Add e-book conversion, a built-in HTML reader and a calibre package

Directory.Packages.props

@@ -42,6 +42,7 @@
     <PackageVersion Include="PdfPig" Version="0.1.16" />
     <PackageVersion Include="MimeKitLite" Version="4.18.1" />
     <PackageVersion Include="ACadSharp" Version="3.8.0" />
+    <PackageVersion Include="AngleSharp" Version="1.8.2" />
   </ItemGroup>
 
   <ItemGroup Label="Tests">

THIRD-PARTY-NOTICES.md

@@ -19,14 +19,15 @@ Each component remains under its own license.
 | SkiaSharp | MIT | https://github.com/mono/SkiaSharp |
 | Svg.Skia (incl. Svg, ShimSkiaSharp, ExCSS; text shaping in `Filee.Engines/Vector/OutlinedTextPlayback.cs` adapted from it) | MIT | https://github.com/wieslawsoltes/Svg.Skia |
 | HarfBuzzSharp | MIT | https://github.com/mono/SkiaSharp |
-| SharpCompress (zstd decompression for engine downloads) | MIT | https://github.com/adamhathcock/sharpcompress |
+| SharpCompress (zstd decompression for engine downloads; RAR, 7z and TAR comics) | MIT | https://github.com/adamhathcock/sharpcompress |
 | Unhwp | MIT | https://github.com/iyulab/unhwp |
 | Markdig | BSD-2-Clause | https://github.com/xoofx/markdig |
 | ExcelNumberFormat | MIT | https://github.com/andersnm/ExcelNumberFormat |
 | ExcelDataReader | MIT | https://github.com/ExcelDataReader/ExcelDataReader |
 | PdfPig (PDF text, layout and pictures) | Apache-2.0 | https://github.com/UglyToad/PdfPig |
 | MimeKitLite (e-mail / MIME parsing) | MIT | https://github.com/jstedfast/MimeKit |
 | ACadSharp (DWG/DXF reading and writing; includes CSMath and CSUtilities) | MIT, Copyright (c) Albert Domenech | https://github.com/DomCR/ACadSharp |
+| AngleSharp | MIT | https://github.com/AngleSharp/AngleSharp |
 | pypandoc-hwpx (Pandoc AST mapping and package layout in `Filee.Engines/Hwp/Hwpx`, incl. the `blank.hwpx` reference document) | MIT, Copyright (c) 2024 pypandoc-hwpx Contributors | https://github.com/msjang/pypandoc-hwpx |
 | Microsoft.Extensions.* | MIT | https://github.com/dotnet/runtime |
 | cu2qu (fontTools): the cubic-to-quadratic approach followed by `Filee.Engines/Fonts/Cff/CubicToQuadratic.cs` | Apache-2.0, Copyright 2016 Google Inc. | https://github.com/fonttools/fonttools |
@@ -59,6 +60,7 @@ Downloaded from their official release pages when the user chooses to install th
 | Ghostscript (conda-forge build) | AGPL-3.0 | https://www.ghostscript.com, https://github.com/conda-forge/ghostscript-feedstock |
 | Microsoft Visual C++ Redistributable (for Ghostscript, conda-forge `vc14_runtime`) | Microsoft Visual C++ Redistributable license | https://github.com/conda-forge/vc-feedstock |
 | FFmpeg 9.0.2 (gyan.dev "full_build-shared" Windows build; ffmpeg.exe, ffprobe.exe and their libraries, incl. x264, x265, libvpx, LAME, Opus, Vorbis, Theora, OpenCORE AMR) | GPL-3.0-or-later (the build is configured with `--enable-gpl --enable-version3`); FFmpeg itself LGPL-2.1-or-later | https://ffmpeg.org, build: https://www.gyan.dev/ffmpeg/builds/ (source: https://github.com/GyanD/codexffmpeg) |
+| calibre (ebook-convert) | GPL-3.0 | https://calibre-ebook.com |
 
 These programs run as separate processes. Their source code is available from the linked projects.
 

