BabelDOC 0.5.2__tar.gz → 0.5.3__tar.gz

{babeldoc-0.5.2 → babeldoc-0.5.3}/.github/workflows/docs.yml

@@ -17,7 +17,7 @@ jobs:
           git config user.name github-actions[bot]
           git config user.email 41898282+github-actions[bot]@users.noreply.github.com
       - name: Setup uv with Python 3.12
-        uses: astral-sh/setup-uv@d9e0f98d3fc6adb07d1e3d37f3043649ddad06a1 # v6.5.0
+        uses: astral-sh/setup-uv@4959332f0f014c5280e7eac8b70c90cb574c9f9b # v6.6.0
         with:
           python-version: "3.12"
           enable-cache: true

{babeldoc-0.5.2 → babeldoc-0.5.3}/.github/workflows/publish-to-pypi.yml

@@ -35,7 +35,7 @@ jobs:
           token: ${{ secrets.GITHUB_TOKEN }}
           
       - name: Setup uv with Python 3.12
-        uses: astral-sh/setup-uv@d9e0f98d3fc6adb07d1e3d37f3043649ddad06a1 # v6.5.0
+        uses: astral-sh/setup-uv@4959332f0f014c5280e7eac8b70c90cb574c9f9b # v6.6.0
         with:
           python-version: "3.12"
           enable-cache: true

{babeldoc-0.5.2 → babeldoc-0.5.3}/.github/workflows/test.yml

@@ -28,7 +28,7 @@ jobs:
           path: ~/.cache/babeldoc
           key: babeldoc-assets-${{ hashFiles('babeldoc/assets/embedding_assets_metadata.py') }}
       - name: Setup uv with Python ${{ matrix.python-version }}
-        uses: astral-sh/setup-uv@d9e0f98d3fc6adb07d1e3d37f3043649ddad06a1 # v6.5.0
+        uses: astral-sh/setup-uv@4959332f0f014c5280e7eac8b70c90cb574c9f9b # v6.6.0
         with:
           python-version: ${{ matrix.python-version }}
           enable-cache: true

{babeldoc-0.5.2 → babeldoc-0.5.3}/.gitignore

@@ -44,4 +44,5 @@ uv.lock
 # Claude Code memory file
 CLAUDE.md
 /.claude
-babeldoc/format/playground
+babeldoc/format/playground
+temp.jpg

{babeldoc-0.5.2 → babeldoc-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: BabelDOC
-Version: 0.5.2
+Version: 0.5.3
 Summary: Yet Another Document Translator
 Project-URL: Homepage, https://github.com/funstory-ai/BabelDOC
 Project-URL: Issues, https://github.com/funstory-ai/BabelDOC/issues

babeldoc-0.5.3/babeldoc/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.5.3"

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/const.py

@@ -3,7 +3,7 @@ import shutil
 import subprocess
 from pathlib import Path
 
-__version__ = "0.5.2"
+__version__ = "0.5.3"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/format/pdf/babelpdf/base14.py

@@ -2482,9 +2482,18 @@ ZapfDingbats = [
     (0, 0, 0, 0),
 ]
 
+base14_alias = {
+    "Times New Roman": "Times-Roman",
+    "Times New Roman,Bold": "Times-Bold",
+    "Times New Roman,Italic": "Times-Italic",
+}
+
 
 def get_base14_bbox(family):
     bbox = []
+    if family in base14_alias:
+        family = base14_alias[family]
+
     if family in base14_bbox:
         base = base14_bbox[family]
         for name in win_ansi:

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/format/pdf/document_il/frontend/il_creater.py

@@ -190,6 +190,15 @@ def parse_font_file(doc, idx, encoding, differences):
             if charmap.encoding_name == "FT_ENCODING_ADOBE_CUSTOM":
                 face.select_charmap(charmap.encoding)
                 break
+    elif enc_name == "MacRomanEncoding":
+        for charmap in face.charmaps:
+            face.select_charmap(charmap.encoding)
+            if (
+                charmap.encoding_name == "FT_ENCODING_ADOBE_CUSTOM"
+                or charmap.encoding_name == "FT_ENCODING_APPLE_ROMAN"
+            ):
+                face.select_charmap(charmap.encoding)
+                break
     for i, x in enumerate(enc_vector):
         if x in glyph_name_set:
             v = get_name_cbox(face, x.encode("U8"))

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/format/pdf/document_il/midend/automatic_term_extractor.py

