Improve the implementation of omitMatches so it is not doing n-square…

…d tree traversals, instead it is a single pass.
lovettchris · Sep 27, 2023 · 0472d20 · 0472d20
1 parent c5a98dd
commit 0472d20
Show file tree

Hide file tree

Showing 19 changed files with 324 additions and 85 deletions.
diff --git a/src/Common/Updates.xsd b/src/Common/Updates.xsd
@@ -0,0 +1,70 @@
+<?xml version="1.0" encoding="utf-8"?>
+<xs:schema attributeFormDefault="unqualified" elementFormDefault="qualified"
+           xmlns:xs="http://www.w3.org/2001/XMLSchema">
+  <xs:element name="updates">
+    <xs:complexType>
+      <xs:sequence>
+        <xs:element name="application">
+          <xs:complexType>
+            <xs:sequence>
+              <xs:element name="title" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>The name of the application being updated.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="location" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>The location of the update xml page.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="download" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>Location of the download page.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="installer" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>Location of the installation page.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="history" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>Location of the page showing update history.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="frequency" type="xs:string" >
+                <xs:annotation>
+                  <xs:documentation>The frequency we need to check for updates to the application, any valid TimeSpan.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+            </xs:sequence>
+          </xs:complexType>
+        </xs:element>
+        <xs:element maxOccurs="unbounded" name="version">
+          <xs:annotation>
+            <xs:documentation>This element describes a new version of the application.</xs:documentation>
+          </xs:annotation>
+          <xs:complexType>
+            <xs:choice minOccurs="0" maxOccurs="unbounded" >
+              <xs:element name="feature" type="xs:string">
+                <xs:annotation>
+                  <xs:documentation>Description of a new feature added in this version.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+              <xs:element name="bug" type="xs:string" >
+                <xs:annotation>
+                  <xs:documentation>Description of a bug fixed in this version.</xs:documentation>
+                </xs:annotation>
+              </xs:element>
+            </xs:choice>
+            <xs:attribute name="number" type="xs:string" use="required">
+              <xs:annotation>
+                <xs:documentation>The version number.</xs:documentation>
+              </xs:annotation>
+            </xs:attribute>
+          </xs:complexType>
+        </xs:element>
+      </xs:sequence>
+    </xs:complexType>
+  </xs:element>
+</xs:schema>
diff --git a/src/Common/Updates.xslt b/src/Common/Updates.xslt
@@ -0,0 +1,76 @@
+<?xml version="1.0" encoding="UTF-8" ?>
+<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+  <xsl:output method="html" indent="yes"/>
+  <xsl:template match="/">
+    <html>
+      <head>
+        <title>
+          <xsl:value-of select="updates/application/title"/>
+        </title>
+        <style>
+          body, th, td { font-family: Verdana; font-size:x-small;}
+        </style>
+      </head>
+      <body>
+        <center>
+          <table width="600"  border="0" cellpadding="0" cellspacing="0">
+            <tr>
+              <td align="center" bgcolor="teal" style="height: 29px">
+                <span style="color:white;background:teal;font-size:18pt">
+                  <xsl:value-of select="updates/application/title"/> - Change History
+                </span>
+              </td>
+            </tr>
+            <tr>
+              <td>
+                <br/>
+                <p>
+                </p>
+              </td>
+            </tr>
+            <tr>
+              <td>
+                <table border="1" cellpadding="2" >
+                  <xsl:apply-templates/>
+                </table>
+              </td>
+            </tr>
+          </table>
+        </center>
+      </body>
+    </html>
+  </xsl:template>
+  <xsl:template match="updates">
+    <xsl:apply-templates/>
+  </xsl:template>
+  <xsl:template match="application">
+  </xsl:template>
+  <xsl:template match="version">
+    <xsl:variable name="color">background:teal;color:white</xsl:variable>
+    <tr>
+      <td style="{$color}"> </td>
+      <td style="{$color}"  align="center">
+        Version <xsl:value-of select="@number"/>
+      </td>
+    </tr>
+    <xsl:apply-templates/>
+  </xsl:template>
+  <xsl:template match="feature">
+    <xsl:variable name="color">background:MediumTurquoise</xsl:variable>
+    <tr>
+      <td style="{$color}" valign="top">Feature</td>
+      <td>
+        <xsl:value-of select="."/>
+      </td>
+    </tr>
+  </xsl:template>
+  <xsl:template match="bug">
+    <xsl:variable name="color">background:LightPink</xsl:variable>
+    <tr>
+      <td style="{$color}" valign="top">Bug</td>
+      <td>
+        <xsl:value-of select="."/>
+      </td>
+    </tr>
+  </xsl:template>
+</xsl:stylesheet>
diff --git a/src/Common/changes.xml b/src/Common/changes.xml
@@ -1,6 +1,17 @@
 <?xml version="1.0" encoding="utf-8"?>
 <?xml-stylesheet type="text/xsl" href="Updates.xslt"?>
 <updates xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="Updates.xsd">
+  <application>
+    <title>Microsoft XML Diff</title>
+    <location>https://raw.githubusercontent.com/lovettchris/xmldiff/master/src/Common/changes.xml</location>
+    <download>https://www.nuget.org/packages/LovettSoftware.XmlDiff</download>
+    <installer>https://www.nuget.org/packages/LovettSoftware.XmlDiff</installer>
+    <history>https://github.com/microsoft/XmlNotepad/blob/master/src/Updates/Updates.xml</history>
+    <frequency>1.00:00:00</frequency>
+  </application>
+  <version number="1.1.0">
+    <feature>Thanks to Mark Roberts for a cool new feature that omits identical output to make the diff HTML output scale better on huge XML files.</feature>
+  </version>
   <version number="1.0.8">
     <bug>Add back strong naming for XmlDiffPatch.dll</bug>
   </version>

