BabelDOC 0.4.8__tar.gz → 0.4.10__tar.gz

{babeldoc-0.4.8 → babeldoc-0.4.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.4.8
+Version: 0.4.10
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -219,6 +219,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
 - `--no-auto-extract-glossary`: Disable automatic term extraction. If this flag is present, the step is skipped. Defaults to enabled.
+- `--save-auto-extracted-glossary`: Save automatically extracted glossary to the specified file. If not set, the glossary will not be saved.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

{babeldoc-0.4.8 → babeldoc-0.4.10}/README.md

@@ -166,6 +166,7 @@ uv run babeldoc --files example.pdf --files example2.pdf --openai --openai-model
 - `--rpc-doclayout`: RPC service host address for document layout analysis (default: None)
 - `--working-dir`: Working directory for translation. If not set, use temp directory.
 - `--no-auto-extract-glossary`: Disable automatic term extraction. If this flag is present, the step is skipped. Defaults to enabled.
+- `--save-auto-extracted-glossary`: Save automatically extracted glossary to the specified file. If not set, the glossary will not be saved.
 
 > [!TIP]
 > - Both `--skip-clean` and `--dual-translate-first` may help improve compatibility with some PDF readers

babeldoc-0.4.10/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.4.10"

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.4.8"
+__version__ = "0.4.10"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/format/pdf/document_il/backend/pdf_creater.py

@@ -1081,7 +1081,25 @@ class PDFCreater:
                 mono_out_path = None
             if self.translation_config.no_dual:
                 dual_out_path = None
-            return TranslateResult(mono_out_path, dual_out_path)
+            auto_extracted_glossary_path = None
+            if (
+                self.translation_config.save_auto_extracted_glossary
+                and self.translation_config.shared_context_cross_split_part.auto_extracted_glossary
+            ):
+                auto_extracted_glossary_path = self.translation_config.get_output_file_path(
+                    f"{basename}{debug_suffix}.{translation_config.lang_out}.glossary.csv"
+                )
+                with auto_extracted_glossary_path.open("w", encoding="utf-8") as f:
+                    logger.info(
+                        f"save auto extracted glossary to {auto_extracted_glossary_path}"
+                    )
+                    f.write(
+                        self.translation_config.shared_context_cross_split_part.auto_extracted_glossary.to_csv()
+                    )
+
+            return TranslateResult(
+                mono_out_path, dual_out_path, auto_extracted_glossary_path
+            )
         except Exception:
             logger.exception(
                 "Failed to create PDF: %s",

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/format/pdf/document_il/midend/typesetting.py

@@ -6,6 +6,7 @@ import unicodedata
 from functools import cache
 
 import pymupdf
+from rtree import index
 
 from babeldoc.const import WATERMARK_VERSION
 from babeldoc.format.pdf.document_il import Box
@@ -16,6 +17,7 @@ from babeldoc.format.pdf.document_il import PdfStyle
 from babeldoc.format.pdf.document_il import il_version_1
 from babeldoc.format.pdf.document_il.utils.fontmap import FontMapper
 from babeldoc.format.pdf.document_il.utils.formular_helper import update_formula_data
+from babeldoc.format.pdf.document_il.utils.layout_helper import box_to_tuple
 from babeldoc.format.pdf.translation_config import TranslationConfig
 from babeldoc.format.pdf.translation_config import WatermarkOutputMode
 
@@ -592,6 +594,62 @@ class Typesetting:
             == WatermarkOutputMode.Watermarked
         ):
             self.add_watermark(page)
+        try:
+            para_index = index.Index()
+            para_map = {}
+            #
+            valid_paras = [
+                p
+                for p in page.pdf_paragraph
+                if p.box
+                and all(c is not None for c in [p.box.x, p.box.y, p.box.x2, p.box.y2])
+            ]
+
+            for i, para in enumerate(valid_paras):
+                para_map[i] = para
+                para_index.insert(i, box_to_tuple(para.box))
+
+            for i, p_upper in para_map.items():
+                required_gap = 6
+                if not (p_upper.box and p_upper.box.y is not None):
+                    continue
+
+                check_area = il_version_1.Box(
+                    x=p_upper.box.x,
+                    y=p_upper.box.y - required_gap,
+                    x2=p_upper.box.x2,
+                    y2=p_upper.box.y,
+                )
+
+                candidate_ids = list(para_index.intersection(box_to_tuple(check_area)))
+
+                conflicting_paras = []
+                for para_id in candidate_ids:
+                    if para_id == i:
+                        continue
+                    p_lower = para_map[para_id]
+                    if not (
+                        p_lower.box
+                        and p_upper.box
+                        and p_lower.box.x2 < p_upper.box.x
+                        or p_lower.box.x > p_upper.box.x2
+                    ):
+                        conflicting_paras.append(p_lower)
+
+                if conflicting_paras:
+                    max_y2 = max(
+                        p.box.y2
+                        for p in conflicting_paras
+                        if p.box and p.box.y2 is not None
+                    )
+
+                    new_y = max_y2 + required_gap
+                    if p_upper.box and new_y < p_upper.box.y2:
+                        p_upper.box.y = new_y
+        except Exception as e:
+            logger.warning(
+                f"Failed to adjust paragraph positions on page {page.page_number}: {e}"
+            )
         # 开始实际的渲染过程
         for paragraph in page.pdf_paragraph:
             self.render_paragraph(paragraph, page, fonts)
@@ -887,7 +945,7 @@ class Typesetting:
             if scale < 0.7 and min_line_spacing > 1.1:
                 if expand_space_flag == 0:
                     # 先尝试向下扩展
-                    min_y = self.get_max_bottom_space(box, page)
+                    min_y = self.get_max_bottom_space(box, page) + 2
                     if min_y < box.y:
                         expanded_box = Box(
                             x=box.x,
@@ -902,7 +960,7 @@ class Typesetting:
                     continue
                 elif expand_space_flag == 1:
                     # 如果向下扩展后还不够，再尝试向右扩展
-                    max_x = self.get_max_right_space(box, page)
+                    max_x = self.get_max_right_space(box, page) - 5
                     if max_x > box.x2:
                         expanded_box = Box(
                             x=box.x,

