # self.sentence_output_dir = config_dict.get("sentence_output_dir")
+ # self.process_level = config_dict.get("process_level")
+ # self.source_type = config_dict.get("source_type")
+ # self.extraction_scheme = config_dict.get("extraction_scheme")
+ # self.config_param_file = config_dict.get("config_param_file")
+ # self.base_ontology_file = config_dict.get("base_ontology_file")
+ # self.cts_file = config_dict.get("cts_file")
+ # self.base_uri = config_dict.get("base_uri")
+ # self.onto_suffix = config_dict.get("onto_suffix")
+ # self.onto_seed_suffix = config_dict.get("onto_seed_suffix")
+ # self.source_sentence_file = config_dict.get("source_sentence_file")
+ # self.frame_ontology_file = config_dict.get("frame_ontology_file")
+ # self.frame_ontology_seed_file = config_dict.get("frame_ontology_seed_file")
+ # self.output_ontology_namespace = config_dict.get("output_ontology_namespace")
+ # self.output_file = config_dict.get("output_file")
+ # self.input_doc_dir = config_dict.get("input_doc_dir")
+ # self.schema_file = config_dict.get("schema_file")
\ No newline at end of file
diff --git a/tenet/extraction/process.py b/tenet/extraction/process.py
index 06c00332..6b0b255a 100644
--- a/tenet/extraction/process.py
+++ b/tenet/extraction/process.py
@@ -228,7 +228,7 @@ def apply_step(config, graph, rule_set, step_number, step_name, step_sequence_de
for sequence_def in step_sequence_def:
graph, triple_list = _apply_sequence(graph, sequence_def)
step_triple_list.extend(triple_list)
-
+
# -- Serialize the working graph updated during the step
if config.technical_dir_path is not None:
os.makedirs(config.sentence_output_dir, exist_ok=True)
@@ -238,7 +238,7 @@ def apply_step(config, graph, rule_set, step_number, step_name, step_sequence_de
str = "----- {0} triples extracted during {1} step"
new_triple_count = len(graph) - graph_length_before_step
logger.info(str.format(new_triple_count, step_name))
-
+
return graph, step_triple_list
except AssertionError:
@@ -265,7 +265,7 @@ def apply(config, graph):
logger.info(f"-- Loading Extraction Scheme ({config.extraction_scheme})")
rule_dir, prefix_list, scheme = load_cts(config)
logger.debug("----- Step number: {0}".format(len(scheme)))
-
+
# -- Loading Extraction Rules
logger.info("-- Loading Extraction Rules ({0}*)".format(rule_dir))
rule_set = load_rule_set(config, rule_dir, prefix_list)
@@ -278,7 +278,7 @@ def apply(config, graph):
step_number += 1
graph, new_triple_list = apply_step(config, graph, rule_set,
step_number, step_name, step_sequence_def)
-
+
# -- Result: file containing only the factoids (last step result)
if config.technical_dir_path is not None:
os.makedirs(config.sentence_output_dir, exist_ok=True)
@@ -293,7 +293,7 @@ def apply(config, graph):
factoid_graph.serialize(destination=factoid_file,
base=base_ref,
format='turtle')
-
+
return graph, new_triple_list
except:
diff --git a/tenet/extraction/structure.py b/tenet/extraction/structure.py
index bd02ac21..d50c8637 100644
--- a/tenet/extraction/structure.py
+++ b/tenet/extraction/structure.py
@@ -173,7 +173,7 @@ def prepare_work_graph(config, sentence_file):
load_sentence(config, work_graph, sentence_file)
else: # process_level == 'document'
load_all_sentences(config, work_graph)
-
+
# -- Result
if config.technical_dir_path is not None:
os.makedirs(config.sentence_output_dir, exist_ok=True)
diff --git a/tenet/main.py b/tenet/main.py
index 28fa3a5e..d34ceb9b 100644
--- a/tenet/main.py
+++ b/tenet/main.py
@@ -40,11 +40,42 @@ def __set_context():
os.chdir(LIB_PATH)
-def __set_config(
- config_file_path,
- source_type, source_corpus, onto_prefix,
