OpenOffice的使用.NET:如何遍历所有throught段落和文本阅读 [英] OpenOffice with .NET: how to iterate throught all paragraphs and read text

查看:195
本文介绍了OpenOffice的使用.NET:如何遍历所有throught段落和文本阅读的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!

问题描述

如何通过OpenOffice的Writer文档和文本输出的所有段落重复。
我有Java的例子,但不知道如何代码转换为C#。
Java的例子可以在这里找到:的http:// wiki.services.openoffice.org/wiki/API/Samples/Java/Writer/TextDocumentStructure



我的C#代码:

  InitOpenOfficeEnvironment(); 
XMultiServiceFactory multiServiceFactory =连接();
XComponentLoader componentLoader =
XComponentLoader)multiServiceFactory.createInstance(com.sun.star.frame.Desktop);

//设置属性
为PropertyValue [] =的PropertyValue新为PropertyValue [1];
为PropertyValue aProperty =新为PropertyValue();
aProperty.Name =隐藏;
aProperty.Value =新uno.Any(假);
的PropertyValue [0] = aProperty;

XComponent xComponent =
componentLoader.loadComponentFromURL(
@的文件:/// C:/code/test3.doc,
_blank,0,为PropertyValue);

XEnumerationAccess xEnumerationAccess =(XEnumerationAccess)xComponent;
XEnumeration xParagraphEnumeration = xEnumerationAccess.createEnumeration();

,而(xParagraphEnumeration.hasMoreElements())
{
//?
//问题是在这里nextElement()返回uno.Any但是
//我一些应该怎么弄XTextContent ????
uno.Any的TextElement = xParagraphEnumeration.nextElement();

//创建另一个枚举得到
//段落
XEnumeration xParaEnumerationAccess = textElement.createEnumeration的所有文字部分();

//第3步通过文字部分枚举,
//获取接口,每个文本部分
}

xComponent.dispose();
xComponent = NULL;


解决方案

OK,我找到了答案,我希望它会节省时间对于那些谁面临着同样的问题...

 使用系统; 
:使用System.IO;使用System.Runtime.InteropServices
;
使用的Microsoft.Win32;使用unoidl.com.sun.star.beans
;
使用unoidl.com.sun.star.container;
使用unoidl.com.sun.star.frame;
使用unoidl.com.sun.star.lang;
使用unoidl.com.sun.star.table;
使用unoidl.com.sun.star.text;

命名空间OOApp
{
类节目
{
静态无效的主要(字串[] args)
{
InitOpenOfficeEnvironment( );
XMultiServiceFactory multiServiceFactory =连接();
XComponent xComponent = NULL;

串docFileName = @C:\test3.doc


{
XComponentLoader componentLoader =
(XComponentLoader)multiServiceFactory
.createInstance(com.sun.star.frame.Desktop);

//设置属性
为PropertyValue [] =的PropertyValue新为PropertyValue [1];
为PropertyValue aProperty =新为PropertyValue();
aProperty.Name =隐藏;
aProperty.Value =新uno.Any(假);
的PropertyValue [0] = aProperty;

xComponent =
componentLoader
.loadComponentFromURL(PathConverter(docFileName),
_blank,0,为PropertyValue);

XTextDocument xTextDocument =((XTextDocument)xComponent);
XEnumerationAccess xEnumerationAccess =
(XEnumerationAccess)xTextDocument.getText();
XEnumeration xParagraphEnumeration =
xEnumerationAccess.createEnumeration();

,而(xParagraphEnumeration.hasMoreElements())
{
uno.Any元= xParagraphEnumeration.nextElement();
XServiceInfo信佛=(XServiceInfo)element.Value;

如果(xinfo.supportsService(com.sun.star.text.TextTable))
{
Console.WriteLine(发现表!);

XTextTable xTextTable =(XTextTable)element.Value;
的String [] = cellNames xTextTable.getCellNames();

的for(int i = 0; I< cellNames.Length;我++)
{
XCELL XCELL = xTextTable.getCellByName(cellNames [I]);
XTEXT xTextCell =(XTEXT)XCELL;

字符串strText的= xTextCell.getString();
Console.WriteLine(strText的);
}
}
,否则
{
XTextContent xTextElement =(XTextContent)element.Value;
XEnumerationAccess xParaEnumerationAccess =
(XEnumerationAccess)xTextElement;

//创建另一个枚举拿到款$ B $的
//所有文字部分b XEnumeration xTextPortionEnum =
xParaEnumerationAccess.createEnumeration();

//第3步通过文字部分枚举,获得接口
//每个单独的文本部分
,而(xTextPortionEnum.hasMoreElements())
{
XTextRange xTextPortion =
(XTextRange)xTextPortionEnum.nextElement()值。
Console.Write(xTextPortion.getString());
}
}
}
}
赶上(unoidl.com.sun.star.uno.Exception EXP1)
{
控制台。的WriteLine(exp1.Message);
Console.WriteLine(exp1.StackTrace);
}
赶上(System.Exception的EXP2)
{
Console.WriteLine(exp2.Message);
Console.WriteLine(exp2.StackTrace);
}
终于
{
xComponent.dispose();
xComponent = NULL;
}

