BabelDOC 0.2.14__tar.gz → 0.2.15__tar.gz

{babeldoc-0.2.14 → babeldoc-0.2.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.2.14
+Version: 0.2.15
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -30,6 +30,7 @@ Requires-Dist: psutil>=7.0.0
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: pymupdf>=1.25.1
 Requires-Dist: python-levenshtein>=0.27.1
+Requires-Dist: rapidocr-onnxruntime>=1.4.4
 Requires-Dist: rich>=13.9.4
 Requires-Dist: scikit-image>=0.25.2
 Requires-Dist: tenacity>=9.0.0
@@ -181,6 +182,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--watermark-output-mode`: Control watermark output mode: 'watermarked' (default) adds watermark to translated PDF, 'no_watermark' doesn't add watermark, 'both' outputs both versions.
 - `--max-pages-per-part`: Maximum number of pages per part for split translation. If not set, no splitting will be performed.
 - `--no-watermark`: [DEPRECATED] Use --watermark-output-mode=no_watermark instead.
+- `--translate-table-text`: Translate table text (experimental, default: False)
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

{babeldoc-0.2.14 → babeldoc-0.2.15}/README.md

@@ -136,6 +136,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--watermark-output-mode`: Control watermark output mode: 'watermarked' (default) adds watermark to translated PDF, 'no_watermark' doesn't add watermark, 'both' outputs both versions.
 - `--max-pages-per-part`: Maximum number of pages per part for split translation. If not set, no splitting will be performed.
 - `--no-watermark`: [DEPRECATED] Use --watermark-output-mode=no_watermark instead.
+- `--translate-table-text`: Translate table text (experimental, default: False)
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

babeldoc-0.2.15/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.2.15"

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/assets/assets.py

@@ -14,6 +14,10 @@ from babeldoc.assets.embedding_assets_metadata import (
 from babeldoc.assets.embedding_assets_metadata import EMBEDDING_FONT_METADATA
 from babeldoc.assets.embedding_assets_metadata import FONT_METADATA_URL
 from babeldoc.assets.embedding_assets_metadata import FONT_URL_BY_UPSTREAM
+from babeldoc.assets.embedding_assets_metadata import (
+    TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256,
+)
+from babeldoc.assets.embedding_assets_metadata import TABLE_DETECTION_RAPIDOCR_MODEL_URL
 from babeldoc.assets.embedding_assets_metadata import TIKTOKEN_CACHES
 from babeldoc.const import get_cache_file_path
 from tenacity import retry
@@ -204,10 +208,36 @@ async def get_doclayout_onnx_model_path_async(client: httpx.AsyncClient | None =
     return onnx_path
 
 
+async def get_table_detection_rapidocr_model_path_async(
+    client: httpx.AsyncClient | None = None,
+):
+    onnx_path = get_cache_file_path("ch_PP-OCRv4_det_infer.onnx", "models")
+    if verify_file(onnx_path, TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256):
+        return onnx_path
+
+    logger.info("table detection rapidocr model not found or corrupted, downloading...")
+    fastest_upstream, _ = await get_fastest_upstream_for_model(client)
+    if fastest_upstream is None:
+        logger.error("Failed to get fastest upstream")
+        exit(1)
+
+    url = TABLE_DETECTION_RAPIDOCR_MODEL_URL[fastest_upstream]
+
+    await download_file(client, url, onnx_path, TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256)
+    logger.info(
+        f"Download table detection rapidocr model from {fastest_upstream} success"
+    )
+    return onnx_path
+
+
 def get_doclayout_onnx_model_path():
     return run_coro(get_doclayout_onnx_model_path_async())
 
 
+def get_table_detection_rapidocr_model_path():
+    return run_coro(get_table_detection_rapidocr_model_path_async())
+
+
 def get_font_url_by_name_and_upstream(font_file_name: str, upstream: str):
     if upstream not in FONT_URL_BY_UPSTREAM:
         logger.critical(f"Invalid upstream: {upstream}")
@@ -329,7 +359,11 @@ def generate_all_assets_file_list():
         {
             "name": "doclayout_yolo_docstructbench_imgsz1024.onnx",
             "sha3_256": DOCLAYOUT_YOLO_DOCSTRUCTBENCH_IMGSZ1024ONNX_SHA3_256,
-        }
+        },
+        {
+            "name": "ch_PP-OCRv4_det_infer.onnx",
+            "sha3_256": TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256,
+        },
     )
     return result
 

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/assets/embedding_assets_metadata.py

@@ -2,6 +2,10 @@ DOCLAYOUT_YOLO_DOCSTRUCTBENCH_IMGSZ1024ONNX_SHA3_256 = (
     "60be061226930524958b5465c8c04af3d7c03bcb0beb66454f5da9f792e3cf2a"
 )
 
+TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256 = (
+    "062f4619afe91b33147c033acadecbb53f2a7b99ac703d157b96d5b10948da5e"
+)
+
 TIKTOKEN_CACHES = {
     "fb374d419588a4632f3f557e76b4b70aebbca790": "cb04bcda5782cfbbe77f2f991d92c0ea785d9496ef1137c91dfc3c8c324528d6"
 }
@@ -26,6 +30,12 @@ DOC_LAYOUT_ONNX_MODEL_URL = {
     "modelscope": "https://www.modelscope.cn/models/AI-ModelScope/DocLayout-YOLO-DocStructBench-onnx/resolve/master/doclayout_yolo_docstructbench_imgsz1024.onnx",
 }
 
+TABLE_DETECTION_RAPIDOCR_MODEL_URL = {
+    "huggingface": "https://huggingface.co/spaces/RapidAI/RapidOCR/resolve/main/models/text_det/ch_PP-OCRv4_det_infer.onnx",
+    "hf-mirror": "https://hf-mirror.com/spaces/RapidAI/RapidOCR/resolve/main/models/text_det/ch_PP-OCRv4_det_infer.onnx",
+    "modelscope": "https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/master/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_infer.onnx",
+}
+
 # from https://github.com/funstory-ai/BabelDOC-Assets/blob/main/font_metadata.json
 EMBEDDING_FONT_METADATA = {
     "GoNotoKurrent-Bold.ttf": {

