修复尺寸报价及目的地补充的上下文边界

2026-10-29 19:11:39 +08:00
parent 8444ded971
commit ce445d0fb8
7 changed files with 87 additions and 42 deletions
@@ -100,6 +100,8 @@ def extract_reference(message):
    message = re.sub(r'(?<![A-Za-z0-9_-])\d{4}-\d{1,2}-\d{1,2}'
                     r'(?:[T ]\d{1,2}:\d{2}(?::\d{2}(?:\.\d+)?)?(?:Z|[+-]\d{2}:?\d{2})?)?'
                     r'(?![A-Za-z0-9_-])', ' ', message)
+    message = re.sub(r'(?<![A-Za-z0-9_.-])\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?\s*[*xX×]\s*\d+(?:\.\d+)?'
+                     r'(?:\s*(?:cm|mm|m|厘米|毫米|米))?(?![A-Za-z0-9_.-])', ' ', message, flags=re.I)
    message = re.sub(r'(?<![A-Za-z0-9_-])\d+(?:\.\d+)?\s*'
                     r'(?:kg|lbs?|cbm|cm|mm|公斤|千克|克|吨|立方米|方|m[³3]|箱|件)'
                     r'(?![A-Za-z0-9_])', ' ', message, flags=re.I)