ocrmypdf-rapidocr 1.0.0__tar.gz

ocrmypdf_rapidocr-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Adrian Mazur
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ocrmypdf_rapidocr-1.0.0/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.3
+Name: ocrmypdf-rapidocr
+Version: 1.0.0
+Author: Adrian Mazur
+License: MIT License
+         
+         Copyright (c) 2026 Adrian Mazur
+         
+         Permission is hereby granted, free of charge, to any person obtaining a copy
+         of this software and associated documentation files (the "Software"), to deal
+         in the Software without restriction, including without limitation the rights
+         to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+         copies of the Software, and to permit persons to whom the Software is
+         furnished to do so, subject to the following conditions:
+         
+         The above copyright notice and this permission notice shall be included in all
+         copies or substantial portions of the Software.
+         
+         THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+         IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+         FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+         AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+         LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+         OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+         SOFTWARE.
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Dist: ocrmypdf>=17.3.0
+Requires-Dist: onnxruntime>=1.24.3
+Requires-Dist: rapidocr>=3.7.0
+Requires-Python: >=3.12
+Project-URL: Homepage, https://github.com/adrianmazur-dev/ocrmypdf-rapidocr
+Project-URL: Repository, https://github.com/adrianmazur-dev/ocrmypdf-rapidocr.git
+Description-Content-Type: text/markdown
+
+# ocrmypdf-rapidocr
+
+`ocrmypdf-rapidocr` is an OCRmyPDF plugin that uses [RapidOCR](https://github.com/RapidAI/RapidOCR) as an OCR engine.
+
+## Status
+
+Supported:
+
+- OCR engine integration via OCRmyPDF plugin hooks
+- `hOCR` output path (`--pdf-renderer auto` or `--pdf-renderer fpdf2`)
+- ONNXRuntime backend only
+- Single language selection from `-l/--language`
+
+Not supported:
+
+- `--pdf-renderer sandwich`
+- multi-language combinations such as `-l eng+fra`
+
+## Installation
+
+```bash
+pip install ocrmypdf-rapidocr
+```
+
+Or from source:
+
+```bash
+pip install .
+```
+
+## Usage
+
+Load the plugin explicitly with `--plugin`:
+
+```bash
+ocrmypdf --plugin ocrmypdf_rapidocr -l eng input.pdf output.pdf
+```
+
+Optional plugin arguments:
+
+- `--rapidocr-config-path PATH`: use a custom RapidOCR YAML config
+
+Example:
+
+```bash
+ocrmypdf \
+  --plugin ocrmypdf_rapidocr \
+  -l deu \
+  input.pdf output.pdf
+```
+
+## Language behavior
+
+The plugin uses the first OCRmyPDF language code and maps it to RapidOCR language families.
+
+- direct mappings: `eng`, `chi_sim`, `chi_tra`, `jpn`, `kor`, `ara`, `rus`, `ukr`, `tha`, `tam`, `tel`, `ell`/`gre`
+- selected Latin-script codes map to RapidOCR `LATIN`
+
+If a language code is unsupported, OCRmyPDF exits with a clear error message.
+
+## Runtime model downloads
+
+RapidOCR downloads model files on first use when model paths are not pinned in config.
+For offline or restricted environments, provide a custom config via
+`--rapidocr-config-path` that points to local model files.
+
+## References
+
+- OCRmyPDF plugin API docs: <https://github.com/ocrmypdf/OCRmyPDF/blob/main/docs/plugins.md>
+- OCRmyPDF EasyOCR reference plugin: <https://github.com/ocrmypdf/OCRmyPDF-EasyOCR>
+- OCRmyPDF AppleOCR reference plugin: <https://github.com/mkyt/OCRmyPDF-AppleOCR>
+- OCRmyPDF PaddleOCR reference plugin: <https://github.com/clefru/ocrmypdf-paddleocr>
+- RapidOCR project: <https://github.com/RapidAI/RapidOCR>