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.2.14"
+__version__ = "0.2.15"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/document_il/midend/paragraph_finder.py

@@ -287,6 +287,7 @@ class ParagraphFinder:
             "abandon",
             "figure_caption",
             "table_caption",
+            "table_text",
         ]
 
     def get_layout(
@@ -313,6 +314,7 @@ class ParagraphFinder:
             "table_footnote",
             "table_caption",
             "figure_caption",
+            "table_text",
             "table",
             "figure",
             "abandon",

babeldoc-0.2.15/babeldoc/document_il/midend/table_parser.py

@@ -0,0 +1,164 @@
+import logging
+from pathlib import Path
+
+import cv2
+import numpy as np
+from pymupdf import Document
+
+from babeldoc.document_il import il_version_1
+from babeldoc.document_il.utils.style_helper import GREEN
+from babeldoc.translation_config import TranslationConfig
+
+logger = logging.getLogger(__name__)
+
+
+class TableParser:
+    stage_name = "Parse Table"
+
+    def __init__(self, translation_config: TranslationConfig):
+        self.translation_config = translation_config
+        self.model = translation_config.table_model
+
+    def _save_debug_image(self, image: np.ndarray, layouts, page_number: int):
+        """Save debug image with drawn boxes if debug mode is enabled."""
+        if not self.translation_config.debug:
+            return
+
+        if not isinstance(layouts, list):
+            layouts = [layouts]
+        debug_dir = Path(
+            self.translation_config.get_working_file_path("table-ocr-box-image")
+        )
+        debug_dir.mkdir(parents=True, exist_ok=True)
+
+        # Draw boxes on the image
+        debug_image = image.copy()
+        for layout in layouts:
+            for box in layout.boxes:
+                x0, y0, x1, y1 = box.xyxy
+                cv2.rectangle(
+                    debug_image,
+                    (int(x0), int(y0)),
+                    (int(x1), int(y1)),
+                    (0, 255, 0),
+                    2,
+                )
+                # Add text label
+                cv2.putText(
+                    debug_image,
+                    layout.names[box.cls],
+                    (int(x0), int(y0) - 5),
+                    cv2.FONT_HERSHEY_SIMPLEX,
+                    0.5,
+                    (0, 255, 0),
+                    1,
+                )
+
+        # Save the image
+        output_path = debug_dir / f"{page_number}.jpg"
+        cv2.imwrite(str(output_path), debug_image)
+
+    def _save_debug_box_to_page(self, page: il_version_1.Page):
+        """Save debug boxes and text labels to the PDF page."""
+        if not self.translation_config.debug:
+            return
+
+        color = GREEN
+
+        for layout in page.page_layout:
+            # Create a rectangle box
+            rect = il_version_1.PdfRectangle(
+                box=il_version_1.Box(
+                    x=layout.box.x,
+                    y=layout.box.y,
+                    x2=layout.box.x2,
+                    y2=layout.box.y2,
+                ),
+                graphic_state=color,
+                debug_info=True,
+            )
+            page.pdf_rectangle.append(rect)
+
+            # Create text label at top-left corner
+            # Note: PDF coordinates are from bottom-left,
+            # so we use y2 for top position
+            style = il_version_1.PdfStyle(
+                font_id="china-ss",
+                font_size=4,
+                graphic_state=color,
+            )
+            page.pdf_paragraph.append(
+                il_version_1.PdfParagraph(
+                    first_line_indent=False,
+                    box=il_version_1.Box(
+                        x=layout.box.x,
+                        y=layout.box.y2,
+                        x2=layout.box.x2,
+                        y2=layout.box.y2 + 5,
+                    ),
+                    vertical=False,
+                    pdf_style=style,
+                    unicode=layout.class_name,
+                    pdf_paragraph_composition=[
+                        il_version_1.PdfParagraphComposition(
+                            pdf_same_style_unicode_characters=il_version_1.PdfSameStyleUnicodeCharacters(
+                                unicode=layout.class_name,
+                                pdf_style=style,
+                                debug_info=True,
+                            ),
+                        ),
+                    ],
+                    xobj_id=-1,
+                ),
+            )
+
+    def process(self, docs: il_version_1.Document, mupdf_doc: Document):
+        """Generate layouts for all pages that need to be translated."""
+        # Get pages that need to be translated
+        have_table_pages = {}
+        for page in docs.page:
+            for layout in page.page_layout:
+                if layout.class_name == "table":
+                    have_table_pages[page.page_number] = page
+        with self.translation_config.progress_monitor.stage_start(
+            self.stage_name,
+            len(have_table_pages),
+        ) as progress:
+            # Process predictions for each page
+            for page, layouts in self.model.handle_document(
+                have_table_pages.values(),
+                mupdf_doc,
+                self.translation_config,
+                self._save_debug_image,
+            ):
+                page_layouts = []
+                for layout in layouts.boxes:
+                    # Convert coordinate system from picture to il
+                    # system to the il coordinate system
+                    x0, y0, x1, y1 = layout.xyxy
+                    pix = mupdf_doc[page.page_number].get_pixmap()
+                    h, w = pix.height, pix.width
+                    x0, y0, x1, y1 = (
+                        np.clip(int(x0 - 1), 0, w - 1),
+                        np.clip(int(h - y1 - 1), 0, h - 1),
+                        np.clip(int(x1 + 1), 0, w - 1),
+                        np.clip(int(h - y0 + 1), 0, h - 1),
+                    )
+                    page_layout = il_version_1.PageLayout(
+                        id=len(page_layouts) + 1,
+                        box=il_version_1.Box(
+                            x0.item(),
+                            y0.item(),
+                            x1.item(),
+                            y1.item(),
+                        ),
+                        conf=layout.conf.item(),
+                        class_name=layouts.names[layout.cls],
+                    )
+                    page_layouts.append(page_layout)
+
+                page.page_layout.extend(page_layouts)
+                self._save_debug_box_to_page(page)
+                progress.advance(1)
+
+        return docs

