mineru 2.6.3__py3-none-any.whl → 2.6.4__py3-none-any.whl

mineru/backend/pipeline/pipeline_analyze.py

@@ -99,7 +99,10 @@ def doc_analyze(
         _lang = lang_list[pdf_idx]
 
         # 收集每个数据集中的页面
+        # load_images_start = time.time()
         images_list, pdf_doc = load_images_from_pdf(pdf_bytes, image_type=ImageType.PIL)
+        # load_images_time = round(time.time() - load_images_start, 2)
+        # logger.debug(f"load images cost: {load_images_time}, speed: {round(len(images_list) / load_images_time, 3)} images/s")
         all_image_lists.append(images_list)
         all_pdf_docs.append(pdf_doc)
         for page_idx in range(len(images_list)):

mineru/backend/vlm/vlm_analyze.py

@@ -8,7 +8,7 @@ from .utils import enable_custom_logits_processors, set_default_gpu_memory_utili
 from .model_output_to_middle_json import result_to_middle_json
 from ...data.data_reader_writer import DataWriter
 from mineru.utils.pdf_image_tools import load_images_from_pdf
-from ...utils.check_mac_env import is_mac_os_version_supported
+from ...utils.check_sys_env import is_mac_os_version_supported
 from ...utils.config_reader import get_device
 
 from ...utils.enum_class import ImageType
@@ -177,7 +177,7 @@ async def aio_doc_analyze(
     images_list, pdf_doc = load_images_from_pdf(pdf_bytes, image_type=ImageType.PIL)
     images_pil_list = [image_dict["img_pil"] for image_dict in images_list]
     # load_images_time = round(time.time() - load_images_start, 2)
-    # logger.info(f"load images cost: {load_images_time}, speed: {round(len(images_base64_list)/load_images_time, 3)} images/s")
+    # logger.debug(f"load images cost: {load_images_time}, speed: {round(len(images_pil_list)/load_images_time, 3)} images/s")
 
     # infer_start = time.time()
     results = await predictor.aio_batch_two_step_extract(images=images_pil_list)

mineru/cli/client.py

@@ -4,7 +4,7 @@ import click
 from pathlib import Path
 from loguru import logger
 
-from mineru.utils.check_mac_env import is_mac_os_version_supported
+from mineru.utils.check_sys_env import is_mac_os_version_supported
 from mineru.utils.cli_parser import arg_parse
 from mineru.utils.config_reader import get_device
 from mineru.utils.guess_suffix_or_lang import guess_suffix_by_path

mineru/cli/common.py

@@ -5,8 +5,8 @@ import os
 import copy
 from pathlib import Path
 
-import pypdfium2 as pdfium
 from loguru import logger
+import pypdfium2 as pdfium
 
 from mineru.data.data_reader_writer import FileBasedDataWriter
 from mineru.utils.draw_bbox import draw_layout_bbox, draw_span_bbox, draw_line_sort_bbox
@@ -16,10 +16,12 @@ 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.utils.pdf_page_id import get_end_page_id
 
 pdf_suffixes = ["pdf"]
 image_suffixes = ["png", "jpeg", "jp2", "webp", "gif", "bmp", "jpg", "tiff"]
 
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
 def read_fn(path):
     if not isinstance(path, Path):
@@ -44,18 +46,10 @@ def prepare_env(output_dir, pdf_file_name, parse_method):
 
 
 def convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id=0, end_page_id=None):
+    pdf = pdfium.PdfDocument(pdf_bytes)
+    output_pdf = pdfium.PdfDocument.new()
     try:
-        # 从字节数据加载PDF
-        pdf = pdfium.PdfDocument(pdf_bytes)
-
-        # 确定结束页
-        end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(pdf) - 1
-        if end_page_id > len(pdf) - 1:
-            logger.warning("end_page_id is out of range, use pdf_docs length")
-            end_page_id = len(pdf) - 1
-
-        # 创建一个新的PDF文档
-        output_pdf = pdfium.PdfDocument.new()
+        end_page_id = get_end_page_id(end_page_id, len(pdf))
 
         # 选择要导入的页面索引
         page_indices = list(range(start_page_id, end_page_id + 1))
@@ -69,13 +63,12 @@ def convert_pdf_bytes_to_bytes_by_pypdfium2(pdf_bytes, start_page_id=0, end_page
 