Console.WriteLine(完成。);
到Console.ReadLine();
}

静态私人无效InitOpenOfficeEnvironment()
{
串baseKey;
// OpenOffice的是一个32位的应用程序,
//它的注册表位置是在64位操作系统
不同的,如果(Marshal.SizeOf(typeof运算(IntPtr的))== 8)
baseKey = @SOFTWARE\Wow6432Node\OpenOffice.org\
,否则
baseKey = @SOFTWARE\OpenOffice.org\

//获取URE目录
串键= baseKey + @Layers\URE\1
的RegistryKey章= Registry.CurrentUser.OpenSubKey(键);
如果(REG == NULL)=章Registry.LocalMachine.OpenSubKey(键);
串urePath = reg.GetValue(UREINSTALLLOCATION)作为字符串;
reg.Close();
urePath = Path.Combine(urePath,本);

//获取UNO路径
键= baseKey + @UNO\InstallPath
=章Registry.CurrentUser.OpenSubKey(键);
如果(REG == NULL)=章Registry.LocalMachine.OpenSubKey(键);
串unoPath = reg.GetValue(空)的字符串;
reg.Close();

线道路;
路径=的String.Format({0} {1},
System.Environment.GetEnvironmentVariable(PATH),urePath);
System.Environment.SetEnvironmentVariable(PATH,路径);
System.Environment.SetEnvironmentVariable(UNO_PATH,unoPath);
}

公共静态XMultiServiceFactory连接()
{
unoidl.com.sun.star.uno.XComponentContext m_xContext = NULL;

{
m_xContext = uno.util.Bootstrap.bootstrap();
的System.Console.WriteLine(OO:引导完成与成功);
}
赶上(System.Exception的EXP)
{
的System.Console.WriteLine(OO:引导<期间除外;+
exp.Message + >中);
的System.Console.WriteLine(OO:源+ exp.Source);
如果(exp.InnerException!= NULL)
{
的System.Console.WriteLine(OO:内部消息+
exp.InnerException.Message);
的System.Console.WriteLine(OO:内源+
exp.InnerException.Source);
}
}
回报率(m_xContext!= NULL)?
(XMultiServiceFactory)m_xContext.getServiceManager():空;
}

私人静态字符串PathConverter(字符串文件)
{

{
档= file.Replace(@\ ,/);
返回文件:///+文件;
}
赶上(System.Exception的前)
{
罚球前;
}
}
}
}


How to iterate through all paragraphs in OpenOffice Writer document and output text. I have Java examples, but don't know how to convert code to C#. Java example could be found here: http://wiki.services.openoffice.org/wiki/API/Samples/Java/Writer/TextDocumentStructure

My C# code:

InitOpenOfficeEnvironment();
XMultiServiceFactory multiServiceFactory = connect();
XComponentLoader componentLoader =           
    XComponentLoader)multiServiceFactory.createInstance("com.sun.star.frame.Desktop"); 

//set the property
PropertyValue[] propertyValue = new PropertyValue[1];
PropertyValue aProperty = new PropertyValue();
aProperty.Name = "Hidden";
aProperty.Value = new uno.Any(false);
propertyValue[0] = aProperty;

XComponent xComponent =
        componentLoader.loadComponentFromURL(
            @"file:///C:/code/test3.doc", 
            "_blank", 0, propertyValue);

XEnumerationAccess xEnumerationAccess = (XEnumerationAccess)xComponent;
XEnumeration xParagraphEnumeration = xEnumerationAccess.createEnumeration();

while ( xParagraphEnumeration.hasMoreElements() ) 
{
    // ???
    // The problem is here nextElement() returns uno.Any but
    // I some how should get XTextContent????
    uno.Any textElement = xParagraphEnumeration.nextElement();

    // create another enumeration to get all text portions of 
    //the paragraph
    XEnumeration xParaEnumerationAccess = textElement.createEnumeration();

    //step 3  Through the Text portions Enumeration, 
    //get interface to each individual text portion
}

xComponent.dispose();
xComponent = null;

解决方案

OK, I found the answer, I hope it will save some time for those who faced the same problem…

using System;
using System.IO;
using System.Runtime.InteropServices;
using Microsoft.Win32;
using unoidl.com.sun.star.beans;
using unoidl.com.sun.star.container;
using unoidl.com.sun.star.frame;
using unoidl.com.sun.star.lang;
using unoidl.com.sun.star.table;
using unoidl.com.sun.star.text;

namespace OOApp
{
    class Program
    {
        static void Main(string[] args)
        {
            InitOpenOfficeEnvironment();
            XMultiServiceFactory multiServiceFactory = Connect();
            XComponent xComponent = null;

            string docFileName = @"C:\test3.doc";

            try
            {
                XComponentLoader componentLoader =                 
                    (XComponentLoader)multiServiceFactory
                    .createInstance("com.sun.star.frame.Desktop");

