Merge pull request #2264 from myhloli/dev

refactor(office_to_pdf): simplify font checking and add logging

docker/ascend_npu/Dockerfile

@@ -36,7 +36,7 @@ RUN /bin/bash -c "wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/m
     source /opt/mineru_venv/bin/activate && \
     pip3 install --upgrade pip -i https://mirrors.aliyun.com/pypi/simple && \
     pip3 install torch==2.3.1 torchvision==0.18.1 -i https://mirrors.aliyun.com/pypi/simple && \
-    pip3 install -U magic-pdf[full] -i https://mirrors.aliyun.com/pypi/simple && \
+    pip3 install -U magic-pdf[full] 'numpy<2' decorator attrs absl-py cloudpickle ml-dtypes tornado einops -i https://mirrors.aliyun.com/pypi/simple && \
     wget https://gitee.com/ascend/pytorch/releases/download/v6.0.rc2-pytorch2.3.1/torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl && \
     pip3 install torch_npu-2.3.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl"
 

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "1.3.3"
+__version__ = "1.3.4"

magic_pdf/utils/office_to_pdf.py

@@ -4,6 +4,8 @@ import platform
 from pathlib import Path
 import shutil
 
+from loguru import logger
+
 
 class ConvertToPdfError(Exception):
     def __init__(self, msg):
@@ -11,35 +13,24 @@ class ConvertToPdfError(Exception):
         super().__init__(self.msg)
 
 
-# Chinese font list
-REQUIRED_CHS_FONTS = ['SimSun', 'Microsoft YaHei', 'Noto Sans CJK SC']
-
-
 def check_fonts_installed():
     """Check if required Chinese fonts are installed."""
     system_type = platform.system()
 
-    if system_type == 'Windows':
-        # Windows: check fonts via registry or system font folder
-        font_dir = Path("C:/Windows/Fonts")
-        installed_fonts = [f.name for f in font_dir.glob("*.ttf")]
-        if any(font for font in REQUIRED_CHS_FONTS if any(font in f for f in installed_fonts)):
-            return True
-        raise EnvironmentError(
-            f"Missing Chinese font. Please install at least one of: {', '.join(REQUIRED_CHS_FONTS)}"
-        )
+    if system_type in ['Windows', 'Darwin']:
+        pass
     else:
-        # Linux/macOS: use fc-list
+        # Linux: use fc-list
         try:
             output = subprocess.check_output(['fc-list', ':lang=zh'], encoding='utf-8')
-            for font in REQUIRED_CHS_FONTS:
-                if font in output:
-                    return True
-            raise EnvironmentError(
-                f"Missing Chinese font. Please install at least one of: {', '.join(REQUIRED_CHS_FONTS)}"
-            )
-        except Exception as e:
-            raise EnvironmentError(f"Font detection failed. Please install 'fontconfig' and fonts: {str(e)}")
+            if output.strip():  # 只要有任何输出（非空）
+                return True
+            else:
+                logger.warning(
+                    f"No Chinese fonts were detected, the converted document may not display Chinese content properly."
+                )
+        except Exception:
+            pass
 
 
 def get_soffice_command():

tests/unittest/test_table/test_rapidtable.py

@@ -1,4 +1,5 @@
 import unittest
+import os
 from PIL import Image
 from lxml import etree
 
@@ -8,7 +9,7 @@ from magic_pdf.model.sub_modules.table.rapidtable.rapid_table import RapidTableM
 
 class TestppTableModel(unittest.TestCase):
     def test_image2html(self):
-        img = Image.open("assets/table.jpg")
+        img = Image.open(os.path.join(os.path.dirname(__file__), "assets/table.jpg"))
         atom_model_manager = AtomModelSingleton()
         ocr_engine = atom_model_manager.get_atom_model(
             atom_model_name='ocr',