sentence

autocorpus.ac_bioc.sentence

This module defines the BioCSentence class.

Classes

BioCSentence(text, offset, infons=dict(), annotations=list(), relations=list()) dataclass

Bases: DataClassJsonMixin

Represents a sentence in the BioC format.

Functions

from_xml(elem) classmethod

Create a BioCSentence instance from an XML element.

Parameters:

Name	Type	Description	Default
elem	Element	An XML element representing a sentence.	required

Returns:

Name	Type	Description
BioCSentence	BioCSentence	An instance of BioCSentence created from the XML element.

Source code in autocorpus/ac_bioc/sentence.py

@classmethod
def from_xml(cls, elem: ET.Element) -> BioCSentence:
    """Create a BioCSentence instance from an XML element.

    Args:
        elem (ET.Element): An XML element representing a sentence.

    Returns:
        BioCSentence: An instance of BioCSentence created from the XML element.
    """
    offset = int(elem.findtext("offset", default="0"))
    text = elem.findtext("text", default="")

    infons = {
        e.attrib["key"]: e.text for e in elem.findall("infon") if e.text is not None
    }

    annotations = [
        BioCAnnotation.from_xml(a_elem) for a_elem in elem.findall("annotation")
    ]

    return cls(
        text=text,
        offset=offset,
        infons=infons,
        annotations=annotations,
    )

to_xml()

Convert the BioCSentence instance to an XML element.

Returns:

Type	Description
Element	ET.Element: An XML element representing the sentence.

Source code in autocorpus/ac_bioc/sentence.py

def to_xml(self) -> ET.Element:
    """Convert the BioCSentence instance to an XML element.

    Returns:
        ET.Element: An XML element representing the sentence.
    """
    sentence_elem = ET.Element("sentence")

    for k, v in self.infons.items():
        infon = ET.SubElement(sentence_elem, "infon", {"key": k})
        infon.text = v

    offset_elem = ET.SubElement(sentence_elem, "offset")
    offset_elem.text = str(self.offset)

    text_elem = ET.SubElement(sentence_elem, "text")
    text_elem.text = self.text

    for ann in self.annotations:
        sentence_elem.append(ann.to_xml())

    return sentence_elem