BabelDOC 0.5.24__tar.gz → 0.6.1__tar.gz

{babeldoc-0.5.24 → babeldoc-0.6.1}/.github/workflows/publish-to-pypi.yml

@@ -55,6 +55,11 @@ jobs:
           version-command: |
             cat pyproject.toml | grep "version = " | head -n 1 | awk -F'"' '{print $2}'
 
+      - name: Check manual release notes
+        if: steps.check-version.outputs.tag
+        run: |
+          test -f "docs/release-notes/${{ steps.check-version.outputs.tag }}.md"
+
       - name: Install Dependencies
         run: |
           uv sync
@@ -151,4 +156,22 @@ jobs:
           publish: ${{ needs.build.outputs.is_release != '' }}
           tag: ${{ needs.build.outputs.is_release }}
         env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Prepend manual release notes
+        if: needs.build.outputs.is_release != ''
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG: ${{ needs.build.outputs.is_release }}
+        run: |
+          set -euo pipefail
+          notes_path="docs/release-notes/${TAG}.md"
+          current_body="$(mktemp)"
+          combined_body="$(mktemp)"
+          gh release view "${TAG}" --json body --jq .body > "${current_body}"
+          {
+            cat "${notes_path}"
+            printf '\n\n---\n\n'
+            cat "${current_body}"
+          } > "${combined_body}"
+          gh release edit "${TAG}" --notes-file "${combined_body}"

{babeldoc-0.5.24 → babeldoc-0.6.1}/.gitignore

@@ -25,7 +25,9 @@ memray*
 .vscode
 __pycache__
 .ruff_cache
+.tmp
 yadt.toml
+yadt.toml*
 examples/
 /make_gif.py
 /dist
@@ -41,10 +43,9 @@ babeldoc/format/txt
 # uv
 uv.lock
 
-# Claude Code memory file
-CLAUDE.md
 /.claude
 babeldoc/format/playground
 temp.jpg
-AGENTS.md
-.serena
+.serena
+.codex
+

{babeldoc-0.5.24 → babeldoc-0.6.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.24
+Version: 0.6.1
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -34,7 +34,6 @@ Requires-Dist: psutil>=7.0.0
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: pymupdf>=1.25.1
 Requires-Dist: pyzstd>=0.17.0
-Requires-Dist: rapidocr-onnxruntime>=1.4.4
 Requires-Dist: rich>=13.9.4
 Requires-Dist: rtree>=1.4.0
 Requires-Dist: scikit-image>=0.25.2
@@ -54,10 +53,7 @@ Provides-Extra: memray
 Requires-Dist: memray>=1.17.1; extra == 'memray'
 Description-Content-Type: text/markdown
 
-<!-- # Yet Another Document Translator -->
-
 <div align="center">
-<!-- <img src="https://s.immersivetranslate.com/assets/r2-uploads/images/babeldoc-banner.png" width="320px"  alt="YADT"/> -->
 
 <br/>
 
@@ -120,11 +116,11 @@ See details: [EN](https://github.com/funstory-ai/jobs) | [ZH](https://github.com
 
 ### Install from PyPI
 
-We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to install yadt.
+We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to install BabelDOC.
 
 1. First, you need to refer to [uv installation](https://github.com/astral-sh/uv#installation) to install uv and set up the `PATH` environment variable as prompted.
 
-2. Use the following command to install yadt:
+2. Use the following command to install BabelDOC:
 
 ```bash
 uv tool install --python 3.12 BabelDOC
@@ -147,7 +143,7 @@ We still recommend using [uv](https://github.com/astral-sh/uv) to manage virtual
 
 1. First, you need to refer to [uv installation](https://github.com/astral-sh/uv#installation) to install uv and set up the `PATH` environment variable as prompted.
 
-2. Use the following command to install yadt:
+2. Use the following command to install BabelDOC:
 
 ```bash
 # clone the project
@@ -291,7 +287,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
-- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/babeldoc/working`.
 - `--report-interval`: Progress report interval in seconds (default: 0.1).
 
 ### General Options
@@ -394,7 +390,7 @@ There are a lot projects and teams working on to make document editing and trans
 - [mathpix](https://mathpix.com/)
 - [Doc2X](https://doc2x.noedgeai.com/)
 - [minerU](https://github.com/opendatalab/MinerU)
-- [PDFMathTranslate](https://github.com/funstory-ai/yadt)
+- [PDFMathTranslate](https://github.com/PDFMathTranslate/PDFMathTranslate)
 
 There are also some solutions to solve specific parts of the problem like:
 
@@ -458,15 +454,25 @@ This project uses a combination of [Semantic Versioning](https://semver.org/) an
 
 ## How to Contribute
 
-We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](https://github.com/funstory-ai/yadt/blob/main/docs/CONTRIBUTING.md) guide.
+BabelDOC is currently developed in a maintainer-led mode. Bug reports,
+reproducible PDFs, documentation fixes, and small compatibility fixes are
+welcome. For changes to parsing, rendering, translation, or service integration
+behavior, please open an issue for discussion before submitting a pull request.
 
