C# Document.GetText方法代码示例

        static void Main(string[] args)
        {
            // Check for license and apply if exists
            string licenseFile = AppDomain.CurrentDomain.BaseDirectory + "Aspose.Words.lic";
            if (File.Exists(licenseFile))
            {
                // Apply Aspose.Words API License
                Aspose.Words.License license = new Aspose.Words.License();
                // Place license file in Bin/Debug/ Folder
                license.SetLicense("Aspose.Words.lic");
            }

            Document doc = new Document("../../data/document.doc");

            // Enter a dummy field into the document.
            DocumentBuilder builder = new DocumentBuilder(doc);
            builder.InsertField("MERGEFIELD Field");

            // GetText will retrieve all field codes and special characters
            Console.WriteLine("GetText() Result: " + doc.GetText());

            string text = doc.GetText();
            text = text.Replace(ControlChar.Cr, ControlChar.CrLf);

            Console.WriteLine("Replaced text Result: " + text);
        }

        public void AddRemove()
        {
            //ExStart
            //ExFor:Document.Sections
            //ExFor:Section.Clone
            //ExFor:SectionCollection
            //ExFor:NodeCollection.RemoveAt(Int32)
            //ExSummary:Shows how to add/remove sections in a document.
            // Open the document.
            Document doc = new Document(MyDir + "Section.AddRemove.doc");

            // This shows what is in the document originally. The document has two sections.
            Console.WriteLine(doc.GetText());

            // Delete the first section from the document
            doc.Sections.RemoveAt(0);

            // Duplicate the last section and append the copy to the end of the document.
            int lastSectionIdx = doc.Sections.Count - 1;
            Section newSection = doc.Sections[lastSectionIdx].Clone();
            doc.Sections.Add(newSection);

            // Check what the document contains after we changed it.
            Console.WriteLine(doc.GetText());
            //ExEnd

            Assert.AreEqual("Hello2\x000cHello2\x000c", doc.GetText());
        }

        public void BodyEnsureMinimum()
        {
            //ExStart
            //ExFor:Section.Body
            //ExFor:Body.EnsureMinimum
            //ExSummary:Clears main text from all sections from the document leaving the sections themselves.

            // Open a document.
            Document doc = new Document(MyDir + "Section.BodyEnsureMinimum.doc");

            // This shows what is in the document originally. The document has two sections.
            Console.WriteLine(doc.GetText());

            // Loop through all sections in the document.
            foreach (Section section in doc.Sections)
            {
                // Each section has a Body node that contains main story (main text) of the section.
                Body body = section.Body;

                // This clears all nodes from the body.
                body.RemoveAllChildren();

                // Technically speaking, for the main story of a section to be valid, it needs to have
                // at least one empty paragraph. That's what the EnsureMinimum method does.
                body.EnsureMinimum();
            }

            // Check how the content of the document looks now.
            Console.WriteLine(doc.GetText());
            //ExEnd

            Assert.AreEqual("\x000c\x000c", doc.GetText());
        }

        static void Main(string[] args)
        {
            Document doc = new Document("../../data/document.doc");

            // Enter a dummy field into the document.
            DocumentBuilder builder = new DocumentBuilder(doc);
            builder.InsertField("MERGEFIELD Field");

            // GetText will retrieve all field codes and special characters
            Console.WriteLine("GetText() Result: " + doc.GetText());

            string text = doc.GetText();
            text = text.Replace(ControlChar.Cr, ControlChar.CrLf);

            Console.WriteLine("Replaced text Result: " + text);
        }

 public string Read(Stream inputStream)
 {
     try
     {
         var document = new Document(inputStream);
         return document.GetText();
     }
     catch (Exception ex)
     {
         throw new ReadException(ErrorMessages.ReadTextFailed, ex);
     }
 }

        public void DeleteSelection()
        {
            //ExStart
            //ExFor:Node.Range
            //ExFor:Range.Delete
            //ExSummary:Shows how to delete a section from a Word document.
            // Open Word document.
            Document doc = new Document(MyDir + "Range.DeleteSection.doc");

