mirror of
https://github.com/daveallie/crosspoint-reader.git
synced 2025-12-18 15:17:42 +03:00
282 lines
8.8 KiB
C++
282 lines
8.8 KiB
C++
#include "ChapterHtmlSlimParser.h"
|
|
|
|
#include <GfxRenderer.h>
|
|
#include <HardwareSerial.h>
|
|
#include <expat.h>
|
|
|
|
#include "../Page.h"
|
|
#include "../htmlEntities.h"
|
|
|
|
const char* HEADER_TAGS[] = {"h1", "h2", "h3", "h4", "h5", "h6"};
|
|
constexpr int NUM_HEADER_TAGS = sizeof(HEADER_TAGS) / sizeof(HEADER_TAGS[0]);
|
|
|
|
const char* BLOCK_TAGS[] = {"p", "li", "div", "br"};
|
|
constexpr int NUM_BLOCK_TAGS = sizeof(BLOCK_TAGS) / sizeof(BLOCK_TAGS[0]);
|
|
|
|
const char* BOLD_TAGS[] = {"b"};
|
|
constexpr int NUM_BOLD_TAGS = sizeof(BOLD_TAGS) / sizeof(BOLD_TAGS[0]);
|
|
|
|
const char* ITALIC_TAGS[] = {"i"};
|
|
constexpr int NUM_ITALIC_TAGS = sizeof(ITALIC_TAGS) / sizeof(ITALIC_TAGS[0]);
|
|
|
|
const char* IMAGE_TAGS[] = {"img"};
|
|
constexpr int NUM_IMAGE_TAGS = sizeof(IMAGE_TAGS) / sizeof(IMAGE_TAGS[0]);
|
|
|
|
const char* SKIP_TAGS[] = {"head", "table"};
|
|
constexpr int NUM_SKIP_TAGS = sizeof(SKIP_TAGS) / sizeof(SKIP_TAGS[0]);
|
|
|
|
bool isWhitespace(const char c) { return c == ' ' || c == '\r' || c == '\n' || c == '\t'; }
|
|
|
|
// given the start and end of a tag, check to see if it matches a known tag
|
|
bool matches(const char* tag_name, const char* possible_tags[], const int possible_tag_count) {
|
|
for (int i = 0; i < possible_tag_count; i++) {
|
|
if (strcmp(tag_name, possible_tags[i]) == 0) {
|
|
return true;
|
|
}
|
|
}
|
|
return false;
|
|
}
|
|
|
|
// start a new text block if needed
|
|
void ChapterHtmlSlimParser::startNewTextBlock(const TextBlock::BLOCK_STYLE style) {
|
|
if (currentTextBlock) {
|
|
// already have a text block running and it is empty - just reuse it
|
|
if (currentTextBlock->isEmpty()) {
|
|
currentTextBlock->setStyle(style);
|
|
return;
|
|
}
|
|
|
|
makePages();
|
|
}
|
|
currentTextBlock.reset(new ParsedText(style));
|
|
}
|
|
|
|
void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char* name, const XML_Char** atts) {
|
|
auto* self = static_cast<ChapterHtmlSlimParser*>(userData);
|
|
(void)atts;
|
|
|
|
// Middle of skip
|
|
if (self->skipUntilDepth < self->depth) {
|
|
self->depth += 1;
|
|
return;
|
|
}
|
|
|
|
if (matches(name, IMAGE_TAGS, NUM_IMAGE_TAGS)) {
|
|
// TODO: Start processing image tags
|
|
self->skipUntilDepth = self->depth;
|
|
self->depth += 1;
|
|
return;
|
|
}
|
|
|
|
if (matches(name, SKIP_TAGS, NUM_SKIP_TAGS)) {
|
|
// start skip
|
|
self->skipUntilDepth = self->depth;
|
|
self->depth += 1;
|
|
return;
|
|
}
|
|
|
|
if (matches(name, HEADER_TAGS, NUM_HEADER_TAGS)) {
|
|
self->startNewTextBlock(TextBlock::CENTER_ALIGN);
|
|
self->boldUntilDepth = min(self->boldUntilDepth, self->depth);
|
|
} else if (matches(name, BLOCK_TAGS, NUM_BLOCK_TAGS)) {
|
|
if (strcmp(name, "br") == 0) {
|
|
self->startNewTextBlock(self->currentTextBlock->getStyle());
|
|
} else {
|
|
self->startNewTextBlock(TextBlock::JUSTIFIED);
|
|
}
|
|
} else if (matches(name, BOLD_TAGS, NUM_BOLD_TAGS)) {
|
|
self->boldUntilDepth = min(self->boldUntilDepth, self->depth);
