{"id":60565,"date":"2026-01-15T22:05:27","date_gmt":"2026-01-15T14:05:27","guid":{"rendered":"https:\/\/www.wsisp.com\/helps\/60565.html"},"modified":"2026-01-15T22:05:27","modified_gmt":"2026-01-15T14:05:27","slug":"python%e7%bc%96%e7%a0%81%e5%9c%b0%e7%8b%b1%e9%80%83%e7%94%9f%e6%8c%87%e5%8d%97%ef%bc%9a%e4%b8%80%e7%af%87%e6%96%87%e7%ab%a0%e5%bd%bb%e5%ba%95%e5%91%8a%e5%88%ab%e4%b9%b1%e7%a0%81%e5%8d%b1%e6%9c%ba","status":"publish","type":"post","link":"https:\/\/www.wsisp.com\/helps\/60565.html","title":{"rendered":"Python\u7f16\u7801\u5730\u72f1\u9003\u751f\u6307\u5357\uff1a\u4e00\u7bc7\u6587\u7ae0\u5f7b\u5e95\u544a\u522b\u4e71\u7801\u5371\u673a"},"content":{"rendered":"

💥 \u4e71\u7801\u7684\u6839\u6e90：\u5f53\u5b57\u8282\u9047\u4e0a\u5b57\u7b26<\/h3>\n

\u5728\u6570\u5b57\u4e16\u754c\u4e2d，\u4e00\u5207\u4fe1\u606f\u6700\u7ec8\u90fd\u8f6c\u5316\u4e3a0\u548c1\u3002\u5f53\u6211\u4eec\u7528Python\u5904\u7406\u6587\u672c\u65f6，\u5b9e\u9645\u4e0a\u662f\u5728\u8fdb\u884c\u7f16\u7801（\u5c06\u5b57\u7b26\u8f6c\u6362\u4e3a\u5b57\u8282）\u548c\u89e3\u7801（\u5c06\u5b57\u8282\u8f6c\u6362\u4e3a\u5b57\u7b26）\u7684\u64cd\u4f5c\u3002\u8fd9\u4e2a\u8fc7\u7a0b\u4e2d\u6700\u5e38\u89c1\u7684\u9519\u8bef\u5c31\u662f：<\/p>\n

UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 2: illegal multibyte sequence<\/p>\n

\u8fd9\u4e2a\u9519\u8bef\u7684\u672c\u8d28\u662f\u7f16\u7801\u4e0d\u4e00\u81f4\u3002\u4f60\u7684\u6587\u4ef6\u7528\u4e00\u79cd\u7f16\u7801\u4fdd\u5b58，\u4f46\u7528\u53e6\u4e00\u79cd\u7f16\u7801\u8bfb\u53d6\u3002\u8ba9\u6211\u4eec\u4ece\u6700\u57fa\u7840\u7684\u539f\u7406\u5f00\u59cb：<\/p>\n

"""
\n\u7f16\u7801\u7684\u57fa\u672c\u539f\u7406\u6f14\u793a
\n\u5c55\u793a\u5b57\u7b26\u5982\u4f55\u8f6c\u6362\u4e3a\u5b57\u8282，\u4ee5\u53ca\u7f16\u7801\u4e0d\u4e00\u81f4\u5bfc\u81f4\u7684\u4e71\u7801
\n"""<\/span>
\ndef<\/span> demonstrate_encoding_basics<\/span>(<\/span>)<\/span>:<\/span>
\n """\u6f14\u793a\u7f16\u7801\u7684\u57fa\u672c\u539f\u7406"""<\/span><\/p>\n

# 1. \u5b57\u7b26\u4e32\u5728\u5185\u5b58\u4e2d\u7684\u8868\u793a<\/span>
\n text =<\/span> "\u4f60\u597d，Python\u7f16\u7801！"<\/span>
\n print<\/span>(<\/span>"\u539f\u59cb\u5b57\u7b26\u4e32:"<\/span>,<\/span> text)<\/span><\/p>\n

# 2. \u4f7f\u7528\u4e0d\u540c\u7f16\u7801\u8f6c\u6362\u4e3a\u5b57\u8282<\/span>
\n encodings =<\/span> [<\/span>'utf-8'<\/span>,<\/span> 'gbk'<\/span>,<\/span> 'utf-16'<\/span>,<\/span> 'latin-1'<\/span>]<\/span><\/p>\n

for<\/span> encoding in<\/span> encodings:<\/span>
\n try<\/span>:<\/span>
\n byte_data =<\/span> text.<\/span>encode(<\/span>encoding)<\/span>
\n print<\/span>(<\/span>f"\\\\n\u7f16\u7801: <\/span>{<\/span>encoding}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f"\u5b57\u8282\u957f\u5ea6: <\/span>{<\/span>len<\/span>(<\/span>byte_data)<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f"\u5b57\u8282\u8868\u793a: <\/span>{<\/span>byte_data}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f"\u5341\u516d\u8fdb\u5236: <\/span>{<\/span>byte_data.<\/span>hex<\/span>(<\/span>)<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n except<\/span> UnicodeEncodeError as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\\\\n\u7f16\u7801 <\/span>{<\/span>encoding}<\/span><\/span> \u5931\u8d25: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# 3. \u89e3\u7801\u6f14\u793a<\/span>
\n print<\/span>(<\/span>"\\\\n"<\/span> +<\/span> "="<\/span>*<\/span>50<\/span>)<\/span>
\n print<\/span>(<\/span>"\u89e3\u7801\u6f14\u793a:"<\/span>)<\/span><\/p>\n

# \u7528UTF-8\u7f16\u7801<\/span>
\n utf8_bytes =<\/span> text.<\/span>encode(<\/span>'utf-8'<\/span>)<\/span><\/p>\n

# \u5c1d\u8bd5\u7528\u4e0d\u540c\u7f16\u7801\u89e3\u7801<\/span>
\n for<\/span> encoding in<\/span> [<\/span>'utf-8'<\/span>,<\/span> 'gbk'<\/span>,<\/span> 'latin-1'<\/span>]<\/span>:<\/span>
\n try<\/span>:<\/span>
\n decoded =<\/span> utf8_bytes.<\/span>decode(<\/span>encoding)<\/span>
\n print<\/span>(<\/span>f"\u7528 <\/span>{<\/span>encoding}<\/span><\/span> \u89e3\u7801: <\/span>{<\/span>decoded}<\/span><\/span>"<\/span><\/span>)<\/span>
\n except<\/span> UnicodeDecodeError:<\/span>
\n print<\/span>(<\/span>f"\u7528 <\/span>{<\/span>encoding}<\/span><\/span> \u89e3\u7801\u5931\u8d25: \u7f16\u7801\u4e0d\u517c\u5bb9"<\/span><\/span>)<\/span><\/p>\n

if<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n demonstrate_encoding_basics(<\/span>)<\/span><\/p>\n

\u8fd0\u884c\u8fd9\u6bb5\u4ee3\u7801，\u4f60\u4f1a\u53d1\u73b0\u540c\u4e00\u4e2a\u5b57\u7b26\u4e32\u7528\u4e0d\u540c\u7f16\u7801\u8f6c\u6362\u5f97\u5230\u7684\u5b57\u8282\u5e8f\u5217\u5b8c\u5168\u4e0d\u540c\u3002\u8fd9\u5c31\u662f\u4e71\u7801\u7684\u6839\u6e90：\u5b57\u8282\u5e8f\u5217\u662f\u6b63\u786e\u7684，\u4f46\u89e3\u7801\u65f6\u4f7f\u7528\u4e86\u9519\u8bef\u7684\u7f16\u7801\u8868\u3002<\/p>\n

🎯 Python\u6587\u4ef6\u7f16\u7801\u5b8c\u5168\u89e3\u51b3\u65b9\u6848<\/h3>\n

1. \u7edf\u4e00\u7f16\u7801\u7684\u9ec4\u91d1\u6cd5\u5219<\/h4>\n

"""
\n\u7edf\u4e00\u7f16\u7801\u7684\u6838\u5fc3\u4ee3\u7801
\n\u6240\u6709\u6587\u4ef6\u64cd\u4f5c\u90fd\u5fc5\u987b\u663e\u5f0f\u6307\u5b9a\u7f16\u7801
\n"""<\/span>
\nimport<\/span> csv
\nimport<\/span> os<\/p>\n

def<\/span> create_files_with_unified_encoding<\/span>(<\/span>)<\/span>:<\/span>
\n """\u521b\u5efa\u7f16\u7801\u4e00\u81f4\u7684\u6587\u4ef6"""<\/span><\/p>\n

# \u6570\u636e\u793a\u4f8b<\/span>
\n data =<\/span> [<\/span>
\n [<\/span>"ID"<\/span>,<\/span> "\u59d3\u540d"<\/span>,<\/span> "\u5e74\u9f84"<\/span>,<\/span> "\u57ce\u5e02"<\/span>]<\/span>,<\/span>
\n [<\/span>1<\/span>,<\/span> "\u5f20\u4e09"<\/span>,<\/span> 25<\/span>,<\/span> "\u5317\u4eac"<\/span>]<\/span>,<\/span>
\n [<\/span>2<\/span>,<\/span> "\u674e\u56db"<\/span>,<\/span> 30<\/span>,<\/span> "\u4e0a\u6d77"<\/span>]<\/span>,<\/span>
\n [<\/span>3<\/span>,<\/span> "\u738b\u4e94"<\/span>,<\/span> 28<\/span>,<\/span> "\u5e7f\u5dde"<\/span>]<\/span>
\n ]<\/span><\/p>\n

# 🎯 \u5173\u952e：\u603b\u662f\u663e\u5f0f\u6307\u5b9a\u7f16\u7801！<\/span>
\n # \u60c5\u51b51：\u4fdd\u5b58\u4e3aCSV\u683c\u5f0f<\/span>
\n with<\/span> open<\/span>(<\/span>'data_utf8.csv'<\/span>,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>,<\/span> newline=<\/span>''<\/span>)<\/span> as<\/span> f:<\/span>
\n writer =<\/span> csv.<\/span>writer(<\/span>f)<\/span>
\n writer.<\/span>writerows(<\/span>data)<\/span><\/p>\n

# \u60c5\u51b52：\u4fdd\u5b58\u4e3aTXT\u683c\u5f0f<\/span>
\n with<\/span> open<\/span>(<\/span>'data_utf8.txt'<\/span>,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f:<\/span>
\n for<\/span> row in<\/span> data:<\/span>
\n f.<\/span>write(<\/span>','<\/span>.<\/span>join(<\/span>str<\/span>(<\/span>x)<\/span> for<\/span> x in<\/span> row)<\/span> +<\/span> '\\\\n'<\/span>)<\/span><\/p>\n

# \u60c5\u51b53：\u4fdd\u5b58\u4e3a\u5e26BOM\u7684UTF-8（Windows Excel\u53cb\u597d）<\/span>
\n with<\/span> open<\/span>(<\/span>'data_utf8_bom.csv'<\/span>,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8-sig'<\/span>,<\/span> newline=<\/span>''<\/span>)<\/span> as<\/span> f:<\/span>
\n writer =<\/span> csv.<\/span>writer(<\/span>f)<\/span>
\n writer.<\/span>writerows(<\/span>data)<\/span><\/p>\n