ocrmypdf_rapidocr-1.0.0/README.md

@@ -0,0 +1,73 @@
+# ocrmypdf-rapidocr
+
+`ocrmypdf-rapidocr` is an OCRmyPDF plugin that uses [RapidOCR](https://github.com/RapidAI/RapidOCR) as an OCR engine.
+
+## Status
+
+Supported:
+
+- OCR engine integration via OCRmyPDF plugin hooks
+- `hOCR` output path (`--pdf-renderer auto` or `--pdf-renderer fpdf2`)
+- ONNXRuntime backend only
+- Single language selection from `-l/--language`
+
+Not supported:
+
+- `--pdf-renderer sandwich`
+- multi-language combinations such as `-l eng+fra`
+
+## Installation
+
+```bash
+pip install ocrmypdf-rapidocr
+```
+
+Or from source:
+
+```bash
+pip install .
+```
+
+## Usage
+
+Load the plugin explicitly with `--plugin`:
+
+```bash
+ocrmypdf --plugin ocrmypdf_rapidocr -l eng input.pdf output.pdf
+```
+
+Optional plugin arguments:
+
+- `--rapidocr-config-path PATH`: use a custom RapidOCR YAML config
+
+Example:
+
+```bash
+ocrmypdf \
+  --plugin ocrmypdf_rapidocr \
+  -l deu \
+  input.pdf output.pdf
+```
+
+## Language behavior
+
+The plugin uses the first OCRmyPDF language code and maps it to RapidOCR language families.
+
+- direct mappings: `eng`, `chi_sim`, `chi_tra`, `jpn`, `kor`, `ara`, `rus`, `ukr`, `tha`, `tam`, `tel`, `ell`/`gre`
+- selected Latin-script codes map to RapidOCR `LATIN`
+
+If a language code is unsupported, OCRmyPDF exits with a clear error message.
+
+## Runtime model downloads
+
+RapidOCR downloads model files on first use when model paths are not pinned in config.
+For offline or restricted environments, provide a custom config via
+`--rapidocr-config-path` that points to local model files.
+
+## References
+
+- OCRmyPDF plugin API docs: <https://github.com/ocrmypdf/OCRmyPDF/blob/main/docs/plugins.md>
+- OCRmyPDF EasyOCR reference plugin: <https://github.com/ocrmypdf/OCRmyPDF-EasyOCR>
+- OCRmyPDF AppleOCR reference plugin: <https://github.com/mkyt/OCRmyPDF-AppleOCR>
+- OCRmyPDF PaddleOCR reference plugin: <https://github.com/clefru/ocrmypdf-paddleocr>
+- RapidOCR project: <https://github.com/RapidAI/RapidOCR>

ocrmypdf_rapidocr-1.0.0/pyproject.toml

@@ -0,0 +1,36 @@
+[project]
+name = "ocrmypdf-rapidocr"
+readme = "README.md"
+license = { file = "LICENSE" }
+authors = [{ name = "Adrian Mazur" }]
+version = "1.0.0"
+requires-python = ">=3.12"
+classifiers = [
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+]
+dependencies = ["ocrmypdf>=17.3.0", "onnxruntime>=1.24.3", "rapidocr>=3.7.0"]
+
+[dependency-groups]
+dev = [
+    "pytest>=9.0.2",
+    "pytest-cov>=7.0.0",
+    "rapidfuzz>=3.14.1",
+    "ruff>=0.15.5",
+    "ty>=0.0.21",
+]
+
+[tool.ruff]
+exclude = ["tests"]
+
+[tool.ty.src]
+exclude = ["tests"]
+
+[project.urls]
+Homepage = "https://github.com/adrianmazur-dev/ocrmypdf-rapidocr"
+Repository = "https://github.com/adrianmazur-dev/ocrmypdf-rapidocr.git"
+
+[build-system]
+requires = ["uv_build>=0.10.8,<0.11.0"]
+build-backend = "uv_build"

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/__init__.py

@@ -0,0 +1,11 @@
+from __future__ import annotations
+
+from ocrmypdf_rapidocr.plugin import add_options, check_options, get_ocr_engine
+from ocrmypdf_rapidocr.version import __version__
+
+__all__ = [
+    "__version__",
+    "add_options",
+    "check_options",
+    "get_ocr_engine",
+]

