mineru 2.7.0__py3-none-any.whl → 2.7.1__py3-none-any.whl

mineru/cli/common.py

@@ -17,8 +17,6 @@ from mineru.utils.pdf_image_tools import images_bytes_to_pdf_bytes
 from mineru.backend.vlm.vlm_middle_json_mkcontent import union_make as vlm_union_make
 from mineru.backend.vlm.vlm_analyze import doc_analyze as vlm_doc_analyze
 from mineru.backend.vlm.vlm_analyze import aio_doc_analyze as aio_vlm_doc_analyze
-from mineru.backend.hybrid.hybrid_analyze import doc_analyze as hybrid_doc_analyze
-from mineru.backend.hybrid.hybrid_analyze import aio_doc_analyze as aio_hybrid_doc_analyze
 from mineru.utils.pdf_page_id import get_end_page_id
 
 if os.getenv("MINERU_LMDEPLOY_DEVICE", "") == "maca":
@@ -326,6 +324,7 @@ def _process_hybrid(
         server_url=None,
         **kwargs,
 ):
+    from mineru.backend.hybrid.hybrid_analyze import doc_analyze as hybrid_doc_analyze
     """同步处理hybrid后端逻辑"""
     if not backend.endswith("client"):
         server_url = None
@@ -378,8 +377,8 @@ async def _async_process_hybrid(
         server_url=None,
         **kwargs,
 ):
+    from mineru.backend.hybrid.hybrid_analyze import aio_doc_analyze as aio_hybrid_doc_analyze
     """异步处理hybrid后端逻辑"""
-
     if not backend.endswith("client"):
         server_url = None
 

mineru/utils/pdf_image_tools.py

@@ -5,7 +5,7 @@ from io import BytesIO
 import numpy as np
 import pypdfium2 as pdfium
 from loguru import logger
-from PIL import Image
+from PIL import Image, ImageOps
 
 from mineru.data.data_reader_writer import FileBasedDataWriter
 from mineru.utils.check_sys_env import is_windows_environment
@@ -41,19 +41,23 @@ def pdf_page_to_image(page: pdfium.PdfPage, dpi=200, image_type=ImageType.PIL) -
     return image_dict
 
 
-def _load_images_from_pdf_worker(pdf_bytes, dpi, start_page_id, end_page_id, image_type):
+def _load_images_from_pdf_worker(
+    pdf_bytes, dpi, start_page_id, end_page_id, image_type
+):
     """用于进程池的包装函数"""
-    return load_images_from_pdf_core(pdf_bytes, dpi, start_page_id, end_page_id, image_type)
+    return load_images_from_pdf_core(
+        pdf_bytes, dpi, start_page_id, end_page_id, image_type
+    )
 
 
 def load_images_from_pdf(
-        pdf_bytes: bytes,
-        dpi=200,
-        start_page_id=0,
-        end_page_id=None,
-        image_type=ImageType.PIL,
-        timeout=None,
-        threads=4,
+    pdf_bytes: bytes,
+    dpi=200,
+    start_page_id=0,
+    end_page_id=None,
+    image_type=ImageType.PIL,
+    timeout=None,
+    threads=4,
 ):
     """带超时控制的 PDF 转图片函数,支持多进程加速
 
@@ -77,7 +81,7 @@ def load_images_from_pdf(
             dpi,
             start_page_id,
             get_end_page_id(end_page_id, len(pdf_doc)),
-            image_type
+            image_type,
         ), pdf_doc
     else:
         if timeout is None:
@@ -116,7 +120,7 @@ def load_images_from_pdf(
                     dpi,
                     range_start,
                     range_end,
-                    image_type
+                    image_type,
                 )
                 futures.append((range_start, future))
 
@@ -163,7 +167,14 @@ def load_images_from_pdf_core(
     return images_list
 
 
-def cut_image(bbox: tuple, page_num: int, page_pil_img, return_path, image_writer: FileBasedDataWriter, scale=2):
+def cut_image(
+    bbox: tuple,
+    page_num: int,
+    page_pil_img,
+    return_path,
+    image_writer: FileBasedDataWriter,
+    scale=2,
+):
     """从第page_num页的page中，根据bbox进行裁剪出一张jpg图片，返回图片路径 save_path：需要同时支持s3和本地,
     图片存放在save_path下，文件名是:
     {page_num}_{bbox[0]}_{bbox[1]}_{bbox[2]}_{bbox[3]}.jpg , bbox内数字取整。"""
@@ -197,7 +208,6 @@ def get_crop_img(bbox: tuple, pil_img, scale=2):
 
 
 def get_crop_np_img(bbox: tuple, input_img, scale=2):
-
     if isinstance(input_img, Image.Image):
         np_img = np.asarray(input_img)
     elif isinstance(input_img, np.ndarray):
@@ -212,17 +222,27 @@ def get_crop_np_img(bbox: tuple, input_img, scale=2):
         int(bbox[3] * scale),
     )
 
