Merge branch 'rl-0.13.0'

.github/workflows/ci.yml

@@ -6,7 +6,16 @@ jobs:
   tests:
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12', 'pypy-3.8', 'pypy-3.9', 'pypy-3.10']
+        python-version: [
+          '3.8',
+          '3.9',
+          '3.10',
+          '3.11',
+          '3.12',
+          'pypy-3.8',
+          'pypy-3.9',
+          'pypy-3.10'
+        ]
         os: [ubuntu]
       fail-fast: true
     runs-on: ${{ matrix.os }}-latest

.pre-commit-config.yaml

@@ -5,38 +5,44 @@ exclude: >
   )
 fail_fast: false
 repos:
--   repo: local
-    hooks:
-      - id: black
-        name: black
-        entry: black
-        language: system
-        types: [python]
-      - id: isort
-        name: isort
-        entry: isort
-        language: system
-        types: [python]
-        args: ["--profile", "black"]
-      - id: flake8
-        name: flake8
-        entry: flake8
-        language: system
+- repo: local
+  hooks:
+    - id: black
+      name: black
+      entry: black
+      language: system
+      types: [python]
+    - id: isort
+      name: isort
+      entry: isort
+      language: system
+      types: [python]
+      args: ["--profile", "black"]
+    - id: flake8
+      name: flake8
+      entry: flake8
+      language: system
+      types: [ python ]
+    - id: mypy
+      name: mypy
+      entry: mypy
+      language: system
         types: [ python ]
-      - id: mypy
-        name: mypy
-        entry: mypy
-        language: system
-        types: [ python ]
--   repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: v1.3.0
-    hooks:
-      - id: forbid-crlf
--   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
-    hooks:
-      - id: check-case-conflict
-      - id: check-merge-conflict
-      - id: end-of-file-fixer
-      - id: check-yaml
-      - id: check-added-large-files
+- repo: https://github.com/Lucas-C/pre-commit-hooks
+  rev: v1.3.0
+  hooks:
+    - id: forbid-crlf
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.3.0
+  hooks:
+    - id: check-case-conflict
+    - id: check-merge-conflict
+    - id: end-of-file-fixer
+    - id: check-yaml
+    - id: check-added-large-files
+- repo: https://github.com/pycqa/flake8
+  rev: 3.8.4
+  hooks:
+  - id: flake8
+    additional_dependencies:
+    - flake8-encodings==0.5.1

Makefile

@@ -24,7 +24,7 @@ tests:
 docs:
 	@echo "> generate project documentation..."
 	@cp README.md docs/index.md
-	mkdocs serve
+	mkdocs serve -a 0.0.0.0:8000
 
 install-deps:
 	@echo "> installing dependencies..."

README.md

@@ -89,23 +89,16 @@ async with aiopytesseract.run(
 	alto_file, tsv_file, txt_file = resp
 ```
 
+For more details on Tesseract best practices and the aiopytesseract, see the folder: `docs`.
+
 ## Examples
 
 If you want to test **aiopytesseract** easily, can you use some options like:
 
-- docker
-- docker-compose
+- docker/docker-compose
 - [streamlit](https://streamlit.io)
 
-### Docker
-
-Just copy and paste the following line.
-
-```bash
-docker run --rm --name aiopytesseract -p 8501:8501 amenezes/aiopytesseract
-```
-
-### docker-compose
+### Docker / docker-compose
 
 After clone this repo run the command below:
 
@@ -117,15 +110,21 @@ docker-compose up -d
 
 For this option it's necessary first install `aiopytesseract` and `streamlit`, after execute:
 
-```python
+``` py
+# remote option:
 streamlit run https://github.com/amenezes/aiopytesseract/blob/master/examples/streamlit/app.py
 ```
 
+``` py
+# local option:
+streamlit run examples/streamlit/app.py
+```
+
 > note: The streamlit example need **python >= 3.10**
 
 ## Links
 
 - License: [Apache License](https://choosealicense.com/licenses/apache-2.0/)
 - Code: [https://github.com/amenezes/aiopytesseract](https://github.com/amenezes/aiopytesseract)
 - Issue tracker: [https://github.com/amenezes/aiopytesseract/issues](https://github.com/amenezes/aiopytesseract/issues)
-- Docs: [https://aiopytesseract.amenezes.net](https://github.com/amenezes/aiopytesseract)
+- Docs: [https://github.com/amenezes/aiopytesseract](https://github.com/amenezes/aiopytesseract)

aiopytesseract/__init__.py

@@ -16,7 +16,7 @@
 )
 from .models import OSD, Box, Data, Parameter
 
-__version__ = "0.12.0"
+__version__ = "0.13.0"
 __all__ = [
     "__version__",
     "OSD",

aiopytesseract/base_command.py

@@ -1,9 +1,10 @@
 import asyncio
 import shlex
+from asyncio.subprocess import Process
 from collections import deque
 from functools import singledispatch
 from pathlib import Path
-from typing import Any, List, Optional, Tuple
+from typing import Any, List, Tuple, Union
 
 from ._logger import logger
 from .constants import (
@@ -17,7 +18,9 @@
 from .validators import file_exists, language_is_valid, oem_is_valid, psm_is_valid
 