            // The document contains two sections. Each section has a paragraph of text.
            Console.WriteLine(doc.GetText());

            // Delete the first section from the document.
            doc.Sections[0].Range.Delete();

            // Check the first section was deleted by looking at the text of the whole document again.
            Console.WriteLine(doc.GetText());
            //ExEnd

            Assert.AreEqual("Hello2\x000c", doc.GetText());
        }

        public static void Run()
        {
            // ExStart:ExtractTextOnly
            Document doc = new Document();

            // Enter a dummy field into the document.
            DocumentBuilder builder = new DocumentBuilder(doc);
            builder.InsertField("MERGEFIELD Field");

            // GetText will retrieve all field codes and special characters
            Console.WriteLine("GetText() Result: " + doc.GetText());

            // ToString will export the node to the specified format. When converted to text it will not retrieve fields code 
            // Or special characters, but will still contain some natural formatting characters such as paragraph markers etc. 
            // This is the same as "viewing" the document as if it was opened in a text editor.
            Console.WriteLine("ToString() Result: " + doc.ToString(SaveFormat.Text));
            // ExEnd:ExtractTextOnly            
        }

        public void ReplaceSimple()
        {
            //ExStart
            //ExFor:Range.Replace(String,String,Boolean,Boolean)
            //ExSummary:Simple find and replace operation.
            // Open the document.
            Document doc = new Document(MyDir + "Range.ReplaceSimple.doc");

            // Check the document contains what we are about to test.
            Console.WriteLine(doc.FirstSection.Body.Paragraphs[0].GetText());

            // Replace the text in the document.
            doc.Range.Replace("_CustomerName_", "James Bond", false, false);

            // Save the modified document.
            doc.Save(MyDir + @"\Artifacts\Range.ReplaceSimple.doc");
            //ExEnd

            Assert.AreEqual("Hello James Bond,\r\x000c", doc.GetText());
        }

        public void DocumentByteArray()
        {
            //ExStart
            //ExId:DocumentToFromByteArray
            //ExSummary:Shows how to convert a document object to an array of bytes and back into a document object again.
            // Load the document.
            Document doc = new Document(MyDir + "Document.doc");

            // Create a new memory stream.
            MemoryStream outStream = new MemoryStream();
            // Save the document to stream.
            doc.Save(outStream, SaveFormat.Docx);

            // Convert the document to byte form.
            byte[] docBytes = outStream.ToArray();

            // The bytes are now ready to be stored/transmitted.

            // Now reverse the steps to load the bytes back into a document object.
            MemoryStream inStream = new MemoryStream(docBytes);

            // Load the stream into a new document object.
            Document loadDoc = new Document(inStream);
            //ExEnd

            Assert.AreEqual(doc.GetText(), loadDoc.GetText());
        }

        public void TrimWhiteSpaces(bool option, string expectedText)
        {
            Document doc = new Document();
            DocumentBuilder builder = new DocumentBuilder(doc);
            
            builder.InsertField("MERGEFIELD field", null);

            doc.MailMerge.TrimWhitespaces = option;
            doc.MailMerge.Execute(new[] { "field" }, new object[] { " first line\rsecond line\rthird line " });