babeldoc-0.2.15/babeldoc/docvision/table_detection/rapidocr.py

@@ -0,0 +1,316 @@
+import logging
+import re
+from collections.abc import Generator
+
+import cv2
+import numpy as np
+from babeldoc.assets.assets import get_table_detection_rapidocr_model_path
+from babeldoc.docvision.doclayout import YoloBox
+from babeldoc.docvision.doclayout import YoloResult
+from rapidocr_onnxruntime import RapidOCR
+
+try:
+    import onnxruntime
+except ImportError as e:
+    if "DLL load failed" in str(e):
+        raise OSError(
+            "Microsoft Visual C++ Redistributable is not installed. "
+            "Download it at https://aka.ms/vs/17/release/vc_redist.x64.exe"
+        ) from e
+    raise
+import babeldoc.document_il.il_version_1
+import pymupdf
+
+logger = logging.getLogger(__name__)
+
+
+def convert_to_yolo_result(predictions):
+    """
+    Convert RapidOCR predictions to YoloResult format.
+
+    Args:
+        predictions (list): List of predictions, where each prediction is a list of coordinates
+                           in format [[x1, y1], [x2, y2], [x3, y3], [x4, y4], (text, confidence)]
+                           or a numpy array of format [x1, y1, x2, y2, ...]
+
+    Returns:
+        YoloResult: Converted predictions in YoloResult format
+    """
+    boxes = []
+
+    for pred in predictions:
+        # Check if the prediction is in the format of 4 corner points
+        if isinstance(pred, list) and len(pred) >= 5 and isinstance(pred[0], list):
+            # Convert 4 corner points to xyxy format (min x, min y, max x, max y)
+            points = np.array(pred[:4])
+            x1, y1 = points[:, 0].min(), points[:, 1].min()
+            x2, y2 = points[:, 0].max(), points[:, 1].max()
+            xyxy = [x1, y1, x2, y2]
+            box = YoloBox(xyxy=xyxy, conf=1.0, cls="text")
+        # Check if the prediction is already in xyxy format
+        elif isinstance(pred, list | np.ndarray) and len(pred) >= 4:
+            if isinstance(pred, np.ndarray):
+                pred = pred.tolist()
+            xyxy = pred[:4]
+            box = YoloBox(xyxy=xyxy, conf=1.0, cls="text")
+        else:
+            continue
+
+        boxes.append(box)
+
+    return YoloResult(names=["text"], boxes=boxes)
+
+
+def create_yolo_result_from_nested_coords(nested_coords: np.ndarray, names: dict):
+    boxes = []
+
+    for quad in nested_coords.tolist():
+        if len(quad) != 4:
+            continue
+
+        # Convert quad coordinates to xyxy format (min x, min y, max x, max y)
+        x1, y1, x2, y2 = quad
+
+        # Create YoloBox with confidence 1.0 and class 'text'
+        box = YoloBox(
+            xyxy=[float(x1), float(y1), float(x2), float(y2)], conf=np.array(1.0), cls=0
+        )
+        boxes.append(box)
+
+    return YoloResult(names=names, boxes=boxes)
+
+
+class RapidOCRModel:
+    def __init__(self):
+        self.use_cuda = False
+        self.use_dml = False
+        available_providers = onnxruntime.get_available_providers()
+        for provider in available_providers:
+            if re.match(r"dml", provider, re.IGNORECASE):
+                self.use_dml = True
+            elif re.match(r"cuda", provider, re.IGNORECASE):
+                self.use_cuda = True
+
+        self.model = RapidOCR(
+            det_model_path=get_table_detection_rapidocr_model_path(),
+            det_use_cuda=self.use_cuda,
+            det_use_dml=self.use_dml,
+        )
+        self.names = {0: "table_text"}
+
+    @property
+    def stride(self):
+        return 32
+
+    def resize_and_pad_image(self, image, new_shape):
+        """
+        Resize and pad the image to the specified size, ensuring dimensions are multiples of stride.
+
+        Parameters:
+        - image: Input image
+        - new_shape: Target size (integer or (height, width) tuple)
+        - stride: Padding alignment stride, default 32
+
+        Returns:
+        - Processed image
+        """
+        if isinstance(new_shape, int):
+            new_shape = (new_shape, new_shape)
+
+        h, w = image.shape[:2]
+        new_h, new_w = new_shape
+
+        # Calculate scaling ratio
+        r = min(new_h / h, new_w / w)
+        resized_h, resized_w = int(round(h * r)), int(round(w * r))
+
+        # Resize image
+        image = cv2.resize(
+            image,
+            (resized_w, resized_h),
+            interpolation=cv2.INTER_LINEAR,
+        )
+
+        # Calculate padding size and align to stride multiple
+        pad_w = (new_w - resized_w) % self.stride
+        pad_h = (new_h - resized_h) % self.stride
+        top, bottom = pad_h // 2, pad_h - pad_h // 2
+        left, right = pad_w // 2, pad_w - pad_w // 2
+
+        # Add padding
+        image = cv2.copyMakeBorder(
+            image,
+            top,
+            bottom,
+            left,
+            right,
+            cv2.BORDER_CONSTANT,
+            value=(114, 114, 114),
+        )
+
+        return image
+
+    def scale_boxes(self, img1_shape, boxes, img0_shape):
+        """
+        Rescales bounding boxes (in the format of xyxy by default) from the shape of the image they were originally
+        specified in (img1_shape) to the shape of a different image (img0_shape).
+
+        Args:
+            img1_shape (tuple): The shape of the image that the bounding boxes are for,
+                in the format of (height, width).
+            boxes (torch.Tensor): the bounding boxes of the objects in the image, in the format of (x1, y1, x2, y2)
+            img0_shape (tuple): the shape of the target image, in the format of (height, width).
+
+        Returns:
+            boxes (torch.Tensor): The scaled bounding boxes, in the format of (x1, y1, x2, y2)
