Merge branch 'rl-0.10.0-RC01'

amenezes · Dec 4, 2022 · 5a4d45e · 5a4d45e
2 parents 2f331d6 + 6312b8a
commit 5a4d45e
Show file tree

Hide file tree

Showing 24 changed files with 283 additions and 118 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -6,7 +6,7 @@ jobs:
   tests:
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', 'pypy-3.8', 'pypy-3.9']
+        python-version: ['3.8', '3.9', '3.10', '3.11', 'pypy-3.8', 'pypy-3.9']
         os: [ubuntu]
       fail-fast: true
     runs-on: ${{ matrix.os }}-latest

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -0,0 +1,42 @@
+exclude: >
+  (?x)(
+    ^alembic.ini$|
+    ^migrations/
+  )
+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
+        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
diff --git a/Makefile b/Makefile
@@ -4,8 +4,8 @@ VERSION := $(shell cat aiopytesseract/__init__.py | grep '__version__ ' | cut -d
 lint:
 ifeq ($(SKIP_STYLE), )
 	@echo "> running isort..."
-	isort aiopytesseract/
-	isort tests/
+	isort aiopytesseract
+	isort tests
 	isort examples
 	@echo "> running black..."
 	black aiopytesseract
@@ -23,11 +23,13 @@ tests:
 
 docs:
 	@echo "> generate project documentation..."
-	portray server
+	@cp README.md docs/index.md
+	mkdocs serve
 
 install-deps:
 	@echo "> installing dependencies..."
 	pip install -r requirements-dev.txt
+	pre-commit install
 
 tox:
 	@echo "> running tox..."
@@ -47,16 +49,10 @@ about:
 
 ci: lint tests
 ifeq ($(GITHUB_HEAD_REF), false)
-	@echo "> download CI dependencies"
-	curl -L https://codeclimate.com/downloads/test-reporter/test-reporter-latest-linux-amd64 > ./cc-test-reporter
-	chmod +x ./cc-test-reporter
 	@echo "> uploading report..."
 	codecov --file coverage.xml -t $$CODECOV_TOKEN
-	./cc-test-reporter format-coverage -t coverage.py -o codeclimate.json
-	./cc-test-reporter upload-coverage -i codeclimate.json -r $$CC_TEST_REPORTER_ID
 endif
 
 all: install-deps ci
 
-
 .PHONY: lint tests ci docs install-deps tox all
diff --git a/aiopytesseract/__init__.py b/aiopytesseract/__init__.py
@@ -1,22 +1,11 @@
-from .commands import (
-    confidence,
-    deskew,
-    get_languages,
-    get_tesseract_version,
-    image_to_boxes,
-    image_to_data,
-    image_to_hocr,
-    image_to_osd,
-    image_to_pdf,
-    image_to_string,
-    languages,
-    run,
-    tesseract_parameters,
-    tesseract_version,
-)
+from .commands import (confidence, deskew, get_languages,
+                       get_tesseract_version, image_to_boxes, image_to_data,
+                       image_to_hocr, image_to_osd, image_to_pdf,
+                       image_to_string, languages, run, tesseract_parameters,
+                       tesseract_version)
 from .models import OSD, Box, Data, Parameter
 
-__version__ = "0.9.0"
+__version__ = "0.10.0"
 __all__ = [
     "__version__",
     "OSD",

diff --git a/aiopytesseract/base_command.py b/aiopytesseract/base_command.py
@@ -6,15 +6,13 @@
 from typing import Any, List, Optional, Tuple
 
 from ._logger import logger
-from .constants import (
-    AIOPYTESSERACT_DEFAULT_ENCODING,
-    AIOPYTESSERACT_DEFAULT_TIMEOUT,
-    OUTPUT_FILE_EXTENSIONS,
-    TESSERACT_CMD,
-)
+from .constants import (AIOPYTESSERACT_DEFAULT_ENCODING,
+                        AIOPYTESSERACT_DEFAULT_TIMEOUT, OUTPUT_FILE_EXTENSIONS,
+                        TESSERACT_CMD)
 from .exceptions import TesseractRuntimeError, TesseractTimeoutError
 from .returncode import ReturnCode
-from .validators import file_exists, language_is_valid, oem_is_valid, psm_is_valid
+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):

diff --git a/aiopytesseract/validators.py b/aiopytesseract/validators.py
@@ -1,12 +1,9 @@
 from pathlib import Path
 
-from .constants import OCR_ENGINE_MODES, PAGE_SEGMENTATION_MODES, TESSERACT_LANGUAGES
-from .exceptions import (
-    LanguageInvalidException,
-    NoSuchFileException,
-    OEMInvalidException,
-    PSMInvalidException,
-)
+from .constants import (OCR_ENGINE_MODES, PAGE_SEGMENTATION_MODES,
+                        TESSERACT_LANGUAGES)
+from .exceptions import (LanguageInvalidException, NoSuchFileException,
+                         OEMInvalidException, PSMInvalidException)
 
 
 async def psm_is_valid(psm: int) -> None:

