From d5018936a0fea482229848944deaf8d1ce3b1827 Mon Sep 17 00:00:00 2001
From: John O'Keefe <jrokeefe@protonmail.com>
Date: Wed, 3 Jun 2026 20:00:40 -0400
Subject: [PATCH] refactor(sync): rewrite extractSurroundingText to use
 block-parent text collection

Instead of reading only from the single resolved text node (which
produces a tiny window when the position is inside <em> or other inline
elements), extractSurroundingText now:

1. Finds the block-level parent (e.g. <p>) of the resolved text node
2. Collects all text within that block, transparently crossing inline
   formatting elements via collectInlineText
3. Computes the global offset of the original text node within the
   concatenated block text
4. Extracts the [offset-window : offset+window] slice

This gives a full context window regardless of inline element
boundaries, enabling accurate text bridging between EPUB and KEPUB
documents even when reading positions fall inside <em>, <strong>,
<span class="koboSpan">, etc.

Falls back to single-node extraction when no block parent is found
(e.g. orphan text nodes in tests).
---
 internal/sync/kepub_cfi_converter.go | 47 +++++++++++++++++++++++-----
 1 file changed, 39 insertions(+), 8 deletions(-)

diff --git a/internal/sync/kepub_cfi_converter.go b/internal/sync/kepub_cfi_converter.go
index 29bc49b..4a2aad1 100644
--- a/internal/sync/kepub_cfi_converter.go
+++ b/internal/sync/kepub_cfi_converter.go
@@ -208,23 +208,54 @@ func extractSurroundingText(textNode *html.Node, offset int, window int) string
 		return ""
 	}
 
-	text := textNode.Data
-	runes := []rune(text)
+	block := findBlockParent(textNode)
+	if block == nil {
+		text := textNode.Data
+		runes := []rune(text)
+		start := offset - window
+		if start < 0 {
+			start = 0
+		}
+		end := offset + window
+		if end > len(runes) {
+			end = len(runes)
+		}
+		if start >= end {
+			return normalizeWhitespace(text)
+		}
+		return normalizeWhitespace(string(runes[start:end]))
+	}
 
-	start := offset - window
+	segments := collectInlineText(block)
+
+	globalOffset := 0
+	for _, seg := range segments {
+		if seg.node == textNode {
+			globalOffset += offset
+			break
+		}
+		globalOffset += len(seg.runes)
+	}
+
+	var allRunes []rune
+	for _, seg := range segments {
+		allRunes = append(allRunes, seg.runes...)
+	}
+
+	start := globalOffset - window
 	if start < 0 {
 		start = 0
 	}
-	end := offset + window
-	if end > len(runes) {
-		end = len(runes)
+	end := globalOffset + window
+	if end > len(allRunes) {
+		end = len(allRunes)
 	}
 
 	if start >= end {
-		return normalizeWhitespace(text)
+		return normalizeWhitespace(string(allRunes))
 	}
 
-	return normalizeWhitespace(string(runes[start:end]))
+	return normalizeWhitespace(string(allRunes[start:end]))
 }
 
 func (k *KEPUBCFIConverter) ComputeKEPUBPercentage(kepubCFI string) (float64, error) {