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/engine.py

@@ -0,0 +1,103 @@
+from __future__ import annotations
+
+import importlib.metadata
+from functools import lru_cache
+from pathlib import Path
+
+from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
+from PIL import Image
+
+from ocrmypdf_rapidocr.hocr import build_hocr_document, extract_hocr_lines
+from ocrmypdf_rapidocr.languages import (
+    SUPPORTED_LANGUAGE_CODES,
+    map_language_to_langrec_name,
+    select_single_language,
+)
+from ocrmypdf_rapidocr.options import get_option_config_path
+from ocrmypdf_rapidocr.version import __version__
+
+
+def _import_rapidocr_symbols():
+    from rapidocr import EngineType, LangRec, RapidOCR
+
+    return RapidOCR, LangRec, EngineType
+
+
+@lru_cache(maxsize=16)
+def get_rapidocr_engine(language: str, config_path: str | None):
+    RapidOCR, LangRec, EngineType = _import_rapidocr_symbols()
+
+    langrec_name = map_language_to_langrec_name(language)
+    langrec_value = getattr(LangRec, langrec_name)
+
+    params = {
+        "Det.engine_type": EngineType.ONNXRUNTIME,
+        "Cls.engine_type": EngineType.ONNXRUNTIME,
+        "Rec.engine_type": EngineType.ONNXRUNTIME,
+        "Rec.lang_type": langrec_value,
+    }
+    return RapidOCR(config_path=config_path, params=params)
+
+
+class RapidOCREngine(OcrEngine):
+    @staticmethod
+    def version() -> str:
+        try:
+            return importlib.metadata.version("rapidocr")
+        except importlib.metadata.PackageNotFoundError:
+            return "unknown"
+
+    @staticmethod
+    def creator_tag(options) -> str:
+        return (
+            f"RapidOCR {RapidOCREngine.version()} via ocrmypdf-rapidocr {__version__}"
+        )
+
+    def __str__(self) -> str:
+        return f"RapidOCR {RapidOCREngine.version()}"
+
+    @staticmethod
+    def languages(options) -> set[str]:
+        return set(SUPPORTED_LANGUAGE_CODES)
+
+    @staticmethod
+    def get_orientation(input_file, options) -> OrientationConfidence:
+        return OrientationConfidence(angle=0, confidence=0.0)
+
+    @staticmethod
+    def get_deskew(input_file, options) -> float:
+        return 0.0
+
+    @staticmethod
+    def generate_hocr(input_file, output_hocr, output_text, options) -> None:
+        language = select_single_language(options)
+        config_path = get_option_config_path(options)
+        rapidocr_engine = get_rapidocr_engine(
+            language,
+            config_path,
+        )
+
+        with Image.open(input_file) as image:
+            page_width, page_height = image.size
+
+        result = rapidocr_engine(str(input_file))
+        lines = extract_hocr_lines(
+            result, page_width=page_width, page_height=page_height
+        )
+        hocr = build_hocr_document(
+            page_width=page_width,
+            page_height=page_height,
+            language=language,
+            lines=lines,
+        )
+        plain_text = "\n".join(text for text, _bbox, _confidence in lines)
+
+        Path(output_hocr).write_text(hocr, encoding="utf-8")
+        Path(output_text).write_text(plain_text, encoding="utf-8")
+
+    @staticmethod
+    def generate_pdf(input_file, output_pdf, output_text, options) -> None:
+        raise NotImplementedError(
+            "ocrmypdf-rapidocr does not support sandwich renderer. "
+            "Use --pdf-renderer auto or --pdf-renderer fpdf2."
+        )