# \u9a8c\u8bc1\u6587\u4ef6<\/span>
\n print<\/span>(<\/span>"\u2705 \u6587\u4ef6\u521b\u5efa\u5b8c\u6210，\u7f16\u7801\u9a8c\u8bc1："<\/span>)<\/span>
\n files =<\/span> [<\/span>'data_utf8.csv'<\/span>,<\/span> 'data_utf8.txt'<\/span>,<\/span> 'data_utf8_bom.csv'<\/span>]<\/span><\/p>\n

for<\/span> filename in<\/span> files:<\/span>
\n try<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'rb'<\/span>)<\/span> as<\/span> f:<\/span>
\n first_bytes =<\/span> f.<\/span>read(<\/span>3<\/span>)<\/span>
\n if<\/span> first_bytes ==<\/span> b'\\\\xef\\\\xbb\\\\xbf'<\/span>:<\/span>
\n encoding =<\/span> 'UTF-8-SIG (\u5e26BOM)'<\/span>
\n else<\/span>:<\/span>
\n # \u5c1d\u8bd5\u7528UTF-8\u8bfb\u53d6<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f2:<\/span>
\n f2.<\/span>read(<\/span>)<\/span>
\n encoding =<\/span> 'UTF-8 (\u65e0BOM)'<\/span>
\n print<\/span>(<\/span>f" 📁 <\/span>{<\/span>filename:<\/span>20<\/span>}<\/span><\/span> -> <\/span>{<\/span>encoding}<\/span><\/span>"<\/span><\/span>)<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f" \u274c <\/span>{<\/span>filename:<\/span>20<\/span>}<\/span><\/span> -> \u8bfb\u53d6\u5931\u8d25: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

return<\/span> files<\/p>\n

# \u6e05\u7406\u548c\u6d4b\u8bd5<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n # \u6e05\u7406\u65e7\u6587\u4ef6<\/span>
\n for<\/span> f in<\/span> [<\/span>'data_utf8.csv'<\/span>,<\/span> 'data_utf8.txt'<\/span>,<\/span> 'data_utf8_bom.csv'<\/span>]<\/span>:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>f)<\/span>:<\/span>
\n os.<\/span>remove(<\/span>f)<\/span><\/p>\n

files =<\/span> create_files_with_unified_encoding(<\/span>)<\/span>
\n print<\/span>(<\/span>"\\\\n\u2705 \u6240\u6709\u6587\u4ef6\u4f7f\u7528\u7edf\u4e00\u7f16\u7801\u521b\u5efa\u6210\u529f！"<\/span>)<\/span><\/p>\n

2. \u81ea\u52a8\u7f16\u7801\u68c0\u6d4b\u4e0e\u8f6c\u6362\u5de5\u5177<\/h4>\n

"""
\n\u667a\u80fd\u7f16\u7801\u68c0\u6d4b\u4e0e\u8f6c\u6362
\n\u81ea\u52a8\u8bc6\u522b\u6587\u4ef6\u7f16\u7801\u5e76\u8f6c\u6362\u4e3a\u76ee\u6807\u7f16\u7801
\n"""<\/span>
\nimport<\/span> os
\nfrom<\/span> typing import<\/span> Optional,<\/span> Tuple<\/p>\n

class<\/span> EncodingConverter<\/span>:<\/span>
\n """\u7f16\u7801\u8f6c\u6362\u5668"""<\/span><\/p>\n

def<\/span> __init__<\/span>(<\/span>self)<\/span>:<\/span>
\n self.<\/span>supported_encodings =<\/span> [<\/span>
\n 'utf-8'<\/span>,<\/span> 'utf-8-sig'<\/span>,<\/span> 'utf-16'<\/span>,<\/span> 'utf-16le'<\/span>,<\/span> 'utf-16be'<\/span>,<\/span>
\n 'gbk'<\/span>,<\/span> 'gb2312'<\/span>,<\/span> 'gb18030'<\/span>,<\/span> # \u4e2d\u6587\u7f16\u7801<\/span>
\n 'big5'<\/span>,<\/span> # \u7e41\u4f53\u4e2d\u6587<\/span>
\n 'shift_jis'<\/span>,<\/span> 'euc-jp'<\/span>,<\/span> # \u65e5\u6587<\/span>
\n 'euc-kr'<\/span>,<\/span> # \u97e9\u6587<\/span>
\n 'latin-1'<\/span>,<\/span> 'cp1252'<\/span>,<\/span> 'iso-8859-1'<\/span> # \u897f\u6b27<\/span>
\n ]<\/span><\/p>\n

def<\/span> detect_encoding<\/span>(<\/span>self,<\/span> filename:<\/span> str<\/span>,<\/span> sample_size:<\/span> int<\/span> =<\/span> 1000<\/span>)<\/span> –<\/span>><\/span> Tuple[<\/span>str<\/span>,<\/span> float<\/span>]<\/span>:<\/span>
\n """
\n \u68c0\u6d4b\u6587\u4ef6\u7f16\u7801<\/p>\n

\u53c2\u6570:
\n filename: \u6587\u4ef6\u540d
\n sample_size: \u91c7\u6837\u5927\u5c0f（\u5b57\u8282）<\/p>\n

\u8fd4\u56de:
\n (\u7f16\u7801\u540d\u79f0, \u7f6e\u4fe1\u5ea6)
\n """<\/span>
\n if<\/span> not<\/span> os.<\/span>path.<\/span>exists(<\/span>filename)<\/span>:<\/span>
\n raise<\/span> FileNotFoundError(<\/span>f"\u6587\u4ef6\u4e0d\u5b58\u5728: <\/span>{<\/span>filename}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

with<\/span> open<\/span>(<\/span>filename,<\/span> 'rb'<\/span>)<\/span> as<\/span> f:<\/span>
\n raw_data =<\/span> f.<\/span>read(<\/span>sample_size)<\/span><\/p>\n

if<\/span> not<\/span> raw_data:<\/span>
\n return<\/span> 'utf-8'<\/span>,<\/span> 0.0<\/span><\/p>\n

# \u68c0\u67e5BOM（\u5b57\u8282\u987a\u5e8f\u6807\u8bb0）<\/span>
\n if<\/span> raw_data.<\/span>startswith(<\/span>b'\\\\xef\\\\xbb\\\\xbf'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-8-sig'<\/span>,<\/span> 1.0<\/span>
\n elif<\/span> raw_data.<\/span>startswith(<\/span>b'\\\\xff\\\\xfe'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-16le'<\/span>,<\/span> 1.0<\/span>
\n elif<\/span> raw_data.<\/span>startswith(<\/span>b'\\\\xfe\\\\xff'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-16be'<\/span>,<\/span> 1.0<\/span><\/p>\n

# \u5c1d\u8bd5\u5e38\u89c1\u7f16\u7801<\/span>
\n encodings_to_try =<\/span> [<\/span>'utf-8'<\/span>,<\/span> 'gbk'<\/span>,<\/span> 'gb2312'<\/span>,<\/span> 'gb18030'<\/span>,<\/span> 'latin-1'<\/span>,<\/span> 'cp1252'<\/span>]<\/span><\/p>\n

for<\/span> enc in<\/span> encodings_to_try:<\/span>
\n try<\/span>:<\/span>
\n # \u5c1d\u8bd5\u89e3\u7801<\/span>
\n raw_data.<\/span>decode(<\/span>enc)<\/span>
\n # \u5982\u679c\u53ef\u4ee5\u89e3\u7801，\u518d\u5c1d\u8bd5\u5b8c\u6574\u89e3\u7801\u786e\u8ba4<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>enc,<\/span> errors=<\/span>'strict'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>read(<\/span>1024<\/span>)<\/span>
\n return<\/span> enc,<\/span> 0.9<\/span>
\n except<\/span> UnicodeDecodeError:<\/span>
\n continue<\/span>
\n except<\/span>:<\/span>
\n pass<\/span><\/p>\n

# \u9ed8\u8ba4\u8fd4\u56deUTF-8<\/span>
\n return<\/span> 'utf-8'<\/span>,<\/span> 0.5<\/span><\/p>\n

def<\/span> convert_encoding<\/span>(<\/span>self,<\/span> source_file:<\/span> str<\/span>,<\/span> target_file:<\/span> str<\/span>,<\/span>
\n target_encoding:<\/span> str<\/span> =<\/span> 'utf-8'<\/span>,<\/span>
\n source_encoding:<\/span> Optional[<\/span>str<\/span>]<\/span> =<\/span> None<\/span>)<\/span> –<\/span>><\/span> bool<\/span>:<\/span>
\n """
\n \u8f6c\u6362\u6587\u4ef6\u7f16\u7801<\/p>\n

\u53c2\u6570:
\n source_file: \u6e90\u6587\u4ef6
\n target_file: \u76ee\u6807\u6587\u4ef6
\n target_encoding: \u76ee\u6807\u7f16\u7801
\n source_encoding: \u6e90\u7f16\u7801（None\u5219\u81ea\u52a8\u68c0\u6d4b）<\/p>\n

\u8fd4\u56de:
\n \u662f\u5426\u6210\u529f
\n """<\/span>
\n try<\/span>:<\/span>
\n # 1. \u68c0\u6d4b\u6e90\u6587\u4ef6\u7f16\u7801<\/span>
\n if<\/span> source_encoding is<\/span> None<\/span>:<\/span>
\n source_encoding,<\/span> confidence =<\/span> self.<\/span>detect_encoding(<\/span>source_file)<\/span>
\n print<\/span>(<\/span>f"🔍 \u68c0\u6d4b\u5230\u7f16\u7801: <\/span>{<\/span>source_encoding}<\/span><\/span> (\u7f6e\u4fe1\u5ea6: <\/span>{<\/span>confidence:<\/span>.1%<\/span>}<\/span><\/span>)"<\/span><\/span>)<\/span><\/p>\n

# 2. \u8bfb\u53d6\u6e90\u6587\u4ef6<\/span>
\n with<\/span> open<\/span>(<\/span>source_file,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>source_encoding,<\/span> errors=<\/span>'replace'<\/span>)<\/span> as<\/span> f:<\/span>
\n content =<\/span> f.<\/span>read(<\/span>)<\/span><\/p>\n

# 3. \u5199\u5165\u76ee\u6807\u6587\u4ef6<\/span>
\n with<\/span> open<\/span>(<\/span>target_file,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>target_encoding)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>content)<\/span><\/p>\n

print<\/span>(<\/span>f"\u2705 \u8f6c\u6362\u6210\u529f: <\/span>{<\/span>source_file}<\/span><\/span> -> <\/span>{<\/span>target_file}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u6e90\u7f16\u7801: <\/span>{<\/span>source_encoding}<\/span><\/span> -> \u76ee\u6807\u7f16\u7801: <\/span>{<\/span>target_encoding}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

return<\/span> True<\/span><\/p>\n

except<\/span> UnicodeDecodeError as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u89e3\u7801\u5931\u8d25: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>"💡 \u5c1d\u8bd5\u4f7f\u7528\u4e0d\u540c\u7f16\u7801:"<\/span>)<\/span><\/p>\n

# \u5c1d\u8bd5\u5176\u4ed6\u7f16\u7801<\/span>
\n for<\/span> enc in<\/span> [<\/span>'gbk'<\/span>,<\/span> 'gb2312'<\/span>,<\/span> 'gb18030'<\/span>,<\/span> 'latin-1'<\/span>,<\/span> 'cp1252'<\/span>,<\/span> 'utf-8'<\/span>]<\/span>:<\/span>
\n if<\/span> enc ==<\/span> source_encoding:<\/span>
\n continue<\/span>
\n try<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>source_file,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>enc,<\/span> errors=<\/span>'replace'<\/span>)<\/span> as<\/span> f:<\/span>
\n content =<\/span> f.<\/span>read(<\/span>)<\/span><\/p>\n

with<\/span> open<\/span>(<\/span>target_file,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>target_encoding)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>content)<\/span><\/p>\n

print<\/span>(<\/span>f"\u2705 \u4f7f\u7528 <\/span>{<\/span>enc}<\/span><\/span> \u7f16\u7801\u6210\u529f\u8f6c\u6362"<\/span><\/span>)<\/span>
\n return<\/span> True<\/span><\/p>\n

except<\/span> Exception as<\/span> e2:<\/span>
\n print<\/span>(<\/span>f" \u5c1d\u8bd5 <\/span>{<\/span>enc}<\/span><\/span> \u5931\u8d25: <\/span>{<\/span>e2}<\/span><\/span>"<\/span><\/span>)<\/span>
\n continue<\/span><\/p>\n

print<\/span>(<\/span>"\u274c \u6240\u6709\u7f16\u7801\u5c1d\u8bd5\u90fd\u5931\u8d25"<\/span>)<\/span>
\n return<\/span> False<\/span><\/p>\n

except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u8f6c\u6362\u5931\u8d25: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span> False<\/span><\/p>\n

def<\/span> batch_convert<\/span>(<\/span>self,<\/span> file_patterns:<\/span> list<\/span>,<\/span> target_encoding:<\/span> str<\/span> =<\/span> 'utf-8'<\/span>)<\/span>:<\/span>
\n """
\n \u6279\u91cf\u8f6c\u6362\u6587\u4ef6\u7f16\u7801<\/p>\n

