Files
crosspoint-reader-mod/lib/Epub/Epub/blocks/TextBlock.cpp
Zach Nelson 3696794591 perf: Replace std::list with std::vector in text layout (#1038)
## Summary

_Revision to @blindbat's #802. Description comes from the original PR._

- Replace `std::list` with `std::vector` for word storage in `TextBlock`
and `ParsedText`
- Use index-based access (`words[i]`) instead of iterator advancement
(`std::advance(it, n)`)
- Remove the separate `continuesVec` copy that was built from
`wordContinues` for O(1) access — now unnecessary since
`std::vector<bool>` already provides O(1) indexing

## Why

`std::list` allocates each node individually on the heap with 16 bytes
of prev/next pointer overhead per node. For text layout with many small
words, this means:
- Scattered heap allocations instead of contiguous memory
- Poor cache locality during iteration (each node can be anywhere in
memory)
- Per-node malloc/free overhead during construction and destruction

`std::vector` stores elements contiguously, giving better cache
performance during the tight rendering and layout loops. The
`extractLine` function also benefits: list splice was O(1) but required
maintaining three parallel iterators, while vector range construction
with move iterators is simpler and still efficient for the small
line-sized chunks involved.

## Files changed

- `lib/Epub/Epub/blocks/TextBlock.h` / `.cpp`
- `lib/Epub/Epub/ParsedText.h` / `.cpp`

## AI Usage

YES

## Test plan

- [ ] Open an EPUB with mixed formatting (bold, italic, underline) —
verify text renders correctly
- [ ] Open a book with justified text — verify word spacing is correct
- [ ] Open a book with hyphenation enabled — verify words break
correctly at hyphens
- [ ] Navigate through pages rapidly — verify no rendering glitches or
crashes
- [ ] Open a book with long paragraphs — verify text layout matches
pre-change behavior

---------

Co-authored-by: Kuanysh Bekkulov <kbekkulov@gmail.com>
2026-02-22 15:28:56 +11:00

115 lines
4.7 KiB
C++

#include "TextBlock.h"
#include <GfxRenderer.h>
#include <Logging.h>
#include <Serialization.h>
void TextBlock::render(const GfxRenderer& renderer, const int fontId, const int x, const int y) const {
// Validate iterator bounds before rendering
if (words.size() != wordXpos.size() || words.size() != wordStyles.size()) {
LOG_ERR("TXB", "Render skipped: size mismatch (words=%u, xpos=%u, styles=%u)\n", (uint32_t)words.size(),
(uint32_t)wordXpos.size(), (uint32_t)wordStyles.size());
return;
}
for (size_t i = 0; i < words.size(); i++) {
const int wordX = wordXpos[i] + x;
const EpdFontFamily::Style currentStyle = wordStyles[i];
renderer.drawText(fontId, wordX, y, words[i].c_str(), true, currentStyle);
if ((currentStyle & EpdFontFamily::UNDERLINE) != 0) {
const std::string& w = words[i];
const int fullWordWidth = renderer.getTextWidth(fontId, w.c_str(), currentStyle);
// y is the top of the text line; add ascender to reach baseline, then offset 2px below
const int underlineY = y + renderer.getFontAscenderSize(fontId) + 2;
int startX = wordX;
int underlineWidth = fullWordWidth;
// if word starts with em-space ("\xe2\x80\x83"), account for the additional indent before drawing the line
if (w.size() >= 3 && static_cast<uint8_t>(w[0]) == 0xE2 && static_cast<uint8_t>(w[1]) == 0x80 &&
static_cast<uint8_t>(w[2]) == 0x83) {
const char* visiblePtr = w.c_str() + 3;
const int prefixWidth = renderer.getTextAdvanceX(fontId, "\xe2\x80\x83", currentStyle);
const int visibleWidth = renderer.getTextWidth(fontId, visiblePtr, currentStyle);
startX = wordX + prefixWidth;
underlineWidth = visibleWidth;
}
renderer.drawLine(startX, underlineY, startX + underlineWidth, underlineY, true);
}
}
}
bool TextBlock::serialize(FsFile& file) const {
if (words.size() != wordXpos.size() || words.size() != wordStyles.size()) {
LOG_ERR("TXB", "Serialization failed: size mismatch (words=%u, xpos=%u, styles=%u)\n", words.size(),
wordXpos.size(), wordStyles.size());
return false;
}
// Word data
serialization::writePod(file, static_cast<uint16_t>(words.size()));
for (const auto& w : words) serialization::writeString(file, w);
for (auto x : wordXpos) serialization::writePod(file, x);
for (auto s : wordStyles) serialization::writePod(file, s);
// Style (alignment + margins/padding/indent)
serialization::writePod(file, blockStyle.alignment);
serialization::writePod(file, blockStyle.textAlignDefined);
serialization::writePod(file, blockStyle.marginTop);
serialization::writePod(file, blockStyle.marginBottom);
serialization::writePod(file, blockStyle.marginLeft);
serialization::writePod(file, blockStyle.marginRight);
serialization::writePod(file, blockStyle.paddingTop);
serialization::writePod(file, blockStyle.paddingBottom);
serialization::writePod(file, blockStyle.paddingLeft);
serialization::writePod(file, blockStyle.paddingRight);
serialization::writePod(file, blockStyle.textIndent);
serialization::writePod(file, blockStyle.textIndentDefined);
return true;
}
std::unique_ptr<TextBlock> TextBlock::deserialize(FsFile& file) {
uint16_t wc;
std::vector<std::string> words;
std::vector<uint16_t> wordXpos;
std::vector<EpdFontFamily::Style> wordStyles;
BlockStyle blockStyle;
// Word count
serialization::readPod(file, wc);
// Sanity check: prevent allocation of unreasonably large vectors (max 10000 words per block)
if (wc > 10000) {
LOG_ERR("TXB", "Deserialization failed: word count %u exceeds maximum", wc);
return nullptr;
}
// Word data
words.resize(wc);
wordXpos.resize(wc);
wordStyles.resize(wc);
for (auto& w : words) serialization::readString(file, w);
for (auto& x : wordXpos) serialization::readPod(file, x);
for (auto& s : wordStyles) serialization::readPod(file, s);
// Style (alignment + margins/padding/indent)
serialization::readPod(file, blockStyle.alignment);
serialization::readPod(file, blockStyle.textAlignDefined);
serialization::readPod(file, blockStyle.marginTop);
serialization::readPod(file, blockStyle.marginBottom);
serialization::readPod(file, blockStyle.marginLeft);
serialization::readPod(file, blockStyle.marginRight);
serialization::readPod(file, blockStyle.paddingTop);
serialization::readPod(file, blockStyle.paddingBottom);
serialization::readPod(file, blockStyle.paddingLeft);
serialization::readPod(file, blockStyle.paddingRight);
serialization::readPod(file, blockStyle.textIndent);
serialization::readPod(file, blockStyle.textIndentDefined);
return std::unique_ptr<TextBlock>(
new TextBlock(std::move(words), std::move(wordXpos), std::move(wordStyles), blockStyle));
}