+        """
+
+        # Calculate scaling ratio
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])
+
+        # Calculate padding size
+        pad_x = round((img1_shape[1] - img0_shape[1] * gain) / 2 - 0.1)
+        pad_y = round((img1_shape[0] - img0_shape[0] * gain) / 2 - 0.1)
+
+        # Remove padding and scale boxes
+        boxes[..., :4] = (boxes[..., :4] - [pad_x, pad_y, pad_x, pad_y]) / gain
+        return boxes
+
+    def predict(self, image, imgsz=800, batch_size=16, **kwargs):
+        """
+        Predict the layout of document pages.
+
+        Args:
+            image: A single image or a list of images of document pages.
+            imgsz: Resize the image to this size. Must be a multiple of the stride.
+            batch_size: Number of images to process in one batch.
+            **kwargs: Additional arguments.
+
+        Returns:
+            A YoloResult object containing the detected boxes.
+        """
+        # Handle single image input
+        assert isinstance(image, np.ndarray) and len(image.shape) == 3
+
+        # Calculate target size based on the maximum height in the batch
+        target_imgsz = 1024
+
+        orig_shape = (image.shape[0], image.shape[1])
+
+        pix = self.resize_and_pad_image(image, new_shape=target_imgsz)
+        # pix = np.transpose(pix, (2, 0, 1))  # CHW
+        # pix = pix.astype(np.float32) / 255.0  # Normalize to [0, 1]
+        input_ = pix
+
+        new_h, new_w = input_.shape[:2]
+
+        # Run inference
+        preds = self.model(input_, use_det=True, use_cls=False, use_rec=False)
+
+        # Process each prediction in the batch
+        if len(preds) > 0:
+            preds_np = np.array(preds[0])[:, [0, 2], :].reshape([-1, 4])
+            preds_np[..., :4] = self.scale_boxes(
+                (new_h, new_w),
+                preds_np[..., :4],
+                orig_shape,
+            )
+
+            # Convert predictions to YoloResult format
+            return create_yolo_result_from_nested_coords(preds_np, self.names)
+        else:
+            # Return empty YoloResult if no predictions
+            return YoloResult(names=self.names, boxes=[])
+
+    def handle_document(
+        self,
+        pages: list[babeldoc.document_il.il_version_1.Page],
+        mupdf_doc: pymupdf.Document,
+        translate_config,
+        save_debug_image,
+    ) -> Generator[
+        tuple[babeldoc.document_il.il_version_1.Page, YoloResult], None, None
+    ]:
+        for page in pages:
+            translate_config.raise_if_cancelled()
+            pix = mupdf_doc[page.page_number].get_pixmap(dpi=72)
+            image = np.fromstring(pix.samples, np.uint8).reshape(
+                pix.height,
+                pix.width,
+                3,
+            )[:, :, ::-1]
+
+            table_boxes = []
+            for layout in page.page_layout:
+                if layout.class_name == "table":
+                    table_boxes.append(layout.box)
+
+            predict_result = self.predict(image)
+
+            ok_boxes = []
+            for box in predict_result.boxes:
+                # Convert the box coordinates to float for proper comparison
+                box_xyxy = [float(coord) for coord in box.xyxy]
+
+                # Check if this box is inside any of the table boxes
+                for table_box in table_boxes:
+                    # Determine if box is inside or overlapping with table_box with image dimensions
+                    if self._is_box_in_table(
+                        box_xyxy, table_box, page, image.shape[1], image.shape[0]
+                    ):
+                        ok_boxes.append(box)
+                        break
+
+            yolo_result = YoloResult(names=self.names, boxes=ok_boxes)
+            save_debug_image(
+                image,
+                yolo_result,
+                page.page_number + 1,
+            )
+            yield page, yolo_result
+
+    def _is_box_in_table(self, box_xyxy, table_box, page, img_width, img_height):
+        """
+        Check if a box from image coordinates is inside a table box from PDF coordinates.
+
+        Args:
+            box_xyxy (list): Box coordinates in image coordinate system [x1, y1, x2, y2]
+            table_box (Box): Table box in PDF coordinate system
+            page: The page object containing information for coordinate conversion
+            img_width: Width of the image
+            img_height: Height of the image
+
+        Returns:
+            bool: True if the box is inside or significantly overlapping with the table box
+        """
+
+        # Get table box coordinates in PDF coordinate system
+        table_pdf_x1 = table_box.x
+        table_pdf_y1 = table_box.y
+        table_pdf_x2 = table_box.x2
+        table_pdf_y2 = table_box.y2
+
+        # Convert table box to image coordinates
+        table_img_x1 = table_pdf_x1
+        table_img_y1 = img_height - table_pdf_y2
+        table_img_x2 = table_pdf_x2
+        table_img_y2 = img_height - table_pdf_y1
+
+        # Now check for overlap between the boxes
+        # Calculate the area of overlap
+        x_overlap = max(
+            0, min(box_xyxy[2], table_img_x2) - max(box_xyxy[0], table_img_x1)
+        )
+        y_overlap = max(
+            0, min(box_xyxy[3], table_img_y2) - max(box_xyxy[1], table_img_y1)
+        )
+        overlap_area = x_overlap * y_overlap
+
+        # Calculate area of the detected box
+        box_area = (box_xyxy[2] - box_xyxy[0]) * (box_xyxy[3] - box_xyxy[1])
+
+        # If overlap area is significant relative to the box area, consider it inside
+        if box_area > 0 and overlap_area / box_area > 0.5:
+            return True
+
+        return False

