BabelDOC 0.1.7__tar.gz → 0.1.9__tar.gz

{babeldoc-0.1.7 → babeldoc-0.1.9}/.github/workflows/publish-to-pypi.yml

@@ -82,7 +82,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: pypi
-      url: https://pypi.org/p/yadt
+      url: https://pypi.org/p/BabelDOC
 
     permissions:
       id-token: write
@@ -106,7 +106,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: testpypi
-      url: https://test.pypi.org/p/yadt
+      url: https://test.pypi.org/p/BabelDOC
 
     permissions:
       id-token: write

{babeldoc-0.1.7 → babeldoc-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.7
+Version: 0.1.9
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -12,7 +12,7 @@ Classifier: Programming Language :: Python :: 3
 Requires-Python: <3.13,>=3.10
 Requires-Dist: bitstring>=4.3.0
 Requires-Dist: configargparse>=1.7
-Requires-Dist: httpx>=0.27.0
+Requires-Dist: httpx[socks]>=0.27.0
 Requires-Dist: huggingface-hub>=0.27.0
 Requires-Dist: msgpack>=1.1.0
 Requires-Dist: numpy>=2.0.2
@@ -274,6 +274,8 @@ We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](http
 
 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).
 
+[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-0.1.7 → babeldoc-0.1.9}/README.md

@@ -242,6 +242,8 @@ We encourage you to contribute to YADT! Please check out the [CONTRIBUTING](http
 
 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).
 
+[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-0.1.9/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.9"

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/document_il/backend/pdf_creater.py

@@ -12,9 +12,12 @@ from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
 
+SUBSET_FONT_STAGE_NAME = "Subset font"
+SAVE_PDF_STAGE_NAME = "Save PDF"
+
 
 class PDFCreater:
-    stage_name = "Create PDF file"
+    stage_name = "Generate drawing instructions"
 
     def __init__(
         self,
@@ -249,7 +252,7 @@ class PDFCreater:
         self.font_mapper.add_font(pdf, self.docs)
         with self.translation_config.progress_monitor.stage_start(
             self.stage_name,
-            len(self.docs.page) + 2,
+            len(self.docs.page),
         ) as pbar:
             for page in self.docs.page:
                 translation_config.raise_if_cancelled()
@@ -346,9 +349,18 @@ class PDFCreater:
                 pdf.update_stream(op_container, draw_op.tobytes())
                 pdf[page.page_number].set_contents(op_container)
                 pbar.advance()
-            translation_config.raise_if_cancelled()
+        translation_config.raise_if_cancelled()
+        with self.translation_config.progress_monitor.stage_start(
+            SUBSET_FONT_STAGE_NAME,
+            1,
+        ) as pbar:
             if not translation_config.skip_clean:
                 pdf.subset_fonts(fallback=False)
+            pbar.advance()
+        with self.translation_config.progress_monitor.stage_start(
+            SAVE_PDF_STAGE_NAME,
+            2,
+        ) as pbar:
             if not translation_config.no_mono:
                 if translation_config.debug:
                     translation_config.raise_if_cancelled()

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/document_il/midend/il_translator.py

@@ -2,6 +2,7 @@ import concurrent.futures
 import json
 import logging
 from pathlib import Path
+from typing import List, Union
 
 from tqdm import tqdm
 
@@ -178,7 +179,7 @@ class ILTranslator:
         def __init__(
             self,
             unicode: str,
-            placeholders: [RichTextPlaceholder | FormulaPlaceholder],
+            placeholders: List[Union[RichTextPlaceholder, FormulaPlaceholder]],
             base_style: PdfStyle = None,
         ):
             self.unicode = unicode
@@ -487,7 +488,9 @@ class ILTranslator:
                     PdfSameStyleCharacters,
                 ) and text.replace(" ", "") == "".join(
                     x.char_unicode for x in placeholder.composition.pdf_character
-                ).replace(" ", ""):
+                ).replace(
+                    " ", ""
+                ):
                     comp = PdfParagraphComposition(
                         pdf_same_style_characters=placeholder.composition,
                     )

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/document_il/translator/cache.py

@@ -8,6 +8,8 @@ from peewee import Model
 from peewee import SqliteDatabase
 from peewee import TextField
 
+from babeldoc.const import CACHE_FOLDER as cache_folder
+
 # we don't init the database here
 db = SqliteDatabase(None)
 
@@ -92,7 +94,6 @@ class TranslationCache:
 
 
 def init_db(remove_exists=False):
-    cache_folder = Path.home() / ".cache" / "pdf2zh"
     cache_folder.mkdir(parents=True, exist_ok=True)
     # The current version does not support database migration, so add the version number to the file name.
     cache_db_path = cache_folder / "cache.v1.db"

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/docvision/rpc_doclayout.py

@@ -75,7 +75,8 @@ def predict_layout(
                 "Content-Type": "application/msgpack",
                 "Accept": "application/msgpack",
             },
-            timeout=30,
+            timeout=300,
+            follow_redirects=True,
         )
 
         logger.debug(f"Response status: {response.status_code}")