build/fetch-engines.ps1

@@ -16,6 +16,8 @@
       ghostscript/   Ghostscript (AGPL-3.0, separate program) from conda-forge, EPS/PS <-> PDF, with the Microsoft
                      C++ runtime DLLs (vcruntime/) copied next to gswin64c.exe
       ffmpeg/        FFmpeg (GPL-3.0 build, separate program), video and audio; bin/ffmpeg.exe + bin/ffprobe.exe
+      calibre/       calibre (GPL-3.0, separate program), extracted from the official MSI via an administrative
+                     install: ebook-convert for LIT, LRF, PDB, ... and MOBI / AZW3 output
 
   Every download is pinned to a version and verified with SHA-256 (src/Filee.Engines/Infrastructure/engines.json,
   shared with the app). Downloads are cached in build/.cache.
@@ -216,4 +218,20 @@ if ('ghostscript' -in $selected) {
     Copy-Item (Join-Path $Destination 'vcruntime\*.dll') $target -Force
 }
 
+if ('calibre' -in $selected) {
+    $msi = Get-Engine 'calibre'
+    $tmp = Join-Path $cache 'calibre-admin'
+    Reset-Folder $tmp
+    Write-Host 'unpack calibre (administrative install, no system changes)'
+    $proc = Start-Process msiexec.exe -ArgumentList @('/a', "`"$msi`"", '/qn', "TARGETDIR=`"$tmp`"") -Wait -PassThru
+    if ($proc.ExitCode -ne 0) { throw "msiexec /a failed with exit code $($proc.ExitCode)." }
+
+    $convert = Get-ChildItem $tmp -Recurse -Filter 'ebook-convert.exe' | Select-Object -First 1
+    if (-not $convert) { throw 'ebook-convert.exe not found after extracting the MSI.' }
+    $target = Join-Path $Destination 'calibre'
+    Reset-Folder $target
+    Get-ChildItem $convert.DirectoryName -Force | Move-Item -Destination $target
+    Remove-Item $tmp -Recurse -Force
+}
+
 Write-Host "Engines ready in $Destination"