|
|
} else if (matches(name, ITALIC_TAGS, NUM_ITALIC_TAGS)) {
|
|
self->italicUntilDepth = min(self->italicUntilDepth, self->depth);
|
|
}
|
|
|
|
self->depth += 1;
|
|
}
|
|
|
|
void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char* s, const int len) {
|
|
auto* self = static_cast<ChapterHtmlSlimParser*>(userData);
|
|
|
|
// Middle of skip
|
|
if (self->skipUntilDepth < self->depth) {
|
|
return;
|
|
}
|
|
|
|
EpdFontStyle fontStyle = REGULAR;
|
|
if (self->boldUntilDepth < self->depth && self->italicUntilDepth < self->depth) {
|
|
fontStyle = BOLD_ITALIC;
|
|
} else if (self->boldUntilDepth < self->depth) {
|
|
fontStyle = BOLD;
|
|
} else if (self->italicUntilDepth < self->depth) {
|
|
fontStyle = ITALIC;
|
|
}
|
|
|
|
for (int i = 0; i < len; i++) {
|
|
if (isWhitespace(s[i])) {
|
|
// Currently looking at whitespace, if there's anything in the partWordBuffer, flush it
|
|
if (self->partWordBufferIndex > 0) {
|
|
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
|
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
|
self->partWordBufferIndex = 0;
|
|
}
|
|
// Skip the whitespace char
|
|
continue;
|
|
}
|
|
|
|
// 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) {
|
|
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
|
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
|
self->partWordBufferIndex = 0;
|
|
}
|
|
|
|
self->partWordBuffer[self->partWordBufferIndex++] = s[i];
|
|
}
|
|
}
|
|
|
|
void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* name) {
|
|
auto* self = static_cast<ChapterHtmlSlimParser*>(userData);
|
|
(void)name;
|
|
|
|
if (self->partWordBufferIndex > 0) {
|
|
// Only flush out part word buffer if we're closing a block tag or are at the top of the HTML file.
|
|
// We don't want to flush out content when closing inline tags like <span>.
|
|
// Currently this also flushes out on closing <b> and <i> tags, but they are line tags so that shouldn't happen,
|
|
// text styling needs to be overhauled to fix it.
|
|
const bool shouldBreakText =
|
|
matches(name, BLOCK_TAGS, NUM_BLOCK_TAGS) || matches(name, HEADER_TAGS, NUM_HEADER_TAGS) ||
|
|
matches(name, BOLD_TAGS, NUM_BOLD_TAGS) || matches(name, ITALIC_TAGS, NUM_ITALIC_TAGS) || self->depth == 1;
|
|
|
|
if (shouldBreakText) {
|
|
EpdFontStyle fontStyle = REGULAR;
|
|
if (self->boldUntilDepth < self->depth && self->italicUntilDepth < self->depth) {
|
|
fontStyle = BOLD_ITALIC;
|
|
} else if (self->boldUntilDepth < self->depth) {
|
|
fontStyle = BOLD;
|
|
} else if (self->italicUntilDepth < self->depth) {
|
|
fontStyle = ITALIC;
|
|
}
|
|
|
|
self->partWordBuffer[self->partWordBufferIndex] = '\0';
|
|
self->currentTextBlock->addWord(std::move(replaceHtmlEntities(self->partWordBuffer)), fontStyle);
|
|
self->partWordBufferIndex = 0;
|
|
}
|
|
}
|
|
|
|
self->depth -= 1;
|
|
|
|
// Leaving skip
|
|
if (self->skipUntilDepth == self->depth) {
|
|
self->skipUntilDepth = INT_MAX;
|
|
}
|
|
|
|
// Leaving bold
|
|
if (self->boldUntilDepth == self->depth) {
|
|
self->boldUntilDepth = INT_MAX;
|
|
}
|
|
|
|
// Leaving italic
