mineru 2.5.3__py3-none-any.whl → 2.5.4__py3-none-any.whl

mineru/cli/common.py

@@ -26,7 +26,7 @@ def read_fn(path):
         path = Path(path)
     with open(str(path), "rb") as input_file:
         file_bytes = input_file.read()
-        file_suffix = guess_suffix_by_bytes(file_bytes)
+        file_suffix = guess_suffix_by_bytes(file_bytes, path)
         if file_suffix in image_suffixes:
             return images_bytes_to_pdf_bytes(file_bytes)
         elif file_suffix in pdf_suffixes:

mineru/cli/gradio_app.py

@@ -86,10 +86,14 @@ def replace_image_with_base64(markdown_text, image_dir_path):
     # 替换图片链接
     def replace(match):
         relative_path = match.group(1)
-        full_path = os.path.join(image_dir_path, relative_path)
-        base64_image = image_to_base64(full_path)
-        return f'![{relative_path}](data:image/jpeg;base64,{base64_image})'
-
+        # 只处理以.jpg结尾的图片
+        if relative_path.endswith('.jpg'):
+            full_path = os.path.join(image_dir_path, relative_path)
+            base64_image = image_to_base64(full_path)
+            return f'![{relative_path}](data:image/jpeg;base64,{base64_image})'
+        else:
+            # 其他格式的图片保持原样
+            return match.group(0)
     # 应用替换
     return re.sub(pattern, replace, markdown_text)
 

mineru/utils/guess_suffix_or_lang.py

@@ -1,3 +1,5 @@
+from pathlib import Path
+
 from magika import Magika
 
 
@@ -10,11 +12,17 @@ def guess_language_by_text(code):
     return lang if lang != "unknown" else DEFAULT_LANG
 
 
-def guess_suffix_by_bytes(file_bytes) -> str:
+def guess_suffix_by_bytes(file_bytes, file_path=None) -> str:
     suffix = magika.identify_bytes(file_bytes).prediction.output.label
+    if file_path and suffix in ["ai"] and Path(file_path).suffix.lower() in [".pdf"]:
+        suffix = "pdf"
     return suffix
 
 
 def guess_suffix_by_path(file_path) -> str:
+    if not isinstance(file_path, Path):
+        file_path = Path(file_path)
     suffix = magika.identify_path(file_path).prediction.output.label
+    if suffix in ["ai"] and file_path.suffix.lower() in [".pdf"]:
+        suffix = "pdf"
     return suffix

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.5.3"
+__version__ = "2.5.4"

{mineru-2.5.3.dist-info → mineru-2.5.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mineru
-Version: 2.5.3
+Version: 2.5.4
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: homepage, https://mineru.net/
@@ -37,7 +37,7 @@ Requires-Dist: scikit-image<1.0.0,>=0.25.0
 Requires-Dist: openai<2,>=1.70.0
 Requires-Dist: beautifulsoup4<5,>=4.13.5
 Requires-Dist: magika<0.7.0,>=0.6.2
-Requires-Dist: mineru-vl-utils<1,>=0.1.8
+Requires-Dist: mineru-vl-utils<1,>=0.1.11
 Provides-Extra: test
 Requires-Dist: mineru[core]; extra == "test"
 Requires-Dist: pytest; extra == "test"
@@ -127,6 +127,9 @@ Dynamic: license-file
 
 # Changelog
 
+- 2025/09/26 2.5.4 released  
+  - Fixed an issue where some `PDF` files were mistakenly identified as `AI` files, causing parsing failures
+
 - 2025/09/20 2.5.3 Released
   - Dependency version range adjustment to enable Turing and earlier architecture GPUs to use vLLM acceleration for MinerU2.5 model inference.
   - `pipeline` backend compatibility fixes for torch 2.8.0.

