[typings] Replace deprecated typing with built-in types (#1794)

.github/verify_pr_labels.py

@@ -11,7 +11,7 @@
 with no labeling responsibility, so we don't want to bother them.
 """
 
-from typing import Any, Set, Tuple
+from typing import Any
 
 import requests
 
@@ -54,7 +54,7 @@ def query_repo(cmd: str, *, accept) -> Any:
     return response.json()
 
 
-def get_pr_merger_and_labels(pr_number: int) -> Tuple[str, Set[str]]:
+def get_pr_merger_and_labels(pr_number: int) -> tuple[str, set[str]]:
     # See https://docs.github.com/en/rest/reference/pulls#get-a-pull-request
     data = query_repo(f"pulls/{pr_number}", accept="application/vnd.github.v3+json")
     merger = data.get("merged_by", {}).get("login")

api/app/routes/detection.py

@@ -3,7 +3,6 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import List
 
 from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
 
@@ -15,8 +14,8 @@
 router = APIRouter()
 
 
-@router.post("/", response_model=List[DetectionOut], status_code=status.HTTP_200_OK, summary="Perform text detection")
-async def text_detection(request: DetectionIn = Depends(), files: List[UploadFile] = [File(...)]):
+@router.post("/", response_model=list[DetectionOut], status_code=status.HTTP_200_OK, summary="Perform text detection")
+async def text_detection(request: DetectionIn = Depends(), files: list[UploadFile] = [File(...)]):
     """Runs docTR text detection model to analyze the input image"""
     try:
         predictor = init_predictor(request)

api/app/routes/kie.py

@@ -3,7 +3,6 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import List
 
 from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
 
@@ -14,8 +13,8 @@
 router = APIRouter()
 
 
-@router.post("/", response_model=List[KIEOut], status_code=status.HTTP_200_OK, summary="Perform KIE")
-async def perform_kie(request: KIEIn = Depends(), files: List[UploadFile] = [File(...)]):
+@router.post("/", response_model=list[KIEOut], status_code=status.HTTP_200_OK, summary="Perform KIE")
+async def perform_kie(request: KIEIn = Depends(), files: list[UploadFile] = [File(...)]):
     """Runs docTR KIE model to analyze the input image"""
     try:
         predictor = init_predictor(request)

api/app/routes/ocr.py

@@ -3,7 +3,6 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import List
 
 from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
 
@@ -14,8 +13,8 @@
 router = APIRouter()
 
 
-@router.post("/", response_model=List[OCROut], status_code=status.HTTP_200_OK, summary="Perform OCR")
-async def perform_ocr(request: OCRIn = Depends(), files: List[UploadFile] = [File(...)]):
+@router.post("/", response_model=list[OCROut], status_code=status.HTTP_200_OK, summary="Perform OCR")
+async def perform_ocr(request: OCRIn = Depends(), files: list[UploadFile] = [File(...)]):
     """Runs docTR OCR model to analyze the input image"""
     try:
         # generator object to list

api/app/routes/recognition.py

@@ -3,7 +3,6 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import List
 
 from fastapi import APIRouter, Depends, File, HTTPException, UploadFile, status
 
@@ -15,9 +14,9 @@
 
 
 @router.post(
-    "/", response_model=List[RecognitionOut], status_code=status.HTTP_200_OK, summary="Perform text recognition"
+    "/", response_model=list[RecognitionOut], status_code=status.HTTP_200_OK, summary="Perform text recognition"
 )
-async def text_recognition(request: RecognitionIn = Depends(), files: List[UploadFile] = [File(...)]):
+async def text_recognition(request: RecognitionIn = Depends(), files: list[UploadFile] = [File(...)]):
     """Runs docTR text recognition model to analyze the input image"""
     try:
         predictor = init_predictor(request)

api/app/schemas.py

@@ -3,7 +3,7 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -54,21 +54,21 @@ class RecognitionOut(BaseModel):
 
 class DetectionOut(BaseModel):
     name: str = Field(..., examples=["example.jpg"])
-    geometries: List[List[float]] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
+    geometries: list[list[float]] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
 
 
 class OCRWord(BaseModel):
     value: str = Field(..., examples=["example"])
-    geometry: List[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
+    geometry: list[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
     objectness_score: float = Field(..., examples=[0.99])
     confidence: float = Field(..., examples=[0.99])
-    crop_orientation: Dict[str, Any] = Field(..., examples=[{"value": 0, "confidence": None}])
+    crop_orientation: dict[str, Any] = Field(..., examples=[{"value": 0, "confidence": None}])
 
 
 class OCRLine(BaseModel):
-    geometry: List[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
+    geometry: list[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
     objectness_score: float = Field(..., examples=[0.99])
-    words: List[OCRWord] = Field(
+    words: list[OCRWord] = Field(
         ...,
         examples=[
             {
@@ -83,9 +83,9 @@ class OCRLine(BaseModel):
 
