Add expat and swap out EPUB HTML parser (#2)

* Add expat and swap out ERB HTML parser

* Increase EpubHtmlParserSlim file buffer to 1024 bytes

* Cleanup TextBlock functions

* Do not break words when leaving spans

lib/Epub/Epub/EpubHtmlParser.cpp

@@ -1,181 +0,0 @@
-#include "EpubHtmlParser.h"
-
-#include <EpdRenderer.h>
-#include <HardwareSerial.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]);
-
-// 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 EpubHtmlParser::startNewTextBlock(const BLOCK_STYLE style) {
-  if (currentTextBlock) {
-    // already have a text block running and it is empty - just reuse it
-    if (currentTextBlock->isEmpty()) {
-      currentTextBlock->set_style(style);
-      return;
-    }
-
-    currentTextBlock->finish();
-    makePages();
-    delete currentTextBlock;
-  }
-  currentTextBlock = new TextBlock(style);
-}
-
-bool EpubHtmlParser::VisitEnter(const tinyxml2::XMLElement& element, const tinyxml2::XMLAttribute* firstAttribute) {
-  const char* tag_name = element.Name();
-  if (matches(tag_name, IMAGE_TAGS, NUM_IMAGE_TAGS)) {
-    const char* src = element.Attribute("src");
-    if (src) {
-      // don't leave an empty text block in the list
-      // const BLOCK_STYLE style = currentTextBlock->get_style();
-      if (currentTextBlock->isEmpty()) {
-        delete currentTextBlock;
-        currentTextBlock = nullptr;
-      }
-      // TODO: Fix this
-      // blocks.push_back(new ImageBlock(m_base_path + src));
-      // start a new text block - with the same style as before
-      // startNewTextBlock(style);
-    } else {
-      // ESP_LOGE(TAG, "Could not find src attribute");
-    }
-    return false;
-  }
-
-  if (matches(tag_name, SKIP_TAGS, NUM_SKIP_TAGS)) {
-    return false;
-  }
-
-  // Serial.printf("Text: %s\n", element.GetText());
-
-  if (matches(tag_name, HEADER_TAGS, NUM_HEADER_TAGS)) {
-    insideBoldTag = true;
-    startNewTextBlock(CENTER_ALIGN);
-  } else if (matches(tag_name, BLOCK_TAGS, NUM_BLOCK_TAGS)) {
-    if (strcmp(tag_name, "br") == 0) {
-      startNewTextBlock(currentTextBlock->get_style());
-    } else {
-      startNewTextBlock(JUSTIFIED);
-    }
-  } else if (matches(tag_name, BOLD_TAGS, NUM_BOLD_TAGS)) {
-    insideBoldTag = true;
-  } else if (matches(tag_name, ITALIC_TAGS, NUM_ITALIC_TAGS)) {
-    insideItalicTag = true;
-  }
-  return true;
-}
-/// Visit a text node.
-bool EpubHtmlParser::Visit(const tinyxml2::XMLText& text) {
-  const char* content = text.Value();
-  currentTextBlock->addSpan(replaceHtmlEntities(content), insideBoldTag, insideItalicTag);
-  return true;
-}
-
-bool EpubHtmlParser::VisitExit(const tinyxml2::XMLElement& element) {
-  const char* tag_name = element.Name();
-  if (matches(tag_name, HEADER_TAGS, NUM_HEADER_TAGS)) {
-    insideBoldTag = false;
-  } else if (matches(tag_name, BLOCK_TAGS, NUM_BLOCK_TAGS)) {
-    // nothing to do
-  } else if (matches(tag_name, BOLD_TAGS, NUM_BOLD_TAGS)) {
-    insideBoldTag = false;
-  } else if (matches(tag_name, ITALIC_TAGS, NUM_ITALIC_TAGS)) {
-    insideItalicTag = false;
-  }
-  return true;
-}
-
-bool EpubHtmlParser::parseAndBuildPages() {
-  startNewTextBlock(JUSTIFIED);
-  tinyxml2::XMLDocument doc(false, tinyxml2::COLLAPSE_WHITESPACE);
-
-  const tinyxml2::XMLError result = doc.LoadFile(filepath);
-  if (result != tinyxml2::XML_SUCCESS) {
-    Serial.printf("Failed to load file, Error: %s\n", tinyxml2::XMLDocument::ErrorIDToName(result));
-    return false;
-  }
-
-  doc.Accept(this);
-  if (currentTextBlock) {
-    makePages();
-    completePageFn(currentPage);
-    currentPage = nullptr;
-    delete currentTextBlock;
-    currentTextBlock = nullptr;
-  }
-
-  return true;
-}
-
-void EpubHtmlParser::makePages() {
-  if (!currentTextBlock) {
-    Serial.println("!! No text block to make pages for !!");
-    return;
-  }
-
-  if (!currentPage) {
-    currentPage = new Page();
-  }
-
-  const int lineHeight = renderer.getLineHeight();
-  const int pageHeight = renderer.getPageHeight();
-
-  // Long running task, make sure to let other things happen
-  vTaskDelay(1);
-
-  if (currentTextBlock->getType() == TEXT_BLOCK) {
-    const auto lines = currentTextBlock->splitIntoLines(renderer);
-
-    for (const auto line : lines) {
-      if (currentPage->nextY + lineHeight > pageHeight) {
-        completePageFn(currentPage);
-        currentPage = new Page();
-      }
-
-      currentPage->elements.push_back(new PageLine(line, currentPage->nextY));
-      currentPage->nextY += lineHeight;
-    }
-    // TODO: Fix spacing between paras
-    // add some extra line between blocks
-    currentPage->nextY += lineHeight / 2;
-  }
-  // TODO: Image block support
-  // if (block->getType() == BlockType::IMAGE_BLOCK) {
-  //   ImageBlock *imageBlock = (ImageBlock *)block;
-  //   if (y + imageBlock->height > page_height) {
-  //     pages.push_back(new Page());
-  //     y = 0;
-  //   }
-  //   pages.back()->elements.push_back(new PageImage(imageBlock, y));
-  //   y += imageBlock->height;
-  // }
-}

