def test_get_full_module_name(self):
from forte.processors.misc import LowerCaserProcessor
full_name = utils.get_full_module_name(LowerCaserProcessor)
self.assertEqual(
full_name,
"forte.processors.misc.lowercaser_processor.LowerCaserProcessor",
)
def __init__(self,
from_cache: bool = False,
cache_directory: Optional[str] = None,
append_to_cache: bool = False):
super().__init__()
self.from_cache = from_cache
self._cache_directory = cache_directory
self.component_name = get_full_module_name(self)
self.append_to_cache = append_to_cache
def __init__(self,
from_cache: bool = False,
cache_directory: Optional[str] = None,
append_to_cache: bool = False,
cache_in_memory: bool = False):
super().__init__()
self.from_cache = from_cache
self._cache_directory = cache_directory
self.component_name = get_full_module_name(self)
self.append_to_cache = append_to_cache
self._cache_in_memory = cache_in_memory
self._cache_ready: bool = False
self._data_packs: List[PackType] = []
def test_get_data(self):
requests = {
Sentence: ["speaker"],
Token: ["pos", "sense"],
EntityMention: [],
PredicateMention: [],
PredicateArgument: {
"fields": [],
"unit": "Token"
},
PredicateLink: {
"component": utils.get_full_module_name(OntonotesReader),
"fields": ["parent", "child", "arg_type"]
}
}
# case 1: get sentence context from the beginning
instances = list(self.data_pack.get_data(Sentence))
self.assertEqual(len(instances), 2)
self.assertEqual(instances[1]["offset"],
len(instances[0]["context"]) + 1)
# case 2: get sentence context from the second instance
instances = list(self.data_pack.get_data(Sentence, skip_k=1))
self.assertEqual(len(instances), 1)
self.assertEqual(instances[0]["offset"], 165)
# case 3: get document context
instances = list(self.data_pack.get_data(Document, skip_k=0))
self.assertEqual(len(instances), 1)
self.assertEqual(instances[0]["offset"], 0)
# case 3.1: test get single
document: Document = self.data_pack.get_single(Document)
self.assertEqual(document.text, instances[0]['context'])
# case 4: test offset out of index
instances = list(self.data_pack.get_data(Sentence, skip_k=10))
self.assertEqual(len(instances), 0)
# case 5: get entries
instances = list(
self.data_pack.get_data(Sentence, request=requests, skip_k=1))
self.assertEqual(len(instances[0].keys()), 9)
self.assertEqual(len(instances[0]["PredicateLink"]), 4)
self.assertEqual(len(instances[0]["Token"]), 5)
self.assertEqual(len(instances[0]["EntityMention"]), 3)
def __init__(
self,
from_cache: bool = False,
cache_directory: Optional[str] = None,
append_to_cache: bool = False,
cache_in_memory: bool = False,
):
super().__init__()
self.from_cache = from_cache
self._cache_directory = cache_directory
self.component_name = get_full_module_name(self)
self.append_to_cache = append_to_cache
self._cache_in_memory = cache_in_memory
self._cache_ready: bool = False
self._data_packs: List[PackType] = []
# needed for time profiling of reader
self._enable_profiling: bool = False
self._start_time: float = 0.0
self.time_profile: float = 0.0
def __init__(self):
self.component_name = get_full_module_name(self)
self.selector = DummySelector()
