def set_attributes(self, schema_file: Union[str, Path] = '', encoding: str = None) -> Set:
"""
The current version SpaCy doesn't differentiate attributes for different annotation types.
Thus, any attributes extended here will be applied to all Spans.
@param schema_file: initiate Span attributes using eHOST schema configuration file
@param encoding: text encoding
@return: a set of attribute names
"""
schema_file = self.check_file_validity(schema_file, False)
attr_names = set()
attr_conf_start = False
if schema_file is not None and schema_file.name.endswith("conf"):
for row in schema_file.read_text(encoding=encoding).split("\n"):
if len(row.strip()) == 0 or row[0] == '#':
continue
if row.startswith(r'[attributes]'):
attr_conf_start = True
continue
elif row[0] == '[':
attr_conf_start = False
if attr_conf_start:
# [attributes]
# Negation Arg:<EVENT>
# Confidence Arg:<EVENT>, Value:Possible|Likely|Certain
name = row.split(' ')[0]
default_value = None
if name not in attr_names and not Span.has_extension(name):
Span.set_extension(name, default=default_value)
attr_names.add(name)
self.schema_set = True
return attr_names
def __init__(self, nlp: Language = None, support_overlap: bool = False,
log_level: int = logging.WARNING, encoding: str = None, doc_name_depth: int = 0,
schema_file: Union[str, Path] = '', store_anno_string: bool = False,
**kwargs):
"""
@param nlp: Spacy Language model
@param support_overlap: whether need to support overlapped annotations
@param log_level: logging level configuration
@param encoding: txt encoding
@param doc_name_depth: depth of parent directories to add into doc_name
default is 0: only use file name
1: use 1 level parent directory name + file name
-1: use full absolution path
if you are dealing with multiple directories,this is helpful to
locate the original files
@param schema_file: initiate Span attributes using eHOST schema configuration file
@param store_anno_string: whether read annotated string from annotations to double check parsed Span's correction
@param kwargs:other parameters
"""
self.schema_set = False
self.attr_names = self.set_attributes(schema_file=schema_file, encoding=encoding)
if store_anno_string:
if not Span.has_extension("span_txt"):
Span.set_extension("span_txt", default="")
super().__init__(nlp=nlp, support_overlap=support_overlap,
log_level=log_level, encoding=encoding, doc_name_depth=doc_name_depth,
schema_file=schema_file, store_anno_string=store_anno_string, **kwargs)
pass
def __call__(self, spacy_span: Span, describer=None):
"""
convenient wrapper around make_issue if you are using spaCy
usage example:
```python
from spacy.tokens import Span
from app.factor import SpacyFactor
SOV = SpacyFactor(
"subject_object_verb_spacing",
"Keep the subject, verb, and object of a sentence close together to help the reader understand the sentence."
)
Span.set_extension("score", default=0)
Span.set_extension("suggestions", default=[])
doc = nlp("Holders of the Class A and Class B-1 certificates will be entitled to receive on each Payment Date, to the extent monies are available therefor (but not more than the Class A Certificate Balance or Class B-1 Certificate Balance then outstanding), a distribution.")
score = analyze(doc)
if score is not None:
span = Span(doc, 0, len(doc)) # or whichever TOKENS are the issue (don't have to worry about character indexes)
span._.score = score
span._.suggestions = get_suggestions(doc)
issues = SOV(span)
```
"""
text, start, end = spacy_span.text, spacy_span.start_char, spacy_span.end_char
score = spacy_span._.score if spacy_span.has_extension("score") else 0
suggestions = (spacy_span._.suggestions
if spacy_span.has_extension("suggestions") else [])
if describer:
description = describer(spacy_span)
else:
description = self.description
return make_issue(
text,
start,
end,
issue_type=self.issue_type,
score=score,
description=description,
suggestions=suggestions,
)
def __init__(self,
nlp: Language = None,
support_overlap: bool = False,
log_level: int = logging.WARNING,
encoding: str = None,
doc_name_depth: int = 0,
schema_file: Union[str, Path] = '',
store_anno_string: bool = False,
use_adjudication: bool = False,
**kwargs):
"""
@param nlp: a SpaCy language model
@param support_overlap: if the EhostDocReader need to support reading from overlapped annotations.
Because SpaCy's Doc.ents does not allows overlapped Spans, to support overlapping, Spans need to be stored
somewhere else----Doc._.concepts
@param log_level: set the logger's logging level. TO debug, set to logging.DEBUG
@param encoding: txt encoding
@param doc_name_depth: depth of parent directories to add into doc_name
default is 0: only use file name
1: use 1 level parent directory name + file name
-1: use full absolution path
if you are dealing with multiple directories,this is helpful to
locate the original files
@param schema_file: initiate Span attributes using eHOST schema configuration file
@param store_anno_string: whether read annotated string from annotations to double check parsed Span's correction
@param use_adjudication: if read annotations from adjudication folder
@param kwargs:other parameters
"""
self.schema_set = False
self.attr_names = self.set_attributes(schema_file=schema_file,
encoding=encoding)
if store_anno_string:
if not Span.has_extension("span_txt"):
Span.set_extension("span_txt", default="")
super().__init__(nlp=nlp,
support_overlap=support_overlap,
log_level=log_level,
encoding=encoding,
doc_name_depth=doc_name_depth,
schema_file=schema_file,
store_anno_string=store_anno_string,
use_adjudication=use_adjudication,
**kwargs)
pass
def __init__(self,
first_name_extension_name=FirstNameListMatcher.EXTENSION_NAME,
last_name_extension_name=LastNameListMatcher.EXTENSION_NAME):
self.token_extension_name = self.TOKEN_EXTENSION_NAME
self.span_extension_name = self.SPAN_EXTENSION_NAME
self.doc_extension_name = self.DOC_EXTENSION_NAME
self.first_name_extension_name = first_name_extension_name
self.last_name_extension_name = last_name_extension_name
if not Token.has_extension(self.token_extension_name):
Token.set_extension(self.token_extension_name,
default=self.ANOT_NONE)
if not Span.has_extension(self.span_extension_name):
Span.set_extension(self.span_extension_name,
getter=self.is_full_name_getter)
if not Doc.has_extension(self.doc_extension_name):
Doc.set_extension(self.doc_extension_name, default=[])
def set_attributes(self,
schema_file: Union[str, Path] = '',
encoding: str = None) -> Set:
"""
The current version SpaCy doesn't differentiate attributes for different annotation types.
Thus, any attributes extended here will be applied to all Spans.
@param schema_file: initiate Span attributes using eHOST schema configuration file
@param encoding: text encoding
@return: a set of attribute names
"""
schema_file = self.check_file_validity(schema_file, False)
attr_names = set()
if schema_file is not None:
root = etree.parse(str(schema_file.absolute()))
for attr_def in root.iter("attributeDef"):
name = attr_def[0].text.replace(' ', '_')
default_value = attr_def[2].text
if name not in attr_names and not Span.has_extension(name):
Span.set_extension(name, default=default_value)
attr_names.add(name)
self.schema_set = True
return attr_names