- base_output_dir, technical_dir_path):
-
+# def __set_config(
+# config_file_path,
+# source_type, source_corpus, onto_prefix,
+# base_output_dir, technical_dir_path):
+
+# logger.info("-- Process Setting ")
+# logger.info(f'----- Corpus source: {source_corpus} ({source_type})')
+# logger.info(f'----- Base output dir: {base_output_dir}')
+# logger.info(f'----- technical dir path: {technical_dir_path}')
+# logger.info(f'----- Ontology target (id): {onto_prefix}')
+# logger.info(f'----- Current path: {os.getcwd()}')
+# logger.debug(f'----- Config file: {config_file_path}')
+
+# process_config = config.Config(config_file_path,
+# onto_prefix,
+# source_corpus,
+# base_output_dir = base_output_dir,
+# technical_dir_path = technical_dir_path,
+# source_type = source_type
+# )
+# #process_config.source_type = source_type
+# # config.output_ontology_namespace = target_ontology_namespace
+
+# logger.debug(process_config.get_full_config())
+
+# return process_config
+
+
+def __set_config(config_dict):
+ config_file_path = config_dict['config_file_path']
+ source_type = config_dict['source_type']
+ source_corpus = config_dict['source_corpus']
+ onto_prefix = config_dict['onto_prefix']
+ base_output_dir = config_dict['base_output_dir']
+ technical_dir_path = config_dict['technical_dir_path']
+
logger.info("-- Process Setting ")
logger.info(f'----- Corpus source: {source_corpus} ({source_type})')
logger.info(f'----- Base output dir: {base_output_dir}')
@@ -52,19 +83,20 @@ def __set_config(
logger.info(f'----- Ontology target (id): {onto_prefix}')
logger.info(f'----- Current path: {os.getcwd()}')
logger.debug(f'----- Config file: {config_file_path}')
-
- process_config = config.Config(config_file_path,
- onto_prefix,
- source_corpus,
- base_output_dir = base_output_dir,
- technical_dir_path = technical_dir_path
- )
- process_config.source_type = source_type
- # config.output_ontology_namespace = target_ontology_namespace
-
- logger.debug(process_config.get_full_config())
-
- return process_config
+
+ # process_config = config.Config(
+ # config_file_path,
+ # onto_prefix,
+ # source_corpus,
+ # base_output_dir=base_output_dir,
+ # technical_dir_path=technical_dir_path,
+ # source_type=source_type
+ # )
+ base_config = config.Config(config_dict)
+
+ logger.debug(base_config.get_full_config())
+
+ return base_config
def __count_number_of_graph(config):
@@ -80,6 +112,7 @@ def __apply_extraction(config, sentence_file):
if config.technical_dir_path is not None:
os.makedirs(config.sentence_output_dir, exist_ok=True)
work_graph = structure.prepare_sentence_work(config, sentence_file)
+
_, new_triple_list = process.apply(config, work_graph)
return new_triple_list
@@ -144,9 +177,22 @@ def create_ontology_from_amrld_file(amrld_file_path,
__set_context()
if onto_prefix is None: onto_prefix = 'DefaultId'
base_output_dir = os.path.dirname(out_file_path) if out_file_path is not None else None
- config = __set_config(OWL_CONFIG_FILE_PATH,
- 'amr', amrld_file_path, onto_prefix,
- base_output_dir, technical_dir_path)
+
+ config_dict = {
+ 'config_file_path': OWL_CONFIG_FILE_PATH,
+ 'source_type': 'amr',
+ 'source_corpus': amrld_file_path,
+ 'onto_prefix': onto_prefix,
+ 'base_output_dir': base_output_dir,
+ 'technical_dir_path': technical_dir_path
+ }
+
+ config = __set_config(config_dict)
+
+ # config = __set_config(OWL_CONFIG_FILE_PATH,
+# 'amr', amrld_file_path, onto_prefix,
+# base_output_dir, technical_dir_path)
+
assert os.path.exists(amrld_file_path), f'input file does not exists ({amrld_file_path})'
# -- Extraction Processing
@@ -201,9 +247,22 @@ def create_ontology_from_amrld_dir(amrld_dir_path,
