panxiang/PythonApp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新 html的解析中 对于 cell 的解析，excel的处理中对于cell 的解析。以及温度处理中 对于 数据的处理增加 时间戳的换算。

Browse Source
This commit is contained in:
panxiang
2026-04-04 21:40:28 +08:00
parent 4e4d132066
commit efddb997e2
3 changed files with 133 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
htmlProcess/htmlReportProcess_cmd_p/htmlReportProcess_cmd_pV1.py
View File

@@ -50,6 +50,17 @@ class LogManager:
def log_statistics(self, statistics_data):
"""记录统计信息到日志文件"""
def mixed_sort_key(item):
"""处理混合类型（数字字符串和普通字符串）的排序键"""
try:
if isinstance(item, str) and item.isdigit():
return (0, int(item))
else:
return (1, str(item))
except (ValueError, TypeError):
return (2, str(item))
with open(self.log_file, 'a', encoding='utf-8') as f:
f.write("\n" + "=" * 80 + "\n")
f.write("处理统计汇总\n")
@@ -73,7 +84,9 @@ class LogManager:
f.write(f"{"="*30}\n")
# 按Cell编号排序
sorted_cells = sorted(cell_stats.keys(), key=lambda x: int(x) if x.isdigit() else x)
# sorted_cells = sorted(cell_stats.keys(), key=lambda x: int(x) if x.isdigit() else x)
# 使用修复后的排序方法
sorted_cells = sorted(cell_stats.keys(), key=mixed_sort_key)
for cell in sorted_cells:
stats = cell_stats[cell]
@@ -92,7 +105,7 @@ class LogManager:
sorted_fail_items = sorted(fail_details.items(), key=lambda x: x[1], reverse=True)[:10]
for test_name, count in sorted_fail_items:
fail_items.append(f"{test_name}({count}次)")
if len (sorted_fail_items)>10:
if len (fail_details.items())>10:
lastitems = sorted(fail_details.items(), key=lambda x: x[1], reverse=True)[10:]
messageappend =''
for test_name, count in lastitems:
@@ -123,7 +136,10 @@ class LogManager:
fail_details = stats.get('fail_details', {})
# Cell列表（逗号分隔）
cell_list = ','.join(sorted(cells, key=lambda x: int(x) if x.isdigit() else x))
# cell_list = ','.join(sorted(cells, key=lambda x: int(x) if x.isdigit() else x))
# 使用修复后的排序方法
cell_list = ','.join(sorted(cells, key=mixed_sort_key))
# 失败项详情
fail_items = []
@@ -292,31 +308,82 @@ class HTMLFileProcessor:
@staticmethod
def _extract_sn_and_cell(soup, filename):
"""提取SN号和cell编号"""
"""提取SN号和cell编号 - 支持多种来源"""
try:
sn_regex = r'F[A-Z0-9]{15}(?:[A-Z0-9]{5,})?'
cell_regex = r'\b\d+\b' # 匹配纯数字的cell编号
# 提取SN
# 初始化默认值
sn = "UNKNOWN_SN"
cell = "UNKNOWN_CELL"
# 优先从HTML内容中提取
if soup is not None:
html_text = soup.get_text(" ", strip=True)
# 方法1: 从Serial Number标签提取SN
sn_tag = soup.find('h3', string=re.compile(r'Serial Number:', re.I))
if sn_tag:
content_match = re.search(rf'\b({sn_regex})\b', sn_tag.get_text(), flags=re.I)
if content_match:
sn = content_match.group(1)
else:
html_text = soup.get_text(" ", strip=True)
# 方法2: 从Test Cell标签提取Cell编号
cell_tag = soup.find('h3', string=re.compile(r'Test Cell:', re.I))
if cell_tag:
cell_content = cell_tag.get_text()
cell_match = re.search(rf'\b({cell_regex})\b', cell_content)
if cell_match:
cell = cell_match.group(1)
# 方法3: 从整个HTML文本中搜索SN（如果前面没找到）
if sn == "UNKNOWN_SN":
content_match = re.search(rf'\b({sn_regex})\b', html_text, flags=re.I)
if content_match:
sn = content_match.group(1)
else:
# 方法4: 从整个HTML文本中搜索Cell编号（如果前面没找到）
if cell == "UNKNOWN_CELL":
# 搜索包含"cell"或"CELL"的文本段，然后提取数字
cell_sections = re.findall(r'(?i)(?:cell|test cell)[^\d]*(\d+)', html_text)
if cell_sections:
cell = cell_sections[0] # 取第一个匹配的cell编号
# 如果HTML中没找到，从文件名中提取
if sn == "UNKNOWN_SN":
content_match = re.search(rf'\b({sn_regex})\b', filename, flags=re.I)
if content_match:
sn = content_match.group(1)
# 提取cell编号（从文件名末尾的"数字"）
cell_match = re.search(r'-(\d+)\.html$', filename)
cell = cell_match.group(1) if cell_match else "UNKNOWN_CELL"
if cell == "UNKNOWN_CELL":
# 从文件名中提取cell编号（多种模式）
# 模式1: 破折号后、下划线或点号前的数字
pattern1 = r'-(\d+)[._]'
# 模式2: 包含"cell"或"CELL"后跟数字
pattern2 = r'(?i)(?:cell|CELL)[^\d]*(\d+)'
# 模式3: 文件名末尾的数字
pattern3 = r'(\d+)\.html?$'
for pattern in [pattern1, pattern2, pattern3]:
cell_match = re.search(pattern, filename)
if cell_match:
cell = cell_match.group(1)
break
# 额外的Cell编号提取逻辑（如果上述方法都没找到）
if cell == "UNKNOWN_CELL" and soup is not None:
# 尝试从表格或其他结构中提取Cell编号
try:
# 查找包含"Cell"的表格单元格
cell_tds = soup.find_all('td', string=re.compile(r'(?i)cell'))
for td in cell_tds:
parent_text = td.parent.get_text()
cell_match = re.search(rf'\b({cell_regex})\b', parent_text)
if cell_match:
cell = cell_match.group(1)
break
except:
pass
return sn, cell
@@ -1147,7 +1214,10 @@ class ParallelHTMLReportProcessor:
"""从文件名提取SN和cell编号"""
sn_regex = r'F[A-Z0-9]{15}(?:[A-Z0-9]{5,})?'
sn_match = re.search(rf'\b({sn_regex})\b', filename, flags=re.I)
cell_match = re.search(r'-(\d+)\.html$', filename)
# 匹配模式：破折号后、下划线或点号前的数字
pattern = r'-(\d+)[._]'
# cell_match = re.search(r'-(\d+)\.html$', filename)
cell_match = re.search(pattern, filename)
sn = sn_match.group(1) if sn_match else "UNKNOWN_SN"
cell = cell_match.group(1) if cell_match else "UNKNOWN_CELL"
@@ -1572,11 +1642,15 @@ if __name__ == "__main__":
# 关键：防止打包环境下的重复执行
mp.freeze_support()
# 额外保护：确保只在主进程中执行
if mp.current_process().name == 'MainProcess':
main()
input(f"输入任意结束程序......")
else:
# 子进程不需要执行任何交互代码
pass
try:
# 额外保护：确保只在主进程中执行
if mp.current_process().name == 'MainProcess':
main()
input(f"输入任意结束程序......")
else:
# 子进程不需要执行任何交互代码
pass
except KeyboardInterrupt:
print(f"用户中断程序")

2
htmlProcess/htmlReportProcess_picHtml/htmlReportProcess_picHtml_2kV1.py
View File

@@ -977,7 +977,7 @@ class MultiFileTestReportScatterPlotter:
print(f"警告：发现 {failed_conversions} 个 'Cell' 值无法转换为数字，这些条目将保留为字符串或根据业务逻辑处理。")
# 业务决策：对于无法转换的，可以保留原字符串，或使用一个默认值
# 例如，将无法转换的条目其数值编号设为-1或一个特定的标识值
# test_data.loc[test_data['Cell编号_数值'].isna(), 'Cell编号_数值'] = -1
test_data.loc[test_data['Cell编号_数值'].isna(), 'Cell编号_数值'] = -1
# 此时，您可以根据需求选择使用 'Cell编号'（字符串）或 'Cell编号_数值'（数字）进行后续分组和可视化
# 对于绘图着色和排序，使用 'Cell编号_数值' 列