lib/Epub/Epub/EpubHtmlParser.h

@@ -1,34 +0,0 @@
-#pragma once
-#include <tinyxml2.h>
-
-#include <functional>
-
-#include "blocks/TextBlock.h"
-
-class Page;
-class EpdRenderer;
-
-class EpubHtmlParser final : public tinyxml2::XMLVisitor {
-  const char* filepath;
-  EpdRenderer& renderer;
-  std::function<void(Page*)> completePageFn;
-
-  bool insideBoldTag = false;
-  bool insideItalicTag = false;
-  TextBlock* currentTextBlock = nullptr;
-  Page* currentPage = nullptr;
-
-  void startNewTextBlock(BLOCK_STYLE style);
-  void makePages();
-
-  // xml parser callbacks
-  bool VisitEnter(const tinyxml2::XMLElement& element, const tinyxml2::XMLAttribute* firstAttribute) override;
-  bool Visit(const tinyxml2::XMLText& text) override;
-  bool VisitExit(const tinyxml2::XMLElement& element) override;
-  // xml parser callbacks
- public:
-  explicit EpubHtmlParser(const char* filepath, EpdRenderer& renderer, const std::function<void(Page*)>& completePageFn)
-      : filepath(filepath), renderer(renderer), completePageFn(completePageFn) {}
-  ~EpubHtmlParser() override = default;
-  bool parseAndBuildPages();
-};

lib/Epub/Epub/EpubHtmlParserSlim.cpp

@@ -0,0 +1,291 @@
+#include "EpubHtmlParserSlim.h"
+
+#include <EpdRenderer.h>
+#include <HardwareSerial.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'; }
+
+// 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 EpubHtmlParserSlim::startNewTextBlock(const 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;
+    }
+
+    currentTextBlock->finish();
+    makePages();
+    delete currentTextBlock;
+  }
+  currentTextBlock = new TextBlock(style);
+}
+
+#include <expat.h>
+
+void XMLCALL EpubHtmlParserSlim::startElement(void* userData, const XML_Char* name, const XML_Char** atts) {
+  auto* self = static_cast<EpubHtmlParserSlim*>(userData);
+  (void)atts;
+
+  // Middle of skip
+  if (self->skipUntilDepth < self->depth) {
+    self->depth += 1;
+    return;
+  }
+
+  if (matches(name, IMAGE_TAGS, NUM_IMAGE_TAGS)) {
+    // const char* src = element.Attribute("src");
+    // if (src) {
+    //   // don't leave an empty text block in the list
+    //   // const BLOCK_STYLE style = currentTextBlock->get_style();
+    //   if (currentTextBlock->isEmpty()) {
+    //     delete currentTextBlock;
+    //     currentTextBlock = nullptr;
+    //   }
+    //   // TODO: Fix this
+    //   // blocks.push_back(new ImageBlock(m_base_path + src));
+    //   // start a new text block - with the same style as before
+    //   // startNewTextBlock(style);
+    // } else {
+    //   // ESP_LOGE(TAG, "Could not find src attribute");
+    // }
+
+    // start skip
+    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(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(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 EpubHtmlParserSlim::characterData(void* userData, const XML_Char* s, const int len) {
+  auto* self = static_cast<EpubHtmlParserSlim*>(userData);
+
+  // Middle of skip
+  if (self->skipUntilDepth < self->depth) {
+    return;
+  }
+
+  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(replaceHtmlEntities(self->partWordBuffer), self->boldUntilDepth < self->depth,
+                                        self->italicUntilDepth < self->depth);
+        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 >= PART_WORD_BUFFER_SIZE - 2) {
+      self->partWordBuffer[self->partWordBufferIndex] = '\0';
+      self->currentTextBlock->addWord(replaceHtmlEntities(self->partWordBuffer), self->boldUntilDepth < self->depth,
+                                      self->italicUntilDepth < self->depth);
+      self->partWordBufferIndex = 0;
+    }
+
+    self->partWordBuffer[self->partWordBufferIndex++] = s[i];
+  }
+}
+
+void XMLCALL EpubHtmlParserSlim::endElement(void* userData, const XML_Char* name) {
+  auto* self = static_cast<EpubHtmlParserSlim*>(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) {
+      self->partWordBuffer[self->partWordBufferIndex] = '\0';
+      self->currentTextBlock->addWord(replaceHtmlEntities(self->partWordBuffer), self->boldUntilDepth < self->depth,
+                                      self->italicUntilDepth < self->depth);
+      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 EpubHtmlParserSlim::parseAndBuildPages() {
+  startNewTextBlock(JUSTIFIED);
+
+  const XML_Parser parser = XML_ParserCreate(nullptr);
+  int done;
+
+  if (!parser) {
+    Serial.println("Couldn't allocate memory for parser");
+    return false;
+  }
+
+  XML_SetUserData(parser, this);
+  XML_SetElementHandler(parser, startElement, endElement);
+  XML_SetCharacterDataHandler(parser, characterData);
+
+  FILE* file = fopen(filepath, "r");
+
+  do {
+    void* const buf = XML_GetBuffer(parser, 1024);
+    if (!buf) {
+      Serial.println("Couldn't allocate memory for buffer");
+      XML_ParserFree(parser);
+      fclose(file);
+      return false;
+    }
+
+    const size_t len = fread(buf, 1, 1024, file);
+
+    if (ferror(file)) {
+      Serial.println("Read error");
+      XML_ParserFree(parser);
+      fclose(file);
+      return false;
+    }
+
+    done = feof(file);
+
+    if (XML_ParseBuffer(parser, static_cast<int>(len), done) == XML_STATUS_ERROR) {
+      Serial.printf("Parse error at line %lu:\n%s\n", 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(currentPage);
+    currentPage = nullptr;
+    delete currentTextBlock;
+    currentTextBlock = nullptr;
+  }
+
+  return true;
+}
+
+void EpubHtmlParserSlim::makePages() {
+  if (!currentTextBlock) {
+    Serial.println("!! No text block to make pages for !!");
+    return;
+  }
+
+  if (!currentPage) {
+    currentPage = new Page();
+  }
+
+  const int lineHeight = renderer.getLineHeight();
+  const int pageHeight = renderer.getPageHeight();
+
+  // Long running task, make sure to let other things happen
+  vTaskDelay(1);
+
+  if (currentTextBlock->getType() == TEXT_BLOCK) {
+    const auto lines = currentTextBlock->splitIntoLines(renderer);
+
+    for (const auto line : lines) {
+      if (currentPage->nextY + lineHeight > pageHeight) {
+        completePageFn(currentPage);
+        currentPage = new Page();
+      }
+
+      currentPage->elements.push_back(new PageLine(line, currentPage->nextY));
+      currentPage->nextY += lineHeight;
+    }
+    // add some extra line between blocks
+    currentPage->nextY += lineHeight / 2;
+  }
+  // TODO: Image block support
+  // if (block->getType() == BlockType::IMAGE_BLOCK) {
+  //   ImageBlock *imageBlock = (ImageBlock *)block;
+  //   if (y + imageBlock->height > page_height) {
+  //     pages.push_back(new Page());
+  //     y = 0;
+  //   }
+  //   pages.back()->elements.push_back(new PageImage(imageBlock, y));
+  //   y += imageBlock->height;
+  // }
+}

