fix: Fix hyphenation and rendering of decomposed characters (#1037)
## Summary * This PR fixes decomposed diacritic handling end-to-end: - Hyphenation: normalize common Latin base+combining sequences to precomposed codepoints before Liang pattern matching, so decomposed words hyphenate correctly - Rendering: correct combining-mark placement logic so non-spacing marks are attached to the preceding base glyph in normal and rotated text rendering paths, with corresponding text-bounds consistency updates. - Hyphenation around non breaking space variants have been fixed (and extended) - Hyphenation of terms that already included of hyphens were fixed to include Liang pattern application (eg "US-Satellitensystem" was *exclusively* broken at the existing hyphen) ## Additional Context * Before <img width="800" height="480" alt="2" src="https://github.com/user-attachments/assets/b9c515c4-ab75-45cc-8b52-f4d86bce519d" /> * After <img width="480" height="800" alt="fix1" src="https://github.com/user-attachments/assets/4999f6a8-f51c-4c0a-b144-f153f77ddb57" /> <img width="800" height="480" alt="fix2" src="https://github.com/user-attachments/assets/7355126b-80c7-441f-b390-4e0897ee3fb6" /> * Note 1: the hyphenation fix is not a 100% bullet proof implementation. It adds composition of *common* base+combining sequences (e.g. O + U+0308 -> Ö) during codepoint collection. A complete solution would require implementing proper Unicode normalization (at least NFC, possibly NFKC in specific cases) before hyphenation and rendering, instead of hand-mapping a few combining marks. That was beyond the scope of this fix. * Note 2: the render fix should be universal and not limited to the constraints outlined above: it properly x-centers the compund glyph over the previous one, and it uses at least 1pt of visual distance in y. Before: <img width="478" height="167" alt="Image" src="https://github.com/user-attachments/assets/f8db60d5-35b1-4477-96d0-5003b4e4a2a1" /> After: <img width="479" height="180" alt="Image" src="https://github.com/user-attachments/assets/1b48ef97-3a77-475a-8522-23f4aca8e904" /> * This should resolve the issues described in #998 --- ### 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:
jpirnay
@@ -174,6 +174,213 @@ std::vector<CodepointInfo> collectCodepoints(const std::string& word) {
|
||||
while (*ptr != 0) {
|
||||
const unsigned char* current = ptr;
|
||||
const uint32_t cp = utf8NextCodepoint(&ptr);
|
||||
// If this is a combining diacritic (e.g., U+0301 = acute) and there's
|
||||
// a previous base character that can be composed into a single
|
||||
// precomposed Unicode scalar (Latin-1 / Latin-Extended), do that
|
||||
// composition here. This provides lightweight NFC-like behavior for
|
||||
// common Western European diacritics (acute, grave, circumflex, tilde,
|
||||
// diaeresis, cedilla) without pulling in a full Unicode normalization
|
||||
// library.
|
||||
if (!cps.empty()) {
|
||||
uint32_t prev = cps.back().value;
|
||||
uint32_t composed = 0;
|
||||
switch (cp) {
|
||||
case 0x0300: // grave
|
||||
switch (prev) {
|
||||
case 0x0041:
|
||||
composed = 0x00C0;
|
||||
break; // A -> À
|
||||
case 0x0061:
|
||||
composed = 0x00E0;
|
||||
break; // a -> à
|
||||
case 0x0045:
|
||||
composed = 0x00C8;
|
||||
break; // E -> È
|
||||
case 0x0065:
|
||||
composed = 0x00E8;
|
||||
break; // e -> è
|
||||
case 0x0049:
|
||||
composed = 0x00CC;
|
||||
break; // I -> Ì
|
||||
case 0x0069:
|
||||
composed = 0x00EC;
|
||||
break; // i -> ì
|
||||
case 0x004F:
|
||||
composed = 0x00D2;
|
||||
break; // O -> Ò
|
||||
case 0x006F:
|
||||
composed = 0x00F2;
|
||||
break; // o -> ò
|
||||
case 0x0055:
|
||||
composed = 0x00D9;
|
||||
break; // U -> Ù
|
||||