docs/ENGINES.md

@@ -15,17 +15,19 @@ Filee chooses engines automatically. Settings → *Engines* shows their status,
 | Spreadsheets (ExcelDataReader for XLS) | built in (library) | **XLSX, XLS, ODS, CSV, TSV → XLSX, ODS, CSV, TSV** (one CSV / TSV per sheet) |
 | Office Open XML | built in | **DOCM / DOTX / DOTM ↔ DOCX, XLSM / XLTX ↔ XLSX, PPTM / POTX / PPSX ↔ PPTX** (macros removed for macro-free types) |
 | Fonts | built in | **TTF, OTF, WOFF, WOFF2, EOT ↔ each other**; CFF (PostScript) outlines become TrueType for TTF and EOT |
-| **HWPX writer** | built in | **DOCX (+ DOCM/DOTX/DOTM), XLSX (+ XLSM/XLTX), XLS, ODS, CSV, TSV, PPTX (+ PPTM/POTX/PPSX), PDF, TXT, Markdown → HWPX** (and with rhwp → PDF and images); HTML, ODT, RTF, reStructuredText, LaTeX → HWPX with Pandoc |
+| **HWPX writer** | built in | **DOCX (+ DOCM/DOTX/DOTM), XLSX (+ XLSM/XLTX), XLS, ODS, CSV, TSV, PPTX (+ PPTM/POTX/PPSX), PDF, HTML, EPUB, MOBI/AZW3, FB2, HWPX, TXT, Markdown → HWPX** (and with rhwp → PDF and images); ODT, RTF, reStructuredText, LaTeX → HWPX with Pandoc |
 | **DOCX writer** | built in | **Markdown, TXT, XLSX, CSV, PPTX (+ variants), PDF → DOCX** |
 | PDF text | built in (PdfPig) | **PDF → TXT** (reading order, also two columns; no OCR) |
 | E-mail | built in (MimeKit) | **EML → HTML** (headers + body, inline pictures), **TXT**, **ZIP** (the attachments) |
+| **E-books** | built in | **EPUB, MOBI/AZW/AZW3/PRC, FB2, HTMLZ, TXTZ → EPUB, HWPX (→ PDF), TXT, HTML, Markdown, FB2, HTMLZ, TXTZ**; HTML, Markdown, TXT, DOCX → EPUB/FB2/HTMLZ/TXTZ; HTML → TXT; comics CBZ/CBR/CB7/CBT/CBC → PDF, EPUB, CBZ; PDF → CBZ; AZW4 → PDF |
 | CAD (ACadSharp + built-in renderer) | built in (library) | **DWG ↔ DXF**; DWG/DXF → **PDF** (vector), **SVG**, PNG, JPG, WEBP, TIFF, BMP, GIF, ICO, AVIF |
 | rhwp | bundled with the installer (`engines/rhwp`) | HWP/HWPX → PDF, **HWP → HWPX, HWPX → HWP** |
 | Archives (7-Zip) | bundled with the installer (`engines/7zip`, ~2.5 MB) + built-in readers | ZIP, 7Z, RAR, TAR (+ GZ/BZ2/XZ/Z/7Z/LZ), CAB, ISO, DMG, … **→ folder, ZIP, 7Z, TAR, TAR.GZ/BZ2/XZ**; ALZ, EGG, lzip read in-process; "Compress into one archive" for any files |
 | LibreOffice + H2Orestart + Java | **optional download** (~420 MB, 1.3 GB on disk) | older and rare formats only: DOC, XLS, PPT, RTF and OpenDocument → PDF and to each other, output as DOCX/ODT/ODS/ODP; HWP/HWPX → DOCX/ODT; read-only formats (see below) → PDF and their kind's editable formats |
 | Pandoc | **optional download** (~42 MB, 240 MB on disk) | Markdown ↔ DOCX/ODT/RTF, DOCX/ODT/HTML/RTF → Markdown, HTML ↔ DOCX/ODT, reStructuredText and LaTeX ↔ Markdown/HTML/DOCX/ODT (and → RTF, EPUB, TXT) |
 | Ghostscript | **optional download** (~20 MB, 31 MB on disk) | EPS/PS → PDF, PDF → EPS/PS, PostScript-based AI → PDF (images through PDF and PDFium) |
 | FFmpeg | **optional download** (~100 MB, 272 MB on disk) | **all video and audio**: video ↔ video, video → animated GIF or a still frame, audio extraction, audio ↔ audio, GIF → MP4/WEBM/MOV |
+| Calibre | **optional download** (~216 MB, 660 MB on disk) | rare e-book formats: LIT, LRF, CHM, PDB, PML, RB, SNB, TCR, OEB → EPUB; EPUB → MOBI, AZW3, LIT, LRF, PDB, PML, RB, SNB, TCR |
 