lib/Epub/Epub/EpubHtmlParserSlim.h

@@ -0,0 +1,42 @@
+#pragma once
+
+#include <expat.h>
+#include <limits.h>
+
+#include <functional>
+
+#include "blocks/TextBlock.h"
+
+class Page;
+class EpdRenderer;
+
+#define PART_WORD_BUFFER_SIZE 200
+
+class EpubHtmlParserSlim {
+  const char* filepath;
+  EpdRenderer& renderer;
+  std::function<void(Page*)> completePageFn;
+  int depth = 0;
+  int skipUntilDepth = INT_MAX;
+  int boldUntilDepth = INT_MAX;
+  int italicUntilDepth = INT_MAX;
+  // If we encounter words longer than this, but this is pretty large
+  char partWordBuffer[PART_WORD_BUFFER_SIZE] = {};
+  int partWordBufferIndex = 0;
+  TextBlock* currentTextBlock = nullptr;
+  Page* currentPage = nullptr;
+
+  void startNewTextBlock(BLOCK_STYLE style);
+  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 endElement(void* userData, const XML_Char* name);
+
+ public:
+  explicit EpubHtmlParserSlim(const char* filepath, EpdRenderer& renderer,
+                              const std::function<void(Page*)>& completePageFn)
+      : filepath(filepath), renderer(renderer), completePageFn(completePageFn) {}
+  ~EpubHtmlParserSlim() = default;
+  bool parseAndBuildPages();
+};

lib/Epub/Epub/Section.cpp

@@ -5,11 +5,11 @@
 
 #include <fstream>
 
-#include "EpubHtmlParser.h"
+#include "EpubHtmlParserSlim.h"
 #include "Page.h"
 
 void Section::onPageComplete(const Page* page) {
-  Serial.printf("Page %d complete\n", pageCount);
+  Serial.printf("Page %d complete - free mem: %lu\n", pageCount, ESP.getFreeHeap());
 
   const auto filePath = cachePath + "/page_" + std::to_string(pageCount) + ".bin";
 
@@ -75,11 +75,11 @@ bool Section::persistPageDataToSD() {
   }
 
   const auto sdTmpHtmlPath = "/sd" + tmpHtmlPath;
-  auto visitor =
-      EpubHtmlParser(sdTmpHtmlPath.c_str(), renderer, [this](const Page* page) { this->onPageComplete(page); });
 
-  // TODO: Come back and see if mem used here can be lowered?
+  auto visitor =
+      EpubHtmlParserSlim(sdTmpHtmlPath.c_str(), renderer, [this](const Page* page) { this->onPageComplete(page); });
   const bool success = visitor.parseAndBuildPages();
+
   SD.remove(tmpHtmlPath.c_str());
   if (!success) {
     Serial.println("Failed to parse and build pages");

lib/Epub/Epub/blocks/TextBlock.cpp

@@ -3,44 +3,11 @@
 #include <EpdRenderer.h>
 #include <Serialization.h>
 
-static bool isWhitespace(const char c) { return c == ' ' || c == '\r' || c == '\n'; }
+void TextBlock::addWord(const std::string& word, const bool is_bold, const bool is_italic) {
+  if (word.length() == 0) return;
 
-// move past anything that should be considered part of a work
-static int skipWord(const std::string& text, int index, const int length) {
-  while (index < length && !isWhitespace(text[index])) {
-    index++;
-  }
-  return index;
-}
-
-// skip past any white space characters
-static int skipWhitespace(const std::string& html, int index, const int length) {
-  while (index < length && isWhitespace(html[index])) {
-    index++;
-  }
-  return index;
-}
-
-void TextBlock::addSpan(const std::string& span, const bool is_bold, const bool is_italic) {
-  // adding a span to text block
-  // make a copy of the text as we'll modify it
-  const int length = span.length();
-  // const auto text = new char[length + 1];
-  // strcpy(text, span);
-  // work out where each word is in the span
-  int index = 0;
-  while (index < length) {
-    // skip past any whitespace to the start of a word
-    index = skipWhitespace(span, index, length);
-    const int wordStart = index;
-    // find the end of the word
-    index = skipWord(span, index, length);
-    const int wordLength = index - wordStart;
-    if (wordLength > 0) {
-      words.push_back(span.substr(wordStart, wordLength));
-      wordStyles.push_back((is_bold ? BOLD_SPAN : 0) | (is_italic ? ITALIC_SPAN : 0));
-    }
-  }
+  words.push_back(word);
+  wordStyles.push_back((is_bold ? BOLD_SPAN : 0) | (is_italic ? ITALIC_SPAN : 0));
 }
 
