Merge pull request #139 from funstory-ai/feat/skip-large-pages

feat: skip pages that are too large to process
funstory-ai · Mar 8, 2025 · 09c4dbe · 09c4dbe
2 parents d774a6f + e46f386
commit 09c4dbe
Show file tree

Hide file tree

Showing 5 changed files with 15 additions and 5 deletions.
diff --git a/babeldoc/__init__.py b/babeldoc/__init__.py
@@ -1 +1 @@
-__version__ = "0.1.28"
+__version__ = "0.1.29"
diff --git a/babeldoc/const.py b/babeldoc/const.py
@@ -2,7 +2,7 @@
 import subprocess
 from pathlib import Path
 
-__version__ = "0.1.28"
+__version__ = "0.1.29"
 
 CACHE_FOLDER = Path.home() / ".cache" / "babeldoc"
 

diff --git a/babeldoc/high_level.py b/babeldoc/high_level.py
@@ -138,8 +138,18 @@ def start_parse_il(
         if pages and (pageno not in pages):
             continue
         page.pageno = pageno
+
         if not translation_config.should_translate_page(pageno + 1):
             continue
+
+        height, width = (
+            page.cropbox[3] - page.cropbox[1],
+            page.cropbox[2] - page.cropbox[0],
+        )
+        if height > 1200 or width > 2000:
+            logger.warning(f"page {pageno + 1} is too large, skip")
+            continue
+
         translation_config.raise_if_cancelled()
         # The current program no longer relies on
         # the following layout recognition results,

diff --git a/babeldoc/main.py b/babeldoc/main.py
@@ -25,7 +25,7 @@
 from babeldoc.translation_config import WatermarkOutputMode
 
 logger = logging.getLogger(__name__)
-__version__ = "0.1.28"
+__version__ = "0.1.29"
 
 
 def create_parser():

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "BabelDOC"
-version = "0.1.28"
+version = "0.1.29"
 description = "Yet Another Document Translator"
 license = "AGPL-3.0"
 readme = "README.md"
@@ -133,7 +133,7 @@ pythonpath = [".", "src"]
 testpaths = ["tests"]
 
 [bumpver]
-current_version = "0.1.28"
+current_version = "0.1.29"
 version_pattern = "MAJOR.MINOR.PATCH[.PYTAGNUM]"
 
 [bumpver.file_patterns]