\u53c2\u6570:
\n file_patterns: \u6587\u4ef6\u6a21\u5f0f\u5217\u8868
\n target_encoding: \u76ee\u6807\u7f16\u7801
\n """<\/span>
\n import<\/span> glob<\/p>\n

for<\/span> pattern in<\/span> file_patterns:<\/span>
\n files =<\/span> glob.<\/span>glob(<\/span>pattern)<\/span>
\n for<\/span> filepath in<\/span> files:<\/span>
\n if<\/span> os.<\/span>path.<\/span>isfile(<\/span>filepath)<\/span>:<\/span>
\n print<\/span>(<\/span>f"\\\\n📁 \u5904\u7406\u6587\u4ef6: <\/span>{<\/span>filepath}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u521b\u5efa\u65b0\u6587\u4ef6\u540d<\/span>
\n dirname,<\/span> basename =<\/span> os.<\/span>path.<\/span>split(<\/span>filepath)<\/span>
\n name,<\/span> ext =<\/span> os.<\/span>path.<\/span>splitext(<\/span>basename)<\/span>
\n new_basename =<\/span> f"<\/span>{<\/span>name}<\/span><\/span>_<\/span>{<\/span>target_encoding}<\/span><\/span>{<\/span>ext}<\/span><\/span>"<\/span><\/span>
\n new_path =<\/span> os.<\/span>path.<\/span>join(<\/span>dirname,<\/span> new_basename)<\/span><\/p>\n

# \u8f6c\u6362\u7f16\u7801<\/span>
\n self.<\/span>convert_encoding(<\/span>filepath,<\/span> new_path,<\/span> target_encoding)<\/span><\/p>\n

# \u4f7f\u7528\u793a\u4f8b<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n converter =<\/span> EncodingConverter(<\/span>)<\/span><\/p>\n

# \u521b\u5efa\u6d4b\u8bd5\u6587\u4ef6<\/span>
\n test_content =<\/span> "\u4e2d\u6587\u6d4b\u8bd5\u6587\u4ef6，\u5305\u542b\u7279\u6b8a\u5b57\u7b26：\u2605\u2606\u2714\u2718\u2192\u2190\u2191\u2193"<\/span>
\n test_content_eng =<\/span> "English test file with special characters: \u2605\u2606\u2714\u2718\u2192\u2190\u2191\u2193"<\/span><\/p>\n

print<\/span>(<\/span>"🔄 \u521b\u5efa\u6d4b\u8bd5\u6587\u4ef6…"<\/span>)<\/span><\/p>\n

# \u7528\u4e0d\u540c\u7f16\u7801\u4fdd\u5b58\u6d4b\u8bd5\u6587\u4ef6<\/span>
\n test_files =<\/span> [<\/span>]<\/span><\/p>\n

# UTF-8\u6587\u4ef6<\/span>
\n filename =<\/span> "test_utf8.txt"<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>test_content)<\/span>
\n test_files.<\/span>append(<\/span>filename)<\/span>
\n print<\/span>(<\/span>f"\u2705 \u521b\u5efa\u6d4b\u8bd5\u6587\u4ef6: <\/span>{<\/span>filename}<\/span><\/span> (utf-8)"<\/span><\/span>)<\/span><\/p>\n

# UTF-8 with BOM<\/span>
\n filename =<\/span> "test_utf8_bom.txt"<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8-sig'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>test_content)<\/span>
\n test_files.<\/span>append(<\/span>filename)<\/span>
\n print<\/span>(<\/span>f"\u2705 \u521b\u5efa\u6d4b\u8bd5\u6587\u4ef6: <\/span>{<\/span>filename}<\/span><\/span> (utf-8-sig)"<\/span><\/span>)<\/span><\/p>\n

# GBK\u6587\u4ef6（\u4e2d\u6587\u7f16\u7801）<\/span>
\n try<\/span>:<\/span>
\n filename =<\/span> "test_gbk.txt"<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'gbk'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>test_content)<\/span>
\n test_files.<\/span>append(<\/span>filename)<\/span>
\n print<\/span>(<\/span>f"\u2705 \u521b\u5efa\u6d4b\u8bd5\u6587\u4ef6: <\/span>{<\/span>filename}<\/span><\/span> (gbk)"<\/span><\/span>)<\/span>
\n except<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u26a0\ufe0f \u65e0\u6cd5\u521b\u5efa GBK \u6587\u4ef6，\u53ef\u80fd\u7cfb\u7edf\u4e0d\u652f\u6301"<\/span><\/span>)<\/span><\/p>\n

print<\/span>(<\/span>f"\\\\n📊 \u5171\u521b\u5efa <\/span>{<\/span>len<\/span>(<\/span>test_files)<\/span>}<\/span><\/span> \u4e2a\u6d4b\u8bd5\u6587\u4ef6"<\/span><\/span>)<\/span><\/p>\n

# \u68c0\u6d4b\u6bcf\u4e2a\u6587\u4ef6\u7684\u7f16\u7801<\/span>
\n print<\/span>(<\/span>"\\\\n🔍 \u68c0\u6d4b\u6587\u4ef6\u7f16\u7801:"<\/span>)<\/span>
\n for<\/span> test_file in<\/span> test_files:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>test_file)<\/span>:<\/span>
\n encoding,<\/span> confidence =<\/span> converter.<\/span>detect_encoding(<\/span>test_file)<\/span>
\n print<\/span>(<\/span>f" <\/span>{<\/span>test_file}<\/span><\/span>: <\/span>{<\/span>encoding}<\/span><\/span> (<\/span>{<\/span>confidence:<\/span>.1%<\/span>}<\/span><\/span>)"<\/span><\/span>)<\/span><\/p>\n

# \u6d4b\u8bd5\u5355\u4e2a\u6587\u4ef6\u8f6c\u6362<\/span>
\n print<\/span>(<\/span>"\\\\n🔄 \u6d4b\u8bd5\u5355\u4e2a\u6587\u4ef6\u8f6c\u6362:"<\/span>)<\/span>
\n if<\/span> test_files:<\/span>
\n source_file =<\/span> test_files[<\/span>0<\/span>]<\/span>
\n target_file =<\/span> "converted_utf8.txt"<\/span><\/p>\n

if<\/span> converter.<\/span>convert_encoding(<\/span>source_file,<\/span> target_file,<\/span> 'utf-8'<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u2705 \u8f6c\u6362\u5b8c\u6210，\u76ee\u6807\u6587\u4ef6: <\/span>{<\/span>target_file}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u663e\u793a\u8f6c\u6362\u540e\u7684\u5185\u5bb9<\/span>
\n try<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>target_file,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f:<\/span>
\n content =<\/span> f.<\/span>read(<\/span>)<\/span>
\n print<\/span>(<\/span>f"📝 \u8f6c\u6362\u540e\u5185\u5bb9: <\/span>{<\/span>content[<\/span>:<\/span>50]<\/span>}<\/span><\/span>…"<\/span><\/span>)<\/span>
\n except<\/span>:<\/span>
\n print<\/span>(<\/span>"\u26a0\ufe0f \u65e0\u6cd5\u8bfb\u53d6\u8f6c\u6362\u540e\u7684\u6587\u4ef6"<\/span>)<\/span><\/p>\n

# \u6e05\u7406\u4e34\u65f6\u6587\u4ef6<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>target_file)<\/span>:<\/span>
\n os.<\/span>remove(<\/span>target_file)<\/span>
\n print<\/span>(<\/span>f"🗑\ufe0f \u5df2\u6e05\u7406\u4e34\u65f6\u6587\u4ef6: <\/span>{<\/span>target_file}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u6e05\u7406\u6d4b\u8bd5\u6587\u4ef6<\/span>
\n print<\/span>(<\/span>"\\\\n🗑\ufe0f \u6e05\u7406\u6d4b\u8bd5\u6587\u4ef6…"<\/span>)<\/span>
\n for<\/span> test_file in<\/span> test_files:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>test_file)<\/span>:<\/span>
\n os.<\/span>remove(<\/span>test_file)<\/span>
\n print<\/span>(<\/span>f" \u5df2\u5220\u9664: <\/span>{<\/span>test_file}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

print<\/span>(<\/span>"\\\\n\u2728 \u6240\u6709\u6d4b\u8bd5\u5b8c\u6210！"<\/span>)<\/span><\/p>\n

# \u663e\u793a\u4f7f\u7528\u8bf4\u660e<\/span>
\n print<\/span>(<\/span>"\\\\n📖 \u4f7f\u7528\u8bf4\u660e:"<\/span>)<\/span>
\n print<\/span>(<\/span>"1. \u521d\u59cb\u5316\u7f16\u7801\u8f6c\u6362\u5668:"<\/span>)<\/span>
\n print<\/span>(<\/span>" converter = EncodingConverter()"<\/span>)<\/span>
\n print<\/span>(<\/span>""<\/span>)<\/span>
\n print<\/span>(<\/span>"2. \u68c0\u6d4b\u6587\u4ef6\u7f16\u7801:"<\/span>)<\/span>
\n print<\/span>(<\/span>" encoding, confidence = converter.detect_encoding('filename.txt')"<\/span>)<\/span>
\n print<\/span>(<\/span>""<\/span>)<\/span>
\n print<\/span>(<\/span>"3. \u8f6c\u6362\u5355\u4e2a\u6587\u4ef6:"<\/span>)<\/span>
\n print<\/span>(<\/span>" converter.convert_encoding('source.txt', 'target.txt', 'utf-8')"<\/span>)<\/span>
\n print<\/span>(<\/span>""<\/span>)<\/span>
\n print<\/span>(<\/span>"4. \u6279\u91cf\u8f6c\u6362:"<\/span>)<\/span>
\n print<\/span>(<\/span>" converter.batch_convert(['*.txt', '*.csv'], 'utf-8')"<\/span>)<\/span><\/p>\n

3. \u4e0a\u4e0b\u6587\u7ba1\u7406\u5668\u786e\u4fdd\u7f16\u7801\u4e00\u81f4<\/h4>\n

"""
\n\u5b89\u5168\u7684\u6587\u4ef6\u64cd\u4f5c\u4e0a\u4e0b\u6587\u7ba1\u7406\u5668
\n\u786e\u4fdd\u8bfb\u5199\u64cd\u4f5c\u4f7f\u7528\u6b63\u786e\u7684\u7f16\u7801
\n"""<\/span>
\nimport<\/span> csv
\nfrom<\/span> typing import<\/span> Union,<\/span> Optional,<\/span> IO,<\/span> Any,<\/span> List
\nfrom<\/span> pathlib import<\/span> Path
\nimport<\/span> os<\/p>\n

class<\/span> SafeFileOpener<\/span>:<\/span>
\n """
\n \u5b89\u5168\u7684\u6587\u4ef6\u64cd\u4f5c\u4e0a\u4e0b\u6587\u7ba1\u7406\u5668<\/p>\n

\u81ea\u52a8\u5904\u7406\u7f16\u7801\u95ee\u9898，\u786e\u4fdd\u8bfb\u5199\u4e00\u81f4\u6027
\n """<\/span><\/p>\n

def<\/span> __init__<\/span>(<\/span>self,<\/span>
\n filename:<\/span> Union[<\/span>str<\/span>,<\/span> Path]<\/span>,<\/span>
\n mode:<\/span> str<\/span> =<\/span> 'r'<\/span>,<\/span>
\n encoding:<\/span> Optional[<\/span>str<\/span>]<\/span> =<\/span> None<\/span>,<\/span>
\n detect_encoding:<\/span> bool<\/span> =<\/span> False<\/span>,<\/span>
\n fallback_encoding:<\/span> str<\/span> =<\/span> 'utf-8'<\/span>)<\/span>:<\/span>
\n """
\n \u521d\u59cb\u5316\u6587\u4ef6\u6253\u5f00\u5668<\/p>\n

