magic-pdf 1.3.9__py3-none-any.whl → 1.3.11__py3-none-any.whl

magic_pdf/dict2md/ocr_mkcontent.py

@@ -5,6 +5,7 @@ from loguru import logger
 from magic_pdf.config.make_content_config import DropMode, MakeMode
 from magic_pdf.config.ocr_content_type import BlockType, ContentType
 from magic_pdf.libs.commons import join_path
+from magic_pdf.libs.config_reader import get_latex_delimiter_config
 from magic_pdf.libs.language import detect_lang
 from magic_pdf.libs.markdown_utils import ocr_escape_special_markdown_char
 from magic_pdf.post_proc.para_split_v3 import ListLineTag
@@ -145,6 +146,19 @@ def full_to_half(text: str) -> str:
             result.append(char)
     return ''.join(result)
 
+latex_delimiters_config = get_latex_delimiter_config()
+
+default_delimiters = {
+    'display': {'left': '$$', 'right': '$$'},
+    'inline': {'left': '$', 'right': '$'}
+}
+
+delimiters = latex_delimiters_config if latex_delimiters_config else default_delimiters
+
+display_left_delimiter = delimiters['display']['left']
+display_right_delimiter = delimiters['display']['right']
+inline_left_delimiter = delimiters['inline']['left']
+inline_right_delimiter = delimiters['inline']['right']
 
 def merge_para_with_text(para_block):
     block_text = ''
@@ -168,9 +182,9 @@ def merge_para_with_text(para_block):
             if span_type == ContentType.Text:
                 content = ocr_escape_special_markdown_char(span['content'])
             elif span_type == ContentType.InlineEquation:
-                content = f"${span['content']}$"
+                content = f"{inline_left_delimiter}{span['content']}{inline_right_delimiter}"
             elif span_type == ContentType.InterlineEquation:
-                content = f"\n$$\n{span['content']}\n$$\n"
+                content = f"\n{display_left_delimiter}\n{span['content']}\n{display_right_delimiter}\n"
 
             content = content.strip()
 

magic_pdf/libs/config_reader.py

@@ -125,6 +125,15 @@ def get_llm_aided_config():
     else:
         return llm_aided_config
 
+def get_latex_delimiter_config():
+    config = read_config()
+    latex_delimiter_config = config.get('latex-delimiter-config')
+    if latex_delimiter_config is None:
+        logger.warning(f"'latex-delimiter-config' not found in {CONFIG_FILE_NAME}, use 'None' as default")
+        return None
+    else:
+        return latex_delimiter_config
+
 
 if __name__ == '__main__':
     ak, sk, endpoint = get_s3_config('llm-raw')

magic_pdf/libs/version.py

@@ -1 +1 @@
-__version__ = "1.3.9"
+__version__ = "1.3.11"

magic_pdf/model/doc_analyze_by_custom_model.py

@@ -156,7 +156,10 @@ def doc_analyze(
         batch_images = [images_with_extra_info]
 
     results = []
-    for batch_image in batch_images:
+    processed_images_count = 0
+    for index, batch_image in enumerate(batch_images):
+        processed_images_count += len(batch_image)
+        logger.info(f'Batch {index + 1}/{len(batch_images)}: {processed_images_count} pages/{len(images_with_extra_info)} pages')
         result = may_batch_image_analyze(batch_image, ocr, show_log,layout_model, formula_enable, table_enable)
         results.extend(result)
 

magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/modeling_unimernet.py

@@ -66,9 +66,9 @@ LEFT_RIGHT_REMOVE_PATTERN = re.compile(r'\\left\.?|\\right\.?')
 