 DOCX, XLSX, XLS, ODS and PPTX → PDF need neither Microsoft Office nor LibreOffice: they are read in-process, written as HWPX
 and rendered by rhwp. Anything the built-in readers understand (including PDF) is written as DOCX by the DOCX writer.
@@ -51,8 +53,9 @@ they can be installed or removed later in Settings → *Engines*. A conversion t
   engine folder only when complete. Redirects to mirrors (even plain HTTP) are followed, because the hash decides.
 - Engines go to `%LOCALAPPDATA%\Filee\engines`: outside the app folder, so updates keep them, and inside Filee's
   install root, so uninstalling removes them.
-- LibreOffice comes as an MSI and is unpacked with an administrative install (`msiexec /a`): files only, no
-  registry entries, no admin rights. Help, gallery and most dictionaries are removed afterwards (~500 MB).
+- LibreOffice and calibre come as MSIs and are unpacked with an administrative install (`msiexec /a`): files only,
+  no registry entries, no admin rights. LibreOffice's help, gallery and most dictionaries are removed afterwards
+  (~500 MB).
 - Ghostscript comes from conda-forge (Artifex publishes only an NSIS installer): a `.conda` package is a zip with a
   zstd tarball, of which only `Library/bin` is unpacked (SharpCompress; `fetch-engines.ps1` uses Windows' `tar.exe`).
   Its fonts and resources are compiled into `gsdll64.dll`. The Microsoft C++ runtime it was built against
@@ -117,9 +120,16 @@ Readers turn the source into a small document model (`Hwp/Hwpx/HwpxModel.cs`) an
   start numbers), task lists, quotes, tables with spans, links, images, footnotes and math. No Pandoc needed.
 - **PDF** is read with PdfPig (see *PDF reader* below); DOCM / DOTX / DOTM, XLSM / XLTX and PPTM / POTX / PPSX
   are read like DOCX, XLSX and PPTX.
-- **HTML, ODT, RTF, reStructuredText, LaTeX** are parsed by Pandoc into its JSON AST (`PandocAstReader.cs`, following
+- **HTML** is parsed with AngleSharp (`HtmlReader.cs`, `HtmlCss.cs`): headings, paragraphs, bold / italic /
+  underline / strike / sub / sup / code / mark, the basic inline CSS (colour, background, font weight, style and
+  size, text-align, text-indent, page breaks) and simple `tag` / `.class` rules of style sheets, nested lists with
+  start numbers and types, tables with spans / header rows / borders, pictures (local files and data: URIs; remote
+  pictures are skipped), links and anchors, quotes, `pre`, `hr` and figures. Scripts, styles, forms and `nav` are
+  skipped. The encoding comes from the BOM, the XML declaration or `<meta charset>`, else UTF-8 or the system
+  code page. No Pandoc needed.
+- **ODT, RTF** are parsed by Pandoc into its JSON AST (`PandocAstReader.cs`, following
   [pypandoc-hwpx](https://github.com/msjang/pypandoc-hwpx)).
-- Markdown and Pandoc keep structure only, so page setup comes from the built-in template (A4).
+- Markdown, HTML and Pandoc keep structure only, so page setup comes from the built-in template (A4).
 
 Element order and attribute values follow files saved by 한글 where the schema and 한글 disagree, for example:
 
@@ -343,6 +353,45 @@ OLE objects, charts, video, form controls, text art (its text is kept), arcs / p
 master pages, memos, character ratio, relative size and offset, paragraph borders, picture cropping and rotation.
 Password-protected (encrypted) HWPX and DRM-wrapped files stop with a clear error.
 
+## E-books
+
+The built-in e-book engine (`src/Filee.Engines/Ebooks`) reads books into the same document model as the HWPX
+writer, so every e-book also reaches HWPX, PDF and images. The document model is written back out by
+`XhtmlWriter` (EPUB chapters, HTMLZ, single-page HTML), `PlainTextWriter`, `MarkdownWriter` and `Fb2Writer`.
+
+- **EPUB 2 / 3**: container.xml → OPF → spine; each chapter is read by the HTML reader and starts a new page, links
+  between chapters become links to bookmarks, pictures come from the package, title / authors / language / cover
+  from the metadata.
+- **EPUB output** is EPUB 3 with an NCX for older readers: `mimetype` first and stored, a navigation document from
+  the headings, chapters split at level-1 headings and page breaks, one style sheet, pictures in formats every
+  reader shows (others become JPEG / PNG), a cover page for covers the content does not show.
+- **MOBI / AZW / AZW3 / PRC** (`Ebooks/Mobi`, written from the MobileRead wiki's format description): PalmDB
+  records, MOBI header and EXTH metadata, PalmDOC (LZ77) and HUFF/CDIC compression, MOBI 6 `filepos` links and
+  `recindex` pictures, KF8 text rebuilt from the skeleton and fragment indexes with `kindle:pos` / `kindle:embed` /
+  `kindle:flow` references resolved, and plain PalmDOC (TEXtREAd) books. **AZW4** (Print Replica) gives back its PDF.
+- **FB2**: nested sections become headings, poems / epigraphs / citations / tables are kept, note links become
+  footnotes, pictures come from the base64 binaries; the XML declaration's encoding (often windows-1251) is used.
+  FB2 output nests sections by heading level.
+- **HTMLZ / TXTZ** (calibre's zipped formats) are read and written, with their `metadata.opf`.
+- **Comics**: CBZ, CBR, CB7, CBT and CBC (a ZIP of CBZ files) are opened with SharpCompress; pages are sorted
+  naturally ("page2" before "page10"). → PDF has one page per picture sized like the picture (JPEGs are embedded
+  as they are), → EPUB is fixed-layout, → CBZ repacks. PDF → CBZ renders the pages with PDFium at the preset DPI.
+- Books with DRM (Adobe, Apple, Kindle) are refused with a clear message; Filee does not remove DRM. KFX and
+  Topaz books are recognised and refused too.
+
+## Calibre
+
+calibre's `ebook-convert` (GPL-3.0) is an optional download for the formats Filee does not read or write itself:
+LIT, LRF, CHM, PDB, PML, RB, SNB, TCR and OEB → EPUB, and EPUB → MOBI, AZW3, LIT, LRF, PDB, PML, RB, SNB and TCR.
+EPUB is the hub, so for example FB2 → AZW3 is FB2 → EPUB (built in) → AZW3 (calibre). Its edges cost 20, so
+built-in routes always win where they exist.
+
+- The pinned `calibre-64bit-<version>.msi` from download.calibre-ebook.com is unpacked like LibreOffice; the folder
+  with `ebook-convert.exe` becomes `engines/calibre`.
+- Each run gets its own configuration, cache and temp folders in the job's work directory
+  (`CALIBRE_CONFIG_DIRECTORY`, ...), so a calibre the user installed is never read or changed; messages are
+  English (`CALIBRE_OVERRIDE_LANG`) and progress comes from its "34% ..." lines.
+
 ## HWP ↔ HWPX
 