case 0x0075:
|
||||
composed = 0x00F9;
|
||||
break; // u -> ù
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case 0x0301: // acute
|
||||
switch (prev) {
|
||||
case 0x0041:
|
||||
composed = 0x00C1;
|
||||
break; // A -> Á
|
||||
case 0x0061:
|
||||
composed = 0x00E1;
|
||||
break; // a -> á
|
||||
case 0x0045:
|
||||
composed = 0x00C9;
|
||||
break; // E -> É
|
||||
case 0x0065:
|
||||
composed = 0x00E9;
|
||||
break; // e -> é
|
||||
case 0x0049:
|
||||
composed = 0x00CD;
|
||||
break; // I -> Í
|
||||
case 0x0069:
|
||||
composed = 0x00ED;
|
||||
break; // i -> í
|
||||
case 0x004F:
|
||||
composed = 0x00D3;
|
||||
break; // O -> Ó
|
||||
case 0x006F:
|
||||
composed = 0x00F3;
|
||||
break; // o -> ó
|
||||
case 0x0055:
|
||||
composed = 0x00DA;
|
||||
break; // U -> Ú
|
||||
case 0x0075:
|
||||
composed = 0x00FA;
|
||||
break; // u -> ú
|
||||
case 0x0059:
|
||||
composed = 0x00DD;
|
||||
break; // Y -> Ý
|
||||
case 0x0079:
|
||||
composed = 0x00FD;
|
||||
break; // y -> ý
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case 0x0302: // circumflex
|
||||
switch (prev) {
|
||||
case 0x0041:
|
||||
composed = 0x00C2;
|
||||
break; // A -> Â
|
||||
case 0x0061:
|
||||
composed = 0x00E2;
|
||||
break; // a -> â
|
||||
case 0x0045:
|
||||
composed = 0x00CA;
|
||||
break; // E -> Ê
|
||||
case 0x0065:
|
||||
composed = 0x00EA;
|
||||
break; // e -> ê
|
||||
case 0x0049:
|
||||
composed = 0x00CE;
|
||||
break; // I -> Î
|
||||
case 0x0069:
|
||||
composed = 0x00EE;
|
||||
break; // i -> î
|
||||
case 0x004F:
|
||||
composed = 0x00D4;
|
||||
break; // O -> Ô
|
||||
case 0x006F:
|
||||
composed = 0x00F4;
|
||||
break; // o -> ô
|
||||
case 0x0055:
|
||||
composed = 0x00DB;
|
||||
break; // U -> Û
|
||||
case 0x0075:
|
||||
composed = 0x00FB;
|
||||
break; // u -> û
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case 0x0303: // tilde
|
||||
switch (prev) {
|
||||
case 0x0041:
|
||||
composed = 0x00C3;
|
||||
break; // A -> Ã
|
||||
case 0x0061:
|
||||
composed = 0x00E3;
|
||||
break; // a -> ã
|
||||
case 0x004E:
|
||||
composed = 0x00D1;
|
||||
break; // N -> Ñ
|
||||
case 0x006E:
|
||||
composed = 0x00F1;
|
||||
break; // n -> ñ
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case 0x0308: // diaeresis/umlaut
|
||||
switch (prev) {
|
||||
case 0x0041:
|
||||
composed = 0x00C4;
|
||||
break; // A -> Ä
|
||||
case 0x0061:
|
||||
composed = 0x00E4;
|
||||
break; // a -> ä
|
||||
case 0x0045:
|
||||
composed = 0x00CB;
|
||||
break; // E -> Ë
|
||||
case 0x0065:
|
||||
composed = 0x00EB;
|
||||
break; // e -> ë
|
||||
case 0x0049:
|
||||
composed = 0x00CF;
|
||||
break; // I -> Ï
|
||||
case 0x0069:
|
||||
composed = 0x00EF;
|
||||
break; // i -> ï
|
||||
case 0x004F:
|
||||
composed = 0x00D6;
|
||||
break; // O -> Ö
|
||||
case 0x006F:
|
||||
composed = 0x00F6;
|
||||
break; // o -> ö
|
||||
case 0x0055:
|
||||
composed = 0x00DC;
|
||||
break; // U -> Ü
|
||||
case 0x0075:
|
||||
composed = 0x00FC;
|
||||
break; // u -> ü
|
||||
case 0x0059:
|
||||
composed = 0x0178;
|
||||
break; // Y -> Ÿ
|
||||
case 0x0079:
|
||||
composed = 0x00FF;
|
||||
break; // y -> ÿ
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
case 0x0327: // cedilla
|
||||
switch (prev) {
|
||||
case 0x0043:
|
||||
composed = 0x00C7;
|
||||
break; // C -> Ç
|
||||
case 0x0063:
|
||||
composed = 0x00E7;
|
||||
break; // c -> ç
|
||||
default:
|
||||
break;
|
||||
}
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
if (composed != 0) {
|
||||
cps.back().value = composed;
|
||||
continue; // skip pushing the combining mark itself
|
||||
}
|
||||
}
|
||||
|
||||
cps.push_back({cp, static_cast<size_t>(current - base)});
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user