Camel.loaders.base io

​

create_file

def create_file(file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the file.
• filename (str): The name of the file.

​

create_file_from_raw_bytes

def create_file_from_raw_bytes(raw_bytes: bytes, filename: str):

• raw_bytes (bytes): The raw bytes content of the file.
• filename (str): The name of the file.

​

File

class File(ABC):

• name (str): The name of the file.
• file_id (str): The unique identifier of the file.
• metadata (Dict[str, Any], optional): Additional metadata associated with the file. Defaults to None.
• docs (List[Dict[str, Any]], optional): A list of documents contained within the file. Defaults to None.
• raw_bytes (bytes, optional): The raw bytes content of the file. Defaults to b"".

​

init

def __init__(
    self,
    name: str,
    file_id: str,
    metadata: Optional[Dict[str, Any]] = None,
    docs: Optional[List[Dict[str, Any]]] = None,
    raw_bytes: bytes = b''
):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the file.
• filename (str): The name of the file.

​

from_raw_bytes

def from_raw_bytes(cls, raw_bytes: bytes, filename: str):

• raw_bytes (bytes): The raw bytes content of the file.
• filename (str): The name of the file.

​

repr

def __repr__(self):

​

str

def __str__(self):

​

copy

def copy(self):

​

strip_consecutive_newlines

def strip_consecutive_newlines(text: str):

• text (str): The string to strip.

​

DocxFile

class DocxFile(File):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the docx file.
• filename (str): The name of the file.

​

PdfFile

class PdfFile(File):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the pdf file.
• filename (str): The name of the file.

​

TxtFile

class TxtFile(File):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the txt file.
• filename (str): The name of the file.

​

JsonFile

class JsonFile(File):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the json file.
• filename (str): The name of the file.

​

HtmlFile

class HtmlFile(File):

​

from_bytes

def from_bytes(cls, file: BytesIO, filename: str):

• file (BytesIO): A BytesIO object representing the contents of the html file.
• filename (str): The name of the file.