From 69805f4ba973b845f62dbef2b605f27f2d022391 Mon Sep 17 00:00:00 2001 From: myhloli Date: Tue, 19 Nov 2024 02:04:27 +0800 Subject: [PATCH] refactor(para): adjust right margin threshold based on block width - Introduce a variable threshold for right margin based on block width - Use 0.26 * block_weight for wider blocks (block_weight_radio >= 0.5) - Use 0.36 * block_weight for narrower blocks- This change aims to improve paragraph splitting accuracy for different block widths --- magic_pdf/para/para_split_v3.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/magic_pdf/para/para_split_v3.py b/magic_pdf/para/para_split_v3.py index 58216185..0af3a573 100644 --- a/magic_pdf/para/para_split_v3.py +++ b/magic_pdf/para/para_split_v3.py @@ -121,8 +121,12 @@ def __is_list_or_index_block(block): right_close_num += 1 else: # 右侧不顶格情况下是否有一段距离,拍脑袋用0.3block宽度做阈值 - # 0.26 - closed_area = 0.35 * block_weight + # block宽的阈值可以小些,block窄的阈值要大 + + if block_weight_radio >= 0.5: + closed_area = 0.26 * block_weight + else: + closed_area = 0.36 * block_weight if block['bbox_fs'][2] - line['bbox'][2] > closed_area: right_not_close_num += 1