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/high_level.py

@@ -34,6 +34,7 @@ from babeldoc.document_il.midend.il_translator_llm_only import ILTranslatorLLMOn
 from babeldoc.document_il.midend.layout_parser import LayoutParser
 from babeldoc.document_il.midend.paragraph_finder import ParagraphFinder
 from babeldoc.document_il.midend.styles_and_formulas import StylesAndFormulas
+from babeldoc.document_il.midend.table_parser import TableParser
 from babeldoc.document_il.midend.typesetting import Typesetting
 from babeldoc.document_il.utils.fontmap import FontMapper
 from babeldoc.document_il.xml_converter import XMLConverter
@@ -51,6 +52,7 @@ TRANSLATE_STAGES = [
     (ILCreater.stage_name, 5.35),  # Parse PDF and Create IR
     (DetectScannedFile.stage_name, 0.5),  # No historical data, estimated
     (LayoutParser.stage_name, 6.42),  # Parse Page Layout
+    (TableParser.stage_name, 0.5),  # Parse Table
     (ParagraphFinder.stage_name, 2.14),  # Parse Paragraphs
     (StylesAndFormulas.stage_name, 1.12),  # Parse Formulas and Styles
     # (RemoveDescent.stage_name, 0.15),  # Remove Char Descent
@@ -588,6 +590,15 @@ def _do_translate_single(
             docs,
             translation_config.get_working_file_path("layout_generator.json"),
         )
+
+    if translation_config.table_model:
+        docs = TableParser(translation_config).process(docs, doc_pdf2zh)
+        logger.debug("finish table parser")
+        if translation_config.debug:
+            xml_converter.write_json(
+                docs,
+                translation_config.get_working_file_path("table_parser.json"),
+            )
     ParagraphFinder(translation_config).process(docs)
     logger.debug(f"finish paragraph finder from {temp_pdf_path}")
     if translation_config.debug:

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/main.py

@@ -18,11 +18,12 @@ from babeldoc.document_il.translator.translator import OpenAITranslator
 from babeldoc.document_il.translator.translator import set_translate_rate_limiter
 from babeldoc.docvision.doclayout import DocLayoutModel
 from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
+from babeldoc.docvision.table_detection.rapidocr import RapidOCRModel
 from babeldoc.translation_config import TranslationConfig
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.2.14"
+__version__ = "0.2.15"
 
 
 def create_parser():
@@ -191,6 +192,12 @@ def create_parser():
         default=0.1,
         help="Progress report interval in seconds (default: 0.1)",
     )
+    translation_group.add_argument(
+        "--translate-table-text",
+        action="store_true",
+        default=False,
+        help="Translate table text (experimental)",
+    )
     # service option argument group
     service_group = translation_group.add_mutually_exclusive_group()
     service_group.add_argument(
@@ -276,6 +283,11 @@ async def main():
     else:
         doc_layout_model = DocLayoutModel.load_onnx()
 
+    if args.translate_table_text:
+        table_model = RapidOCRModel()
+    else:
+        table_model = None
+
     pending_files = []
     for file in args.files:
         # 清理文件路径，去除两端的引号
@@ -350,6 +362,7 @@ async def main():
             min_text_length=args.min_text_length,
             watermark_output_mode=watermark_output_mode,
             split_strategy=split_strategy,
+            table_model=table_model,
         )
 
         # Create progress handler

{babeldoc-0.2.14 → babeldoc-0.2.15}/babeldoc/translation_config.py

@@ -65,6 +65,7 @@ class TranslationConfig:
         watermark_output_mode: WatermarkOutputMode = WatermarkOutputMode.Watermarked,
         # Add split-related parameters
         split_strategy: BaseSplitStrategy | None = None,
+        table_model=None,
     ):
         self.translator = translator
 
@@ -142,6 +143,8 @@ class TranslationConfig:
         self._part_working_dirs: dict[int, Path] = {}
         self._part_output_dirs: dict[int, Path] = {}
 
+        self.table_model = table_model
+
     def parse_pages(self, pages_str: str | None) -> list[tuple[int, int]] | None:
         """解析页码字符串，返回页码范围列表
 

{babeldoc-0.2.14 → babeldoc-0.2.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.2.14"
+version = "0.2.15"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -42,6 +42,7 @@ dependencies = [
     "tiktoken>=0.9.0",
     "python-levenshtein>=0.27.1",
     "opencv-python-headless>=4.10.0.84",
+    "rapidocr-onnxruntime>=1.4.4",
 ]
 
 [project.optional-dependencies]
@@ -147,7 +148,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.2.14"
+current_version = "0.2.15"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.2.14 → babeldoc-0.2.15}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.2.14"
+version = "0.2.15"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },
@@ -69,6 +69,7 @@ dependencies = [
     { name = "pydantic" },
     { name = "pymupdf" },
     { name = "python-levenshtein" },
+    { name = "rapidocr-onnxruntime" },
     { name = "rich" },
     { name = "scikit-image" },
     { name = "tenacity" },
@@ -123,6 +124,7 @@ requires-dist = [
     { name = "pydantic", specifier = ">=2.10.6" },
     { name = "pymupdf", specifier = ">=1.25.1" },
     { name = "python-levenshtein", specifier = ">=0.27.1" },
+    { name = "rapidocr-onnxruntime", specifier = ">=1.4.4" },
     { name = "rich", specifier = ">=13.9.4" },
     { name = "scikit-image", specifier = ">=0.25.2" },
     { name = "tenacity", specifier = ">=9.0.0" },
@@ -1416,6 +1418,23 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/3b/1ba418920ecd1eae7cc4d4ac8a01711ee0879b1a57dd81d10551e5b9a2ea/openai-1.66.5-py3-none-any.whl", hash = "sha256:74be528175f8389f67675830c51a15bd51e874425c86d3de6153bf70ed6c2884", size = 571144 },
 ]
 
