checkpoint: refactor TextBlock/ParsedText from std::list to std::vector
Reduces heap fragmentation by ~12x fewer allocations per TextBlock. This fixes crashes when repeatedly navigating dictionary pages. - Replace std::list with std::vector in TextBlock members - Replace splice() with move+erase in ParsedText::extractLine() - Use index-based access in hyphenateWordAtIndex()
This commit is contained in:
parent
62643ae933
commit
6ceba56620
@ -281,14 +281,9 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get iterators to target word and style.
|
||||
auto wordIt = words.begin();
|
||||
auto styleIt = wordStyles.begin();
|
||||
std::advance(wordIt, wordIndex);
|
||||
std::advance(styleIt, wordIndex);
|
||||
|
||||
const std::string& word = *wordIt;
|
||||
const auto style = *styleIt;
|
||||
// Direct index access for vectors (more efficient than iterator + advance)
|
||||
const std::string& word = words[wordIndex];
|
||||
const auto wordStyle = wordStyles[wordIndex];
|
||||
|
||||
// Collect candidate breakpoints (byte offsets and hyphen requirements).
|
||||
auto breakInfos = Hyphenator::breakOffsets(word, allowFallbackBreaks);
|
||||
@ -308,7 +303,7 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
|
||||
}
|
||||
|
||||
const bool needsHyphen = info.requiresInsertedHyphen;
|
||||
const int prefixWidth = measureWordWidth(renderer, fontId, word.substr(0, offset), style, needsHyphen);
|
||||
const int prefixWidth = measureWordWidth(renderer, fontId, word.substr(0, offset), wordStyle, needsHyphen);
|
||||
if (prefixWidth > availableWidth || prefixWidth <= chosenWidth) {
|
||||
continue; // Skip if too wide or not an improvement
|
||||
}
|
||||
@ -325,20 +320,18 @@ bool ParsedText::hyphenateWordAtIndex(const size_t wordIndex, const int availabl
|
||||
|
||||
// Split the word at the selected breakpoint and append a hyphen if required.
|
||||
std::string remainder = word.substr(chosenOffset);
|
||||
wordIt->resize(chosenOffset);
|
||||
words[wordIndex].resize(chosenOffset);
|
||||
if (chosenNeedsHyphen) {
|
||||
wordIt->push_back('-');
|
||||
words[wordIndex].push_back('-');
|
||||
}
|
||||
|
||||
// Insert the remainder word (with matching style) directly after the prefix.
|
||||
auto insertWordIt = std::next(wordIt);
|
||||
auto insertStyleIt = std::next(styleIt);
|
||||
words.insert(insertWordIt, remainder);
|
||||
wordStyles.insert(insertStyleIt, style);
|
||||
words.insert(words.begin() + wordIndex + 1, remainder);
|
||||
wordStyles.insert(wordStyles.begin() + wordIndex + 1, wordStyle);
|
||||
|
||||
// Update cached widths to reflect the new prefix/remainder pairing.