diff --git a/src/Common/version.props b/src/Common/version.props
@@ -2,8 +2,8 @@
   <PropertyGroup>
     <Company>Lovett Software</Company>
     <Copyright>Copyright © Lovett Software</Copyright>  
-    <FileVersion>1.0.8</FileVersion>
-    <AssemblyVersion>1.0.8</AssemblyVersion>
-    <Version>1.0.8</Version>
+    <FileVersion>1.1.0</FileVersion>
+    <AssemblyVersion>1.1.0</AssemblyVersion>
+    <Version>1.1.0</Version>
   </PropertyGroup>
 </Project>
diff --git a/src/Common/version.txt b/src/Common/version.txt
@@ -1 +1 @@
-1.0.8
+1.1.0
diff --git a/src/UnitTests/UnitTest1.cs b/src/UnitTests/UnitTest1.cs
@@ -79,6 +79,27 @@ public void SideBySideDiffView()
             }
         }
 
+        [Fact]
+        public void SideBySideDiffViewCompact()
+        {
+            using (var col = new TempFileCollection())
+            {
+                var xmlSource = col.CreateTempFile("<root id='3'><apple></apple><banana><temp/></banana><elephant size='big'/></root>");
+                var xmlChanged = col.CreateTempFile("<root id='3'><apple></apple><banana></banana><carrot/><elephant size='big'/></root>");
+
+                var view = new XmlDiffView();
+                var options = XmlDiffOptions.IgnoreChildOrder | XmlDiffOptions.IgnoreWhitespace;
+                var results = view.DifferencesSideBySideAsHtml(xmlSource, xmlChanged, false, options, true);
+
+                var diff = results.ReadToEnd();
+                Assert.Contains("root", diff);
+                Assert.Contains("banana", diff);
+                Assert.Contains("&lt;temp", diff);
+                Assert.DoesNotContain("apple", diff);
+                Assert.DoesNotContain("elephant", diff);
+            }
+        }
+
         private string ToComparibleString(XmlDocument doc)
         {
             // avoid comparing the hash.