+[[package]]
+name = "opencv-python"
+version = "4.11.0.86"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/17/06/68c27a523103dad5837dc5b87e71285280c4f098c60e4fe8a8db6486ab09/opencv-python-4.11.0.86.tar.gz", hash = "sha256:03d60ccae62304860d232272e4a4fda93c39d595780cb40b161b310244b736a4", size = 95171956 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/05/4d/53b30a2a3ac1f75f65a59eb29cf2ee7207ce64867db47036ad61743d5a23/opencv_python-4.11.0.86-cp37-abi3-macosx_13_0_arm64.whl", hash = "sha256:432f67c223f1dc2824f5e73cdfcd9db0efc8710647d4e813012195dc9122a52a", size = 37326322 },
+    { url = "https://files.pythonhosted.org/packages/3b/84/0a67490741867eacdfa37bc18df96e08a9d579583b419010d7f3da8ff503/opencv_python-4.11.0.86-cp37-abi3-macosx_13_0_x86_64.whl", hash = "sha256:9d05ef13d23fe97f575153558653e2d6e87103995d54e6a35db3f282fe1f9c66", size = 56723197 },
+    { url = "https://files.pythonhosted.org/packages/f3/bd/29c126788da65c1fb2b5fb621b7fed0ed5f9122aa22a0868c5e2c15c6d23/opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b92ae2c8852208817e6776ba1ea0d6b1e0a1b5431e971a2a0ddd2a8cc398202", size = 42230439 },
+    { url = "https://files.pythonhosted.org/packages/2c/8b/90eb44a40476fa0e71e05a0283947cfd74a5d36121a11d926ad6f3193cc4/opencv_python-4.11.0.86-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b02611523803495003bd87362db3e1d2a0454a6a63025dc6658a9830570aa0d", size = 62986597 },
+    { url = "https://files.pythonhosted.org/packages/fb/d7/1d5941a9dde095468b288d989ff6539dd69cd429dbf1b9e839013d21b6f0/opencv_python-4.11.0.86-cp37-abi3-win32.whl", hash = "sha256:810549cb2a4aedaa84ad9a1c92fbfdfc14090e2749cedf2c1589ad8359aa169b", size = 29384337 },
+    { url = "https://files.pythonhosted.org/packages/a4/7d/f1c30a92854540bf789e9cd5dde7ef49bbe63f855b85a2e6b3db8135c591/opencv_python-4.11.0.86-cp37-abi3-win_amd64.whl", hash = "sha256:085ad9b77c18853ea66283e98affefe2de8cc4c1f43eda4c100cf9b2721142ec", size = 39488044 },
+]
+
 [[package]]
 name = "opencv-python-headless"
 version = "4.11.0.86"
@@ -1637,6 +1656,32 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/50/1b/6921afe68c74868b4c9fa424dad3be35b095e16687989ebbb50ce4fceb7c/psutil-7.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:4cf3d4eb1aa9b348dec30105c55cd9b7d4629285735a102beb4441e38db90553", size = 244885 },
 ]
 
