Free, open-source file converter. Convert 263 formats offline by drag & drop — images, PDF, Word, Excel, PowerPoint, HWP/HWPX, video, audio, e-books and archives. No upload, no Office needed.
C# audio-converteravaloniabatch-conversionconvertercsharpdocument-converterdocx-to-pdfdotnetdrag-and-dropfile-conversionfile-converterheic-converterhwphwpximage-converterlinuxmacospdf-convertervideo-converterwindows
Revert "Merge pull request #686 from KnifeLemon/engine/resource-limits"
KnifeLemone081cec771d1
diff --git a/.github/workflows/fuzz.yml b/.github/workflows/fuzz.ymldeleted file mode 100644index caa5c0ca..00000000--- a/.github/workflows/fuzz.yml+++ /dev/null@@ -1,58 +0,0 @@-# Nightly mutation fuzzing of the document readers (tests/Filee.Engines.Tests/DocumentFuzzTests.cs): each reader gets a-# few minutes of inputs changed from seeds written in code, with a new random seed every night. Pull requests run the-# same tests briefly with a fixed seed as part of the normal test run; this job only adds the long run. A failure-# names the seed (FILEE_FUZZ_SEED repeats it) and uploads the inputs that failed.-name: Fuzz--on:- schedule:- - cron: "17 18 * * *" # 03:17 in Korea- workflow_dispatch:- inputs:- seconds:- description: Seconds per reader- default: "180"- seed:- description: Seed to repeat (empty for a new one)- default: ""--permissions:- contents: read--concurrency:- group: fuzz- cancel-in-progress: true--jobs:- fuzz:- runs-on: ubuntu-24.04- timeout-minutes: 25- steps:- - uses: actions/checkout@v7-- - uses: actions/setup-dotnet@v6- with:- global-json-file: global.json-- - name: Build- run: dotnet build tests/Filee.Engines.Tests/Filee.Engines.Tests.csproj -c Release-- - name: Fuzz the document readers- env:- FILEE_FUZZ_SECONDS: ${{ inputs.seconds || '180' }}- FILEE_FUZZ_SEED: ${{ inputs.seed }}- FILEE_FUZZ_OUT: ${{ runner.temp }}/fuzz-failures- run: |- mkdir -p "$FILEE_FUZZ_OUT"- dotnet test tests/Filee.Engines.Tests/Filee.Engines.Tests.csproj --no-build -c Release --filter "Category=Fuzz" \- --blame-crash --results-directory TestResults --logger "console;verbosity=detailed"-- - name: Upload the inputs that failed- if: failure()- uses: actions/upload-artifact@v7- with:- name: fuzz-failures- path: |- ${{ runner.temp }}/fuzz-failures/- TestResults/- if-no-files-found: ignorediff --git a/docs/ENGINES.md b/docs/ENGINES.mdindex bf918f9f..e2b6f68e 100644--- a/docs/ENGINES.md+++ b/docs/ENGINES.md@@ -628,8 +628,7 @@ sits on the office donut (settings schema 27 teaches existing donuts `.ofd`).resource files (PublicRes, DocumentRes, a page's PageRes, and the unnamed `Res.xml` WPS writes next to them).Parts are looked up by name inside the ZIP and never written out under their own names; references are resolvedagainst the referring part (or the package root for "/…"), "." and ".." applied, and anything that leaves the- package, a URL or a drive path finds nothing. The package is read like HWPX and DOCX (`Documents/DocumentPackage.cs`,- see [HWPX reader](#hwpx-reader)): XML without DTDs; a part may unpack to 64 MB, a picture to+ package, a URL or a drive path finds nothing. XML is read without DTDs; a part may unpack to 64 MB, a picture to32 MB (larger ones are left out), the whole package to 1 GB; at most 100,000 parts, 10,000 pages, 2,000,000drawing objects, page blocks nested 32 deep. DeltaX / DeltaY "g n d" repeats never yield more values than thetext has characters.@@ -1235,31 +1234,6 @@ OLE objects, charts, video, form controls, text art (its text is kept), arcs / pmaster 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.-**Limits.** Untrusted documents must not hang, exhaust the memory or crash Filee. The HWPX, DOCX and OFD readers (and-the HWP 5.0 reader and the layout engine when they come) share `Documents/DocumentLimits.cs`; a document that passes-one stops with `error.document_too_complex` and says which:--- the package (`Documents/DocumentPackage.cs`): at most 100,000 parts; a part may unpack to 64 MB, all parts together- to 1 GB, counted while they unpack (a ZIP header can understate a size), and a part over 4 MB to no more than 200- times its packed size; parts are found by name inside the package only, and extracted pictures get names Filee- makes (`hwpx-media-1.png`), never the part's;-- XML (`Infrastructure/SafeXml.cs`, also used for KML and GPX): no DTD and no resolver, so no entity expands and- nothing outside the package is read; at most 512 levels deep and 5,000,000 elements in a package;-- the document (`Documents/DocumentBudget.cs`): tables in tables, text boxes, notes, groups and fields nest at most 32- levels; at most 1,000,000 paragraphs and 200,000 tables, pictures and drawing objects; table columns, spans and- row spans are cut to the table (at most 16,384 columns); Word style chains are followed 20 styles deep;-- pictures (`Documents/PictureSize.cs`): one whose PNG, JPEG, GIF, BMP or WebP header claims more than- 16,384 × 16,384 pixels is left out before anything decodes it;-- layout (`Documents/LayoutGuard.cs`, for the layout engine): at most 20,000 pages, 64 empty pages in a row, ten minutes;- cancellation and the time are checked per paragraph, and an object larger than the page is clipped and placed.--Embedded fonts (DOCX `word/fonts`, HWPX and OFD font files) are not read; a reader that uses them must pass them-through Filee's SFNT parser (`Fonts/SfntFont.cs`) first. `DocumentHostileInputTests` holds ZIP bombs, deep nesting,-DTDs and huge pictures; `DocumentFuzzTests` changes packages written in code at random (attributes set to extreme-values, elements removed, repeated, renamed or nested, text and bytes damaged) and allows a reader only to read a-file or refuse it with `InvalidDataException` / `ConversionRefusedException`. It runs briefly with every test run and-for a few minutes per reader every night (`.github/workflows/fuzz.yml`); `FILEE_FUZZ_SEED` repeats a run.-## E-booksThe built-in e-book engine (`src/Filee.Engines/Ebooks`) reads books into the same document model as the HWPXdiff --git a/src/Filee.App/Assets/i18n/ar.json b/src/Filee.App/Assets/i18n/ar.jsonindex 384a2e14..2e42b067 100644--- a/src/Filee.App/Assets/i18n/ar.json+++ b/src/Filee.App/Assets/i18n/ar.json@@ -130,7 +130,6 @@"error.fon_unsupported": "هذا النوع من خطوط .fon غير مدعوم","error.fon_too_large": "خط .fon كبير جدًا بحيث لا يمكن تحويله","error.fon_damaged": "ملف .fon تالف أو غير مكتمل",- "error.document_too_complex": "المستند كبير جدًا أو معقّد جدًا بحيث لا يمكن قراءته بأمان","error.m4s_needs_init": "ملف .m4s هذا جزء من فيديو متدفّق، ولا يمكن قراءته دون مقطع البداية (init) المنفصل الخاص به","notice.pdf_not_smaller": "تعذّر تقليل الحجم، لذا نُسخ الملف كما هو","notice.cad_newer_left_out": "حُذفت كائنات لا يدعمها إصدار AutoCAD المختار (أسهم توضيحية متعددة، شبكات …)",diff --git a/src/Filee.App/Assets/i18n/de.json b/src/Filee.App/Assets/i18n/de.jsonindex 6b0f62ea..9ff6b6d6 100644--- a/src/Filee.App/Assets/i18n/de.json+++ b/src/Filee.App/Assets/i18n/de.json@@ -130,7 +130,6 @@"error.fon_unsupported": "Diese Art von .fon-Schrift wird nicht unterstützt","error.fon_too_large": "Die .fon-Schrift ist zu groß zum Konvertieren","error.fon_damaged": "Die .fon-Datei ist beschädigt oder unvollständig",- "error.document_too_complex": "Das Dokument ist zu groß oder zu komplex, um es sicher zu lesen","error.m4s_needs_init": "Diese .m4s-Datei ist ein Stück eines gestreamten Videos und lässt sich ohne ihr separates Startsegment (init) nicht lesen","notice.pdf_not_smaller": "Die Datei ließ sich nicht verkleinern und wurde unverändert kopiert","notice.cad_newer_left_out": "Objekte, die die gewählte AutoCAD-Version nicht unterstützt (Multiführungslinien, Netze …), wurden weggelassen",diff --git a/src/Filee.App/Assets/i18n/en.json b/src/Filee.App/Assets/i18n/en.jsonindex bf28b748..5d09bbf7 100644--- a/src/Filee.App/Assets/i18n/en.json+++ b/src/Filee.App/Assets/i18n/en.json@@ -136,7 +136,6 @@"error.fon_unsupported": "This kind of .fon font isn't supported","error.fon_too_large": "The .fon font is too large to convert","error.fon_damaged": "The .fon file is damaged or cut short",- "error.document_too_complex": "The document is too large or too complex to read safely","error.m4s_needs_init": "This .m4s is one piece of a streamed video: it can't be read without its separate start (init) segment","notice.pdf_not_smaller": "Couldn't make it smaller, so it was copied as it is","notice.cad_newer_left_out": "Objects the chosen AutoCAD version doesn't have (multileaders, meshes …) were left out",diff --git a/src/Filee.App/Assets/i18n/es.json b/src/Filee.App/Assets/i18n/es.jsonindex 7ef306f5..048ceac5 100644--- a/src/Filee.App/Assets/i18n/es.json+++ b/src/Filee.App/Assets/i18n/es.json@@ -130,7 +130,6 @@"error.fon_unsupported": "Este tipo de fuente .fon no es compatible","error.fon_too_large": "La fuente .fon es demasiado grande para convertirla","error.fon_damaged": "El archivo .fon está dañado o incompleto",- "error.document_too_complex": "El documento es demasiado grande o complejo para leerlo de forma segura","error.m4s_needs_init": "Este .m4s es un fragmento de un vídeo en streaming y no se puede leer sin su segmento de inicio (init) aparte","notice.pdf_not_smaller": "No se pudo reducir su tamaño, por lo que se copió tal cual","notice.cad_newer_left_out": "Se omitieron objetos que la versión de AutoCAD elegida no tiene (directrices múltiples, mallas…)",diff --git a/src/Filee.App/Assets/i18n/fr.json b/src/Filee.App/Assets/i18n/fr.jsonindex f329c4f4..7b517140 100644--- a/src/Filee.App/Assets/i18n/fr.json+++ b/src/Filee.App/Assets/i18n/fr.json@@ -136,7 +136,6 @@"error.fon_unsupported": "Ce type de police .fon n'est pas pris en charge","error.fon_too_large": "La police .fon est trop grande pour être convertie","error.fon_damaged": "Le fichier .fon est endommagé ou incomplet",- "error.document_too_complex": "Le document est trop volumineux ou trop complexe pour être lu en toute sécurité","error.m4s_needs_init": "Ce .m4s est un morceau d'une vidéo diffusée en streaming : il ne peut pas être lu sans son segment de départ (init) séparé","notice.pdf_not_smaller": "Impossible de réduire sa taille : le fichier a été copié tel quel","notice.cad_newer_left_out": "Des objets que la version d'AutoCAD choisie n'a pas (multilignes de repère, maillages…) ont été omis",diff --git a/src/Filee.App/Assets/i18n/hi.json b/src/Filee.App/Assets/i18n/hi.jsonindex 6d87f7cb..e44149bf 100644--- a/src/Filee.App/Assets/i18n/hi.json+++ b/src/Filee.App/Assets/i18n/hi.json@@ -130,7 +130,6 @@"error.fon_unsupported": "इस तरह का .fon फ़ॉन्ट समर्थित नहीं है","error.fon_too_large": ".fon फ़ॉन्ट बदलने के लिए बहुत बड़ा है","error.fon_damaged": ".fon फ़ाइल खराब है या अधूरी है",- "error.document_too_complex": "दस्तावेज़ इतना बड़ा या जटिल है कि उसे सुरक्षित रूप से पढ़ा नहीं जा सकता","error.m4s_needs_init": "यह .m4s स्ट्रीम किए गए वीडियो का एक हिस्सा है: इसके अलग शुरुआती (init) सेगमेंट के बिना इसे पढ़ा नहीं जा सकता","notice.pdf_not_smaller": "इसे छोटा नहीं किया जा सका, इसलिए जैसा है वैसा ही कॉपी कर दिया गया","notice.cad_newer_left_out": "चुने गए AutoCAD संस्करण में न होने वाले ऑब्जेक्ट (मल्टीलीडर, मेश …) छोड़ दिए गए",diff --git a/src/Filee.App/Assets/i18n/ja.json b/src/Filee.App/Assets/i18n/ja.jsonindex 547b261b..cc0d2b3e 100644--- a/src/Filee.App/Assets/i18n/ja.json+++ b/src/Filee.App/Assets/i18n/ja.json@@ -130,7 +130,6 @@"error.fon_unsupported": "この種類の.fonフォントには対応していません","error.fon_too_large": ".fonフォントが大きすぎて変換できません","error.fon_damaged": ".fonファイルが破損しているか、途中で切れています",- "error.document_too_complex": "文書が大きすぎるか複雑すぎるため、安全に読み込めません","error.m4s_needs_init": "この .m4s はストリーミング動画の一部で、別にある開始(init)セグメントがないと読み込めません","notice.pdf_not_smaller": "サイズを小さくできなかったため、元のままコピーしました","notice.cad_newer_left_out": "選んだ AutoCAD のバージョンにないオブジェクト(マルチ引出線、メッシュ …)を省きました",diff --git a/src/Filee.App/Assets/i18n/ko.json b/src/Filee.App/Assets/i18n/ko.jsonindex 2098d6a6..d5f1e16e 100644--- a/src/Filee.App/Assets/i18n/ko.json+++ b/src/Filee.App/Assets/i18n/ko.json@@ -136,7 +136,6 @@"error.fon_unsupported": "지원하지 않는 종류의 .fon 글꼴이에요","error.fon_too_large": ".fon 글꼴이 너무 커서 변환할 수 없어요","error.fon_damaged": ".fon 파일이 손상되었거나 잘렸어요",- "error.document_too_complex": "문서가 너무 크거나 복잡해서 안전하게 읽을 수 없어요","error.m4s_needs_init": "스트리밍 동영상의 한 조각인 .m4s 파일이에요. 따로 있는 시작(init) 세그먼트 없이는 읽을 수 없어요","notice.pdf_not_smaller": "더 작게 만들 수 없어서 그대로 복사했어요","notice.cad_newer_left_out": "선택한 AutoCAD 버전에 없는 개체(다중 지시선, 메시 …)는 빼고 저장했어요",diff --git a/src/Filee.App/Assets/i18n/ne.json b/src/Filee.App/Assets/i18n/ne.jsonindex 0a38f331..5e8926ee 100644--- a/src/Filee.App/Assets/i18n/ne.json+++ b/src/Filee.App/Assets/i18n/ne.json@@ -130,7 +130,6 @@"error.fon_unsupported": "यस प्रकारको .fon फन्ट समर्थित छैन","error.fon_too_large": ".fon फन्ट रूपान्तरण गर्न धेरै ठूलो छ","error.fon_damaged": ".fon फाइल बिग्रिएको वा अपूर्ण छ",- "error.document_too_complex": "कागजात सुरक्षित रूपमा पढ्न नसकिने गरी धेरै ठूलो वा जटिल छ","error.m4s_needs_init": "यो .m4s स्ट्रिम गरिएको भिडियोको एउटा टुक्रा हो: छुट्टै सुरुवाती (init) खण्डबिना यसलाई पढ्न सकिँदैन","notice.pdf_not_smaller": "यसलाई सानो बनाउन सकिएन, त्यसैले जस्तो छ त्यस्तै प्रतिलिपि गरियो","notice.cad_newer_left_out": "छानिएको AutoCAD संस्करणमा नभएका वस्तुहरू (मल्टिलिडर, मेस …) छोडिए",diff --git a/src/Filee.App/Assets/i18n/pl.json b/src/Filee.App/Assets/i18n/pl.jsonindex c4e18c3c..8f50edcc 100644--- a/src/Filee.App/Assets/i18n/pl.json+++ b/src/Filee.App/Assets/i18n/pl.json@@ -136,7 +136,6 @@"error.fon_unsupported": "Ten rodzaj czcionki .fon nie jest obsługiwany","error.fon_too_large": "Czcionka .fon jest zbyt duża, aby ją przekonwertować","error.fon_damaged": "Plik .fon jest uszkodzony lub niekompletny",- "error.document_too_complex": "Dokument jest zbyt duży lub zbyt złożony, aby bezpiecznie go odczytać","error.m4s_needs_init": "Ten plik .m4s to fragment wideo strumieniowego i nie da się go odczytać bez osobnego segmentu początkowego (init)","notice.pdf_not_smaller": "Nie udało się zmniejszyć pliku, więc skopiowano go bez zmian","notice.cad_newer_left_out": "Pominięto obiekty, których wybrana wersja AutoCAD nie ma (multiodnośniki, siatki…)",diff --git a/src/Filee.App/Assets/i18n/pt-BR.json b/src/Filee.App/Assets/i18n/pt-BR.jsonindex 96fefb71..9b96f02f 100644--- a/src/Filee.App/Assets/i18n/pt-BR.json+++ b/src/Filee.App/Assets/i18n/pt-BR.json@@ -136,7 +136,6 @@"error.fon_unsupported": "Este tipo de fonte .fon não é compatível","error.fon_too_large": "A fonte .fon é grande demais para converter","error.fon_damaged": "O arquivo .fon está danificado ou incompleto",- "error.document_too_complex": "O documento é grande ou complexo demais para ser lido com segurança","error.m4s_needs_init": "Este .m4s é um pedaço de um vídeo transmitido por streaming e não pode ser lido sem o seu segmento inicial (init) separado","notice.pdf_not_smaller": "Não deu para deixar menor, então foi copiado como está","notice.cad_newer_left_out": "Objetos que a versão do AutoCAD escolhida não tem (multilinhas de chamada, malhas…) ficaram de fora",diff --git a/src/Filee.App/Assets/i18n/pt-PT.json b/src/Filee.App/Assets/i18n/pt-PT.jsonindex d9784665..41c27c75 100644--- a/src/Filee.App/Assets/i18n/pt-PT.json+++ b/src/Filee.App/Assets/i18n/pt-PT.json@@ -136,7 +136,6 @@"error.fon_unsupported": "Este tipo de fonte .fon não é suportado","error.fon_too_large": "A fonte .fon é demasiado grande para converter","error.fon_damaged": "O ficheiro .fon está danificado ou incompleto",- "error.document_too_complex": "O documento é demasiado grande ou complexo para ser lido em segurança","error.m4s_needs_init": "Este .m4s é um pedaço de um vídeo em streaming e não pode ser lido sem o respetivo segmento inicial (init) separado","notice.pdf_not_smaller": "Não foi possível reduzir o tamanho, pelo que o ficheiro foi copiado sem alterações","notice.cad_newer_left_out": "Os objetos que a versão de AutoCAD escolhida não suporta (linhas de chamada múltiplas, malhas…) foram omitidos",diff --git a/src/Filee.App/Assets/i18n/ru.json b/src/Filee.App/Assets/i18n/ru.jsonindex e7548813..e1a24eb7 100644--- a/src/Filee.App/Assets/i18n/ru.json+++ b/src/Filee.App/Assets/i18n/ru.json@@ -136,7 +136,6 @@"error.fon_unsupported": "Этот тип шрифта .fon не поддерживается","error.fon_too_large": "Шрифт .fon слишком велик для преобразования","error.fon_damaged": "Файл .fon повреждён или обрезан",- "error.document_too_complex": "Документ слишком большой или сложный, чтобы безопасно его прочитать","error.m4s_needs_init": "Этот .m4s — фрагмент потокового видео: без отдельного начального сегмента (init) его не прочитать","notice.pdf_not_smaller": "Уменьшить не получилось, файл скопирован как есть","notice.cad_newer_left_out": "Объекты, которых нет в выбранной версии AutoCAD (мультивыноски, сети…), не сохранены",diff --git a/src/Filee.App/Assets/i18n/th.json b/src/Filee.App/Assets/i18n/th.jsonindex 12e899c4..536d044e 100644--- a/src/Filee.App/Assets/i18n/th.json+++ b/src/Filee.App/Assets/i18n/th.json@@ -130,7 +130,6 @@"error.fon_unsupported": "ไม่รองรับฟอนต์ .fon ประเภทนี้","error.fon_too_large": "ฟอนต์ .fon มีขนาดใหญ่เกินกว่าจะแปลงได้","error.fon_damaged": "ไฟล์ .fon เสียหายหรือไม่สมบูรณ์",- "error.document_too_complex": "เอกสารใหญ่หรือซับซ้อนเกินกว่าจะอ่านได้อย่างปลอดภัย","error.m4s_needs_init": "ไฟล์ .m4s นี้เป็นชิ้นส่วนหนึ่งของวิดีโอสตรีมมิง และอ่านไม่ได้หากไม่มีเซกเมนต์เริ่มต้น (init) ที่แยกไว้","notice.pdf_not_smaller": "ไม่สามารถบีบอัดให้เล็กลงได้ จึงคัดลอกไฟล์ตามเดิม","notice.cad_newer_left_out": "ละวัตถุที่ AutoCAD เวอร์ชันที่เลือกไม่มี (มัลติลีดเดอร์ เมช …) ไว้",diff --git a/src/Filee.App/Assets/i18n/tr.json b/src/Filee.App/Assets/i18n/tr.jsonindex 96f6dc4e..449f8b30 100644--- a/src/Filee.App/Assets/i18n/tr.json+++ b/src/Filee.App/Assets/i18n/tr.json@@ -130,7 +130,6 @@"error.fon_unsupported": "Bu tür .fon yazı tipi desteklenmiyor","error.fon_too_large": ".fon yazı tipi dönüştürmek için çok büyük","error.fon_damaged": ".fon dosyası hasarlı veya eksik",- "error.document_too_complex": "Belge güvenli şekilde okunamayacak kadar büyük veya karmaşık","error.m4s_needs_init": "Bu .m4s, akışla gelen bir videonun bir parçası: ayrı başlangıç (init) segmenti olmadan okunamaz","notice.pdf_not_smaller": "Küçültülemediği için olduğu gibi kopyalandı","notice.cad_newer_left_out": "Seçilen AutoCAD sürümünün desteklemediği nesneler (çoklu kılavuzlar, ağlar…) çıkarıldı",diff --git a/src/Filee.App/Assets/i18n/zh-CN.json b/src/Filee.App/Assets/i18n/zh-CN.jsonindex 46155fad..8d069c66 100644--- a/src/Filee.App/Assets/i18n/zh-CN.json+++ b/src/Filee.App/Assets/i18n/zh-CN.json@@ -136,7 +136,6 @@"error.fon_unsupported": "不支持此类 .fon 字体","error.fon_too_large": ".fon 字体太大,无法转换","error.fon_damaged": ".fon 文件已损坏或不完整",- "error.document_too_complex": "文档过大或过于复杂,无法安全读取","error.m4s_needs_init": "此 .m4s 是流媒体视频的一个片段,没有单独的起始(init)分段就无法读取","notice.pdf_not_smaller": "无法再缩小,已原样复制","notice.cad_newer_left_out": "已省略所选 AutoCAD 版本没有的对象(多重引线、网格……)",diff --git a/src/Filee.App/Assets/i18n/zh-TW.json b/src/Filee.App/Assets/i18n/zh-TW.jsonindex 3b801805..5d555109 100644--- a/src/Filee.App/Assets/i18n/zh-TW.json+++ b/src/Filee.App/Assets/i18n/zh-TW.json@@ -136,7 +136,6 @@"error.fon_unsupported": "不支援此類 .fon 字型","error.fon_too_large": ".fon 字型太大,無法轉換","error.fon_damaged": ".fon 檔案已損壞或不完整",- "error.document_too_complex": "文件過大或過於複雜,無法安全讀取","error.m4s_needs_init": "此 .m4s 是串流影片的一個片段,沒有另外的起始(init)區段就無法讀取","notice.pdf_not_smaller": "無法再縮小,已原樣複製","notice.cad_newer_left_out": "已略過所選 AutoCAD 版本沒有的物件(複線引線、網格……)",diff --git a/src/Filee.Engines/Documents/DocumentBudget.cs b/src/Filee.Engines/Documents/DocumentBudget.csdeleted file mode 100644index 631f19cb..00000000--- a/src/Filee.Engines/Documents/DocumentBudget.cs+++ /dev/null@@ -1,58 +0,0 @@-// What one document reader may still build: nesting (tables in tables, text boxes, notes, groups, fields) and the-// number of paragraphs and objects. Readers call it where they recurse or add to the model, so a small file that-// expands into millions of paragraphs, or nests deeply enough to overflow the stack in a writer, is refused.