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/high_level.py

@@ -20,6 +20,8 @@ from babeldoc import asynchronize
 from babeldoc.const import CACHE_FOLDER
 from babeldoc.const import get_cache_file_path
 from babeldoc.converter import TranslateConverter
+from babeldoc.document_il.backend.pdf_creater import SAVE_PDF_STAGE_NAME
+from babeldoc.document_il.backend.pdf_creater import SUBSET_FONT_STAGE_NAME
 from babeldoc.document_il.backend.pdf_creater import PDFCreater
 from babeldoc.document_il.frontend.il_creater import ILCreater
 from babeldoc.document_il.midend.add_debug_information import AddDebugInformation
@@ -48,6 +50,8 @@ TRANSLATE_STAGES = [
     Typesetting.stage_name,
     FontMapper.stage_name,
     PDFCreater.stage_name,
+    SUBSET_FONT_STAGE_NAME,
+    SAVE_PDF_STAGE_NAME,
 ]
 
 resfont_map = {

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/main.py

@@ -20,7 +20,7 @@ from babeldoc.document_il.translator.translator import set_translate_rate_limite
 from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.7"
+__version__ = "0.1.9"
 
 
 def create_parser():

{babeldoc-0.1.7 → babeldoc-0.1.9}/babeldoc/progress_monitor.py

@@ -61,6 +61,7 @@ class ProgressMonitor:
                 stage_progress=0.0,
                 stage_current=0,
                 stage_total=total,
+                overall_progress=self.calculate_current_progress(),
             )
         self.last_report_time = 0.0
         return stage
@@ -110,7 +111,7 @@ class ProgressMonitor:
     def stage_update(self, stage, n: int):
         with self.lock:
             report_time_delta = time.time() - self.last_report_time
-            if report_time_delta < self.report_interval:
+            if report_time_delta < self.report_interval and stage.total > 3:
                 return
             if self.progress_change_callback:
                 self.progress_change_callback(

babeldoc-0.1.9/docs/CONTRIBUTOR_REWARD.md

@@ -0,0 +1,81 @@
+# BabelDOC/PDFMathTranslate 贡献者奖励规则
+
+### **月度活跃贡献者奖励规则**
+**一、资格标准**
+1. **贡献类型要求**
+   - 需提交 **至少 1 个有效 PR**（Pull Request），或进行 **PR 审核、文档编写** 等贡献。
+   - 有效贡献定义：
+     - 非简单的文档错别字修复
+     - 非简单的代码格式化调整（如仅调整缩进、空格等）
+     - 需做出实质性贡献（如功能开发、Bug 修复、性能优化、架构调整、技术文档编写、PR 审核等）
+   - 示例合格贡献：新增功能模块、修复逻辑错误、优化算法效率、编写技术文档等
+
+2. **时间范围**
+   - 每月 1 日至月末最后一天合并的 PR 计入当月统计
+
+**二、申请流程**
+1. **申请条件**
+   - PR 需被成功合并至[funstory-ai/BabelDOC](https://github.com/funstory-ai/BabelDOC/pulls) 仓库或 [Byaidu/PDFMathTranslate](https://github.com/Byaidu/PDFMathTranslate/pulls)的主分支。
+   - 审核 PR、撰写 wiki 等贡献也必须是以上两个仓库。
+   - 同一贡献者每月仅可申请一次（无论提交 PR 数量）
+   - 同一贡献者每月最多可以获得 1 个兑换码
+   - 对于 PR，只有发起者可以申请兑换码
+   - 仅可使用当月的贡献申请兑换码（特殊情况请联系 aw@funstory.ai 说明）
+
+2. **申请方式**
+   - 发送邮件至 **aw@funstory.ai**
+   - 邮件标题格式：`[贡献者会员兑换码申请] GitHub用户名-月份`（例：`[贡献者会员兑换码申请] awwaawwa-2024-07`）
+   - 邮件正文需包含：
+     - GitHub 用户名
+     - 合并 PR 的完整链接
+   - 附件要求：
+     - PR 页面完整截图（需包含合并状态、仓库名称及点击头像后弹出来的侧边栏，如下图所示）
+
+![附件示例](images/contributor_reward_example.png)
+
+3. **奖励说明**
+   - 奖励内容：[沉浸式翻译（Immersive Translate）](https://immersivetranslate.com/zh-Hans/pricing/)月度会员兑换码
+   - 兑换码使用：在[沉浸式翻译官网兑换页](https://immersivetranslate.com/zh-Hans/exchange)输入即可激活
+   - 会员权益：沉浸式翻译 Pro 会员一个月（详见[官网价格页](https://immersivetranslate.com/zh-Hans/pricing/)说明）
+   - 兑换码为专属福利，不可转让
+
+**三、审核与发放**
+1. **审核周期**
+   - 我们会尽力在收到申请邮件后 1 个工作日内完成审核
+   - 审核时间可能因申请数量、审核复杂度等因素有所延长
+   - 审核通过后，兑换码将通过邮件方式发送
+   - 若审核未通过，我们会通过邮件说明原因
+
+2. 兑换码规则：
+   - 使用方式：[官网兑换页](https://immersivetranslate.com/zh-Hans/exchange)输入兑换码激活
+   - 权益内容：月度会员（具体权益见[官网价格页](https://immersivetranslate.com/zh-Hans/pricing/)说明）
+   - 不可转让
+
+**四、注意事项**
+1. **禁止行为**
+   - 将完整功能拆分为多个无关 PR 提交
+   - 提交质量不合格或具有潜在危害的代码
+   - 提供虚假或误导性的申请材料
+
+2. **特别说明**
+   - funstory.ai 保留对贡献价值的评估权、规则的最终解释权等所有必要权利
+   - 规则如有更新，将提前 1 天在 [BabelDOC GitHub PR](https://github.com/funstory-ai/BabelDOC/pulls) 公告
+   - 过期未使用的兑换码不予补发
+   - 自 2025 年 2 月 1 日起的贡献可以申请兑换码
+   - 为了确认您是 Pull Request (PR) 的发起者，防止他人冒领，我们可能会要求您使用发起者账号在 PR 下方留言指定的随机数字。
+
+
+---
+### **常见问题解答（FAQ）**
+
+Q：如何判断文档翻译贡献是否有效？
+A：系统性的人工翻译（如完整章节的翻译并经过人工校对）视为有效贡献。零散段落翻译或仅依赖机器翻译的内容不计入有效贡献。
+
+Q：兑换码过期了可以补发吗？
+A：为确保公平性，过期的兑换码将不予补发，请在有效期内及时使用。
+
+Q：为什么这个文档是中文的？
+A：因为目前应该是中文贡献者多吧，所以就先写中文的。后面再撰写英文版的。
+
+---
+**规则公示**：本规则文档存放于 BabelDOC 仓库 [CONTRIBUTOR_REWARD.md](https://github.com/funstory-ai/BabelDOC/blob/main/docs/CONTRIBUTOR_REWARD.md)。

