BabelDOC 0.1.17__tar.gz → 0.1.19__tar.gz

{babeldoc-0.1.17 → babeldoc-0.1.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.1.17
+Version: 0.1.19
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues
@@ -58,6 +58,7 @@ Description-Content-Type: text/markdown
 
 PDF scientific paper translation and bilingual comparison library.
 
+- Beta version launched [Immersive Translate - BabelDOC](https://app.immersivetranslate.com/babel-doc/) 1000 free pages per month.
 - Provides a simple [command line interface](#getting-started).
 - Provides a [Python API](#python-api).
 - Mainly designed to be embedded into other programs, but can also be used directly for simple translation tasks.
@@ -133,6 +134,10 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 
 > [!TIP]
 > Currently, this project mainly focuses on English-to-Chinese translation, and other scenarios have not been tested yet.
+> 
+> (2025.3.1 update): Basic English target language support has been added, primarily to minimize line breaks within words([0-9A-Za-z]+).
+> 
+> [HELP WANTED: Collecting word regular expressions for more languages](https://github.com/funstory-ai/BabelDOC/issues/129)
 
 ### PDF Processing Options
 

{babeldoc-0.1.17 → babeldoc-0.1.19}/README.md

@@ -24,6 +24,7 @@
 
 PDF scientific paper translation and bilingual comparison library.
 
+- Beta version launched [Immersive Translate - BabelDOC](https://app.immersivetranslate.com/babel-doc/) 1000 free pages per month.
 - Provides a simple [command line interface](#getting-started).
 - Provides a [Python API](#python-api).
 - Mainly designed to be embedded into other programs, but can also be used directly for simple translation tasks.
@@ -99,6 +100,10 @@ uv run babeldoc --bing --files example.pdf --files example2.pdf
 
 > [!TIP]
 > Currently, this project mainly focuses on English-to-Chinese translation, and other scenarios have not been tested yet.
+> 
+> (2025.3.1 update): Basic English target language support has been added, primarily to minimize line breaks within words([0-9A-Za-z]+).
+> 
+> [HELP WANTED: Collecting word regular expressions for more languages](https://github.com/funstory-ai/BabelDOC/issues/129)
 
 ### PDF Processing Options
 

babeldoc-0.1.19/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.19"

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/const.py

@@ -2,7 +2,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.17"
+__version__ = "0.1.19"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/document_il/backend/pdf_creater.py

@@ -413,11 +413,11 @@ class PDFCreater:
 
         # 使用子进程进行字体子集化
         if not translation_config.skip_clean:
-            pdf = self.subset_fonts_in_subprocess(pdf, translation_config)
+            pdf = self.subset_fonts_in_subprocess(pdf, translation_config, tag="debug")
         return pdf
 
     def subset_fonts_in_subprocess(
-        self, pdf: pymupdf.Document, translation_config: TranslationConfig
+        self, pdf: pymupdf.Document, translation_config: TranslationConfig, tag: str
     ) -> pymupdf.Document:
         """Run font subsetting in a subprocess with timeout.
 
@@ -431,14 +431,10 @@ class PDFCreater:
         original_pdf = pdf
         # Create temporary file paths
         temp_input = str(
-            translation_config.get_working_file_path(
-                f"temp_subset_input_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_subset_input_{tag}.pdf")
         )
         temp_output = str(
-            translation_config.get_working_file_path(
-                f"temp_subset_output_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_subset_output_{tag}.pdf")
         )
 
         # Save PDF to temporary file without subsetting
@@ -504,6 +500,7 @@ class PDFCreater:
         deflate_fonts: bool = True,
         linear: bool = False,
         timeout: int = 120,
+        tag: str = "",
     ) -> bool:
         """Save a PDF document with a timeout for the clean=True operation.
 
@@ -523,14 +520,10 @@ class PDFCreater:
         """
         # Create temporary file paths
         temp_input = str(
-            translation_config.get_working_file_path(
-                f"temp_save_input_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_save_input_{tag}.pdf")
         )
         temp_output = str(
-            translation_config.get_working_file_path(
-                f"temp_save_output_{int(time.time())}.pdf"
-            )
+            translation_config.get_working_file_path(f"temp_save_output_{tag}.pdf")
         )
 
         # Save PDF to temporary file first
@@ -614,6 +607,9 @@ class PDFCreater:
                 logger.error(f"Error copying saved PDF: {e}")
                 pdf.save(output_path)  # Fallback to direct save
                 return False
+            finally:
+                Path(temp_input).unlink()
+                Path(temp_output).unlink()
         else:
             logger.warning(
                 f"PDF save with clean=True failed with exit code {exit_code} or produced empty file"
@@ -748,7 +744,9 @@ class PDFCreater:
             1,
         ) as pbar:
             if not translation_config.skip_clean:
-                pdf = self.subset_fonts_in_subprocess(pdf, translation_config)
+                pdf = self.subset_fonts_in_subprocess(
+                    pdf, translation_config, tag="mono"
+                )
 
             pbar.advance()
         with self.translation_config.progress_monitor.stage_start(
@@ -773,6 +771,7 @@ class PDFCreater:
                     clean=not translation_config.skip_clean,
                     deflate_fonts=True,
                     linear=False,
+                    tag="mono",
                 )
             pbar.advance()
             dual_out_path = None
@@ -823,6 +822,7 @@ class PDFCreater:
                     clean=not translation_config.skip_clean,
                     deflate_fonts=True,
                     linear=False,
+                    tag="dual",
                 )
                 if translation_config.debug:
                     translation_config.raise_if_cancelled()