--namespace Filee.Engines.Documents;--/// <summary>Counts what a reader builds against <see cref="DocumentLimits"/>.</summary>-internal sealed class DocumentBudget(DocumentLimits limits)-{- private int _depth;- private int _paragraphs;- private int _objects;-- public DocumentLimits Limits { get; } = limits;-- /// <summary>Current nesting depth.</summary>- public int Depth => _depth;-- public int Paragraphs => _paragraphs;-- public int Objects => _objects;-- /// <summary>Enters a nested level (a table cell, text box, note, group); dispose the result to leave it.</summary>- public Level Enter()- {- if (_depth >= Limits.MaxNestingDepth)- throw DocumentLimits.Exceeded($"Tables, text boxes, notes or groups are nested more than {Limits.MaxNestingDepth} levels deep.");- _depth++;- return new Level(this);- }-- /// <summary>Checks a count of open fields (fields inside fields).</summary>- public void Fields(int open)- {- if (open > Limits.MaxNestingDepth)- throw DocumentLimits.Exceeded($"Fields are nested more than {Limits.MaxNestingDepth} levels deep.");- }-- /// <summary>Counts a paragraph.</summary>- public void Paragraph()- {- if (++_paragraphs > Limits.MaxParagraphs)- throw DocumentLimits.Exceeded($"The document has more than {DocumentLimits.Count(Limits.MaxParagraphs)} paragraphs.");- }-- /// <summary>Counts a table, picture, shape, text box or equation.</summary>- public void Object()- {- if (++_objects > Limits.MaxObjects)- throw DocumentLimits.Exceeded($"The document has more than {DocumentLimits.Count(Limits.MaxObjects)} tables, pictures and drawing objects.");- }-- /// <summary>A nested level; leaves it when disposed.</summary>- public readonly struct Level(DocumentBudget budget) : IDisposable- {- public void Dispose() => budget._depth--;- }-}diff --git a/src/Filee.Engines/Documents/DocumentLimits.cs b/src/Filee.Engines/Documents/DocumentLimits.csdeleted file mode 100644index 892cf8e0..00000000--- a/src/Filee.Engines/Documents/DocumentLimits.cs+++ /dev/null@@ -1,96 +0,0 @@-// How much of an untrusted document Filee reads and lays out, shared by the document readers (HWPX, DOCX, OFD, and-// the HWP 5.0 reader when it comes) and the layout engine, so a hostile file can't hang, exhaust the memory or crash-// Filee. Every limit is far above what real documents need: a document that passes one is refused with-// error.document_too_complex rather than read in part.-//-// Where they apply:-// * DocumentPackage ZIP packages: entries, bytes per part and in total (counted while unpacking, so a header that-// understates a part does not help), the inflate ratio, XML depth and elements (SafeXml).-// * DocumentBudget readers: nesting of tables, text boxes, notes, groups and fields; paragraphs and objects.-// * PictureSize pictures whose header claims more than MaxPicturePixels are left out.-// * LayoutGuard the layout loop: pages, empty pages in a row, the time budget and cancellation.-// A compound file (CFB) reader adds its stream sizes to MaxPartBytes / MaxPackageBytes and must check sector chains-// for cycles itself.-//-// Embedded fonts are not read by any reader (DOCX odttf parts, HWPX and OFD font files keep only their names). A-// reader that ever uses them must pass them through Filee's own SFNT parser (Fonts/SfntFont) before Skia or HarfBuzz.--using System.Globalization;-using Filee.Core.Conversion;-using Filee.Engines.Infrastructure;--namespace Filee.Engines.Documents;--/// <summary>Limits for reading and laying out one document.</summary>-internal sealed record DocumentLimits-{- /// <summary>The limits Filee uses.</summary>- public static DocumentLimits Default { get; } = new();-- /// <summary>The error key of a document refused for passing a limit.</summary>- public const string ErrorKey = "error.document_too_complex";-- /// <summary>Bytes one part of a package (an XML part, a picture) may unpack to.</summary>- public long MaxPartBytes { get; init; } = 64L * 1024 * 1024;-- /// <summary>Bytes all parts read from one package may unpack to together.</summary>- public long MaxPackageBytes { get; init; } = 1024L * 1024 * 1024;-- /// <summary>Entries in a package (real documents have a few per page or picture).</summary>- public int MaxPackageEntries { get; init; } = 100_000;-- /// <summary>- /// How many times its compressed size a part may unpack to, once it is larger than <see cref="InflateRatioFloor"/>.- /// Deflate reaches about 1,000 on runs of one byte; XML from word processors stays far below 100.- /// </summary>- public int MaxInflateRatio { get; init; } = 200;-- /// <summary>What a part may always unpack to, whatever its ratio (small parts of repeated markup compress well).</summary>- public long InflateRatioFloor { get; init; } = 4L * 1024 * 1024;-- /// <summary>Levels of XML elements in a part. Tables nested <see cref="MaxNestingDepth"/> deep stay well within.</summary>- public int MaxXmlDepth { get; init; } = 512;-- /// <summary>XML elements in all parts of a package together (each costs some 100 bytes of memory in the tree).</summary>- public int MaxXmlElements { get; init; } = 5_000_000;-- /// <summary>Levels of tables in tables, text boxes, notes, groups and fields.</summary>- public int MaxNestingDepth { get; init; } = 32;-- /// <summary>Paragraphs in a document (cells, notes, headers and text boxes included).</summary>- public int MaxParagraphs { get; init; } = 1_000_000;-- /// <summary>Tables, pictures, shapes, text boxes and equations in a document.</summary>- public int MaxObjects { get; init; } = 200_000;-- /// <summary>- /// Columns of a table (as many as a spreadsheet has). Column numbers and spans beyond are cut there, so a damaged- /// cell address can't make a table of two billion columns.- /// </summary>- public int MaxTableColumns { get; init; } = 16_384;-- /// <summary>Pages the layout engine makes of one document.</summary>- public int MaxPages { get; init; } = 20_000;-- /// <summary>Pixels of one picture (16,384 × 16,384, beyond every camera); bigger pictures are left out.</summary>- public long MaxPicturePixels { get; init; } = 16_384L * 16_384;-- /// <summary>Pages in a row with nothing placed on them before the layout counts as stuck.</summary>- public int MaxConsecutiveEmptyPages { get; init; } = 64;-- /// <summary>How long laying out one document may take.</summary>- public TimeSpan LayoutTimeBudget { get; init; } = TimeSpan.FromMinutes(10);-- /// <summary>The XML limits of one part, given how many elements the package's other parts held.</summary>- internal XmlLimits Xml(int elementsBefore, bool preserveWhitespace) =>- new(MaxXmlDepth, MaxXmlElements, MaxPartBytes, preserveWhitespace, ElementsBefore: elementsBefore);-- /// <summary>The refusal for a document that passes a limit; <paramref name="detail"/> says which (in English).</summary>- public static ConversionRefusedException Exceeded(string detail) => new(ErrorKey, detail);-- /// <summary>"64 MB" for messages.</summary>- internal static string Megabytes(long bytes) => (bytes / (1024 * 1024)).ToString("N0", CultureInfo.InvariantCulture) + " MB";-- /// <summary>"20,000" for messages.</summary>- internal static string Count(long count) => count.ToString("N0", CultureInfo.InvariantCulture);-}diff --git a/src/Filee.Engines/Documents/DocumentPackage.cs b/src/Filee.Engines/Documents/DocumentPackage.csdeleted file mode 100644index 0cccc713..00000000--- a/src/Filee.Engines/Documents/DocumentPackage.cs+++ /dev/null@@ -1,240 +0,0 @@-// The ZIP package of a document (HWPX, DOCX, OFD), read within DocumentLimits: parts are looked up by name inside the-// package only, every part is counted while it is unpacked (its own size, the package's total and the inflate ratio),-// XML is read by SafeXml without DTDs or a resolver, and parts are only ever written out under names Filee makes.-// A damaged package fails with InvalidDataException, one that passes a limit with error.document_too_complex.--using System.IO.Compression;-using System.Text;-using System.Xml;-using System.Xml.Linq;-using Filee.Engines.Infrastructure;--namespace Filee.Engines.Documents;--/// <summary>A document package opened for reading.</summary>-internal sealed class DocumentPackage : IDisposable-{- private readonly ZipArchive _zip;- private long _total;- private int _elements;-- private DocumentPackage(ZipArchive zip, DocumentLimits limits)- {- _zip = zip;- Limits = limits;- }-- public DocumentLimits Limits { get; }-- /// <summary>Bytes unpacked so far.</summary>- public long BytesRead => _total;-- /// <summary>XML elements read so far.</summary>- public int ElementsRead => _elements;-- public IReadOnlyCollection<ZipArchiveEntry> Entries => _zip.Entries;-- /// <summary>Opens the package at <paramref name="path"/>; <paramref name="notAPackage"/> makes the error for a file that is no ZIP.</summary>- public static DocumentPackage Open(string path, DocumentLimits? limits = null, Func<Exception>? notAPackage = null) =>- Open(() => ZipFile.OpenRead(path), limits ?? DocumentLimits.Default, notAPackage);-- /// <summary>A package in a stream (left open).</summary>- public static DocumentPackage Open(Stream stream, DocumentLimits? limits = null, Func<Exception>? notAPackage = null) =>- Open(() => new ZipArchive(stream, ZipArchiveMode.Read, leaveOpen: true), limits ?? DocumentLimits.Default, notAPackage);-- private static DocumentPackage Open(Func<ZipArchive> open, DocumentLimits limits, Func<Exception>? notAPackage)- {- ZipArchive zip;- try- {- zip = open();- }- catch (Exception ex) when (ex is InvalidDataException or EndOfStreamException or ArgumentException or NotSupportedException- || ex is IOException and not (FileNotFoundException or DirectoryNotFoundException))- {- throw notAPackage?.Invoke() ?? new InvalidDataException("The file is not a ZIP package. It may be damaged.", ex);- }- try- {- // The central directory is read when the entries are first listed.- if (zip.Entries.Count > limits.MaxPackageEntries)- throw DocumentLimits.Exceeded($"The package has more than {DocumentLimits.Count(limits.MaxPackageEntries)} parts.");- }- catch (Exception ex) when (ex is InvalidDataException or EndOfStreamException or ArgumentException or IOException)- {- zip.Dispose();- throw notAPackage?.Invoke() ?? new InvalidDataException("The file is not a ZIP package. It may be damaged.", ex);- }- catch- {- zip.Dispose();- throw;- }- return new DocumentPackage(zip, limits);- }-- public void Dispose() => _zip.Dispose();-- /// <summary>The entry of that exact name; null when there is none.</summary>- public ZipArchiveEntry? GetEntry(string name)- {- try- {- return name.Length == 0 ? null : _zip.GetEntry(name);- }- catch (ArgumentException)- {- return null;- }- }-- /// <summary>- /// The unpacked bytes of <paramref name="entry"/>, counted against the part, package and ratio limits. A part whose- /// header already claims too much is refused before it is unpacked.- /// </summary>- public Stream Open(ZipArchiveEntry entry)- {- var name = entry.FullName;- if (entry.Length > Limits.MaxPartBytes)- throw PartTooLarge(name);- if (_total + entry.Length > Limits.MaxPackageBytes)- throw PackageTooLarge();- Stream inner;- try- {- inner = entry.Open();- }- catch (Exception ex) when (ex is IOException or NotSupportedException or ArgumentException)- {- throw new InvalidDataException($"The part {name} of the package can't be unpacked ({ex.Message}).", ex);- }- var compressed = Math.Max(1, entry.CompressedLength);- long counted = 0;- return new LimitedStream(new DamageStream(inner, name), Limits.MaxPartBytes, () => PartTooLarge(name), read =>- {- _total += read - counted;- counted = read;- if (_total > Limits.MaxPackageBytes)- throw PackageTooLarge();- if (read > Limits.InflateRatioFloor && read / compressed > Limits.MaxInflateRatio)- throw DocumentLimits.Exceeded($"The part {name} unpacks to more than {Limits.MaxInflateRatio} times its packed size.");- });- }-- /// <summary>- /// An XML part read by <see cref="SafeXml"/>; its elements count against the package's. Throws- /// <see cref="XmlException"/> for a part that is not well-formed XML (callers say which part of which format).- /// </summary>- public XDocument LoadXml(ZipArchiveEntry entry, bool preserveWhitespace = true)- {- using var stream = Open(entry);- try- {- var document = SafeXml.Load(stream, Limits.Xml(_elements, preserveWhitespace),- message => DocumentLimits.Exceeded($"{entry.FullName}: {message}"), out var elements);- _elements += elements;- return document;- }- catch (Exception ex) when (ex is DecoderFallbackException or ArgumentException)- {- throw new XmlException(ex.Message, ex);- }- }-- /// <summary>The bytes of a part; null when it holds more than <paramref name="max"/> (the part is then left out).</summary>- public byte[]? ReadBytes(ZipArchiveEntry entry, long max)- {- if (entry.Length > max)- return null;- using var stream = Open(entry);- using var copy = new MemoryStream((int)Math.Min(entry.Length, 1024 * 1024));- var buffer = new byte[81920];- int count;- while ((count = stream.Read(buffer)) > 0)- {- if (copy.Length + count > max)- return null;- copy.Write(buffer, 0, count);- }- return copy.ToArray();- }-- /// <summary>- /// Unpacks a picture into a new file at <paramref name="path"/>. Returns false (and leaves no file) when its- /// header claims more than <see cref="DocumentLimits.MaxPicturePixels"/>.- /// </summary>- public bool ExtractPicture(ZipArchiveEntry entry, string path)- {- using (var source = Open(entry))- using (var target = File.Create(path))- source.CopyTo(target);- if (PictureSize.Read(path) is { } size && (long)size.Width * size.Height > Limits.MaxPicturePixels)- {- File.Delete(path);- return false;- }- return true;- }-- /// <summary>- /// The extension of a part name for a file Filee writes: "." and up to 8 ASCII letters or digits, else "" (a name- /// in a hostile package may hold anything, ":stream" included).- /// </summary>- public static string SafeExtension(string name)- {- var dot = name.LastIndexOf('.');- if (dot < 0 || name.Length - dot - 1 is < 1 or > 8 || name.AsSpan(dot + 1).ContainsAnyExcept(AsciiLettersAndDigits))- return "";- return name[dot..].ToLowerInvariant();- }-- private static readonly System.Buffers.SearchValues<char> AsciiLettersAndDigits =- System.Buffers.SearchValues.Create("ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789");-- /// <summary>Reads a part; a package cut short or damaged inside a part is invalid data, not a failing disk.</summary>- private sealed class DamageStream(Stream inner, string name) : Stream- {- public override bool CanRead => true;- public override bool CanSeek => false;- public override bool CanWrite => false;- public override long Length => throw new NotSupportedException();-- public override long Position- {- get => throw new NotSupportedException();- set => throw new NotSupportedException();- }-- public override int Read(byte[] buffer, int offset, int count) => Read(buffer.AsSpan(offset, count));-- public override int Read(Span<byte> buffer)- {- try- {- return inner.Read(buffer);- }- catch (IOException ex)- {- throw new InvalidDataException($"The part {name} of the package is damaged ({ex.Message}).", ex);- }- }-- protected override void Dispose(bool disposing)- {- if (disposing)- inner.Dispose();- base.Dispose(disposing);- }-- public override void Flush() { }- public override long Seek(long offset, SeekOrigin origin) => throw new NotSupportedException();- public override void SetLength(long value) => throw new NotSupportedException();- public override void Write(byte[] buffer, int offset, int count) => throw new NotSupportedException();- }-- private Exception PartTooLarge(string name) =>- DocumentLimits.Exceeded($"The part {name} unpacks to more than {DocumentLimits.Megabytes(Limits.MaxPartBytes)}.");-- private Exception PackageTooLarge() =>- DocumentLimits.Exceeded($"The package unpacks to more than {DocumentLimits.Megabytes(Limits.MaxPackageBytes)}.");-}diff --git a/src/Filee.Engines/Documents/LayoutGuard.cs b/src/Filee.Engines/Documents/LayoutGuard.csdeleted file mode 100644index 79c142fa..00000000--- a/src/Filee.Engines/Documents/LayoutGuard.cs+++ /dev/null@@ -1,71 +0,0 @@-// Guards for the layout loop, so a document can't keep the layout engine busy forever: every paragraph checks the-// cancellation token and the time budget, every page counts against MaxPages, and pages in a row that receive nothing-// mean the layout is stuck. An object larger than every page is clipped to the area it goes into and placed, so it-// can't push itself from page to page without end.--using System.Diagnostics;--namespace Filee.Engines.Documents;--/// <summary>Checks a layout run against <see cref="DocumentLimits"/>.</summary>-internal sealed class LayoutGuard-{- private readonly DocumentLimits _limits;- private readonly CancellationToken _cancellationToken;- private readonly Func<TimeSpan> _elapsed;- private int _pages;- private int _emptyInARow;-- /// <param name="elapsed">Time since the layout started (tests pass their own clock).</param>- public LayoutGuard(DocumentLimits limits, CancellationToken cancellationToken, Func<TimeSpan>? elapsed = null)- {- _limits = limits;- _cancellationToken = cancellationToken;- if (elapsed is null)- {- var start = Stopwatch.GetTimestamp();- elapsed = () => Stopwatch.GetElapsedTime(start);- }- _elapsed = elapsed;- }-- /// <summary>Pages finished so far.</summary>- public int Pages => _pages;-- /// <summary>Called before each paragraph is laid out: throws when the job was cancelled or the time is up.</summary>- /// <exception cref="OperationCanceledException">The job was cancelled.</exception>- public void Paragraph()- {- _cancellationToken.ThrowIfCancellationRequested();- if (_elapsed() > _limits.LayoutTimeBudget)- throw DocumentLimits.Exceeded($"Laying out the document took longer than {Describe(_limits.LayoutTimeBudget)}.");- }-- private static string Describe(TimeSpan time) => time.TotalMinutes >= 1- ? time.TotalMinutes == 1 ? "1 minute" : $"{time.TotalMinutes:0} minutes"- : time.TotalSeconds == 1 ? "1 second" : $"{time.TotalSeconds:0} seconds";-- /// <summary>Called when a page is finished; <paramref name="empty"/> when nothing was placed on it.