Maik Allgöwer
72ca7ec63c
I've been reading "Children of Time" over the last days and that book, annyoingly, has some tabular content. This content is relevant for the story so I needed some really basic way to at least be able to read those tables. This commit simply renders the contents of table cells as separate paragraphs with a small header describing its position in the table. For me, it's better than nothing. ## Summary * **What is the goal of this PR?** Implements really basic table support * **What changes are included?** * Minimal changes to ChapterHtmlSlimParser * A demo book in test/epubs ## Additional Context Here's some screenshots of the demo-book I provide with this PR.   --- ### 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**_ _Little bit of guidance on what to touch, parts of the impl, rest manually._
110 lines
3.9 KiB
C++
110 lines
3.9 KiB
C++
#pragma once
|
|
|
|
#include <expat.h>
|
|
|
|
#include <climits>
|
|
#include <functional>
|
|
#include <memory>
|
|
|
|
#include "../ParsedText.h"
|
|
#include "../blocks/ImageBlock.h"
|
|
#include "../blocks/TextBlock.h"
|
|
#include "../css/CssParser.h"
|
|
#include "../css/CssStyle.h"
|
|
|
|
class Page;
|
|
class GfxRenderer;
|
|
class Epub;
|
|
|
|
#define MAX_WORD_SIZE 200
|
|
|
|
class ChapterHtmlSlimParser {
|
|
std::shared_ptr<Epub> epub;
|
|
const std::string& filepath;
|
|
GfxRenderer& renderer;
|
|
std::function<void(std::unique_ptr<Page>)> completePageFn;
|
|
std::function<void()> popupFn; // Popup callback
|
|
int depth = 0;
|
|
int skipUntilDepth = INT_MAX;
|
|
int boldUntilDepth = INT_MAX;
|
|
int italicUntilDepth = INT_MAX;
|
|
int underlineUntilDepth = INT_MAX;
|
|
// buffer for building up words from characters, will auto break if longer than this
|
|
// leave one char at end for null pointer
|
|
char partWordBuffer[MAX_WORD_SIZE + 1] = {};
|
|
int partWordBufferIndex = 0;
|
|
bool nextWordContinues = false; // true when next flushed word attaches to previous (inline element boundary)
|
|
std::unique_ptr<ParsedText> currentTextBlock = nullptr;
|
|
std::unique_ptr<Page> currentPage = nullptr;
|
|
int16_t currentPageNextY = 0;
|
|
int fontId;
|
|
float lineCompression;
|
|
bool extraParagraphSpacing;
|
|
uint8_t paragraphAlignment;
|
|
uint16_t viewportWidth;
|
|
uint16_t viewportHeight;
|
|
bool hyphenationEnabled;
|
|
const CssParser* cssParser;
|
|
bool embeddedStyle;
|
|
std::string contentBase;
|
|
std::string imageBasePath;
|
|
int imageCounter = 0;
|
|
|
|
// Style tracking (replaces depth-based approach)
|
|
struct StyleStackEntry {
|
|
int depth = 0;
|
|
bool hasBold = false, bold = false;
|
|
bool hasItalic = false, italic = false;
|
|
bool hasUnderline = false, underline = false;
|
|
};
|
|
std::vector<StyleStackEntry> inlineStyleStack;
|
|
CssStyle currentCssStyle;
|
|
bool effectiveBold = false;
|
|
bool effectiveItalic = false;
|
|
bool effectiveUnderline = false;
|
|
int tableDepth = 0;
|
|
int tableRowIndex = 0;
|
|
int tableColIndex = 0;
|
|
|
|
void updateEffectiveInlineStyle();
|
|
void startNewTextBlock(const BlockStyle& blockStyle);
|
|
void flushPartWordBuffer();
|
|
void makePages();
|
|
// XML callbacks
|
|
static void XMLCALL startElement(void* userData, const XML_Char* name, const XML_Char** atts);
|
|
static void XMLCALL characterData(void* userData, const XML_Char* s, int len);
|
|
static void XMLCALL defaultHandlerExpand(void* userData, const XML_Char* s, int len);
|
|
static void XMLCALL endElement(void* userData, const XML_Char* name);
|
|
|
|
public:
|
|
explicit ChapterHtmlSlimParser(std::shared_ptr<Epub> epub, const std::string& filepath, GfxRenderer& renderer,
|
|
const int fontId, const float lineCompression, const bool extraParagraphSpacing,
|
|
const uint8_t paragraphAlignment, const uint16_t viewportWidth,
|
|
const uint16_t viewportHeight, const bool hyphenationEnabled,
|
|
const std::function<void(std::unique_ptr<Page>)>& completePageFn,
|
|
const bool embeddedStyle, const std::string& contentBase,
|
|
const std::string& imageBasePath, const std::function<void()>& popupFn = nullptr,
|
|
const CssParser* cssParser = nullptr)
|
|
|
|
: epub(epub),
|
|
filepath(filepath),
|
|
renderer(renderer),
|
|
fontId(fontId),
|
|
lineCompression(lineCompression),
|
|
extraParagraphSpacing(extraParagraphSpacing),
|
|
paragraphAlignment(paragraphAlignment),
|
|
viewportWidth(viewportWidth),
|
|
viewportHeight(viewportHeight),
|
|
hyphenationEnabled(hyphenationEnabled),
|
|
completePageFn(completePageFn),
|
|
popupFn(popupFn),
|
|
cssParser(cssParser),
|
|
embeddedStyle(embeddedStyle),
|
|
contentBase(contentBase),
|
|
imageBasePath(imageBasePath) {}
|
|
|
|
~ChapterHtmlSlimParser() = default;
|
|
bool parseAndBuildPages();
|
|
void addLineToPage(std::shared_ptr<TextBlock> line);
|
|
};
|