         # 获取字节数据
         output_bytes = output_buffer.getvalue()
-
-        pdf.close()  # 关闭原PDF文档以释放资源
-        output_pdf.close()  # 关闭新PDF文档以释放资源
     except Exception as e:
         logger.warning(f"Error in converting PDF bytes: {e}, Using original PDF bytes.")
         output_bytes = pdf_bytes
 
+    pdf.close()
+    output_pdf.close()
     return output_bytes
 
 

mineru/cli/gradio_app.py

@@ -13,7 +13,7 @@ from gradio_pdf import PDF
 from loguru import logger
 
 from mineru.cli.common import prepare_env, read_fn, aio_do_parse, pdf_suffixes, image_suffixes
-from mineru.utils.check_mac_env import is_mac_os_version_supported
+from mineru.utils.check_sys_env import is_mac_os_version_supported
 from mineru.utils.cli_parser import arg_parse
 from mineru.utils.hash_utils import str_sha256
 

mineru/model/table/rec/slanet_plus/table_structure.py

@@ -16,6 +16,7 @@ from typing import Any, Dict, List, Tuple
 
 import numpy as np
 
+from mineru.utils.os_env_config import get_op_num_threads
 from .table_structure_utils import (
     OrtInferSession,
     TableLabelDecode,
@@ -29,6 +30,9 @@ class TableStructurer:
         self.preprocess_op = TablePreprocess()
         self.batch_preprocess_op = BatchTablePreprocess()
 
+        config["intra_op_num_threads"] = get_op_num_threads("MINERU_INTRA_OP_NUM_THREADS")
+        config["inter_op_num_threads"] = get_op_num_threads("MINERU_INTER_OP_NUM_THREADS")
+
         self.session = OrtInferSession(config)
 
         self.character = self.session.get_metadata()

mineru/model/table/rec/unet_table/table_structure_unet.py

@@ -5,6 +5,8 @@ from typing import Optional, Dict, Any, Tuple
 import cv2
 import numpy as np
 from skimage import measure
+
+from mineru.utils.os_env_config import get_op_num_threads
 from .utils import OrtInferSession, resize_img
 from .utils_table_line_rec import (
     get_table_line,
@@ -28,6 +30,9 @@ class TSRUnet:
         self.inp_height = 1024
         self.inp_width = 1024
 
+        config["intra_op_num_threads"] = get_op_num_threads("MINERU_INTRA_OP_NUM_THREADS")
+        config["inter_op_num_threads"] = get_op_num_threads("MINERU_INTER_OP_NUM_THREADS")
+
         self.session = OrtInferSession(config)
 
     def __call__(

mineru/utils/{check_mac_env.py → check_sys_env.py}

@@ -4,6 +4,10 @@ import platform
 from packaging import version
 
 
+def is_windows_environment() -> bool:
+    return platform.system() == "Windows"
+
+
 # Detect if the current environment is a Mac computer
 def is_mac_environment() -> bool:
     return platform.system() == "Darwin"

mineru/utils/os_env_config.py

@@ -0,0 +1,30 @@
+import os
+
+
+def get_op_num_threads(env_name: str) -> int:
+    env_value = os.getenv(env_name, None)
+    return get_value_from_string(env_value, -1)
+
+
+def get_load_images_timeout() -> int:
+    env_value = os.getenv('MINERU_PDF_RENDER_TIMEOUT', None)
+    return get_value_from_string(env_value, 300)
+
+
+def get_value_from_string(env_value: str, default_value: int) -> int:
+    if env_value is not None:
+        try:
+            num_threads = int(env_value)
+            if num_threads > 0:
+                return num_threads
+        except ValueError:
+            return default_value
+    return default_value
+
+
+if __name__ == '__main__':
+    print(get_value_from_string('1', -1))
+    print(get_value_from_string('0', -1))
+    print(get_value_from_string('-1', -1))
+    print(get_value_from_string('abc', -1))
+    print(get_load_images_timeout())

mineru/utils/pdf_image_tools.py

@@ -1,4 +1,5 @@
 # Copyright (c) Opendatalab. All rights reserved.
+import os
 from io import BytesIO
 
 import numpy as np
@@ -7,9 +8,14 @@ from loguru import logger
 from PIL import Image
 