 rhwp converts between the two 한글 formats without Hancom Office (`export-hwpx` and `convert`). Anything → HWP goes

src/Filee.App/Assets/i18n/en.json

@@ -322,6 +322,8 @@
   "engines.package.ghostscript.description": "EPS, PS and older Illustrator files → PDF, PNG and other images, and PDF or SVG → EPS/PS. SVG and AI files saved with PDF compatibility convert without it.",
   "engines.package.ffmpeg.name": "FFmpeg (video and audio)",
   "engines.package.ffmpeg.description": "Video ↔ video (MP4, MOV, MKV, WEBM, AVI, WMV and more), video → animated GIF or a still image, sound from videos (→ MP3, M4A, WAV …), audio ↔ audio (MP3, M4A, FLAC, WAV, OGG, OPUS and more) and GIF → MP4, WEBM, MOV. Only needed for video and audio.",
+  "engines.package.calibre.name": "Calibre (Kindle and rare e-book formats)",
+  "engines.package.calibre.description": "Saves as MOBI and AZW3 for Kindle, and converts rare e-book formats: LIT, LRF, PDB, PML, RB, SNB and TCR, plus CHM and OEB input. EPUB, MOBI, AZW3, FB2 and comics (CBZ, CBR) are read without it.",
   "engines.package.size": "Download {0} · {1} on disk",
   "engines.progress_detail": "{0} of {1} · {2}/s · {3}",
   "engines.eta.estimating": "estimating time left…",

src/Filee.App/Assets/i18n/ko.json

@@ -322,6 +322,8 @@
   "engines.package.ghostscript.description": "EPS·PS 파일과 예전 일러스트레이터 파일을 PDF·PNG 등 이미지로, PDF·SVG를 EPS·PS로 변환해요. SVG와 PDF 호환으로 저장한 AI 파일은 없어도 변환돼요.",
   "engines.package.ffmpeg.name": "FFmpeg (동영상·오디오)",
   "engines.package.ffmpeg.description": "동영상 ↔ 동영상(MP4·MOV·MKV·WEBM·AVI·WMV 등), 동영상 → 움직이는 GIF·정지 이미지, 동영상에서 소리 추출(→ MP3·M4A·WAV 등), 오디오 ↔ 오디오(MP3·M4A·FLAC·WAV·OGG·OPUS 등), GIF → MP4·WEBM·MOV 변환을 추가해요. 동영상과 오디오에만 필요해요.",
+  "engines.package.calibre.name": "Calibre (킨들과 드문 전자책 형식)",
+  "engines.package.calibre.description": "킨들용 MOBI·AZW3로 저장하고, 드문 전자책 형식(LIT·LRF·PDB·PML·RB·SNB·TCR, CHM·OEB 읽기)을 변환해요. EPUB·MOBI·AZW3·FB2와 만화책(CBZ·CBR)은 없어도 읽을 수 있어요.",
   "engines.package.size": "다운로드 {0} · 설치 후 {1}",
   "engines.progress_detail": "{0} / {1} · {2}/s · {3}",
   "engines.eta.estimating": "남은 시간 계산 중…",