__set_context()
if onto_prefix is None: onto_prefix = 'DefaultId'
base_output_dir = os.path.dirname(out_file_path) if out_file_path is not None else None
- config = __set_config(OWL_CONFIG_FILE_PATH,
- 'amr', amrld_dir_path, onto_prefix,
- base_output_dir, technical_dir_path)
+
+ config_dict = {
+ 'config_file_path': OWL_CONFIG_FILE_PATH,
+ 'source_type': 'amr',
+ 'source_corpus': amrld_dir_path,
+ 'onto_prefix': onto_prefix,
+ 'base_output_dir': base_output_dir,
+ 'technical_dir_path': technical_dir_path
+ }
+
+ config = __set_config(config_dict)
+
+ # config = __set_config(OWL_CONFIG_FILE_PATH,
+# 'amr', amrld_dir_path, onto_prefix,
+# base_output_dir, technical_dir_path)
+
assert os.path.exists(amrld_dir_path), f'input directory does not exists ({amrld_dir_path})'
__count_number_of_graph(config)
@@ -238,41 +297,41 @@ def create_ontology_from_amrld_dir(amrld_dir_path,
# AMR Main Methods (to create an ontology) - Multiprocessing
#==============================================================================
-global result_triple_queue
-global sentence_file_list
+#global result_triple_queue
+#global sentence_file_list
def dump_queue(q):
q.put(None)
return list(iter(q.get, None))
-def pool_function(arg_dic):
- global result_triple_queue
- global sentence_file_list
- print(f'==================== TEST A')
- process_config = config.Config(OWL_CONFIG_FILE_PATH, 'default', 'default')
- process_config.update_from_dict(arg_dic)
- print(f'==================== TEST B')
- print(f'==================== process_config (1): {process_config}')
- sentence_indice = arg_dic['sentence_list_indice']
- print(f'==================== process_config (2): {process_config}')
+def pool_function(arg_dict):
+ #global result_triple_queue
+ #global sentence_file_list
+
+ #process_config = config.Config(OWL_CONFIG_FILE_PATH, 'default', 'default')
+ #process_config.update_from_dict(arg_dict)
+ process_config = config.Config(arg_dict)
+
+ sentence_indice = arg_dict['sentence_list_indice']
sentence_file = sentence_file_list[sentence_indice]
- print(f'==================== sentence_file: {sentence_file}')
+
logger.info(f' *** sentence {sentence_indice} *** ')
- process_config.sentence_output_dir = f'-{sentence_indice}'
+ process_config.sentence_output_dir = f'-{sentence_indice}\n'
new_triple_list = __apply_extraction(process_config, sentence_file)
- print(f'==================== TEST C')
+
# The following must handled via a global queue
- result_triple_queue.extend(new_triple_list)
+ #result_triple_queue.extend(new_triple_list)
+
return(new_triple_list)
#@timed
-def create_ontology_from_amrld_dir_with_multiprocessing(amrld_dir_path,
+def create_ontology_from_amrld_dir_multi_cpu(amrld_dir_path,
base_ontology_path=None,
onto_prefix=None,
out_file_path=None,
technical_dir_path=None,
- processes=3#multiprocessing.cpu_count()-1
+ processes=multiprocessing.cpu_count()-1
):
"""
Method to create an ontology (as Turtle String) from a transduction
@@ -302,9 +361,22 @@ def create_ontology_from_amrld_dir_with_multiprocessing(amrld_dir_path,
__set_context()
if onto_prefix is None: onto_prefix = 'DefaultId'
base_output_dir = os.path.dirname(out_file_path) if out_file_path is not None else None
- config = __set_config(OWL_CONFIG_FILE_PATH,
- 'amr', amrld_dir_path, onto_prefix,
- base_output_dir, technical_dir_path)
+
+ config_dict = {
+ 'config_file_path': OWL_CONFIG_FILE_PATH,
+ 'source_type': 'amr',
+ 'source_corpus': amrld_dir_path,
+ 'onto_prefix': onto_prefix,
+ 'base_output_dir': base_output_dir,
+ 'technical_dir_path': technical_dir_path
+ }
+