-Everyone interacting in YADT and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the YADT [Code of Conduct](https://github.com/funstory-ai/yadt/blob/main/docs/CODE_OF_CONDUCT.md).
+Everyone interacting in BabelDOC and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the BabelDOC [Code of Conduct](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CODE_OF_CONDUCT.md).
 
 [Immersive Translation](https://immersivetranslate.com) sponsors monthly Pro membership redemption codes for active contributors to this project, see details at: [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)
 
 ## Acknowledgements
 
-- [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
+BabelDOC is still at an early stage of development, and many parts are not as
+polished as we would like yet. We sincerely appreciate every bug report,
+criticism, suggestion, reproducible PDF, downstream integration experience, and
+contribution from people working on BabelDOC and related upstream/downstream
+projects. We will keep iterating on BabelDOC, fixing bugs, and making it better
+step by step.
+
+- [PDFMathTranslate](https://github.com/PDFMathTranslate/PDFMathTranslate)
 - [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
 - [pdfminer](https://github.com/pdfminer/pdfminer.six)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)

{babeldoc-0.5.24 → babeldoc-0.6.1}/README.md

@@ -1,7 +1,4 @@
-<!-- # Yet Another Document Translator -->
-
 <div align="center">
-<!-- <img src="https://s.immersivetranslate.com/assets/r2-uploads/images/babeldoc-banner.png" width="320px"  alt="YADT"/> -->
 
 <br/>
 
@@ -64,11 +61,11 @@ See details: [EN](https://github.com/funstory-ai/jobs) | [ZH](https://github.com
 
 ### Install from PyPI
 
-We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to install yadt.
+We recommend using the Tool feature of [uv](https://github.com/astral-sh/uv) to install BabelDOC.
 
 1. First, you need to refer to [uv installation](https://github.com/astral-sh/uv#installation) to install uv and set up the `PATH` environment variable as prompted.
 
-2. Use the following command to install yadt:
+2. Use the following command to install BabelDOC:
 
 ```bash
 uv tool install --python 3.12 BabelDOC
@@ -91,7 +88,7 @@ We still recommend using [uv](https://github.com/astral-sh/uv) to manage virtual
 
 1. First, you need to refer to [uv installation](https://github.com/astral-sh/uv#installation) to install uv and set up the `PATH` environment variable as prompted.
 
-2. Use the following command to install yadt:
+2. Use the following command to install BabelDOC:
 
 ```bash
 # clone the project
@@ -235,7 +232,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 ### Output Control
 
 - `--output`, `-o`: Output directory for translated files. If not set, use current working directory.
-- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/yadt/working`.
+- `--debug`: Enable debug logging level and export detailed intermediate results in `~/.cache/babeldoc/working`.
 - `--report-interval`: Progress report interval in seconds (default: 0.1).
 
 ### General Options
@@ -338,7 +335,7 @@ There are a lot projects and teams working on to make document editing and trans
 - [mathpix](https://mathpix.com/)
 - [Doc2X](https://doc2x.noedgeai.com/)
 - [minerU](https://github.com/opendatalab/MinerU)
-- [PDFMathTranslate](https://github.com/funstory-ai/yadt)
+- [PDFMathTranslate](https://github.com/PDFMathTranslate/PDFMathTranslate)
 
 There are also some solutions to solve specific parts of the problem like:
 
@@ -402,15 +399,25 @@ This project uses a combination of [Semantic Versioning](https://semver.org/) an
 
 ## How to Contribute
 
-We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](https://github.com/funstory-ai/yadt/blob/main/docs/CONTRIBUTING.md) guide.
+BabelDOC is currently developed in a maintainer-led mode. Bug reports,
+reproducible PDFs, documentation fixes, and small compatibility fixes are
+welcome. For changes to parsing, rendering, translation, or service integration
+behavior, please open an issue for discussion before submitting a pull request.
 
-Everyone interacting in YADT and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the YADT [Code of Conduct](https://github.com/funstory-ai/yadt/blob/main/docs/CODE_OF_CONDUCT.md).
+Everyone interacting in BabelDOC and its sub-projects' codebases, issue trackers, chat rooms, and mailing lists is expected to follow the BabelDOC [Code of Conduct](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CODE_OF_CONDUCT.md).
 
