Skip to content

fix: encoding detection bug #5592

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hpwamr merged 2 commits into from
Mar 12, 2026
+16 −12
Merged

fix: encoding detection bug #5592

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ae87bea
fix: encoding detection bug
RaiKoHoff Mar 12, 2026
8d5a289
fix: revert ASCII as UTF-8 for unicode detection - false positives
RaiKoHoff Mar 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 16 additions & 12 deletions src/EncodingDetection.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1233,7 +1233,7 @@ extern "C" ENC_DET_T Encoding_DetectEncoding(const HPATHL hpath, const char* lpD
Encoding_AnalyzeText(lpData, cbNbytes4Analysis, &encDetRes, iAnalyzeHint);
// ---------------------------------------------------------------------------
}
encDetRes.bPureASCII7Bit = (encDetRes.analyzedEncoding == CPI_ASCII_7BIT) || IsPureAscii7Bit(lpData, cbData);
encDetRes.bPureASCII7Bit = IsPureAscii7Bit(lpData, cbData);

if (encDetRes.analyzedEncoding == CPI_NONE) {
encDetRes.analyzedEncoding = iAnalyzeHint;
Expand Down Expand Up @@ -1297,23 +1297,26 @@ extern "C" ENC_DET_T Encoding_DetectEncoding(const HPATHL hpath, const char* lpD
}
else if (Encoding_IsValid(encDetRes.analyzedEncoding) && (encDetRes.bIsAnalysisReliable || !Settings.UseReliableCEDonly))
{
if (!encDetRes.bIsAnalysisReliable && !Encoding_IsUTF8(encDetRes.analyzedEncoding) && encDetRes.bValidUTF8) {
encDetRes.Encoding = CPI_UTF8; // unreliable non-UTF-8 guess, but data is valid UTF-8
} else {
encDetRes.Encoding = (encDetRes.analyzedEncoding == CPI_ASCII_7BIT) ? CPI_UTF8 : encDetRes.analyzedEncoding;
}
else if (Encoding_IsUNICODE(encDetRes.unicodeAnalysis))
{
// unicodeAnalysis (IsTextUnicode) confirms Unicode structure,
// iConfidence is from UCHARDET analysis — use analyzedEncoding (intentional)
if (Encoding_IsValid(encDetRes.analyzedEncoding)) {
encDetRes.Encoding = encDetRes.analyzedEncoding;
}
//~else if ((encDetRes.analyzedEncoding == CPI_ASCII_7BIT) && encDetRes.bValidUTF8) {
//~ encDetRes.Encoding = CPI_UTF8;
//~}
else {
encDetRes.Encoding = encDetRes.unicodeAnalysis;
}
}
else if (!encDetRes.bIsAnalysisReliable && (Encoding_IsValid(encDetRes.analyzedEncoding) || encDetRes.bPureASCII7Bit))
{
else if (encDetRes.bPureASCII7Bit || (encDetRes.analyzedEncoding == CPI_ASCII_7BIT)) {
// UCHARDET below confidence threshold (UseReliableCEDonly is true)
encDetRes.Encoding = encDetRes.bValidUTF8 ? CPI_UTF8 : CPI_ANSI_DEFAULT;
}
else if (Encoding_IsUNICODE(encDetRes.unicodeAnalysis) && (iConfidence > 50))
{
// unicodeAnalysis (IsTextUnicode) confirms Unicode structure,
// iConfidence is from UCHARDET analysis — use analyzedEncoding (intentional)
encDetRes.Encoding = encDetRes.analyzedEncoding;
}
else if (Encoding_IsValid(Encoding_SrcWeak(CPI_GET)))
{
encDetRes.Encoding = Encoding_SrcWeak(CPI_GET);
Expand All @@ -1323,6 +1326,7 @@ extern "C" ENC_DET_T Encoding_DetectEncoding(const HPATHL hpath, const char* lpD
encDetRes.Encoding = iAnalyzeHint;
}

// final check
if (!Encoding_IsValid(encDetRes.Encoding)) {
encDetRes.Encoding = CPI_PREFERRED_ENCODING;
}
Expand Down
Loading