</summary>- public void PageFinished(bool empty)- {- if (++_pages > _limits.MaxPages)- throw DocumentLimits.Exceeded($"The document has more than {DocumentLimits.Count(_limits.MaxPages)} pages.");- _emptyInARow = empty ? _emptyInARow + 1 : 0;- if (_emptyInARow > _limits.MaxConsecutiveEmptyPages)- throw DocumentLimits.Exceeded($"The layout made more than {_limits.MaxConsecutiveEmptyPages} empty pages in a row.");- }-- /// <summary>- /// The size an object is placed with in an area of <paramref name="areaWidth"/> × <paramref name="areaHeight"/>- /// (the body of an empty page): its own size when it fits, else clipped to the area. <c>Clipped</c> tells the- /// layout to draw only that part rather than move the object to the next page again. Sizes that are not finite- /// numbers or negative count as 0.- /// </summary>- public static (double Width, double Height, bool Clipped) Fit(double width, double height, double areaWidth, double areaHeight)- {- static double Clean(double value) => double.IsFinite(value) && value > 0 ? value : 0;- (width, height, areaWidth, areaHeight) = (Clean(width), Clean(height), Clean(areaWidth), Clean(areaHeight));- var clipped = width > areaWidth || height > areaHeight;- return (Math.Min(width, areaWidth), Math.Min(height, areaHeight), clipped);- }-}diff --git a/src/Filee.Engines/Documents/PictureSize.cs b/src/Filee.Engines/Documents/PictureSize.csdeleted file mode 100644index ce944b0a..00000000--- a/src/Filee.Engines/Documents/PictureSize.cs+++ /dev/null@@ -1,146 +0,0 @@-// The pixel size a picture's header claims, read without decoding it, so a picture that would take gigabytes once-// decoded (a few kilobytes of PNG can claim 100,000 × 100,000 pixels) is left out before anything decodes it. PNG,-// JPEG, GIF, BMP and WebP; other formats (TIFF, EMF, WMF, SVG) give no size here and are checked where they are drawn.--using System.Buffers.Binary;--namespace Filee.Engines.Documents;--/// <summary>Reads the width and height from a picture's header.</summary>-internal static class PictureSize-{- /// <summary>JPEG segments looked at before the frame header (files have a dozen).</summary>- private const int MaxJpegSegments = 1000;-- /// <summary>The size in pixels; null for formats it does not know and headers it can't read.</summary>- public static (int Width, int Height)? Read(string path)- {- try- {- using var stream = File.OpenRead(path);- return Read(stream);- }- catch (Exception ex) when (ex is IOException or UnauthorizedAccessException)- {- return null;- }- }-- /// <inheritdoc cref="Read(string)"/>- public static (int Width, int Height)? Read(Stream stream)- {- Span<byte> head = stackalloc byte[30];- var length = ReadUpTo(stream, head);- head = head[..length];- if (head is [0x89, (byte)'P', (byte)'N', (byte)'G', ..] && head.Length >= 24)- return Size(BinaryPrimitives.ReadUInt32BigEndian(head[16..]), BinaryPrimitives.ReadUInt32BigEndian(head[20..]));- if (head is [(byte)'G', (byte)'I', (byte)'F', (byte)'8', ..] && head.Length >= 10)- return Size(BinaryPrimitives.ReadUInt16LittleEndian(head[6..]), BinaryPrimitives.ReadUInt16LittleEndian(head[8..]));- if (head is [(byte)'B', (byte)'M', ..] && head.Length >= 26)- {- var header = BinaryPrimitives.ReadUInt32LittleEndian(head[14..]);- return header == 12- ? Size(BinaryPrimitives.ReadUInt16LittleEndian(head[18..]), BinaryPrimitives.ReadUInt16LittleEndian(head[20..]))- : Size((uint)Math.Abs((long)BinaryPrimitives.ReadInt32LittleEndian(head[18..])), (uint)Math.Abs((long)BinaryPrimitives.ReadInt32LittleEndian(head[22..])));- }- if (head is [(byte)'R', (byte)'I', (byte)'F', (byte)'F', _, _, _, _, (byte)'W', (byte)'E', (byte)'B', (byte)'P', ..] && head.Length >= 30)- return WebP(head);- if (head is [0xFF, 0xD8, ..])- return Jpeg(stream, head);- return null;- }-- private static (int Width, int Height)? WebP(ReadOnlySpan<byte> head)- {- var chunk = head.Slice(12, 4);- if (chunk.SequenceEqual("VP8X"u8))- {- var width = head[24] | head[25] << 8 | head[26] << 16;- var height = head[27] | head[28] << 8 | head[29] << 16;- return Size((uint)width + 1, (uint)height + 1);- }- if (chunk.SequenceEqual("VP8L"u8) && head[20] == 0x2F)- {- var bits = BinaryPrimitives.ReadUInt32LittleEndian(head[21..]);- return Size((bits & 0x3FFF) + 1, ((bits >> 14) & 0x3FFF) + 1);- }- if (chunk.SequenceEqual("VP8 "u8))- return Size(BinaryPrimitives.ReadUInt16LittleEndian(head[26..]) & 0x3FFFu, BinaryPrimitives.ReadUInt16LittleEndian(head[28..]) & 0x3FFFu);- return null;- }-- /// <summary>The first frame header (SOFn) after the segments before it.</summary>- private static (int Width, int Height)? Jpeg(Stream stream, ReadOnlySpan<byte> head)- {- // Continue from byte 2 of the file: the head was read already.- var buffered = new Queue<byte>(head[2..].ToArray());- int Next()- {- if (buffered.Count > 0)- return buffered.Dequeue();- return stream.ReadByte();- }-- Span<byte> frame = stackalloc byte[5];- for (var segment = 0; segment < MaxJpegSegments; segment++)- {- var marker = Next();- if (marker < 0)- return null;- if (marker != 0xFF)- return null;- var code = Next();- while (code == 0xFF)- code = Next();- if (code < 0 || code is 0xD9 or 0xDA)- return null; // end of image or scan data before any frame header- if (code is 0x01 or (>= 0xD0 and <= 0xD7))- continue; // markers without a length- var high = Next();- var low = Next();- if (high < 0 || low < 0)- return null;- var length = high << 8 | low;- if (length < 2)- return null;- if (code is >= 0xC0 and <= 0xCF and not (0xC4 or 0xC8 or 0xCC))- {- for (var i = 0; i < frame.Length; i++)- {- var b = Next();- if (b < 0)- return null;- frame[i] = (byte)b;- }- return Size(BinaryPrimitives.ReadUInt16BigEndian(frame[3..]), BinaryPrimitives.ReadUInt16BigEndian(frame[1..]));- }- var skip = length - 2;- for (; skip > 0 && buffered.Count > 0; skip--)- buffered.Dequeue();- if (stream.CanSeek)- {- if (stream.Seek(skip, SeekOrigin.Current) > stream.Length)- return null;- continue;- }- for (; skip > 0; skip--)- {- if (Next() < 0)- return null;- }- }- return null;- }-- private static (int Width, int Height)? Size(uint width, uint height) =>- width == 0 || height == 0 ? null : ((int)Math.Min(width, int.MaxValue), (int)Math.Min(height, int.MaxValue));-- private static int ReadUpTo(Stream stream, Span<byte> buffer)- {- var total = 0;- int read;- while (total < buffer.Length && (read = stream.Read(buffer[total..])) > 0)- total += read;- return total;- }-}diff --git a/src/Filee.Engines/Geo/KmlFormat.cs b/src/Filee.Engines/Geo/KmlFormat.csindex c22612bd..c6c35c37 100644--- a/src/Filee.Engines/Geo/KmlFormat.cs+++ b/src/Filee.Engines/Geo/KmlFormat.cs@@ -11,7 +11,6 @@ using System.IO.Compression;using System.Text.Json;using System.Xml;using System.Xml.Linq;-using Filee.Engines.Infrastructure;namespace Filee.Engines.Geo;@@ -410,15 +409,67 @@ internal static class GeoXml/// <summary>/// Parses XML without DTDs or external entities, so a hostile file can't read files or expand into gigabytes, and- /// refuses elements nested more than <see cref="MaxElementDepth"/> levels (see <see cref="SafeXml"/>). Namespace- /// declarations and prefixes are not kept; names are the local name and namespace.+ /// refuses elements nested more than <see cref="MaxElementDepth"/> levels. The tree is built here from the reader+ /// rather than by <c>XDocument.Load</c>, which takes time quadratic in the depth (a 1.4 MB file nested 100,000 deep+ /// kept it busy for 48 seconds, the reader alone needs a quarter of a second) and so couldn't be allowed to see such+ /// a file. Namespace declarations and prefixes are not kept; names are the local name and namespace./// </summary>public static XDocument Load(Stream stream, int maxElements = MaxElements){- try+ var settings = new XmlReaderSettings{+ DtdProcessing = DtdProcessing.Prohibit,+ XmlResolver = null,+ MaxCharactersFromEntities = 0,+ CheckCharacters = false,// About 1 GB of memory at the most: the tree takes some 16 bytes for every character.- return SafeXml.Load(stream, new XmlLimits(MaxElementDepth, maxElements, 1L << 26, KeepNamespaceDeclarations: false, CheckCharacters: false));+ MaxCharactersInDocument = 1L << 26,+ };+ try+ {+ using var reader = XmlReader.Create(stream, settings);+ var document = new XDocument();+ XContainer current = document;+ var depth = 0;+ var elements = 0;+ while (reader.Read())+ {+ switch (reader.NodeType)+ {+ case XmlNodeType.Element:+ if (++depth > MaxElementDepth)+ throw new InvalidDataException($"The file nests elements more than {MaxElementDepth} levels deep.");+ if (++elements > maxElements)+ throw new InvalidDataException("The file has more than " + maxElements.ToString("N0", System.Globalization.CultureInfo.InvariantCulture) + " elements.");+ var element = new XElement(XName.Get(reader.LocalName, reader.NamespaceURI));+ var empty = reader.IsEmptyElement;+ if (reader.HasAttributes)+ {+ while (reader.MoveToNextAttribute())+ {+ if (reader.NamespaceURI != "http://www.w3.org/2000/xmlns/")+ element.SetAttributeValue(XName.Get(reader.LocalName, reader.NamespaceURI), reader.Value);+ }+ reader.MoveToElement();+ }+ current.Add(element);+ if (empty)+ depth--;+ else+ current = element;+ break;+ case XmlNodeType.EndElement:+ current = current.Parent ?? (XContainer)document;+ depth--;+ break;+ case XmlNodeType.Text or XmlNodeType.CDATA or XmlNodeType.SignificantWhitespace or XmlNodeType.Whitespace:+ // Text outside the root element (white space between declarations) is no content.+ if (current is XElement)+ current.Add(new XText(reader.Value));+ break;+ }+ }+ return document;}catch (XmlException ex){diff --git a/src/Filee.Engines/Infrastructure/LimitedStream.cs b/src/Filee.Engines/Geo/LimitedStream.cssimilarity index 51%rename from src/Filee.Engines/Infrastructure/LimitedStream.csrename to src/Filee.Engines/Geo/LimitedStream.csindex ed171a01..57e7aa38 100644--- a/src/Filee.Engines/Infrastructure/LimitedStream.cs+++ b/src/Filee.Engines/Geo/LimitedStream.cs@@ -1,31 +1,13 @@// A read-only wrapper that counts the bytes read through it and fails once they pass a limit, so a ZIP entry that// unpacks to far more than its header says (a ZIP bomb) stops at a known size instead of filling the memory.-namespace Filee.Engines.Infrastructure;+namespace Filee.Engines.Geo;-/// <summary>Reads at most <c>limit</c> bytes of <c>inner</c>, then throws (<see cref="InvalidDataException"/> by default).</summary>-internal sealed class LimitedStream : Stream+/// <summary>Reads at most <c>limit</c> bytes of <paramref name="inner"/>, then throws <see cref="InvalidDataException"/>.</summary>+internal sealed class LimitedStream(Stream inner, long limit, string message) : Stream{- private readonly Stream _inner;- private readonly long _limit;- private readonly Func<Exception> _over;- private readonly Action<long>? _onRead;private long _read;- public LimitedStream(Stream inner, long limit, string message) : this(inner, limit, () => new InvalidDataException(message))- {- }-- /// <param name="over">The exception thrown once more than <paramref name="limit"/> bytes were read.</param>- /// <param name="onRead">Called after every read with the number of bytes read so far (for limits shared by several streams).</param>- public LimitedStream(Stream inner, long limit, Func<Exception> over, Action<long>? onRead = null)- {- _inner = inner;- _limit = limit;- _over = over;- _onRead = onRead;- }-public override bool CanRead => true;public override bool CanSeek => false;public override bool CanWrite => false;@@ -41,19 +23,17 @@ internal sealed class LimitedStream : Streampublic override int Read(Span<byte> buffer){- var read = _inner.Read(buffer);+ var read = inner.Read(buffer);_read += read;- if (_read > _limit)- throw _over();- if (read > 0)- _onRead?.Invoke(_read);+ if (_read > limit)+ throw new InvalidDataException(message);return read;}protected override void Dispose(bool disposing){if (disposing)- _inner.Dispose();+ inner.Dispose();base.Dispose(disposing);}diff --git a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Drawing.cs b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Drawing.csindex 0d8a4388..c70003a5 100644--- a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Drawing.cs+++ b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Drawing.cs@@ -3,7 +3,6 @@using System.Globalization;using System.Xml.Linq;-using Filee.Engines.Documents;namespace Filee.Engines.Hwp.Hwpx.Docx;@@ -59,7 +58,6 @@ internal sealed partial class DocxReader{foreach (var obj in objects){- _budget.Object();if (obj.Name == Pic + "pic"){if (Picture(obj, width, height, anchor) is { } picture)@@ -81,7 +79,6 @@ internal sealed partial class DocxReaderprivate IEnumerable<HInline> Group(XElement group, int width, int height, HAnchor? anchor,(double X, double Y, double ScaleX, double ScaleY) parent){- using var level = _budget.Enter();var xfrm = group.Element(Wpg + "grpSpPr")?.Element(A + "xfrm") ?? group.Element(A + "grpSpPr")?.Element(A + "xfrm");var chOff = xfrm?.Element(A + "chOff");var chExt = xfrm?.Element(A + "chExt");@@ -233,7 +230,6 @@ internal sealed partial class DocxReader/// <summary>Text box paragraphs; Word's document grid does not apply inside text boxes.</summary>private void ReadTextBoxContent(XElement content, List<HBlock> output){- using var level = _budget.Enter();_textBoxDepth++;try{@@ -404,12 +400,13 @@ internal sealed partial class DocxReaderreturn null;if (_media.TryGetValue(rel.Target, out var existing))return existing;- if (_package.GetEntry(rel.Target) is not { } entry)+ if (_zip.GetEntry(rel.Target) is not { } entry)return null;Directory.CreateDirectory(_mediaFolder);- string? path = Path.Combine(_mediaFolder, $"docx-media-{_media.Count + 1}{DocumentPackage.SafeExtension(rel.Target)}");- if (!_package.ExtractPicture(entry, path))- path = null; // larger than any picture should be: left out+ var path = Path.Combine(_mediaFolder, $"docx-media-{_media.Count + 1}{Path.GetExtension(rel.Target)}");+ using (var source = entry.Open())+ using (var target = File.Create(path))+ source.CopyTo(target);_media[rel.Target] = path;return path;}@@ -425,12 +422,10 @@ internal sealed partial class DocxReadercontinue;if (shape.Name.LocalName == "group"){- using var level = _budget.Enter();foreach (var inline in Vml(shape, format))yield return inline;continue;}- _budget.Object();if (shape.Name.LocalName is "shapetype")continue;diff --git a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Styles.cs b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Styles.csindex 537fcc60..328980fe 100644--- a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Styles.cs+++ b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Styles.cs@@ -294,10 +294,8 @@ internal sealed partial class DocxReadervar root = part?.Xml.Root;if (root is null)return;- // Of two definitions with one id (a damaged file) the first counts.- var abstracts = new Dictionary<string, XElement>();- foreach (var abstractNum in root.Elements(W + "abstractNum"))- abstracts.TryAdd(Attr(abstractNum, "abstractNumId") ?? "", abstractNum);+ var abstracts = root.Elements(W + "abstractNum")+ .ToDictionary(a => Attr(a, "abstractNumId") ?? "", a => a);foreach (var num in root.Elements(W + "num")){var numId = Attr(num, "numId") ?? "";@@ -337,11 +335,7 @@ internal sealed partial class DocxReader// ───────────────────────── Resolution ─────────────────────────/// <summary>Merged properties of a paragraph or character style including everything it is based on.</summary>- private (ParaProps Para, RunProps Run) ResolveStyle(string? styleId) => ResolveStyle(styleId, 0);-- /// <param name="depth">Styles below this one in the chain: a chain longer than <see cref="MaxStyleChain"/> (a- /// damaged or hostile file; real chains are a few long) starts from the defaults instead of overflowing the stack.</param>- private (ParaProps Para, RunProps Run) ResolveStyle(string? styleId, int depth)+ private (ParaProps Para, RunProps Run) ResolveStyle(string? styleId){if (styleId is null || !_styles.TryGetValue(styleId, out var style))return (_defaultPara.Clone(), _defaultRun.Clone());@@ -350,9 +344,7 @@ internal sealed partial class DocxReader// Guard against basedOn cycles in damaged files._resolvedStyles[styleId] = (_defaultPara.Clone(), _defaultRun.Clone());- var (para, run) = style.BasedOn is { } parent && parent != styleId && depth < MaxStyleChain- ? ResolveStyle(parent, depth + 1)- : (_defaultPara.Clone(), _defaultRun.Clone());+ var (para, run) = style.BasedOn is { } parent && parent != styleId ? ResolveStyle(parent) : (_defaultPara.Clone(), _defaultRun.Clone());para.Apply(style.PPr);run.Apply(style.RPr);_resolvedStyles[styleId] = (para.Clone(), run.Clone());@@ -395,7 +387,7 @@ internal sealed partial class DocxReader{// Character styles only carry run properties; apply their chain on top of the paragraph's.var chain = new List<Style>();- for (var current = style; current is not null && chain.Count < MaxStyleChain; current = current.BasedOn is { } b ? _styles.GetValueOrDefault(b) : null)+ for (var current = style; current is not null && chain.Count < 20; current = current.BasedOn is { } b ? _styles.GetValueOrDefault(b) : null)chain.Add(current);for (var i = chain.Count - 1; i >= 0; i--)run.Apply(chain[i].RPr);@@ -691,16 +683,8 @@ internal sealed partial class DocxReaderprivate static string? Val(XElement? element) => Attr(element, "val");- /// <summary>- /// A length in twips (or another whole number). Values beyond ±100 million (70 km of twips; real ones stay below- /// 50,000) are cut there, so arithmetic on them (HWPUNIT is 5 twips, Math.Abs) can't overflow.- /// </summary>private static int? Twips(XElement? element, string name) =>- double.TryParse(Attr(element, name), NumberStyles.Float, CultureInfo.InvariantCulture, out var value) && !double.IsNaN(value)- ? (int)Math.Clamp(value, -MaxTwips, MaxTwips)- : null;-- private const int MaxTwips = 100_000_000;+ double.TryParse(Attr(element, name), NumberStyles.Float, CultureInfo.InvariantCulture, out var value) ? (int)value : null;private static long? Long(XElement? element, string name) =>long.TryParse(Attr(element, name), NumberStyles.Integer, CultureInfo.InvariantCulture, out var value) ? value : null;diff --git a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Tables.cs b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Tables.csindex 2baeadab..d5eaf6e4 100644--- a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Tables.cs+++ b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.Tables.cs@@ -10,8 +10,6 @@ internal sealed partial class DocxReader{private HTable ReadTable(XElement tbl){- _budget.Object();- using var level = _budget.Enter();var tblPr = tbl.Element(W + "tblPr");var style = _styles.GetValueOrDefault(Val(tblPr?.Element(W + "tblStyle")) ?? _defaultTableStyle ?? "");var styleChain = StyleChain(style);@@ -66,18 +64,16 @@ internal sealed partial class DocxReaderif (trPr?.Element(W + "trHeight") is { } height && Twips(height, "val") is > 0 and var h)row.Height = HwpxUnits.FromTwips(h);- // Column numbers and spans of damaged files stay within the limit, so they can't overflow.