 from mineru.data.data_reader_writer import FileBasedDataWriter
+from mineru.utils.check_sys_env import is_windows_environment
+from mineru.utils.os_env_config import get_load_images_timeout
 from mineru.utils.pdf_reader import image_to_b64str, image_to_bytes, page_to_image
-from .enum_class import ImageType
-from .hash_utils import str_sha256
+from mineru.utils.enum_class import ImageType
+from mineru.utils.hash_utils import str_sha256
+from mineru.utils.pdf_page_id import get_end_page_id
+
+from concurrent.futures import ProcessPoolExecutor, TimeoutError as FuturesTimeoutError
 
 
 def pdf_page_to_image(page: pdfium.PdfPage, dpi=200, image_type=ImageType.PIL) -> dict:
@@ -35,7 +41,106 @@ 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):
+    """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)
+
+
 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,
+):
+    """带超时控制的 PDF 转图片函数,支持多进程加速
+
+    Args:
+        pdf_bytes (bytes): PDF 文件的 bytes
+        dpi (int, optional): reset the dpi of dpi. Defaults to 200.
+        start_page_id (int, optional): 起始页码. Defaults to 0.
+        end_page_id (int | None, optional): 结束页码. Defaults to None.
+        image_type (ImageType, optional): 图片类型. Defaults to ImageType.PIL.
+        timeout (int | None, optional): 超时时间(秒)。如果为 None，则从环境变量 MINERU_PDF_LOAD_IMAGES_TIMEOUT 读取，若未设置则默认为 300 秒。
+        threads (int): 进程数,默认 4
+
+    Raises:
+        TimeoutError: 当转换超时时抛出
+    """
+    pdf_doc = pdfium.PdfDocument(pdf_bytes)
+    if is_windows_environment():
+        # Windows 环境下不使用多进程
+        return load_images_from_pdf_core(
+            pdf_bytes,
+            dpi,
+            start_page_id,
+            get_end_page_id(end_page_id, len(pdf_doc)),
+            image_type
+        ), pdf_doc
+    else:
+        if timeout is None:
+            timeout = get_load_images_timeout()
+        end_page_id = get_end_page_id(end_page_id, len(pdf_doc))
+
+        # 计算总页数
+        total_pages = end_page_id - start_page_id + 1
+
+        # 实际使用的进程数不超过总页数
+        actual_threads = min(os.cpu_count() or 1, threads, total_pages)
+
+        # 根据实际进程数分组页面范围
+        pages_per_thread = max(1, total_pages // actual_threads)
+        page_ranges = []
+
+        for i in range(actual_threads):
+            range_start = start_page_id + i * pages_per_thread
+            if i == actual_threads - 1:
+                # 最后一个进程处理剩余所有页面
+                range_end = end_page_id
+            else:
+                range_end = start_page_id + (i + 1) * pages_per_thread - 1
+
+            page_ranges.append((range_start, range_end))
+
+        # logger.debug(f"PDF to images using {actual_threads} processes, page ranges: {page_ranges}")
+
+        with ProcessPoolExecutor(max_workers=actual_threads) as executor:
+            # 提交所有任务
+            futures = []
+            for range_start, range_end in page_ranges:
+                future = executor.submit(
+                    _load_images_from_pdf_worker,
+                    pdf_bytes,
+                    dpi,
+                    range_start,
+                    range_end,
+                    image_type
+                )
+                futures.append((range_start, future))
+
+            try:
+                # 收集结果并按页码排序
+                all_results = []
+                for range_start, future in futures:
+                    images_list = future.result(timeout=timeout)
+                    all_results.append((range_start, images_list))
+
+                # 按起始页码排序并合并结果
+                all_results.sort(key=lambda x: x[0])
+                images_list = []
+                for _, imgs in all_results:
+                    images_list.extend(imgs)
+
+                return images_list, pdf_doc
+            except FuturesTimeoutError:
+                pdf_doc.close()
+                executor.shutdown(wait=False, cancel_futures=True)
+                raise TimeoutError(f"PDF to images conversion timeout after {timeout}s")
+
+
+def load_images_from_pdf_core(
     pdf_bytes: bytes,
     dpi=200,
     start_page_id=0,
@@ -45,18 +150,17 @@ def load_images_from_pdf(
     images_list = []
     pdf_doc = pdfium.PdfDocument(pdf_bytes)
     pdf_page_num = len(pdf_doc)
-    end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else pdf_page_num - 1
-    if end_page_id > pdf_page_num - 1:
-        logger.warning("end_page_id is out of range, use images length")
-        end_page_id = pdf_page_num - 1
-
-    for index in range(0, pdf_page_num):
-        if start_page_id <= index <= end_page_id:
-            page = pdf_doc[index]
-            image_dict = pdf_page_to_image(page, dpi=dpi, image_type=image_type)
-            images_list.append(image_dict)
-
-    return images_list, pdf_doc
+    end_page_id = get_end_page_id(end_page_id, pdf_page_num)
+
+    for index in range(start_page_id, end_page_id + 1):
+        # logger.debug(f"Converting page {index}/{pdf_page_num} to image")
+        page = pdf_doc[index]
+        image_dict = pdf_page_to_image(page, dpi=dpi, image_type=image_type)
+        images_list.append(image_dict)
+
+    pdf_doc.close()
+
+    return images_list
 