 
-async def execute_cmd(cmd_args: str, timeout: float = AIOPYTESSERACT_DEFAULT_TIMEOUT):
+async def execute_cmd(
+    cmd_args: str, timeout: float = AIOPYTESSERACT_DEFAULT_TIMEOUT
+) -> Process:
     logger.debug(
         f"aiopytesseract command: '{TESSERACT_CMD} {shlex.join(shlex.split(cmd_args))}'"
     )
@@ -31,6 +34,8 @@ async def execute_cmd(cmd_args: str, timeout: float = AIOPYTESSERACT_DEFAULT_TIM
         ),
         timeout=timeout,
     )
+    if proc is None:
+        raise TesseractRuntimeError()
     return proc
 
 
@@ -42,10 +47,10 @@ async def execute(
     psm: int,
     oem: int,
     timeout: float,
-    lang: Optional[str] = None,
-    user_words: Optional[str] = None,
-    user_patterns: Optional[str] = None,
-    tessdata_dir: Optional[str] = None,
+    lang: Union[None, str] = None,
+    user_words: Union[None, str] = None,
+    user_patterns: Union[None, str] = None,
+    tessdata_dir: Union[None, str] = None,
 ) -> bytes:
     raise NotImplementedError
 
@@ -58,10 +63,10 @@ async def _(
     psm: int,
     oem: int,
     timeout: float,
-    lang: Optional[str] = None,
-    user_words: Optional[str] = None,
-    user_patterns: Optional[str] = None,
-    tessdata_dir: Optional[str] = None,
+    lang: Union[None, str] = None,
+    user_words: Union[None, str] = None,
+    user_patterns: Union[None, str] = None,
+    tessdata_dir: Union[None, str] = None,
 ) -> bytes:
     await file_exists(image)
     response: bytes = await execute(
@@ -84,13 +89,13 @@ async def _(
     image: bytes,
     output_format: str,
     dpi: int,
-    lang: Optional[str],
+    lang: Union[None, str],
     psm: int,
     oem: int,
     timeout: float,
-    user_words: Optional[str] = None,
-    user_patterns: Optional[str] = None,
-    tessdata_dir: Optional[str] = None,
+    user_words: Union[None, str] = None,
+    user_patterns: Union[None, str] = None,
+    tessdata_dir: Union[None, str] = None,
     encoding: str = AIOPYTESSERACT_DEFAULT_ENCODING,
 ) -> bytes:
     cmd_args = await _build_cmd_args(
@@ -134,9 +139,9 @@ async def execute_multi_output_cmd(
     psm: int,
     oem: int,
     timeout: float,
-    user_words: Optional[str] = None,
-    user_patterns: Optional[str] = None,
-    tessdata_dir: Optional[str] = None,
+    user_words: Union[None, str] = None,
+    user_patterns: Union[None, str] = None,
+    tessdata_dir: Union[None, str] = None,
     encoding: str = AIOPYTESSERACT_DEFAULT_ENCODING,
 ) -> Tuple[str, ...]:
     cmd_args = await _build_cmd_args(
@@ -168,7 +173,7 @@ async def execute_multi_output_cmd(
     if proc.returncode != ReturnCode.SUCCESS:
         raise TesseractRuntimeError(stderr.decode(encoding))
     return tuple(
-        [f"{output_file}{OUTPUT_FILE_EXTENSIONS[ext]}" for ext in output_format.split()]  # type: ignore
+        [f"{output_file}{OUTPUT_FILE_EXTENSIONS[ext]}" for ext in output_format.split()]
     )
 
 
@@ -177,10 +182,10 @@ async def _build_cmd_args(
     dpi: int,
     psm: int,
     oem: int,
-    user_words: Optional[str] = None,
-    user_patterns: Optional[str] = None,
-    tessdata_dir: Optional[str] = None,
-    lang: Optional[str] = None,
+    user_words: Union[None, str] = None,
+    user_patterns: Union[None, str] = None,
+    tessdata_dir: Union[None, str] = None,
+    lang: Union[None, str] = None,
     output: str = "stdout",
 ) -> List[str]:
     await asyncio.gather(psm_is_valid(psm), oem_is_valid(oem))