+ config = __set_config(config_dict)
+
+ # config = __set_config(OWL_CONFIG_FILE_PATH,
+# 'amr', amrld_dir_path, onto_prefix,
+# base_output_dir, technical_dir_path)
+
assert os.path.exists(amrld_dir_path), f'input directory does not exists ({amrld_dir_path})'
__count_number_of_graph(config)
@@ -314,14 +386,14 @@ def create_ontology_from_amrld_dir_with_multiprocessing(amrld_dir_path,
sentence_count = 0
result_triple_list = []
- result_triple_queue = multiprocessing.Queue()
+ #result_triple_queue = multiprocessing.Queue()
sentence_file_list = glob.glob(sentence_dir, recursive = True)
# The following is for multiprocessing logging (must be exec before the pool is created
multiprocessing_logging.install_mp_handler()
- config_dict = config.to_dict()
+ # config_dict = config.to_dict()
#star_iterable = [(i, config) for i in range(len(sentence_file_list))]
mapIterable = []
@@ -329,15 +401,17 @@ def create_ontology_from_amrld_dir_with_multiprocessing(amrld_dir_path,
for i in range(len(sentence_file_list)):
config_dict['sentence_list_indice'] = i
mapIterable = mapIterable + [config_dict.copy()]
- print(config_dict)
with multiprocessing.Pool(processes) as p:
- print (f'\n mapIterable: {mapIterable}')
- triples = p.map(pool_function, mapIterable)
+ triplesLists = p.map(pool_function, mapIterable)
+
+ result_triple_list = []
+ for tripleList in triplesLists :
+ result_triple_list = result_triple_list + tripleList
# -- Final Ontology Generation (factoid_graph)
logger.info('\n === Final Ontology Generation === ')
- result_triple_list = dump_queue(result_triple_queue)
+ #result_triple_list = dump_queue(result_triple_queue)
factoid_graph = __generate_final_ontology(result_triple_list)
ontology_turtle_string = __serialize_factoid_graph(config, factoid_graph, out_file_path)
diff --git a/tenet/scheme/owl_amr_scheme_1.py b/tenet/scheme/owl_amr_scheme_1.py
index b0069466..50b6a7a1 100644
--- a/tenet/scheme/owl_amr_scheme_1.py
+++ b/tenet/scheme/owl_amr_scheme_1.py
@@ -151,3 +151,156 @@ scheme = {
}
+#!/usr/bin/python3.10
+# -*-coding:Utf-8 -*
+
+#==============================================================================
+# TENET: Composition Transduction Scheme for AMR analysis
+#------------------------------------------------------------------------------
+# Composition Transduction Scheme (CTS) using CTR (rules) for analysis of AMR
+# structure.
+#==============================================================================
+
+import scheme.amr_master_rule as rule
+
+#==============================================================================
+# Rule Directory
+#==============================================================================
+
+rule_dir = 'amr_master_rule/'
+
+
+#==============================================================================
+# Prefix using in CTR
+#==============================================================================
+
+prefix_list = [('owl', '<http://www.w3.org/2002/07/owl#>'),
+ ('odrl', '<http://www.w3.org/ns/odrl/2/>'),
+ ('cc', '<https://creativecommons.org/ns#>'),
+ ('rdf', '<http://www.w3.org/1999/02/22-rdf-syntax-ns#>'),
+ ('rdfs', '<http://www.w3.org/2000/01/rdf-schema#>'),
+ ('xsd', '<http://www.w3.org/2001/XMLSchema#>'),
+ ('amr', '<https://amr.tetras-libre.fr/rdf/schema#>'),
+ ('ns1', '<http://amr.isi.edu/frames/ld/v1.2.2/>'),
+ ('ns2', '<http://amr.isi.edu/rdf/amr-terms#>'),
+ ('ns3', '<http://amr.isi.edu/rdf/core-amr#>'),
+ ('ns4', '<http://amr.isi.edu/entity-types#>'),
+ ('net', '<https://tenet.tetras-libre.fr/semantic-net#>'),
+ ('cprm', '<https://tenet.tetras-libre.fr/config/parameters#>'),