 std::list<TextBlock*> TextBlock::splitIntoLines(const EpdRenderer& renderer) {
@@ -189,17 +156,12 @@ std::list<TextBlock*> TextBlock::splitIntoLines(const EpdRenderer& renderer) {
 
 void TextBlock::render(const EpdRenderer& renderer, const int x, const int y) const {
   for (int i = 0; i < words.size(); i++) {
-    // get the style
-    const uint8_t wordStyle = wordStyles[i];
     // render the word
     EpdFontStyle fontStyle = REGULAR;
-    if (wordStyles[i] & BOLD_SPAN) {
-      if (wordStyles[i] & ITALIC_SPAN) {
-        fontStyle = BOLD_ITALIC;
-      } else {
-        fontStyle = BOLD;
-      }
-
+    if (wordStyles[i] & BOLD_SPAN && wordStyles[i] & ITALIC_SPAN) {
+      fontStyle = BOLD_ITALIC;
+    } else if (wordStyles[i] & BOLD_SPAN) {
+      fontStyle = BOLD;
     } else if (wordStyles[i] & ITALIC_SPAN) {
       fontStyle = ITALIC;
     }

lib/Epub/Epub/blocks/TextBlock.h

@@ -30,15 +30,15 @@ class TextBlock final : public Block {
   BLOCK_STYLE style;
 
  public:
-  void addSpan(const std::string& span, bool is_bold, bool is_italic);
   explicit TextBlock(const BLOCK_STYLE style) : style(style) {}
   explicit TextBlock(const std::vector<std::string>& words, const std::vector<uint16_t>& word_xpos,
                      // the styles of each word
                      const std::vector<uint8_t>& word_styles, const BLOCK_STYLE style)
       : words(words), wordXpos(word_xpos), wordStyles(word_styles), style(style) {}
   ~TextBlock() override = default;
-  void set_style(const BLOCK_STYLE style) { this->style = style; }
-  BLOCK_STYLE get_style() const { return style; }
+  void addWord(const std::string& word, bool is_bold, bool is_italic);
+  void setStyle(const BLOCK_STYLE style) { this->style = style; }
+  BLOCK_STYLE getStyle() const { return style; }
   bool isEmpty() override { return words.empty(); }
   void layout(EpdRenderer& renderer) override {};
   // given a renderer works out where to break the words into lines

lib/expat/.gitignore

@@ -0,0 +1,17 @@
+Makefile
+.libs
+*.lo
+Debug
+Debug-w
+Release
+Release-w
+expat.ncb
+expat.opt
+expat.plg
+Debug_static
+Debug-w_static
+Release_static
+Release-w_static
+expat_static.plg
+expatw.plg
+expatw_static.plg

lib/expat/Makefile.am

@@ -0,0 +1,87 @@
+#
+#                          __  __            _
+#                       ___\ \/ /_ __   __ _| |_
+#                      / _ \\  /| '_ \ / _` | __|
+#                     |  __//  \| |_) | (_| | |_
+#                      \___/_/\_\ .__/ \__,_|\__|
+#                               |_| XML parser
+#
+# Copyright (c) 2017-2024 Sebastian Pipping <sebastian@pipping.org>
+# Copyright (c) 2017      Tomasz Kłoczko <kloczek@fedoraproject.org>
+# Copyright (c) 2019      David Loffredo <loffredo@steptools.com>
+# Licensed under the MIT license:
+#
+# Permission is  hereby granted,  free of charge,  to any  person obtaining
+# a  copy  of  this  software   and  associated  documentation  files  (the
+# "Software"),  to  deal in  the  Software  without restriction,  including
+# without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons  to whom  the Software  is  furnished to  do so,  subject to  the
+# following conditions:
+#
+# The above copyright  notice and this permission notice  shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+# EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+include_HEADERS = \
+    ../expat_config.h \
+    expat.h \
+    expat_external.h
+
+lib_LTLIBRARIES = libexpat.la
+if WITH_TESTS
+noinst_LTLIBRARIES = libtestpat.la
+endif
+
+libexpat_la_LDFLAGS = \
+    @AM_LDFLAGS@ \
+    @LIBM@ \
+    -no-undefined \
+    -version-info @LIBCURRENT@:@LIBREVISION@:@LIBAGE@
+
+libexpat_la_SOURCES = \
+    xmlparse.c \
+    xmltok.c \
+    xmlrole.c
+
+if WITH_TESTS
+libtestpat_la_CPPFLAGS = -DXML_TESTING
+
+libtestpat_la_SOURCES = $(libexpat_la_SOURCES)
+endif
+
+doc_DATA = \
+    ../AUTHORS \
+    ../Changes
+
+install-data-hook:
+	cd "$(DESTDIR)$(docdir)" && $(am__mv) Changes changelog
+
+uninstall-local:
+	$(RM) "$(DESTDIR)$(docdir)/changelog"
+
+EXTRA_DIST = \
+    ascii.h \
+    asciitab.h \
+    expat_external.h \
+    expat.h \
+    iasciitab.h \
+    internal.h \
+    latin1tab.h \
+    libexpat.def.cmake \
+    nametab.h \
+    siphash.h \
+    utf8tab.h \
+    winconfig.h \
+    xmlrole.h \
+    xmltok.h \
+    xmltok_impl.c \
+    xmltok_impl.h \
+    xmltok_ns.c