 def fix_latex_left_right(s):
     """
-    修复LaTeX中的\left和\right命令
+    修复LaTeX中的\\left和\\right命令
     1. 确保它们后面跟有效分隔符
-    2. 平衡\left和\right的数量
+    2. 平衡\\left和\\right的数量
     """
     # 白名单分隔符
     valid_delims_list = [r'(', r')', r'[', r']', r'{', r'}', r'/', r'|',
@@ -106,7 +106,7 @@ def fix_latex_left_right(s):
 
 def fix_left_right_pairs(latex_formula):
     """
-    检测并修复LaTeX公式中\left和\right不在同一组的情况
+    检测并修复LaTeX公式中\\left和\\right不在同一组的情况
 
     Args:
         latex_formula (str): 输入的LaTeX公式
@@ -308,9 +308,9 @@ ENV_FORMAT_PATTERNS = {env: re.compile(r'\\begin\{' + env + r'\}\{([^}]*)\}') fo
 
 def fix_latex_environments(s):
     """
-    检测LaTeX中环境（如array）的\begin和\end是否匹配
-    1. 如果缺少\begin标签则在开头添加
-    2. 如果缺少\end标签则在末尾添加
+    检测LaTeX中环境（如array）的\\begin和\\end是否匹配
+    1. 如果缺少\\begin标签则在开头添加
+    2. 如果缺少\\end标签则在末尾添加
     """
     for env in ENV_TYPES:
         begin_count = len(ENV_BEGIN_PATTERNS[env].findall(s))
@@ -334,7 +334,7 @@ def fix_latex_environments(s):
 
 UP_PATTERN = re.compile(r'\\up([a-zA-Z]+)')
 COMMANDS_TO_REMOVE_PATTERN = re.compile(
-    r'\\(?:lefteqn|boldmath|ensuremath|centering|textsubscript|sides|textsl|textcent|emph)')
+    r'\\(?:lefteqn|boldmath|ensuremath|centering|textsubscript|sides|textsl|textcent|emph|protect|null)')
 REPLACEMENTS_PATTERNS = {
     re.compile(r'\\underbar'): r'\\underline',
     re.compile(r'\\Bar'): r'\\hat',
@@ -342,7 +342,13 @@ REPLACEMENTS_PATTERNS = {
     re.compile(r'\\Tilde'): r'\\tilde',
     re.compile(r'\\slash'): r'/',
     re.compile(r'\\textperthousand'): r'‰',
-    re.compile(r'\\sun'): r'☉'
+    re.compile(r'\\sun'): r'☉',
+    re.compile(r'\\textunderscore'): r'\\_',
+    re.compile(r'\\fint'): r'⨏',
+    re.compile(r'\\up '): r'\\ ',
+    re.compile(r'\\vline = '): r'\\models ',
+    re.compile(r'\\vDash '): r'\\models ',
+    re.compile(r'\\sq \\sqcup '): r'\\square ',
 }
 QQUAD_PATTERN = re.compile(r'\\qquad(?!\s)')
 

magic_pdf/model/sub_modules/model_utils.py

@@ -172,8 +172,8 @@ def filter_nested_tables(table_res_list, overlap_threshold=0.8, area_threshold=0
         tables_inside = [j for j in range(len(table_res_list))
                          if i != j and is_inside(table_info[j], table_info[i], overlap_threshold)]
 
-        # Continue if there are at least 2 tables inside
-        if len(tables_inside) >= 2:
+        # Continue if there are at least 3 tables inside
+        if len(tables_inside) >= 3:
             # Check if inside tables overlap with each other
             tables_overlap = any(do_overlap(table_info[tables_inside[idx1]], table_info[tables_inside[idx2]])
                                  for idx1 in range(len(tables_inside))