+ ('fprm', '<https://tenet.tetras-libre.fr/frame/parameters#>'),
+ ('base-out', '<https://tenet.tetras-libre.fr/base-ontology#>'),
+ ('ext-out', '<https://tenet.tetras-libre.fr/extract-result#>')]
+
+
+#==============================================================================
+# Sequences
+#==============================================================================
+
+# ---------------------------------------------
+# Preprocessing Sequence(s)
+# ---------------------------------------------
+
+amr_bug_fixing_sequence = ['Bug fixing for some known anomalies of AMR-LD data',
+ rule.fix_amr_bug_1
+ ]
+
+amr_reification_sequence = ['AMR reification from AMR-Linked-Data to AMR (tenet) structure',
+ rule.reclassify_concept_1,
+ rule.reclassify_concept_2,
+ rule.reclassify_concept_3,
+ rule.reclassify_concept_4,
+ rule.reclassify_concept_5,
+ rule.reify_roles_as_concept,
+ rule.reclassify_existing_variable,
+ rule.add_new_variable_for_reified_concept,
+ rule.add_amr_leaf_for_reclassified_concept,
+ rule.add_amr_leaf_for_reified_concept,
+ rule.add_amr_edge_for_core_relation,
+ rule.add_amr_edge_for_reified_concept,
+ rule.add_amr_edge_for_name_relation,
+ rule.add_amr_edge_for_quant_relation,
+ rule.add_amr_edge_for_polarity_relation,
+ rule.update_amr_edge_role_1,
+ rule.add_amr_root
+ ]
+
+# ---------------------------------------------
+# Transduction Sequences
+# ---------------------------------------------
+
+atomic_extraction_sequence = ['atomic extraction sequence',
+ rule.extract_atom_class,
+ rule.extract_atom_individual,
+ rule.extract_atom_property,
+ rule.extract_atom_value,
+ rule.extract_atom_phenomena,
+ rule.propagate_atom_relation]
+
+classification_sequence_1 = ['classification sequence (1)',
+ rule.classify_modality_phenomena,
+ rule.reclassify_argument_property_to_class
+ ]
+
+phenomena_analyze_sequence_1 = ['phenomena analyze sequence (1)',
+ rule.analyze_phenomena_polarity_1,
+ rule.analyze_phenomena_polarity_2,
+ rule.analyze_phenomena_polarity_3,
+ rule.analyze_phenomena_polarity_4,
+ rule.analyze_phenomena_polarity_5,
+ rule.analyze_phenomena_mod_1,
+ rule.classify_modality_phenomena
+ ]
+
+phenomena_analyze_sequence_2 = ['phenomena analyze sequence (2)',
+ rule.analyze_phenomena_or_1,
+ rule.analyze_phenomena_or_2,
+ rule.analyze_phenomena_and_1,
+ rule.analyze_phenomena_and_2]
+
+composite_class_extraction_sequence = ['composite class extraction sequence',
+ rule.extract_composite_class_1,
+ rule.extract_composite_class_2]
+
+classification_sequence_2 = ['classification sequence (2)',
+ rule.classify_entity_from_core_arguments,
+ rule.classify_entity_from_part_relation,
+ rule.classify_entity_from_degree_arguments,
+ rule.classify_mother_from_domain_relation,
+ rule.propagate_individual_1,
+ rule.propagate_individual_2
+ ]
+
+
+# # ---------------------------------------------
+# # OWL Generation
+# # ---------------------------------------------
+
+owl_generation_sequence = ['OWL Generation Sequence',
+ rule.generate_owl_class,
+ rule.generate_owl_property,
+ rule.generate_owl_individual
+ ]
+
+
+
+#==============================================================================
+# Transduction Scheme
+#==============================================================================
+
+scheme = {
+
+ 'Preprocessing': [amr_bug_fixing_sequence,
+ amr_reification_sequence],
+
+ 'Transduction': [atomic_extraction_sequence,
+ classification_sequence_1,
+ phenomena_analyze_sequence_1,
+ phenomena_analyze_sequence_2,
+ composite_class_extraction_sequence,
+ classification_sequence_2],
+
+ 'Generation': [owl_generation_sequence]
+
+ }
+
+
--
GitLab