diff --git a/docs/best-practices.md b/docs/best-practices.md
@@ -0,0 +1,15 @@
+## Tips to improve recognition
+
+### Reference
+
+- [https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html](https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html)
+- [https://www.pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/](https://www.pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/)
+
+
+## Tesseract Command line
+
+### Reference
+
+- [https://tesseract-ocr.github.io/tessdoc/](https://tesseract-ocr.github.io/tessdoc/)
+- [https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html](https://tesseract-ocr.github.io/tessdoc/Command-Line-Usage.html)
+- [https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc](https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc)
diff --git a/docs/development.md b/docs/development.md
@@ -0,0 +1,24 @@
+# Development
+
+## Install development dependencies
+
+```bash
+make install-deps
+```
+
+> OR: pip install -r requirements-dev.txt
+
+## Execute tests
+
+```bash
+make tests
+```
+
+> OR: pytest
+
+## Generating documentation locally.
+
+```bash
+pip install 'aiopytesseract[docs]'
+make docs
+```
diff --git a/docs/index.md b/docs/index.md
@@ -0,0 +1,131 @@
+[![ci](https://github.com/amenezes/aiopytesseract/actions/workflows/ci.yml/badge.svg)](https://github.com/amenezes/aiopytesseract/actions/workflows/ci.yml)
+[![codecov](https://codecov.io/gh/amenezes/aiopytesseract/branch/master/graph/badge.svg)](https://codecov.io/gh/amenezes/aiopytesseract)
+[![PyPI version](https://badge.fury.io/py/aiopytesseract.svg)](https://badge.fury.io/py/aiopytesseract)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/aiopytesseract)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+# aiopytesseract
+
+A Python [asyncio](https://docs.python.org/3/library/asyncio.html) wrapper for [Tesseract-OCR](https://tesseract-ocr.github.io/tessdoc/).
+
+## Installation
+
+Install and update using pip:
+
+````bash
+pip install aiopytesseract
+````
+
+## Usage
+
+```python
+from pathlib import Path
+
+import aiopytesseract
+
+
+# list all available languages by tesseract installation
+await aiopytesseract.languages()
+await aiopytesseract.get_languages()
+
+
+# tesseract version
+await aiopytesseract.tesseract_version()
+await aiopytesseract.get_tesseract_version()
+
+
+# tesseract parameters
+await aiopytesseract.tesseract_parameters()
+
+
+# confidence only info
+await aiopytesseract.confidence("tests/samples/file-sample_150kB.png")
+
+
+# deskew info
+await aiopytesseract.deskew("tests/samples/file-sample_150kB.png")
+
+
+# extract text from an image: locally or bytes
+await aiopytesseract.image_to_string("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_string(
+	Path("tests/samples/file-sample_150kB.png")read_bytes(), dpi=220, lang='eng+por'
+)
+
+
+# box estimates
+await aiopytesseract.image_to_boxes("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_boxes(Path("tests/samples/file-sample_150kB.png")
+
+
+# boxes, confidence and page numbers
+await aiopytesseract.image_to_data("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_data(Path("tests/samples/file-sample_150kB.png")
+
+
+# information about orientation and script detection
+await aiopytesseract.image_to_osd("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_osd(Path("tests/samples/file-sample_150kB.png")
+
+
+# generate a searchable PDF
+await aiopytesseract.image_to_pdf("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_pdf(Path("tests/samples/file-sample_150kB.png")
+
+
+# generate HOCR output
+await aiopytesseract.image_to_hocr("tests/samples/file-sample_150kB.png")
+await aiopytesseract.image_to_hocr(Path("tests/samples/file-sample_150kB.png")
+
+
+# multi ouput
+async with aiopytesseract.run(
+	Path('tests/samples/file-sample_150kB.png').read_bytes(),
+	'output',
+	'alto tsv txt'
+) as resp:
+	# will generate (output.xml, output.tsv and output.txt)
+	print(resp)
+	alto_file, tsv_file, txt_file = resp
+```
+
+## Examples
+
+If you want to test **aiopytesseract** easily, can you use some options like:
+
+- 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
+
+After clone this repo run the command below:
+
+```bash
+docker-compose up -d
+```
+
+### streamlit app
+
+For this option it's necessary first install `aiopytesseract` and `streamlit`, after execute:
+
+```python
+streamlit run https://github.com/amenezes/aiopytesseract/blob/master/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)
diff --git a/docs/more.md b/docs/more.md
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -0,0 +1,42 @@
+site_name: aiopytesseract
+repo_url: https://github.com/amenezes/aiopytesseract
+repo_name: amenezes/aiopytesseract
+theme:
+  name: material
+  features:
+    - navigation.instant
+    - navigation.top
+    - navigation.prune
+    - toc.integrate 
+    - search.highlight
+    - search.suggest
+    - search.share
+    - content.code.annotate
+    - content.tooltips
+    - toc.follow
+  palette:
+    - scheme: default
+      primary: blue grey
+      accent: indigo
+      toggle:
+        icon: material/lightbulb-on
+        name: Switch to dark mode
+    - scheme: slate
+      primary: blue grey
+      accent: indigo
+      toggle:
+        icon: material/lightbulb
+        name: Switch to light mode
+  icon:
+    repo: fontawesome/brands/github-alt
+extra:
+  social:
+    - icon: fontawesome/brands/github
+      link: https://github.com/amenezes/aiopytesseract
+    - icon: fontawesome/solid/bug
+      link: https://github.com/amenezes/aiopytesseract/issues
+    - icon: fontawesome/solid/envelope
+      link: mailto:[email protected]
+nav:
+- Best practices: best-practices.md
+- Development: development.md