            Assert.AreEqual(expectedText, doc.GetText());
        }

 private string ExtractNestedTypes(string source, bool staticOnly)
 {
     Func<TypeDeclaration, bool> predicate = null;
     Func<TypeDeclaration, TextRange> selector = null;
     Document document = new Document();
     document.set_Language(new CSharpSyntaxLanguage());
     document.set_Text(source);
     IAstNode root = null;
     TextRange[] rangeArray = null;
     ClassDeclaration declaration = null;
     for (int i = 0; i < 50; i++)
     {
         if (i > 0)
         {
             Thread.Sleep(50);
         }
         root = document.get_SemanticParseData() as IAstNode;
         if (root != null)
         {
             declaration = root.get_ChildNodes().OfType<ClassDeclaration>().FirstOrDefault<ClassDeclaration>(c => c.get_FullName() == "UserQuery");
             if (declaration != null)
             {
                 if (i < 3)
                 {
                     i = 0x2f;
                 }
                 else
                 {
                     i = 0x2d;
                 }
                 if (predicate == null)
                 {
                     predicate = m => !staticOnly || ((m is ClassDeclaration) && ((m.get_Modifiers() & 0x100000) == 0x100000));
                 }
                 if (selector == null)
                 {
                     selector = m => (((m.get_AttributeSections() == null) || (m.get_AttributeSections().Count == 0)) || ((m.get_AttributeSections().get_Item(0).get_StartOffset() < 0) || (m.get_AttributeSections().get_Item(0).get_StartOffset() <= root.get_StartOffset()))) ? m.get_TextRange() : new TextRange(m.get_AttributeSections().get_Item(0).get_StartOffset(), m.get_TextRange().get_EndOffset());
                 }
                 rangeArray = declaration.get_Members().OfType<TypeDeclaration>().Where<TypeDeclaration>(predicate).Select<TypeDeclaration, TextRange>(selector).ToArray<TextRange>();
                 if (rangeArray.Length > 0)
                 {
                     break;
                 }
             }
         }
     }
     string text = document.GetText(0);
     StringBuilder builder = new StringBuilder();
     StringBuilder builder2 = new StringBuilder();
     int startIndex = 0;
     foreach (TextRange range in rangeArray)
     {
         builder.Append(text.Substring(startIndex, range.get_StartOffset() - startIndex));
         int introduced18 = range.get_StartOffset();
         int num4 = text.Take<char>((introduced18 + range.get_Length())).Count<char>(c => (c == '\n')) + 1;
         builder.Append("\n#line " + num4 + "\n");
         num4 = text.Take<char>(range.get_StartOffset()).Count<char>(c => (c == '\n')) + 1;
         object[] objArray = new object[5];
         objArray[0] = "#line ";
         objArray[1] = num4;
         objArray[2] = "\n";
         int introduced19 = range.get_StartOffset();
         objArray[3] = text.Substring(introduced19, range.get_Length());
         objArray[4] = "\n";
         builder2.Append(string.Concat(objArray));
         startIndex = range.get_EndOffset();
     }
     builder.Append(text.Substring(startIndex));
     return (builder.ToString() + "\n" + builder2.ToString());
 }

        public void OpenFromStream()
        {
            //ExStart
            //ExFor:Document.#ctor(Stream)
            //ExId:OpenFromStream
            //ExSummary:Opens a document from a stream.
            // Open the stream. Read only access is enough for Aspose.Words to load a document.
            Stream stream = File.OpenRead(MyDir + "Document.doc");

            // Load the entire document into memory.
            Document doc = new Document(stream);

            // You can close the stream now, it is no longer needed because the document is in memory.
            stream.Close();

            // ... do something with the document
            //ExEnd

            Assert.AreEqual("Hello World!\x000c", doc.GetText());
        }

        public void DocumentGetText_ToTxt()
        {
            //ExStart
            //ExFor:CompositeNode.GetText
            //ExFor:Node.ToTxt
            //ExId:NodeTxtExportDifferences
            //ExSummary:Shows the difference between calling the GetText and ToTxt methods on a node.
            Document doc = new Document();

            // Enter a dummy field into the document.
            DocumentBuilder builder = new DocumentBuilder(doc);
            builder.InsertField("MERGEFIELD Field");

            // GetText will retrieve all field codes and special characters
            Console.WriteLine("GetText() Result: " + doc.GetText());

            // ToTxt will not retrieve fields code or special characters, but will still contain some natural formatting characters
            // such as paragraph markers etc. This is the same as "viewing" the document as if it was opened in a text editor
            // Only the results of fields are shown without any internal codes or characters
            Console.WriteLine("ToTxt() Result: " + doc.ToTxt());
            //ExEnd
        }

        public void DocumentGetText_ToString()
        {
            //ExStart
            //ExFor:CompositeNode.GetText
            //ExFor:Node.ToString(SaveFormat)
            //ExId:NodeTxtExportDifferences
            //ExSummary:Shows the difference between calling the GetText and ToString methods on a node.
            Document doc = new Document();