@@ -14,6 +14,12 @@ from babeldoc.format.pdf.document_il import (
 from babeldoc.format.pdf.document_il import PdfParagraph  # Renamed to avoid conflict
 from babeldoc.format.pdf.document_il.midend.il_translator import Page
 from babeldoc.format.pdf.document_il.utils.paragraph_helper import is_cid_paragraph
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_placeholder_only_paragraph,
+)
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_pure_numeric_paragraph,
+)
 from babeldoc.utils.priority_thread_pool_executor import PriorityThreadPoolExecutor
 
 if TYPE_CHECKING:
@@ -194,6 +200,12 @@ class AutomaticTermExtractor:
             if is_cid_paragraph(paragraph):
                 pbar.advance(1)
                 continue
+            if is_pure_numeric_paragraph(paragraph):
+                pbar.advance(1)
+                continue
+            if is_placeholder_only_paragraph(paragraph):
+                pbar.advance(1)
+                continue
             # if len(paragraph.unicode) < self.translation_config.min_text_length:
             #     pbar.advance(1)
             #     continue

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/format/pdf/document_il/midend/il_translator.py

@@ -28,6 +28,12 @@ from babeldoc.format.pdf.document_il.utils.layout_helper import (
 from babeldoc.format.pdf.document_il.utils.layout_helper import (
     is_same_style_except_size,
 )
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_placeholder_only_paragraph,
+)
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_pure_numeric_paragraph,
+)
 from babeldoc.format.pdf.translation_config import TranslationConfig
 from babeldoc.translator.translator import BaseTranslator
 from babeldoc.utils.priority_thread_pool_executor import PriorityThreadPoolExecutor
@@ -436,6 +442,14 @@ class ILTranslator:
     ):
         if not paragraph.pdf_paragraph_composition:
             return
+
+        # Skip pure numeric paragraphs
+        if is_pure_numeric_paragraph(paragraph):
+            return None
+
+        # Skip paragraphs with only placeholders
+        if is_placeholder_only_paragraph(paragraph):
+            return None
         if len(paragraph.pdf_paragraph_composition) == 1:
             # 如果整个段落只有一个组成部分，那么直接返回，不需要套占位符等
             composition = paragraph.pdf_paragraph_composition[0]

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/format/pdf/document_il/midend/il_translator_llm_only.py

@@ -20,6 +20,12 @@ from babeldoc.format.pdf.document_il.midend.il_translator import ILTranslator
 from babeldoc.format.pdf.document_il.midend.il_translator import PageTranslateTracker
 from babeldoc.format.pdf.document_il.utils.fontmap import FontMapper
 from babeldoc.format.pdf.document_il.utils.paragraph_helper import is_cid_paragraph
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_placeholder_only_paragraph,
+)
+from babeldoc.format.pdf.document_il.utils.paragraph_helper import (
+    is_pure_numeric_paragraph,
+)
 from babeldoc.format.pdf.translation_config import TranslationConfig
 from babeldoc.translator.translator import BaseTranslator
 from babeldoc.utils.priority_thread_pool_executor import PriorityThreadPoolExecutor
@@ -482,6 +488,16 @@ class ILTranslatorLLMOnly:
                     pbar.advance(1)
                 continue
 
+            if is_pure_numeric_paragraph(paragraph):
+                if pbar:
+                    pbar.advance(1)
+                continue
+
+            if is_placeholder_only_paragraph(paragraph):
+                if pbar:
+                    pbar.advance(1)
+                continue
+
             # self.translate_paragraph(paragraph, pbar,tracker.new_paragraph(), page_font_map, page_xobj_font_map)
             total_token_count += self.calc_token_count(paragraph.unicode)
             paragraphs.append(paragraph)