 
 class OCRBlock(BaseModel):
-    geometry: List[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
+    geometry: list[float] = Field(..., examples=[[0.0, 0.0, 0.0, 0.0]])
     objectness_score: float = Field(..., examples=[0.99])
-    lines: List[OCRLine] = Field(
+    lines: list[OCRLine] = Field(
         ...,
         examples=[
             {
@@ -105,7 +105,7 @@ class OCRBlock(BaseModel):
 
 
 class OCRPage(BaseModel):
-    blocks: List[OCRBlock] = Field(
+    blocks: list[OCRBlock] = Field(
         ...,
         examples=[
             {
@@ -133,10 +133,10 @@ class OCRPage(BaseModel):
 
 class OCROut(BaseModel):
     name: str = Field(..., examples=["example.jpg"])
-    orientation: Dict[str, Union[float, None]] = Field(..., examples=[{"value": 0.0, "confidence": 0.99}])
-    language: Dict[str, Union[str, float, None]] = Field(..., examples=[{"value": "en", "confidence": 0.99}])
-    dimensions: Tuple[int, int] = Field(..., examples=[(100, 100)])
-    items: List[OCRPage] = Field(
+    orientation: dict[str, float | None] = Field(..., examples=[{"value": 0.0, "confidence": 0.99}])
+    language: dict[str, str | float | None] = Field(..., examples=[{"value": "en", "confidence": 0.99}])
+    dimensions: tuple[int, int] = Field(..., examples=[(100, 100)])
+    items: list[OCRPage] = Field(
         ...,
         examples=[
             {
@@ -164,7 +164,7 @@ class OCROut(BaseModel):
 
 class KIEElement(BaseModel):
     class_name: str = Field(..., examples=["example"])
-    items: List[Dict[str, Union[str, List[float], float, Dict[str, Any]]]] = Field(
+    items: list[dict[str, str | list[float] | float | dict[str, Any]]] = Field(
         ...,
         examples=[
             {
@@ -180,7 +180,7 @@ class KIEElement(BaseModel):
 
 class KIEOut(BaseModel):
     name: str = Field(..., examples=["example.jpg"])
-    orientation: Dict[str, Union[float, None]] = Field(..., examples=[{"value": 0.0, "confidence": 0.99}])
-    language: Dict[str, Union[str, float, None]] = Field(..., examples=[{"value": "en", "confidence": 0.99}])
-    dimensions: Tuple[int, int] = Field(..., examples=[(100, 100)])
-    predictions: List[KIEElement]
+    orientation: dict[str, float | None] = Field(..., examples=[{"value": 0.0, "confidence": 0.99}])
+    language: dict[str, str | float | None] = Field(..., examples=[{"value": "en", "confidence": 0.99}])
+    dimensions: tuple[int, int] = Field(..., examples=[(100, 100)])
+    predictions: list[KIEElement]

api/app/utils.py

@@ -4,7 +4,7 @@
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 
-from typing import Any, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 from fastapi import UploadFile
@@ -14,20 +14,20 @@
 
 def resolve_geometry(
     geom: Any,
-) -> Union[Tuple[float, float, float, float], Tuple[float, float, float, float, float, float, float, float]]:
+) -> tuple[float, float, float, float] | tuple[float, float, float, float, float, float, float, float]:
     if len(geom) == 4:
         return (*geom[0], *geom[1], *geom[2], *geom[3])
     return (*geom[0], *geom[1])
 
 
-async def get_documents(files: List[UploadFile]) -> Tuple[List[np.ndarray], List[str]]:  # pragma: no cover
+async def get_documents(files: list[UploadFile]) -> tuple[list[np.ndarray], list[str]]:  # pragma: no cover
     """Convert a list of UploadFile objects to lists of numpy arrays and their corresponding filenames
 
     Args:
         files: list of UploadFile objects
 
     Returns:
-        Tuple[List[np.ndarray], List[str]]: list of numpy arrays and their corresponding filenames
+        tuple[list[np.ndarray], list[str]]: list of numpy arrays and their corresponding filenames
 
     """
     filenames = []

api/app/vision.py

@@ -4,7 +4,7 @@
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
 
-from typing import Callable, Union
+from collections.abc import Callable
 
 import torch
 
@@ -25,7 +25,7 @@ def _move_to_device(predictor: Callable) -> Callable:
     return predictor.to(torch.device("cuda" if torch.cuda.is_available() else "cpu"))
 
 
-def init_predictor(request: Union[KIEIn, OCRIn, RecognitionIn, DetectionIn]) -> Callable:
+def init_predictor(request: KIEIn | OCRIn | RecognitionIn | DetectionIn) -> Callable:
     """Initialize the predictor based on the request
 
     Args:

doctr/contrib/artefacts.py

@@ -3,7 +3,7 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
 import cv2
 import numpy as np
@@ -14,7 +14,7 @@
 