\u53c2\u6570:
\n filename: \u6587\u4ef6\u540d
\n mode: \u6253\u5f00\u6a21\u5f0f
\n encoding: \u6307\u5b9a\u7f16\u7801
\n detect_encoding: \u662f\u5426\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801
\n fallback_encoding: \u5907\u7528\u7f16\u7801
\n """<\/span>
\n self.<\/span>filename =<\/span> str<\/span>(<\/span>filename)<\/span>
\n self.<\/span>mode =<\/span> mode
\n self.<\/span>requested_encoding =<\/span> encoding
\n self.<\/span>detect_encoding =<\/span> detect_encoding
\n self.<\/span>fallback_encoding =<\/span> fallback_encoding
\n self.<\/span>file<\/span> =<\/span> None<\/span><\/p>\n

def<\/span> _determine_encoding<\/span>(<\/span>self)<\/span> –<\/span>><\/span> str<\/span>:<\/span>
\n """\u786e\u5b9a\u4f7f\u7528\u7684\u7f16\u7801"""<\/span>
\n # 1. \u5982\u679c\u6307\u5b9a\u4e86\u7f16\u7801，\u4f7f\u7528\u6307\u5b9a\u7684<\/span>
\n if<\/span> self.<\/span>requested_encoding:<\/span>
\n return<\/span> self.<\/span>requested_encoding<\/p>\n

# 2. \u5982\u679c\u662f\u5199\u5165\u6a21\u5f0f，\u4f7f\u7528utf-8<\/span>
\n if<\/span> 'w'<\/span> in<\/span> self.<\/span>mode or<\/span> 'a'<\/span> in<\/span> self.<\/span>mode:<\/span>
\n return<\/span> 'utf-8'<\/span><\/p>\n

# 3. \u5982\u679c\u662f\u8bfb\u53d6\u6a21\u5f0f，\u68c0\u6d4b\u7f16\u7801<\/span>
\n if<\/span> self.<\/span>detect_encoding and<\/span> os.<\/span>path.<\/span>exists(<\/span>self.<\/span>filename)<\/span>:<\/span>
\n try<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>self.<\/span>filename,<\/span> 'rb'<\/span>)<\/span> as<\/span> f:<\/span>
\n raw =<\/span> f.<\/span>read(<\/span>1024<\/span>)<\/span> # \u8bfb\u53d6\u66f4\u591a\u5b57\u8282\u4ee5\u63d0\u9ad8\u68c0\u6d4b\u7cbe\u5ea6<\/span><\/p>\n

# \u68c0\u67e5BOM<\/span>
\n if<\/span> raw.<\/span>startswith(<\/span>b'\\\\xef\\\\xbb\\\\xbf'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-8-sig'<\/span>
\n elif<\/span> raw.<\/span>startswith(<\/span>b'\\\\xff\\\\xfe'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-16le'<\/span>
\n elif<\/span> raw.<\/span>startswith(<\/span>b'\\\\xfe\\\\xff'<\/span>)<\/span>:<\/span>
\n return<\/span> 'utf-16be'<\/span><\/p>\n

# \u5c1d\u8bd5\u68c0\u6d4b\u5e38\u89c1\u7f16\u7801<\/span>
\n try<\/span>:<\/span>
\n raw.<\/span>decode(<\/span>'utf-8'<\/span>)<\/span>
\n return<\/span> 'utf-8'<\/span>
\n except<\/span> UnicodeDecodeError:<\/span>
\n pass<\/span><\/p>\n

try<\/span>:<\/span>
\n raw.<\/span>decode(<\/span>'gbk'<\/span>)<\/span>
\n return<\/span> 'gbk'<\/span>
\n except<\/span> UnicodeDecodeError:<\/span>
\n pass<\/span><\/p>\n

try<\/span>:<\/span>
\n raw.<\/span>decode(<\/span>'latin-1'<\/span>)<\/span>
\n return<\/span> 'latin-1'<\/span>
\n except<\/span> UnicodeDecodeError:<\/span>
\n pass<\/span><\/p>\n

except<\/span> Exception:<\/span>
\n pass<\/span><\/p>\n

# 4. \u9ed8\u8ba4\u4f7f\u7528utf-8<\/span>
\n return<\/span> self.<\/span>fallback_encoding<\/p>\n

def<\/span> __enter__<\/span>(<\/span>self)<\/span> –<\/span>><\/span> IO:<\/span>
\n """\u8fdb\u5165\u4e0a\u4e0b\u6587"""<\/span>
\n encoding =<\/span> self.<\/span>_determine_encoding(<\/span>)<\/span><\/p>\n

try<\/span>:<\/span>
\n # \u5bf9\u4e8eCSV\u6587\u4ef6，\u9700\u8981\u7279\u6b8a\u5904\u7406newline\u53c2\u6570<\/span>
\n if<\/span> self.<\/span>filename.<\/span>endswith(<\/span>(<\/span>'.csv'<\/span>,<\/span> '.tsv'<\/span>)<\/span>)<\/span>:<\/span>
\n self.<\/span>file<\/span> =<\/span> open<\/span>(<\/span>self.<\/span>filename,<\/span> self.<\/span>mode,<\/span>
\n encoding=<\/span>encoding,<\/span>
\n newline=<\/span>''<\/span>)<\/span>
\n else<\/span>:<\/span>
\n self.<\/span>file<\/span> =<\/span> open<\/span>(<\/span>self.<\/span>filename,<\/span> self.<\/span>mode,<\/span>
\n encoding=<\/span>encoding)<\/span>
\n except<\/span> UnicodeDecodeError as<\/span> e:<\/span>
\n # \u5982\u679c\u89e3\u7801\u5931\u8d25，\u5c1d\u8bd5\u4f7f\u7528\u5907\u9009\u7f16\u7801<\/span>
\n if<\/span> encoding !=<\/span> self.<\/span>fallback_encoding:<\/span>
\n print<\/span>(<\/span>f"\u26a0\ufe0f \u7f16\u7801 <\/span>{<\/span>encoding}<\/span><\/span> \u89e3\u7801\u5931\u8d25，\u5c1d\u8bd5\u4f7f\u7528 <\/span>{<\/span>self.<\/span>fallback_encoding}<\/span><\/span>"<\/span><\/span>)<\/span>
\n encoding =<\/span> self.<\/span>fallback_encoding
\n if<\/span> self.<\/span>filename.<\/span>endswith(<\/span>(<\/span>'.csv'<\/span>,<\/span> '.tsv'<\/span>)<\/span>)<\/span>:<\/span>
\n self.<\/span>file<\/span> =<\/span> open<\/span>(<\/span>self.<\/span>filename,<\/span> self.<\/span>mode,<\/span>
\n encoding=<\/span>encoding,<\/span>
\n newline=<\/span>''<\/span>)<\/span>
\n else<\/span>:<\/span>
\n self.<\/span>file<\/span> =<\/span> open<\/span>(<\/span>self.<\/span>filename,<\/span> self.<\/span>mode,<\/span>
\n encoding=<\/span>encoding)<\/span>
\n else<\/span>:<\/span>
\n raise<\/span><\/p>\n

# \u5b58\u50a8\u5b9e\u9645\u4f7f\u7528\u7684\u7f16\u7801<\/span>
\n self.<\/span>actual_encoding =<\/span> encoding<\/p>\n

if<\/span> 'w'<\/span> in<\/span> self.<\/span>mode or<\/span> 'a'<\/span> in<\/span> self.<\/span>mode:<\/span>
\n print<\/span>(<\/span>f"📝 \u5199\u5165\u6587\u4ef6: <\/span>{<\/span>self.<\/span>filename}<\/span><\/span> (\u7f16\u7801: <\/span>{<\/span>encoding}<\/span><\/span>)"<\/span><\/span>)<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>f"📖 \u8bfb\u53d6\u6587\u4ef6: <\/span>{<\/span>self.<\/span>filename}<\/span><\/span> (\u7f16\u7801: <\/span>{<\/span>encoding}<\/span><\/span>)"<\/span><\/span>)<\/span><\/p>\n

return<\/span> self.<\/span>file<\/span><\/p>\n

def<\/span> __exit__<\/span>(<\/span>self,<\/span> exc_type,<\/span> exc_val,<\/span> exc_tb)<\/span>:<\/span>
\n """\u9000\u51fa\u4e0a\u4e0b\u6587"""<\/span>
\n if<\/span> self.<\/span>file<\/span>:<\/span>
\n self.<\/span>file<\/span>.<\/span>close(<\/span>)<\/span><\/p>\n

if<\/span> exc_type is<\/span> None<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u2705 \u6587\u4ef6\u64cd\u4f5c\u5b8c\u6210: <\/span>{<\/span>self.<\/span>filename}<\/span><\/span>"<\/span><\/span>)<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u274c \u6587\u4ef6\u64cd\u4f5c\u5f02\u5e38: <\/span>{<\/span>self.<\/span>filename}<\/span><\/span> – <\/span>{<\/span>exc_val}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u8fd4\u56deFalse\u8ba9\u5f02\u5e38\u7ee7\u7eed\u4f20\u64ad<\/span>
\n return<\/span> False<\/span><\/p>\n

def<\/span> read_file_safely<\/span>(<\/span>filename:<\/span> str<\/span>,<\/span> **<\/span>kwargs)<\/span> –<\/span>><\/span> str<\/span>:<\/span>
\n """\u5b89\u5168\u8bfb\u53d6\u6587\u4ef6"""<\/span>
\n with<\/span> SafeFileOpener(<\/span>filename,<\/span> 'r'<\/span>,<\/span> **<\/span>kwargs)<\/span> as<\/span> f:<\/span>
\n return<\/span> f.<\/span>read(<\/span>)<\/span><\/p>\n

def<\/span> write_file_safely<\/span>(<\/span>filename:<\/span> str<\/span>,<\/span> content:<\/span> str<\/span>,<\/span> **<\/span>kwargs)<\/span>:<\/span>
\n """\u5b89\u5168\u5199\u5165\u6587\u4ef6"""<\/span>
\n with<\/span> SafeFileOpener(<\/span>filename,<\/span> 'w'<\/span>,<\/span> **<\/span>kwargs)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>content)<\/span><\/p>\n

def<\/span> write_csv_safely<\/span>(<\/span>filename:<\/span> str<\/span>,<\/span> data:<\/span> List[<\/span>List[<\/span>Any]<\/span>]<\/span>,<\/span> headers:<\/span> List[<\/span>str<\/span>]<\/span> =<\/span> None<\/span>,<\/span> **<\/span>kwargs)<\/span>:<\/span>
\n """\u5b89\u5168\u5199\u5165CSV\u6587\u4ef6"""<\/span>
\n with<\/span> SafeFileOpener(<\/span>filename,<\/span> 'w'<\/span>,<\/span> **<\/span>kwargs)<\/span> as<\/span> f:<\/span>
\n writer =<\/span> csv.<\/span>writer(<\/span>f)<\/span>
\n if<\/span> headers:<\/span>
\n writer.<\/span>writerow(<\/span>headers)<\/span>
\n writer.<\/span>writerows(<\/span>data)<\/span><\/p>\n

def<\/span> read_csv_safely<\/span>(<\/span>filename:<\/span> str<\/span>,<\/span> **<\/span>kwargs)<\/span> –<\/span>><\/span> List[<\/span>List[<\/span>str<\/span>]<\/span>]<\/span>:<\/span>
\n """\u5b89\u5168\u8bfb\u53d6CSV\u6587\u4ef6"""<\/span>
\n with<\/span> SafeFileOpener(<\/span>filename,<\/span> 'r'<\/span>,<\/span> **<\/span>kwargs)<\/span> as<\/span> f:<\/span>
\n reader =<\/span> csv.<\/span>reader(<\/span>f)<\/span>
\n return<\/span> list<\/span>(<\/span>reader)<\/span><\/p>\n

class<\/span> EncodingConverter<\/span>:<\/span>
\n """\u7f16\u7801\u8f6c\u6362\u5668"""<\/span><\/p>\n

@staticmethod<\/span>
\n def<\/span> convert_encoding<\/span>(<\/span>input_file:<\/span> str<\/span>,<\/span> output_file:<\/span> str<\/span>,<\/span>
\n target_encoding:<\/span> str<\/span> =<\/span> 'utf-8'<\/span>,<\/span>
\n source_encoding:<\/span> Optional[<\/span>str<\/span>]<\/span> =<\/span> None<\/span>)<\/span>:<\/span>
\n """
\n \u8f6c\u6362\u6587\u4ef6\u7f16\u7801<\/p>\n