babeldoc-0.5.3/babeldoc/format/pdf/document_il/utils/paragraph_helper.py

@@ -0,0 +1,94 @@
+import logging
+import re
+
+from babeldoc.format.pdf.document_il import il_version_1
+
+logger = logging.getLogger(__name__)
+
+
+def is_cid_paragraph(paragraph: il_version_1.PdfParagraph):
+    chars: list[il_version_1.PdfCharacter] = []
+    for composition in paragraph.pdf_paragraph_composition:
+        if composition.pdf_line:
+            chars.extend(composition.pdf_line.pdf_character)
+        elif composition.pdf_same_style_characters:
+            chars.extend(composition.pdf_same_style_characters.pdf_character)
+        elif composition.pdf_same_style_unicode_characters:
+            continue
+        #     chars.extend(composition.pdf_same_style_unicode_characters.unicode)
+        elif composition.pdf_formula:
+            chars.extend(composition.pdf_formula.pdf_character)
+        elif composition.pdf_character:
+            chars.append(composition.pdf_character)
+        else:
+            logger.error(
+                f"Unknown composition type. "
+                f"Composition: {composition}. "
+                f"Paragraph: {paragraph}. ",
+            )
+            continue
+
+    cid_count = 0
+    for char in chars:
+        if re.match(r"^\(cid:\d+\)$", char.char_unicode):
+            cid_count += 1
+
+    return cid_count > len(chars) * 0.8
+
+
+NUMERIC_PATTERN = re.compile(r"^-?\d+(\.\d+)?$")
+
+
+def is_pure_numeric_paragraph(paragraph) -> bool:
+    """只检查段落是否为纯数字（支持整数、小数、负数）"""
+
+    if not paragraph or not getattr(paragraph, "unicode", None):
+        return False
+
+    text = paragraph.unicode.strip()
+    if not text:
+        return False
+
+    return bool(NUMERIC_PATTERN.match(text))
+
+
+def is_placeholder_only_paragraph(paragraph: il_version_1.PdfParagraph) -> bool:
+    """Check if a paragraph contains only placeholders and whitespace.
+
+    Args:
+        paragraph: PDF paragraph to check
+
+    Returns:
+        True if the paragraph contains only placeholders (formula or style tags)
+        and whitespace, False otherwise
+    """
+    if not paragraph or not paragraph.unicode:
+        return False
+
+    for composition in paragraph.pdf_paragraph_composition:
+        if composition.pdf_formula:
+            # Formula composition is allowed
+            continue
+        elif composition.pdf_character:
+            # Check if single character is whitespace
+            if not composition.pdf_character.char_unicode.isspace():
+                return False
+        elif composition.pdf_line:
+            # Check if all characters in the line are whitespace
+            for char in composition.pdf_line.pdf_character:
+                if not char.char_unicode.isspace():
+                    return False
+        elif composition.pdf_same_style_characters:
+            # Check if all characters in the group are whitespace
+            for char in composition.pdf_same_style_characters.pdf_character:
+                if not char.char_unicode.isspace():
+                    return False
+        elif composition.pdf_same_style_unicode_characters:
+            # Check if the unicode content is only whitespace
+            if not composition.pdf_same_style_unicode_characters.unicode.isspace():
+                return False
+        else:
+            # Unknown composition type, conservatively return False
+            return False
+
+    return True

{babeldoc-0.5.2 → babeldoc-0.5.3}/babeldoc/main.py

@@ -22,7 +22,7 @@ from babeldoc.translator.translator import OpenAITranslator
 from babeldoc.translator.translator import set_translate_rate_limiter
 
 logger = logging.getLogger(__name__)
-__version__ = "0.5.2"
+__version__ = "0.5.3"
 
 
 def create_parser():

{babeldoc-0.5.2 → babeldoc-0.5.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.5.2"
+version = "0.5.3"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -162,7 +162,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.5.2"
+current_version = "0.5.3"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]

babeldoc-0.5.2/babeldoc/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.5.2"

babeldoc-0.5.2/babeldoc/format/pdf/document_il/utils/paragraph_helper.py

@@ -1,36 +0,0 @@
-import logging
-import re
-
-from babeldoc.format.pdf.document_il import il_version_1
-
-logger = logging.getLogger(__name__)
-
-
-def is_cid_paragraph(paragraph: il_version_1.PdfParagraph):
-    chars: list[il_version_1.PdfCharacter] = []
-    for composition in paragraph.pdf_paragraph_composition:
-        if composition.pdf_line:
-            chars.extend(composition.pdf_line.pdf_character)
-        elif composition.pdf_same_style_characters:
-            chars.extend(composition.pdf_same_style_characters.pdf_character)
-        elif composition.pdf_same_style_unicode_characters:
-            continue
-        #     chars.extend(composition.pdf_same_style_unicode_characters.unicode)
-        elif composition.pdf_formula:
-            chars.extend(composition.pdf_formula.pdf_character)
-        elif composition.pdf_character:
-            chars.append(composition.pdf_character)
-        else:
-            logger.error(
-                f"Unknown composition type. "
-                f"Composition: {composition}. "
-                f"Paragraph: {paragraph}. ",
-            )
-            continue
-
-    cid_count = 0
-    for char in chars:
-        if re.match(r"^\(cid:\d+\)$", char.char_unicode):
-            cid_count += 1
-
-    return cid_count > len(chars) * 0.8