{mineru-2.5.3.dist-info → mineru-2.5.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
 mineru/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
-mineru/version.py,sha256=9As6EseYF3Vi8VWUZnZuuTi-kW5fYIv8u6cHK0RidGo,22
+mineru/version.py,sha256=u7qJtvbcGbgT3ue2tQMbSOeGJqqkDTDm-_7HUe49PZA,22
 mineru/backend/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/pipeline/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/pipeline/batch_analyze.py,sha256=dOnktvOMjfg84w1H34YlJg6N9_x6Yfvf14NIpOQcZqQ,22221
@@ -18,9 +18,9 @@ mineru/backend/vlm/vlm_magic_model.py,sha256=o1WKwgArV0f4lp7ufmSq9zRZaM5bnfOdx1A
 mineru/backend/vlm/vlm_middle_json_mkcontent.py,sha256=Ie95XpwTgi7EmidcwE_scvXMRQjE2xASU_Rm_F8EP-I,13377
 mineru/cli/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/cli/client.py,sha256=uo7db9Wqj1Mc11MYuaM-bi54BfKKU3SFB9Urc8md5X4,6641
-mineru/cli/common.py,sha256=yJPdrwSYVidl2hTJ2Hn2YhnfH97GJ-QZi20dGFz7h5c,14025
+mineru/cli/common.py,sha256=HNJA6wVue1k8uZJlkEb9bTJfmLRc2CjemPB2o7ZosCk,14031
 mineru/cli/fast_api.py,sha256=-GDT4gOCjKQrRjrx9WVJw-D-EC7Adv-F2rAiSWdl2CA,11328
-mineru/cli/gradio_app.py,sha256=m1ppNVVOS-gdMpQPWOgHQCBQkLZ4B6gKCZuUyhfsR1g,13482
+mineru/cli/gradio_app.py,sha256=z59i5cWKLQ6TC7EwNKWEcrMHkz3Lsf1LYJTHXVpJiVo,13674
 mineru/cli/models_download.py,sha256=TCKtzTRJ-ShaqZnRQID40QsILqp2b3basU142FMTmns,4775
 mineru/cli/vlm_vllm_server.py,sha256=fQJyD-gIPQ41hR_6aIaDJczl66N310t0CiZEBAfX5mc,90
 mineru/data/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
@@ -157,7 +157,7 @@ mineru/utils/cut_image.py,sha256=g3m4nfcJNWlxi-P0kpXTtlmspXkMcLCfGwmYuQ-Z2hE,751
 mineru/utils/draw_bbox.py,sha256=FkgppjUzRhN-uxvChdkhHXcDavJEaApMD6qC6qoRwfQ,20292
 mineru/utils/enum_class.py,sha256=34lVsjeAYLha7Q-1qxY9seJFdK6fjuEphXfYFibghEY,2442
 mineru/utils/format_utils.py,sha256=2s89vHcSISjuolk8Hvg3K-5-rRbiT3Us7eFLzUKrNKs,10233
-mineru/utils/guess_suffix_or_lang.py,sha256=q7CbPpiaDFA2AmOS66oJ_HwzamEftNSsmOn5mbrtO9I,540
+mineru/utils/guess_suffix_or_lang.py,sha256=nznyQpUn1BSA8JNw9HuG3pVV-xtVAtrtcGuHZ-VXt9M,856
 mineru/utils/hash_utils.py,sha256=UPS_8NRBmVumdyOv16Lmv6Ly2xK8OVDJEe5gG6gKIFk,857
 mineru/utils/language.py,sha256=7RT3mxSa7jdpoC5ySd7ZddHA7TO7UsnmDOWiYZAxuyg,1433
 mineru/utils/llm_aided.py,sha256=0W6AlBpLfflON1ob6p72IgwdCJKFXhYpDWlrhrToR5s,4892
@@ -173,9 +173,9 @@ mineru/utils/run_async.py,sha256=rPeP4BCZerR8VByRDhiYzfZiahLVqoZEBVAS54dAjNg,128
 mineru/utils/span_block_fix.py,sha256=0eVQjJCrT03woRt9hoh6Uu42Tp1dacfGTv2x3B9qq94,8797
 mineru/utils/span_pre_proc.py,sha256=h41q2uQajI0xQbc_30hqaju1dv3oVYxBAlKgURl8HIc,13692
 mineru/utils/table_merge.py,sha256=zYUpYLrfhBCnbHCYZi6rG8-s38NDnTbiNTObvLdYwJk,11494
-mineru-2.5.3.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-mineru-2.5.3.dist-info/METADATA,sha256=T45OlRf2MarpDXHk36RO4Hx8EN2A15V2UJmmjTd8YCE,64957
-mineru-2.5.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mineru-2.5.3.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
-mineru-2.5.3.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
-mineru-2.5.3.dist-info/RECORD,,
+mineru-2.5.4.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+mineru-2.5.4.dist-info/METADATA,sha256=_D0D86ss-j3hi40UMzMYWBY9kzKNN6G_F8aRSH33fYo,65098
+mineru-2.5.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mineru-2.5.4.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
+mineru-2.5.4.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
+mineru-2.5.4.dist-info/RECORD,,