diff --git a/src/XmlDiffView/XmlDiff.nuspec b/src/XmlDiffView/XmlDiff.nuspec
@@ -2,7 +2,7 @@
 <package >
   <metadata>
     <id>LovettSoftware.XmlDiff</id>
-    <version>1.0.9</version>
+    <version>1.1.0</version>
     <authors>Chris Lovett</authors>
     <description>A library that compares and merges XML files.</description>
     <projectUrl>https://github.com/lovettchris/xmldiff</projectUrl>

diff --git a/src/XmlDiffView/XmlDiffView.cs b/src/XmlDiffView/XmlDiffView.cs
@@ -425,21 +425,24 @@ public XmlDiffViewResults DifferencesAsFormattedText(
         /// <param name="resultHtmlViewFile">the html output file</param>
         /// <param name="fragment">the file is only an Xml fragment</param>
         /// <param name="options">comparison filtering options</param>
+        /// <param name="omitIdenticalHtmlOutput">omit html output for identical xml elements</param>
         /// <returns>Differences were not found after filtering.</returns>
         public bool DifferencesSideBySideAsHtml(
             string sourceXmlFile,
             string changedXmlFile,
             string resultHtmlViewFile,
             bool fragment,
-            XmlDiffOptions options)
+            XmlDiffOptions options,
+            bool omitIdenticalHtmlOutput = false)
         {
             bool identicalData = this.DifferencesSideBySideAsHtml(
                 sourceXmlFile,
                 changedXmlFile,
                 resultHtmlViewFile,
                 fragment,
                 true,
-                options);
+                options,
+                omitIdenticalHtmlOutput);
 
             return identicalData;
         }
@@ -453,14 +456,16 @@ public bool DifferencesSideBySideAsHtml(
         /// <param name="fragment">the file is only an Xml fragment</param>
         /// <param name="appendToOutputFile">Append to existing output file</param>
         /// <param name="options">comparison filtering options</param>
+        /// <param name="omitIdenticalHtmlOutput">omit html output for identical xml elements</param>
         /// <returns>Differences were not found after filtering.</returns>
         public bool DifferencesSideBySideAsHtml(
             string sourceXmlFile,
             string changedXmlFile,
             string resultHtmlViewFile,
             bool fragment,
             bool appendToOutputFile,
-            XmlDiffOptions options)
+            XmlDiffOptions options,
+            bool omitIdenticalHtmlOutput = false)
         {
             // Append to the specified output file.
             FileMode mode;
@@ -481,11 +486,12 @@ public bool DifferencesSideBySideAsHtml(
             bool identicalData;
             try
             {
-                identicalData = this.DifferencesSideBySideAsHtml(
+                identicalData = this.InternalDifferencesSideBySideAsHtml(
                     sourceXmlFile,
                     changedXmlFile,
                     fragment,
                     options,
+                    omitIdenticalHtmlOutput,
                     this.outputData);
             }
             finally
@@ -503,12 +509,14 @@ public bool DifferencesSideBySideAsHtml(
         /// <param name="changedXmlFile">the actual (or target) file</param>
         /// <param name="fragment">the file is only an Xml fragment</param>
         /// <param name="options">comparison filtering options</param>
+        /// <param name="omitIdenticalHtmlOutput">omit html output for identical xml elements</param>
         /// <returns>Differences were not found after filtering.</returns>
         public XmlDiffViewResults DifferencesSideBySideAsHtml(
             string sourceXmlFile,
             string changedXmlFile,
             bool fragment,
-            XmlDiffOptions options)
+            XmlDiffOptions options,
+            bool omitIdenticalHtmlOutput = false)
         {
             MemoryStream data = new MemoryStream();
 
@@ -521,11 +529,12 @@ public XmlDiffViewResults DifferencesSideBySideAsHtml(
             bool identicalData = false;
             try
             {
-                identicalData = this.DifferencesSideBySideAsHtml(
+                identicalData = this.InternalDifferencesSideBySideAsHtml(
                     sourceXmlFile,
                     changedXmlFile,
                     fragment,
                     options,
+                    omitIdenticalHtmlOutput,
                     this.outputData);
 
             }
@@ -556,12 +565,18 @@ public XmlDiffViewResults DifferencesSideBySideAsHtml(
         /// TextWriter object (which may be a file).
         /// </summary>
         /// <param name="htmlOutput">Data stream for output</param>
-        public void GetHtml(TextWriter htmlOutput, bool omitMatches = false)
+        /// <param name="omitMatches">Omit matching lines to compress the size of the HTML output</param>
+        /// <param name="indentPoints">HTML indent to show in points - default is padding-left: 10pt;</param>
+        public void GetHtml(TextWriter htmlOutput, bool omitMatches = false, int indentPoints = 10)
         {
             LastVisitedOpId = 0;
             XmlDiffViewNode.ResetLineNumbers();
             XmlTextWriter writer = new XmlTextWriter(htmlOutput);
-            this.viewDocument.DrawHtml(writer, 10, new XmlDiffViewRenderState { OmitMatches = omitMatches });
+            if (omitMatches)
+            {
+                this.viewDocument.PruneMatchingElements();
+            }
+            this.viewDocument.DrawHtml(writer, indentPoints);
         }
 
