Files
Crosspoint/lib/Epub/Epub/parsers/TocNavParser.cpp
T
Julia bd101b2af8 fix(epub): decode percent-encoded internal asset paths so assets render correctly (#2249)
## Summary

* **What is the goal of this PR?** 
* Fix EPUBs where internal file references are written in URL-style
escaped form, like spaces appearing as `%20`, so the reader can find the
right files instead of treating those references as missing.
* **What changes are included?**
* Added a small shared helper that converts those escaped EPUB-internal
paths back into their normal filenames before we try to look them up.
* Applied that cleanup step across the EPUB parsing flow wherever we
resolve internal references, including cover images, manifest items, TOC
links, spine entries, and inline HTML images.
* Kept the change narrowly focused on EPUB-internal asset resolution
rather than changing broader URL or networking behavior.

## Additional Context

* The user-facing bug here is that some books package their internal
filenames in an escaped form, so a file like `Chapter 1.xhtml` may be
referenced more like `Chapter%201.xhtml`. The reader was treating that
escaped text as the literal filename, which means otherwise-valid books
could lose images, covers, or chapter targets because the lookup no
longer matched the real file inside the EPUB.
* Risk is intentionally low. The helper only rewrites valid `%XX` escape
sequences and leaves malformed input alone, so it should improve
compatibility with escaped filenames without broadening the parser’s
behavior in unrelated cases.

## Local Testing Performed
* This was tested on my device with the user-provided optimized epub
that was not rendering images within the text prior to this fix (cover
image and chapter headers were rendering fine):

[orv_main_baseline.epub.zip](https://github.com/user-attachments/files/28529545/orv_main_baseline.epub.zip)
* This was also tested by the user with a local build and the affected
epub and confirmed to be working

## Steps for Testing
* Try to open the affected epub (linked above) or any epub that has
similar percent-encoding on a build prior to this fix.
* Apply this fix, clear book cache, and re-open the affected book.
* Images should render properly.
---

### 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? _**< YES >**_
2026-06-05 10:31:20 -04:00

172 lines
4.8 KiB
C++

#include "TocNavParser.h"
#include <FsHelpers.h>
#include <Logging.h>
#include <XmlParserUtils.h>
#include "Epub/BookMetadataCache.h"
bool TocNavParser::setup() {
parser = XML_ParserCreate(nullptr);
if (!parser) {
LOG_DBG("NAV", "Couldn't allocate memory for parser");
return false;
}
XML_SetUserData(parser, this);
XML_SetElementHandler(parser, startElement, endElement);
XML_SetCharacterDataHandler(parser, characterData);
return true;
}
TocNavParser::~TocNavParser() { destroyXmlParser(parser); }
size_t TocNavParser::write(const uint8_t data) { return write(&data, 1); }
size_t TocNavParser::write(const uint8_t* buffer, const size_t size) {
if (!parser) return 0;
const uint8_t* currentBufferPos = buffer;
auto remainingInBuffer = size;
while (remainingInBuffer > 0) {
void* const buf = XML_GetBuffer(parser, 1024);
if (!buf) {
LOG_DBG("NAV", "Couldn't allocate memory for buffer");
destroyXmlParser(parser);
return 0;
}
const auto toRead = remainingInBuffer < 1024 ? remainingInBuffer : 1024;
memcpy(buf, currentBufferPos, toRead);
if (XML_ParseBuffer(parser, static_cast<int>(toRead), remainingSize == toRead) == XML_STATUS_ERROR) {
LOG_DBG("NAV", "Parse error at line %lu: %s", XML_GetCurrentLineNumber(parser),
XML_ErrorString(XML_GetErrorCode(parser)));
destroyXmlParser(parser);
return 0;
}
currentBufferPos += toRead;
remainingInBuffer -= toRead;
remainingSize -= toRead;
}
return size;
}
void XMLCALL TocNavParser::startElement(void* userData, const XML_Char* name, const XML_Char** atts) {
auto* self = static_cast<TocNavParser*>(userData);
// Track HTML structure loosely - we mainly care about finding <nav epub:type="toc">
if (strcmp(name, "html") == 0) {
self->state = IN_HTML;
return;
}
if (self->state == IN_HTML && strcmp(name, "body") == 0) {
self->state = IN_BODY;
return;
}
// Look for <nav epub:type="toc"> anywhere in body (or nested elements)
if (self->state >= IN_BODY && strcmp(name, "nav") == 0) {
for (int i = 0; atts[i]; i += 2) {
if ((strcmp(atts[i], "epub:type") == 0 || strcmp(atts[i], "type") == 0) && strcmp(atts[i + 1], "toc") == 0) {
self->state = IN_NAV_TOC;
LOG_DBG("NAV", "Found nav toc element");
return;
}
}
return;
}
// Only process ol/li/a if we're inside the toc nav
if (self->state < IN_NAV_TOC) {
return;
}
if (strcmp(name, "ol") == 0) {
self->olDepth++;
self->state = IN_OL;
return;
}
if (self->state == IN_OL && strcmp(name, "li") == 0) {
self->state = IN_LI;
self->currentLabel.clear();
self->currentHref.clear();
return;
}
if (self->state == IN_LI && strcmp(name, "a") == 0) {
self->state = IN_ANCHOR;
// Get href attribute
for (int i = 0; atts[i]; i += 2) {
if (strcmp(atts[i], "href") == 0) {
self->currentHref = atts[i + 1];
break;
}
}
return;
}
}
void XMLCALL TocNavParser::characterData(void* userData, const XML_Char* s, const int len) {
auto* self = static_cast<TocNavParser*>(userData);
// Only collect text when inside an anchor within the TOC nav
if (self->state == IN_ANCHOR) {
self->currentLabel.append(s, len);
}
}
void XMLCALL TocNavParser::endElement(void* userData, const XML_Char* name) {
auto* self = static_cast<TocNavParser*>(userData);
if (strcmp(name, "a") == 0 && self->state == IN_ANCHOR) {
// Create TOC entry when closing anchor tag (we have all data now)
if (!self->currentLabel.empty() && !self->currentHref.empty()) {
const std::string rawTarget = self->baseContentPath + self->currentHref;
const size_t pos = rawTarget.find('#');
const std::string rawPath = pos == std::string::npos ? rawTarget : rawTarget.substr(0, pos);
std::string href = FsHelpers::normalisePath(FsHelpers::decodeUriEscapes(rawPath));
std::string anchor;
if (pos != std::string::npos) {
anchor = FsHelpers::decodeUriEscapes(rawTarget.substr(pos + 1));
}
if (self->cache) {
// olDepth gives us the nesting level (1-based from the outer ol)
self->cache->createTocEntry(self->currentLabel, href, anchor, self->olDepth);
}
self->currentLabel.clear();
self->currentHref.clear();
}
self->state = IN_LI;
return;
}
if (strcmp(name, "li") == 0 && (self->state == IN_LI || self->state == IN_OL)) {
self->state = IN_OL;
return;
}
if (strcmp(name, "ol") == 0 && self->state >= IN_NAV_TOC) {
self->olDepth--;
if (self->olDepth == 0) {
self->state = IN_NAV_TOC;
} else {
self->state = IN_LI; // Back to parent li
}
return;
}
if (strcmp(name, "nav") == 0 && self->state >= IN_NAV_TOC) {
self->state = IN_BODY;
LOG_DBG("NAV", "Finished parsing nav toc");
return;
}
}