 
 def cut_image(bbox: tuple, page_num: int, page_pil_img, return_path, image_writer: FileBasedDataWriter, scale=2):

mineru/utils/pdf_page_id.py

@@ -0,0 +1,10 @@
+# Copyright (c) Opendatalab. All rights reserved.
+from loguru import logger
+
+
+def get_end_page_id(end_page_id, pdf_page_num):
+    end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else pdf_page_num - 1
+    if end_page_id > pdf_page_num - 1:
+        logger.warning("end_page_id is out of range, use images length")
+        end_page_id = pdf_page_num - 1
+    return end_page_id

mineru/version.py

@@ -1 +1 @@
-__version__ = "2.6.3"
+__version__ = "2.6.4"

{mineru-2.6.3.dist-info → mineru-2.6.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mineru
-Version: 2.6.3
+Version: 2.6.4
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: homepage, https://mineru.net/
@@ -130,6 +130,10 @@ Dynamic: license-file
 </div>
 
 # Changelog
+- 2025/11/04 2.6.4 Release
+  - Added timeout configuration for PDF image rendering, default is 300 seconds, can be configured via environment variable `MINERU_PDF_RENDER_TIMEOUT` to prevent long blocking of the rendering process caused by some abnormal PDF files.
+  - Added CPU thread count configuration options for ONNX models, default is the system CPU core count, can be configured via environment variables `MINERU_INTRA_OP_NUM_THREADS` and `MINERU_INTER_OP_NUM_THREADS` to reduce CPU resource contention conflicts in high concurrency scenarios.
+
 - 2025/10/31 2.6.3 Release
   - Added support for a new backend `vlm-mlx-engine`, enabling MLX-accelerated inference for the MinerU2.5 model on Apple Silicon devices. Compared to the `vlm-transformers` backend, `vlm-mlx-engine` delivers a 100%–200% speed improvement.
   - Bug fixes: #3849, #3859