\u53c2\u6570:
\n input_file: \u8f93\u5165\u6587\u4ef6
\n output_file: \u8f93\u51fa\u6587\u4ef6
\n target_encoding: \u76ee\u6807\u7f16\u7801
\n source_encoding: \u6e90\u7f16\u7801（None\u5219\u81ea\u52a8\u68c0\u6d4b）
\n """<\/span>
\n try<\/span>:<\/span>
\n # \u8bfb\u53d6\u6e90\u6587\u4ef6<\/span>
\n with<\/span> SafeFileOpener(<\/span>input_file,<\/span> 'r'<\/span>,<\/span>
\n encoding=<\/span>source_encoding,<\/span>
\n detect_encoding=<\/span>True<\/span>)<\/span> as<\/span> f:<\/span>
\n content =<\/span> f.<\/span>read(<\/span>)<\/span><\/p>\n

# \u5199\u5165\u76ee\u6807\u6587\u4ef6<\/span>
\n with<\/span> SafeFileOpener(<\/span>output_file,<\/span> 'w'<\/span>,<\/span>
\n encoding=<\/span>target_encoding)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>content)<\/span><\/p>\n

print<\/span>(<\/span>f"🔄 \u8f6c\u6362\u5b8c\u6210: <\/span>{<\/span>input_file}<\/span><\/span> -> <\/span>{<\/span>output_file}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u6e90\u7f16\u7801: <\/span>{<\/span>f.<\/span>actual_encoding if<\/span> hasattr<\/span>(<\/span>f,<\/span> 'actual_encoding'<\/span>)<\/span> else<\/span> 'unknown'<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u76ee\u6807\u7f16\u7801: <\/span>{<\/span>target_encoding}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u8f6c\u6362\u5931\u8d25 <\/span>{<\/span>input_file}<\/span><\/span>: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u4f7f\u7528\u793a\u4f8b<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n # 1. \u5b89\u5168\u5199\u5165\u6587\u4ef6<\/span>
\n data =<\/span> [<\/span>
\n [<\/span>"\u9879\u76ee"<\/span>,<\/span> "\u4ef7\u683c"<\/span>,<\/span> "\u6570\u91cf"<\/span>]<\/span>,<\/span>
\n [<\/span>"\u82f9\u679c"<\/span>,<\/span> 5.5<\/span>,<\/span> 10<\/span>]<\/span>,<\/span>
\n [<\/span>"\u9999\u8549"<\/span>,<\/span> 3.2<\/span>,<\/span> 20<\/span>]<\/span>,<\/span>
\n [<\/span>"\u6a59\u5b50"<\/span>,<\/span> 4.8<\/span>,<\/span> 15<\/span>]<\/span>
\n ]<\/span><\/p>\n

# \u5199\u5165\u4e0d\u540c\u7f16\u7801\u7684\u6587\u4ef6<\/span>
\n print<\/span>(<\/span>"📤 \u5199\u5165\u4e0d\u540c\u7f16\u7801\u7684\u6587\u4ef6:"<\/span>)<\/span>
\n write_csv_safely(<\/span>'data_utf8.csv'<\/span>,<\/span> data,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span>
\n write_csv_safely(<\/span>'data_gbk.csv'<\/span>,<\/span> data,<\/span> encoding=<\/span>'gbk'<\/span>)<\/span>
\n write_csv_safely(<\/span>'data_utf8_sig.csv'<\/span>,<\/span> data,<\/span> encoding=<\/span>'utf-8-sig'<\/span>)<\/span><\/p>\n

# 2. \u5b89\u5168\u8bfb\u53d6\u6587\u4ef6（\u6307\u5b9a\u7f16\u7801）<\/span>
\n print<\/span>(<\/span>"\\\\n📥 \u8bfb\u53d6\u5e76\u9a8c\u8bc1\u6587\u4ef6（\u6307\u5b9a\u7f16\u7801）:"<\/span>)<\/span>
\n for<\/span> filename,<\/span> encoding in<\/span> [<\/span>
\n (<\/span>'data_utf8.csv'<\/span>,<\/span> 'utf-8'<\/span>)<\/span>,<\/span>
\n (<\/span>'data_gbk.csv'<\/span>,<\/span> 'gbk'<\/span>)<\/span>,<\/span>
\n (<\/span>'data_utf8_sig.csv'<\/span>,<\/span> 'utf-8-sig'<\/span>)<\/span>
\n ]<\/span>:<\/span>
\n try<\/span>:<\/span>
\n content =<\/span> read_file_safely(<\/span>filename,<\/span> encoding=<\/span>encoding)<\/span>
\n print<\/span>(<\/span>f"\u2705 \u6210\u529f\u8bfb\u53d6: <\/span>{<\/span>filename}<\/span><\/span> (<\/span>{<\/span>len<\/span>(<\/span>content)<\/span>}<\/span><\/span> \u5b57\u7b26)"<\/span><\/span>)<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u8bfb\u53d6\u5931\u8d25 <\/span>{<\/span>filename}<\/span><\/span>: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# 3. \u5b89\u5168\u8bfb\u53d6\u6587\u4ef6（\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801）<\/span>
\n print<\/span>(<\/span>"\\\\n📥 \u8bfb\u53d6\u5e76\u9a8c\u8bc1\u6587\u4ef6（\u81ea\u52a8\u68c0\u6d4b\u7f16\u7801）:"<\/span>)<\/span>
\n for<\/span> filename in<\/span> [<\/span>'data_utf8.csv'<\/span>,<\/span> 'data_gbk.csv'<\/span>,<\/span> 'data_utf8_sig.csv'<\/span>]<\/span>:<\/span>
\n try<\/span>:<\/span>
\n content =<\/span> read_file_safely(<\/span>filename,<\/span> detect_encoding=<\/span>True<\/span>)<\/span>
\n print<\/span>(<\/span>f"\u2705 \u6210\u529f\u8bfb\u53d6: <\/span>{<\/span>filename}<\/span><\/span> (<\/span>{<\/span>len<\/span>(<\/span>content)<\/span>}<\/span><\/span> \u5b57\u7b26)"<\/span><\/span>)<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u8bfb\u53d6\u5931\u8d25 <\/span>{<\/span>filename}<\/span><\/span>: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# 4. \u6279\u91cf\u8f6c\u6362\u7f16\u7801<\/span>
\n print<\/span>(<\/span>"\\\\n🔄 \u6279\u91cf\u8f6c\u6362\u7f16\u7801:"<\/span>)<\/span>
\n converter =<\/span> EncodingConverter(<\/span>)<\/span>
\n for<\/span> filename in<\/span> [<\/span>'data_utf8.csv'<\/span>,<\/span> 'data_gbk.csv'<\/span>,<\/span> 'data_utf8_sig.csv'<\/span>]<\/span>:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>filename)<\/span>:<\/span>
\n new_name =<\/span> filename.<\/span>replace(<\/span>'.csv'<\/span>,<\/span> '_converted.csv'<\/span>)<\/span>
\n converter.<\/span>convert_encoding(<\/span>filename,<\/span> new_name,<\/span> 'utf-8'<\/span>)<\/span><\/p>\n

# 5. \u8bfb\u53d6\u8f6c\u6362\u540e\u7684\u6587\u4ef6<\/span>
\n print<\/span>(<\/span>"\\\\n📥 \u9a8c\u8bc1\u8f6c\u6362\u540e\u7684\u6587\u4ef6:"<\/span>)<\/span>
\n for<\/span> filename in<\/span> [<\/span>'data_utf8_converted.csv'<\/span>,<\/span>
\n 'data_gbk_converted.csv'<\/span>,<\/span>
\n 'data_utf8_sig_converted.csv'<\/span>]<\/span>:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>filename)<\/span>:<\/span>
\n try<\/span>:<\/span>
\n rows =<\/span> read_csv_safely(<\/span>filename)<\/span>
\n print<\/span>(<\/span>f"\u2705 <\/span>{<\/span>filename}<\/span><\/span>: <\/span>{<\/span>len<\/span>(<\/span>rows)<\/span>}<\/span><\/span> \u884c"<\/span><\/span>)<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f"\u274c \u8bfb\u53d6\u5931\u8d25 <\/span>{<\/span>filename}<\/span><\/span>: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u6e05\u7406<\/span>
\n print<\/span>(<\/span>"\\\\n🧹 \u6e05\u7406\u4e34\u65f6\u6587\u4ef6…"<\/span>)<\/span>
\n for<\/span> f in<\/span> [<\/span>'data_utf8.csv'<\/span>,<\/span> 'data_gbk.csv'<\/span>,<\/span> 'data_utf8_sig.csv'<\/span>,<\/span>
\n 'data_utf8_converted.csv'<\/span>,<\/span> 'data_gbk_converted.csv'<\/span>,<\/span> 'data_utf8_sig_converted.csv'<\/span>]<\/span>:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>f)<\/span>:<\/span>
\n os.<\/span>remove(<\/span>f)<\/span>
\n print<\/span>(<\/span>f"🗑\ufe0f \u5df2\u5220\u9664: <\/span>{<\/span>f}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

4. \u4fee\u590d\u539f\u95ee\u9898\u7684\u5b8c\u6574\u89e3\u51b3\u65b9\u6848<\/h4>\n

"""
\n\u89e3\u51b3\u539f\u95ee\u9898：\u751f\u6210WC-Co\u6570\u636e\u5e76\u786e\u4fdd\u7f16\u7801\u4e00\u81f4
\n\u8fd9\u662f\u5bf9\u539f\u4ee3\u7801\u7684\u5b8c\u6574\u4fee\u590d
\n"""<\/span>
\nimport<\/span> csv
\nimport<\/span> random
\nfrom<\/span> datetime import<\/span> datetime<\/p>\n

def<\/span> generate_wc_data_with_fixed_encoding<\/span>(<\/span>)<\/span>:<\/span>
\n """
\n \u751f\u6210WC-Co\u6570\u636e，\u4fee\u590d\u7f16\u7801\u95ee\u9898<\/p>\n

\u539f\u95ee\u9898：\u4e24\u4e2a\u6587\u4ef6\u7f16\u7801\u4e0d\u4e00\u81f4
\n \u89e3\u51b3\u65b9\u6848：\u663e\u5f0f\u6307\u5b9a\u7f16\u7801\u53c2\u6570
\n """<\/span><\/p>\n

# \u5b9a\u4e49\u53c2\u6570\u8303\u56f4<\/span>
\n wc_range =<\/span> (<\/span>0.2<\/span>,<\/span> 0.8<\/span>)<\/span> # WC\u6676\u7c92\u5c3a\u5bf8 (\u03bcm)<\/span>
\n cr3c2_range =<\/span> (<\/span>0.1<\/span>,<\/span> 0.8<\/span>)<\/span> # Cr\u2083C\u2082\u542b\u91cf (%)<\/span>
\n vc_range =<\/span> (<\/span>0.1<\/span>,<\/span> 0.7<\/span>)<\/span> # VC\u542b\u91cf (%)<\/span>
\n co_range =<\/span> (<\/span>5.0<\/span>,<\/span> 15.0<\/span>)<\/span> # Co\u542b\u91cf (%)<\/span>
\n hv_range =<\/span> (<\/span>1200<\/span>,<\/span> 1700<\/span>)<\/span> # \u7ef4\u6c0f\u786c\u5ea6 (HV)<\/span>
\n kic_range =<\/span> (<\/span>8.0<\/span>,<\/span> 15.0<\/span>)<\/span> # \u65ad\u88c2\u97e7\u6027 (MPa\u00b7m^0.5)<\/span>
\n tres_range =<\/span> (<\/span>1800<\/span>,<\/span> 2900<\/span>)<\/span> # \u6297\u5f2f\u5f3a\u5ea6 (MPa)<\/span>
\n pos_range =<\/span> (<\/span>1.33<\/span>,<\/span> 5.0<\/span>)<\/span> # \u5b54\u4f4d\u7cbe\u5ea6 (mm)<\/span><\/p>\n

# \u751f\u6210\u6570\u636e<\/span>
\n data =<\/span> [<\/span>]<\/span>
\n for<\/span> i in<\/span> range<\/span>(<\/span>56<\/span>)<\/span>:<\/span>
\n wc =<\/span> random.<\/span>uniform(<\/span>*<\/span>wc_range)<\/span>
\n co =<\/span> random.<\/span>uniform(<\/span>*<\/span>co_range)<\/span><\/p>\n

