Skip to content

Detect valid UTF-8 as UTF-8 #572

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

Draft
filip-hejsek wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Detect valid UTF-8 as UTF-8 #572

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
32 changes: 32 additions & 0 deletions libaegisub/common/charset.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,15 @@
#include "libaegisub/charset.h"

#include "libaegisub/file_mapping.h"
#include "libaegisub/log.h"
#include "libaegisub/scoped_ptr.h"

#include <array>
#include <memory>

#ifdef WITH_UCHARDET
#include <uchardet.h>
#include <unicode/ucnv.h>
#endif

namespace agi::charset {
Expand Down Expand Up @@ -51,13 +56,37 @@ std::string Detect(agi::fs::path const& file) {

#ifdef WITH_UCHARDET
agi::scoped_holder<uchardet_t> ud(uchardet_new(), uchardet_delete);

UErrorCode utf8Status = U_ZERO_ERROR;
std::unique_ptr<UConverter, decltype(&ucnv_close)> conv = {ucnv_open("UTF-8", &utf8Status), ucnv_close};
if (conv)
ucnv_setToUCallBack(conv.get(), UCNV_TO_U_CALLBACK_STOP, nullptr, nullptr, nullptr, &utf8Status);
if (utf8Status != U_ZERO_ERROR)
LOG_W("charset/detect") << "Unexpected ICU error: " << u_errorName(utf8Status);
std::array<UChar, 2048> convBuffer;

for (uint64_t offset = 0; offset < fp.size(); ) {
auto read = std::min<uint64_t>(4096, fp.size() - offset);
auto buf = fp.read(offset, read);
uchardet_handle_data(ud, buf, read);

offset += read;

const char *source = buf;
const char *sourceLimit = source + read;
bool flush = offset >= fp.size();
while (U_SUCCESS(utf8Status)) {
UChar *target = convBuffer.data();
UChar *targetLimit = target + convBuffer.size();
ucnv_toUnicode(conv.get(), &target, targetLimit, &source, sourceLimit, nullptr, flush, &utf8Status);
if (utf8Status == U_BUFFER_OVERFLOW_ERROR) {
// result didn't fit in target buffer, try again
utf8Status = U_ZERO_ERROR;
} else if (source == sourceLimit) {
break;
}
}

// A dumb heuristic to detect binary files
for (size_t i = 0; i < read; ++i) {
if ((unsigned char)buf[i] < 32 && (buf[i] != '\r' && buf[i] != '\n' && buf[i] != '\t'))
Expand All @@ -67,6 +96,9 @@ std::string Detect(agi::fs::path const& file) {
if (binaryish > offset / 8)
return "binary";
}
LOG_D("charset/detect") << "UTF-8 detection result: " << u_errorName(utf8Status);
if (U_SUCCESS(utf8Status))
return "utf-8";
uchardet_data_end(ud);
return uchardet_get_charset(ud);
#else
Expand Down
Loading