- var maxColumns = _budget.Limits.MaxTableColumns;- var column = Math.Clamp(Twips(trPr?.Element(W + "gridBefore"), "val") ?? 0, 0, maxColumns);+ var column = Twips(trPr?.Element(W + "gridBefore"), "val") ?? 0;foreach (var tc in tr.Elements().SelectMany(e => e.Name == W + "tc" ? [e] : FlattenCells(e))){var tcPr = tc.Element(W + "tcPr");- var span = Math.Clamp(Twips(tcPr?.Element(W + "gridSpan"), "val") ?? 1, 1, maxColumns);+ var span = Math.Max(1, Twips(tcPr?.Element(W + "gridSpan"), "val") ?? 1);var vMerge = tcPr?.Element(W + "vMerge");if (vMerge is not null && Val(vMerge) is not "restart" && mergeOrigin.TryGetValue(column, out var origin)){origin.RowSpan++;- column = Math.Min(column + span, maxColumns);+ column += span;continue;}@@ -123,7 +119,7 @@ internal sealed partial class DocxReaderelsemergeOrigin.Remove(column);row.Cells.Add(cell);- column = Math.Min(column + span, maxColumns);+ column += span;}table.Rows.Add(row);table.ColumnCount = Math.Max(table.ColumnCount, column);@@ -134,7 +130,7 @@ internal sealed partial class DocxReaderprivate List<Style> StyleChain(Style? style){var chain = new List<Style>();- for (var current = style; current is not null && chain.Count < MaxStyleChain; current = current.BasedOn is { } b ? _styles.GetValueOrDefault(b) : null)+ for (var current = style; current is not null && chain.Count < 20; current = current.BasedOn is { } b ? _styles.GetValueOrDefault(b) : null)chain.Insert(0, current);return chain;}diff --git a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.cs b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.csindex 0006b843..8a3f316c 100644--- a/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.cs+++ b/src/Filee.Engines/Hwp/Hwpx/Docx/DocxReader.cs@@ -4,14 +4,11 @@// footnotes and endnotes, bookmarks and hyperlinks (including the links of a Word table of contents).//// Split over partial files: this one walks the package and the text, DocxReader.Styles resolves formatting,-// DocxReader.Tables and DocxReader.Drawing handle tables and graphic objects. The package is read within-// DocumentLimits (Documents/DocumentPackage); embedded fonts (word/fonts) are not read.+// DocxReader.Tables and DocxReader.Drawing handle tables and graphic objects.using System.IO.Compression;using System.Text;-using System.Xml;using System.Xml.Linq;-using Filee.Engines.Documents;namespace Filee.Engines.Hwp.Hwpx.Docx;@@ -31,14 +28,10 @@ internal sealed partial class DocxReaderprivate static readonly XNamespace M = "http://schemas.openxmlformats.org/officeDocument/2006/math";private static readonly XNamespace Dc = "http://purl.org/dc/elements/1.1/";- /// <summary>Styles followed through basedOn at the most (real chains are a few long; damaged files loop).</summary>- private const int MaxStyleChain = 20;-- private readonly DocumentPackage _package;- private readonly DocumentBudget _budget;+ private readonly ZipArchive _zip;private readonly string _mediaFolder;private readonly Dictionary<string, Part?> _parts = [];- private readonly Dictionary<string, string?> _media = [];+ private readonly Dictionary<string, string> _media = [];private readonly Dictionary<string, XElement> _footnotes = [];private readonly Dictionary<string, XElement> _endnotes = [];private readonly List<FieldState> _fields = [];@@ -51,16 +44,12 @@ internal sealed partial class DocxReaderprivate int _sectionIndex;private int _textBoxDepth;- /// <summary>True while a note is read: Word has no notes in notes, and a note that refers to itself would never end.</summary>- private bool _inNote;-/// <summary>The part being read; relationship ids (images, links) are resolved against it.</summary>private Part _part;- private DocxReader(DocumentPackage package, string mediaFolder)+ private DocxReader(ZipArchive zip, string mediaFolder){- _package = package;- _budget = new DocumentBudget(package.Limits);+ _zip = zip;_mediaFolder = mediaFolder;var mainPath = RelationshipsOf("").FirstOrDefault(r => r.Value.Type.EndsWith("/officeDocument", StringComparison.Ordinal)).Value.Target ?? "word/document.xml";@@ -68,27 +57,10 @@ internal sealed partial class DocxReader}/// <summary>Reads <paramref name="path"/>; embedded pictures are extracted into <paramref name="mediaFolder"/>.</summary>- public static HDocument Read(string path, string mediaFolder) => Read(path, mediaFolder, DocumentLimits.Default);-- /// <summary>Reads within other <paramref name="limits"/> than <see cref="DocumentLimits.Default"/> (for tests).</summary>- internal static HDocument Read(string path, string mediaFolder, DocumentLimits limits)+ public static HDocument Read(string path, string mediaFolder){- using var package = DocumentPackage.Open(path, limits,- () => new InvalidDataException("The file is not a Word document (it is not a ZIP package). It may be damaged or protected by document security (DRM) software."));- return new DocxReader(package, mediaFolder).ReadDocument();- }-- /// <summary>An XML part; damaged XML is invalid data with the part's name.</summary>- private XDocument LoadXml(ZipArchiveEntry entry, bool preserveWhitespace)- {- try- {- return _package.LoadXml(entry, preserveWhitespace);- }- catch (XmlException ex)- {- throw new InvalidDataException($"The Word document cannot be read ({entry.FullName} is not valid XML). It may be encrypted or damaged. {ex.Message}", ex);- }+ using var zip = ZipFile.OpenRead(path);+ return new DocxReader(zip, mediaFolder).ReadDocument();}// ───────────────────────── Package ─────────────────────────@@ -107,10 +79,11 @@ internal sealed partial class DocxReaderif (_parts.TryGetValue(path, out var cached))return cached;Part? part = null;- if (_package.GetEntry(path) is { } entry)+ if (_zip.GetEntry(path) is { } entry){+ using var stream = entry.Open();// Whitespace matters: <w:t xml:space="preserve"> </w:t> is a real space.- part = new Part(path, LoadXml(entry, preserveWhitespace: true), RelationshipsOf(path));+ part = new Part(path, XDocument.Load(stream, LoadOptions.PreserveWhitespace), RelationshipsOf(path));}_parts[path] = part;return part;@@ -122,9 +95,10 @@ internal sealed partial class DocxReadervar folder = partPath.Contains('/') ? partPath[..partPath.LastIndexOf('/')] : "";var relsPath = partPath.Length == 0 ? "_rels/.rels" : $"{folder}/_rels/{partPath[(partPath.LastIndexOf('/') + 1)..]}.rels".TrimStart('/');var result = new Dictionary<string, Relationship>();- if (_package.GetEntry(relsPath) is not { } entry)+ if (_zip.GetEntry(relsPath) is not { } entry)return result;- foreach (var rel in LoadXml(entry, preserveWhitespace: false).Root?.Elements(PackageRelationships + "Relationship") ?? [])+ using var stream = entry.Open();+ foreach (var rel in XDocument.Load(stream).Root?.Elements(PackageRelationships + "Relationship") ?? []){var id = (string?)rel.Attribute("Id") ?? "";var target = (string?)rel.Attribute("Target") ?? "";@@ -227,10 +201,11 @@ internal sealed partial class DocxReaderprivate string? Title(){- var core = _package.GetEntry("docProps/core.xml");+ var core = _zip.GetEntry("docProps/core.xml");if (core is null)return null;- return NullIfEmpty(LoadXml(core, preserveWhitespace: false).Descendants(Dc + "title").FirstOrDefault()?.Value);+ using var stream = core.Open();+ return NullIfEmpty(XDocument.Load(stream).Descendants(Dc + "title").FirstOrDefault()?.Value);}private void AddSection(HDocument document, List<HBlock> blocks, XElement? sectPr,@@ -556,7 +531,6 @@ internal sealed partial class DocxReaderprivate void ReadParagraph(XElement p, List<HBlock> output){- _budget.Paragraph();var pPr = p.Element(W + "pPr");var (props, mark) = ParagraphProperties(pPr);var builder = new ParagraphBuilder(this, output, props, mark, pPr);@@ -604,7 +578,6 @@ internal sealed partial class DocxReader{var field = new FieldState();field.Instruction.Append(Attr(element, "instr"));- _budget.Fields(_fields.Count + 1);_fields.Add(field);StartFieldResult(field, builder, CharFormat(styleRun));ParagraphContent(element.Elements(), builder, styleRun);@@ -737,7 +710,6 @@ internal sealed partial class DocxReader/// </summary>private void Equations(XElement math, ParagraphBuilder builder, RunProps styleRun){- _budget.Object();var rPr = math.Descendants(M + "r").Select(r => r.Element(W + "rPr")).FirstOrDefault(p => p is not null);var format = CharFormat(RunProperties(rPr, styleRun)) with { Italic = true };var lines = math.Name.LocalName == "oMathPara" ? math.Elements(M + "oMath").ToList() : [math];@@ -769,25 +741,14 @@ internal sealed partial class DocxReaderprivate HNote? Note(XElement reference, Dictionary<string, XElement> notes, Part? part, bool endnote){- if (_inNote || part is null || !notes.TryGetValue(Attr(reference, "id") ?? "", out var element))+ if (part is null || !notes.TryGetValue(Attr(reference, "id") ?? "", out var element))return null;var note = new HNote(endnote);- using (_budget.Enter())+ WithPart(part, () =>{- _inNote = true;- try- {- WithPart(part, () =>- {- ReadBlocks(element.Elements(), note.Blocks);- return 0;- });- }- finally- {- _inNote = false;- }- }+ ReadBlocks(element.Elements(), note.Blocks);+ return 0;+ });// Word notes start with the reference mark and a space; 한글 writes its own number.if (note.Blocks.FirstOrDefault() is HParagraph first && first.Inlines.FirstOrDefault() is HText { Text: var text } leading){@@ -823,8 +784,6 @@ internal sealed partial class DocxReaderswitch (Attr(fldChar, "fldCharType")){case "begin":- // ShowsText looks at every open field for every run, so their number is limited.- _budget.Fields(_fields.Count + 1);_fields.Add(new FieldState());break;case "separate":diff --git a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Body.cs b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Body.csindex 674bda48..a74fc163 100644--- a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Body.cs+++ b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Body.cs@@ -29,7 +29,6 @@ internal sealed partial class HwpxReadervar blocks = new List<HBlock>();if (subList is null)return blocks;- using var level = _budget.Enter();// Fields, highlighting and tracked deletions do not reach into or out of a nested paragraph list.var (fields, markpen, deleted) = (_fields, _markpen, _deleted);(_fields, _markpen, _deleted) = ([], null, false);@@ -151,7 +150,6 @@ internal sealed partial class HwpxReaderprivate void ReadParagraph(XElement p, List<HBlock> output, SectionState? section){- _budget.Paragraph();var shape = ParaShapeOf(Attr(p, "paraPrIDRef"));var (heading, list) = HeadingAndList(shape, Attr(p, "styleIDRef"));var builder = new ParagraphBuilder(output, _fields, shape.Format, heading, list, _forLayout) { MarkFormat = CharFormat(null) };@@ -434,9 +432,7 @@ internal sealed partial class HwpxReaderbuilder.Add(new HBookmark(name));break;}- // Other fields (click-here, date, file name, ...) keep their result text, which follows until fieldEnd. Every- // paragraph reopens the links of the open fields, so their number is limited.- _budget.Fields(_fields.Count + 1);+ // Other fields (click-here, date, file name, ...) keep their result text, which follows until fieldEnd._fields.Add(new OpenField(Attr(control, "id"), target));if (target is not null)builder.OpenLink(target);@@ -494,12 +490,9 @@ internal sealed partial class HwpxReaderprivate HTable Table(XElement tbl){- _budget.Object();- // Column numbers and spans of damaged files stay within the limit, so they can't overflow.- var maxColumns = _budget.Limits.MaxTableColumns;var table = new HTable{- ColumnCount = Math.Clamp(Int(tbl, "colCnt"), 0, maxColumns),+ ColumnCount = Math.Max(0, Int(tbl, "colCnt")),PageBreak = Attr(tbl, "pageBreak") switch{"NONE" => HTablePageBreak.None,@@ -542,8 +535,8 @@ internal sealed partial class HwpxReadervar subList = Child(tc, "subList");var cell = new HCell{- Column = address is null ? -1 : Math.Clamp(Int(address, "colAddr"), 0, maxColumns - 1),- ColSpan = Math.Clamp(Int(span, "colSpan", 1), 1, maxColumns),+ Column = address is null ? -1 : Math.Max(0, Int(address, "colAddr")),+ ColSpan = Math.Max(1, Int(span, "colSpan", 1)),RowSpan = Math.Max(1, Int(span, "rowSpan", 1)),VerticalAlign = VerticalAlign(Attr(subList, "vertAlign")),};@@ -573,21 +566,13 @@ internal sealed partial class HwpxReader// Cells with their own margins (hasMargin) set the table's padding when they all agree.if (cellMargins.Count == 1 && cellMargins.Single() is { } shared)table.CellMargin = shared;- // A cell can't span rows below the table (writers walk the rows it covers).- for (var r = 0; r < table.Rows.Count; r++)- {- foreach (var cell in table.Rows[r].Cells)- cell.RowSpan = Math.Min(cell.RowSpan, table.Rows.Count - r);- }- table.ColumnCount = Math.Min(maxColumns, Math.Max(table.ColumnCount, widths.Select(w => w.Column + w.Span).DefaultIfEmpty(1).Max()));+ table.ColumnCount = Math.Max(table.ColumnCount, widths.Select(w => w.Column + w.Span).DefaultIfEmpty(1).Max());table.ColumnWidths = ColumnWidths(widths, table.ColumnCount);if (Child(Child(tbl, "caption"), "subList") is { } caption)table.Caption.AddRange(ReadSubList(caption));return table;}- private const long MaxCoveredColumns = 4_000_000;-/// <summary>Column widths from the cell widths: single cells first, then what spanning cells leave over.</summary>private static int[]? ColumnWidths(List<(int Column, int Span, int Width)> cells, int columns){@@ -599,10 +584,7 @@ internal sealed partial class HwpxReaderif (span == 1 && column < columns && width > 0)widths[column] ??= width;}- // Spanning cells are spread over the columns they cover; past a few million columns covered (a damaged or- // hostile table, real ones cover thousands) only the single cells count.- var covered = cells.Sum(c => c.Span > 1 ? (long)Math.Min(c.Span, columns) : 0);- for (var changed = covered <= MaxCoveredColumns; changed;)+ for (var changed = true; changed;){changed = false;foreach (var (column, span, width) in cells.Where(c => c.Span > 1 && c.Width > 0))@@ -611,9 +593,9 @@ internal sealed partial class HwpxReadervar unknown = range.Where(i => widths[i] is null).ToList();if (unknown.Count == 0)continue;- var rest = width - range.Sum(i => (long)(widths[i] ?? 0));+ var rest = width - range.Sum(i => widths[i] ?? 0);foreach (var i in unknown)- widths[i] = (int)Math.Clamp(rest / unknown.Count, 1, int.MaxValue);+ widths[i] = Math.Max(1, rest / unknown.Count);changed = true;}}diff --git a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Objects.cs b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Objects.csindex 23524320..2a611296 100644--- a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Objects.cs+++ b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.Objects.cs@@ -56,7 +56,6 @@ internal sealed partial class HwpxReader/// <summary>The model objects for one drawing object; groups give one object per member.</summary>private IEnumerable<HInline> Shapes(XElement element, Placement placement){- _budget.Object();switch (element.Name.LocalName){case "pic":@@ -243,7 +242,6 @@ internal sealed partial class HwpxReader/// </summary>private IEnumerable<HInline> Group(XElement container, Placement placement){- using var level = _budget.Enter();var anchor = placement.Anchor ?? new HAnchor("COLUMN", "LEFT", 0, "PARA", "TOP", 0, "IN_FRONT_OF_TEXT", true);foreach (var member in Elements(container)){diff --git a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.cs b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.csindex 3a7da3da..e88e25a1 100644--- a/src/Filee.Engines/Hwp/Hwpx/HwpxReader.cs+++ b/src/Filee.Engines/Hwp/Hwpx/HwpxReader.cs@@ -14,9 +14,9 @@// and master pages are read. Both fill the rendering detail of formats and objects (HwpxModel.Layout.cs).using System.Globalization;+using System.IO.Compression;using System.Xml;using System.Xml.Linq;-using Filee.Engines.Documents;namespace Filee.Engines.Hwp.Hwpx;@@ -34,13 +34,10 @@ internal sealed partial class HwpxReader/// </summary>internal const string EstimatedLinesMeta = "FileeLineSegments";- private readonly DocumentPackage? _package;+ private readonly ZipArchive? _zip;private readonly string _mediaFolder;private readonly bool _forLayout;- /// <summary>Nesting, paragraphs and objects read so far, against the package's limits.</summary>- private readonly DocumentBudget _budget;-/// <summary>Manifest item id → zip entry (master page parts are found through it).</summary>private Dictionary<string, string> _items = new(StringComparer.Ordinal);@@ -56,15 +53,14 @@ internal sealed partial class HwpxReader/// <summary>Elements the model cannot hold, by local name, with the number of times they were skipped.</summary>private readonly Dictionary<string, int> _skipped = new(StringComparer.Ordinal);- private HwpxReader(DocumentPackage? package, string mediaFolder, bool forLayout)+ private HwpxReader(ZipArchive? zip, string mediaFolder, bool forLayout){- _package = package;+ _zip = zip;_mediaFolder = mediaFolder;_forLayout = forLayout;- _budget = new DocumentBudget(package?.Limits ?? DocumentLimits.Default);}- private DocumentPackage Package => _package ?? throw new InvalidOperationException("This reader only has a header.");+ private ZipArchive Zip => _zip ?? throw new InvalidOperationException("This reader only has a header.");// ───────────────────────── Entry points ─────────────────────────@@ -73,18 +69,14 @@ internal sealed partial class HwpxReader/// <param name="skipped">Receives the elements that were skipped because the model has no equivalent (local name → count).</param>public static HDocument Read(string path, string mediaFolder, IDictionary<string, int>? skipped) =>- ReadPackage(path, mediaFolder, skipped, forLayout: false, DocumentLimits.Default);-- /// <summary>Reads within other <paramref name="limits"/> than <see cref="DocumentLimits.Default"/> (for tests).</summary>- internal static HDocument Read(string path, string mediaFolder, IDictionary<string, int>? skipped, DocumentLimits limits) =>- ReadPackage(path, mediaFolder, skipped, forLayout: false, limits);+ ReadPackage(path, mediaFolder, skipped, forLayout: false);/// <summary>/// Reads <paramref name="path"/> for the layout engine: like <see cref="Read(string, string, IDictionary{string, int}?)"/>,/// plus what only a renderer uses (runs apart by layout detail, polygons / curves / arcs, master pages)./// </summary>- public static HDocument ReadForLayout(string path, string mediaFolder, IDictionary<string, int>? skipped = null, DocumentLimits? limits = null) =>- ReadPackage(path, mediaFolder, skipped, forLayout: true, limits ?? DocumentLimits.Default);+ public static HDocument ReadForLayout(string path, string mediaFolder, IDictionary<string, int>? skipped = null) =>+ ReadPackage(path, mediaFolder, skipped, forLayout: true);/// <summary>A reader of header.xml alone, for its character and paragraph shapes (see <see cref="StyleResolver"/>).