# \u7269\u7406\u76f8\u5173\u6027\u6a21\u578b<\/span>
\n hardness_base =<\/span> 1700<\/span> –<\/span> 600<\/span> *<\/span> (<\/span>wc –<\/span> 0.2<\/span>)<\/span> \/<\/span> 0.6<\/span>
\n hardness =<\/span> hardness_base –<\/span> 20<\/span> *<\/span> (<\/span>co –<\/span> 5<\/span>)<\/span> \/<\/span> 10<\/span>
\n toughness =<\/span> 8<\/span> +<\/span> 7<\/span> *<\/span> (<\/span>co –<\/span> 5<\/span>)<\/span> \/<\/span> 10<\/span> –<\/span> 2<\/span> *<\/span> (<\/span>wc –<\/span> 0.2<\/span>)<\/span> \/<\/span> 0.6<\/span>
\n strength =<\/span> 1800<\/span> +<\/span> 1100<\/span> *<\/span> (<\/span>0.8<\/span> –<\/span> wc)<\/span> \/<\/span> 0.6<\/span> –<\/span> 100<\/span> *<\/span> (<\/span>co –<\/span> 5<\/span>)<\/span> \/<\/span> 10<\/span><\/p>\n

cr3c2 =<\/span> random.<\/span>uniform(<\/span>*<\/span>cr3c2_range)<\/span>
\n vc =<\/span> random.<\/span>uniform(<\/span>*<\/span>vc_range)<\/span><\/p>\n

hardness +=<\/span> 50<\/span> *<\/span> (<\/span>cr3c2 +<\/span> vc)<\/span> \/<\/span> 1.5<\/span>
\n toughness -=<\/span> 1.5<\/span> *<\/span> (<\/span>cr3c2 +<\/span> vc)<\/span> \/<\/span> 1.5<\/span>
\n accuracy =<\/span> random.<\/span>uniform(<\/span>*<\/span>pos_range)<\/span><\/p>\n

# \u6dfb\u52a0\u566a\u58f0<\/span>
\n hardness *=<\/span> random.<\/span>uniform(<\/span>0.95<\/span>,<\/span> 1.05<\/span>)<\/span>
\n toughness *=<\/span> random.<\/span>uniform(<\/span>0.95<\/span>,<\/span> 1.05<\/span>)<\/span>
\n strength *=<\/span> random.<\/span>uniform(<\/span>0.95<\/span>,<\/span> 1.05<\/span>)<\/span>
\n accuracy *=<\/span> random.<\/span>uniform(<\/span>0.95<\/span>,<\/span> 1.05<\/span>)<\/span><\/p>\n

# \u786e\u4fdd\u5728\u8303\u56f4\u5185<\/span>
\n wc =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>wc_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>wc_range[<\/span>1<\/span>]<\/span>,<\/span> wc)<\/span>)<\/span>,<\/span> 2<\/span>)<\/span>
\n cr3c2 =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>cr3c2_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>cr3c2_range[<\/span>1<\/span>]<\/span>,<\/span> cr3c2)<\/span>)<\/span>,<\/span> 2<\/span>)<\/span>
\n vc =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>vc_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>vc_range[<\/span>1<\/span>]<\/span>,<\/span> vc)<\/span>)<\/span>,<\/span> 2<\/span>)<\/span>
\n co =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>co_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>co_range[<\/span>1<\/span>]<\/span>,<\/span> co)<\/span>)<\/span>,<\/span> 2<\/span>)<\/span>
\n hardness =<\/span> int<\/span>(<\/span>max<\/span>(<\/span>hv_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>hv_range[<\/span>1<\/span>]<\/span>,<\/span> hardness)<\/span>)<\/span>)<\/span>
\n toughness =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>kic_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>kic_range[<\/span>1<\/span>]<\/span>,<\/span> toughness)<\/span>)<\/span>,<\/span> 2<\/span>)<\/span>
\n strength =<\/span> int<\/span>(<\/span>max<\/span>(<\/span>tres_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>tres_range[<\/span>1<\/span>]<\/span>,<\/span> strength)<\/span>)<\/span>)<\/span>
\n accuracy =<\/span> round<\/span>(<\/span>max<\/span>(<\/span>pos_range[<\/span>0<\/span>]<\/span>,<\/span> min<\/span>(<\/span>pos_range[<\/span>1<\/span>]<\/span>,<\/span> accuracy)<\/span>)<\/span>,<\/span> 4<\/span>)<\/span><\/p>\n

data.<\/span>append(<\/span>[<\/span>wc,<\/span> cr3c2,<\/span> vc,<\/span> co,<\/span> hardness,<\/span> toughness,<\/span> strength,<\/span> accuracy]<\/span>)<\/span><\/p>\n

# 🎯 \u5173\u952e\u4fee\u590d：\u663e\u5f0f\u6307\u5b9a\u7f16\u7801！<\/span>
\n # \u4f7f\u7528utf-8-sig\u786e\u4fddWindows Excel\u517c\u5bb9\u6027<\/span>
\n encoding_to_use =<\/span> 'utf-8-sig'<\/span><\/p>\n

# \u4fdd\u5b58\u5e26\u8868\u5934\u7684\u6587\u4ef6<\/span>
\n header_file =<\/span> 'wc_co_data_fixed.csv'<\/span>
\n with<\/span> open<\/span>(<\/span>header_file,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>encoding_to_use,<\/span> newline=<\/span>''<\/span>)<\/span> as<\/span> f:<\/span>
\n writer =<\/span> csv.<\/span>writer(<\/span>f)<\/span>
\n writer.<\/span>writerow(<\/span>[<\/span>'WC\u6676\u7c92\u5c3a\u5bf8(\u03bcm)'<\/span>,<\/span> 'Cr3C2\u542b\u91cf(%)'<\/span>,<\/span> 'VC\u542b\u91cf(%)'<\/span>,<\/span> 'Co\u542b\u91cf(%)'<\/span>,<\/span>
\n '\u7ef4\u6c0f\u786c\u5ea6(HV)'<\/span>,<\/span> '\u65ad\u88c2\u97e7\u6027(MPa\u00b7m^0.5)'<\/span>,<\/span>
\n '\u6297\u5f2f\u5f3a\u5ea6(MPa)'<\/span>,<\/span> '\u5b54\u4f4d\u7cbe\u5ea6(mm)'<\/span>]<\/span>)<\/span>
\n writer.<\/span>writerows(<\/span>data)<\/span><\/p>\n

# \u4fdd\u5b58\u7eaf\u6570\u636e\u7248\u672c<\/span>
\n raw_file =<\/span> 'wc_co_data_raw_fixed.csv'<\/span>
\n with<\/span> open<\/span>(<\/span>raw_file,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>encoding_to_use,<\/span> newline=<\/span>''<\/span>)<\/span> as<\/span> f:<\/span>
\n for<\/span> row in<\/span> data:<\/span>
\n f.<\/span>write(<\/span>','<\/span>.<\/span>join(<\/span>str<\/span>(<\/span>x)<\/span> for<\/span> x in<\/span> row)<\/span> +<\/span> '\\\\n'<\/span>)<\/span><\/p>\n

# \u9a8c\u8bc1\u7f16\u7801<\/span>
\n print<\/span>(<\/span>"="<\/span>*<\/span>60<\/span>)<\/span>
\n print<\/span>(<\/span>"🔧 \u7f16\u7801\u95ee\u9898\u4fee\u590d\u9a8c\u8bc1"<\/span>)<\/span>
\n print<\/span>(<\/span>"="<\/span>*<\/span>60<\/span>)<\/span><\/p>\n

for<\/span> filename in<\/span> [<\/span>header_file,<\/span> raw_file]<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'rb'<\/span>)<\/span> as<\/span> f:<\/span>
\n first_bytes =<\/span> f.<\/span>read(<\/span>3<\/span>)<\/span>
\n if<\/span> first_bytes ==<\/span> b'\\\\xef\\\\xbb\\\\xbf'<\/span>:<\/span>
\n encoding =<\/span> "UTF-8 with BOM (Excel\u517c\u5bb9)"<\/span>
\n else<\/span>:<\/span>
\n encoding =<\/span> "\u672a\u77e5（\u53ef\u80fd\u65e0BOM）"<\/span><\/p>\n

with<\/span> open<\/span>(<\/span>filename,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>'utf-8-sig'<\/span>)<\/span> as<\/span> f:<\/span>
\n lines =<\/span> f.<\/span>readlines(<\/span>)<\/span><\/p>\n

print<\/span>(<\/span>f"\\\\n📁 \u6587\u4ef6: <\/span>{<\/span>filename}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u7f16\u7801: <\/span>{<\/span>encoding}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u884c\u6570: <\/span>{<\/span>len<\/span>(<\/span>lines)<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u5927\u5c0f: <\/span>{<\/span>os.<\/span>path.<\/span>getsize(<\/span>filename)<\/span>}<\/span><\/span> \u5b57\u8282"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u793a\u4f8b: <\/span>{<\/span>lines[<\/span>0<\/span>]<\/span>[<\/span>:<\/span>50]<\/span>}<\/span><\/span>…"<\/span><\/span> if<\/span> lines[<\/span>0<\/span>]<\/span> else<\/span> " \u793a\u4f8b: (\u7a7a\u6587\u4ef6)"<\/span>)<\/span><\/p>\n

print<\/span>(<\/span>"\\\\n"<\/span> +<\/span> "="<\/span>*<\/span>60<\/span>)<\/span>
\n print<\/span>(<\/span>"\u2705 \u4fee\u590d\u5b8c\u6210！\u4e24\u4e2a\u6587\u4ef6\u73b0\u5728\u4f7f\u7528\u76f8\u540c\u7684\u7f16\u7801"<\/span>)<\/span>
\n print<\/span>(<\/span>" 📄 wc_co_data_fixed.csv – \u5e26\u8868\u5934\u7248\u672c"<\/span>)<\/span>
\n print<\/span>(<\/span>" 📄 wc_co_data_raw_fixed.csv – \u7eaf\u6570\u636e\u7248\u672c"<\/span>)<\/span>
\n print<\/span>(<\/span>f" 🔤 \u7edf\u4e00\u7f16\u7801: <\/span>{<\/span>encoding_to_use}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>"="<\/span>*<\/span>60<\/span>)<\/span><\/p>\n

return<\/span> data,<\/span> header_file,<\/span> raw_file<\/p>\n

# \u8fd0\u884c\u793a\u4f8b<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n import<\/span> os<\/p>\n

# \u6e05\u7406\u53ef\u80fd\u5b58\u5728\u7684\u65e7\u6587\u4ef6<\/span>
\n for<\/span> f in<\/span> [<\/span>'wc_co_data_fixed.csv'<\/span>,<\/span> 'wc_co_data_raw_fixed.csv'<\/span>]<\/span>:<\/span>
\n if<\/span> os.<\/span>path.<\/span>exists(<\/span>f)<\/span>:<\/span>
\n os.<\/span>remove(<\/span>f)<\/span><\/p>\n

# \u751f\u6210\u6570\u636e<\/span>
\n data,<\/span> header_file,<\/span> raw_file =<\/span> generate_wc_data_with_fixed_encoding(<\/span>)<\/span><\/p>\n

# \u663e\u793a\u524d5\u884c\u6570\u636e<\/span>
\n print<\/span>(<\/span>"\\\\n📊 \u751f\u6210\u7684\u6570\u636e\u793a\u4f8b（\u524d5\u884c）:"<\/span>)<\/span>
\n print<\/span>(<\/span>"-"<\/span>*<\/span>100<\/span>)<\/span>
\n print<\/span>(<\/span>"WC(\u03bcm) | Cr3C2(%) | VC(%) | Co(%) | \u786c\u5ea6(HV) | \u97e7\u6027(MPa\u00b7\u221am) | \u5f3a\u5ea6(MPa) | \u7cbe\u5ea6(mm)"<\/span>)<\/span>
\n print<\/span>(<\/span>"-"<\/span>*<\/span>100<\/span>)<\/span>
\n for<\/span> i in<\/span> range<\/span>(<\/span>min<\/span>(<\/span>5<\/span>,<\/span> len<\/span>(<\/span>data)<\/span>)<\/span>)<\/span>:<\/span>
\n row =<\/span> data[<\/span>i]<\/span>
\n print<\/span>(<\/span>f"<\/span>{<\/span>row[<\/span>0<\/span>]<\/span>:<\/span>7.2f<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>1<\/span>]<\/span>:<\/span>8.2f<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>2<\/span>]<\/span>:<\/span>5.2f<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>3<\/span>]<\/span>:<\/span>5.1f<\/span>}<\/span><\/span> | "<\/span><\/span>
\n f"<\/span>{<\/span>row[<\/span>4<\/span>]<\/span>:<\/span>8d<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>5<\/span>]<\/span>:<\/span>12.2f<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>6<\/span>]<\/span>:<\/span>8d<\/span>}<\/span><\/span> | <\/span>{<\/span>row[<\/span>7<\/span>]<\/span>:<\/span>7.4f<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