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/hocr.py

@@ -0,0 +1,118 @@
+from __future__ import annotations
+
+from html import escape
+from typing import Any
+
+HocrLine = tuple[str, tuple[int, int, int, int], int]
+
+
+def confidence_to_percent(score: Any) -> int:
+    if score is None:
+        return 0
+    try:
+        value = float(score)
+    except (TypeError, ValueError):
+        return 0
+    if value <= 1.0:
+        value *= 100.0
+    return max(0, min(100, int(round(value))))
+
+
+def bbox_from_polygon(polygon: Any, width: int, height: int) -> tuple[int, int, int, int]:
+    try:
+        points = list(polygon)
+    except TypeError:
+        return (0, 0, width, height)
+
+    xs: list[float] = []
+    ys: list[float] = []
+    for point in points:
+        try:
+            x = float(point[0])
+            y = float(point[1])
+        except (TypeError, ValueError, IndexError):
+            continue
+        xs.append(x)
+        ys.append(y)
+
+    if not xs or not ys:
+        return (0, 0, width, height)
+
+    x0 = max(0, min(width - 1, int(round(min(xs)))))
+    y0 = max(0, min(height - 1, int(round(min(ys)))))
+    x1 = max(x0 + 1, min(width, int(round(max(xs)))))
+    y1 = max(y0 + 1, min(height, int(round(max(ys)))))
+    return (x0, y0, x1, y1)
+
+
+def extract_hocr_lines(
+    result: Any,
+    *,
+    page_width: int,
+    page_height: int,
+) -> list[HocrLine]:
+    boxes_raw = getattr(result, "boxes", None)
+    texts_raw = getattr(result, "txts", None)
+    scores_raw = getattr(result, "scores", None)
+
+    boxes = list(boxes_raw) if boxes_raw is not None else []
+    texts = list(texts_raw) if texts_raw is not None else []
+    scores = list(scores_raw) if scores_raw is not None else []
+    count = min(len(boxes), len(texts))
+
+    extracted: list[HocrLine] = []
+    for index in range(count):
+        text = str(texts[index]).strip()
+        if not text:
+            continue
+        box = boxes[index]
+        score = scores[index] if index < len(scores) else None
+        bbox = bbox_from_polygon(box, page_width, page_height)
+        confidence = confidence_to_percent(score)
+        extracted.append((text, bbox, confidence))
+    return extracted
+
+
+def build_hocr_document(
+    *,
+    page_width: int,
+    page_height: int,
+    language: str,
+    lines: list[HocrLine],
+) -> str:
+    hocr_lines = [
+        '<?xml version="1.0" encoding="UTF-8"?>',
+        '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"',
+        '    "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">',
+        '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">',
+        "<head>",
+        "<title></title>",
+        '<meta http-equiv="content-type" content="text/html; charset=utf-8" />',
+        '<meta name="ocr-system" content="RapidOCR via ocrmypdf-rapidocr" />',
+        '<meta name="ocr-capabilities" content="ocr_page ocr_carea ocr_par ocr_line ocrx_word" />',
+        "</head>",
+        "<body>",
+        f'<div class="ocr_page" id="page_1" title="bbox 0 0 {page_width} {page_height}">',
+    ]
+
+    for line_id, (text, bbox, confidence) in enumerate(lines, start=1):
+        x0, y0, x1, y1 = bbox
+        text_escaped = escape(text, quote=False)
+        hocr_lines.append(
+            f'<div class="ocr_carea" id="carea_{line_id}" title="bbox {x0} {y0} {x1} {y1}">'
+        )
+        hocr_lines.append(
+            f'<p class="ocr_par" id="par_{line_id}" lang="{language}" title="bbox {x0} {y0} {x1} {y1}">'
+        )
+        hocr_lines.append(
+            f'<span class="ocr_line" id="line_{line_id}" '
+            f'title="bbox {x0} {y0} {x1} {y1}; baseline 0 0; x_wconf {confidence}">'
+        )
+        hocr_lines.append(
+            f'<span class="ocrx_word" id="word_{line_id}" '
+            f'title="bbox {x0} {y0} {x1} {y1}; x_wconf {confidence}">{text_escaped}</span>'
+        )
+        hocr_lines.extend(["</span>", "</p>", "</div>"])
+
+    hocr_lines.extend(["</div>", "</body>", "</html>"])
+    return "\n".join(hocr_lines)

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/languages.py

@@ -0,0 +1,105 @@
+from __future__ import annotations
+
+from typing import Any, Sequence
+
+from ocrmypdf.exceptions import BadArgsError
+
+# Map OCRmyPDF/Tesseract language codes to RapidOCR LangRec values.
+_DIRECT_LANGUAGE_MAP: dict[str, str] = {
+    "ara": "ARABIC",
+    "chi_sim": "CH",
+    "chi_tra": "CHINESE_CHT",
+    "eng": "EN",
+    "ell": "EL",
+    "gre": "EL",
+    "jpn": "JAPAN",
+    "kor": "KOREAN",
+    "tha": "TH",
+    "tam": "TA",
+    "tel": "TE",
+    "bel": "CYRILLIC",
+    "bul": "CYRILLIC",
+    "mkd": "CYRILLIC",
+    "rus": "CYRILLIC",
+    "srp": "CYRILLIC",
+    "ukr": "CYRILLIC",
+}
+
+_LATIN_LANGUAGE_CODES: set[str] = {
+    "afr",
+    "cat",
+    "ces",
+    "dan",
+    "deu",
+    "est",
+    "eus",
+    "fin",
+    "fra",
+    "gle",
+    "hrv",
+    "hun",
+    "ind",
+    "isl",
+    "ita",
+    "lav",
+    "lit",
+    "mlt",
+    "msa",
+    "nld",
+    "nor",
+    "pol",
+    "por",
+    "ron",
+    "slk",
+    "slv",
+    "spa",
+    "sqi",
+    "swe",
+    "tgl",
+    "tur",
+    "vie",
+}
+
+SUPPORTED_LANGUAGE_CODES: frozenset[str] = frozenset(
+    set(_DIRECT_LANGUAGE_MAP) | _LATIN_LANGUAGE_CODES
+)
+
+
+def normalize_languages(languages: Sequence[str] | None) -> list[str]:
+    if not languages:
+        return ["eng"]
+    return [
+        str(language).strip().lower() for language in languages if str(language).strip()
+    ]
+
+
+def select_single_language(options: Any) -> str:
+    languages = normalize_languages(getattr(options, "languages", None))
+    if len(languages) != 1:
+        raise BadArgsError(
+            "RapidOCR supports exactly one language. "
+            "Pass a single language to -l/--language."
+        )
+
+    language = languages[0]
+    if "+" in language:
+        raise BadArgsError(
+            "RapidOCR does not support language combinations like eng+fra."
+        )
+
+    if language not in SUPPORTED_LANGUAGE_CODES:
+        supported = ", ".join(sorted(SUPPORTED_LANGUAGE_CODES))
+        raise BadArgsError(
+            f"Language '{language}' is not supported by ocrmypdf-rapidocr. "
+            f"Supported values: {supported}"
+        )
+    return language
+
+
+def map_language_to_langrec_name(language: str) -> str:
+    normalized = language.lower()
+    if normalized in _DIRECT_LANGUAGE_MAP:
+        return _DIRECT_LANGUAGE_MAP[normalized]
+    if normalized in _LATIN_LANGUAGE_CODES:
+        return "LATIN"
+    raise KeyError(normalized)

