fix: line break (#525)

## Summary

* Fixes #519 
* Refactors repeated code into new function:
`ChapterHtmlSlimParser::flushPartWordBuffer()`
    
## Additional Context 
  
* The `<br/>` tag is self closing and _in-line_, so the existing logic
for closing block tags does not get applied to `<br/>` tags.
* This PR adds the _in-line_ logic to:
* Flush the word preceding the `<br/>` tag from `partWordBuffer` to
`currentTextBlock` before calling `startNewTextBlock`
* **New function**: `ChapterHtmlSlimParser::flushPartWordBuffer()`
* **Purpose**: Consolidates the logic for flushing `partWordBuffer` to
`currentTextBlock`
* **Impact**: Simplifies `ChapterHtmlSlimParser::characterData(…)`,
`ChapterHtmlSlimParser::startElement(…)`, and
`ChapterHtmlSlimParser::endElement(…)` by integrating reused code into
single function

---

### 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? _**NO**_

lib/Epub/Epub/parsers/ChapterHtmlSlimParser.cpp

@@ -40,6 +40,23 @@ bool matches(const char* tag_name, const char* possible_tags[], const int possib
   return false;
 }
 
+// flush the contents of partWordBuffer to currentTextBlock
+void ChapterHtmlSlimParser::flushPartWordBuffer() {
+  // determine font style
+  EpdFontFamily::Style fontStyle = EpdFontFamily::REGULAR;
+  if (boldUntilDepth < depth && italicUntilDepth < depth) {
+    fontStyle = EpdFontFamily::BOLD_ITALIC;
+  } else if (boldUntilDepth < depth) {
+    fontStyle = EpdFontFamily::BOLD;
+  } else if (italicUntilDepth < depth) {
+    fontStyle = EpdFontFamily::ITALIC;
+  }
+  // flush the buffer
+  partWordBuffer[partWordBufferIndex] = '\0';
+  currentTextBlock->addWord(partWordBuffer, fontStyle);
+  partWordBufferIndex = 0;
+}
+
 // start a new text block if needed
 void ChapterHtmlSlimParser::startNewTextBlock(const TextBlock::Style style) {
   if (currentTextBlock) {
@@ -125,6 +142,10 @@ void XMLCALL ChapterHtmlSlimParser::startElement(void* userData, const XML_Char*
     self->boldUntilDepth = std::min(self->boldUntilDepth, self->depth);
   } else if (matches(name, BLOCK_TAGS, NUM_BLOCK_TAGS)) {
     if (strcmp(name, "br") == 0) {
+      if (self->partWordBufferIndex > 0) {
+        // flush word preceding <br/> to currentTextBlock before calling startNewTextBlock
+        self->flushPartWordBuffer();
+      }
       self->startNewTextBlock(self->currentTextBlock->getStyle());
     } else {
       self->startNewTextBlock((TextBlock::Style)self->paragraphAlignment);
@@ -149,22 +170,11 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
     return;
   }
 
-  EpdFontFamily::Style fontStyle = EpdFontFamily::REGULAR;
-  if (self->boldUntilDepth < self->depth && self->italicUntilDepth < self->depth) {
-    fontStyle = EpdFontFamily::BOLD_ITALIC;
-  } else if (self->boldUntilDepth < self->depth) {
-    fontStyle = EpdFontFamily::BOLD;
-  } else if (self->italicUntilDepth < self->depth) {
-    fontStyle = EpdFontFamily::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->flushPartWordBuffer();
-        self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
-        self->partWordBufferIndex = 0;
       }
       // Skip the whitespace char
       continue;
@@ -186,9 +196,7 @@ void XMLCALL ChapterHtmlSlimParser::characterData(void* userData, const XML_Char
 
     // 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->flushPartWordBuffer();
-      self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
-      self->partWordBufferIndex = 0;
     }
 
     self->partWordBuffer[self->partWordBufferIndex++] = s[i];
@@ -219,18 +227,7 @@ void XMLCALL ChapterHtmlSlimParser::endElement(void* userData, const XML_Char* n
         matches(name, BOLD_TAGS, NUM_BOLD_TAGS) || matches(name, ITALIC_TAGS, NUM_ITALIC_TAGS) || self->depth == 1;
 
     if (shouldBreakText) {
-      EpdFontFamily::Style fontStyle = EpdFontFamily::REGULAR;
+      self->flushPartWordBuffer();
-      if (self->boldUntilDepth < self->depth && self->italicUntilDepth < self->depth) {
-        fontStyle = EpdFontFamily::BOLD_ITALIC;
-      } else if (self->boldUntilDepth < self->depth) {
-        fontStyle = EpdFontFamily::BOLD;
-      } else if (self->italicUntilDepth < self->depth) {
-        fontStyle = EpdFontFamily::ITALIC;
-      }
-
-      self->partWordBuffer[self->partWordBufferIndex] = '\0';
-      self->currentTextBlock->addWord(self->partWordBuffer, fontStyle);
-      self->partWordBufferIndex = 0;
     }
   }
 

lib/Epub/Epub/parsers/ChapterHtmlSlimParser.h

@@ -39,6 +39,7 @@ class ChapterHtmlSlimParser {
   bool hyphenationEnabled;
 
   void startNewTextBlock(TextBlock::Style style);
+  void flushPartWordBuffer();
   void makePages();
   // XML callbacks
   static void XMLCALL startElement(void* userData, const XML_Char* name, const XML_Char** atts);