Merge pull request #54 from VerifyTests/add-docx-support

add docx support

Author: SimonCropp

.claude/settings.local.json

@@ -6,7 +6,13 @@
       "WebFetch(domain:api.github.com)",
       "Bash(git restore:*)",
       "Bash(dotnet build:*)",
-      "Bash([ -d \"D:\\Code\\VerifyTests\\Verify.OpenXml\\src\\Verify.OpenXml\\Converters\" ])"
+      "Bash([ -d \"D:\\Code\\VerifyTests\\Verify.OpenXml\\src\\Verify.OpenXml\\Converters\" ])",
+      "Bash(ls:*)",
+      "Bash(dotnet run:*)",
+      "Bash(dotnet test:*)",
+      "Bash(for f in *.received.*)",
+      "Bash(do mv \"$f\" \"$f/received/verified\")",
+      "Bash(done)"
     ]
   }
 }

readme.md

@@ -6,16 +6,26 @@
 
 Extends [Verify](https://github.com/VerifyTests/Verify) to allow verification of Excel documents via  [OpenXML](https://github.com/dotnet/Open-XML-SDK/).<!-- singleLineInclude: intro. path: /docs/intro.include.md -->
 
-Converts Excel documents (xlsx) to CSV for verification.
+Supports Excel (xlsx) and Word (docx) documents.
 
 ## Features
 
+### Excel (xlsx)
+
  * Converts workbooks to CSV format for each worksheet
  * Extracts formulas and displays them alongside cell values
  * Captures document metadata (title, subject, creator, keywords, category, etc.)
  * Supports date scrubbing and GUID scrubbing for deterministic tests
  * Generates deterministic XLSX output using DeterministicIoPackaging
 
+### Word (docx)
+
+ * Extracts document text content from paragraphs and tables
+ * Captures document properties (title, subject, creator, keywords, etc.)
+ * Captures custom document properties
+ * Extracts font information
+ * Generates deterministic DOCX output using DeterministicIoPackaging
+
 **See [Milestones](../../milestones?state=closed) for release notes.**
 
 
@@ -100,7 +110,7 @@ public Task VerifySpreadsheetDocument()
 <!-- endSnippet -->
 
 
-### Example snapshot
+#### Example snapshot
 
 <!-- snippet: Samples.VerifyExcel.verified.csv -->
 <a id='snippet-Samples.VerifyExcel.verified.csv'></a>
@@ -115,3 +125,52 @@ public Task VerifySpreadsheetDocument()
 ```
 <sup><a href='/src/Tests/Samples.VerifyExcel.verified.csv#L1-L7' title='Snippet source file'>snippet source</a> | <a href='#snippet-Samples.VerifyExcel.verified.csv' title='Start of snippet'>anchor</a></sup>
 <!-- endSnippet -->
+
+
+### Word
+
+
+#### Verify a file
+
+<!-- snippet: VerifyWord -->
+<a id='snippet-VerifyWord'></a>
+```cs
+[Test]
+public Task VerifyWord() =>
+    VerifyFile("sample.docx");
+```
+<sup><a href='/src/Tests/Samples.cs#L44-L50' title='Snippet source file'>snippet source</a> | <a href='#snippet-VerifyWord' title='Start of snippet'>anchor</a></sup>
+<!-- endSnippet -->
+
+
+#### Verify a Stream
+
+<!-- snippet: VerifyWordStream -->
+<a id='snippet-VerifyWordStream'></a>
+```cs
+[Test]
+public Task VerifyWordStream()
+{
+    var stream = new MemoryStream(File.ReadAllBytes("sample.docx"));
+    return Verify(stream, "docx");
+}
+```
+<sup><a href='/src/Tests/Samples.cs#L64-L73' title='Snippet source file'>snippet source</a> | <a href='#snippet-VerifyWordStream' title='Start of snippet'>anchor</a></sup>
+<!-- endSnippet -->
+
+
+#### Verify a WordprocessingDocument
+
+<!-- snippet: WordprocessingDocument -->
+<a id='snippet-WordprocessingDocument'></a>
+```cs
+[Test]
+public Task VerifyWordprocessingDocument()
+{
+    using var stream = File.OpenRead("sample.docx");
+    using var reader = WordprocessingDocument.Open(stream, false);
+    return Verify(reader);
+}
+```
+<sup><a href='/src/Tests/Samples.cs#L52-L62' title='Snippet source file'>snippet source</a> | <a href='#snippet-WordprocessingDocument' title='Start of snippet'>anchor</a></sup>
+<!-- endSnippet -->

src/Directory.Build.props

@@ -2,7 +2,7 @@
 <Project>
   <PropertyGroup>
     <NoWarn>CS1591;CS0649;CA1416;NU1608;NU1109</NoWarn>
-    <Version>0.1.0</Version>
+    <Version>0.2.0</Version>
     <LangVersion>preview</LangVersion>
     <AssemblyVersion>1.0.0</AssemblyVersion>
     <PackageTags>OpenXML, Verify</PackageTags>
@@ -15,4 +15,4 @@
   <ItemGroup>
     <Using Include="System.ReadOnlySpan&lt;System.Char&gt;" Alias="CharSpan" />
   </ItemGroup>
-</Project>
+</Project>

src/Tests/CreateSampleDocx.csx

@@ -0,0 +1,29 @@
+#r "nuget: DocumentFormat.OpenXml, 3.0.0"
+using DocumentFormat.OpenXml;
+using DocumentFormat.OpenXml.Packaging;
+using DocumentFormat.OpenXml.Wordprocessing;
+
+using (var doc = WordprocessingDocument.Create("sample.docx", WordprocessingDocumentType.Document))
+{
+    doc.PackageProperties.Title = "Sample Document";
+    doc.PackageProperties.Creator = "Test Author";
+    doc.PackageProperties.Subject = "Test Subject";
+    
+    var mainPart = doc.AddMainDocumentPart();
+    mainPart.Document = new Document(
+        new Body(
+            new Paragraph(
+                new Run(
+                    new Text("Hello World! This is a sample Word document.")
+                )
+            ),
+            new Paragraph(
+                new Run(
+                    new Text("This is the second paragraph with some more text.")
+                )
+            )
+        )
+    );
+    mainPart.Document.Save();
+}
+Console.WriteLine("Created sample.docx");

src/Tests/Samples.VerifyWord#00.verified.txt

@@ -0,0 +1,10 @@
+{
+  Properties: {
+    Creator: Test Author,
+    Subject: Test Subject,
+    Title: Sample Document
+  },
+  Text:
+Hello World! This is a sample Word document.
+This is the second paragraph with some more text.
+}

src/Tests/Samples.VerifyWord#01.verified.txt

@@ -0,0 +1,2 @@
+Hello World! This is a sample Word document.
+This is the second paragraph with some more text.

src/Tests/Samples.VerifyWord.verified.docx

@@ -0,0 +1,10 @@
+{
+  Properties: {
+    Creator: Test Author,
+    Subject: Test Subject,
+    Title: Sample Document
+  },
+  Text:
+Hello World! This is a sample Word document.
+This is the second paragraph with some more text.
+}

src/Tests/Samples.VerifyWordStream#00.verified.txt

@@ -0,0 +1,2 @@
+Hello World! This is a sample Word document.
+This is the second paragraph with some more text.