diff --git a/README.md b/README.md index e03d0f98..a2b8acd2 100644 --- a/README.md +++ b/README.md @@ -48,6 +48,9 @@ Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple inte # 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. + - Pinned `pdfminer.six` to version `20250324` to prevent parsing failures caused by new versions. - 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 diff --git a/README_zh-CN.md b/README_zh-CN.md index ea710050..41d3715e 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -47,6 +47,9 @@ # 更新记录 +- 2025/04/29 1.3.10 发布 + - 支持使用自定义公式标识符,可通过修改用户目录下的magic-pdf.json文件中的`latex-delimiter-config`项实现。 + - 锁定`pdfminer.six`至`20250324`版本,以避免新版本导致的解析失败问题。 - 2025/04/27 1.3.9 发布 - 优化公式解析功能,提升公式渲染的成功率 - 更新`pdfminer.six`到最新版本,修复了部分pdf解析异常问题 diff --git a/magic_pdf/model/sub_modules/model_utils.py b/magic_pdf/model/sub_modules/model_utils.py index a47d6364..1ef02239 100644 --- a/magic_pdf/model/sub_modules/model_utils.py +++ b/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))