from quickner import Quickner, Config

config = Config(path="config.toml") # or Config() if the config file is in the current directory

# Initialize the annotator
quick = Quickner(config=config)

# Annotate the texts using the config file
quick.process() # or annotator.process(True) to save the annotated data to a file

from quickner import Quickner, Document

# Create documents
rust = Document("rust is made by Mozilla")
python = Document("Python was created by Guido van Rossum")
java = Document("Java was created by James Gosling")

# Documents can be added to a list
documents = [rust, python, java]

# Initialize the annotator

quick = Quickner(documents=documents)
quick
>>> Entities: 0 | Documents: 3 | Annotations:
>>> quick.documents
[Document(id="87e03d58b1ba4d72", text=rust is made by Mozilla, label=[]), Document(id="f1da5d23ef88f3dc", text=Python was created by Guido van Rossum, label=[]), Document(id="e4324f9818e7e598", text=Java was created by James Gosling, label=[])]
>>> quick.entities
[]

from quickner import Quickner, Document, Entity

# Create documents from texts
texts = (
  "rust is made by Mozilla",
  "Python was created by Guido van Rossum",
  "Java was created by James Gosling at Sun Microsystems",
  "Swift was created by Chris Lattner and Apple",
)
documents = [Document(text) for text in texts]

# Create entities
entities = (
  ("Rust", "PL"),
  ("Python", "PL"),
  ("Java", "PL"),
  ("Swift", "PL"),
  ("Mozilla", "ORG"),
  ("Apple", "ORG"),
  ("Sun Microsystems", "ORG"),
  ("Guido van Rossum", "PERSON"),
  ("James Gosling", "PERSON"),
  ("Chris Lattner", "PERSON"),
)
entities = [Entity(*(entity)) for entity in entities]

# Initialize the annotator
quick = Quickner(documents=documents, entities=entities)
quick.process()

>>> quick
Entities: 6 | Documents: 3 | Annotations: PERSON: 2, PL: 3, ORG: 1
>>> quick.documents 
[Document(id=87e03d58b1ba4d72, text=rust is made by Mozilla, label=[(0, 4, PL), (16, 23, ORG)]), Document(id=f1da5d23ef88f3dc, text=Python was created by Guido van Rossum, label=[(0, 6, PL), (22, 38, PERSON)]), Document(id=e4324f9818e7e598, text=Java was created by James Gosling, label=[(0, 4, PL), (20, 33, PERSON)])]

# Find documents by label
>>> quick.find_documents_by_label("PERSON")
[Document(id=f1da5d23ef88f3dc, text=Python was created by Guido van Rossum, label=[(0, 6, PL), (22, 38, PERSON)]), Document(id=e4324f9818e7e598, text=Java was created by James Gosling, label=[(0, 4, PL), (20, 33, PERSON)])]

# Find documents by entity
>>> quick.find_documents_by_entity("Guido van Rossum")
[Document(id=f1da5d23ef88f3dc, text=Python was created by Guido van Rossum, label=[(0, 6, PL), (22, 38, PERSON)])]
>>> quick.find_documents_by_entity("rust")
[Document(id=87e03d58b1ba4d72, text=rust is made by Mozilla, label=[(0, 4, PL), (16, 23, ORG)])]
>>> quick.find_documents_by_entity("Chris Lattner")
[Document(id=3b0b3b5b0b5b0b5b, text=Swift was created by Chris Lattner and Apple, label=[(0, 5, PL), (21, 35, PERSON), (40, 45, ORG)])]

# Get a spacy compatible generator object
>>> quick.spacy()
<builtins.SpacyGenerator object at 0x102311440>
# Divide the documents into chunks
>>> chunks = quick.spacy(chunks=2)
>>> for chunk in chunks:
...     print(chunk)
...
[('rust is made by Mozilla', {'entitiy': [(0, 4, 'PL'), (16, 23, 'ORG')]}), ('Python was created by Guido van Rossum', {'entitiy': [(0, 6, 'PL'), (22, 38, 'PERSON')]})]
[('Java was created by James Gosling at Sun Microsystems', {'entitiy': [(0, 4, 'PL'), (20, 33, 'PERSON'), (37, 53, 'ORG')]}), ('Swift was created by Chris Lattner and Apple', {'entitiy': [(0, 5, 'PL'), (21, 34, 'PERSON'), (39, 44, 'ORG')]})]

from quickner import Document, Entity

# Create a document from a string
# Method 1
rust = Document.from_string("rust is made by Mozilla")
# Method 2
rust = Document("rust is made by Mozilla")

# Create a list of entities
entities = [Entity("Rust", "PL"), Entity("Mozilla", "ORG")]
# Annotate the document with the entities, case_sensitive is set to False by default
>>> rust.annotate(entities, case_sensitive=True)
>>> rust
Document(id="87e03d58b1ba4d72", text=rust is made by Mozilla, label=[(16, 23, ORG)])
>>> rust.annotate(entities, case_sensitive=False)
>>> rust
Document(id="87e03d58b1ba4d72", text=rust is made by Mozilla, label=[(16, 23, ORG), (0, 4, PL)])

from quickner import Quickner

quick = Quickner.from_jsonl("annotations.jsonl") # load the annotations from a jsonl file
quick = Quickner.from_spacy("annotations.json") # load the annotations from a spaCy file