</summary>internal static HwpxReader ForHeader(XElement head)@@ -94,11 +86,21 @@ internal sealed partial class HwpxReaderreturn reader;}- private static HDocument ReadPackage(string path, string mediaFolder, IDictionary<string, int>? skipped, bool forLayout, DocumentLimits limits)+ private static HDocument ReadPackage(string path, string mediaFolder, IDictionary<string, int>? skipped, bool forLayout){- using (var package = DocumentPackage.Open(path, limits, () => NotAPackage(path)))+ ZipArchive zip;+ try+ {+ zip = ZipFile.OpenRead(path);+ }+ catch (InvalidDataException)+ {+ throw NotAPackage(path);+ }++ using (zip){- var reader = new HwpxReader(package, mediaFolder, forLayout);+ var reader = new HwpxReader(zip, mediaFolder, forLayout);var document = reader.ReadDocument();if (skipped is not null){@@ -198,7 +200,7 @@ internal sealed partial class HwpxReaderif (result.Count > 0)return result;- return Package.Entries+ return Zip.Entries.Where(e => e.FullName.StartsWith("Contents/", StringComparison.OrdinalIgnoreCase) && IsSection(e.FullName)).OrderBy(e => int.TryParse(Path.GetFileNameWithoutExtension(e.Name).AsSpan(7), NumberStyles.Integer, CultureInfo.InvariantCulture, out var n) ? n : int.MaxValue).Select(e => e.FullName)@@ -208,14 +210,14 @@ internal sealed partial class HwpxReaderprivate string? EntryPath(string href, string folder){var path = Uri.UnescapeDataString(href).Replace('\\', '/').TrimStart('/');- if (Package.GetEntry(path) is not null)+ if (Zip.GetEntry(path) is not null)return path;- return folder.Length > 0 && Package.GetEntry(folder + path) is not null ? folder + path : path;+ return folder.Length > 0 && Zip.GetEntry(folder + path) is not null ? folder + path : path;}private XDocument? LoadXml(string path, bool required){- var entry = Package.GetEntry(path);+ var entry = Zip.GetEntry(path);if (entry is null){return required@@ -224,8 +226,9 @@ internal sealed partial class HwpxReader}try{+ using var stream = entry.Open();// Whitespace matters: <hp:t> </hp:t> is a real space.- return Package.LoadXml(entry, preserveWhitespace: true);+ return XDocument.Load(stream, LoadOptions.PreserveWhitespace);}catch (XmlException ex){@@ -244,15 +247,16 @@ internal sealed partial class HwpxReader// Without a manifest entry, 한글's naming (BinData/<id>.<ext>) still finds the file.var entryPath = _binaryItems.GetValueOrDefault(itemId)- ?? Package.Entries.FirstOrDefault(e => e.FullName.StartsWith("BinData/", StringComparison.OrdinalIgnoreCase) &&+ ?? Zip.Entries.FirstOrDefault(e => e.FullName.StartsWith("BinData/", StringComparison.OrdinalIgnoreCase) &&string.Equals(Path.GetFileNameWithoutExtension(e.Name), itemId, StringComparison.OrdinalIgnoreCase))?.FullName;string? path = null;- if (entryPath is not null && Package.GetEntry(entryPath) is { } entry)+ if (entryPath is not null && Zip.GetEntry(entryPath) is { } entry){Directory.CreateDirectory(_mediaFolder);- path = Path.Combine(_mediaFolder, $"hwpx-media-{_media.Count + 1}{DocumentPackage.SafeExtension(entry.Name)}");- if (!Package.ExtractPicture(entry, path))- path = null; // larger than any picture should be: left out+ path = Path.Combine(_mediaFolder, $"hwpx-media-{_media.Count + 1}{Path.GetExtension(entry.Name).ToLowerInvariant()}");+ using var source = entry.Open();+ using var target = File.Create(path);+ source.CopyTo(target);}_media[itemId] = path;return path;diff --git a/src/Filee.Engines/Hwp/Hwpx/HwpxUnits.cs b/src/Filee.Engines/Hwp/Hwpx/HwpxUnits.csindex 5d62baa9..5d095302 100644--- a/src/Filee.Engines/Hwp/Hwpx/HwpxUnits.cs+++ b/src/Filee.Engines/Hwp/Hwpx/HwpxUnits.cs@@ -40,9 +40,6 @@ internal static class HwpxUnits"%" => number * 1.5, // % of a ~150 mm text width_ => number * 25.4 / 96, // px or unitless};- // Lengths beyond ±500 million (1.7 km) are cut there, so differences of two can't overflow.- return (int)Math.Clamp(Math.Round(mm * PerMm), -MaxLength, MaxLength);+ return (int)Math.Round(mm * PerMm);}-- private const int MaxLength = 500_000_000;}diff --git a/src/Filee.Engines/Hwp/Hwpx/StyleResolver.cs b/src/Filee.Engines/Hwp/Hwpx/StyleResolver.csindex 831492b0..7afdd824 100644--- a/src/Filee.Engines/Hwp/Hwpx/StyleResolver.cs+++ b/src/Filee.Engines/Hwp/Hwpx/StyleResolver.cs@@ -8,9 +8,8 @@// coloured) and the per-language slots the writer fills from Font / EastAsianFont / Spacing. Rendering detail the// source set (HParaLayout, HCharLayout) wins over the style's.-using System.Xml;+using System.IO.Compression;using System.Xml.Linq;-using Filee.Engines.Documents;namespace Filee.Engines.Hwp.Hwpx;@@ -42,18 +41,10 @@ internal sealed class StyleResolvervar stream = template ?? HwpxWriter.OpenBuiltInTemplate();try{- using var package = DocumentPackage.Open(stream);- var entry = package.GetEntry("Contents/header.xml") ?? throw new InvalidDataException("The template has no Contents/header.xml.");- XDocument header;- try- {- header = package.LoadXml(entry, preserveWhitespace: false);- }- catch (XmlException ex)- {- throw new InvalidDataException($"The template's header.xml is not valid XML ({ex.Message}).", ex);- }- return new StyleResolver(header.Root ?? throw new InvalidDataException("header.xml has no root element."));+ using var zip = new ZipArchive(stream, ZipArchiveMode.Read, leaveOpen: true);+ var entry = zip.GetEntry("Contents/header.xml") ?? throw new InvalidDataException("The template has no Contents/header.xml.");+ using var header = entry.Open();+ return new StyleResolver(XDocument.Load(header).Root ?? throw new InvalidDataException("header.xml has no root element."));}finally{diff --git a/src/Filee.Engines/Infrastructure/SafeXml.cs b/src/Filee.Engines/Infrastructure/SafeXml.csdeleted file mode 100644index f03b2622..00000000--- a/src/Filee.Engines/Infrastructure/SafeXml.cs+++ /dev/null@@ -1,130 +0,0 @@-// XML from files Filee did not write: no DTDs, no resolver (so nothing outside the file is ever read and no entity-// expands into gigabytes), and limits on depth, element count and size. The tree is built here from the reader rather-// than by XDocument.Load, which takes time quadratic in the depth (a 1.4 MB file nested 100,000 deep kept it busy for-// 48 seconds; the reader alone needs a quarter of a second) and so must never see such a file. Shared by the-// geospatial formats (KML, GPX) and the document readers (HWPX, DOCX, OFD).--using System.Globalization;-using System.Xml;-using System.Xml.Linq;--namespace Filee.Engines.Infrastructure;--/// <summary>What <see cref="SafeXml.Load(Stream, XmlLimits, Func{string, Exception}?)"/> accepts.</summary>-/// <param name="MaxDepth">Levels of elements (the root is level 1).</param>-/// <param name="MaxElements">Elements in the file.</param>-/// <param name="MaxCharacters">Characters in the file.</param>-/// <param name="PreserveWhitespace">Keep white space between elements (like <see cref="LoadOptions.PreserveWhitespace"/>).</param>-/// <param name="KeepNamespaceDeclarations">Keep xmlns attributes, so prefixes can be looked up as after XDocument.Load.</param>-/// <param name="CheckCharacters">Refuse characters XML 1.0 does not allow.</param>-/// <param name="ElementsBefore">Elements read before this file that count against <paramref name="MaxElements"/> (other parts of one package).</param>-internal readonly record struct XmlLimits(- int MaxDepth,- int MaxElements,- long MaxCharacters,- bool PreserveWhitespace = true,- bool KeepNamespaceDeclarations = true,- bool CheckCharacters = true,- int ElementsBefore = 0);--/// <summary>Parses untrusted XML into an <see cref="XDocument"/> within <see cref="XmlLimits"/>.</summary>-internal static class SafeXml-{- private const string XmlnsNamespace = "http://www.w3.org/2000/xmlns/";-- /// <summary>- /// The document in <paramref name="stream"/>. Comments and processing instructions are left out. Throws- /// <see cref="XmlException"/> for XML that is not well formed or has a DTD.- /// </summary>- /// <param name="limitExceeded">Makes the exception for a limit that was passed from a message saying which- /// (<see cref="InvalidDataException"/> when null).</param>- public static XDocument Load(Stream stream, XmlLimits limits, Func<string, Exception>? limitExceeded = null) =>- Load(stream, limits, limitExceeded, out _);-- /// <param name="elements">The number of elements read.</param>- public static XDocument Load(Stream stream, XmlLimits limits, Func<string, Exception>? limitExceeded, out int elements)- {- limitExceeded ??= message => new InvalidDataException(message);- var settings = new XmlReaderSettings- {- DtdProcessing = DtdProcessing.Prohibit,- XmlResolver = null,- MaxCharactersFromEntities = 0,- MaxCharactersInDocument = limits.MaxCharacters,- CheckCharacters = limits.CheckCharacters,- IgnoreWhitespace = !limits.PreserveWhitespace,- IgnoreComments = true,- IgnoreProcessingInstructions = true,- };- using var reader = XmlReader.Create(stream, settings);- var document = new XDocument();- XContainer current = document;- var depth = 0;- elements = 0;- try- {- while (reader.Read())- {- switch (reader.NodeType)- {- case XmlNodeType.Element:- if (++depth > limits.MaxDepth)- throw limitExceeded($"The file nests elements more than {limits.MaxDepth} levels deep.");- if (++elements > limits.MaxElements - limits.ElementsBefore)- {- throw limitExceeded((limits.ElementsBefore > 0 ? "The package has more than " : "The file has more than ")- + limits.MaxElements.ToString("N0", CultureInfo.InvariantCulture) + " elements.");- }- var element = new XElement(XName.Get(reader.LocalName, reader.NamespaceURI));- var empty = reader.IsEmptyElement;- if (reader.HasAttributes)- {- while (reader.MoveToNextAttribute())- {- if (reader.NamespaceURI == XmlnsNamespace)- {- if (limits.KeepNamespaceDeclarations)- element.Add(new XAttribute(reader.Prefix.Length == 0 ? XName.Get("xmlns") : XNamespace.Xmlns + reader.LocalName, reader.Value));- }- else- {- element.SetAttributeValue(XName.Get(reader.LocalName, reader.NamespaceURI), reader.Value);- }- }- reader.MoveToElement();- }- current.Add(element);- if (empty)- depth--;- else- current = element;- break;- case XmlNodeType.EndElement:- current = current.Parent ?? (XContainer)document;- depth--;- break;- case XmlNodeType.CDATA:- if (current is XElement)- current.Add(new XCData(reader.Value));- break;- case XmlNodeType.Text or XmlNodeType.SignificantWhitespace or XmlNodeType.Whitespace:- // Text outside the root element (white space between declarations) is no content. Text next- // to text becomes one node, as XDocument.Load makes it.- if (current is XElement parent)- {- if (parent.LastNode is XText last and not XCData)- last.Value += reader.Value;- else- parent.Add(new XText(reader.Value));- }- break;- }- }- }- catch (XmlException ex) when (ex.Message.Contains("MaxCharactersInDocument", StringComparison.Ordinal))- {- throw limitExceeded("The file has more than " + limits.MaxCharacters.ToString("N0", CultureInfo.InvariantCulture) + " characters.");- }- return document;- }-}diff --git a/src/Filee.Engines/Ofd/OfdPackage.cs b/src/Filee.Engines/Ofd/OfdPackage.csindex 2959f129..2e74863b 100644--- a/src/Filee.Engines/Ofd/OfdPackage.cs+++ b/src/Filee.Engines/Ofd/OfdPackage.cs@@ -1,40 +1,69 @@// The ZIP container of an OFD file, read defensively: parts are looked up by name inside the package and never// written out under their own names, references ("../Res/a.png", "/Doc_0/Document.xml") are resolved against the-// package root and cannot leave it, and the package is read within DocumentLimits (Documents/DocumentPackage): XML-// without DTDs and with a depth limit, every part with a size limit that is also checked while decompressing, so a-// lying header does not help a zip bomb.+// package root and cannot leave it, XML is read without DTDs, and every part is read with a size limit (also checked+// while decompressing, so a lying header does not help a zip bomb).using System.IO.Compression;using System.Xml;using System.Xml.Linq;-using Filee.Engines.Documents;namespace Filee.Engines.Ofd;/// <summary>An OFD package opened for reading.</summary>internal sealed class OfdPackage : IDisposable{+ /// <summary>More parts than this are refused (real OFD files have a few per page).</summary>+ private const int MaxEntries = 100_000;++ /// <summary>Largest XML part read (a page, a resource list).</summary>+ private const long MaxXmlBytes = 64L * 1024 * 1024;+/// <summary>Largest picture taken; bigger ones are left out.</summary>public const long MaxPictureBytes = 32L * 1024 * 1024;- private readonly DocumentPackage _package;+ /// <summary>Everything read from one package together.</summary>+ private const long MaxTotalBytes = 1024L * 1024 * 1024;++ private static readonly XmlReaderSettings XmlSettings = new()+ {+ DtdProcessing = DtdProcessing.Prohibit,+ XmlResolver = null,+ IgnoreComments = true,+ IgnoreProcessingInstructions = true,+ MaxCharactersInDocument = MaxXmlBytes,+ };++ private readonly ZipArchive _zip;private readonly Dictionary<string, ZipArchiveEntry> _entries = new(StringComparer.OrdinalIgnoreCase);+ private readonly long _maxTotal;+ private long _read;- public OfdPackage(string path) : this(limits => DocumentPackage.Open(path, limits, NotAPackage), DocumentLimits.Default)+ public OfdPackage(string path) : this(() => ZipFile.OpenRead(path), MaxTotalBytes){}/// <summary>A package held in memory (the seal picture inside a signature), with its own limit on what it unpacks to.</summary>- public OfdPackage(byte[] bytes, long maxTotal) : this(- limits => DocumentPackage.Open(new MemoryStream(bytes, writable: false), limits, NotAPackage),- DocumentLimits.Default with { MaxPackageBytes = Math.Min(maxTotal, DocumentLimits.Default.MaxPackageBytes) })+ public OfdPackage(byte[] bytes, long maxTotal) : this(() => new ZipArchive(new MemoryStream(bytes, writable: false), ZipArchiveMode.Read), maxTotal){}- private OfdPackage(Func<DocumentLimits, DocumentPackage> open, DocumentLimits limits)+ private OfdPackage(Func<ZipArchive> open, long maxTotal){- _package = open(limits);- foreach (var entry in _package.Entries)+ _maxTotal = Math.Min(maxTotal, MaxTotalBytes);+ try+ {+ _zip = open();+ }+ catch (InvalidDataException ex)+ {+ throw new InvalidDataException("The file is not an OFD document (it is not a ZIP package). It may be damaged.", ex);+ }+ if (_zip.Entries.Count > MaxEntries)+ {+ _zip.Dispose();+ throw new InvalidDataException($"The OFD package has more than {MaxEntries:N0} parts; Filee does not read it.");+ }+ foreach (var entry in _zip.Entries){// Names that climb out of the package ("../x") are unreachable; of two parts with one name the first wins.if (!entry.FullName.EndsWith('/') && Resolve("", entry.FullName) is { } name)@@ -42,13 +71,7 @@ internal sealed class OfdPackage : IDisposable}}- private static InvalidDataException NotAPackage() =>- new("The file is not an OFD document (it is not a ZIP package). It may be damaged.");-- public void Dispose() => _package.Dispose();-- /// <summary>The limits the package is read with.</summary>- public DocumentLimits Limits => _package.Limits;+ public void Dispose() => _zip.Dispose();/// <summary>True when the package has a part of that (resolved) name.</summary>public bool Has(string? name) => name is not null && _entries.ContainsKey(name);@@ -97,11 +120,14 @@ internal sealed class OfdPackage : IDisposable/// <summary>An XML part, or null when the package has no such part. Throws for parts that are not XML.</summary>public XDocument? LoadXml(string? name){- if (name is null || !_entries.TryGetValue(name, out var entry))+ if (name is null || !_entries.ContainsKey(name))return null;+ var bytes = Read(name, MaxXmlBytes)+ ?? throw new InvalidDataException($"The OFD part {name} is larger than {MaxXmlBytes / (1024 * 1024)} MB; Filee does not read it.");try{- return _package.LoadXml(entry, preserveWhitespace: true);+ using var reader = XmlReader.Create(new MemoryStream(bytes), XmlSettings);+ return XDocument.Load(reader);}catch (XmlException ex){@@ -110,6 +136,23 @@ internal sealed class OfdPackage : IDisposable}/// <summary>The bytes of a part; null when it is missing or larger than <paramref name="max"/>.</summary>- public byte[]? Read(string name, long max) =>- _entries.TryGetValue(name, out var entry) ? _package.ReadBytes(entry, max) : null;+ public byte[]? Read(string name, long max)+ {+ if (!_entries.TryGetValue(name, out var entry) || entry.Length > max)+ return null;+ using var stream = entry.Open();+ using var copy = new MemoryStream((int)Math.Min(entry.Length, 1024 * 1024));+ var buffer = new byte[81920];+ int count;+ while ((count = stream.Read(buffer)) > 0)+ {+ if (copy.Length + count > max)+ return null;+ _read += count;+ if (_read > _maxTotal)+ throw new InvalidDataException($"The OFD package unpacks to more than {_maxTotal / (1024 * 1024)} MB; Filee does not read it.");+ copy.Write(buffer, 0, count);+ }+ return copy.ToArray();+ }}diff --git a/src/Filee.Engines/Ofd/OfdReader.cs b/src/Filee.Engines/Ofd/OfdReader.csindex 274843c3..56ec9395 100644--- a/src/Filee.Engines/Ofd/OfdReader.cs+++ b/src/Filee.Engines/Ofd/OfdReader.cs@@ -21,7 +21,6 @@using System.Globalization;using System.Xml.Linq;-using Filee.Engines.Documents;using Filee.Engines.Hwp.Hwpx;using ImageMagick;@@ -611,9 +610,6 @@ internal sealed partial class OfdReadervar name = Path.Combine(_mediaFolder, $"ofd-{Guid.NewGuid():N}");if (kind is "png" or "jpg" or "gif" or "bmp"){- // Copied as they are; one that claims more pixels than any picture should have is left out.- if (PictureSize.Read(new MemoryStream(bytes, writable: false)) is { } size && (long)size.Width * size.Height > _package.Limits.MaxPicturePixels)- return null;File.WriteAllBytes($"{name}.{kind}", bytes);return $"{name}.{kind}";}diff --git a/tests/Filee.Engines.Tests/DocumentFuzzTests.cs b/tests/Filee.Engines.Tests/DocumentFuzzTests.csdeleted file mode 100644index bef2303d..00000000--- a/tests/Filee.Engines.Tests/DocumentFuzzTests.cs+++ /dev/null@@ -1,233 +0,0 @@-// Mutation fuzzing of the document readers (HWPX for conversion and for layout, DOCX): seeds are written in code,-// DocumentFuzzer changes them, and every input must be read or refused with InvalidDataException /-// ConversionRefusedException, in time. In a normal test run each reader gets a short, fixed run (the same inputs every-// time); the nightly fuzz workflow sets FILEE_FUZZ_SECONDS for a longer run with a new random seed, and-// FILEE_FUZZ_OUT for a folder that keeps the inputs that failed. FILEE_FUZZ_SEED repeats a run.--using System.Globalization;-using Filee.Engines.Hwp.Hwpx;-using Filee.Engines.Hwp.Hwpx.Docx;-using static Filee.Engines.Tests.DocxBuilder;--namespace Filee.Engines.Tests;--[Trait("Category", "Fuzz")]-public class DocumentFuzzTests(EngineFixture fx) : IClassFixture<EngineFixture>-{- /// <summary>Inputs per reader in a normal test run.</summary>- private const int QuickIterations = 50;-- private static readonly TimeSpan ReadTimeout = TimeSpan.FromSeconds(30);-- [Fact]- public void HwpxReader_reads_or_refuses_every_mutated_package() =>- Fuzz("hwpx", "hwpx", HwpxSeeds(), (path, media) => HwpxReader.Read(path, media));-- [Fact]- public void HwpxReader_for_layout_reads_or_refuses_every_mutated_package() =>- Fuzz("hwpx-layout", "hwpx", HwpxSeeds(), (path, media) => HwpxReader.ReadForLayout(path, media));-- [Fact]- public void DocxReader_reads_or_refuses_every_mutated_package() =>- Fuzz("docx", "docx", DocxSeeds(), (path, media) => DocxReader.Read(path, media));-- // ───────────────────────── Seeds ─────────────────────────-- private List<byte[]> HwpxSeeds()- {- var folder = fx.NewFolder();- var hangul = HwpxReaderTests.HangulStylePackage(folder);- // DOCX read and written as HWPX: what Filee's own writer makes.