From 3fb9ac9e297388062a1ca468ca76b22d2fbcc77b Mon Sep 17 00:00:00 2001
From: jpirnay <jens@pirnay.com>
Date: Mon, 20 Apr 2026 13:15:05 +0200
Subject: [PATCH] Finetuning 2

---
 lib/Epub/Epub/Section.cpp                     | 18 +++----
 .../ChapterXPathReverseMapper.cpp             | 54 +++++++++++--------
 2 files changed, 40 insertions(+), 32 deletions(-)

diff --git a/lib/Epub/Epub/Section.cpp b/lib/Epub/Epub/Section.cpp
index 06ff3420..bdf6c0a5 100644
--- a/lib/Epub/Epub/Section.cpp
+++ b/lib/Epub/Epub/Section.cpp
@@ -584,23 +584,21 @@ std::optional<uint16_t> Section::getPageForParagraphIndex(const uint16_t pIndex)
     return std::nullopt;
   }
 
-  // Find the page that contains the requested paragraph index.
-  // Each entry stores the first paragraph index for that page, so the page
-  // containing pIndex is the last page whose start paragraph is <= pIndex.
-  uint16_t resultPage = 0;
+  // Each LUT entry stores the paragraph index at page-break time — i.e. the last
+  // <p> whose start tag had been seen while page i was being laid out. Paragraph
+  // P therefore first appears on the smallest i where storedPIdx[i] >= P.
   for (uint16_t i = 0; i < count; i++) {
-    uint32_t byteOffset;
+    f.seek(paragraphLutOffset + sizeof(uint16_t) + i * ENTRY_SIZE + sizeof(uint32_t));
     uint16_t pagePIdx;
-    serialization::readPod(f, byteOffset);
     serialization::readPod(f, pagePIdx);
-    if (pagePIdx > pIndex) {
-      break;
+    if (pagePIdx >= pIndex) {
+      f.close();
+      return i;
     }
-    resultPage = i;
   }
 
   f.close();
-  return resultPage;
+  return static_cast<uint16_t>(count - 1);
 }
 
 std::optional<uint16_t> Section::getParagraphIndexForPage(const uint16_t page) const {
diff --git a/lib/KOReaderSync/ChapterXPathReverseMapper.cpp b/lib/KOReaderSync/ChapterXPathReverseMapper.cpp
index b9cc9d81..ecf82b7a 100644
--- a/lib/KOReaderSync/ChapterXPathReverseMapper.cpp
+++ b/lib/KOReaderSync/ChapterXPathReverseMapper.cpp
@@ -47,33 +47,43 @@ struct ReverseState : StackState {
   const char* bestTierName = nullptr;
 
   ReverseState(const int spineIndex, const std::string& xpath) : spineIndex(spineIndex) {
-    // Parse optional /text()[N].M suffix before normalizing for element matching.
+    // Parse optional text-node suffix before normalizing for element matching.
+    // KOReader emits two shapes that both land here:
+    //   /text()[N].M  — explicit 1-based text-node index + codepoint offset
+    //   /text().M     — implicit first text-node (N=1) + codepoint offset
     std::string raw = xpath;
     for (char& c : raw) c = static_cast<char>(std::tolower(static_cast<unsigned char>(c)));
-    const std::string tnPat = "/text()[";
+    const std::string tnPat = "/text()";
     const size_t tnPos = raw.rfind(tnPat);
     if (tnPos != std::string::npos) {
-      const size_t numStart = tnPos + tnPat.size();
-      size_t numEnd = numStart;
-      while (numEnd < raw.size() && std::isdigit(static_cast<unsigned char>(raw[numEnd]))) {
-        numEnd++;
+      size_t cursor = tnPos + tnPat.size();
+      int nodeIdx = 1;
+      bool valid = true;
+      if (cursor < raw.size() && raw[cursor] == '[') {
+        cursor++;
+        size_t numEnd = cursor;
+        while (numEnd < raw.size() && std::isdigit(static_cast<unsigned char>(raw[numEnd]))) {
+          numEnd++;
+        }
+        if (numEnd > cursor && numEnd < raw.size() && raw[numEnd] == ']') {
+          nodeIdx = static_cast<int>(std::strtol(raw.substr(cursor, numEnd - cursor).c_str(), nullptr, 10));
+          cursor = numEnd + 1;
+        } else {
+          valid = false;
+        }
       }
-      if (numEnd > numStart && numEnd < raw.size() && raw[numEnd] == ']') {
-        const long nodeIdx = std::strtol(raw.substr(numStart, numEnd - numStart).c_str(), nullptr, 10);
-        if (nodeIdx >= 1) {
-          targetTextNodeIndex = static_cast<int>(nodeIdx);
-          size_t after = numEnd + 1;
-          if (after < raw.size() && raw[after] == '.') {
-            after++;
-            size_t charEnd = after;
-            while (charEnd < raw.size() && std::isdigit(static_cast<unsigned char>(raw[charEnd]))) {
-              charEnd++;
-            }
-            if (charEnd > after) {
-              const long charOff = std::strtol(raw.substr(after, charEnd - after).c_str(), nullptr, 10);
-              if (charOff >= 0) {
-                targetCharOffset = static_cast<int>(charOff);
-              }
+      if (valid && nodeIdx >= 1) {
+        targetTextNodeIndex = nodeIdx;
+        if (cursor < raw.size() && raw[cursor] == '.') {
+          cursor++;
+          size_t charEnd = cursor;
+          while (charEnd < raw.size() && std::isdigit(static_cast<unsigned char>(raw[charEnd]))) {
+            charEnd++;
+          }
+          if (charEnd > cursor) {
+            const long charOff = std::strtol(raw.substr(cursor, charEnd - cursor).c_str(), nullptr, 10);
+            if (charOff >= 0) {
+              targetCharOffset = static_cast<int>(charOff);
             }
           }
         }