Merge pull request #180 from Codeuctivity/main

OpenXmlRegex should ignore lastRenderedPageBreak (temporary layout marker does not represent any document text)

Author: stesee

.github/workflows/dotnet.yml

@@ -51,7 +51,7 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - name: Download build artifacts
-        uses: actions/download-artifact@v6
+        uses: actions/download-artifact@v7
         with:
           name: build-artifacts
       - name: NugetPush
@@ -75,7 +75,7 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - name: Download build artifacts
-        uses: actions/download-artifact@v6
+        uses: actions/download-artifact@v7
         with:
           name: build-artifacts
       - name: NugetPush

OpenXmlPowerTools.Tests/DocumentAssemblerTests.cs

@@ -176,6 +176,7 @@ public void DA102_Throws(string name, string data)
 
         [Theory]
         [InlineData("DA025-TemplateDocument.docx", "DA-Data.xml", false)]
+        [InlineData("DA-lastRenderedPageBreak.docx", "DA-lastRenderedPageBreak.xml", false)]
         public void DA103_UseXmlDocument(string name, string data, bool err)
         {
             var sourceDir = new DirectoryInfo("../../../../TestFiles/");

OpenXmlPowerTools.Tests/OpenXmlRegexTests.cs

@@ -197,6 +197,21 @@ public class OpenXmlRegexTests
   </w:body>
 </w:document>";
 
+        private const string LastRenderedPageBreakXmlString =
+@"<w:document xmlns:w=""http://schemas.openxmlformats.org/wordprocessingml/2006/main"">
+  <w:body>
+    <w:p>
+      <w:r>
+        <w:t>ThisIsAParagraphContainingNoNaturalLi</w:t>
+      </w:r>
+      <w:r>
+        <w:lastRenderedPageBreak/>
+        <w:t>neBreaksSoTheLineBreakIsForced.</w:t>
+      </w:r>
+    </w:p>
+  </w:body>
+</w:document>";
+
         private static string InnerText(XContainer e)
         {
             return e.Descendants(W.r)
@@ -365,5 +380,30 @@ public void CanReplaceTextWithFields()
             Assert.Equal(1, count);
             Assert.Equal("As stated in Article {__1} and this Section {__1.1}, this is described in Exhibit 4.", innerText);
         }
+
+        [Fact]
+        public void CanMatchDespiteInvisibleLayoutMarkers()
+        {
+            XDocument partDocument = XDocument.Parse(LastRenderedPageBreakXmlString);
+            XElement p = partDocument.Descendants(W.p).Last();
+
+            using (var stream = new MemoryStream())
+            using (WordprocessingDocument wordDocument = WordprocessingDocument.Create(stream, DocumentType))
+            {
+                MainDocumentPart part = wordDocument.AddMainDocumentPart();
+                part.PutXDocument(partDocument);
+
+                var content = partDocument.Descendants(W.p);
+                var regex = new Regex(@"LineBreak");
+                int count = OpenXmlRegex.Replace(content, regex, "LB", null);
+
+                p = partDocument.Descendants(W.p).Last();
+                string innerText = InnerText(p);
+
+                Assert.Equal(2, count);
+                Assert.Equal("ThisIsAParagraphContainingNoNaturalLBsSoTheLBIsForced.", innerText);
+            }
+        }
+
     }
 }

OpenXmlPowerTools.Tests/UnicodeMapperTests.cs

@@ -124,5 +124,34 @@ public void CanStringifySymbols()
             Assert.Equal(symFromChar1.ToString(SaveOptions.None), symFromChar2.ToString(SaveOptions.None));
             Assert.Equal(symFromChar1.ToString(SaveOptions.None), symFromChar3.ToString(SaveOptions.None));
         }
+
+        private const string LastRenderedPageBreakXmlString =
+@"<w:document xmlns:w=""http://schemas.openxmlformats.org/wordprocessingml/2006/main"">
+  <w:body>
+    <w:p>
+      <w:r>
+        <w:t>ThisIsAParagraphContainingNoNaturalLi</w:t>
+      </w:r>
+      <w:r>
+        <w:lastRenderedPageBreak/>
+        <w:t>neBreaksSoTheLineBreakIsForced.</w:t>
+      </w:r>
+    </w:p>
+  </w:body>
+</w:document>";
+
+        [Fact]
+        public void IgnoresTemporaryLayoutMarkers()
+        {
+            XDocument partDocument = XDocument.Parse(LastRenderedPageBreakXmlString);
+            XElement p = partDocument.Descendants(W.p).Last();
+            string actual = p.Descendants(W.r)
+                .Select(UnicodeMapper.RunToString)
+                .StringConcatenate();
+            // p.Value is "the concatenated text content of this element", which
+            // (in THIS test case, which does not feature any symbols or special
+            // characters) should exactly match the output of UnicodeMapper:
+            Assert.Equal(p.Value, actual);
+        }
     }
 }

OpenXmlPowerTools/OpenXmlRegex.cs

@@ -446,7 +446,7 @@ private static object WmlSearchAndReplaceTransform(XNode node, Regex regex, stri
             if (element.Name == W.r)
             {
                 return element.Elements()
-                    .Where(e => e.Name != W.rPr)
+                    .Where(e => e.Name != W.rPr && e.Name != W.lastRenderedPageBreak)
                     .Select(e => e.Name == W.t
                         ? ((string)e).Select(c =>
                            new XElement(W.r,

OpenXmlPowerTools/UnicodeMapper.cs

@@ -99,6 +99,11 @@ public static string RunToString(XElement element)
             {
                 return HorizontalTabulation.ToString();
             }
+            // Ignore temporary layout markers that are not actual document content
+            if (element.Name == W.lastRenderedPageBreak)
+            {
+                return string.Empty;
+            }
 
             if (element.Name == W.fldChar)
             {

TestFiles/DA-lastRenderedPageBreak.docx

@@ -0,0 +1,4 @@
+<TestCase>
+  <noun1>test</noun1>
+  <noun2>emergency</noun2>
+</TestCase>