         #endregion
@@ -907,13 +922,15 @@ private bool GetDifferencesAsFormattedText(
         /// <param name="changedXmlFile">actual file</param>
         /// <param name="fragment">xml data fragment</param>
         /// <param name="options">Comparison options</param>
+        /// <param name="omitIdenticalHtmlOutput">omit html output for identical xml elements</param>
         /// <param name="resultHtml">output data</param>
         /// <returns>data is identical</returns>
-        private bool DifferencesSideBySideAsHtml(
+        private bool InternalDifferencesSideBySideAsHtml(
             string sourceXmlFile,
             string changedXmlFile,
             bool fragment,
             XmlDiffOptions options,
+            bool omitIdenticalHtmlOutput,
             TextWriter resultHtml)
         {
             bool identicalData = this.MarkupBaselineWithChanges(
@@ -929,7 +946,7 @@ private bool DifferencesSideBySideAsHtml(
                 identicalData,
                 resultHtml);
 
-            this.GetHtml(resultHtml);
+            this.GetHtml(resultHtml, omitIdenticalHtmlOutput);
 
             this.SideBySideHtmlFooter(resultHtml);
 

diff --git a/src/XmlDiffView/XmlDiffViewAttribute.cs b/src/XmlDiffView/XmlDiffViewAttribute.cs
@@ -249,7 +249,7 @@ internal override XmlDiffViewNode Clone(bool deep)
         /// <param name="writer">output stream</param>
         /// <param name="indent">size of indent</param>
         [Obsolete("This method should never be called", true)]
-        internal override void DrawHtml(XmlWriter writer, int indent, XmlDiffViewRenderState renderState)
+        internal override void DrawHtml(XmlWriter writer, int indent)
         {
             throw new Exception("This method should never be called.");
         }

diff --git a/src/XmlDiffView/XmlDiffViewCharData.cs b/src/XmlDiffView/XmlDiffViewCharData.cs
@@ -122,7 +122,7 @@ internal override XmlDiffViewNode Clone(bool deep)
         /// </summary>
         /// <param name="writer">output stream</param>
         /// <param name="indent">number of indentations</param>
-        internal override void DrawHtml(XmlWriter writer, int indent, XmlDiffViewRenderState renderState)
+        internal override void DrawHtml(XmlWriter writer, int indent)
         {
             if (Operation == XmlDiffViewOperation.Change)
             {

diff --git a/src/XmlDiffView/XmlDiffViewDocument.cs b/src/XmlDiffView/XmlDiffViewDocument.cs
@@ -78,9 +78,9 @@ internal override XmlDiffViewNode Clone(bool deep)
         /// <param name="writer">output stream</param>
         /// <param name="indent">number of indentations</param>
         /// <param name="renderState"></param>
-        internal override void DrawHtml(XmlWriter writer, int indent, XmlDiffViewRenderState renderState) 
+        internal override void DrawHtml(XmlWriter writer, int indent) 
         {
-            HtmlDrawChildNodes(writer, indent, renderState);
+            HtmlDrawChildNodes(writer, indent);
         }
 
         /// <summary>

diff --git a/src/XmlDiffView/XmlDiffViewDocumentType.cs b/src/XmlDiffView/XmlDiffViewDocumentType.cs
@@ -183,7 +183,7 @@ internal override XmlDiffViewNode Clone(bool deep)
         /// </summary>
         /// <param name="writer">output stream</param>
         /// <param name="indent">number of indentations</param>
-        internal override void DrawHtml(XmlWriter writer, int indent, XmlDiffViewRenderState renderState) 
+        internal override void DrawHtml(XmlWriter writer, int indent) 
         {
             if (Operation == XmlDiffViewOperation.Change) 
             {