lib/expat/ascii.h

@@ -0,0 +1,123 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 1999-2000 Thai Open Source Software Center Ltd
+   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2002      Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2007      Karl Waclawek <karl@waclawek.net>
+   Copyright (c) 2017      Sebastian Pipping <sebastian@pipping.org>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#define ASCII_A 0x41
+#define ASCII_B 0x42
+#define ASCII_C 0x43
+#define ASCII_D 0x44
+#define ASCII_E 0x45
+#define ASCII_F 0x46
+#define ASCII_G 0x47
+#define ASCII_H 0x48
+#define ASCII_I 0x49
+#define ASCII_J 0x4A
+#define ASCII_K 0x4B
+#define ASCII_L 0x4C
+#define ASCII_M 0x4D
+#define ASCII_N 0x4E
+#define ASCII_O 0x4F
+#define ASCII_P 0x50
+#define ASCII_Q 0x51
+#define ASCII_R 0x52
+#define ASCII_S 0x53
+#define ASCII_T 0x54
+#define ASCII_U 0x55
+#define ASCII_V 0x56
+#define ASCII_W 0x57
+#define ASCII_X 0x58
+#define ASCII_Y 0x59
+#define ASCII_Z 0x5A
+
+#define ASCII_a 0x61
+#define ASCII_b 0x62
+#define ASCII_c 0x63
+#define ASCII_d 0x64
+#define ASCII_e 0x65
+#define ASCII_f 0x66
+#define ASCII_g 0x67
+#define ASCII_h 0x68
+#define ASCII_i 0x69
+#define ASCII_j 0x6A
+#define ASCII_k 0x6B
+#define ASCII_l 0x6C
+#define ASCII_m 0x6D
+#define ASCII_n 0x6E
+#define ASCII_o 0x6F
+#define ASCII_p 0x70
+#define ASCII_q 0x71
+#define ASCII_r 0x72
+#define ASCII_s 0x73
+#define ASCII_t 0x74
+#define ASCII_u 0x75
+#define ASCII_v 0x76
+#define ASCII_w 0x77
+#define ASCII_x 0x78
+#define ASCII_y 0x79
+#define ASCII_z 0x7A
+
+#define ASCII_0 0x30
+#define ASCII_1 0x31
+#define ASCII_2 0x32
+#define ASCII_3 0x33
+#define ASCII_4 0x34
+#define ASCII_5 0x35
+#define ASCII_6 0x36
+#define ASCII_7 0x37
+#define ASCII_8 0x38
+#define ASCII_9 0x39
+
+#define ASCII_TAB 0x09
+#define ASCII_SPACE 0x20
+#define ASCII_EXCL 0x21
+#define ASCII_QUOT 0x22
+#define ASCII_AMP 0x26
+#define ASCII_APOS 0x27
+#define ASCII_MINUS 0x2D
+#define ASCII_PERIOD 0x2E
+#define ASCII_COLON 0x3A
+#define ASCII_SEMI 0x3B
+#define ASCII_LT 0x3C
+#define ASCII_EQUALS 0x3D
+#define ASCII_GT 0x3E
+#define ASCII_LSQB 0x5B
+#define ASCII_RSQB 0x5D
+#define ASCII_UNDERSCORE 0x5F
+#define ASCII_LPAREN 0x28
+#define ASCII_RPAREN 0x29
+#define ASCII_FF 0x0C
+#define ASCII_SLASH 0x2F
+#define ASCII_HASH 0x23
+#define ASCII_PIPE 0x7C
+#define ASCII_COMMA 0x2C

lib/expat/asciitab.h

@@ -0,0 +1,66 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2002      Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2017      Sebastian Pipping <sebastian@pipping.org>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
+    /* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML,
+    /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
+    /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
+    /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
+    /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
+    /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
+    /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
+    /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
+    /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
+    /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
+    /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
+    /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
+    /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
+    /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
+    /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
+    /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
+    /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,

lib/expat/expat_external.h

@@ -0,0 +1,163 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2000-2004 Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2001-2002 Greg Stein <gstein@users.sourceforge.net>
+   Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net>
+   Copyright (c) 2016      Cristian Rodríguez <crrodriguez@opensuse.org>
+   Copyright (c) 2016-2019 Sebastian Pipping <sebastian@pipping.org>
+   Copyright (c) 2017      Rhodri James <rhodri@wildebeest.org.uk>
+   Copyright (c) 2018      Yury Gribov <tetra2005@gmail.com>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#ifndef Expat_External_INCLUDED
+#define Expat_External_INCLUDED 1
+
+/* External API definitions */
+
+/* Expat tries very hard to make the API boundary very specifically
+   defined.  There are two macros defined to control this boundary;
+   each of these can be defined before including this header to
+   achieve some different behavior, but doing so it not recommended or
+   tested frequently.
+
+   XMLCALL    - The calling convention to use for all calls across the
+                "library boundary."  This will default to cdecl, and
+                try really hard to tell the compiler that's what we
+                want.
+
+   XMLIMPORT  - Whatever magic is needed to note that a function is
+                to be imported from a dynamically loaded library
+                (.dll, .so, or .sl, depending on your platform).
+
+   The XMLCALL macro was added in Expat 1.95.7.  The only one which is
+   expected to be directly useful in client code is XMLCALL.
+
+   Note that on at least some Unix versions, the Expat library must be
+   compiled with the cdecl calling convention as the default since
+   system headers may assume the cdecl convention.
+*/
+#ifndef XMLCALL
+#if defined(_MSC_VER)
+#define XMLCALL __cdecl
+#elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER)
+#define XMLCALL __attribute__((cdecl))
+#else
+/* For any platform which uses this definition and supports more than
+   one calling convention, we need to extend this definition to
+   declare the convention used on that platform, if it's possible to
+   do so.
+
+   If this is the case for your platform, please file a bug report
+   with information on how to identify your platform via the C
+   pre-processor and how to specify the same calling convention as the
+   platform's malloc() implementation.
+*/
+#define XMLCALL
+#endif
+#endif /* not defined XMLCALL */
+
+#if !defined(XML_STATIC) && !defined(XMLIMPORT)
+#ifndef XML_BUILDING_EXPAT
+/* using Expat from an application */
+
+#if defined(_MSC_VER) && !defined(__BEOS__) && !defined(__CYGWIN__)
+#define XMLIMPORT __declspec(dllimport)
+#endif
+
+#endif
+#endif /* not defined XML_STATIC */
+
+#ifndef XML_ENABLE_VISIBILITY
+#define XML_ENABLE_VISIBILITY 0
+#endif
+
+#if !defined(XMLIMPORT) && XML_ENABLE_VISIBILITY
+#define XMLIMPORT __attribute__((visibility("default")))
+#endif
+
+/* If we didn't define it above, define it away: */
+#ifndef XMLIMPORT
+#define XMLIMPORT
+#endif
+
+#if defined(__GNUC__) && (__GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 96))
+#define XML_ATTR_MALLOC __attribute__((__malloc__))
+#else
+#define XML_ATTR_MALLOC
+#endif
+
+#if defined(__GNUC__) && ((__GNUC__ > 4) || (__GNUC__ == 4 && __GNUC_MINOR__ >= 3))
+#define XML_ATTR_ALLOC_SIZE(x) __attribute__((__alloc_size__(x)))
+#else
+#define XML_ATTR_ALLOC_SIZE(x)
+#endif
+
+#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#ifdef XML_UNICODE_WCHAR_T
+#ifndef XML_UNICODE
+#define XML_UNICODE
+#endif
+#if defined(__SIZEOF_WCHAR_T__) && (__SIZEOF_WCHAR_T__ != 2)
+#error "sizeof(wchar_t) != 2; Need -fshort-wchar for both Expat and libc"
+#endif
+#endif
+
+#ifdef XML_UNICODE /* Information is UTF-16 encoded. */
+#ifdef XML_UNICODE_WCHAR_T
+typedef wchar_t XML_Char;
+typedef wchar_t XML_LChar;
+#else
+typedef unsigned short XML_Char;
+typedef char XML_LChar;
+#endif /* XML_UNICODE_WCHAR_T */
+#else  /* Information is UTF-8 encoded. */
+typedef char XML_Char;
+typedef char XML_LChar;
+#endif /* XML_UNICODE */
+
+#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */
+typedef long long XML_Index;
+typedef unsigned long long XML_Size;
+#else
+typedef long XML_Index;
+typedef unsigned long XML_Size;
+#endif /* XML_LARGE_SIZE */
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* not Expat_External_INCLUDED */