{mineru-2.6.3.dist-info → mineru-2.6.4.dist-info}/RECORD

@@ -1,5 +1,5 @@
 mineru/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
-mineru/version.py,sha256=uJ6TLK18jhCrL0aclBja7NzlAGLAyZjVpX-gq3d461k,22
+mineru/version.py,sha256=ODIwI6SfzWmx_FdtwCfr6k5TmpNuA5JdvGyV-9G9YrM,22
 mineru/backend/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/utils.py,sha256=GLJU3IznDmhE1_qNmkU1UOtsuskIHBezgsEVO6Uar-Y,698
 mineru/backend/pipeline/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
@@ -8,20 +8,20 @@ mineru/backend/pipeline/model_init.py,sha256=OAylOcQD9gu5TBcX7nMt7X5NpJMtQICI5Iv
 mineru/backend/pipeline/model_json_to_middle_json.py,sha256=reXkUR_wKmJD64d7vRNXMxFviwkzDlGjRshpdwsVquI,10951
 mineru/backend/pipeline/model_list.py,sha256=7cXMBfZrP0K6qWueg1D_-WoUANeSINzkn_ic9E7YQLs,222
 mineru/backend/pipeline/para_split.py,sha256=Kq95MmvkPm7rKxlCSGiTvVKyF7CErHI2eGGAs5sLl0Q,17119
-mineru/backend/pipeline/pipeline_analyze.py,sha256=rbO5AetOdnxR5ctkoDzFCFoElkz7Jgb7gi2Ct596NK8,6655
+mineru/backend/pipeline/pipeline_analyze.py,sha256=O_HGifodg03VZbmTve-U6Cmo0T03AmuK86t1v1J9X-Q,6897
 mineru/backend/pipeline/pipeline_magic_model.py,sha256=w8jGx8f6yZN0Wf2yPP3L9rYKc9rogxreZCrUJzJvPO8,14974
 mineru/backend/pipeline/pipeline_middle_json_mkcontent.py,sha256=YlnEbbUnkniZXS13aLo5mjfFQvQM5SrIVvTAGBZsLmw,14478
 mineru/backend/vlm/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/backend/vlm/model_output_to_middle_json.py,sha256=AqYX44gS9crUO_t7SuUatD71EVjow6pI6yA2Ik3gQ0s,5139
 mineru/backend/vlm/utils.py,sha256=woGqyRI4S7p69daLCU07XNXWTV27aLf7YBjjVH1x-5o,2794
-mineru/backend/vlm/vlm_analyze.py,sha256=7c5_JN1F9YTDNNgA_Rmw6xX1PI7gcIT4A4ujtGQHH9Q,8792
+mineru/backend/vlm/vlm_analyze.py,sha256=EQKNtc12pQ6so5NuUE-ppUtWI1QH_CQnsx1QfHdzAwA,8790
 mineru/backend/vlm/vlm_magic_model.py,sha256=Pd0sOr7G1crAJIVeq6h_03gNSuxmV5U8dvGTGT_rrjs,23452
 mineru/backend/vlm/vlm_middle_json_mkcontent.py,sha256=5V-AU9KkxxMn0DDSQBrb15I4GVpEyiQy8uNI_tQhS6M,13498
 mineru/cli/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
-mineru/cli/client.py,sha256=ArnoT2psOQRnTqLpsFwPaoi-l444iIVkbBn90Pm16n8,6915
-mineru/cli/common.py,sha256=jxFJMdc-02UMO3SXAtcZ6aIdPrakAE6DCccZ9kDlPKc,14276
+mineru/cli/client.py,sha256=ul2Twu-MWT2pCPrtvWbhIwWnoR6aurHJ3KhFOmElP90,6915
+mineru/cli/common.py,sha256=3kd6sF6BlnBNL_UeMjXKJ11fGQA4Y9lOckznWNiIWY8,13988
 mineru/cli/fast_api.py,sha256=t5bda769VbM5iokAboiJfPIOnm-r5GTFReE-KQy8L3g,10941
-mineru/cli/gradio_app.py,sha256=6dA0ARpdOoewFeXmHrleF1amCgBV9ilY_nkWAmAmN8A,14731
+mineru/cli/gradio_app.py,sha256=hyhI38y-JahMJgYZiikC3CYUVrtYVjbZb67Q4RUKbw4,14731
 mineru/cli/models_download.py,sha256=LNfoIpUlJM7m7qb2SiCxtjMDw4jILBQtZwNP2JoY81U,4815
 mineru/cli/vlm_vllm_server.py,sha256=fQJyD-gIPQ41hR_6aIaDJczl66N310t0CiZEBAfX5mc,90
 mineru/data/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
@@ -77,12 +77,12 @@ mineru/model/table/rec/slanet_plus/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQe
 mineru/model/table/rec/slanet_plus/main.py,sha256=vfrcvQ9JBf32YZU9eNoetoqdpcrFNsA1WNqQBsG8i2o,7646
 mineru/model/table/rec/slanet_plus/matcher.py,sha256=uwF-wCLaYlaQ3JQ_-YywGVl1XQYnx7G_RTuWLW8JlBk,7321
 mineru/model/table/rec/slanet_plus/matcher_utils.py,sha256=9wt_ydeeViLd57bU6g3lnXXni49qLSra2C6wSFQZkiw,9597
-mineru/model/table/rec/slanet_plus/table_structure.py,sha256=Ve9eUdA0ivHf5bf9gwvHHfb7-E7drJLP3S3MPlh3uZ0,3844