|
||||
wordWidths[wordIndex] = static_cast<uint16_t>(chosenWidth);
|
||||
const uint16_t remainderWidth = measureWordWidth(renderer, fontId, remainder, style);
|
||||
const uint16_t remainderWidth = measureWordWidth(renderer, fontId, remainder, wordStyle);
|
||||
wordWidths.insert(wordWidths.begin() + wordIndex + 1, remainderWidth);
|
||||
return true;
|
||||
}
|
||||
@ -375,28 +368,30 @@ void ParsedText::extractLine(const size_t breakIndex, const int pageWidth, const
|
||||
}
|
||||
|
||||
// Pre-calculate X positions for words
|
||||
std::list<uint16_t> lineXPos;
|
||||
std::vector<uint16_t> lineXPos;
|
||||
lineXPos.reserve(lineWordCount);
|
||||
for (size_t i = lastBreakAt; i < lineBreak; i++) {
|
||||
const uint16_t currentWordWidth = wordWidths[i];
|
||||
lineXPos.push_back(xpos);
|
||||
xpos += currentWordWidth + spacing;
|
||||
}
|
||||
|
||||
// Iterators always start at the beginning as we are moving content with splice below
|
||||
auto wordEndIt = words.begin();
|
||||
auto wordStyleEndIt = wordStyles.begin();
|
||||
auto wordUnderlineEndIt = wordUnderlines.begin();
|
||||
std::advance(wordEndIt, lineWordCount);
|
||||
std::advance(wordStyleEndIt, lineWordCount);
|
||||
std::advance(wordUnderlineEndIt, lineWordCount);
|
||||
// *** CRITICAL STEP: CONSUME DATA USING MOVE + ERASE ***
|
||||
// Move first lineWordCount elements from words into lineWords
|
||||
std::vector<std::string> lineWords(
|
||||
std::make_move_iterator(words.begin()),
|
||||
std::make_move_iterator(words.begin() + lineWordCount));
|
||||
words.erase(words.begin(), words.begin() + lineWordCount);
|
||||
|
||||
// *** CRITICAL STEP: CONSUME DATA USING SPLICE ***
|
||||
std::list<std::string> lineWords;
|
||||
lineWords.splice(lineWords.begin(), words, words.begin(), wordEndIt);
|
||||
std::list<EpdFontFamily::Style> lineWordStyles;
|
||||
lineWordStyles.splice(lineWordStyles.begin(), wordStyles, wordStyles.begin(), wordStyleEndIt);
|
||||
std::list<bool> lineWordUnderlines;
|
||||
lineWordUnderlines.splice(lineWordUnderlines.begin(), wordUnderlines, wordUnderlines.begin(), wordUnderlineEndIt);
|
||||
std::vector<EpdFontFamily::Style> lineWordStyles(
|
||||
std::make_move_iterator(wordStyles.begin()),
|
||||
std::make_move_iterator(wordStyles.begin() + lineWordCount));
|
||||
wordStyles.erase(wordStyles.begin(), wordStyles.begin() + lineWordCount);
|
||||
|
||||
std::vector<bool> lineWordUnderlines(
|
||||
wordUnderlines.begin(),
|
||||
wordUnderlines.begin() + lineWordCount);
|
||||
wordUnderlines.erase(wordUnderlines.begin(), wordUnderlines.begin() + lineWordCount);
|
||||
|
||||
for (auto& word : lineWords) {
|
||||
if (containsSoftHyphen(word)) {
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
#include <EpdFontFamily.h>
|
||||
|
||||
#include <functional>
|
||||
#include <list>
|
||||
#include <memory>
|
||||
#include <string>
|
||||
#include <vector>
|
||||
@ -14,9 +13,9 @@
|
||||
class GfxRenderer;
|
||||
|
||||
class ParsedText {
|
||||
std::list<std::string> words;
|
||||
std::list<EpdFontFamily::Style> wordStyles;
|
||||
std::list<bool> wordUnderlines; // Track underline per word
|
||||
std::vector<std::string> words;
|
||||
std::vector<EpdFontFamily::Style> wordStyles;
|
||||
std::vector<bool> wordUnderlines; // Track underline per word
|
||||
TextBlock::Style style;
|
||||
BlockStyle blockStyle;
|
||||
bool extraParagraphSpacing;
|
||||
|
||||
@ -98,23 +98,23 @@ bool TextBlock::serialize(FsFile& file) const {
|
||||
|
||||
std::unique_ptr<TextBlock> TextBlock::deserialize(FsFile& file) {
|
||||
uint16_t wc;
|
||||
std::list<std::string> words;
|
||||
std::list<uint16_t> wordXpos;
|
||||
std::list<EpdFontFamily::Style> wordStyles;
|
||||
std::list<bool> wordUnderlines;
|
||||
std::vector<std::string> words;
|
||||
std::vector<uint16_t> wordXpos;
|
||||
std::vector<EpdFontFamily::Style> wordStyles;