{magic_pdf-1.3.9.dist-info → magic_pdf-1.3.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 1.3.9
+Version: 1.3.11
 Summary: A practical tool for converting PDF to Markdown
 License: AGPL-3.0
 Project-URL: Home, https://mineru.net/
@@ -10,7 +10,7 @@ Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Python: >=3.10,<4
+Requires-Python: >=3.10,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
 Requires-Dist: Brotli >=1.1.0
@@ -20,10 +20,10 @@ Requires-Dist: click >=8.1.7
 Requires-Dist: fast-langdetect <0.3.0,>=0.2.3
 Requires-Dist: loguru >=0.6.0
 Requires-Dist: numpy >=1.21.6
-Requires-Dist: pdfminer.six >=20250416
+Requires-Dist: pdfminer.six ==20250506
 Requires-Dist: pydantic <2.11,>=2.7.2
 Requires-Dist: scikit-learn >=1.0.2
-Requires-Dist: torch !=2.5.0,!=2.5.1,>=2.2.2
+Requires-Dist: torch !=2.5.0,!=2.5.1,<3,>=2.2.2
 Requires-Dist: torchvision
 Requires-Dist: tqdm >=4.67.1
 Requires-Dist: transformers !=4.51.0,<5.0.0,>=4.49.0
@@ -107,9 +107,10 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte
 </div>
 
 # Changelog
+- 2025/04/29 1.3.10 Released
+  - Support for custom formula delimiters can be achieved by modifying the `latex-delimiter-config` item in the `magic-pdf.json` file under the user directory.
 - 2025/04/27 1.3.9 Released  
-  - Optimized the formula parsing function to improve the success rate of formula rendering  
-  - Updated `pdfminer.six` to the latest version, fixing some abnormal PDF parsing issues
+  - Optimized the formula parsing function to improve the success rate of formula rendering
 - 2025/04/23 1.3.8 Released
   - The default `ocr` model (`ch`) has been updated to `PP-OCRv4_server_rec_doc` (model update required)
     - `PP-OCRv4_server_rec_doc` is trained on a mix of more Chinese document data and PP-OCR training data, enhancing recognition capabilities for some traditional Chinese characters, Japanese, and special characters. It supports over 15,000 recognizable characters, improving text recognition in documents while also boosting general text recognition.
@@ -411,7 +412,7 @@ There are three different ways to experience MinerU:
     </tr>
     <tr>
         <td colspan="3">Python Version</td>
-        <td colspan="3">>=3.10</td>
+        <td colspan="3">3.10~3.13</td>
     </tr>
     <tr>
         <td colspan="3">Nvidia Driver Version</td>
@@ -421,8 +422,7 @@ There are three different ways to experience MinerU:
     </tr>
     <tr>
         <td colspan="3">CUDA Environment</td>
-        <td>11.8/12.4/12.6/12.8</td>
-        <td>11.8/12.4/12.6/12.8</td>
+        <td colspan="2"><a href="https://pytorch.org/get-started/locally/">Refer to the PyTorch official website</a></td>
         <td>None</td>
     </tr>
     <tr>
@@ -453,7 +453,7 @@ Synced with dev branch updates:
 #### 1. Install magic-pdf
 
 ```bash
-conda create -n mineru 'python>=3.10' -y
+conda create -n mineru 'python=3.12' -y
 conda activate mineru
 pip install -U "magic-pdf[full]"
 ```