- var written = Path.Combine(folder, "written.hwpx");- HwpxWriter.Write(DocxReader.Read(RichDocx(folder), Path.Combine(folder, "media-docx")), written);- return [File.ReadAllBytes(hangul), File.ReadAllBytes(written)];- }-- private List<byte[]> DocxSeeds()- {- var folder = fx.NewFolder();- var rich = RichDocx(folder);- // The 한글-style package written as DOCX: what Filee's own writer makes.- var written = Path.Combine(folder, "written.docx");- DocxWriter.Write(HwpxReader.Read(HwpxReaderTests.HangulStylePackage(folder), Path.Combine(folder, "media-hwpx")), written);- return [File.ReadAllBytes(rich), File.ReadAllBytes(written)];- }-- /// <summary>- /// A DOCX with most of what the reader handles: styles based on styles, a numbered list, a nested table with- /// merged cells, inline and floating pictures, a text box with a VML fallback, a group, fields, a hyperlink,- /// notes, a header and footer, math, a content control, a VML picture and a symbol.- /// </summary>- internal static string RichDocx(string folder)- {- var builder = new DocxBuilder- {- Numbering = """- <w:abstractNum w:abstractNumId="0"><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/><w:pPr><w:ind w:left="720" w:hanging="360"/></w:pPr></w:lvl>- <w:lvl w:ilvl="1"><w:start w:val="1"/><w:numFmt w:val="bullet"/><w:lvlText w:val=""/><w:rPr><w:rFonts w:ascii="Symbol"/></w:rPr></w:lvl></w:abstractNum>- <w:num w:numId="1"><w:abstractNumId w:val="0"/></w:num>- """,- Settings = "<w:evenAndOddHeaders/><w:noLineBreaksBefore w:lang=\"ko-KR\" w:val=\"!%),.:;?]}\"/>",- };- builder.Styles += """- <w:style w:type="paragraph" w:styleId="Quote"><w:name w:val="Quote"/><w:basedOn w:val="Heading1"/><w:pPr><w:ind w:left="400"/><w:jc w:val="center"/></w:pPr><w:rPr><w:i/></w:rPr></w:style>- <w:style w:type="paragraph" w:styleId="Loop"><w:name w:val="Loop"/><w:basedOn w:val="Loop2"/></w:style>- <w:style w:type="paragraph" w:styleId="Loop2"><w:name w:val="Loop2"/><w:basedOn w:val="Loop"/></w:style>- """;- var png = builder.Image(TinyPng(4, 3));- var link = builder.Hyperlink("https://example.invalid/page");- var header = builder.Header(P(R("머리말 ") + Field("PAGE", "1")));- var footer = builder.Footer(P(R("꼬리말 ") + Field("NUMPAGES", "3")));- builder.Footnotes("<w:footnote w:id=\"1\"><w:p><w:r><w:footnoteRef/></w:r>" + R(" 각주 본문") + "</w:p></w:footnote>");- builder.Endnotes("<w:endnote w:id=\"1\"><w:p><w:r><w:endnoteRef/></w:r>" + R(" 미주 본문") + "</w:p></w:endnote>");- builder.SectionProperties = $"<w:headerReference w:type=\"default\" r:id=\"{header}\"/><w:footerReference w:type=\"default\" r:id=\"{footer}\"/>" +- DefaultPage + "<w:cols w:num=\"2\" w:space=\"720\"/><w:docGrid w:type=\"lines\" w:linePitch=\"360\"/><w:titlePg/>";-- const string Cell = "<w:tc><w:tcPr><w:tcW w:w=\"2000\" w:type=\"dxa\"/></w:tcPr>{0}</w:tc>";- var inner = "<w:tbl><w:tblPr><w:tblStyle w:val=\"TableGrid\"/></w:tblPr><w:tblGrid><w:gridCol w:w=\"1000\"/></w:tblGrid><w:tr>" +- string.Format(CultureInfo.InvariantCulture, Cell, P(R("안쪽 표"))) + "</w:tr></w:tbl>";- var table = "<w:tbl><w:tblPr><w:tblStyle w:val=\"TableGrid\"/><w:tblLook w:firstRow=\"1\"/></w:tblPr><w:tblGrid><w:gridCol w:w=\"2000\"/><w:gridCol w:w=\"2000\"/><w:gridCol w:w=\"2000\"/></w:tblGrid>" +- "<w:tr><w:trPr><w:tblHeader/><w:trHeight w:val=\"400\"/></w:trPr>" +- "<w:tc><w:tcPr><w:gridSpan w:val=\"2\"/><w:shd w:val=\"clear\" w:fill=\"FFFF00\"/></w:tcPr>" + P(R("병합")) + "</w:tc>" +- "<w:tc><w:tcPr><w:vMerge w:val=\"restart\"/><w:vAlign w:val=\"center\"/></w:tcPr>" + P(R("세로")) + "</w:tc></w:tr>" +- "<w:tr><w:trPr><w:cantSplit/></w:trPr>" + string.Format(CultureInfo.InvariantCulture, Cell, inner + P("")) +- string.Format(CultureInfo.InvariantCulture, Cell, P(R("칸"))) + "<w:tc><w:tcPr><w:vMerge/></w:tcPr>" + P("") + "</w:tc></w:tr></w:tbl>";- var textBox = "<w:r><mc:AlternateContent><mc:Choice Requires=\"wps\"><w:drawing><wp:anchor distT=\"0\" distB=\"0\" distL=\"0\" distR=\"0\" simplePos=\"0\" relativeHeight=\"3\" behindDoc=\"0\" locked=\"0\" layoutInCell=\"1\" allowOverlap=\"1\">" +- "<wp:simplePos x=\"0\" y=\"0\"/><wp:positionH relativeFrom=\"column\"><wp:posOffset>100</wp:posOffset></wp:positionH><wp:positionV relativeFrom=\"paragraph\"><wp:align>top</wp:align></wp:positionV>" +- "<wp:extent cx=\"914400\" cy=\"457200\"/><wp:wrapSquare wrapText=\"bothSides\"/><wp:docPr id=\"3\" name=\"tb\"/><a:graphic><a:graphicData uri=\"" + ShapeUri + "\">" +- "<wps:wsp><wps:spPr><a:xfrm rot=\"5400000\"><a:off x=\"0\" y=\"0\"/><a:ext cx=\"914400\" cy=\"457200\"/></a:xfrm><a:prstGeom prst=\"roundRect\"/><a:solidFill><a:srgbClr val=\"DDEEFF\"/></a:solidFill><a:ln w=\"12700\"><a:solidFill><a:schemeClr val=\"accent1\"/></a:solidFill></a:ln></wps:spPr>" +- "<wps:txbx><w:txbxContent>" + P(R("글상자")) + "</w:txbxContent></wps:txbx><wps:bodyPr lIns=\"0\" tIns=\"45720\" anchor=\"ctr\"/></wps:wsp></a:graphicData></a:graphic></wp:anchor></w:drawing></mc:Choice>" +- "<mc:Fallback><w:pict><v:rect style=\"position:absolute;width:72pt;height:36pt;z-index:2\" fillcolor=\"#ddeeff\" strokecolor=\"red\" strokeweight=\"1pt\"><v:textbox><w:txbxContent>" + P(R("VML 글상자")) + "</w:txbxContent></v:textbox></v:rect></w:pict></mc:Fallback></mc:AlternateContent></w:r>";- var group = Anchor("http://schemas.microsoft.com/office/word/2010/wordprocessingGroup",- "<wpg:wgp><wpg:cNvGrpSpPr/><wpg:grpSpPr><a:xfrm><a:off x=\"0\" y=\"0\"/><a:ext cx=\"1828800\" cy=\"914400\"/><a:chOff x=\"0\" y=\"0\"/><a:chExt cx=\"1828800\" cy=\"914400\"/></a:xfrm></wpg:grpSpPr>" +- Picture(png, 914400, 914400).Replace("<pic:pic>", "<pic:pic xmlns:pic=\"http://schemas.openxmlformats.org/drawingml/2006/picture\">", StringComparison.Ordinal) +- "<wps:wsp><wps:spPr><a:xfrm><a:off x=\"914400\" y=\"0\"/><a:ext cx=\"914400\" cy=\"914400\"/></a:xfrm><a:prstGeom prst=\"ellipse\"/></wps:spPr><wps:bodyPr/></wps:wsp>" +- "<wpg:grpSp><wpg:grpSpPr><a:xfrm><a:off x=\"0\" y=\"457200\"/><a:ext cx=\"914400\" cy=\"457200\"/><a:chOff x=\"0\" y=\"0\"/><a:chExt cx=\"914400\" cy=\"457200\"/></a:xfrm></wpg:grpSpPr>" +- "<wps:wsp><wps:spPr><a:xfrm><a:off x=\"0\" y=\"0\"/><a:ext cx=\"457200\" cy=\"457200\"/></a:xfrm><a:prstGeom prst=\"rect\"/></wps:spPr><wps:txbx><w:txbxContent>" + P(R("묶음 안")) + "</w:txbxContent></wps:txbx><wps:bodyPr/></wps:wsp></wpg:grpSp></wpg:wgp>",- 1828800, 914400, "<wp:positionH relativeFrom=\"page\"><wp:align>center</wp:align></wp:positionH>", "<wp:positionV relativeFrom=\"page\"><wp:posOffset>914400</wp:posOffset></wp:positionV>");-- builder.Paragraph(P(R("제목") + "<w:bookmarkStart w:id=\"0\" w:name=\"top\"/><w:bookmarkEnd w:id=\"0\"/>", "<w:pStyle w:val=\"Heading1\"/>"))- .Paragraph(P(R("인용", "<w:b/><w:color w:val=\"FF0000\"/><w:highlight w:val=\"yellow\"/>"), "<w:pStyle w:val=\"Quote\"/><w:spacing w:before=\"120\" w:after=\"240\" w:line=\"360\" w:lineRule=\"auto\"/>"))- .Paragraph(P(R("고리"), "<w:pStyle w:val=\"Loop\"/>"))- .Paragraph(P(R("첫째"), "<w:numPr><w:ilvl w:val=\"0\"/><w:numId w:val=\"1\"/></w:numPr>"))- .Paragraph(P(R("둘째"), "<w:numPr><w:ilvl w:val=\"1\"/><w:numId w:val=\"1\"/></w:numPr>"))- .Paragraph(table)- .Paragraph(P(InlinePicture(png, 381000, 285750) + textBox + group))- .Paragraph(P($"<w:hyperlink r:id=\"{link}\">{R("링크", "<w:rStyle w:val=\"Hyperlink\"/>")}</w:hyperlink>" +- "<w:hyperlink w:anchor=\"top\">" + R("책갈피") + "</w:hyperlink>" +- Field("HYPERLINK \"https://example.invalid/field\" \\o \"tip\"", "필드 링크") +- "<w:fldSimple w:instr=\" PAGE \">" + R("1") + "</w:fldSimple>" +- "<w:r><w:footnoteReference w:id=\"1\"/></w:r><w:r><w:endnoteReference w:id=\"1\"/></w:r>" +- "<w:r><w:sym w:font=\"Wingdings\" w:char=\"F0FC\"/><w:tab/><w:br/><w:t>끝</w:t><w:br w:type=\"column\"/></w:r>"))- .Paragraph(P("<m:oMath><m:f><m:num><m:r><m:t>x</m:t></m:r></m:num><m:den><m:sSup><m:e><m:r><m:t>y</m:t></m:r></m:e><m:sup><m:r><m:t>2</m:t></m:r></m:sup></m:sSup></m:den></m:f><m:rad><m:radPr><m:degHide m:val=\"1\"/></m:radPr><m:deg/><m:e><m:r><m:t>z</m:t></m:r></m:e></m:rad></m:oMath>"))- .Paragraph("<w:sdt><w:sdtPr/><w:sdtContent>" + P(R("내용 컨트롤")) + "</w:sdtContent></w:sdt>")- .Paragraph(P($"<w:r><w:pict><v:shape style=\"width:30pt;height:20pt\"><v:imagedata r:id=\"{png}\"/></v:shape><v:line from=\"0,0\" to=\"10pt,20pt\" strokecolor=\"#0000ff\"/></w:pict></w:r>" +- "<w:r><w:br w:type=\"page\"/></w:r>" + R("다음 쪽", "<w:rFonts w:ascii=\"Arial\" w:eastAsia=\"바탕\"/><w:sz w:val=\"28\"/><w:spacing w:val=\"20\"/><w:w w:val=\"90\"/><w:vertAlign w:val=\"superscript\"/>")))- .Paragraph("<w:p><w:pPr><w:sectPr>" + DefaultPage + "<w:type w:val=\"continuous\"/></w:sectPr></w:pPr></w:p>");- return builder.Save(Path.Combine(folder, "rich.docx"));- }-- /// <summary>A valid PNG of <paramref name="width"/> × <paramref name="height"/> grey pixels.</summary>- internal static byte[] TinyPng(int width, int height)- {- using var output = new MemoryStream();- output.Write([0x89, 0x50, 0x4E, 0x47, 0x0D, 0x0A, 0x1A, 0x0A]);- void Chunk(string type, byte[] data)- {- var length = new byte[4];- System.Buffers.Binary.BinaryPrimitives.WriteInt32BigEndian(length, data.Length);- output.Write(length);- var body = System.Text.Encoding.ASCII.GetBytes(type).Concat(data).ToArray();- output.Write(body);- var crc = new byte[4];- System.Buffers.Binary.BinaryPrimitives.WriteUInt32BigEndian(crc, Filee.Engines.Archives.Crc32.Compute(body));- output.Write(crc);- }- var header = new byte[13];- System.Buffers.Binary.BinaryPrimitives.WriteInt32BigEndian(header, width);- System.Buffers.Binary.BinaryPrimitives.WriteInt32BigEndian(header.AsSpan(4), height);- header[8] = 8; // bit depth- header[9] = 0; // greyscale- Chunk("IHDR", header);- using (var pixels = new MemoryStream())- {- using (var zlib = new System.IO.Compression.ZLibStream(pixels, System.IO.Compression.CompressionLevel.Optimal, leaveOpen: true))- {- for (var y = 0; y < height; y++)- {- zlib.WriteByte(0); // no filter- for (var x = 0; x < width; x++)- zlib.WriteByte(0x80);- }- }- Chunk("IDAT", pixels.ToArray());- }- Chunk("IEND", []);- return output.ToArray();- }-- // ───────────────────────── Running ─────────────────────────-- /// <param name="name">Names the kept inputs.</param>- private void Fuzz(string name, string extension, List<byte[]> seeds, Action<string, string> read)- {- var seconds = int.TryParse(Environment.GetEnvironmentVariable("FILEE_FUZZ_SECONDS"), out var s) && s > 0 ? s : 0;- var seed = int.TryParse(Environment.GetEnvironmentVariable("FILEE_FUZZ_SEED"), out var fixedSeed) ? fixedSeed- : seconds > 0 ? Environment.TickCount : 20261028;- var outFolder = Environment.GetEnvironmentVariable("FILEE_FUZZ_OUT") is { Length: > 0 } o ? o : null;- var keep = outFolder ?? fx.NewFolder();- var output = TestContext.Current.TestOutputHelper;- output?.WriteLine($"Seed {seed}, {(seconds > 0 ? seconds + " s" : QuickIterations + " inputs per seed package")}");-- var random = new Random(seed);- var fuzzers = seeds.Select(bytes => new DocumentFuzzer(bytes, random)).ToList();- var folder = fx.NewFolder();- // With an output folder the input being read lives there: a crash that ends the process (a stack overflow)- // leaves it behind for the report. A run that ends normally removes it.- var input = Path.Combine(outFolder ?? folder, $"running-{name}.{extension}");- var media = Path.Combine(folder, "media");-- // Every seed itself reads without trouble.- foreach (var bytes in seeds)- {- File.WriteAllBytes(input, bytes);- Assert.Equal(DocumentFuzzer.Outcome.Read, DocumentFuzzer.Run(() => read(input, media), ReadTimeout));- }-- var failures = new Dictionary<string, string>();- var (inputs, refused) = (0, 0);- var stopwatch = System.Diagnostics.Stopwatch.StartNew();- while (seconds > 0 ? stopwatch.Elapsed < TimeSpan.FromSeconds(seconds) : inputs < QuickIterations * seeds.Count)- {- var fuzzer = fuzzers[inputs % fuzzers.Count];- var bytes = fuzzer.Next();- inputs++;- File.WriteAllBytes(input, bytes);- if (Directory.Exists(media))- Directory.Delete(media, recursive: true);- try- {- if (DocumentFuzzer.Run(() => read(input, media), ReadTimeout) == DocumentFuzzer.Outcome.Refused)- refused++;- }- catch (DocumentFuzzer.FuzzFailure failure)- {- // One input per kind of failure (exception type and the frame it came from).- var frame = failure.InnerException?.StackTrace?.Split('\n').FirstOrDefault()?.Trim() ?? "";- var kind = $"{failure.InnerException?.GetType().Name ?? "Timeout"} {frame}";- if (!failures.ContainsKey(kind))- {- var kept = Path.Combine(keep, $"{name}-{seed}-{inputs}.{extension}");- File.WriteAllBytes(kept, bytes);- failures[kind] = $"{failure.Message} (input {kept})\n{failure.InnerException}";- }- if (failure.InnerException is null)- break; // a read that hangs keeps running; don't pile them up- }- }- output?.WriteLine($"{inputs} inputs, {refused} refused, {inputs - refused - failures.Count} read, {failures.Count} kinds of failure");- if (failures.Count == 0 || failures.Keys.All(k => !k.StartsWith("Timeout", StringComparison.Ordinal)))- File.Delete(input); // a read that still runs holds it open- Assert.True(failures.Count == 0, $"Seed {seed}: " + string.Join("\n\n", failures.Values));- }-}diff --git a/tests/Filee.Engines.Tests/DocumentFuzzer.cs b/tests/Filee.Engines.Tests/DocumentFuzzer.csdeleted file mode 100644index 727ad59a..00000000--- a/tests/Filee.Engines.Tests/DocumentFuzzer.cs+++ /dev/null@@ -1,375 +0,0 @@-// A mutation fuzzer for document packages (HWPX, DOCX): it takes a valid package written in code, changes it a little-// at random and hands it to a reader. Most changes edit the XML tree, so the file stays well-formed and reaches the-// reader's logic (attributes set to extreme or foreign values, elements removed, repeated, renamed or moved inside one-// another); some edit the text or the bytes, so the XML and ZIP error paths are covered too. A reader may refuse a-// file only with InvalidDataException or ConversionRefusedException; anything else, or a read that takes too long, is-// a failure, and the input that caused it is kept for the report.--using System.IO.Compression;-using System.Text;-using System.Xml;-using System.Xml.Linq;-using Filee.Core.Conversion;--namespace Filee.Engines.Tests;--internal sealed class DocumentFuzzer-{- /// <summary>Attribute values that have broken readers before: bounds of every integer type, non-numbers, paths.</summary>- private static readonly string[] Interesting =- [- "", "0", "1", "-1", "2", "255", "65535", "65536", "-32768", "2147483647", "-2147483648", "2147483648", "4294967295",- "4294967296", "9223372036854775807", "-9223372036854775808", "18446744073709551615", "99999999999999999999999",- "1e308", "-1e308", "1e-308", "NaN", "Infinity", "-Infinity", "0.5", "-0.0", "1.#INF", "0x7FFFFFFF", "#", "#FFF",- "#GGGGGG", "#AARRGGBB", "#FF00FF00", "none", "auto", "true", "false", "x", " ", "\t", "%", "50%", "1in", "-5cm",- "12pt", "999999999in", "../../../../../etc/passwd", "/word/document.xml", "Contents/header.xml", "BinData/image1.png",- "C:\\Windows\\win.ini", "\\\\server\\share\\x", "file:///c:/x", "http://example.invalid/a", "rId1", "rId10", "0,0",- "1,2,3", "-1,-1", ",,,", "a:b", "image.png:stream", "con", "nul.png", new string('9', 400), new string('a', 5000),- ];-- /// <summary>Numbers at the edges of what readers parse and compute with.</summary>- private static readonly string[] Numbers =- [- "0", "-1", "1", "2", "-2147483648", "2147483647", "2147483648", "4294967295", "4294967296", "-4294967296",- "9223372036854775807", "-9223372036854775808", "1e308", "-1e308", "1e30", "-1e30", "100000000", "-100000000",- "65536", "1073741824", "-1073741824", "0.0001", "NaN", "Infinity",- ];-- private readonly Random _random;- private readonly List<(string Name, byte[] Bytes)> _seed;- private readonly List<string> _xmlParts;-- public DocumentFuzzer(byte[] seedPackage, Random random)- {- _random = random;- _seed = [];- using (var zip = new ZipArchive(new MemoryStream(seedPackage), ZipArchiveMode.Read))- {- foreach (var entry in zip.Entries)- {- using var stream = entry.Open();- using var copy = new MemoryStream();- stream.CopyTo(copy);- _seed.Add((entry.FullName, copy.ToArray()));- }- }- _xmlParts = _seed.Where(p => IsXml(p.Name)).Select(p => p.Name).ToList();- }-- private static bool IsXml(string name) =>- name.EndsWith(".xml", StringComparison.OrdinalIgnoreCase) || name.EndsWith(".rels", StringComparison.OrdinalIgnoreCase)- || name.EndsWith(".hpf", StringComparison.OrdinalIgnoreCase);-- /// <summary>A mutated copy of the seed package.</summary>- public byte[] Next()- {- var parts = _seed.Select(p => (p.Name, p.Bytes)).ToList();- var rounds = 1 + _random.Next(4);- for (var i = 0; i < rounds; i++)- {- var choice = _random.Next(100);- if (choice < 70 && _xmlParts.Count > 0)- MutateTree(parts);- else if (choice < 82 && _xmlParts.Count > 0)- MutateText(parts);- else if (choice < 90)- MutateBinary(parts);- else if (choice < 95 && parts.Count > 1)- parts.RemoveAt(_random.Next(parts.Count));- else- Splice(parts);- }- var package = Pack(parts);- if (_random.Next(100) < 4)- {- // Bytes of the ZIP itself: headers, sizes, compressed data.- for (var flips = 1 + _random.Next(8); flips > 0; flips--)- package[_random.Next(package.Length)] = (byte)_random.Next(256);- }- return package;- }-- private byte[] Pack(List<(string Name, byte[] Bytes)> parts)- {- using var output = new MemoryStream();- using (var zip = new ZipArchive(output, ZipArchiveMode.Create, leaveOpen: true))- {- foreach (var (name, bytes) in parts)- {- using var stream = zip.CreateEntry(name, _random.Next(4) == 0 ? CompressionLevel.NoCompression : CompressionLevel.Fastest).Open();- stream.Write(bytes);- }- }- return output.ToArray();- }-- /// <summary>An XML part, the larger ones (the body, the styles) more often.</summary>- private int PickXml(List<(string Name, byte[] Bytes)> parts)- {- var candidates = Enumerable.Range(0, parts.Count).Where(i => _xmlParts.Contains(parts[i].Name)).ToList();- if (candidates.Count == 0)- return -1;- if (_random.Next(4) == 0)- return candidates[_random.Next(candidates.Count)];- var total = candidates.Sum(i => (long)parts[i].Bytes.Length + 1);- var pick = _random.NextInt64(total);- foreach (var i in candidates)- {- pick -= parts[i].Bytes.Length + 1;- if (pick < 0)- return i;- }- return candidates[^1];- }-- // ───────────────────────── Tree ─────────────────────────-- private void MutateTree(List<(string Name, byte[] Bytes)> parts)- {- var index = PickXml(parts);- if (index < 0)- return;- XDocument document;- try- {- document = XDocument.Parse(Encoding.UTF8.GetString(parts[index].Bytes), LoadOptions.PreserveWhitespace);- }- catch (XmlException)- {- return; // an earlier round broke it- }- var elements = document.Descendants().ToList();- if (elements.Count == 0)- return;- for (var edits = 1 + _random.Next(3); edits > 0; edits--)- {- var element = elements[_random.Next(elements.Count)];- switch (_random.Next(9))- {- case 0 or 1 or 2:- SetAttribute(element, elements);- break;- case 3:- if (element.Parent is not null)- element.Remove();- break;- case 4:- // The same element many times: counts, ids and caches.