Fixed ASCII folding for non-foldable non-ASCII characters
Problem: Add an object, name it using cyrilic, Slice, click Export: the proposed name is mangled. Affects all platforms, 2.2.0 was fine.
Cause: It is mangled during ASCII folding, which was broken with 28c0880
when it was generalized to be used from the fuzzy matcher.
fold_to_ascii(wchar_t c, char *out) relies on narrowing char = wchar_t assignment, the old one used std::back_insert_iterator<std::wstring>.
It is thus unable to leave a character alone even when it should (it should, right?).
Solution:
1. Typed the fold_to_ascii function so it works on wchar_t only, which should mimic the old behaviour.
2. Changed the respective call in fts_fuzzy_match.h. That function also works with wide char C-strings.
Cleanup:
1. Removed the unused fold_utf8_to_ascii(const char *src) overload to avoid code duplication.
2. Untemplated the fold_to_ascii(wchar_t c, std::back_insert_iterator<std::wstring>& out) function, it was never called with a different type.
3. The function is now static in ASCIIFolding.cpp, nobody else needs to know.
This commit is contained in:
parent
1f5ac7d2f7
commit
78a3d8b63e
3 changed files with 17 additions and 29 deletions
|
@ -116,10 +116,10 @@ namespace fts {
|
|||
int num_matched = std::tolower(*pattern) == std::tolower(*str) ? 1 : 0;
|
||||
bool folded_match = false;
|
||||
if (! num_matched) {
|
||||
char tmp[4];
|
||||
char *end = Slic3r::fold_to_ascii(*str, tmp);
|
||||
char *c = tmp;
|
||||
for (const wchar_t* d = pattern; c != end && *d != 0 && wchar_t(std::tolower(*c)) == std::tolower(*d); ++c, ++d);
|
||||
wchar_t tmp[4];
|
||||
wchar_t *end = Slic3r::fold_to_ascii(*str, tmp);
|
||||
wchar_t *c = tmp;
|
||||
for (const wchar_t* d = pattern; c != end && *d != 0 && std::towlower(*c) == std::towlower(*d); ++c, ++d);
|
||||
if (c == end) {
|
||||
folded_match = true;
|
||||
num_matched = end - tmp;
|
||||
|
|
|
@ -11,7 +11,7 @@ namespace Slic3r {
|
|||
// Convert the input UNICODE character to a string of maximum 4 output ASCII characters.
|
||||
// Return the end of the string written to the output.
|
||||
// The output buffer must be at least 4 characters long.
|
||||
char* fold_to_ascii(wchar_t c, char *out)
|
||||
wchar_t* fold_to_ascii(wchar_t c, wchar_t *out)
|
||||
{
|
||||
if (c < 0x080) {
|
||||
*out ++ = c;
|
||||
|
@ -1925,7 +1925,7 @@ char* fold_to_ascii(wchar_t c, char *out)
|
|||
*out ++ = '~';
|
||||
break;
|
||||
default:
|
||||
*out ++ = c;
|
||||
*out ++ = c;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
@ -1934,6 +1934,14 @@ char* fold_to_ascii(wchar_t c, char *out)
|
|||
return out;
|
||||
}
|
||||
|
||||
static void fold_to_ascii(wchar_t c, std::back_insert_iterator<std::wstring>& out)
|
||||
{
|
||||
wchar_t tmp[4];
|
||||
wchar_t *end = fold_to_ascii(c, tmp);
|
||||
for (wchar_t *it = tmp; it != end; ++ it)
|
||||
*out = *it;
|
||||
}
|
||||
|
||||
std::string fold_utf8_to_ascii(const std::string &src)
|
||||
{
|
||||
std::wstring wstr = boost::locale::conv::utf_to_utf<wchar_t>(src.c_str(), src.c_str() + src.size());
|
||||
|
@ -1945,15 +1953,5 @@ std::string fold_utf8_to_ascii(const std::string &src)
|
|||
return boost::locale::conv::utf_to_utf<char>(dst.c_str(), dst.c_str() + dst.size());
|
||||
}
|
||||
|
||||
std::string fold_utf8_to_ascii(const char *src)
|
||||
{
|
||||
std::wstring wstr = boost::locale::conv::utf_to_utf<wchar_t>(src, src + strlen(src));
|
||||
std::wstring dst;
|
||||
dst.reserve(wstr.size());
|
||||
auto out = std::back_insert_iterator<std::wstring>(dst);
|
||||
for (wchar_t c : wstr)
|
||||
fold_to_ascii(c, out);
|
||||
return boost::locale::conv::utf_to_utf<char>(dst.c_str(), dst.c_str() + dst.size());
|
||||
}
|
||||
|
||||
}; // namespace Slic3r
|
||||
} // namespace Slic3r
|
||||
|
|
|
@ -7,23 +7,13 @@ namespace Slic3r {
|
|||
|
||||
// If possible, remove accents from accented latin characters.
|
||||
// This function is useful for generating file names to be processed by legacy firmwares.
|
||||
extern std::string fold_utf8_to_ascii(const char *src);
|
||||
extern std::string fold_utf8_to_ascii(const std::string &src);
|
||||
|
||||
// Convert the input UNICODE character to a string of maximum 4 output ASCII characters.
|
||||
// Return the end of the string written to the output.
|
||||
// The output buffer must be at least 4 characters long.
|
||||
extern char* fold_to_ascii(wchar_t c, char *out);
|
||||
extern wchar_t* fold_to_ascii(wchar_t c, wchar_t *out);
|
||||
|
||||
template<typename OUTPUT_ITERATOR>
|
||||
void fold_to_ascii(wchar_t c, OUTPUT_ITERATOR out)
|
||||
{
|
||||
char tmp[4];
|
||||
char *end = fold_to_ascii(c, tmp);
|
||||
for (char *it = tmp; it != end; ++ it)
|
||||
*out = *it;
|
||||
}
|
||||
|
||||
}; // namespace Slic3r
|
||||
} // namespace Slic3r
|
||||
|
||||
#endif /* slic3r_ASCIIFolding_hpp_ */
|
||||
|
|
Loading…
Reference in a new issue