|
||||
std::vector<bool> wordUnderlines;
|
||||
Style style;
|
||||
BlockStyle blockStyle;
|
||||
|
||||
// Word count
|
||||
serialization::readPod(file, wc);
|
||||
|
||||
// Sanity check: prevent allocation of unreasonably large lists (max 10000 words per block)
|
||||
// Sanity check: prevent allocation of unreasonably large vectors (max 10000 words per block)
|
||||
if (wc > 10000) {
|
||||
Serial.printf("[%lu] [TXB] Deserialization failed: word count %u exceeds maximum\n", millis(), wc);
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
// Word data
|
||||
// Word data - reserve capacity then resize
|
||||
words.resize(wc);
|
||||
wordXpos.resize(wc);
|
||||
wordStyles.resize(wc);
|
||||
@ -124,14 +124,14 @@ std::unique_ptr<TextBlock> TextBlock::deserialize(FsFile& file) {
|
||||
|
||||
// Underline flags (packed as bytes, 8 words per byte)
|
||||
wordUnderlines.resize(wc, false);
|
||||
auto underlineIt = wordUnderlines.begin();
|
||||
size_t underlineIdx = 0;
|
||||
const int bytesNeeded = (wc + 7) / 8;
|
||||
for (int byteIdx = 0; byteIdx < bytesNeeded; byteIdx++) {
|
||||
uint8_t underlineByte;
|
||||
serialization::readPod(file, underlineByte);
|
||||
for (int bit = 0; bit < 8 && underlineIt != wordUnderlines.end(); bit++) {
|
||||
*underlineIt = (underlineByte & 1 << bit) != 0;
|
||||
++underlineIt;
|
||||
for (int bit = 0; bit < 8 && underlineIdx < wc; bit++) {
|
||||
wordUnderlines[underlineIdx] = (underlineByte & (1 << bit)) != 0;
|
||||
++underlineIdx;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -2,7 +2,7 @@
|
||||
#include <EpdFontFamily.h>
|
||||
#include <SdFat.h>
|
||||
|
||||
#include <list>
|
||||
#include <vector>
|
||||
#include <memory>
|
||||
#include <string>
|
||||
|
||||
@ -20,17 +20,17 @@ class TextBlock final : public Block {
|
||||
};
|
||||
|
||||
private:
|
||||
std::list<std::string> words;
|
||||
std::list<uint16_t> wordXpos;
|
||||
std::list<EpdFontFamily::Style> wordStyles;
|
||||
std::list<bool> wordUnderlines; // Track underline per word
|
||||
std::vector<std::string> words;
|
||||
std::vector<uint16_t> wordXpos;
|
||||
std::vector<EpdFontFamily::Style> wordStyles;
|
||||
std::vector<bool> wordUnderlines; // Track underline per word
|
||||
Style style;
|
||||
BlockStyle blockStyle;
|
||||
|
||||
public:
|
||||
explicit TextBlock(std::list<std::string> words, std::list<uint16_t> word_xpos,
|
||||
std::list<EpdFontFamily::Style> word_styles, const Style style,
|
||||
const BlockStyle& blockStyle = BlockStyle(), std::list<bool> word_underlines = std::list<bool>())
|
||||
explicit TextBlock(std::vector<std::string> words, std::vector<uint16_t> word_xpos,
|
||||
std::vector<EpdFontFamily::Style> word_styles, const Style style,
|
||||
const BlockStyle& blockStyle = BlockStyle(), std::vector<bool> word_underlines = std::vector<bool>())
|
||||
: words(std::move(words)),
|
||||
wordXpos(std::move(word_xpos)),
|
||||
wordStyles(std::move(word_styles)),
|
||||
@ -50,9 +50,9 @@ class TextBlock final : public Block {
|
||||
bool isEmpty() override { return words.empty(); }
|
||||
|
||||
// Getters for word selection support
|
||||
const std::list<std::string>& getWords() const { return words; }
|
||||
const std::list<uint16_t>& getWordXPositions() const { return wordXpos; }
|
||||
const std::list<EpdFontFamily::Style>& getWordStyles() const { return wordStyles; }
|
||||
const std::vector<std::string>& getWords() const { return words; }
|
||||
const std::vector<uint16_t>& getWordXPositions() const { return wordXpos; }
|
||||
const std::vector<EpdFontFamily::Style>& getWordStyles() const { return wordStyles; }
|
||||
size_t getWordCount() const { return words.size(); }
|
||||
void layout(GfxRenderer& renderer) override {};
|
||||
// given a renderer works out where to break the words into lines
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user