+[[package]]
+name = "pyclipper"
+version = "1.3.0.post6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/4a/b2/550fe500e49c464d73fabcb8cb04d47e4885d6ca4cfc1f5b0a125a95b19a/pyclipper-1.3.0.post6.tar.gz", hash = "sha256:42bff0102fa7a7f2abdd795a2594654d62b786d0c6cd67b72d469114fdeb608c", size = 165909 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b5/34/0dca299fe41e9a92e78735502fed5238a4ac734755e624488df9b2eeec46/pyclipper-1.3.0.post6-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fa0f5e78cfa8262277bb3d0225537b3c2a90ef68fd90a229d5d24cf49955dcf4", size = 269504 },
+    { url = "https://files.pythonhosted.org/packages/8a/5b/81528b08134b3c2abdfae821e1eff975c0703802d41974b02dfb2e101c55/pyclipper-1.3.0.post6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a01f182d8938c1dc515e8508ed2442f7eebd2c25c7d5cb29281f583c1a8008a4", size = 142599 },
+    { url = "https://files.pythonhosted.org/packages/84/a4/3e304f6c0d000382cd54d4a1e5f0d8fc28e1ae97413a2ec1016a7b840319/pyclipper-1.3.0.post6-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:640f20975727994d4abacd07396f564e9e5665ba5cb66ceb36b300c281f84fa4", size = 912209 },
+    { url = "https://files.pythonhosted.org/packages/f5/6a/28ec55cc3f972368b211fca017e081cf5a71009d1b8ec3559767cda5b289/pyclipper-1.3.0.post6-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a63002f6bb0f1efa87c0b81634cbb571066f237067e23707dabf746306c92ba5", size = 929511 },
+    { url = "https://files.pythonhosted.org/packages/c4/56/c326f3454c5f30a31f58a5c3154d891fce58ad73ccbf1d3f4aacfcbd344d/pyclipper-1.3.0.post6-cp310-cp310-win32.whl", hash = "sha256:106b8622cd9fb07d80cbf9b1d752334c55839203bae962376a8c59087788af26", size = 100126 },
+    { url = "https://files.pythonhosted.org/packages/f8/e6/f8239af6346848b20a3448c554782fe59298ab06c1d040490242dc7e3c26/pyclipper-1.3.0.post6-cp310-cp310-win_amd64.whl", hash = "sha256:9699e98862dadefd0bea2360c31fa61ca553c660cbf6fb44993acde1b959f58f", size = 110470 },
+    { url = "https://files.pythonhosted.org/packages/50/a9/66ca5f252dcac93ca076698591b838ba17f9729591edf4b74fef7fbe1414/pyclipper-1.3.0.post6-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:c4247e7c44b34c87acbf38f99d48fb1acaf5da4a2cf4dcd601a9b24d431be4ef", size = 270930 },
+    { url = "https://files.pythonhosted.org/packages/59/fe/2ab5818b3504e179086e54a37ecc245525d069267b8c31b18ec3d0830cbf/pyclipper-1.3.0.post6-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:851b3e58106c62a5534a1201295fe20c21714dee2eda68081b37ddb0367e6caa", size = 143411 },
+    { url = "https://files.pythonhosted.org/packages/09/f7/b58794f643e033a6d14da7c70f517315c3072f3c5fccdf4232fa8c8090c1/pyclipper-1.3.0.post6-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:16cc1705a915896d2aff52131c427df02265631279eac849ebda766432714cc0", size = 951754 },
+    { url = "https://files.pythonhosted.org/packages/c1/77/846a21957cd4ed266c36705ee340beaa923eb57d2bba013cfd7a5c417cfd/pyclipper-1.3.0.post6-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ace1f0753cf71c5c5f6488b8feef5dd0fa8b976ad86b24bb51f708f513df4aac", size = 969608 },
+    { url = "https://files.pythonhosted.org/packages/c9/2b/580703daa6606d160caf596522d4cfdf62ae619b062a7ce6f905821a57e8/pyclipper-1.3.0.post6-cp311-cp311-win32.whl", hash = "sha256:dbc828641667142751b1127fd5c4291663490cf05689c85be4c5bcc89aaa236a", size = 100227 },
+    { url = "https://files.pythonhosted.org/packages/17/4b/a4cda18e8556d913ff75052585eb0d658500596b5f97fe8401d05123d47b/pyclipper-1.3.0.post6-cp311-cp311-win_amd64.whl", hash = "sha256:1c03f1ae43b18ee07730c3c774cc3cf88a10c12a4b097239b33365ec24a0a14a", size = 110442 },
+    { url = "https://files.pythonhosted.org/packages/fc/c8/197d9a1d8354922d24d11d22fb2e0cc1ebc182f8a30496b7ddbe89467ce1/pyclipper-1.3.0.post6-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:6363b9d79ba1b5d8f32d1623e797c1e9f994600943402e68d5266067bdde173e", size = 270487 },
+    { url = "https://files.pythonhosted.org/packages/8e/8e/eb14eadf054494ad81446e21c4ea163b941747610b0eb9051644395f567e/pyclipper-1.3.0.post6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:32cd7fb9c1c893eb87f82a072dbb5e26224ea7cebbad9dc306d67e1ac62dd229", size = 143469 },
+    { url = "https://files.pythonhosted.org/packages/cf/e5/6c4a8df6e904c133bb4c5309d211d31c751db60cbd36a7250c02b05494a1/pyclipper-1.3.0.post6-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3aab10e3c10ed8fa60c608fb87c040089b83325c937f98f06450cf9fcfdaf1d", size = 944206 },
+    { url = "https://files.pythonhosted.org/packages/76/65/cb014acc41cd5bf6bbfa4671c7faffffb9cee01706642c2dec70c5209ac8/pyclipper-1.3.0.post6-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58eae2ff92a8cae1331568df076c4c5775bf946afab0068b217f0cf8e188eb3c", size = 963797 },
+    { url = "https://files.pythonhosted.org/packages/80/ec/b40cd81ab7598984167508a5369a2fa31a09fe3b3e3d0b73aa50e06d4b3f/pyclipper-1.3.0.post6-cp312-cp312-win32.whl", hash = "sha256:793b0aa54b914257aa7dc76b793dd4dcfb3c84011d48df7e41ba02b571616eaf", size = 99456 },
+    { url = "https://files.pythonhosted.org/packages/24/3a/7d6292e3c94fb6b872d8d7e80d909dc527ee6b0af73b753c63fdde65a7da/pyclipper-1.3.0.post6-cp312-cp312-win_amd64.whl", hash = "sha256:d3f9da96f83b8892504923beb21a481cd4516c19be1d39eb57a92ef1c9a29548", size = 110278 },
+]
+
 [[package]]
 name = "pycparser"
 version = "2.22"
@@ -1929,6 +1974,25 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/09/f6/fa777f336629aee8938f3d5c95c09df38459d4eadbdbe34642889857fb6a/rapidfuzz-3.12.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:54bb69ebe5ca0bd7527357e348f16a4c0c52fe0c2fcc8a041010467dcb8385f7", size = 1555000 },
 ]
 
+[[package]]
+name = "rapidocr-onnxruntime"
+version = "1.4.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+    { name = "onnxruntime" },
+    { name = "opencv-python" },
+    { name = "pillow" },
+    { name = "pyclipper" },
+    { name = "pyyaml" },
+    { name = "shapely" },
+    { name = "six" },
+    { name = "tqdm" },
+]
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ba/12/1e5497183bdbe782dbb91bad1d0d2297dba4d2831b2652657f7517bfc6df/rapidocr_onnxruntime-1.4.4-py3-none-any.whl", hash = "sha256:971d7d5f223a7a808662229df1ef69893809d8457d834e6373d3854bc1782cbf", size = 14915192 },
+]
+
 [[package]]
 name = "regex"
 version = "2024.11.6"
@@ -2108,6 +2172,35 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f5/6f/e6e5aff77ea2a48dd96808bb51d7450875af154ee7cbe72188afb0b37929/scipy-1.15.2-cp312-cp312-win_amd64.whl", hash = "sha256:e7c68b6a43259ba0aab737237876e5c2c549a031ddb7abc28c7b47f22e202ded", size = 40942317 },
 ]
 