🎪 \u7f16\u7801\u9009\u62e9\u51b3\u7b56\u6307\u5357<\/h3>\n

\u7406\u89e3\u4e0d\u540c\u7f16\u7801\u7684\u9002\u7528\u573a\u666f\u662f\u89e3\u51b3\u7f16\u7801\u95ee\u9898\u7684\u5173\u952e\u3002\u6bcf\u4e2a\u7f16\u7801\u65b9\u6848\u90fd\u6709\u5176\u7279\u5b9a\u7684\u4f7f\u7528\u573a\u666f：<\/p>\n

"""
\n\u7f16\u7801\u9009\u62e9\u667a\u80fd\u51b3\u7b56\u7cfb\u7edf
\n\u6839\u636e\u9700\u6c42\u81ea\u52a8\u9009\u62e9\u6700\u4f73\u7f16\u7801
\n"""<\/span>
\ndef<\/span> encoding_decision_system<\/span>(<\/span>requirements:<\/span> dict<\/span>)<\/span> –<\/span>><\/span> str<\/span>:<\/span>
\n """
\n \u6839\u636e\u9700\u6c42\u9009\u62e9\u6700\u4f73\u7f16\u7801<\/p>\n

\u53c2\u6570:
\n requirements: \u9700\u6c42\u5b57\u5178，\u5305\u542b：
\n – platform: \u76ee\u6807\u5e73\u53f0 ('windows', 'linux', 'mac', 'web', 'all')
\n – contains_chinese: \u662f\u5426\u5305\u542b\u4e2d\u6587
\n – excel_compatible: \u662f\u5426\u9700\u8981Excel\u517c\u5bb9
\n – file_size_matters: \u6587\u4ef6\u5927\u5c0f\u662f\u5426\u91cd\u8981
\n – legacy_system: \u662f\u5426\u7528\u4e8e\u65e7\u7cfb\u7edf<\/p>\n

\u8fd4\u56de:
\n \u63a8\u8350\u7684\u7f16\u7801
\n """<\/span><\/p>\n

encoding_rules =<\/span> [<\/span>
\n {<\/span>
\n 'condition'<\/span>:<\/span> lambda<\/span> r:<\/span> r.<\/span>get(<\/span>'excel_compatible'<\/span>,<\/span> False<\/span>)<\/span> and<\/span> r.<\/span>get(<\/span>'platform'<\/span>)<\/span> in<\/span> [<\/span>'windows'<\/span>,<\/span> 'all'<\/span>]<\/span>,<\/span>
\n 'encoding'<\/span>:<\/span> 'utf-8-sig'<\/span>,<\/span>
\n 'reason'<\/span>:<\/span> 'Excel\u5728Windows\u4e0a\u9700\u8981BOM\u6765\u6b63\u786e\u8bc6\u522bUTF-8'<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'condition'<\/span>:<\/span> lambda<\/span> r:<\/span> r.<\/span>get(<\/span>'platform'<\/span>)<\/span> ==<\/span> 'web'<\/span> or<\/span> r.<\/span>get(<\/span>'platform'<\/span>)<\/span> ==<\/span> 'all'<\/span>,<\/span>
\n 'encoding'<\/span>:<\/span> 'utf-8'<\/span>,<\/span>
\n 'reason'<\/span>:<\/span> 'Web\u6807\u51c6，\u8de8\u5e73\u53f0\u517c\u5bb9\u6027\u6700\u597d'<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'condition'<\/span>:<\/span> lambda<\/span> r:<\/span> r.<\/span>get(<\/span>'contains_chinese'<\/span>,<\/span> True<\/span>)<\/span> and<\/span> r.<\/span>get(<\/span>'legacy_system'<\/span>,<\/span> False<\/span>)<\/span>,<\/span>
\n 'encoding'<\/span>:<\/span> 'gbk'<\/span>,<\/span>
\n 'reason'<\/span>:<\/span> '\u65e7\u7248\u4e2d\u6587Windows\u7cfb\u7edf\u517c\u5bb9'<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'condition'<\/span>:<\/span> lambda<\/span> r:<\/span> r.<\/span>get(<\/span>'file_size_matters'<\/span>,<\/span> False<\/span>)<\/span>,<\/span>
\n 'encoding'<\/span>:<\/span> 'utf-8'<\/span>,<\/span>
\n 'reason'<\/span>:<\/span> '\u65e0BOM，\u6587\u4ef6\u66f4\u5c0f'<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'condition'<\/span>:<\/span> lambda<\/span> r:<\/span> r.<\/span>get(<\/span>'contains_chinese'<\/span>,<\/span> False<\/span>)<\/span> and<\/span> not<\/span> r.<\/span>get(<\/span>'legacy_system'<\/span>,<\/span> False<\/span>)<\/span>,<\/span>
\n 'encoding'<\/span>:<\/span> 'utf-8'<\/span>,<\/span>
\n 'reason'<\/span>:<\/span> '\u73b0\u4ee3\u4e2d\u6587\u5e94\u7528\u6807\u51c6'<\/span>
\n }<\/span>
\n ]<\/span><\/p>\n

# \u5e94\u7528\u89c4\u5219<\/span>
\n for<\/span> rule in<\/span> encoding_rules:<\/span>
\n if<\/span> rulerequirements:<\/span>
\n return<\/span> rule[<\/span>'encoding'<\/span>]<\/span>,<\/span> rule[<\/span>'reason'<\/span>]<\/span><\/p>\n

# \u9ed8\u8ba4<\/span>
\n return<\/span> 'utf-8'<\/span>,<\/span> '\u5b89\u5168\u9ed8\u8ba4\u9009\u62e9'<\/span><\/p>\n

# \u4f7f\u7528\u793a\u4f8b<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n test_cases =<\/span> [<\/span>
\n {<\/span>
\n 'name'<\/span>:<\/span> 'Windows + Excel + \u4e2d\u6587'<\/span>,<\/span>
\n 'requirements'<\/span>:<\/span> {<\/span>
\n 'platform'<\/span>:<\/span> 'windows'<\/span>,<\/span>
\n 'contains_chinese'<\/span>:<\/span> True<\/span>,<\/span>
\n 'excel_compatible'<\/span>:<\/span> True<\/span>,<\/span>
\n 'file_size_matters'<\/span>:<\/span> False<\/span>,<\/span>
\n 'legacy_system'<\/span>:<\/span> False<\/span>
\n }<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'name'<\/span>:<\/span> '\u8de8\u5e73\u53f0Web\u5e94\u7528'<\/span>,<\/span>
\n 'requirements'<\/span>:<\/span> {<\/span>
\n 'platform'<\/span>:<\/span> 'all'<\/span>,<\/span>
\n 'contains_chinese'<\/span>:<\/span> True<\/span>,<\/span>
\n 'excel_compatible'<\/span>:<\/span> False<\/span>,<\/span>
\n 'file_size_matters'<\/span>:<\/span> True<\/span>,<\/span>
\n 'legacy_system'<\/span>:<\/span> False<\/span>
\n }<\/span>
\n }<\/span>,<\/span>
\n {<\/span>
\n 'name'<\/span>:<\/span> '\u65e7\u7248\u4e2d\u6587\u7cfb\u7edf'<\/span>,<\/span>
\n 'requirements'<\/span>:<\/span> {<\/span>
\n 'platform'<\/span>:<\/span> 'windows'<\/span>,<\/span>
\n 'contains_chinese'<\/span>:<\/span> True<\/span>,<\/span>
\n 'excel_compatible'<\/span>:<\/span> False<\/span>,<\/span>
\n 'file_size_matters'<\/span>:<\/span> False<\/span>,<\/span>
\n 'legacy_system'<\/span>:<\/span> True<\/span>
\n }<\/span>
\n }<\/span>
\n ]<\/span><\/p>\n

print<\/span>(<\/span>"🧠 \u7f16\u7801\u9009\u62e9\u51b3\u7b56\u7cfb\u7edf"<\/span>)<\/span>
\n print<\/span>(<\/span>"="<\/span>*<\/span>60<\/span>)<\/span><\/p>\n

for<\/span> case<\/span> in<\/span> test_cases:<\/span>
\n encoding,<\/span> reason =<\/span> encoding_decision_system(<\/span>case<\/span>[<\/span>'requirements'<\/span>]<\/span>)<\/span>
\n print<\/span>(<\/span>f"\\\\n📋 \u573a\u666f: <\/span>{<\/span>case<\/span>[<\/span>'name'<\/span>]<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" \u9700\u6c42: <\/span>{<\/span>case<\/span>[<\/span>'requirements'<\/span>]<\/span>}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" 🎯 \u63a8\u8350\u7f16\u7801: <\/span>{<\/span>encoding}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>f" 💡 \u539f\u56e0: <\/span>{<\/span>reason}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

📊 \u7f16\u7801\u95ee\u9898\u8bca\u65ad\u5de5\u5177<\/h3>\n

"""
\n\u7f16\u7801\u95ee\u9898\u8bca\u65ad\u5de5\u5177
\n\u68c0\u6d4b\u548c\u4fee\u590d\u5e38\u89c1\u7684\u7f16\u7801\u95ee\u9898
\n"""<\/span>
\nimport<\/span> os
\nimport<\/span> sys
\nimport<\/span> locale<\/p>\n

def<\/span> diagnose_system_encoding<\/span>(<\/span>)<\/span>:<\/span>
\n """\u8bca\u65ad\u7cfb\u7edf\u7f16\u7801\u8bbe\u7f6e"""<\/span><\/p>\n

print<\/span>(<\/span>"🔧 \u7cfb\u7edf\u7f16\u7801\u8bca\u65ad\u62a5\u544a"<\/span>)<\/span>
\n print<\/span>(<\/span>"="<\/span>*<\/span>60<\/span>)<\/span><\/p>\n

# \u83b7\u53d6\u7cfb\u7edf\u7f16\u7801\u4fe1\u606f<\/span>
\n encoding_info =<\/span> {<\/span>
\n '\u7cfb\u7edf\u9ed8\u8ba4\u7f16\u7801'<\/span>:<\/span> sys.<\/span>getdefaultencoding(<\/span>)<\/span>,<\/span>
\n '\u6587\u4ef6\u7cfb\u7edf\u7f16\u7801'<\/span>:<\/span> sys.<\/span>getfilesystemencoding(<\/span>)<\/span>,<\/span>
\n '\u533a\u57df\u8bbe\u7f6e\u7f16\u7801'<\/span>:<\/span> locale.<\/span>getpreferredencoding(<\/span>)<\/span>,<\/span>
\n '\u6807\u51c6\u8f93\u5165\u7f16\u7801'<\/span>:<\/span> sys.<\/span>stdin.<\/span>encoding,<\/span>
\n '\u6807\u51c6\u8f93\u51fa\u7f16\u7801'<\/span>:<\/span> sys.<\/span>stdout.<\/span>encoding,<\/span>
\n '\u6807\u51c6\u9519\u8bef\u7f16\u7801'<\/span>:<\/span> sys.<\/span>stderr.<\/span>encoding,<\/span>
\n 'Python\u7248\u672c'<\/span>:<\/span> sys.<\/span>version,<\/span>
\n '\u5e73\u53f0'<\/span>:<\/span> sys.<\/span>platform
\n }<\/span><\/p>\n

for<\/span> key,<\/span> value in<\/span> encoding_info.<\/span>items(<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>f"<\/span>{<\/span>key:<\/span>20<\/span>}<\/span><\/span>: <\/span>{<\/span>value}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u68c0\u67e5\u5e38\u89c1\u95ee\u9898<\/span>
\n print<\/span>(<\/span>"\\\\n🔍 \u5e38\u89c1\u95ee\u9898\u68c0\u67e5:"<\/span>)<\/span><\/p>\n