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/format/pdf/result_merger.py

@@ -127,10 +127,27 @@ class ResultMerger:
                 logger.error(f"Error merging no-watermark PDFs: {e}")
                 merged_no_watermark_dual_path = None
 
+        auto_extracted_glossary_path = None
+        if (
+            self.config.save_auto_extracted_glossary
+            and self.config.shared_context_cross_split_part.auto_extracted_glossary
+        ):
+            auto_extracted_glossary_path = self.config.get_output_file_path(
+                f"{basename}{debug_suffix}.{self.config.lang_out}.glossary.csv"
+            )
+            with auto_extracted_glossary_path.open("w", encoding="utf-8") as f:
+                logger.info(
+                    f"save auto extracted glossary to {auto_extracted_glossary_path}"
+                )
+                f.write(
+                    self.config.shared_context_cross_split_part.auto_extracted_glossary.to_csv()
+                )
+
         # Create merged result
         merged_result = TranslateResult(
             mono_pdf_path=merged_mono_path,
             dual_pdf_path=merged_dual_path,
+            auto_extracted_glossary_path=auto_extracted_glossary_path,
         )
         merged_result.no_watermark_mono_pdf_path = merged_no_watermark_mono_path
         merged_result.no_watermark_dual_pdf_path = merged_no_watermark_dual_path

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/format/pdf/translation_config.py

@@ -154,6 +154,7 @@ class TranslationConfig:
         auto_enable_ocr_workaround: bool = False,
         primary_font_family: str | None = None,
         only_include_translated_page: bool | None = False,
+        save_auto_extracted_glossary: bool = True,
     ):
         self.translator = translator
         initial_user_glossaries = list(glossaries) if glossaries else []
@@ -274,6 +275,8 @@ class TranslationConfig:
 
         self.only_include_translated_page = only_include_translated_page
 
+        self.save_auto_extracted_glossary = save_auto_extracted_glossary
+
     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
 
@@ -380,13 +383,19 @@ class TranslationConfig:
 class TranslateResult:
     original_pdf_path: str
     total_seconds: float
-    mono_pdf_path: str | None
-    dual_pdf_path: str | None
-    no_watermark_mono_pdf_path: str | None
-    no_watermark_dual_pdf_path: str | None
+    mono_pdf_path: Path | None
+    dual_pdf_path: Path | None
+    no_watermark_mono_pdf_path: Path | None
+    no_watermark_dual_pdf_path: Path | None
     peak_memory_usage: int | None
+    auto_extracted_glossary_path: Path | None
 
-    def __init__(self, mono_pdf_path: str | None, dual_pdf_path: str | None):
+    def __init__(
+        self,
+        mono_pdf_path: Path | None,
+        dual_pdf_path: Path | None,
+        auto_extracted_glossary_path: Path | None = None,
+    ):
         self.mono_pdf_path = mono_pdf_path
         self.dual_pdf_path = dual_pdf_path
 
@@ -395,6 +404,8 @@ class TranslateResult:
         self.no_watermark_mono_pdf_path = mono_pdf_path
         self.no_watermark_dual_pdf_path = dual_pdf_path
 
+        self.auto_extracted_glossary_path = auto_extracted_glossary_path
+
     def __str__(self):
         """Return a human-readable string representation of the translation result."""
         result = []
@@ -428,6 +439,14 @@ class TranslateResult:
                 f"\tNo-watermark Dual-language PDF: {self.no_watermark_dual_pdf_path}"
             )
 
+        if (
+            hasattr(self, "auto_extracted_glossary_path")
+            and self.auto_extracted_glossary_path
+        ):
+            result.append(
+                f"\tAuto-extracted glossary: {self.auto_extracted_glossary_path}"
+            )
+
         if hasattr(self, "peak_memory_usage") and self.peak_memory_usage:
             result.append(f"\tPeak memory usage: {self.peak_memory_usage} MB")
 

{babeldoc-0.4.8 → babeldoc-0.4.10}/babeldoc/main.py

@@ -21,7 +21,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.4.8"
+__version__ = "0.4.10"
 
 
 def create_parser():
@@ -271,6 +271,12 @@ def create_parser():
         default=False,
         help="Only include translated pages in the output PDF. Effective only when --pages is used.",
     )
+    translation_group.add_argument(
+        "--save-auto-extracted-glossary",
+        action="store_true",
+        default=False,
+        help="Save automatically extracted glossary terms to a CSV file in the output directory.",
+    )
     # service option argument group
     service_group = translation_group.add_mutually_exclusive_group()
     service_group.add_argument(
@@ -498,6 +504,7 @@ async def main():
             auto_enable_ocr_workaround=args.auto_enable_ocr_workaround,
             primary_font_family=args.primary_font_family,
             only_include_translated_page=args.only_include_translated_page,
+            save_auto_extracted_glossary=args.save_auto_extracted_glossary,
         )
 
         # Create progress handler

{babeldoc-0.4.8 → babeldoc-0.4.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.4.8"
+version = "0.4.10"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -158,7 +158,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.4.8"
+current_version = "0.4.10"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.4.8 → babeldoc-0.4.10}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.4.8"
+version = "0.4.10"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.4.8/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.4.8"