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/document_il/midend/typesetting.py

@@ -1,4 +1,5 @@
 import logging
+import re
 import statistics
 import unicodedata
 from functools import cache
@@ -83,6 +84,15 @@ class TypesettingUnit:
             ]
         return False
 
+    @property
+    def can_break_line(self):
+        unicode = self.try_get_unicode()
+        if not unicode:
+            return True
+        if re.match(r"^[a-zA-Z0-9]+$", unicode):
+            return False
+        return True
+
     @property
     def is_chinese_char(self):
         if self.formular:
@@ -146,33 +156,85 @@ class TypesettingUnit:
 
         if unicode:
             return unicode in [
+                # 英文标点
                 ",",
                 ".",
                 ":",
                 ";",
                 "?",
                 "!",
-                "，",
-                "。",
-                "：",
-                "？",
-                "！",
-                "]",
-                "}",
-                "）",
-                "〕",
-                "〉",
-                "】",
-                "〗",
-                "」",
-                "』",
-                "、",
-                "”",
-                '"',
-                "；",
+                # 中文点号
+                "，",  # 逗号
+                "。",  # 句号
+                "．",  # 全角句号
+                "、",  # 顿号
+                "：",  # 冒号
+                "；",  # 分号
+                "！",  # 叹号
+                "‼",  # 双叹号
+                "？",  # 问号
+                "⁇",  # 双问号
+                # 结束引号
+                "”",  # 右双引号
+                "’",  # 右单引号
+                "」",  # 右直角单引号
+                "』",  # 右直角双引号
+                # 结束括号
+                ")",  # 右圆括号
+                "]",  # 右方括号
+                "}",  # 右花括号
+                "）",  # 右圆括号
+                "〕",  # 右龟甲括号
+                "〉",  # 右单书名号
+                "】",  # 右黑色方头括号
+                "〗",  # 右空白方头括号
+                "］",  # 全角右方括号
+                "｝",  # 全角右花括号
+                # 结束双书名号
+                "》",  # 右双书名号
+                # 连接号
+                "～",  # 全角波浪号
+                "-",  # 连字符减号
+                "–",  # 短破折号(EN DASH)
+                "—",  # 长破折号(EM DASH)
+                # 间隔号
+                "·",  # 中间点
+                "・",  # 片假名中间点
+                "‧",  # 连字点
+                # 分隔号
+                "/",  # 斜杠
+                "／",  # 全角斜杠
+                "⁄",  # 分数斜杠
             ]
         return False
 
+    @property
+    def is_cannot_appear_in_line_end_punctuation(self):
+        if self.formular:
+            return False
+        unicode = self.try_get_unicode()
+        if not unicode:
+            return False
+        return unicode in [
+            # 开始引号
+            "“",  # 左双引号
+            "‘",  # 左单引号
+            "「",  # 左直角单引号
+            "『",  # 左直角双引号
+            # 开始括号
+            "(",  # 左圆括号
+            "[",  # 左方括号
+            "{",  # 左花括号
+            "（",  # 左圆括号
+            "〔",  # 左龟甲括号
+            "〈",  # 左单书名号
+            "《",  # 左双书名号
+            # 开始单双书名号
+            "〖",  # 左空白方头括号
+            "〘",  # 左黑色方头括号
+            "〚",  # 左单书名号
+        ]
+
     def passthrough(self) -> [PdfCharacter]:
         if self.char:
             return [self.char]
@@ -450,6 +512,21 @@ class Typesetting:
         paragraph.pdf_paragraph_composition = []
         self.retypeset(paragraph, page, typesetting_units)
 
+    def _get_width_before_next_break_point(
+        self, typesetting_units: list[TypesettingUnit], scale: float
+    ) -> float:
+        if not typesetting_units:
+            return 0
+        if typesetting_units[0].can_break_line:
+            return 0
+
+        total_width = 0
+        for unit in typesetting_units:
+            if unit.can_break_line:
+                return total_width * scale
+            total_width += unit.width
+        return total_width * scale
+
     def _layout_typesetting_units(
         self,
         typesetting_units: list[TypesettingUnit],
@@ -457,6 +534,7 @@ class Typesetting:
         scale: float,
         line_spacing: float,
         paragraph: il_version_1.PdfParagraph,
+        use_english_line_break: bool = True,
     ) -> tuple[list[TypesettingUnit], bool]:
         """布局排版单元。
 
