From 0b8a9d51e1ccc16f346ed15da7b7d52bd97dfee5 Mon Sep 17 00:00:00 2001 From: myhloli Date: Wed, 9 Jul 2025 19:45:29 +0800 Subject: [PATCH 1/2] feat: add content field to interline equation block in model_json_to_middle_json.py --- mineru/backend/pipeline/model_json_to_middle_json.py | 1 + 1 file changed, 1 insertion(+) diff --git a/mineru/backend/pipeline/model_json_to_middle_json.py b/mineru/backend/pipeline/model_json_to_middle_json.py index 7a8b04bf..3905ff88 100644 --- a/mineru/backend/pipeline/model_json_to_middle_json.py +++ b/mineru/backend/pipeline/model_json_to_middle_json.py @@ -89,6 +89,7 @@ def page_model_info_to_page_info(page_model_info, image_dict, page, image_writer "type": ContentType.INTERLINE_EQUATION, 'score': block['score'], "bbox": block['bbox'], + "content": "", }) all_bboxes, all_discarded_blocks, footnote_blocks = prepare_block_bboxes( From 5f4f5174801bb06b72b76f807a03ec06681a5328 Mon Sep 17 00:00:00 2001 From: myhloli Date: Thu, 10 Jul 2025 18:46:04 +0800 Subject: [PATCH 2/2] feat: add Noto fonts installation for Chinese character support in Dockerfile --- docker/china/Dockerfile | 9 +++++++-- docker/global/Dockerfile | 7 ++++++- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/docker/china/Dockerfile b/docker/china/Dockerfile index 43e7dcc8..625ffd8e 100644 --- a/docker/china/Dockerfile +++ b/docker/china/Dockerfile @@ -1,8 +1,13 @@ # Use the official sglang image FROM lmsysorg/sglang:v0.4.8.post1-cu126 -# Install libgl for opencv support -RUN apt-get update && apt-get install -y libgl1 && apt-get clean && rm -rf /var/lib/apt/lists/* +# Install libgl for opencv support & Noto fonts for Chinese characters +RUN apt-get update && \ + apt-get install -y fonts-noto-core fonts-noto-cjk && \ + apt-get install -y libgl1 && \ + apt-get clean && \ + fc-cache -fv && \ + rm -rf /var/lib/apt/lists/* # Install mineru latest RUN python3 -m pip install -U 'mineru[core]' -i https://mirrors.aliyun.com/pypi/simple --break-system-packages diff --git a/docker/global/Dockerfile b/docker/global/Dockerfile index 49eccae8..aa2461bd 100644 --- a/docker/global/Dockerfile +++ b/docker/global/Dockerfile @@ -2,7 +2,12 @@ FROM lmsysorg/sglang:v0.4.8.post1-cu126 # Install libgl for opencv support -RUN apt-get update && apt-get install -y libgl1 && apt-get clean && rm -rf /var/lib/apt/lists/* +RUN apt-get update && \ + apt-get install -y fonts-noto-core fonts-noto-cjk && \ + apt-get install -y libgl1 && \ + apt-get clean && \ + fc-cache -fv && \ + rm -rf /var/lib/apt/lists/* # Install mineru latest RUN python3 -m pip install -U 'mineru[core]' --break-system-packages