+[[package]]
+name = "shapely"
+version = "2.0.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/21/c0/a911d1fd765d07a2b6769ce155219a281bfbe311584ebe97340d75c5bdb1/shapely-2.0.7.tar.gz", hash = "sha256:28fe2997aab9a9dc026dc6a355d04e85841546b2a5d232ed953e3321ab958ee5", size = 283413 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/15/2e/02c694d6ddacd4f13b625722d313d2838f23c5b988cbc680132983f73ce3/shapely-2.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:33fb10e50b16113714ae40adccf7670379e9ccf5b7a41d0002046ba2b8f0f691", size = 1478310 },
+    { url = "https://files.pythonhosted.org/packages/87/69/b54a08bcd25e561bdd5183c008ace4424c25e80506e80674032504800efd/shapely-2.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f44eda8bd7a4bccb0f281264b34bf3518d8c4c9a8ffe69a1a05dabf6e8461147", size = 1336082 },
+    { url = "https://files.pythonhosted.org/packages/b3/f9/40473fcb5b66ff849e563ca523d2a26dafd6957d52dd876ffd0eded39f1c/shapely-2.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf6c50cd879831955ac47af9c907ce0310245f9d162e298703f82e1785e38c98", size = 2371047 },
+    { url = "https://files.pythonhosted.org/packages/d6/f3/c9cc07a7a03b5f5e83bd059f9adf3e21cf086b0e41d7f95e6464b151e798/shapely-2.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04a65d882456e13c8b417562c36324c0cd1e5915f3c18ad516bb32ee3f5fc895", size = 2469112 },
+    { url = "https://files.pythonhosted.org/packages/5d/b9/fc63d6b0b25063a3ff806857a5dc88851d54d1c278288f18cef1b322b449/shapely-2.0.7-cp310-cp310-win32.whl", hash = "sha256:7e97104d28e60b69f9b6a957c4d3a2a893b27525bc1fc96b47b3ccef46726bf2", size = 1296057 },
+    { url = "https://files.pythonhosted.org/packages/fe/d1/8df43f94cf4cda0edbab4545f7cdd67d3f1d02910eaff152f9f45c6d00d8/shapely-2.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:35524cc8d40ee4752520819f9894b9f28ba339a42d4922e92c99b148bed3be39", size = 1441787 },
+    { url = "https://files.pythonhosted.org/packages/1d/ad/21798c2fec013e289f8ab91d42d4d3299c315b8c4460c08c75fef0901713/shapely-2.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:5cf23400cb25deccf48c56a7cdda8197ae66c0e9097fcdd122ac2007e320bc34", size = 1473091 },
+    { url = "https://files.pythonhosted.org/packages/15/63/eef4f180f1b5859c70e7f91d2f2570643e5c61e7d7c40743d15f8c6cbc42/shapely-2.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d8f1da01c04527f7da59ee3755d8ee112cd8967c15fab9e43bba936b81e2a013", size = 1332921 },
+    { url = "https://files.pythonhosted.org/packages/fe/67/77851dd17738bbe7762a0ef1acf7bc499d756f68600dd68a987d78229412/shapely-2.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f623b64bb219d62014781120f47499a7adc30cf7787e24b659e56651ceebcb0", size = 2427949 },
+    { url = "https://files.pythonhosted.org/packages/0b/a5/2c8dbb0f383519771df19164e3bf3a8895d195d2edeab4b6040f176ee28e/shapely-2.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e6d95703efaa64aaabf278ced641b888fc23d9c6dd71f8215091afd8a26a66e3", size = 2529282 },
+    { url = "https://files.pythonhosted.org/packages/dc/4e/e1d608773c7fe4cde36d48903c0d6298e3233dc69412403783ac03fa5205/shapely-2.0.7-cp311-cp311-win32.whl", hash = "sha256:2f6e4759cf680a0f00a54234902415f2fa5fe02f6b05546c662654001f0793a2", size = 1295751 },
+    { url = "https://files.pythonhosted.org/packages/27/57/8ec7c62012bed06731f7ee979da7f207bbc4b27feed5f36680b6a70df54f/shapely-2.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:b52f3ab845d32dfd20afba86675c91919a622f4627182daec64974db9b0b4608", size = 1442684 },
+    { url = "https://files.pythonhosted.org/packages/4f/3e/ea100eec5811bafd0175eb21828a3be5b0960f65250f4474391868be7c0f/shapely-2.0.7-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:4c2b9859424facbafa54f4a19b625a752ff958ab49e01bc695f254f7db1835fa", size = 1482451 },
+    { url = "https://files.pythonhosted.org/packages/ce/53/c6a3487716fd32e1f813d2a9608ba7b72a8a52a6966e31c6443480a1d016/shapely-2.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:5aed1c6764f51011d69a679fdf6b57e691371ae49ebe28c3edb5486537ffbd51", size = 1345765 },
+    { url = "https://files.pythonhosted.org/packages/fd/dd/b35d7891d25cc11066a70fb8d8169a6a7fca0735dd9b4d563a84684969a3/shapely-2.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73c9ae8cf443187d784d57202199bf9fd2d4bb7d5521fe8926ba40db1bc33e8e", size = 2421540 },
+    { url = "https://files.pythonhosted.org/packages/62/de/8dbd7df60eb23cb983bb698aac982944b3d602ef0ce877a940c269eae34e/shapely-2.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a9469f49ff873ef566864cb3516091881f217b5d231c8164f7883990eec88b73", size = 2525741 },
+    { url = "https://files.pythonhosted.org/packages/96/64/faf0413ebc7a84fe7a0790bf39ec0b02b40132b68e57aba985c0b6e4e7b6/shapely-2.0.7-cp312-cp312-win32.whl", hash = "sha256:6bca5095e86be9d4ef3cb52d56bdd66df63ff111d580855cb8546f06c3c907cd", size = 1296552 },
+    { url = "https://files.pythonhosted.org/packages/63/05/8a1c279c226d6ad7604d9e237713dd21788eab96db97bf4ce0ea565e5596/shapely-2.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:f86e2c0259fe598c4532acfcf638c1f520fa77c1275912bbc958faecbf00b108", size = 1443464 },
+]
+
 [[package]]
 name = "six"
 version = "1.17.0"

babeldoc-0.2.14/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.2.14"