lib/expat/iasciitab.h

@@ -0,0 +1,67 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2002      Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2017      Sebastian Pipping <sebastian@pipping.org>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */
+/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML,
+    /* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML,
+    /* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML,
+    /* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM,
+    /* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS,
+    /* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS,
+    /* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL,
+    /* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
+    /* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT,
+    /* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI,
+    /* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST,
+    /* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
+    /* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
+    /* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB,
+    /* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT,
+    /* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX,
+    /* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT,
+    /* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
+    /* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER,

lib/expat/internal.h

@@ -0,0 +1,187 @@
+/* internal.h
+
+   Internal definitions used by Expat.  This is not needed to compile
+   client code.
+
+   The following calling convention macros are defined for frequently
+   called functions:
+
+   FASTCALL    - Used for those internal functions that have a simple
+                 body and a low number of arguments and local variables.
+
+   PTRCALL     - Used for functions called though function pointers.
+
+   PTRFASTCALL - Like PTRCALL, but for low number of arguments.
+
+   inline      - Used for selected internal functions for which inlining
+                 may improve performance on some platforms.
+
+   Note: Use of these macros is based on judgement, not hard rules,
+         and therefore subject to change.
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 2002-2003 Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2002-2006 Karl Waclawek <karl@waclawek.net>
+   Copyright (c) 2003      Greg Stein <gstein@users.sourceforge.net>
+   Copyright (c) 2016-2025 Sebastian Pipping <sebastian@pipping.org>
+   Copyright (c) 2018      Yury Gribov <tetra2005@gmail.com>
+   Copyright (c) 2019      David Loffredo <loffredo@steptools.com>
+   Copyright (c) 2023-2024 Sony Corporation / Snild Dolkow <snild@sony.com>
+   Copyright (c) 2024      Taichi Haradaguchi <20001722@ymail.ne.jp>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+#if defined(__GNUC__) && defined(__i386__) && !defined(__MINGW32__)
+/* We'll use this version by default only where we know it helps.
+
+   regparm() generates warnings on Solaris boxes.   See SF bug #692878.
+
+   Instability reported with egcs on a RedHat Linux 7.3.
+   Let's comment out:
+   #define FASTCALL __attribute__((stdcall, regparm(3)))
+   and let's try this:
+*/
+#define FASTCALL __attribute__((regparm(3)))
+#define PTRFASTCALL __attribute__((regparm(3)))
+#endif
+
+/* Using __fastcall seems to have an unexpected negative effect under
+   MS VC++, especially for function pointers, so we won't use it for
+   now on that platform. It may be reconsidered for a future release
+   if it can be made more effective.
+   Likely reason: __fastcall on Windows is like stdcall, therefore
+   the compiler cannot perform stack optimizations for call clusters.
+*/
+
+/* Make sure all of these are defined if they aren't already. */
+
+#ifndef FASTCALL
+#define FASTCALL
+#endif
+
+#ifndef PTRCALL
+#define PTRCALL
+#endif
+
+#ifndef PTRFASTCALL
+#define PTRFASTCALL
+#endif
+
+#ifndef XML_MIN_SIZE
+#if !defined(__cplusplus) && !defined(inline)
+#ifdef __GNUC__
+#define inline __inline
+#endif /* __GNUC__ */
+#endif
+#endif /* XML_MIN_SIZE */
+
+#ifdef __cplusplus
+#define inline inline
+#else
+#ifndef inline
+#define inline
+#endif
+#endif
+
+#include <limits.h>  // ULONG_MAX
+#include <stddef.h>  // size_t
+
+#if defined(_WIN32) && (!defined(__USE_MINGW_ANSI_STDIO) || (1 - __USE_MINGW_ANSI_STDIO - 1 == 0))
+#define EXPAT_FMT_ULL(midpart) "%" midpart "I64u"
+#if defined(_WIN64)  // Note: modifiers "td" and "zu" do not work for MinGW
+#define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "I64d"
+#define EXPAT_FMT_SIZE_T(midpart) "%" midpart "I64u"
+#else
+#define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d"
+#define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u"
+#endif
+#else
+#define EXPAT_FMT_ULL(midpart) "%" midpart "llu"
+#if !defined(ULONG_MAX)
+#error Compiler did not define ULONG_MAX for us
+#elif ULONG_MAX == 18446744073709551615u  // 2^64-1
+#define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "ld"
+#define EXPAT_FMT_SIZE_T(midpart) "%" midpart "lu"
+#elif defined(EMSCRIPTEN)  // 32bit mode Emscripten
+#define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "ld"
+#define EXPAT_FMT_SIZE_T(midpart) "%" midpart "zu"
+#else
+#define EXPAT_FMT_PTRDIFF_T(midpart) "%" midpart "d"
+#define EXPAT_FMT_SIZE_T(midpart) "%" midpart "u"
+#endif
+#endif
+
+#ifndef UNUSED_P
+#define UNUSED_P(p) (void)p
+#endif
+
+/* NOTE BEGIN If you ever patch these defaults to greater values
+              for non-attack XML payload in your environment,
+              please file a bug report with libexpat.  Thank you!
+*/
+#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_MAXIMUM_AMPLIFICATION_DEFAULT 100.0f
+#define EXPAT_BILLION_LAUGHS_ATTACK_PROTECTION_ACTIVATION_THRESHOLD_DEFAULT 8388608  // 8 MiB, 2^23
+
+#define EXPAT_ALLOC_TRACKER_MAXIMUM_AMPLIFICATION_DEFAULT 100.0f
+#define EXPAT_ALLOC_TRACKER_ACTIVATION_THRESHOLD_DEFAULT 67108864  // 64 MiB, 2^26
+
+// NOTE: If function expat_alloc was user facing, EXPAT_MALLOC_ALIGNMENT would
+//       have to take sizeof(long double) into account
+#define EXPAT_MALLOC_ALIGNMENT sizeof(long long)  // largest parser (sub)member
+#define EXPAT_MALLOC_PADDING ((EXPAT_MALLOC_ALIGNMENT) - sizeof(size_t))
+
+/* NOTE END */
+
+#include "expat.h"  // so we can use type XML_Parser below
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+void _INTERNAL_trim_to_complete_utf8_characters(const char* from, const char** fromLimRef);
+
+#if defined(XML_GE) && XML_GE == 1
+unsigned long long testingAccountingGetCountBytesDirect(XML_Parser parser);
+unsigned long long testingAccountingGetCountBytesIndirect(XML_Parser parser);
+const char* unsignedCharToPrintable(unsigned char c);
+#endif
+
+extern
+#if !defined(XML_TESTING)
+    const
+#endif
+    XML_Bool g_reparseDeferralEnabledDefault;  // written ONLY in runtests.c
+#if defined(XML_TESTING)
+void* expat_malloc(XML_Parser parser, size_t size, int sourceLine);
+void expat_free(XML_Parser parser, void* ptr, int sourceLine);
+void* expat_realloc(XML_Parser parser, void* ptr, size_t size, int sourceLine);
+extern unsigned int g_bytesScanned;  // used for testing only
+#endif
+
+#ifdef __cplusplus
+}
+#endif