            // Enter a dummy field into the document.
            DocumentBuilder builder = new DocumentBuilder(doc);
            builder.InsertField("MERGEFIELD Field");

            // GetText will retrieve all field codes and special characters
            Console.WriteLine("GetText() Result: " + doc.GetText());

            // ToString will export the node to the specified format. When converted to text it will not retrieve fields code 
            // or special characters, but will still contain some natural formatting characters such as paragraph markers etc. 
            // This is the same as "viewing" the document as if it was opened in a text editor.
            Console.WriteLine("ToString() Result: " + doc.ToString(SaveFormat.Text));
            //ExEnd
        }

        public void CreateFromScratch()
        {
            //ExStart
            //ExFor:Node.GetText
            //ExFor:CompositeNode.RemoveAllChildren
            //ExFor:CompositeNode.AppendChild
            //ExFor:Section
            //ExFor:Section.#ctor
            //ExFor:Section.PageSetup
            //ExFor:PageSetup.SectionStart
            //ExFor:PageSetup.PaperSize
            //ExFor:SectionStart
            //ExFor:PaperSize
            //ExFor:Body
            //ExFor:Body.#ctor
            //ExFor:Paragraph
            //ExFor:Paragraph.#ctor
            //ExFor:Paragraph.ParagraphFormat
            //ExFor:ParagraphFormat
            //ExFor:ParagraphFormat.StyleName
            //ExFor:ParagraphFormat.Alignment
            //ExFor:ParagraphAlignment
            //ExFor:Run
            //ExFor:Run.#ctor(DocumentBase)
            //ExFor:Run.Text
            //ExFor:Inline.Font
            //ExSummary:Creates a simple document from scratch using the Aspose.Words object model.

            // Create an "empty" document. Note that like in Microsoft Word,
            // the empty document has one section, body and one paragraph in it.
            Document doc = new Document();

            // This truly makes the document empty. No sections (not possible in Microsoft Word).
            doc.RemoveAllChildren();

            // Create a new section node.
            // Note that the section has not yet been added to the document,
            // but we have to specify the parent document.
            Section section = new Section(doc);

            // Append the section to the document.
            doc.AppendChild(section);

            // Lets set some properties for the section.
            section.PageSetup.SectionStart = SectionStart.NewPage;
            section.PageSetup.PaperSize = PaperSize.Letter;

            // The section that we created is empty, lets populate it. The section needs at least the Body node.
            Body body = new Body(doc);
            section.AppendChild(body);

            // The body needs to have at least one paragraph.
            // Note that the paragraph has not yet been added to the document,
            // but we have to specify the parent document.
            // The parent document is needed so the paragraph can correctly work
            // with styles and other document-wide information.
            Paragraph para = new Paragraph(doc);
            body.AppendChild(para);

            // We can set some formatting for the paragraph
            para.ParagraphFormat.StyleName = "Heading 1";
            para.ParagraphFormat.Alignment = ParagraphAlignment.Center;

            // So far we have one empty paragraph in the document.
            // The document is valid and can be saved, but lets add some text before saving.
            // Create a new run of text and add it to our paragraph.
            Run run = new Run(doc);
            run.Text = "Hello World!";
            run.Font.Color = System.Drawing.Color.Red;
            para.AppendChild(run);

            // As a matter of interest, you can retrieve text of the whole document and
            // see that \x000c is automatically appended. \x000c is the end of section character.
            Console.WriteLine("Hello World!\x000c", doc.GetText());

            // Save the document.
            doc.Save(MyDir + "Section.CreateFromScratch Out.doc");
            //ExEnd

            Assert.AreEqual("Hello World!\x000c", doc.GetText());
        }