|
|
if (self->italicUntilDepth == self->depth) {
|
|
self->italicUntilDepth = INT_MAX;
|
|
}
|
|
}
|
|
|
|
bool ChapterHtmlSlimParser::parseAndBuildPages() {
|
|
startNewTextBlock(TextBlock::JUSTIFIED);
|
|
|
|
const XML_Parser parser = XML_ParserCreate(nullptr);
|
|
int done;
|
|
|
|
if (!parser) {
|
|
Serial.printf("[%lu] [EHP] Couldn't allocate memory for parser\n", millis());
|
|
return false;
|
|
}
|
|
|
|
XML_SetUserData(parser, this);
|
|
XML_SetElementHandler(parser, startElement, endElement);
|
|
XML_SetCharacterDataHandler(parser, characterData);
|
|
|
|
FILE* file = fopen(filepath, "r");
|
|
if (!file) {
|
|
Serial.printf("[%lu] [EHP] Couldn't open file %s\n", millis(), filepath);
|
|
XML_ParserFree(parser);
|
|
return false;
|
|
}
|
|
|
|
do {
|
|
void* const buf = XML_GetBuffer(parser, 1024);
|
|
if (!buf) {
|
|
Serial.printf("[%lu] [EHP] Couldn't allocate memory for buffer\n", millis());
|
|
XML_ParserFree(parser);
|
|
fclose(file);
|
|
return false;
|
|
}
|
|
|
|
const size_t len = fread(buf, 1, 1024, file);
|
|
|
|
if (ferror(file)) {
|
|
Serial.printf("[%lu] [EHP] File read error\n", millis());
|
|
XML_ParserFree(parser);
|
|
fclose(file);
|
|
return false;
|
|
}
|
|
|
|
done = feof(file);
|
|
|
|
if (XML_ParseBuffer(parser, static_cast<int>(len), done) == XML_STATUS_ERROR) {
|
|
Serial.printf("[%lu] [EHP] Parse error at line %lu:\n%s\n", millis(), XML_GetCurrentLineNumber(parser),
|
|
XML_ErrorString(XML_GetErrorCode(parser)));
|
|
XML_ParserFree(parser);
|
|
fclose(file);
|
|
return false;
|
|
}
|
|
} while (!done);
|
|
|
|
XML_ParserFree(parser);
|
|
fclose(file);
|
|
|
|
// Process last page if there is still text
|
|
if (currentTextBlock) {
|
|
makePages();
|
|
completePageFn(std::move(currentPage));
|
|
currentPage.reset();
|
|
currentTextBlock.reset();
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
void ChapterHtmlSlimParser::addLineToPage(std::shared_ptr<TextBlock> line) {
|
|
const int lineHeight = renderer.getLineHeight(fontId) * lineCompression;
|
|
const int pageHeight = GfxRenderer::getScreenHeight() - marginTop - marginBottom;
|
|
|
|
if (currentPageNextY + lineHeight > pageHeight) {
|
|
completePageFn(std::move(currentPage));
|
|
currentPage.reset(new Page());
|
|
currentPageNextY = marginTop;
|
|
}
|
|
|
|
currentPage->elements.push_back(std::make_shared<PageLine>(line, marginLeft, currentPageNextY));
|
|
currentPageNextY += lineHeight;
|
|
}
|
|
|
|
void ChapterHtmlSlimParser::makePages() {
|
|
if (!currentTextBlock) {
|
|
Serial.printf("[%lu] [EHP] !! No text block to make pages for !!\n", millis());
|
|
return;
|
|
}
|
|
|
|
if (!currentPage) {
|
|
currentPage.reset(new Page());
|
|
currentPageNextY = marginTop;
|
|
}
|
|
|
|
const int lineHeight = renderer.getLineHeight(fontId) * lineCompression;
|
|
currentTextBlock->layoutAndExtractLines(
|
|
renderer, fontId, marginLeft + marginRight,
|
|
[this](const std::shared_ptr<TextBlock>& textBlock) { addLineToPage(textBlock); });
|
|
// Extra paragraph spacing if enabled
|
|
if (extraParagraphSpacing) {
|
|
currentPageNextY += lineHeight / 2;
|
|
}
|
|
}
|