snark13/Xteink-X4-crosspoint-reader
1
0
Fork 0
mirror of https://github.com/daveallie/crosspoint-reader.git synced 2026-02-07 08:07:40 +03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

use language hyphenator for overfit words

Browse Source
This commit is contained in:
Arthur Tazhitdinov 2026-01-14 22:56:12 +05:00
parent 04a084f6c8
commit 10fa0cc060
2 changed files with 26 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
lib/Epub/Epub/ParsedText.cpp
View File

@ -75,7 +75,7 @@ void ParsedText::layoutAndExtractLines(const GfxRenderer& renderer, const int fo
// Use greedy layout that can split words mid-loop when a hyphenated prefix fits. // Use greedy layout that can split words mid-loop when a hyphenated prefix fits.
lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths); lineBreakIndices = computeHyphenatedLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths);
} else { } else {
lineBreakIndices = computeLineBreaks(pageWidth, spaceWidth, wordWidths); lineBreakIndices = computeLineBreaks(renderer, fontId, pageWidth, spaceWidth, wordWidths);
} }
const size_t lineCount = includeLastLine ? lineBreakIndices.size() : lineBreakIndices.size() - 1; const size_t lineCount = includeLastLine ? lineBreakIndices.size() : lineBreakIndices.size() - 1;
@ -103,8 +103,25 @@ std::vector<uint16_t> ParsedText::calculateWordWidths(const GfxRenderer& rendere
return wordWidths; return wordWidths;
} }
std::vector<size_t> ParsedText::computeLineBreaks(const int pageWidth, const int spaceWidth, std::vector<size_t> ParsedText::computeLineBreaks(const GfxRenderer& renderer, const int fontId, const int pageWidth,
const std::vector<uint16_t>& wordWidths) const { const int spaceWidth, std::vector<uint16_t>& wordWidths) {
if (words.empty()) {
return {};
}
// Ensure any word that would overflow even as the first entry on a line is split using fallback hyphenation.
for (size_t i = 0; i < wordWidths.size(); ++i) {
while (wordWidths[i] > pageWidth) {
// Try language-aware hyphenation first; only fall back to heuristics when no dictionary break fits.
if (hyphenateWordAtIndex(i, pageWidth, renderer, fontId, wordWidths, /*allowFallbackBreaks=*/false)) {
continue;
}
if (!hyphenateWordAtIndex(i, pageWidth, renderer, fontId, wordWidths, /*allowFallbackBreaks=*/true)) {
break;
}
}
}
const size_t totalWordCount = words.size(); const size_t totalWordCount = words.size();
// DP table to store the minimum badness (cost) of lines starting at index i // DP table to store the minimum badness (cost) of lines starting at index i
@ -260,7 +277,10 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
const auto style = *styleIt; const auto style = *styleIt;
// Collect candidate breakpoints (byte offsets and hyphen requirements). // Collect candidate breakpoints (byte offsets and hyphen requirements).
const auto breakInfos = Hyphenator::breakOffsets(word, allowFallbackBreaks); auto breakInfos = Hyphenator::breakOffsets(word, /*allowFallback=*/false);
if (breakInfos.empty() && allowFallbackBreaks) {
breakInfos = Hyphenator::breakOffsets(word, /*allowFallback=*/true);
}
if (breakInfos.empty()) { if (breakInfos.empty()) {
return false; return false;
} }

3
lib/Epub/Epub/ParsedText.h
View File

@ -20,7 +20,8 @@ class ParsedText {
bool hyphenationEnabled; bool hyphenationEnabled;
void applyParagraphIndent(); void applyParagraphIndent();
std::vector<size_t> computeLineBreaks(int pageWidth, int spaceWidth, const std::vector<uint16_t>& wordWidths) const; std::vector<size_t> computeLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth, int spaceWidth,
std::vector<uint16_t>& wordWidths);
std::vector<size_t> computeHyphenatedLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth, std::vector<size_t> computeHyphenatedLineBreaks(const GfxRenderer& renderer, int fontId, int pageWidth,
int spaceWidth, std::vector<uint16_t>& wordWidths); int spaceWidth, std::vector<uint16_t>& wordWidths);
bool hyphenateWordAtIndex(size_t wordIndex, int availableWidth, const GfxRenderer& renderer, int fontId, bool hyphenateWordAtIndex(size_t wordIndex, int availableWidth, const GfxRenderer& renderer, int fontId,