lib/expat/latin1tab.h

@@ -0,0 +1,66 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 1997-2000 Thai Open Source Software Center Ltd
+   Copyright (c) 2000      Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2002      Fred L. Drake, Jr. <fdrake@users.sourceforge.net>
+   Copyright (c) 2017      Sebastian Pipping <sebastian@pipping.org>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
+    /* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME,
+    /* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER,
+    /* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER,
+    /* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
+    /* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER,
+    /* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,
+    /* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT,

lib/expat/libexpat.def.cmake

@@ -0,0 +1,84 @@
+; DEF file for MS VC++
+
+EXPORTS
+  XML_DefaultCurrent @1
+  XML_ErrorString @2
+  XML_ExpatVersion @3
+  XML_ExpatVersionInfo @4
+  XML_ExternalEntityParserCreate @5
+  XML_GetBase @6
+  XML_GetBuffer @7
+  XML_GetCurrentByteCount @8
+  XML_GetCurrentByteIndex @9
+  XML_GetCurrentColumnNumber @10
+  XML_GetCurrentLineNumber @11
+  XML_GetErrorCode @12
+  XML_GetIdAttributeIndex @13
+  XML_GetInputContext @14
+  XML_GetSpecifiedAttributeCount @15
+  XML_Parse @16
+  XML_ParseBuffer @17
+  XML_ParserCreate @18
+  XML_ParserCreateNS @19
+  XML_ParserCreate_MM @20
+  XML_ParserFree @21
+  XML_SetAttlistDeclHandler @22
+  XML_SetBase @23
+  XML_SetCdataSectionHandler @24
+  XML_SetCharacterDataHandler @25
+  XML_SetCommentHandler @26
+  XML_SetDefaultHandler @27
+  XML_SetDefaultHandlerExpand @28
+  XML_SetDoctypeDeclHandler @29
+  XML_SetElementDeclHandler @30
+  XML_SetElementHandler @31
+  XML_SetEncoding @32
+  XML_SetEndCdataSectionHandler @33
+  XML_SetEndDoctypeDeclHandler @34
+  XML_SetEndElementHandler @35
+  XML_SetEndNamespaceDeclHandler @36
+  XML_SetEntityDeclHandler @37
+  XML_SetExternalEntityRefHandler @38
+  XML_SetExternalEntityRefHandlerArg @39
+  XML_SetNamespaceDeclHandler @40
+  XML_SetNotStandaloneHandler @41
+  XML_SetNotationDeclHandler @42
+  XML_SetParamEntityParsing @43
+  XML_SetProcessingInstructionHandler @44
+  XML_SetReturnNSTriplet @45
+  XML_SetStartCdataSectionHandler @46
+  XML_SetStartDoctypeDeclHandler @47
+  XML_SetStartElementHandler @48
+  XML_SetStartNamespaceDeclHandler @49
+  XML_SetUnknownEncodingHandler @50
+  XML_SetUnparsedEntityDeclHandler @51
+  XML_SetUserData @52
+  XML_SetXmlDeclHandler @53
+  XML_UseParserAsHandlerArg @54
+; added with version 1.95.3
+  XML_ParserReset @55
+  XML_SetSkippedEntityHandler @56
+; added with version 1.95.5
+  XML_GetFeatureList @57
+  XML_UseForeignDTD @58
+; added with version 1.95.6
+  XML_FreeContentModel @59
+  XML_MemMalloc @60
+  XML_MemRealloc @61
+  XML_MemFree @62
+; added with version 1.95.8
+  XML_StopParser @63
+  XML_ResumeParser @64
+  XML_GetParsingStatus @65
+; added with version 2.1.1
+@_EXPAT_COMMENT_ATTR_INFO@ XML_GetAttributeInfo @66
+  XML_SetHashSalt @67
+; internal @68 removed with version 2.3.1
+; added with version 2.4.0
+@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetBillionLaughsAttackProtectionActivationThreshold @69
+@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetBillionLaughsAttackProtectionMaximumAmplification @70
+; added with version 2.6.0
+  XML_SetReparseDeferralEnabled @71
+; added with version 2.7.2
+@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetAllocTrackerMaximumAmplification @72
+@_EXPAT_COMMENT_DTD_OR_GE@ XML_SetAllocTrackerActivationThreshold @73

