Support pptx (PowerPoint) as an input format.

New module `Text.Pandoc.Readers.Pptx`,
exporting `readPptx`. [API change]

Factored out some common OOXML functions from
Text.Pandoc.Readers.Docx.Util into a non-exported module
Text.Pandoc.Readers.OOXML.Shared.

4 files changed, 214 insertions, 0 deletions

diff --git a/test/Tests/Readers/Pptx.hs b/test/Tests/Readers/Pptx.hs
new file mode 100644
index 000000000..613d5b50f
--- /dev/null
+++ b/test/Tests/Readers/Pptx.hs
@@ -0,0 +1,63 @@
+{-# LANGUAGE OverloadedStrings #-}
+{- |
+   Module      : Tests.Readers.Pptx
+   Copyright   : © 2025 Anton Antic
+   License     : GNU GPL, version 2 or above
+
+   Maintainer  : Anton Antic <[email protected]>
+   Stability   : alpha
+   Portability : portable
+
+Tests for the PPTX reader.
+-}
+module Tests.Readers.Pptx (tests) where
+
+import Data.Algorithm.Diff (getDiff)
+import qualified Data.ByteString as BS
+import qualified Data.ByteString.Lazy as B
+import qualified Data.Text as T
+import Test.Tasty
+import Test.Tasty.Golden.Advanced
+import Tests.Helpers
+import Text.Pandoc
+import Text.Pandoc.UTF8 as UTF8
+
+defopts :: ReaderOptions
+defopts = def{ readerExtensions = getDefaultExtensions "pptx" }
+
+testCompare :: String -> FilePath -> FilePath -> TestTree
+testCompare = testCompareWithOpts defopts
+
+nativeDiff :: FilePath -> Pandoc -> Pandoc -> IO (Maybe String)
+nativeDiff normPath expectedNative actualNative
+  | expectedNative == actualNative = return Nothing
+  | otherwise = Just <$> do
+      expected <- T.unpack <$> runIOorExplode (writeNative def expectedNative)
+      actual <- T.unpack <$> runIOorExplode (writeNative def actualNative)
+      let dash = replicate 72 '-'
+      let diff = getDiff (lines actual) (lines expected)
+      return $ '\n' : dash ++
+               "\n--- " ++ normPath ++
+               "\n+++ " ++ "test" ++ "\n" ++
+               showDiff (1,1) diff ++ dash
+
+testCompareWithOpts :: ReaderOptions -> String -> FilePath -> FilePath -> TestTree
+testCompareWithOpts opts testName pptxFP nativeFP =
+  goldenTest
+  testName
+  (do nf <- UTF8.toText <$> BS.readFile nativeFP
+      runIOorExplode (readNative def nf))
+  (do df <- B.readFile pptxFP
+      runIOorExplode (readPptx opts df))
+  (nativeDiff nativeFP)
+  (\a -> runIOorExplode (writeNative def{ writerTemplate = Just mempty} a)
+            >>= BS.writeFile nativeFP . UTF8.fromText)
+
+tests :: [TestTree]
+tests = [ testGroup "basic"
+          [ testCompare
+            "text extraction"
+            "pptx-reader/basic.pptx"
+            "pptx-reader/basic.native"
+          ]
+        ]
diff --git a/test/pptx-reader/basic.native b/test/pptx-reader/basic.native
new file mode 100644
index 000000000..954cb9345
--- /dev/null
+++ b/test/pptx-reader/basic.native
@@ -0,0 +1,149 @@
+[ Header 2 ( "slide-1" , [] , [] ) [ Str "LLMs" ]
+, BulletList
+    [ [ Plain
+          [ Str
+              "Provider  \61664 Available LLMs \8211 who manages? How?"
+          ]
+      ]
+    , [ Plain
+          [ Str
+              "EW maintained list of \8220approved\8221 LLMs for Universal workers"
+          ]
+      ]
+    , [ Plain
+          [ Str
+              "Rebuilding of UWs to the \8220Newgen\8221 thing completely"
+          ]
+      ]
+    , [ Plain [ Str "Streaming support" ] ]
+    , [ Plain [ Str "Multimodal (voice streaming) models?" ] ]
+    ]
+, Header
+    2
+    ( "slide-2" , [] , [] )
+    [ Str "Everworker   venn   diagram" ]
+, Para [ Str "SKILLS" ]
+, Para [ Str "" ]
+, Para [ Str "Specialized Workers / Workflows:" ]
+, Para [ Str "" ]
+, Para [ Str "n8n, UI Path, " ]
+, Para [ Str "other RPA" ]
+, Para [ Str "BRAINS" ]
+, Para [ Str "" ]
+, Para [ Str "Universal Workers / AI Agents:" ]