# 1. \u68c0\u67e5Python\u7248\u672c<\/span>
\n if<\/span> sys.<\/span>version_info <<\/span> (<\/span>3<\/span>,<\/span> 0<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>"\u274c Python 2.x \u5b58\u5728\u4e25\u91cd\u7f16\u7801\u95ee\u9898，\u8bf7\u5347\u7ea7\u5230Python 3.x"<\/span>)<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2705 \u4f7f\u7528Python 3.x，\u7f16\u7801\u652f\u6301\u826f\u597d"<\/span>)<\/span><\/p>\n

# 2. \u68c0\u67e5Windows\u4e0a\u7684\u7f16\u7801\u95ee\u9898<\/span>
\n if<\/span> sys.<\/span>platform ==<\/span> 'win32'<\/span>:<\/span>
\n if<\/span> locale.<\/span>getpreferredencoding(<\/span>)<\/span>.<\/span>lower(<\/span>)<\/span> in<\/span> [<\/span>'cp936'<\/span>,<\/span> 'gbk'<\/span>,<\/span> 'gb2312'<\/span>]<\/span>:<\/span>
\n print<\/span>(<\/span>"\u26a0\ufe0f Windows\u4e2d\u6587\u7cfb\u7edf\u4f7f\u7528GBK\u7f16\u7801，\u6ce8\u610f\u4e0eUTF-8\u7684\u517c\u5bb9\u6027"<\/span>)<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2705 Windows\u7cfb\u7edf\u7f16\u7801\u8bbe\u7f6e\u6b63\u5e38"<\/span>)<\/span><\/p>\n

# 3. \u68c0\u67e5\u73af\u5883\u53d8\u91cf<\/span>
\n print<\/span>(<\/span>"\\\\n🌍 \u73af\u5883\u53d8\u91cf\u68c0\u67e5:"<\/span>)<\/span>
\n env_vars =<\/span> [<\/span>'PYTHONIOENCODING'<\/span>,<\/span> 'PYTHONUTF8'<\/span>,<\/span> 'LANG'<\/span>,<\/span> 'LC_ALL'<\/span>,<\/span> 'LC_CTYPE'<\/span>]<\/span><\/p>\n

for<\/span> var in<\/span> env_vars:<\/span>
\n value =<\/span> os.<\/span>environ.<\/span>get(<\/span>var,<\/span> '(\u672a\u8bbe\u7f6e)'<\/span>)<\/span>
\n print<\/span>(<\/span>f" <\/span>{<\/span>var:<\/span>20<\/span>}<\/span><\/span>: <\/span>{<\/span>value}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u5efa\u8bae<\/span>
\n print<\/span>(<\/span>"\\\\n💡 \u5efa\u8bae:"<\/span>)<\/span>
\n print<\/span>(<\/span>" 1. \u8bbe\u7f6e\u73af\u5883\u53d8\u91cf: set PYTHONIOENCODING=utf-8 (Windows)"<\/span>)<\/span>
\n print<\/span>(<\/span>" 2. \u8bbe\u7f6e\u73af\u5883\u53d8\u91cf: export PYTHONIOENCODING=utf-8 (Linux\/Mac)"<\/span>)<\/span>
\n print<\/span>(<\/span>" 3. \u5728Python\u811a\u672c\u5f00\u5934\u6dfb\u52a0: # -*- coding: utf-8 -*-"<\/span>)<\/span>
\n print<\/span>(<\/span>" 4. \u6240\u6709\u6587\u4ef6\u64cd\u4f5c\u663e\u5f0f\u6307\u5b9a\u7f16\u7801"<\/span>)<\/span><\/p>\n

def<\/span> diagnose_file<\/span>(<\/span>filename:<\/span> str<\/span>)<\/span>:<\/span>
\n """\u8bca\u65ad\u7279\u5b9a\u6587\u4ef6\u7684\u7f16\u7801\u95ee\u9898"""<\/span><\/p>\n

if<\/span> not<\/span> os.<\/span>path.<\/span>exists(<\/span>filename)<\/span>:<\/span>
\n print<\/span>(<\/span>f"\u274c \u6587\u4ef6\u4e0d\u5b58\u5728: <\/span>{<\/span>filename}<\/span><\/span>"<\/span><\/span>)<\/span>
\n return<\/span><\/p>\n

print<\/span>(<\/span>f"\\\\n🔍 \u6587\u4ef6\u7f16\u7801\u8bca\u65ad: <\/span>{<\/span>filename}<\/span><\/span>"<\/span><\/span>)<\/span>
\n print<\/span>(<\/span>"-"<\/span>*<\/span>40<\/span>)<\/span><\/p>\n

# \u83b7\u53d6\u6587\u4ef6\u4fe1\u606f<\/span>
\n file_size =<\/span> os.<\/span>path.<\/span>getsize(<\/span>filename)<\/span>
\n print<\/span>(<\/span>f"\u6587\u4ef6\u5927\u5c0f: <\/span>{<\/span>file_size}<\/span><\/span> \u5b57\u8282"<\/span><\/span>)<\/span><\/p>\n

# \u8bfb\u53d6\u524d1024\u5b57\u8282\u8fdb\u884c\u5206\u6790<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'rb'<\/span>)<\/span> as<\/span> f:<\/span>
\n header =<\/span> f.<\/span>read(<\/span>1024<\/span>)<\/span><\/p>\n

# \u68c0\u67e5BOM<\/span>
\n bom_detected =<\/span> False<\/span>
\n if<\/span> header.<\/span>startswith(<\/span>b'\\\\xef\\\\xbb\\\\xbf'<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2705 \u68c0\u6d4b\u5230UTF-8 BOM"<\/span>)<\/span>
\n bom_detected =<\/span> True<\/span>
\n elif<\/span> header.<\/span>startswith(<\/span>b'\\\\xff\\\\xfe'<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2705 \u68c0\u6d4b\u5230UTF-16 LE BOM"<\/span>)<\/span>
\n bom_detected =<\/span> True<\/span>
\n elif<\/span> header.<\/span>startswith(<\/span>b'\\\\xfe\\\\xff'<\/span>)<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2705 \u68c0\u6d4b\u5230UTF-16 BE BOM"<\/span>)<\/span>
\n bom_detected =<\/span> True<\/span>
\n else<\/span>:<\/span>
\n print<\/span>(<\/span>"\u2139\ufe0f \u672a\u68c0\u6d4b\u5230BOM\u6807\u8bb0"<\/span>)<\/span><\/p>\n

# \u5c1d\u8bd5\u7528\u4e0d\u540c\u7f16\u7801\u8bfb\u53d6<\/span>
\n test_encodings =<\/span> [<\/span>'utf-8'<\/span>,<\/span> 'utf-8-sig'<\/span>,<\/span> 'gbk'<\/span>,<\/span> 'gb2312'<\/span>,<\/span>
\n 'gb18030'<\/span>,<\/span> 'big5'<\/span>,<\/span> 'latin-1'<\/span>,<\/span> 'cp1252'<\/span>]<\/span><\/p>\n

print<\/span>(<\/span>"\\\\n🔤 \u7f16\u7801\u6d4b\u8bd5:"<\/span>)<\/span>
\n for<\/span> enc in<\/span> test_encodings:<\/span>
\n try<\/span>:<\/span>
\n with<\/span> open<\/span>(<\/span>filename,<\/span> 'r'<\/span>,<\/span> encoding=<\/span>enc)<\/span> as<\/span> f:<\/span>
\n content =<\/span> f.<\/span>read(<\/span>200<\/span>)<\/span><\/p>\n

# \u68c0\u67e5\u662f\u5426\u5305\u542b\u4e71\u7801\u5b57\u7b26<\/span>
\n has_garbled =<\/span> any<\/span>(<\/span>ord<\/span>(<\/span>c)<\/span> ==<\/span> 65533<\/span> for<\/span> c in<\/span> content)<\/span> # 65533\u662f\u66ff\u6362\u5b57\u7b26'�'<\/span><\/p>\n

if<\/span> has_garbled:<\/span>
\n print<\/span>(<\/span>f" \u26a0\ufe0f <\/span>{<\/span>enc:<\/span>12<\/span>}<\/span><\/span> – \u53ef\u8bfb\u4f46\u5305\u542b\u66ff\u6362\u5b57\u7b26"<\/span><\/span>)<\/span>
\n else<\/span>:<\/span>
\n # \u68c0\u67e5\u662f\u5426\u5305\u542b\u4e2d\u6587\u5b57\u7b26<\/span>
\n has_chinese =<\/span> any<\/span>(<\/span>'\\\\u4e00'<\/span> <=<\/span> c <=<\/span> '\\\\u9fff'<\/span> for<\/span> c in<\/span> content)<\/span>
\n status =<\/span> "\u2705"<\/span> if<\/span> not<\/span> has_garbled else<\/span> "\u26a0\ufe0f "<\/span>
\n chinese_info =<\/span> " (\u542b\u4e2d\u6587)"<\/span> if<\/span> has_chinese else<\/span> ""<\/span>
\n print<\/span>(<\/span>f" <\/span>{<\/span>status}<\/span><\/span> <\/span>{<\/span>enc:<\/span>12<\/span>}<\/span><\/span> – \u53ef\u6b63\u5e38\u8bfb\u53d6<\/span>{<\/span>chinese_info}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

except<\/span> UnicodeDecodeError as<\/span> e:<\/span>
\n print<\/span>(<\/span>f" \u274c <\/span>{<\/span>enc:<\/span>12<\/span>}<\/span><\/span> – \u89e3\u7801\u5931\u8d25: <\/span>{<\/span>str<\/span>(<\/span>e)<\/span>[<\/span>:<\/span>30]<\/span>}<\/span><\/span>…"<\/span><\/span>)<\/span>
\n except<\/span> Exception as<\/span> e:<\/span>
\n print<\/span>(<\/span>f" \u274c <\/span>{<\/span>enc:<\/span>12<\/span>}<\/span><\/span> – \u9519\u8bef: <\/span>{<\/span>e}<\/span><\/span>"<\/span><\/span>)<\/span><\/p>\n

# \u8fd0\u884c\u8bca\u65ad<\/span>
\nif<\/span> __name__ ==<\/span> "__main__"<\/span>:<\/span>
\n diagnose_system_encoding(<\/span>)<\/span><\/p>\n

# \u6d4b\u8bd5\u6587\u4ef6<\/span>
\n test_files =<\/span> [<\/span>'wc_co_data_fixed.csv'<\/span>]<\/span> if<\/span> os.<\/span>path.<\/span>exists(<\/span>'wc_co_data_fixed.csv'<\/span>)<\/span> else<\/span> [<\/span>]<\/span><\/p>\n

for<\/span> test_file in<\/span> test_files:<\/span>
\n diagnose_file(<\/span>test_file)<\/span><\/p>\n

🎓 \u7f16\u7801\u6700\u4f73\u5b9e\u8df5\u603b\u7ed3<\/h3>\n

\u7ecf\u8fc7\u6df1\u5165\u5206\u6790，\u6211\u4eec\u53ef\u4ee5\u603b\u7ed3\u51faPython\u7f16\u7801\u95ee\u9898\u7684\u7ec8\u6781\u89e3\u51b3\u65b9\u6848：<\/p>\n

1. \u9ec4\u91d1\u6cd5\u5219<\/h4>\n

\u6c38\u8fdc\u4e0d\u8981\u7701\u7565encoding\u53c2\u6570\u3002\u65e0\u8bba\u8bfb\u53d6\u8fd8\u662f\u5199\u5165，\u90fd\u5fc5\u987b\u663e\u5f0f\u6307\u5b9a\u7f16\u7801：<\/p>\n

# \u274c \u9519\u8bef：\u4f9d\u8d56\u7cfb\u7edf\u9ed8\u8ba4\u7f16\u7801<\/span>
\nwith<\/span> open<\/span>(<\/span>'file.txt'<\/span>,<\/span> 'w'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>"\u5185\u5bb9"<\/span>)<\/span><\/p>\n

# \u2705 \u6b63\u786e：\u663e\u5f0f\u6307\u5b9a\u7f16\u7801<\/span>
\nwith<\/span> open<\/span>(<\/span>'file.txt'<\/span>,<\/span> 'w'<\/span>,<\/span> encoding=<\/span>'utf-8'<\/span>)<\/span> as<\/span> f:<\/span>
\n f.<\/span>write(<\/span>"\u5185\u5bb9"<\/span>)<\/span><\/p>\n

2. \u7f16\u7801\u9009\u62e9\u7b56\u7565<\/h4>\n