lib/expat/library.json

@@ -0,0 +1,11 @@
+{
+  "name": "expat",
+  "version": "2.7.3",
+  "build": {
+    "srcFilter": [
+      "+<xmlparse.c>",
+      "+<xmlrole.c>",
+      "+<xmltok.c>"
+    ]
+  }
+}

lib/expat/nametab.h

@@ -0,0 +1,102 @@
+/*
+                            __  __            _
+                         ___\ \/ /_ __   __ _| |_
+                        / _ \\  /| '_ \ / _` | __|
+                       |  __//  \| |_) | (_| | |_
+                        \___/_/\_\ .__/ \__,_|\__|
+                                 |_| XML parser
+
+   Copyright (c) 2000 Clark Cooper <coopercc@users.sourceforge.net>
+   Copyright (c) 2017 Sebastian Pipping <sebastian@pipping.org>
+   Licensed under the MIT license:
+
+   Permission is  hereby granted,  free of charge,  to any  person obtaining
+   a  copy  of  this  software   and  associated  documentation  files  (the
+   "Software"),  to  deal in  the  Software  without restriction,  including
+   without  limitation the  rights  to use,  copy,  modify, merge,  publish,
+   distribute, sublicense, and/or sell copies of the Software, and to permit
+   persons  to whom  the Software  is  furnished to  do so,  subject to  the
+   following conditions:
+
+   The above copyright  notice and this permission notice  shall be included
+   in all copies or substantial portions of the Software.
+
+   THE  SOFTWARE  IS  PROVIDED  "AS  IS",  WITHOUT  WARRANTY  OF  ANY  KIND,
+   EXPRESS  OR IMPLIED,  INCLUDING  BUT  NOT LIMITED  TO  THE WARRANTIES  OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+   NO EVENT SHALL THE AUTHORS OR  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+   DAMAGES OR  OTHER LIABILITY, WHETHER  IN AN  ACTION OF CONTRACT,  TORT OR
+   OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+   USE OR OTHER DEALINGS IN THE SOFTWARE.
+*/
+
+static const unsigned namingBitmap[] = {
+    0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFF,
+    0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x00000000, 0x04000000,
+    0x87FFFFFE, 0x07FFFFFE, 0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, 0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE,
+    0x7FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF, 0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF,
+    0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFD740,
+    0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, 0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, 0xFFFF0003, 0xFFFFFFFF,
+    0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, 0x0000007F, 0x00000000, 0xFFFF0000,
+    0x000707FF, 0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000, 0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060,
+    0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, 0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003, 0xFFF987E0,
+    0x036DFDFF, 0x5E000000, 0x001C0000, 0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, 0xFFF99FE0, 0x23CDFDFF,
+    0xB0000000, 0x00000003, 0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, 0xFFFDDFE0, 0x03EFFDFF, 0x00000000,
+    0x00000003, 0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003, 0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003,
+    0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000, 0xFEF02596,
+    0x200D6CAE, 0x0000001F, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, 0x00000000, 0x00000000,
+    0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFF003F,
+    0x007FFFFF, 0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB, 0x40000000, 0xF580C900, 0x00000007, 0x02010800,
+    0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF, 0x3F3FFFFF,
+    0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, 0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, 0x00000000, 0x00004C40,
+    0x00000000, 0x00000000, 0x00000007, 0x00000000, 0x00000000, 0x00000000, 0x00000080, 0x000003FE, 0xFFFFFFFE,
+    0xFFFFFFFF, 0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF, 0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000,
+    0x00000000, 0x00000000, 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF,
+    0x0000003F, 0x00000000, 0x00000000, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x0000000F,
+    0x00000000, 0x00000000, 0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, 0x00000000, 0x00800000, 0xFF7FFFFF,
+    0xFF7FFFFF, 0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, 0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000,
+    0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, 0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, 0xFFFFDFFE,
+    0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, 0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, 0x00000000, 0xFFFE0000,
+    0x027FFFFF, 0xFFFFFFFE, 0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, 0x00000000, 0x07FFFFFE, 0x0007FFFF,
+    0xFFFF03FF, 0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF, 0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF,
+    0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, 0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0, 0xFFFBAFEE,
+    0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, 0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, 0xD63DC7EC, 0xC3BFC718,
+    0x00803DC7, 0x0000FF80, 0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, 0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF,
+    0x0000FFC3, 0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+    0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, 0xFEF02596, 0x3BFF6CAE, 0x03FF3F5F, 0x00000000, 0x03000000,
+    0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, 0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, 0x00000000, 0x00000000,
+    0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, 0x000000A0, 0x003EFFFE, 0xFFFFFFFE,
+    0xFFFFFFFF, 0x661FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF,
+};
+static const unsigned char nmstrtPages[] = {
+    0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, 0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x00, 0x14, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x15, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+static const unsigned char namePages[] = {
+    0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, 0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x10, 0x11, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, 0x26, 0x14, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x27, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
+    0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};