- if (element.Parent is not null)- {- var copies = _random.Next(3) == 0 ? 1 + _random.Next(200) : 1 + _random.Next(3);- for (var c = 0; c < copies; c++)- element.AddAfterSelf(new XElement(element));- }- break;- case 5:- {- // An element inside another: tables in cells in tables, notes in notes, groups in groups.- var host = elements[_random.Next(elements.Count)];- if (!host.AncestorsAndSelf().Contains(element) && !element.AncestorsAndSelf().Contains(host))- host.Add(new XElement(element));- else if (host == element)- host.Add(new XElement(element));- break;- }- case 6:- {- // The name of another element of the part.- var other = elements[_random.Next(elements.Count)];- element.Name = other.Name;- break;- }- case 7:- element.ReplaceNodes(_random.Next(3) switch- {- 0 => "",- 1 => new string('가', 1 + _random.Next(2000)),- _ => Interesting[_random.Next(Interesting.Length)],- });- break;- default:- {- var attributes = element.Attributes().Where(a => !a.IsNamespaceDeclaration).ToList();- if (attributes.Count > 0)- attributes[_random.Next(attributes.Count)].Remove();- break;- }- }- elements = document.Descendants().ToList();- if (elements.Count == 0)- break;- }- var text = new StringBuilder();- try- {- using var writer = XmlWriter.Create(text, new XmlWriterSettings { OmitXmlDeclaration = false, CheckCharacters = false });- document.Save(writer);- }- catch (Exception ex) when (ex is ArgumentException or XmlException or InvalidOperationException)- {- return; // a tree XML can't hold (xml:space="", a prefix bound twice): this edit is dropped- }- parts[index] = (parts[index].Name, Encoding.UTF8.GetBytes(text.ToString().Replace("encoding=\"utf-16\"", "encoding=\"utf-8\"", StringComparison.Ordinal)));- }-- private void SetAttribute(XElement element, List<XElement> elements)- {- var attributes = element.Attributes().Where(a => !a.IsNamespaceDeclaration).ToList();- if (_random.Next(2) == 0)- {- // Any attribute of the part, so the few that matter (a table's column count) come up as often as any.- attributes = [.. elements.SelectMany(e => e.Attributes()).Where(a => !a.IsNamespaceDeclaration)];- }- var target = attributes.Count > 0 ? attributes[_random.Next(attributes.Count)] : null;- string value;- if (_random.Next(3) == 0)- {- // A value from elsewhere in the part: ids that point at the wrong thing.- var source = elements[_random.Next(elements.Count)].Attributes().Where(a => !a.IsNamespaceDeclaration).ToList();- value = source.Count > 0 ? source[_random.Next(source.Count)].Value : Interesting[_random.Next(Interesting.Length)];- }- else if (target is not null && double.TryParse(target.Value, System.Globalization.CultureInfo.InvariantCulture, out _) && _random.Next(4) > 0)- {- // A number stays a number, of an extreme size.- value = Numbers[_random.Next(Numbers.Length)];- }- else- {- value = Interesting[_random.Next(Interesting.Length)];- }- if (target is not null && _random.Next(5) > 0)- {- target.Value = value;- }- else- {- // An attribute this element does not have, named like one elsewhere.- var named = elements[_random.Next(elements.Count)].Attributes().Where(a => !a.IsNamespaceDeclaration).ToList();- if (named.Count > 0)- element.SetAttributeValue(named[_random.Next(named.Count)].Name, value);- }- }-- // ───────────────────────── Text and bytes ─────────────────────────-- private void MutateText(List<(string Name, byte[] Bytes)> parts)- {- var index = PickXml(parts);- if (index < 0)- return;- var bytes = parts[index].Bytes.ToList();- if (bytes.Count == 0)- return;- switch (_random.Next(5))- {- case 0:- for (var flips = 1 + _random.Next(4); flips > 0; flips--)- bytes[_random.Next(bytes.Count)] = (byte)_random.Next(256);- break;- case 1:- {- var start = _random.Next(bytes.Count);- bytes.RemoveRange(start, Math.Min(bytes.Count - start, 1 + _random.Next(64)));- break;- }- case 2:- {- var start = _random.Next(bytes.Count);- var span = bytes.GetRange(start, Math.Min(bytes.Count - start, 1 + _random.Next(256)));- bytes.InsertRange(_random.Next(bytes.Count), span);- break;- }- case 3:- bytes = bytes.Take(_random.Next(bytes.Count)).ToList(); // cut short- break;- default:- {- // A DTD with entities in front of the root: must be refused, never expanded or resolved.- var text = Encoding.UTF8.GetString([.. bytes]);- var root = text.IndexOf('<', Math.Max(0, text.IndexOf("?>", StringComparison.Ordinal)));- if (root < 0)- root = 0;- var dtd = _random.Next(2) == 0- ? "<!DOCTYPE x [<!ENTITY a \"aaaaaaaaaa\"><!ENTITY b \"&a;&a;&a;&a;&a;&a;&a;&a;&a;&a;\"><!ENTITY c \"&b;&b;&b;&b;&b;&b;&b;&b;&b;&b;\">]>"- : "<!DOCTYPE x SYSTEM \"file:///c:/windows/win.ini\">";- bytes = [.. Encoding.UTF8.GetBytes(text.Insert(root, dtd))];- break;- }- }- parts[index] = (parts[index].Name, [.. bytes]);- }-- private void MutateBinary(List<(string Name, byte[] Bytes)> parts)- {- var binaries = Enumerable.Range(0, parts.Count).Where(i => !IsXml(parts[i].Name)).ToList();- if (binaries.Count == 0)- return;- var index = binaries[_random.Next(binaries.Count)];- var bytes = (byte[])parts[index].Bytes.Clone();- if (bytes.Length >= 24 && bytes[0] == 0x89 && _random.Next(2) == 0)- {- // A PNG that claims an enormous size.- bytes[16] = bytes[20] = 0x7F;- bytes[17] = bytes[21] = 0xFF;- }- else if (bytes.Length > 0)- {- for (var flips = 1 + _random.Next(8); flips > 0; flips--)- bytes[_random.Next(bytes.Length)] = (byte)_random.Next(256);- if (_random.Next(4) == 0)- bytes = bytes[.._random.Next(bytes.Length)];- }- parts[index] = (parts[index].Name, bytes);- }-- /// <summary>A part under the name of another, or an XML part where a picture should be.</summary>- private void Splice(List<(string Name, byte[] Bytes)> parts)- {- if (parts.Count < 2)- return;- var from = parts[_random.Next(parts.Count)];- var to = _random.Next(parts.Count);- parts[to] = (parts[to].Name, from.Bytes);- }-- // ───────────────────────── Running ─────────────────────────-- /// <summary>What a reader did with one input.</summary>- public enum Outcome- {- Read,- Refused,- }-- /// <summary>- /// Runs <paramref name="read"/>; returns how it ended, or throws- /// <see cref="FuzzFailure"/> for an exception a reader must not throw or a read longer than <paramref name="timeout"/>.- /// </summary>- public static Outcome Run(Action read, TimeSpan timeout)- {- Exception? error = null;- var thread = new Thread(() =>- {- try- {- read();- }- catch (Exception ex)- {- error = ex;- }- }, 1024 * 1024); // the smallest stack a conversion runs on: what the limits allow must fit in it- thread.IsBackground = true;- thread.Start();- if (!thread.Join(timeout))- throw new FuzzFailure($"The read took longer than {timeout.TotalSeconds:0} s.", null);- return error switch- {- null => Outcome.Read,- InvalidDataException or ConversionRefusedException => Outcome.Refused,- _ => throw new FuzzFailure($"{error.GetType().Name}: {error.Message}", error),- };- }-- public sealed class FuzzFailure(string message, Exception? inner) : Exception(message, inner);-}diff --git a/tests/Filee.Engines.Tests/DocumentHostileInputTests.cs b/tests/Filee.Engines.Tests/DocumentHostileInputTests.csdeleted file mode 100644index 07882465..00000000--- a/tests/Filee.Engines.Tests/DocumentHostileInputTests.cs+++ /dev/null@@ -1,637 +0,0 @@-// Hostile HWPX and DOCX packages for the document readers and the limits they share (Documents/DocumentLimits): ZIP-// bombs, XML nested or repeated far beyond real documents, DTDs, tables, groups, notes and fields nested without end,-// pictures that claim gigapixels, and the inputs the fuzzer (DocumentFuzzTests) found. Each must be refused or read-// within the limits, quickly and on the smallest stack a conversion runs on. The layout loop guards are tested here too.--using System.IO.Compression;-using System.Text;-using Filee.Core.Conversion;-using Filee.Engines.Documents;-using Filee.Engines.Hwp.Hwpx;-using Filee.Engines.Hwp.Hwpx.Docx;-using Filee.Engines.Infrastructure;-using static Filee.Engines.Tests.DocxBuilder;--namespace Filee.Engines.Tests;--public class DocumentHostileInputTests(EngineFixture fx) : IClassFixture<EngineFixture>-{- private const string HwpNamespaces =- "xmlns:hp=\"http://www.hancom.co.kr/hwpml/2011/paragraph\" xmlns:hs=\"http://www.hancom.co.kr/hwpml/2011/section\" xmlns:hc=\"http://www.hancom.co.kr/hwpml/2011/core\"";-- // ───────────────────────── Helpers ─────────────────────────-- /// <summary>- /// Runs <paramref name="action"/> on a thread with a 1 MB stack (the smallest a conversion gets) and returns what- /// it threw; fails when it takes longer than <paramref name="seconds"/>.- /// </summary>- private static Exception? OnSmallStack(Action action, int seconds = 60)- {- Exception? error = null;- var thread = new Thread(() =>- {- try- {- action();- }- catch (Exception ex)- {- error = ex;- }- }, 1024 * 1024);- thread.IsBackground = true;- thread.Start();- Assert.True(thread.Join(TimeSpan.FromSeconds(seconds)), $"Still running after {seconds} s");- return error;- }-- private static ConversionRefusedException Refused(Action action)- {- var refusal = Assert.IsType<ConversionRefusedException>(OnSmallStack(action));- Assert.Equal(DocumentLimits.ErrorKey, refusal.ErrorKey);- return refusal;- }-- private static void Reads(Action action) => Assert.Null(OnSmallStack(action));-- /// <summary>A copy of a package with some parts replaced (written by the action) or added.</summary>- private static string Rewrite(string source, string target, Dictionary<string, Action<Stream>> parts)- {- using (var input = ZipFile.OpenRead(source))- using (var output = ZipFile.Open(target, ZipArchiveMode.Create))- {- foreach (var entry in input.Entries)- {- if (parts.ContainsKey(entry.FullName))- continue;- using var from = entry.Open();- using var to = output.CreateEntry(entry.FullName).Open();- from.CopyTo(to);- }- foreach (var (name, write) in parts)- {- using var to = output.CreateEntry(name).Open();- write(to);- }- }- return target;- }-- private static Action<Stream> Text(string text) => stream => stream.Write(Encoding.UTF8.GetBytes(text));-- private string Docx(string body, Action<DocxBuilder>? setup = null)- {- var builder = new DocxBuilder();- builder.Paragraph(body);- setup?.Invoke(builder);- return builder.Save(Path.Combine(fx.NewFolder(), "input.docx"));- }-- /// <summary>An HWPX package written by Filee whose section0.xml holds <paramref name="paragraphs"/>.</summary>- private string Hwpx(string paragraphs, Dictionary<string, Action<Stream>>? more = null)- {- var folder = fx.NewFolder();- var document = new HDocument();- document.Sections.Add(new HSection { Blocks = { Paragraph("seed") } });- var seed = Path.Combine(folder, "seed.hwpx");- HwpxWriter.Write(document, seed);- var parts = new Dictionary<string, Action<Stream>>(more ?? [])- {- ["Contents/section0.xml"] = Text($"<?xml version=\"1.0\" encoding=\"UTF-8\"?><hs:sec {HwpNamespaces}>{paragraphs}</hs:sec>"),- };- return Rewrite(seed, Path.Combine(folder, "input.hwpx"), parts);- }-- private static string Hp(string runContent) => $"<hp:p paraPrIDRef=\"0\" styleIDRef=\"0\"><hp:run charPrIDRef=\"0\">{runContent}</hp:run></hp:p>";-- private static HParagraph Paragraph(string text)- {- var paragraph = new HParagraph();- paragraph.Inlines.Add(new HText(text, default));- return paragraph;- }-- /// <summary>A table with one cell, nested <paramref name="levels"/> deep, the innermost holding "inside".</summary>- private static HTable NestedTables(int levels)- {- HBlock content = Paragraph("inside");- HTable? table = null;- for (var i = 0; i < levels; i++)- {- table = new HTable { ColumnCount = 1 };- var cell = new HCell();- cell.Blocks.Add(content);- var row = new HRow();- row.Cells.Add(cell);- table.Rows.Add(row);- content = table;- }- return table!;- }-- private string Media() => Path.Combine(fx.NewFolder(), "media");-- private static int Depth(IEnumerable<HBlock> blocks) =>- blocks.OfType<HTable>().Select(t => 1 + t.Rows.SelectMany(r => r.Cells).Select(c => Depth(c.Blocks)).DefaultIfEmpty(0).Max()).DefaultIfEmpty(0).Max();-- // ───────────────────────── The limits ─────────────────────────-- [Fact]- public void The_limits_are_the_planned_ones()- {- var limits = DocumentLimits.Default;- Assert.Equal(64L << 20, limits.MaxPartBytes);- Assert.Equal(1L << 30, limits.MaxPackageBytes);- Assert.Equal(32, limits.MaxNestingDepth);- Assert.Equal(20_000, limits.MaxPages);- Assert.Equal(16_384L * 16_384, limits.MaxPicturePixels);- Assert.True(limits.MaxXmlDepth >= limits.MaxNestingDepth * 8, "tables nested to the limit must fit in the XML depth");- }-- // ───────────────────────── ZIP bombs ─────────────────────────-- [Fact]- public void A_part_larger_than_64_MB_is_refused_before_it_is_unpacked()- {- var path = Rewrite(Docx(P(R("x"))), Path.Combine(fx.NewFolder(), "big.docx"), new()- {- ["word/header9.xml"] = stream =>- {- var chunk = new byte[1 << 20];- Array.Fill(chunk, (byte)' ');- for (var i = 0; i < 65; i++)- stream.Write(chunk);- },- });- using var package = DocumentPackage.Open(path);- var entry = package.GetEntry("word/header9.xml")!;- var refusal = Assert.Throws<ConversionRefusedException>(() => package.Open(entry));- Assert.Contains("more than 64 MB", refusal.Detail);- Assert.Equal(0, package.BytesRead);- }-- [Fact]- public void A_part_that_inflates_like_a_bomb_is_refused_while_it_is_unpacked()- {- // 6 MB of spaces packs into a few kilobytes: far beyond what any word processor's XML compresses to.- var body = "<w:p><w:r><w:t>" + new string(' ', 6 << 20) + "</w:t></w:r></w:p>";- var refusal = Refused(() => DocxReader.Read(Docx(body), Media()));- Assert.Contains("times its packed size", refusal.Detail);- }-- [Fact]- public void A_part_whose_header_understates_its_size_is_counted_as_it_unpacks()- {- var docx = Docx(P(R(new string('x', 2 << 20))));- var bytes = File.ReadAllBytes(docx);- UnderstateSize(bytes, "word/document.xml", 100);- var lying = Path.Combine(fx.NewFolder(), "lying.docx");- File.WriteAllBytes(lying, bytes);- // What .NET makes of the size is its business; Filee must not take 2 MB for a part of 1 MB at the most.- var error = OnSmallStack(() => DocxReader.Read(lying, Media(), DocumentLimits.Default with { MaxPartBytes = 1 << 20 }));- Assert.True(error is InvalidDataException or ConversionRefusedException, error?.ToString() ?? "read");- }-- /// <summary>Writes <paramref name="size"/> as the unpacked size of <paramref name="name"/> in its local and central headers.</summary>- private static void UnderstateSize(byte[] zip, string name, uint size)- {- var nameBytes = Encoding.UTF8.GetBytes(name);- for (var i = 0; i + 46 < zip.Length; i++)- {- var signature = BitConverter.ToUInt32(zip, i);- if (signature == 0x04034B50 && zip.AsSpan(i + 30, nameBytes.Length).SequenceEqual(nameBytes))- BitConverter.TryWriteBytes(zip.AsSpan(i + 22), size);- else if (signature == 0x02014B50 && zip.AsSpan(i + 46, nameBytes.Length).SequenceEqual(nameBytes))- BitConverter.TryWriteBytes(zip.AsSpan(i + 24), size);- }- }-- [Fact]- public void A_package_whose_parts_together_pass_the_limit_is_refused()- {- var limits = DocumentLimits.Default with { MaxPackageBytes = 3 << 20 };- var docx = Docx(P(R("x")), builder =>- {- var references = string.Concat(Enumerable.Range(0, 4).Select(i =>- $"<w:headerReference w:type=\"{(i % 2 == 0 ? "default" : "even")}\" r:id=\"{builder.Header(P(R(new string('x', 1 << 20))))}\"/>"));- builder.SectionProperties = references + DefaultPage;- });- var refusal = Refused(() => DocxReader.Read(docx, Media(), limits));- Assert.Contains("The package unpacks to more than 3 MB", refusal.Detail);- Reads(() => DocxReader.Read(docx, Media()));- }-- [Fact]- public void A_package_of_too_many_parts_is_refused()- {- var docx = Docx(P(R("x")));- var refusal = Refused(() => DocxReader.Read(docx, Media(), DocumentLimits.Default with { MaxPackageEntries = 3 }));- Assert.Contains("more than 3 parts", refusal.Detail);- }-- // ───────────────────────── XML ─────────────────────────-- [Theory]- [InlineData("docx")]- [InlineData("hwpx")]- public void Xml_nested_a_hundred_thousand_levels_deep_is_refused_at_once(string format)- {- var nested = string.Concat(Enumerable.Repeat("<x>", 100_000)) + string.Concat(Enumerable.Repeat("</x>", 100_000));- var refusal = format == "docx"- ? Refused(() => DocxReader.Read(Docx(P("<w:r>" + nested + "</w:r>")), Media()))- : Refused(() => HwpxReader.Read(Hwpx(Hp(nested)), Media()));- Assert.Contains("512 levels deep", refusal.Detail);- }-- [Fact]- public void Xml_of_countless_tiny_elements_is_refused_before_it_fills_the_memory()- {- var limits = DocumentLimits.Default with { MaxXmlElements = 10_000 };- var docx = Docx(P(string.Concat(Enumerable.Repeat("<w:r/>", 20_000))));- var refusal = Refused(() => DocxReader.Read(docx, Media(), limits));- Assert.Contains("more than 10,000 elements", refusal.Detail);- Reads(() => DocxReader.Read(docx, Media()));- }-- [Theory]- [InlineData("<!DOCTYPE w:document [<!ENTITY a \"aaaaaaaaaa\"><!ENTITY b \"&a;&a;&a;&a;&a;&a;&a;&a;&a;&a;\"><!ENTITY c \"&b;&b;&b;&b;&b;&b;&b;&b;&b;&b;\"><!ENTITY d \"&c;&c;&c;&c;&c;&c;&c;&c;&c;&c;\">]>", "&d;")]- [InlineData("<!DOCTYPE w:document [<!ENTITY secret SYSTEM \"file:///C:/Windows/win.ini\">]>", "&secret;")]- [InlineData("<!DOCTYPE w:document SYSTEM \"http://example.invalid/word.dtd\">", "x")]- public void A_document_with_a_DTD_is_refused_without_expanding_or_fetching_anything(string doctype, string text)- {- var docx = Docx(P(R("x")));- var path = Rewrite(docx, Path.Combine(fx.NewFolder(), "dtd.docx"), new()- {- ["word/document.xml"] = Text($"<?xml version=\"1.0\" encoding=\"UTF-8\"?>{doctype}<w:document {Namespaces}><w:body><w:p><w:r><w:t>{text}</w:t></w:r></w:p></w:body></w:document>"),- });- var error = Assert.IsType<InvalidDataException>(OnSmallStack(() => DocxReader.Read(path, Media())));- Assert.Contains("DTD", error.Message);- }-- [Fact]- public void Geo_xml_still_reads_through_the_shared_loader()- {- using var stream = new MemoryStream("<a xmlns:p=\"urn:p\"><p:b>1 & 2</p:b><![CDATA[x]]></a>"u8.ToArray());- var root = Filee.Engines.Geo.GeoXml.Load(stream).Root!;- Assert.Equal("1 & 2", root.Element(XmlNamespace("urn:p") + "b")!.Value);- Assert.Empty(root.Attributes()); // namespace declarations are not kept for the geospatial formats- }-- private static System.Xml.Linq.XNamespace XmlNamespace(string uri) => System.Xml.Linq.XNamespace.Get(uri);-- [Fact]- public void The_shared_loader_keeps_what_the_readers_look_up_like_XDocument_Load()- {- const string xml = "<?xml version=\"1.0\"?><r xmlns=\"urn:d\" xmlns:p=\"urn:p\" p:a=\"1\"><t xml:space=\"preserve\"> a <![CDATA[<b>]]> c </t><!