                //set the property
                PropertyValue[] propertyValue = new PropertyValue[1];
                PropertyValue aProperty = new PropertyValue();
                aProperty.Name = "Hidden";
                aProperty.Value = new uno.Any(false);
                propertyValue[0] = aProperty;

                xComponent =
                    componentLoader
                    .loadComponentFromURL(PathConverter(docFileName), 
                        "_blank", 0, propertyValue);

                XTextDocument xTextDocument = ((XTextDocument)xComponent);
                XEnumerationAccess xEnumerationAccess =    
                    (XEnumerationAccess)xTextDocument.getText();
                XEnumeration xParagraphEnumeration = 
                    xEnumerationAccess.createEnumeration();

                while (xParagraphEnumeration.hasMoreElements())
                {
                    uno.Any element = xParagraphEnumeration.nextElement();
                    XServiceInfo xinfo = (XServiceInfo)element.Value;

                    if (xinfo.supportsService("com.sun.star.text.TextTable"))
                    {
                        Console.WriteLine("Found Table!");

                        XTextTable xTextTable = (XTextTable)element.Value;
                        String[] cellNames = xTextTable.getCellNames();

                        for (int i = 0; i < cellNames.Length; i++) 
                        {
                            XCell xCell = xTextTable.getCellByName(cellNames[i]);
                            XText xTextCell = (XText)xCell;

                            String strText = xTextCell.getString();
                            Console.WriteLine(strText);
                        } 
                    }
                    else
                    {
                        XTextContent xTextElement = (XTextContent)element.Value;
                        XEnumerationAccess xParaEnumerationAccess = 
                            (XEnumerationAccess)xTextElement;

                        // create another enumeration to get all text portions of 
                        //the paragraph
                        XEnumeration xTextPortionEnum = 
                            xParaEnumerationAccess.createEnumeration();

                        //step 3  Through the Text portions Enumeration, get interface 
                        //to each individual text portion
                        while (xTextPortionEnum.hasMoreElements())
                        {
                            XTextRange xTextPortion = 
                                (XTextRange)xTextPortionEnum.nextElement().Value;
                            Console.Write(xTextPortion.getString());
                        }
                    }                    
                }
            }
            catch (unoidl.com.sun.star.uno.Exception exp1)
            {
                Console.WriteLine(exp1.Message);
                Console.WriteLine(exp1.StackTrace);
            }
            catch(System.Exception exp2)
            {
                Console.WriteLine(exp2.Message);
                Console.WriteLine(exp2.StackTrace);
            }
            finally
            {
                xComponent.dispose();
                xComponent = null;
            }

            Console.WriteLine("Done.");
            Console.ReadLine();
        }

        static private void InitOpenOfficeEnvironment()
        {
            string baseKey;
            // OpenOffice being a 32 bit app, 
            //its registry location is different in a 64 bit OS
            if (Marshal.SizeOf(typeof(IntPtr)) == 8)
                baseKey = @"SOFTWARE\Wow6432Node\OpenOffice.org\";
            else
                baseKey = @"SOFTWARE\OpenOffice.org\";

            // Get the URE directory
            string key = baseKey + @"Layers\URE\1";
            RegistryKey reg = Registry.CurrentUser.OpenSubKey(key);
            if (reg == null) reg = Registry.LocalMachine.OpenSubKey(key);
            string urePath = reg.GetValue("UREINSTALLLOCATION") as string;
            reg.Close();
            urePath = Path.Combine(urePath, "bin");

            // Get the UNO Path
            key = baseKey + @"UNO\InstallPath";
            reg = Registry.CurrentUser.OpenSubKey(key);
            if (reg == null) reg = Registry.LocalMachine.OpenSubKey(key);
            string unoPath = reg.GetValue(null) as string;
            reg.Close();

            string path;
            path = string.Format("{0};{1}",     
                System.Environment.GetEnvironmentVariable("PATH"), urePath);
            System.Environment.SetEnvironmentVariable("PATH", path);
            System.Environment.SetEnvironmentVariable("UNO_PATH", unoPath);
        }

        public static XMultiServiceFactory Connect()
        {
            unoidl.com.sun.star.uno.XComponentContext m_xContext = null;
            try
            {
                m_xContext = uno.util.Bootstrap.bootstrap();
                System.Console.WriteLine("OO: bootstrap finished with success");
            }
            catch (System.Exception exp)
            {
                System.Console.WriteLine("OO: Exception during bootstrap <" + 
                    exp.Message + ">");
                System.Console.WriteLine("OO: Source" + exp.Source);
                if (exp.InnerException != null)
                {
                    System.Console.WriteLine("OO: Inner Message" + 
                        exp.InnerException.Message);
                    System.Console.WriteLine("OO: Inner Source" + 
                        exp.InnerException.Source);
                }
            } 
            return (m_xContext != null) ? 
                (XMultiServiceFactory)m_xContext.getServiceManager() : null;
        }

        private static string PathConverter(string file)
        {
            try
            {
                file = file.Replace(@"\", "/");
                return "file:///" + file;
            }
            catch (System.Exception ex)
            {
                throw ex;
            }
        }
    }
}

这篇关于OpenOffice的使用.NET:如何遍历所有throught段落和文本阅读的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!

查看全文
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