@@ -504,7 +582,7 @@ class Typesetting:
         if paragraph.first_line_indent:
             current_x += space_width * 4
         # 遍历所有排版单元
-        for unit in typesetting_units:
+        for i, unit in enumerate(typesetting_units):
             # 计算当前单元在当前缩放下的尺寸
             unit_width = unit.width * scale
             unit_height = unit.height * scale
@@ -528,11 +606,36 @@ class Typesetting:
                 and current_x > box.x  # 不是行首
                 and unit.try_get_unicode() != " "  # 不是空格
                 and last_unit.try_get_unicode() != " "  # 不是空格
+                and last_unit.try_get_unicode()
+                not in [
+                    "。",
+                    "！",
+                    "？",
+                    "；",
+                    "：",
+                    "，",
+                ]
             ):
                 current_x += space_width * 0.5
+            if use_english_line_break:
+                width_before_next_break_point = self._get_width_before_next_break_point(
+                    typesetting_units[i + 1 :], scale
+                )
+            else:
+                width_before_next_break_point = 0
 
             # 如果当前行放不下这个元素，换行
-            if current_x + unit_width > box.x2 and not unit.is_hung_punctuation:
+            if not unit.is_hung_punctuation and (
+                (current_x + unit_width > box.x2)
+                or (
+                    use_english_line_break
+                    and current_x + unit_width + width_before_next_break_point > box.x2
+                )
+                or (
+                    unit.is_cannot_appear_in_line_end_punctuation
+                    and current_x + unit_width * 2 > box.x2
+                )
+            ):
                 # 换行
                 current_x = box.x
                 current_y -= line_height * line_spacing
@@ -568,6 +671,7 @@ class Typesetting:
         paragraph: il_version_1.PdfParagraph,
         page: il_version_1.Page,
         typesetting_units: list[TypesettingUnit],
+        use_english_line_break: bool = True,
     ):
         box = paragraph.box
         scale = 1.0
@@ -584,6 +688,7 @@ class Typesetting:
                 scale,
                 line_spacing,
                 paragraph,
+                use_english_line_break,
             )
 
             # 如果所有单元都放得下，就完成排版
@@ -629,6 +734,11 @@ class Typesetting:
                 min_line_spacing = 1.1
                 scale = 1.0
                 line_spacing = 1.5
+        # 如果仍然放不下，则尝试去除英文换行限制
+        if use_english_line_break:
+            self.retypeset(
+                paragraph, page, typesetting_units, use_english_line_break=False
+            )
 
     def create_typesetting_units(
         self,

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/high_level.py

@@ -419,6 +419,7 @@ def do_translate(pm, translation_config):
     finally:
         logger.debug("do_translate finally")
         pm.on_finish()
+        translation_config.cleanup_temp_files()
 
 
 def download_font_assets():

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/main.py

@@ -23,7 +23,7 @@ from babeldoc.docvision.rpc_doclayout import RpcDocLayoutModel
 from babeldoc.translation_config import TranslationConfig
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.17"
+__version__ = "0.1.19"
 
 
 def create_parser():

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/pdfinterp.py

@@ -249,7 +249,13 @@ class PDFPageInterpreterEx(PDFPageInterpreter):
         subtype = xobj.get("Subtype")
         if subtype is LITERAL_FORM and "BBox" in xobj:
             interpreter = self.dup()
-            bbox = cast(Rect, list_value(xobj["BBox"]))
+
+            # In extremely rare cases, a none might be mixed in the bbox, for example
+            # /BBox [ 0 3.052 null 274.9 157.3 ]
+            bbox = list(
+                filter(lambda x: x is not None, cast(Rect, list_value(xobj["BBox"])))
+            )
+
             matrix = cast(Matrix, list_value(xobj.get("Matrix", MATRIX_IDENTITY)))
             # According to PDF reference 1.7 section 4.9.1, XObjects in
             # earlier PDFs (prior to v1.2) use the page's Resources entry

{babeldoc-0.1.17 → babeldoc-0.1.19}/babeldoc/translation_config.py

@@ -1,3 +1,5 @@
+import logging
+import shutil
 import tempfile
 import threading
 from pathlib import Path
@@ -7,6 +9,8 @@ from babeldoc.document_il.translator.translator import BaseTranslator
 from babeldoc.docvision.doclayout import DocLayoutModel
 from babeldoc.progress_monitor import ProgressMonitor
 
+logger = logging.getLogger(__name__)
+
 
 class TranslationConfig:
     def __init__(
@@ -158,6 +162,11 @@ class TranslationConfig:
         if self.progress_monitor is not None:
             self.progress_monitor.cancel()
 
+    def cleanup_temp_files(self):
+        if self._is_temp_dir:
+            logger.info(f"cleanup temp files: {self.working_dir}")
+            shutil.rmtree(self.working_dir)
+
 
 class TranslateResult:
     original_pdf_path: str

{babeldoc-0.1.17 → babeldoc-0.1.19}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.17"
+version = "0.1.19"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -132,7 +132,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.17"
+current_version = "0.1.19"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

{babeldoc-0.1.17 → babeldoc-0.1.19}/uv.lock

@@ -48,7 +48,7 @@ wheels = [
 
 [[package]]
 name = "babeldoc"
-version = "0.1.17"
+version = "0.1.19"
 source = { editable = "." }
 dependencies = [
     { name = "bitstring" },

babeldoc-0.1.17/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.17"