-- note --><p:e/>\n</r>";- using var stream = new MemoryStream(Encoding.UTF8.GetBytes(xml));- var safe = SafeXml.Load(stream, new XmlLimits(10, 100, 10_000));- var reference = System.Xml.Linq.XDocument.Parse(xml, System.Xml.Linq.LoadOptions.PreserveWhitespace);- Assert.Equal(reference.Root!.Value, safe.Root!.Value);- Assert.Equal("urn:p", safe.Root.GetNamespaceOfPrefix("p")?.NamespaceName);- Assert.Equal(reference.Root.Attributes().Select(a => a.ToString()), safe.Root.Attributes().Select(a => a.ToString()));- Assert.Equal(reference.Root.Elements().Select(e => e.Name), safe.Root.Elements().Select(e => e.Name));- }-- // ───────────────────────── Nesting ─────────────────────────-- [Fact]- public void Hwpx_tables_nested_to_the_limit_are_read_and_one_deeper_refused()- {- string Write(int levels)- {- var document = new HDocument();- document.Sections.Add(new HSection { Blocks = { NestedTables(levels) } });- var path = Path.Combine(fx.NewFolder(), $"nested-{levels}.hwpx");- HwpxWriter.Write(document, path);- return path;- }- HDocument? read = null;- Reads(() => read = HwpxReader.Read(Write(32), Media()));- Assert.Equal(32, Depth(read!.Sections[0].Blocks));- var refusal = Refused(() => HwpxReader.ReadForLayout(Write(33), Media()));- Assert.Contains("nested more than 32 levels deep", refusal.Detail);- }-- [Fact]- public void Docx_tables_nested_to_the_limit_are_read_and_one_deeper_refused()- {- string Write(int levels)- {- var document = new HDocument();- document.Sections.Add(new HSection { Blocks = { NestedTables(levels) } });- var path = Path.Combine(fx.NewFolder(), $"nested-{levels}.docx");- DocxWriter.Write(document, path);- return path;- }- HDocument? read = null;- Reads(() => read = DocxReader.Read(Write(32), Media()));- Assert.Equal(32, Depth(read!.Sections[0].Blocks));- Refused(() => DocxReader.Read(Write(33), Media()));- }-- [Fact]- public void Groups_nested_without_end_are_refused()- {- var hwpx = Hwpx(Hp(string.Concat(Enumerable.Repeat("<hp:container>", 60)) + "<hp:rect/>" + string.Concat(Enumerable.Repeat("</hp:container>", 60))));- Refused(() => HwpxReader.Read(hwpx, Media()));-- var group = string.Concat(Enumerable.Repeat("<wpg:grpSp>", 60)) + "<wps:wsp><wps:bodyPr/></wps:wsp>" + string.Concat(Enumerable.Repeat("</wpg:grpSp>", 60));- var docx = Docx(P(Anchor("http://schemas.microsoft.com/office/word/2010/wordprocessingGroup", "<wpg:wgp>" + group + "</wpg:wgp>", 914400, 914400,- "<wp:positionH relativeFrom=\"page\"><wp:posOffset>0</wp:posOffset></wp:positionH>", "<wp:positionV relativeFrom=\"page\"><wp:posOffset>0</wp:posOffset></wp:positionV>")));- Refused(() => DocxReader.Read(docx, Media()));-- var vml = Docx(P("<w:r><w:pict>" + string.Concat(Enumerable.Repeat("<v:group>", 60)) + "<v:rect style=\"width:10pt;height:10pt\"/>" + string.Concat(Enumerable.Repeat("</v:group>", 60)) + "</w:pict></w:r>"));- Refused(() => DocxReader.Read(vml, Media()));- }-- [Fact]- public void A_footnote_that_refers_to_itself_is_read_once()- {- // Before, reading the note read its reference, which read the note again until the stack overflowed.- var docx = Docx(P(R("본문") + "<w:r><w:footnoteReference w:id=\"1\"/></w:r>"), builder =>- builder.Footnotes("<w:footnote w:id=\"1\"><w:p>" + R("각주") + "<w:r><w:footnoteReference w:id=\"1\"/></w:r></w:p></w:footnote>"));- HDocument? read = null;- Reads(() => read = DocxReader.Read(docx, Media()));- var note = Assert.Single(read!.Sections[0].Blocks.OfType<HParagraph>().SelectMany(p => p.Inlines).OfType<HNote>());- Assert.Empty(note.Blocks.OfType<HParagraph>().SelectMany(p => p.Inlines).OfType<HNote>());- }-- [Fact]- public void Fields_that_never_end_are_refused_instead_of_slowing_every_run()- {- var docx = Docx(P(string.Concat(Enumerable.Repeat("<w:r><w:fldChar w:fldCharType=\"begin\"/></w:r>", 100_000)) + R("x")));- var refusal = Refused(() => DocxReader.Read(docx, Media()));- Assert.Contains("Fields are nested", refusal.Detail);-- // Every paragraph reopened the links of every open HWPX field: links nested as deep as the fields.- const string Begin = "<hp:ctrl><hp:fieldBegin type=\"HYPERLINK\"><hp:parameters><hp:stringParam name=\"Command\">https\\://example.invalid;1;0;0;</hp:stringParam></hp:parameters></hp:fieldBegin></hp:ctrl>";- var hwpx = Hwpx(Hp(string.Concat(Enumerable.Repeat(Begin, 1000))) + Hp("<hp:t>x</hp:t>"));- Refused(() => HwpxReader.Read(hwpx, Media()));- }-- [Fact]- public void A_style_chain_of_a_hundred_thousand_styles_is_read_without_overflowing_the_stack()- {- var styles = new StringBuilder();- for (var i = 0; i < 100_000; i++)- styles.Append($"<w:style w:type=\"paragraph\" w:styleId=\"S{i}\"><w:basedOn w:val=\"S{i + 1}\"/><w:pPr><w:jc w:val=\"center\"/></w:pPr></w:style>");- var docx = Docx(P(R("x"), "<w:pStyle w:val=\"S0\"/>"), builder => builder.Styles += styles.ToString());- HDocument? read = null;- Reads(() => read = DocxReader.Read(docx, Media()));- Assert.Equal(HAlign.Center, read!.Sections[0].Blocks.OfType<HParagraph>().First().Format.Align);- }-- // ───────────────────────── Counts ─────────────────────────-- [Fact]- public void Paragraphs_and_objects_beyond_the_limits_are_refused()- {- var limits = DocumentLimits.Default with { MaxParagraphs = 100, MaxObjects = 10 };- var paragraphs = Docx(string.Concat(Enumerable.Repeat(P(R("x")), 101)));- Assert.Contains("more than 100 paragraphs", Refused(() => DocxReader.Read(paragraphs, Media(), limits)).Detail);- var hwpxParagraphs = Hwpx(string.Concat(Enumerable.Repeat(Hp("<hp:t>x</hp:t>"), 101)));- Assert.Contains("more than 100 paragraphs", Refused(() => HwpxReader.Read(hwpxParagraphs, Media(), null, limits)).Detail);-- var shapes = Hwpx(Hp(string.Concat(Enumerable.Repeat("<hp:rect/>", 11))));- Assert.Contains("more than 10 tables, pictures and drawing objects", Refused(() => HwpxReader.Read(shapes, Media(), null, limits)).Detail);- Reads(() => HwpxReader.Read(shapes, Media()));- }-- // ───────────────────────── Pictures ─────────────────────────-- /// <summary>A PNG of 4 × 3 pixels whose header claims <paramref name="width"/> × <paramref name="height"/>.</summary>- private static byte[] ClaimingPng(int width, int height)- {- var png = DocumentFuzzTests.TinyPng(4, 3);- System.Buffers.Binary.BinaryPrimitives.WriteInt32BigEndian(png.AsSpan(16), width);- System.Buffers.Binary.BinaryPrimitives.WriteInt32BigEndian(png.AsSpan(20), height);- return png;- }-- [Fact]- public void A_picture_that_claims_ten_gigapixels_is_left_out_and_the_document_still_reads()- {- var huge = new DocxBuilder();- var big = huge.Image(ClaimingPng(100_000, 100_000));- var small = huge.Image(DocumentFuzzTests.TinyPng(4, 3));- huge.Paragraph(P(InlinePicture(big, 914400, 914400) + InlinePicture(small, 914400, 914400) + R("글")));- var docx = huge.Save(Path.Combine(fx.NewFolder(), "huge.docx"));- HDocument? read = null;- var media = Media();- Reads(() => read = DocxReader.Read(docx, media));- var image = Assert.Single(read!.Sections[0].Blocks.OfType<HParagraph>().SelectMany(p => p.Inlines).OfType<HImage>());- Assert.Equal((4, 3), PictureSize.Read(image.Path));- Assert.Single(Directory.GetFiles(media)); // the huge one was not kept on disk either-- // HWPX: the same picture through the HWPX writer, then its header made huge.- var document = new HDocument();- var paragraph = new HParagraph();- var picture = Path.Combine(fx.NewFolder(), "p.png");- File.WriteAllBytes(picture, DocumentFuzzTests.TinyPng(4, 3));- paragraph.Inlines.Add(new HImage(picture) { Width = 1000, Height = 750 });- document.Sections.Add(new HSection { Blocks = { paragraph } });- var seed = Path.Combine(fx.NewFolder(), "picture.hwpx");- HwpxWriter.Write(document, seed);- string binData;- using (var zip = ZipFile.OpenRead(seed))- binData = zip.Entries.Single(e => e.FullName.StartsWith("BinData/", StringComparison.Ordinal)).FullName;- var hwpx = Rewrite(seed, Path.Combine(fx.NewFolder(), "huge.hwpx"), new() { [binData] = s => s.Write(ClaimingPng(100_000, 100_000)) });- Reads(() => read = HwpxReader.Read(hwpx, Media()));- Assert.Empty(read!.Sections[0].Blocks.OfType<HParagraph>().SelectMany(p => p.Inlines).OfType<HImage>());- }-- [Fact]- public void Picture_sizes_are_read_from_the_headers_of_every_common_format()- {- (int, int)? Size(byte[] bytes) => PictureSize.Read(new MemoryStream(bytes));- Assert.Equal((4, 3), Size(DocumentFuzzTests.TinyPng(4, 3)));- Assert.Equal((100_000, 70_000), Size(ClaimingPng(100_000, 70_000)));- Assert.Equal((640, 480), Size([.. "GIF89a"u8, 0x80, 0x02, 0xE0, 0x01, 0, 0, 0]));- // BMP: BITMAPINFOHEADER with a negative (top-down) height.- var bmp = new byte[54];- "BM"u8.CopyTo(bmp);- BitConverter.TryWriteBytes(bmp.AsSpan(14), 40);- BitConverter.TryWriteBytes(bmp.AsSpan(18), 300);- BitConverter.TryWriteBytes(bmp.AsSpan(22), -200);- Assert.Equal((300, 200), Size(bmp));- // JPEG: an APP0 segment, then the frame header (SOF0) with height 1080 and width 1920.- byte[] jpeg = [0xFF, 0xD8, 0xFF, 0xE0, 0x00, 0x10, .. new byte[14], 0xFF, 0xC0, 0x00, 0x11, 0x08, 0x04, 0x38, 0x07, 0x80, 0x03, .. new byte[9], 0xFF, 0xD9];- Assert.Equal((1920, 1080), Size(jpeg));- // WebP: VP8X with a canvas of 5000 × 4000.- var webp = new byte[30];- "RIFF"u8.CopyTo(webp);- "WEBPVP8X"u8.CopyTo(webp.AsSpan(8));- webp[24] = (5000 - 1) & 0xFF;- webp[25] = (5000 - 1) >> 8;- webp[27] = (4000 - 1) & 0xFF;- webp[28] = (4000 - 1) >> 8;- Assert.Equal((5000, 4000), Size(webp));- // Unknown, cut short or endless headers give no size.- Assert.Null(Size("%PDF-1.7"u8.ToArray()));- Assert.Null(Size([0x89, (byte)'P', (byte)'N', (byte)'G']));- Assert.Null(Size([0xFF, 0xD8, .. Enumerable.Repeat<byte>(0xFF, 5000)]));- }-- [Fact]- public void Part_names_never_become_file_names()- {- Assert.Equal(".png", DocumentPackage.SafeExtension("word/media/image1.PNG"));- Assert.Equal("", DocumentPackage.SafeExtension("media/image.png:stream"));- Assert.Equal("", DocumentPackage.SafeExtension("../../evil"));- Assert.Equal("", DocumentPackage.SafeExtension("x.p/n\\g"));- Assert.Equal("", DocumentPackage.SafeExtension("x." + new string('a', 9)));- Assert.Equal("", DocumentPackage.SafeExtension("noextension"));-- // A relationship target with a stream name and a path still lands as docx-media-1 in the media folder.- var builder = new DocxBuilder();- var id = builder.Image(DocumentFuzzTests.TinyPng(4, 3));- builder.Paragraph(P(InlinePicture(id, 914400, 914400)));- var docx = builder.Save(Path.Combine(fx.NewFolder(), "names.docx"));- var renamed = Path.Combine(fx.NewFolder(), "renamed.docx");- using (var input = ZipFile.OpenRead(docx))- using (var output = ZipFile.Open(renamed, ZipArchiveMode.Create))- {- foreach (var entry in input.Entries)- {- var name = entry.FullName == "word/media/image1.png" ? "word/media/image1.png:evil" : entry.FullName;- using var from = entry.Open();- var text = name.EndsWith(".rels", StringComparison.Ordinal) ? new StreamReader(from).ReadToEnd().Replace("media/image1.png", "media/image1.png:evil", StringComparison.Ordinal) : null;- using var to = output.CreateEntry(name).Open();- if (text is null)- from.CopyTo(to);- else- to.Write(Encoding.UTF8.GetBytes(text));- }- }- var media = Media();- Reads(() => DocxReader.Read(renamed, media));- Assert.Equal(["docx-media-1"], Directory.GetFiles(media).Select(Path.GetFileName));- }-- [Fact]- public void Embedded_fonts_are_not_read()- {- var docx = Docx(P(R("x", "<w:rFonts w:ascii=\"Hostile\"/>")));- var withFont = Rewrite(docx, Path.Combine(fx.NewFolder(), "font.docx"), new()- {- ["word/fonts/font1.odttf"] = s => s.Write(new byte[4096]),- ["word/fontTable.xml"] = Text($"<w:fonts {Namespaces}><w:font w:name=\"Hostile\"><w:embedRegular r:id=\"rIdFont\" w:fontKey=\"{{00000000-0000-0000-0000-000000000000}}\"/></w:font></w:fonts>"),- });- var media = Media();- Reads(() => DocxReader.Read(withFont, media));- Assert.False(Directory.Exists(media) && Directory.EnumerateFiles(media).Any());- }-- // ───────────────────────── What the fuzzer found ─────────────────────────-- [Fact]- public void Fuzz_finding_two_numberings_with_one_id_read_with_the_first()- {- // ArgumentException: an item with the same key has already been added (DocxReader.LoadNumbering).- var docx = Docx(P(R("항목"), "<w:numPr><w:ilvl w:val=\"0\"/><w:numId w:val=\"1\"/></w:numPr>"), builder => builder.Numbering =- "<w:abstractNum w:abstractNumId=\"0\"><w:lvl w:ilvl=\"0\"><w:numFmt w:val=\"decimal\"/><w:lvlText w:val=\"%1)\"/></w:lvl></w:abstractNum>" +- "<w:abstractNum w:abstractNumId=\"0\"><w:lvl w:ilvl=\"0\"><w:numFmt w:val=\"bullet\"/><w:lvlText w:val=\"*\"/></w:lvl></w:abstractNum>" +- "<w:num w:numId=\"1\"><w:abstractNumId w:val=\"0\"/></w:num>");- HDocument? read = null;- Reads(() => read = DocxReader.Read(docx, Media()));- var list = read!.Sections[0].Blocks.OfType<HParagraph>().First().List;- Assert.Equal("^1)", list!.Numbering.Levels[0].Text);- }-- [Theory]- [InlineData("-1e308")]- [InlineData("-2147483648")]- [InlineData("-9223372036854775808")]- public void Fuzz_finding_page_sizes_at_the_end_of_the_number_range_read(string value)- {- // OverflowException: negating the minimum value of a twos complement number (Math.Abs in DocxReader.Page).- var docx = Docx(P(R("x")), builder => builder.SectionProperties =- $"<w:pgSz w:w=\"{value}\" w:h=\"16838\"/><w:pgMar w:top=\"{value}\" w:right=\"1440\" w:bottom=\"1440\" w:left=\"1440\" w:header=\"720\" w:footer=\"720\" w:gutter=\"0\"/>");- Reads(() => DocxReader.Read(docx, Media()));- // VML line ends at both ends of the range (Math.Abs of their difference).- var line = Docx(P("<w:r><w:pict><v:line from=\"-99999999999in,0\" to=\"0,0\"/></w:pict></w:r>"));- Reads(() => DocxReader.Read(line, Media()));- }-- [Fact]- public void Fuzz_finding_damaged_xml_in_a_docx_is_invalid_data()- {- // XmlException escaped DocxReader for every part (document, relationships, core properties).- foreach (var part in new[] { "word/document.xml", "word/_rels/document.xml.rels", "docProps/core.xml" })- {- var path = Rewrite(Docx(P(R("x"))), Path.Combine(fx.NewFolder(), "damaged.docx"), new() { [part] = Text("<a><b></a>") });- var error = Assert.IsType<InvalidDataException>(OnSmallStack(() => DocxReader.Read(path, Media())));- Assert.Contains(part, error.Message);- }- }-- [Theory]- [InlineData("colCnt=\"2147483647\"", "colAddr=\"0\"", "colSpan=\"1\"")] // fuzzer: OutOfMemoryException, array dimensions exceeded- [InlineData("colCnt=\"2\"", "colAddr=\"2147483647\"", "colSpan=\"2147483647\"")] // fuzzer: ArgumentOutOfRangeException in ColumnWidths- [InlineData("colCnt=\"3\"", "colAddr=\"0\"", "colSpan=\"3\"")] // found with them: the widths of the cells below overflowed their sum- public void Fuzz_finding_hwpx_tables_with_column_numbers_at_the_end_of_the_range_read(string count, string address, string span)- {- static string Cell(string text, int column, int row, string width) =>- $"<hp:tc><hp:subList><hp:p><hp:run><hp:t>{text}</hp:t></hp:run></hp:p></hp:subList><hp:cellAddr colAddr=\"{column}\" rowAddr=\"{row}\"/>" +- $"<hp:cellSpan colSpan=\"1\" rowSpan=\"1\"/><hp:cellSz width=\"{width}\" height=\"1000\"/></hp:tc>";- var cell = $"<hp:tc><hp:subList><hp:p><hp:run><hp:t>칸</hp:t></hp:run></hp:p></hp:subList><hp:cellAddr {address} rowAddr=\"0\"/>" +- $"<hp:cellSpan {span} rowSpan=\"2147483647\"/><hp:cellSz width=\"2147483647\" height=\"1000\"/></hp:tc>";- var below = Cell("둘", 0, 1, "2147483647") + Cell("셋", 1, 1, "2147483647");- var hwpx = Hwpx(Hp($"<hp:tbl {count} rowCnt=\"2\"><hp:tr>{cell}</hp:tr><hp:tr>{below}</hp:tr></hp:tbl>"));- HDocument? read = null;- Reads(() => read = HwpxReader.Read(hwpx, Media()));- var table = read!.Sections[0].Blocks.OfType<HTable>().Single();- Assert.InRange(table.ColumnCount, 1, DocumentLimits.Default.MaxTableColumns);- Assert.Equal(2, table.Rows[0].Cells[0].RowSpan); // no further than the last row- }-- // ───────────────────────── Layout guards ─────────────────────────-- [Fact]- public void The_layout_stops_at_the_page_limit_and_after_too_many_empty_pages()- {- var limits = DocumentLimits.Default with { MaxPages = 5, MaxConsecutiveEmptyPages = 2 };- var guard = new LayoutGuard(limits, CancellationToken.None);- for (var i = 0; i < 5; i++)- guard.PageFinished(empty: false);- Assert.Contains("more than 5 pages", Assert.Throws<ConversionRefusedException>(() => guard.PageFinished(empty: false)).Detail);-- var stuck = new LayoutGuard(limits with { MaxPages = 100 }, CancellationToken.None);- stuck.PageFinished(empty: true);- stuck.PageFinished(empty: true);- stuck.PageFinished(empty: false); // something placed: the count starts again- stuck.PageFinished(empty: true);- stuck.PageFinished(empty: true);- Assert.Contains("more than 2 empty pages in a row", Assert.Throws<ConversionRefusedException>(() => stuck.PageFinished(empty: true)).Detail);- }-- [Fact]- public void Every_paragraph_checks_cancellation_and_the_time_budget()- {- var elapsed = TimeSpan.Zero;- var guard = new LayoutGuard(DocumentLimits.Default with { LayoutTimeBudget = TimeSpan.FromMinutes(1) }, CancellationToken.None, () => elapsed);- guard.Paragraph();- elapsed = TimeSpan.FromSeconds(61);- var refusal = Assert.Throws<ConversionRefusedException>(guard.Paragraph);- Assert.Equal(DocumentLimits.ErrorKey, refusal.ErrorKey);- Assert.Contains("longer than 1 minute.", refusal.Detail);-- using var cancelled = new CancellationTokenSource();- var cancellable = new LayoutGuard(DocumentLimits.Default, cancelled.Token);- cancellable.Paragraph();- cancelled.Cancel();- Assert.Throws<OperationCanceledException>(cancellable.Paragraph);- }-- [Theory]- [InlineData(100, 50, 200, 300, 100, 50, false)] // fits- [InlineData(500, 50, 200, 300, 200, 50, true)] // too wide: clipped to the column- [InlineData(100, 9e9, 200, 300, 100, 300, true)] // taller than any page: clipped and placed, not moved on- [InlineData(double.NaN, double.PositiveInfinity, 200, 300, 0, 0, false)] // sizes that are no numbers- [InlineData(-5, 10, 200, 300, 0, 10, false)]- public void An_object_that_fits_no_page_is_clipped_and_placed(double width, double height, double areaWidth, double areaHeight,- double placedWidth, double placedHeight, bool clipped)- {- Assert.Equal((placedWidth, placedHeight, clipped), LayoutGuard.Fit(width, height, areaWidth, areaHeight));- }-}diff --git a/tests/Filee.Engines.Tests/GeoHostileInputTests.cs b/tests/Filee.Engines.Tests/GeoHostileInputTests.csindex 8b141e41..95daaea9 100644--- a/tests/Filee.Engines.Tests/GeoHostileInputTests.cs+++ b/tests/Filee.Engines.Tests/GeoHostileInputTests.cs@@ -7,7 +7,6 @@ using System.IO.Compression;using System.Text;using Filee.Core.Conversion;using Filee.Engines.Geo;-using Filee.Engines.Infrastructure;namespace Filee.Engines.Tests;diff --git a/tests/Filee.Engines.Tests/HwpxReaderTests.cs b/tests/Filee.Engines.Tests/HwpxReaderTests.csindex e9a83e84..9b44da77 100644--- a/tests/Filee.Engines.Tests/HwpxReaderTests.cs+++ b/tests/Filee.Engines.Tests/HwpxReaderTests.cs@@ -636,7 +636,7 @@ public class HwpxReaderTests(EngineFixture fx) : IClassFixture<EngineFixture>/// one missing), a group, equation, compose, ruby text, notes, a chart with an OLE fallback, and in the second/// section other namespace prefixes./// </summary>- internal static string HangulStylePackage(string folder)+ private static string HangulStylePackage(string folder){const string Namespaces ="xmlns:ha=\"http://www.hancom.co.kr/hwpml/2011/app\" xmlns:hp=\"http://www.hancom.co.kr/hwpml/2011/paragraph\" " +