 __all__ = ["ArtefactDetector"]
 
-default_cfgs: Dict[str, Dict[str, Any]] = {
+default_cfgs: dict[str, dict[str, Any]] = {
     "yolov8_artefact": {
         "input_shape": (3, 1024, 1024),
         "labels": ["bar_code", "qr_code", "logo", "photo"],
@@ -49,9 +49,9 @@ def __init__(
         self,
         arch: str = "yolov8_artefact",
         batch_size: int = 2,
-        model_path: Optional[str] = None,
-        labels: Optional[List[str]] = None,
-        input_shape: Optional[Tuple[int, int, int]] = None,
+        model_path: str | None = None,
+        labels: list[str] | None = None,
+        input_shape: tuple[int, int, int] | None = None,
         conf_threshold: float = 0.5,
         iou_threshold: float = 0.5,
         **kwargs: Any,
@@ -65,7 +65,7 @@ def __init__(
     def preprocess(self, img: np.ndarray) -> np.ndarray:
         return np.transpose(cv2.resize(img, (self.input_shape[2], self.input_shape[1])), (2, 0, 1)) / np.array(255.0)
 
-    def postprocess(self, output: List[np.ndarray], input_images: List[List[np.ndarray]]) -> List[List[Dict[str, Any]]]:
+    def postprocess(self, output: list[np.ndarray], input_images: list[list[np.ndarray]]) -> list[list[dict[str, Any]]]:
         results = []
 
         for batch in zip(output, input_images):

doctr/contrib/base.py

@@ -3,7 +3,7 @@
 # This program is licensed under the Apache License 2.0.
 # See LICENSE or go to <https://opensource.org/licenses/Apache-2.0> for full license details.
 
-from typing import Any, List, Optional
+from typing import Any
 
 import numpy as np
 
@@ -22,14 +22,14 @@ class _BasePredictor:
         **kwargs: additional arguments to be passed to `download_from_url`
     """
 
-    def __init__(self, batch_size: int, url: Optional[str] = None, model_path: Optional[str] = None, **kwargs) -> None:
+    def __init__(self, batch_size: int, url: str | None = None, model_path: str | None = None, **kwargs) -> None:
         self.batch_size = batch_size
         self.session = self._init_model(url, model_path, **kwargs)
 
-        self._inputs: List[np.ndarray] = []
-        self._results: List[Any] = []
+        self._inputs: list[np.ndarray] = []
+        self._results: list[Any] = []
 
-    def _init_model(self, url: Optional[str] = None, model_path: Optional[str] = None, **kwargs: Any) -> Any:
+    def _init_model(self, url: str | None = None, model_path: str | None = None, **kwargs: Any) -> Any:
         """
         Download the model from the given url if needed
 
@@ -61,7 +61,7 @@ def preprocess(self, img: np.ndarray) -> np.ndarray:
         """
         raise NotImplementedError
 
-    def postprocess(self, output: List[np.ndarray], input_images: List[List[np.ndarray]]) -> Any:
+    def postprocess(self, output: list[np.ndarray], input_images: list[list[np.ndarray]]) -> Any:
         """
         Postprocess the model output
 
@@ -74,7 +74,7 @@ def postprocess(self, output: List[np.ndarray], input_images: List[List[np.ndarr
         """
         raise NotImplementedError
 
-    def __call__(self, inputs: List[np.ndarray]) -> Any:
+    def __call__(self, inputs: list[np.ndarray]) -> Any:
         """
         Call the model on the given inputs
 

doctr/datasets/cord.py

@@ -6,7 +6,7 @@
 import json
 import os
 from pathlib import Path
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any
 
 import numpy as np
 from tqdm import tqdm
@@ -71,9 +71,9 @@ def __init__(
                 + "To get the whole dataset with boxes and labels leave both parameters to False."
             )
 
-        # List images
+        # list images
         tmp_root = os.path.join(self.root, "image")
-        self.data: List[Tuple[Union[str, np.ndarray], Union[str, Dict[str, Any], np.ndarray]]] = []
+        self.data: list[tuple[str | np.ndarray, str | dict[str, Any] | np.ndarray]] = []
         self.train = train
         np_dtype = np.float32
         for img_path in tqdm(iterable=os.listdir(tmp_root), desc="Unpacking CORD", total=len(os.listdir(tmp_root))):
@@ -90,7 +90,7 @@ def __init__(
                         if len(word["text"]) > 0:
                             x = word["quad"]["x1"], word["quad"]["x2"], word["quad"]["x3"], word["quad"]["x4"]
                             y = word["quad"]["y1"], word["quad"]["y2"], word["quad"]["y3"], word["quad"]["y4"]
-                            box: Union[List[float], np.ndarray]
+                            box: list[float] | np.ndarray
                             if use_polygons:
                                 # (x, y) coordinates of top left, top right, bottom right, bottom left corners
                                 box = np.array(