From 7c5cdcd4d7b407121b7f93ddcd30e51fb3086ef8 Mon Sep 17 00:00:00 2001 From: myhloli Date: Thu, 2 Jan 2025 14:24:37 +0800 Subject: [PATCH] refactor(pdf_parse): improve character spacing handling in PDF text extraction - Update the logic for inserting spaces between characters- Consider the next character's position instead of the previous one - Adjust the spacing threshold to 25% of the average character width - Ignore spaces at the end of lines to prevent double spaces --- magic_pdf/pdf_parse_union_core_v2.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/magic_pdf/pdf_parse_union_core_v2.py b/magic_pdf/pdf_parse_union_core_v2.py index c7491a41..ef069487 100644 --- a/magic_pdf/pdf_parse_union_core_v2.py +++ b/magic_pdf/pdf_parse_union_core_v2.py @@ -92,9 +92,12 @@ def chars_to_content(span): content = '' for char in span['chars']: # 如果下一个char的x0和上一个char的x1距离超过一个字符宽度，则需要在中间插入一个空格 - if char['bbox'][0] - span['chars'][span['chars'].index(char) - 1]['bbox'][2] > char_avg_width: - content += ' ' - content += char['c'] + char1 = char + char2 = span['chars'][span['chars'].index(char) + 1] if span['chars'].index(char) + 1 < len(span['chars']) else None + if char2 and char2['bbox'][0] - char1['bbox'][2] > char_avg_width * 0.25 and char['c'] != ' ' and char2['c'] != ' ': + content += f"{char['c']} " + else: + content += char['c'] content = __replace_ligatures(content) span['content'] = __replace_0xfffd(content)