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/options.py

@@ -0,0 +1,56 @@
+from __future__ import annotations
+
+import importlib.util
+from pathlib import Path
+from typing import Any
+
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
+
+
+def is_rapidocr_selected(options: Any) -> bool:
+    return getattr(options, "ocr_engine", "auto") in ("auto", "rapidocr")
+
+
+def add_plugin_options(parser) -> None:
+    rapidocr_options = parser.add_argument_group("RapidOCR", "RapidOCR engine options")
+    rapidocr_options.add_argument(
+        "--rapidocr-config-path",
+        default=None,
+        help=(
+            "Path to a RapidOCR YAML config file. "
+            "If omitted, RapidOCR defaults are used."
+        ),
+    )
+
+
+def check_runtime_dependencies() -> None:
+    if importlib.util.find_spec("rapidocr") is None:
+        raise MissingDependencyError(
+            "RapidOCR is not installed. Install it with: pip install rapidocr"
+        )
+    if importlib.util.find_spec("onnxruntime") is None:
+        raise MissingDependencyError(
+            "onnxruntime is not installed. Install it with: pip install onnxruntime"
+        )
+
+
+def get_option_config_path(options: Any) -> str | None:
+    value = getattr(options, "rapidocr_config_path", None)
+    if value is None:
+        return None
+    return str(value)
+
+
+def validate_plugin_options(options: Any) -> None:
+    if getattr(options, "pdf_renderer", "auto") == "sandwich":
+        raise BadArgsError("ocrmypdf-rapidocr only supports hOCR/fpdf2 flow. ")
+
+    config_path = get_option_config_path(options)
+    if config_path is None:
+        return
+
+    path = Path(config_path)
+    if not path.exists():
+        raise BadArgsError(f"--rapidocr-config-path does not exist: {path}")
+    if not path.is_file():
+        raise BadArgsError(f"--rapidocr-config-path is not a file: {path}")

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/plugin.py

@@ -0,0 +1,40 @@
+from __future__ import annotations
+
+import logging
+
+from ocrmypdf import hookimpl
+
+from ocrmypdf_rapidocr.engine import RapidOCREngine
+from ocrmypdf_rapidocr.languages import select_single_language
+from ocrmypdf_rapidocr.options import (
+    add_plugin_options,
+    check_runtime_dependencies,
+    is_rapidocr_selected,
+    validate_plugin_options,
+)
+
+log = logging.getLogger(__name__)
+
+
+@hookimpl
+def add_options(parser) -> None:
+    add_plugin_options(parser)
+
+
+@hookimpl
+def check_options(options) -> None:
+    if not is_rapidocr_selected(options):
+        return
+
+    check_runtime_dependencies()
+    validate_plugin_options(options)
+    select_single_language(options)
+
+
+@hookimpl
+def get_ocr_engine(options=None):
+    if options is not None:
+        ocr_engine = getattr(options, "ocr_engine", "auto")
+        if ocr_engine not in ("auto", "rapidocr"):
+            return None
+    return RapidOCREngine()

ocrmypdf_rapidocr-1.0.0/src/ocrmypdf_rapidocr/version.py

@@ -0,0 +1,8 @@
+from __future__ import annotations
+
+import importlib.metadata
+
+try:
+    __version__ = importlib.metadata.version(__name__)
+except importlib.metadata.PackageNotFoundError:
+    __version__ = "0.0.0"