{magic_pdf-1.3.9.dist-info → magic_pdf-1.3.11.dist-info}/RECORD

@@ -25,7 +25,7 @@ magic_pdf/data/io/base.py,sha256=SqNQqe30ZvoVvg7GVv-hLMCjN6yBgDyQQWeLgGsTfhQ,111
 magic_pdf/data/io/http.py,sha256=XlKB0DNf4a_uUnfgcclvaaOtmE7lmddx0DnK8A-emAM,958
 magic_pdf/data/io/s3.py,sha256=hyA7sbNriQy64xd_uyJ7acN_oneQ1Pdmoc7_xcvkue8,3606
 magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/dict2md/ocr_mkcontent.py,sha256=U4DqKfD4dJ2S5Z8NEAGhuLYkEOIeC-BWuArMbwi7BJs,13784
+magic_pdf/dict2md/ocr_mkcontent.py,sha256=jRGoSNeR3XBgzGhKdQ25CmsdW0pi7NA-5NY3TB2pja0,14421
 magic_pdf/filter/__init__.py,sha256=_7lSez_myu4b6cdzPpQ-NfREuqeBSq_QdyBPKVLyq2U,1505
 magic_pdf/filter/pdf_classify_by_type.py,sha256=YNYXamxYgEiSujwilCNHOtrwpgJGDiQ597qJfardDVc,42354
 magic_pdf/filter/pdf_meta_scan.py,sha256=eOuM0-JgaXvHolSgepGoNDJDmv_uITWLQpH_0MfnVQw,17478
@@ -38,7 +38,7 @@ magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/libs/boxbase.py,sha256=DKZXhwpJd-HE2_Du7NmkeeYW5gG-iwX3GeSWL7rYGv0,16956
 magic_pdf/libs/clean_memory.py,sha256=OsQexCjmBO2i-Hv-0uYQfn72dbUWR8sTW81nG2zlNQQ,479
 magic_pdf/libs/commons.py,sha256=xD0fGA16KNB5rhbl4zRrOqdrNHYwaRablT_s9W2ZTbw,1174
-magic_pdf/libs/config_reader.py,sha256=9GXK7jtDyA_jxXKWZAQ69rB02v5UW4mOmo1IaOYOkW0,4374
+magic_pdf/libs/config_reader.py,sha256=Z8C5o2uYfByB0Sj-jpgzu6VRobNp0y2gTheVXWkZV_0,4716
 magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
 magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
 magic_pdf/libs/draw_bbox.py,sha256=hpUmpPiQVu7UgWQa3M49dS22G6A9gcG2jpq4dQjTjzA,18331
@@ -52,17 +52,17 @@ magic_pdf/libs/pdf_check.py,sha256=7GWWvDR6g_rj_fE6XJlbTq5AFVX11ngRIzT0N18F214,3
 magic_pdf/libs/pdf_image_tools.py,sha256=_au7plmKKctpPKozBumSKgP8689q4vH1mU8VMLO0IbM,2260
 magic_pdf/libs/performance_stats.py,sha256=DW-c6nUTUnWKGTONRKfpucsYZm1ake016F9K7jJwbik,2136
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
-magic_pdf/libs/version.py,sha256=SaWgUI6v92kVfF_Qdoxbfc38bwA34RuDGZmXMqa5g3c,22
+magic_pdf/libs/version.py,sha256=cYqar-M7VsRkfFRByjCNAq9dYm1GavgcND7ugDzle7Q,23
 magic_pdf/model/__init__.py,sha256=sa-dO2k-TLy25I2gRrzjm_cQeYfzMf-pLwBJHkIxGo0,51
 magic_pdf/model/batch_analyze.py,sha256=F0WsjbQ6z9txdiUiVy6n6zhyJWJ-4moljNx8fe8HFws,10977
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=-cjn7DQi6kZCqVZ0IxbXuL2kmeGhSVLzLaezIHPFzMU,10317
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=R-d3_ZLZtlAztA23yaDvC0YC2-heXxrBBEyGlX7or7c,10547
 magic_pdf/model/magic_model.py,sha256=yZKWo_wRck_-YLyFGRiUHGar8sV1Y6458BFLbyBAt74,30682
 magic_pdf/model/model_list.py,sha256=aqfEJlEfbib3D3ISrxc0Coh6SbffYh8Yq2FlQN35_zA,213
 magic_pdf/model/pdf_extract_kit.py,sha256=C3sKqRkoD20Ldmo-cqGn1zRldEL-l5NYqcFvd05_fGU,10845
 magic_pdf/model/pp_structure_v2.py,sha256=NcqFWL4nUtjl82MFak8HX_8V3i4Aw_fK4dATrIp5uGs,3840
 magic_pdf/model/sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/model_init.py,sha256=e2t95kxiuU47luOHByDokbQ2uob6oQhEA4b6UGVfMjY,8303