-    return np_img[scale_bbox[1]:scale_bbox[3], scale_bbox[0]:scale_bbox[2]]
+    return np_img[scale_bbox[1] : scale_bbox[3], scale_bbox[0] : scale_bbox[2]]
+
 
 def images_bytes_to_pdf_bytes(image_bytes):
     # 内存缓冲区
     pdf_buffer = BytesIO()
 
     # 载入并转换所有图像为 RGB 模式
-    image = Image.open(BytesIO(image_bytes)).convert("RGB")
+    image = Image.open(BytesIO(image_bytes))
+    # 根据 EXIF 信息自动转正（处理手机拍摄的带 Orientation 标记的图片）
+    image = ImageOps.exif_transpose(image) or image
+    # 只在必要时转换
+    if image.mode != "RGB":
+        image = image.convert("RGB")
 
     # 第一张图保存为 PDF，其余追加
-    image.save(pdf_buffer, format="PDF", save_all=True)
+    image.save(
+        pdf_buffer,
+        format="PDF",
+        # save_all=True
+    )
 
     # 获取 PDF bytes 并重置指针（可选）
     pdf_bytes = pdf_buffer.getvalue()

mineru/utils/table_merge.py

@@ -9,7 +9,14 @@ from mineru.utils.char_utils import full_to_half
 from mineru.utils.enum_class import BlockType, SplitFlag
 
 
-CONTINUATION_MARKERS = ["(续)", "(续表)", "(continued)", "(cont.)"]
+CONTINUATION_MARKERS = [
+    "(续)",
+    "(续表)",
+    "(续上表)",
+    "(continued)",
+    "(cont.)",
+    "(cont’d)",
+]
 
 
 def calculate_table_total_columns(soup):

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.7.0"
+__version__ = "2.7.1"

{mineru-2.7.0.dist-info → mineru-2.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mineru
-Version: 2.7.0
+Version: 2.7.1
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: homepage, https://mineru.net/
@@ -19,7 +19,7 @@ Requires-Dist: boto3>=1.28.43
 Requires-Dist: click>=8.1.7
 Requires-Dist: loguru>=0.7.2
 Requires-Dist: numpy>=1.21.6
-Requires-Dist: pdfminer.six==20250506
+Requires-Dist: pdfminer.six>=20251230
 Requires-Dist: tqdm>=4.67.1
 Requires-Dist: requests
 Requires-Dist: httpx
@@ -81,9 +81,9 @@ Requires-Dist: mineru[vlm]; extra == "core"
 Requires-Dist: mineru[pipeline]; extra == "core"
 Requires-Dist: mineru[api]; extra == "core"
 Requires-Dist: mineru[gradio]; extra == "core"
-Requires-Dist: mineru[mlx]; sys_platform == "darwin" and extra == "core"
 Provides-Extra: all
 Requires-Dist: mineru[core]; extra == "all"
+Requires-Dist: mineru[mlx]; sys_platform == "darwin" and extra == "all"
 Requires-Dist: mineru[vllm]; sys_platform == "linux" and extra == "all"
 Requires-Dist: mineru[lmdeploy]; sys_platform == "windows" and extra == "all"
 Dynamic: license-file
@@ -135,6 +135,11 @@ Dynamic: license-file
 
 # Changelog
 
+- 2026/01/06 2.7.1 Release
+  - fix bug: #4300
+  - Updated pdfminer.six dependency version to resolve [CVE-2025-64512](https://github.com/advisories/GHSA-wf5f-4jwr-ppcp)
+  - Support automatic correction of input image exif orientation to improve OCR recognition accuracy  #4283
+
 - 2025/12/30 2.7.0 Release
   - Simplified installation process. No need to separately install `vlm` acceleration engine dependencies. Using `uv pip install mineru[all]` during installation will install all optional backend dependencies.
   - Added new `hybrid` backend, which combines the advantages of `pipeline` and `vlm` backends. Built on vlm, it integrates some capabilities of pipeline, adding extra extensibility on top of high accuracy:

{mineru-2.7.0.dist-info → mineru-2.7.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
 mineru/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
-mineru/version.py,sha256=EtKWW0Hnl5oWglRNH0HZigvcDT2FEs58ek8buJdwW1E,22
+mineru/version.py,sha256=yRpSH6mBb4BJgbFlT7rt8MSjCUW17Ycx0RziLf-lQLA,22
 mineru/backend/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/utils.py,sha256=GLJU3IznDmhE1_qNmkU1UOtsuskIHBezgsEVO6Uar-Y,698
 mineru/backend/hybrid/__init__.py,sha256=IFgr2C8NfSAj8q7JF7QOqMvCiJ6Fc8TIuU3Uh2DaFZU,51
@@ -23,7 +23,7 @@ mineru/backend/vlm/vlm_magic_model.py,sha256=mD-irxboo2DmMu4QF1wnvbti2xdNyBmNflb
 mineru/backend/vlm/vlm_middle_json_mkcontent.py,sha256=w-Szbm4HitR7MY4pinSCZZdXtPSqmtlU9cjNh4IOQyg,29499
 mineru/cli/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/cli/client.py,sha256=mPNfMEShVG-ithmlJQ5nGRIad2gCZgUjBGHN7zAmLhQ,6978
-mineru/cli/common.py,sha256=srzkJeh0dMlaccDlGWaDBIToqXLPFeyYL4JsARCGHTc,20468
+mineru/cli/common.py,sha256=fMPc235DtnupQkh9uFIMHUpxOSvCp5yc3A56sAabAWY,20475
 mineru/cli/fast_api.py,sha256=TGpZqyUE1kg2eXsP76pr0p1yqNOOU9jyjL5Pc0FJwRc,16637
 mineru/cli/gradio_app.py,sha256=2IIWOm2bEHHq5BZMlfmN3yAJw1Nf8SUALTQ95o-bYy0,21863
 mineru/cli/models_download.py,sha256=LNfoIpUlJM7m7qb2SiCxtjMDw4jILBQtZwNP2JoY81U,4815
@@ -177,17 +177,17 @@ mineru/utils/models_download_utils.py,sha256=UfjvwhxO6BkJHa5JSpEVNZ71GoLMPMmJpym
 mineru/utils/ocr_utils.py,sha256=lPIrwNUib5mrzUkponRYHuUCdjV2qvETNLSzOLyflrU,15990
 mineru/utils/os_env_config.py,sha256=ZNtkR4KrJW72CeIoTNzGDL6tMKv_hL8nzvWIssGWbqY,842
 mineru/utils/pdf_classify.py,sha256=6DF5pH_9Uq83fsFtp7n4i-OdYQGzoNOV9L0VBUhgBMQ,8078
-mineru/utils/pdf_image_tools.py,sha256=86_xvsGOEde5QGlKz5uJemjoO1upr6n_K7o3lCdyIjQ,7981
+mineru/utils/pdf_image_tools.py,sha256=L2kHKoFaQo4CGjS1d68JACrlBycx6gyCnnFlbBFRKuw,8273
 mineru/utils/pdf_page_id.py,sha256=em966k12CRW4Rj49RGiLB_8ILwkXPBnWRetApax3eTs,400
 mineru/utils/pdf_reader.py,sha256=WeINm5SyWBUXT0wP9lzIbeHs8P6WUIkN6nVL5X4LzG4,3267
 mineru/utils/pdf_text_tool.py,sha256=KEztjfdqsIHHuiTEAMAL7Lr1OS3R7Ur-uTqGiCRjReQ,1364
 mineru/utils/run_async.py,sha256=rPeP4BCZerR8VByRDhiYzfZiahLVqoZEBVAS54dAjNg,1286
 mineru/utils/span_block_fix.py,sha256=0eVQjJCrT03woRt9hoh6Uu42Tp1dacfGTv2x3B9qq94,8797
 mineru/utils/span_pre_proc.py,sha256=nu6Bh5TWPKFzHuFfbEs0Asr04M4xOL5IONz_8GJHn44,13862
-mineru/utils/table_merge.py,sha256=zPjDwso28bHEaH9mwlQMtPvwAPcdNfwDK-pinXTf7E8,15129
-mineru-2.7.0.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-mineru-2.7.0.dist-info/METADATA,sha256=NoPOfPd9ZWB153FfrhRLnlqBcNShcZP1WEDiCc8U93k,35263
-mineru-2.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mineru-2.7.0.dist-info/entry_points.txt,sha256=JbtrCPhx1T32s7TONUsteKg-24ZwRT1HSiFtW5jypVw,376
-mineru-2.7.0.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
-mineru-2.7.0.dist-info/RECORD,,
+mineru/utils/table_merge.py,sha256=X2vQCCKx8hG9Iipn4UEP8pXHc9jeNmYNYvl5zxaTS2E,15185
+mineru-2.7.1.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+mineru-2.7.1.dist-info/METADATA,sha256=gtaeoZmMvmHA8JDW1QnpszDa0-cTwogQ-5BOPTdikWA,35540
+mineru-2.7.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mineru-2.7.1.dist-info/entry_points.txt,sha256=JbtrCPhx1T32s7TONUsteKg-24ZwRT1HSiFtW5jypVw,376
+mineru-2.7.1.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
+mineru-2.7.1.dist-info/RECORD,,