fix: truncating chapter titles using UTF-8 safe function (#599)

## Summary

* Truncating chapter titles using utf8 safe functions (Cyrillic titles
were split mid codepoint)
* refactoring of lib/Utf8

---

### AI Usage

While CrossPoint doesn't have restrictions on AI tools in contributing,
please be transparent about their usage as it
helps set the right context for reviewers.

Did you use AI tools to help write this code? _**< PARTIALLY >**_
This commit is contained in:
Arthur Tazhitdinov
2026-02-01 16:23:48 +05:00
committed by GitHub
parent 0d82b03981
commit b1dcb7733b
8 changed files with 45 additions and 40 deletions

View File

@@ -61,23 +61,4 @@ bool checkFileExtension(const String& fileName, const char* extension) {
return localFile.endsWith(localExtension);
}
size_t utf8RemoveLastChar(std::string& str) {
if (str.empty()) return 0;
size_t pos = str.size() - 1;
// Walk back to find the start of the last UTF-8 character
// UTF-8 continuation bytes start with 10xxxxxx (0x80-0xBF)
while (pos > 0 && (static_cast<unsigned char>(str[pos]) & 0xC0) == 0x80) {
--pos;
}
str.resize(pos);
return pos;
}
// Truncate string by removing N UTF-8 characters from the end
void utf8TruncateChars(std::string& str, const size_t numChars) {
for (size_t i = 0; i < numChars && !str.empty(); ++i) {
utf8RemoveLastChar(str);
}
}
} // namespace StringUtils

View File

@@ -19,10 +19,4 @@ std::string sanitizeFilename(const std::string& name, size_t maxLength = 100);
bool checkFileExtension(const std::string& fileName, const char* extension);
bool checkFileExtension(const String& fileName, const char* extension);
// UTF-8 safe string truncation - removes one character from the end
// Returns the new size after removing one UTF-8 character
size_t utf8RemoveLastChar(std::string& str);
// Truncate string by removing N UTF-8 characters from the end
void utf8TruncateChars(std::string& str, size_t numChars);
} // namespace StringUtils