src/Filee.App/Assets/i18n/zh-CN.json

@@ -322,6 +322,8 @@
   "engines.package.ghostscript.description": "EPS、PS 和旧版 Illustrator 文件 → PDF、PNG 等图片，以及 PDF 或 SVG → EPS/PS。SVG 和以 PDF 兼容方式保存的 AI 文件无需它即可转换。",
   "engines.package.ffmpeg.name": "FFmpeg（视频和音频）",
   "engines.package.ffmpeg.description": "支持视频 ↔ 视频（MP4、MOV、MKV、WEBM、AVI、WMV 等）、视频 → GIF 动图或静态图片、从视频提取声音（→ MP3、M4A、WAV 等）、音频 ↔ 音频（MP3、M4A、FLAC、WAV、OGG、OPUS 等）以及 GIF → MP4、WEBM、MOV。仅视频和音频转换需要它。",
+  "engines.package.calibre.name": "Calibre（Kindle 与少见电子书格式）",
+  "engines.package.calibre.description": "可保存为 Kindle 使用的 MOBI 和 AZW3，并转换少见的电子书格式：LIT、LRF、PDB、PML、RB、SNB、TCR，以及读取 CHM 和 OEB。EPUB、MOBI、AZW3、FB2 和漫画（CBZ、CBR）无需它即可读取。",
   "engines.package.size": "下载 {0} · 占用 {1}",
   "engines.progress_detail": "{0} / {1} · {2}/s · {3}",
   "engines.eta.estimating": "正在估算剩余时间…",

src/Filee.App/ViewModels/EngineSetupViewModel.cs

@@ -21,8 +21,8 @@ public EngineSetupViewModel(EngineDownloadService downloads, ILocalizer loc)
         foreach (var package in Packages)
         {
             // Large downloads are offered, not pre-selected: LibreOffice is only needed for older formats (DOC, XLS,
-            // PPT, OpenDocument), FFmpeg (~100 MB) only for video and audio. Ghostscript is small but only needed for
-            // EPS / PostScript.
+            // PPT, OpenDocument), FFmpeg (~100 MB) only for video and audio, calibre (~230 MB) only for rare e-book
+            // formats and Kindle output. Ghostscript is small but only needed for EPS / PostScript.
             package.Selected = !package.IsInstalled
                                && Filee.Engines.Infrastructure.EngineDownloads.DownloadSize(package.Package) < PreselectLimit
                                && package.Package.Id != "ghostscript";

src/Filee.Engines/Cad/CadConverter.cs

@@ -2,6 +2,7 @@
 // DXF and DWG; the drawing is rendered with SkiaSharp to PDF (vector), SVG and raster images.
 
 using Filee.Core.Conversion;
+using Filee.Engines.Infrastructure;
 using Filee.Engines.Magick;
 using ImageMagick;
 using Microsoft.Extensions.Logging;
@@ -41,7 +42,7 @@ from target in (string[])["pdf", "svg", .. ImageEncoder.Writable]
            select new ConversionEdge(source, target),
     ];
 
-    public EngineStatus GetStatus() => EngineStatus.Available("ACadSharp: DWG R13–2018+, DXF");
+    public EngineStatus GetStatus() => EngineStatus.Available("ACadSharp: DWG R13–2018+, DXF", $"{EngineVersions.BuiltIn} · {EngineVersions.Library("ACadSharp", typeof(ACadSharp.CadDocument))}");
 
     public Task<IReadOnlyList<string>> ConvertAsync(ConversionStep step, IProgress<double>? progress, CancellationToken cancellationToken) =>
         Task.Run<IReadOnlyList<string>>(() =>