snark13/Xteink-X4-crosspoint-reader
1
0
Fork 0
mirror of https://github.com/daveallie/crosspoint-reader.git synced 2026-02-06 23:57:39 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Skip BOM character (sometimes used in front of em-dashes)

Browse Source
This commit is contained in:
Jonas Diemer 2026-01-12 22:03:12 +01:00
parent 52995fa722
commit 68130d3c44
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp
View File

@ -151,6 +151,20 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
} }
} }
// Skip Zero Width No-Break Space / BOM (U+FEFF) = 0xEF 0xBB 0xBF
const XML_Char FEFF_BYTE_1 = static_cast<XML_Char>(0xEF);
const XML_Char FEFF_BYTE_2 = static_cast<XML_Char>(0xBB);
const XML_Char FEFF_BYTE_3 = static_cast<XML_Char>(0xBF);
if (s[i] == FEFF_BYTE_1) {
// Check if the next two bytes complete the 3-byte sequence
if ((i + 2 < len) && (s[i + 1] == FEFF_BYTE_2) && (s[i + 2] == FEFF_BYTE_3)) {
// Sequence 0xEF 0xBB 0xBF found!
i += 2; // Skip the next two bytes
continue; // Move to the next iteration
}
}
// If we're about to run out of space, then cut the word off and start a new one // If we're about to run out of space, then cut the word off and start a new one
if (self->partWordBufferIndex >= MAX_WORD_SIZE) { if (self->partWordBufferIndex >= MAX_WORD_SIZE) {
self->partWordBuffer[self->partWordBufferIndex] = '\0'; self->partWordBuffer[self->partWordBufferIndex] = '\0';