feat: in-book search for epubs

.github/workflows/ci.yml

@@ -12,8 +12,9 @@ jobs:
   clang-format:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
+          persist-credentials: false
           submodules: recursive
 
       - uses: actions/setup-python@v6
@@ -36,8 +37,9 @@ jobs:
   cppcheck:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
+          persist-credentials: false
           submodules: recursive
 
       - uses: actions/setup-python@v6
@@ -67,8 +69,9 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
         with:
+          persist-credentials: false
           submodules: recursive
 
       - uses: actions/setup-python@v6
@@ -116,6 +119,26 @@ jobs:
             .pio/build/tiny/firmware-tiny.bin
           if-no-files-found: error
 
+  unit-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
+        with:
+          persist-credentials: false
+          submodules: recursive
+
+      - name: Verify CMake
+        run: cmake --version
+
+      - name: Configure test suite
+        run: cmake -S test -B test/build -DCMAKE_BUILD_TYPE=Release
+
+      - name: Build test suite
+        run: cmake --build test/build -j"$(nproc)"
+
+      - name: Run test suite
+        run: ctest --test-dir test/build --output-on-failure
+
   # This job is used as the PR required actions check, allows for changes to other steps in the future without breaking
   # PR requirements.
   test-status:
@@ -124,6 +147,7 @@ jobs:
       - build
       - clang-format
       - cppcheck
+      - unit-tests
     if: always()
     runs-on: ubuntu-latest
     steps:

CHANGELOG.md

@@ -1,4 +1,11 @@
 # Changelog
+
+## [Unreleased]
+
+### Added
+
+- In-book search: find a word or phrase within the current EPUB and jump to a match, with the matched words highlighted on the page. Matching respects word boundaries while still finding words broken by hyphenation across a line or page.
+
 ## [v1.3.4] - 2026-06-24
 
 ### Added

docs/file-formats.md

@@ -229,19 +229,20 @@ Binary layout:
 
 ## `section.bin`
 
-### Version 41
+### Version 42
 
 Each file in `sections/*.bin` stores one laid-out spine section. The header is
 also the cache-busting key: if any layout-affecting setting differs from the
 current reader settings, the section is discarded and rebuilt.
 
-Version 41 includes:
+Version 42 includes:
 
 - cache-busting fields for font, line compression, extra paragraph spacing,
   forced paragraph indents, paragraph alignment, viewport size, hyphenation,
   embedded CSS, image rendering mode, Bionic Reading, Guide Dots, and EPUB
   render mode
-- page offset LUT
+- paired page/search-text offset LUT
+- compact per-page text records used by bounded-memory in-book search
 - anchor-to-page map for fragment and footnote navigation
 - paragraph and list-item LUTs used by KOReader sync page refinement
 - optional per-word Bionic Reading split metadata
@@ -252,14 +253,17 @@ Version 41 includes:
 - per-page footnote entries
 - per-page publisher page markers
 
+See [In-Book Search Architecture](./search-architecture.md) for the
+memory and SD-space trade-offs behind the search records.
+
 ImHex pattern:
 
 ```c++
 import std.mem;
 import std.string;
 import std.core;
 
-#define EXPECTED_VERSION 41
+#define EXPECTED_VERSION 42
 #define MAX_STRING_LENGTH 65535
 #define FOOTNOTE_NUMBER_LEN 32
 #define FOOTNOTE_HREF_LEN 96
@@ -426,6 +430,17 @@ struct Page {
     PublisherPageMarker publisherPageMarkers[publisherPageMarkerCount];
 };
 
+struct PageRecord {
+    Page page [[inline]];
+    u32 searchTextLength;
+    char searchText[searchTextLength] [[comment("Rendered words joined by ASCII spaces")]];
+};
+
+struct PageLutEntry {
+    u32 pageOffset [[comment("Serialized Page offset")]];
+    u32 searchTextOffset [[comment("searchTextLength field offset")]];
+};
+
 struct AnchorEntry {
     String anchor;
     u16 page;
@@ -467,14 +482,14 @@ struct SectionBin {
     u32 paragraphLutOffset;
     u32 listItemLutOffset;
 
-    Page pages[pageCount];
+    PageRecord pages[pageCount];
 
     u32 currentOffset = $;
     if (currentOffset != pageLutOffset) {
         std::warning(std::format("Page LUT offset mismatch: expected 0x{:X}, got 0x{:X}", pageLutOffset, currentOffset));
     }
 
-    u32 pageLut[pageCount] [[comment("Page data offsets")]];
+    PageLutEntry pageLut[pageCount] [[comment("Page and search-text offsets")]];
 
     if (anchorMapOffset != 0) {
         AnchorMap anchorMap @ anchorMapOffset;