+mineru/model/table/rec/slanet_plus/table_structure.py,sha256=qt-HPYIQyp0aWG_MmnM_sMQCV8ZLb4rALSueyCohPgM,4085
 mineru/model/table/rec/slanet_plus/table_structure_utils.py,sha256=YYSkwN2WdLx7qkWMSGkPY7yXOH5ENVhg5CsRGhtZ5Wk,19281
 mineru/model/table/rec/unet_table/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mineru/model/table/rec/unet_table/main.py,sha256=J13Q7_6stYyedmVedf9CZD7R0tuguGfTg3Z3ob4GDuM,15565
 mineru/model/table/rec/unet_table/table_recover.py,sha256=rSyeWyuP10M8dLKA5e0n4P2DXMYbVbmgLxEcdZA8_0E,9059
-mineru/model/table/rec/unet_table/table_structure_unet.py,sha256=beBMmBHAOR2lAuf2rcOKRSbFaJqwuIgMJWxWQsFmIRI,7908
+mineru/model/table/rec/unet_table/table_structure_unet.py,sha256=hnmYLzZFRlK0Y4gr874G9GaLahcKnNZYNun869FdmH8,8150
 mineru/model/table/rec/unet_table/utils.py,sha256=CYAqJW0wePJk4NAemb8W203N7E32v0ujiWbxanDhd8I,16083
 mineru/model/table/rec/unet_table/utils_table_line_rec.py,sha256=zrCdPwI4M8nu0FEfd7lRJAe0z8kYq3KFbzwElM82USE,11174
 mineru/model/table/rec/unet_table/utils_table_recover.py,sha256=XksJsY82ZS0kqUnNT-jvaYzxJ3V3svMSzj0puwIau1k,10651
@@ -153,7 +153,7 @@ mineru/utils/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 mineru/utils/block_pre_proc.py,sha256=uGBmxf2MR9bplTnQI8xHjCI-kj3plRhJr0hcWKidbOQ,9632
 mineru/utils/block_sort.py,sha256=5e1mOLB3W7xu5Y1hmhvGSHPL_aQ41R_4VXcP4vjYAOU,12976
 mineru/utils/boxbase.py,sha256=moP660AmZq_udHEsfvFkTQdJ4gjrrBwN7t0Enx7CIL8,6903
-mineru/utils/check_mac_env.py,sha256=pbmbcnS60zZRqNRBxFJbbPrCosU1lC464b0v6JUlgaE,1031
+mineru/utils/check_sys_env.py,sha256=1o7Do3k84Hnwvlnmzx8JqkcGJA3UqiGfucMv9sPgPyI,1113
 mineru/utils/cli_parser.py,sha256=4seFAu1kulsYnw6WM2q_cxgEOt2tErZVkI-LNEF_kGw,1445
 mineru/utils/config_reader.py,sha256=IRVWTpBnbnRpck6eXZUKw-fcLt7hon5S4uqWW-RBb1w,4075
 mineru/utils/cut_image.py,sha256=g3m4nfcJNWlxi-P0kpXTtlmspXkMcLCfGwmYuQ-Z2hE,751
@@ -168,17 +168,19 @@ mineru/utils/magic_model_utils.py,sha256=2xOvi4oqg3MSw1FUrJTnYDtWeFrrm6qbmlEorLZ
 mineru/utils/model_utils.py,sha256=6OsgFLsABX5JuShSzCMSNHWV-yi-1cjwHweafyxIgRo,18448
 mineru/utils/models_download_utils.py,sha256=UfjvwhxO6BkJHa5JSpEVNZ71GoLMPMmJpym3THET2T4,2957
 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=mioLEHOdDtM1YbspNaa0wWhnLw_4-H7rdHlIM40vrT4,4077
+mineru/utils/pdf_image_tools.py,sha256=86_xvsGOEde5QGlKz5uJemjoO1upr6n_K7o3lCdyIjQ,7981
+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=h41q2uQajI0xQbc_30hqaju1dv3oVYxBAlKgURl8HIc,13692
 mineru/utils/table_merge.py,sha256=d98zNbM1ZQ8V1kUt6RugParNUNPv7DGL-XKIzR3iJVQ,15360
-mineru-2.6.3.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-mineru-2.6.3.dist-info/METADATA,sha256=mUBTxFG5tgdyQ1caZVRNrk4MhIX36PECY09dwCNYXZ4,70689
-mineru-2.6.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mineru-2.6.3.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
-mineru-2.6.3.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
-mineru-2.6.3.dist-info/RECORD,,
+mineru-2.6.4.dist-info/licenses/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+mineru-2.6.4.dist-info/METADATA,sha256=igOwr_rwmoJGD4KXKyEBgpESlUr6CZHThNXXE2PQ59U,71241
+mineru-2.6.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mineru-2.6.4.dist-info/entry_points.txt,sha256=luXmbhPiZK_tKlRgWuYOaW_V6EFpG-yJcAevVv9MEqE,252
+mineru-2.6.4.dist-info/top_level.txt,sha256=zuGQfZcbsHv4I4oKI9gaKPqEWBFm6xJroKuug2LnKP8,7
+mineru-2.6.4.dist-info/RECORD,,