{babeldoc-0.1.7 → babeldoc-0.1.9}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.7"
+version = "0.1.9"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -13,7 +13,7 @@ keywords = ["PDF"]
 dependencies = [
     "bitstring>=4.3.0",
     "configargparse>=1.7",
-    "httpx>=0.27.0",
+    "httpx[socks]>=0.27.0",
     "huggingface-hub>=0.27.0",
     "numpy>=2.0.2",
     "onnx>=1.17.0",
@@ -117,7 +117,7 @@ dev = [
 ]
 
 [bumpver]
-current_version = "0.1.7"
+current_version = "0.1.9"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.7 → babeldoc-0.1.9}/uv.lock

@@ -1,4 +1,5 @@
 version = 1
+revision = 1
 requires-python = ">=3.10, <3.13"
 resolution-markers = [
     "python_full_version >= '3.12' and sys_platform == 'darwin'",
@@ -38,12 +39,12 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.7"
+version = "0.1.9"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },
     { name = "configargparse" },
-    { name = "httpx" },
+    { name = "httpx", extra = ["socks"] },
     { name = "huggingface-hub" },
     { name = "msgpack" },
     { name = "numpy" },
@@ -72,7 +73,7 @@ dev = [
 requires-dist = [
     { name = "bitstring", specifier = ">=4.3.0" },
     { name = "configargparse", specifier = ">=1.7" },
-    { name = "httpx", specifier = ">=0.27.0" },
+    { name = "httpx", extras = ["socks"], specifier = ">=0.27.0" },
     { name = "huggingface-hub", specifier = ">=0.27.0" },
     { name = "msgpack", specifier = ">=1.1.0" },
     { name = "numpy", specifier = ">=2.0.2" },
@@ -489,6 +490,11 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517 },
 ]
 
+[package.optional-dependencies]
+socks = [
+    { name = "socksio" },
+]
+
 [[package]]
 name = "huggingface-hub"
 version = "0.27.1"
@@ -1245,6 +1251,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
 ]
 
+[[package]]
+name = "socksio"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/5c/48a7d9495be3d1c651198fd99dbb6ce190e2274d0f28b9051307bdec6b85/socksio-1.0.0.tar.gz", hash = "sha256:f88beb3da5b5c38b9890469de67d0cb0f9d494b78b106ca1845f96c10b91c4ac", size = 19055 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/37/c3/6eeb6034408dac0fa653d126c9204ade96b819c936e136c5e8a6897eee9c/socksio-1.0.0-py3-none-any.whl", hash = "sha256:95dc1f15f9b34e8d7b16f06d74b8ccf48f609af32ab33c608d08761c5dcbb1f3", size = 12763 },
+]
+
 [[package]]
 name = "sympy"
 version = "1.13.3"

babeldoc-0.1.7/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.7"