 [Immersive Translation](https://immersivetranslate.com) sponsors monthly Pro membership redemption codes for active contributors to this project, see details at: [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)
 
 ## Acknowledgements
 
-- [PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate)
+BabelDOC is still at an early stage of development, and many parts are not as
+polished as we would like yet. We sincerely appreciate every bug report,
+criticism, suggestion, reproducible PDF, downstream integration experience, and
+contribution from people working on BabelDOC and related upstream/downstream
+projects. We will keep iterating on BabelDOC, fixing bugs, and making it better
+step by step.
+
+- [PDFMathTranslate](https://github.com/PDFMathTranslate/PDFMathTranslate)
 - [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
 - [pdfminer](https://github.com/pdfminer/pdfminer.six)
 - [PyMuPDF](https://github.com/pymupdf/PyMuPDF)

babeldoc-0.6.1/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.6.1"

{babeldoc-0.5.24 → babeldoc-0.6.1}/babeldoc/assets/assets.py

@@ -17,10 +17,6 @@ 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
@@ -38,20 +34,33 @@ _FASTEST_FONT_METADATA: dict | None = None
 class ResultContainer:
     def __init__(self):
         self.result = None
+        self.exception: BaseException | None = None
 
     def set_result(self, result):
         self.result = result
 
+    def set_exception(self, exc: BaseException):
+        self.exception = exc
+
 
 def run_in_another_thread(coro):
     result_container = ResultContainer()
 
     def _wrapper():
-        result_container.set_result(asyncio.run(coro))
+        try:
+            result_container.set_result(asyncio.run(coro))
+        except BaseException as exc:  # noqa: BLE001
+            result_container.set_exception(exc)
 
     thread = threading.Thread(target=_wrapper)
     thread.start()
     thread.join()
+    if result_container.exception is not None:
+        msg = (
+            "asset coroutine failed: "
+            f"{type(result_container.exception).__name__}: {result_container.exception}"
+        )
+        raise RuntimeError(msg) from result_container.exception
     return result_container.result
 
 
@@ -248,23 +257,10 @@ async def get_doclayout_onnx_model_path_async(client: httpx.AsyncClient | None =
 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
+    _ = client
+    dummy_path = get_cache_file_path("rapidocr-retired-dummy.txt", "models")
+    dummy_path.write_text("RapidOCR table detection is retired.\n", encoding="utf-8")
+    return dummy_path
 
 
 def get_doclayout_onnx_model_path():
@@ -457,12 +453,9 @@ async def async_warmup():
     _ = encoding_for_model("gpt-4o")
     async with httpx.AsyncClient() as client:
         onnx_task = asyncio.create_task(get_doclayout_onnx_model_path_async(client))
-        onnx_task2 = asyncio.create_task(
-            get_table_detection_rapidocr_model_path_async(client)
-        )
         font_tasks = asyncio.create_task(download_all_fonts_async(client))
         cmap_tasks = asyncio.create_task(download_all_cmaps_async(client))
-        await asyncio.gather(onnx_task, onnx_task2, font_tasks, cmap_tasks)
+        await asyncio.gather(onnx_task, font_tasks, cmap_tasks)
 
 
 def warmup():
@@ -502,12 +495,6 @@ def generate_all_assets_file_list():
             "sha3_256": DOCLAYOUT_YOLO_DOCSTRUCTBENCH_IMGSZ1024ONNX_SHA3_256,
         },
     )
-    result["models"].append(
-        {
-            "name": "ch_PP-OCRv4_det_infer.onnx",
-            "sha3_256": TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256,
-        },
-    )
     return result
 
 
@@ -620,6 +607,4 @@ if __name__ == "__main__":
     logging.getLogger("httpcore").setLevel(logging.WARNING)
     # warmup()
     # generate_offline_assets_package()
-    # restore_offline_assets_package(Path(
-    #     '/Users/aw/.cache/babeldoc/assets/offline_assets_33971e4940e90ba0c35baacda44bbe83b214f4703a7bdb8b837de97d0383508c.zip'))
     # warmup()

{babeldoc-0.5.24 → babeldoc-0.6.1}/babeldoc/assets/embedding_assets_metadata.py

@@ -4,10 +4,6 @@ DOCLAYOUT_YOLO_DOCSTRUCTBENCH_IMGSZ1024ONNX_SHA3_256 = (
     "60be061226930524958b5465c8c04af3d7c03bcb0beb66454f5da9f792e3cf2a"
 )
 
-TABLE_DETECTION_RAPIDOCR_MODEL_SHA3_256 = (
-    "062f4619afe91b33147c033acadecbb53f2a7b99ac703d157b96d5b10948da5e"
-)
-
 TIKTOKEN_CACHES = {
     "fb374d419588a4632f3f557e76b4b70aebbca790": "cb04bcda5782cfbbe77f2f991d92c0ea785d9496ef1137c91dfc3c8c324528d6"
 }
@@ -39,12 +35,6 @@ 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-0.5.24 → babeldoc-0.6.1}/babeldoc/const.py

@@ -6,7 +6,7 @@ import subprocess
 import threading
 from pathlib import Path
 
-__version__ = "0.5.24"
+__version__ = "0.6.1"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"