-magic_pdf/model/sub_modules/model_utils.py,sha256=HKRC9ubCs6O0nNqaztrZO0YKuFpRhs0LKWOaeZfDrTw,12166
+magic_pdf/model/sub_modules/model_utils.py,sha256=Md5yOki9uqW31sWIi7AKRwAJNKnCJBVSfQx6LXRKngs,12166
 magic_pdf/model/sub_modules/language_detection/__init__.py,sha256=8CRrCQVuExa0BttRFh3Z40lFy2K5jN0sp67KWjOlj5c,50
 magic_pdf/model/sub_modules/language_detection/utils.py,sha256=Q__v6DdNJztt8GhVSuSB0txahVq-aj8RLhWn2VScx4w,3047
 magic_pdf/model/sub_modules/language_detection/yolov11/YOLOv11.py,sha256=7T8eFl8zlZe6F0j0jSB3jrwOapDft320JQ1fuWxpvAY,5230
@@ -97,7 +97,7 @@ magic_pdf/model/sub_modules/mfr/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm
 magic_pdf/model/sub_modules/mfr/unimernet/Unimernet.py,sha256=hq48TP1Ac8Y4FlK7GamnU-WZTQfdZotxBKuFhOIjrcM,5349
 magic_pdf/model/sub_modules/mfr/unimernet/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/__init__.py,sha256=kHcISG8GS4TWJW34SCJCei1jxo6HxvO00aC0dqyNFgI,413
-magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/modeling_unimernet.py,sha256=uRqyXsr3S0bw6CnkkJzAgne_MT3Q9Wz-npIXIMlRnlo,17986
+magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/modeling_unimernet.py,sha256=v5vf3a4sBLZ11FKbhb9bE_GEXcGbmdLxgTtl2pRmW34,18260
 magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/__init__.py,sha256=9T2rBpyGX5YFQYj89-mWujRokOuz4xgNreBuegcg1_c,228
 magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/configuration_unimer_mbart.py,sha256=hwRar3pqN_cVs3TRTNSuhB4wacBncfJ-qvaTajRb0xc,7934
 magic_pdf/model/sub_modules/mfr/unimernet/unimernet_hf/unimer_mbart/modeling_unimer_mbart.py,sha256=Y5nwqDRzSb8zAbY1U0HGJGVtFggJW1zATP8RdnasNcA,113605
@@ -196,9 +196,9 @@ magic_pdf/tools/common.py,sha256=-x0RSFr7SNbdYq7DntaLYmQmaxyF-xKSf4xMpSUTzA0,126
 magic_pdf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/utils/annotations.py,sha256=82ou3uELNbQWa9hOFFkVt0gsIskAKf5msCv5J2IJ5V0,211
 magic_pdf/utils/office_to_pdf.py,sha256=bFRYe6v3-pfx5R8-bV8cmf12jPnOrYZsleKoECTXzbM,3958
-magic_pdf-1.3.9.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
-magic_pdf-1.3.9.dist-info/METADATA,sha256=L98_kmfvo1RrBO3LR3Np2ySVd9nkMmXDf3TA5LmTVcQ,47611
-magic_pdf-1.3.9.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-magic_pdf-1.3.9.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
-magic_pdf-1.3.9.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-1.3.9.dist-info/RECORD,,
+magic_pdf-1.3.11.dist-info/LICENSE.md,sha256=jVa0BUaKrRH4erV2P5AeJ24I2WRv9chIGxditreJ6e0,34524
+magic_pdf-1.3.11.dist-info/METADATA,sha256=MFffMcv9-ZlVG8jBKDtTPofJC_F-x_OPU4aLwxd-aUs,47765
+magic_pdf-1.3.11.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+magic_pdf-1.3.11.dist-info/entry_points.txt,sha256=wXwYke3j8fqDQTocUspL-CqDUEv3Tfcwp09fM8dZAhA,98
+magic_pdf-1.3.11.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-1.3.11.dist-info/RECORD,,