+, Para [ Str "" ]
+, Para [ Str "openai , anthropic," ]
+, Para [ Str "Crew AI, other " ]
+, Para [ Str "\8220AI natives\8221" ]
+, Para [ Str "KNOWLEDGE " ]
+, Para [ Str "" ]
+, Para [ Str "Data / " ]
+, Para [ Str "RAG Pipelines" ]
+, Para [ Str "" ]
+, Para
+    [ Str "Vector DBs, specialized data prep vendors, \8230" ]
+, Para [ Str "glean" ]
+, Para [ Str "EW" ]
+, Header 2 ( "slide-3" , [] , [] ) [ Str "Table" ]
+, Table
+    ( "" , [] , [] )
+    (Caption Nothing [])
+    [ ( AlignDefault , ColWidthDefault )
+    , ( AlignDefault , ColWidthDefault )
+    , ( AlignDefault , ColWidthDefault )
+    ]
+    (TableHead
+       ( "" , [] , [] )
+       [ Row
+           ( "" , [] , [] )
+           [ Cell
+               ( "" , [] , [] )
+               AlignDefault
+               (RowSpan 1)
+               (ColSpan 1)
+               [ Plain [ Str "Col1" ] ]
+           , Cell
+               ( "" , [] , [] )
+               AlignDefault
+               (RowSpan 1)
+               (ColSpan 1)
+               [ Plain [ Str "Col2" ] ]
+           , Cell
+               ( "" , [] , [] )
+               AlignDefault
+               (RowSpan 1)
+               (ColSpan 1)
+               [ Plain [ Str "Col3" ] ]
+           ]
+       ])
+    [ TableBody
+        ( "" , [] , [] )
+        (RowHeadColumns 0)
+        []
+        [ Row
+            ( "" , [] , [] )
+            [ Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "Name" ] ]
+            , Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "Anton" ] ]
+            , Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "Antich" ] ]
+            ]
+        , Row
+            ( "" , [] , [] )
+            [ Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "Age" ] ]
+            , Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "23" ] ]
+            , Cell
+                ( "" , [] , [] )
+                AlignDefault
+                (RowSpan 1)
+                (ColSpan 1)
+                [ Plain [ Str "years" ] ]
+            ]
+        ]
+    ]
+    (TableFoot ( "" , [] , [] ) [])
+, Para
+    [ Image
+        ( "" , [] , [] ) [] ( "ppt/media/image1.png" , "Picture 6" )
+    ]
+, Header 2 ( "slide-4" , [] , [] ) [ Str "Smart Art" ]
+, Div
+    ( ""
+    , [ "smartart" , "chevron2" ]
+    , [ ( "layout" , "chevron2" ) ]
+    )
+    [ Para [ Strong [ Str "First" ] ]
+    , BulletList
+        [ [ Plain [ Str "another" ] ]
+        , [ Plain [ Str "subtitle" ] ]
+        ]
+    , Para [ Strong [ Str "Second" ] ]
+    , BulletList
+        [ [ Plain [ Str "and yet again" ] ]
+        , [ Plain [ Str "yet more" ] ]
+        ]
+    ]
+]
diff --git a/test/pptx-reader/basic.pptx b/test/pptx-reader/basic.pptx
new file mode 100644
index 000000000..44caef9c3
--- /dev/null
+++ b/test/pptx-reader/basic.pptx
diff --git a/test/test-pandoc.hs b/test/test-pandoc.hs
index 80d4ada7f..0d04b361f 100644
--- a/test/test-pandoc.hs
+++ b/test/test-pandoc.hs
@@ -12,6 +12,7 @@ import qualified Tests.Command
 import qualified Tests.Old
 import qualified Tests.Readers.Creole
 import qualified Tests.Readers.Docx
+import qualified Tests.Readers.Pptx
 import qualified Tests.Readers.DokuWiki
 import qualified Tests.Readers.EPUB
 import qualified Tests.Readers.FB2
@@ -95,6 +96,7 @@ tests pandocPath = testGroup "pandoc tests"
           , testGroup "RST" Tests.Readers.RST.tests
           , testGroup "RTF" Tests.Readers.RTF.tests
           , testGroup "Docx" Tests.Readers.Docx.tests
+          , testGroup "Pptx" Tests.Readers.Pptx.tests
           , testGroup "ODT" Tests.Readers.ODT.tests
           , testGroup "Txt2Tags" Tests.Readers.Txt2Tags.tests
           , testGroup "EPUB" Tests.Readers.EPUB.tests