篇二:基于OneNote难点突破和批量识别
【1】开篇概述:在对本章技术介绍前,还是梳理下思路。描述下本章功能和开发过程。做个系统大致了解之后,在粘贴出本节效果图配以完整代码,然后分拆之,个体技术剖析。这样既可以达到全局整体效果,也可以对局部技术或者知识点做以小结。功能看图描述:本程序开发基于C#+WPF,然后这些条件具备前需要安装office2010以上版本,包含OneNote即可
完整代码:
namespace OnenoteOCRDemo
{
/// <summary>
/// Main.xaml 的交互逻辑
/// </summary>
public partial class Main : Window
{
#region 全局变量
private string __OutputFileName = string.Empty;
private WebClient client = new WebClient();
private delegate void UpdateProgressBarDelegate(System.Windows.DependencyProperty dp, Object value);
#endregion
#region 系统函数
public Main()
{
InitializeComponent();
}
#endregion
#region 用户函数
#region 验证文件夹是否存在,以及是否为空 :2014-7-10 17:12:57
//验证文件夹是否存在,以及是否为空
//时间:2014-7-10 14:54:44
//作者:白宁超
private bool fn数据验证()
{
if ((bool)this.rbtn本地图片.IsChecked)
{
if (!Directory.Exists(this.txtfile.Text))
{
this.labMsg.Content = "目录不存在,重新选择!";
this.txtfile.Focus();
return true;
}
System.IO.DirectoryInfo di = new System.IO.DirectoryInfo(@txtfile.Text);
if (di.GetFiles().Length + di.GetDirectories().Length == 0)
{
this.labMsg.Content = "目录为空!";
this.txtfile.Focus();
return true;
}
}
if (!Directory.Exists(this.txt输出目录.Text))
{
this.labMsg.Content = "输出目录不存在,请重新选择。";
this.txt输出目录.Focus();
return true;
}
return false;
}
#endregion
#region 遍历出文件中图片路径
//文件中选择所有文件处理
//时间:2014-7-10 17:17:29
//作者:白宁超
public List<string> GetImgPath(string Filepath)
{
DirectoryInfo d = new DirectoryInfo(Filepath);
ArrayList Flst = GetAll(d); //存放图片完整路径
List<string> imgpath = new List<string>();
foreach (object o in Flst)
{
imgpath.Add(@txtfile.Text + "\\" + o.ToString());
}
return imgpath;//返回图片路径集合
}
#endregion
#region 获取图片的过程
private void fnStartDownload(string v_strImgPath, string v_strOutputDir, out string v_strTmpPath)
{
int n = v_strImgPath.LastIndexOf('/');
string URLAddress = v_strImgPath.Substring(0, n);
string fileName = v_strImgPath.Substring(n + 1, v_strImgPath.Length - n - 1);
this.__OutputFileName = v_strOutputDir + "\\" + fileName.Substring(0, fileName.LastIndexOf(".")) + ".txt";
if (!Directory.Exists(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]))
{
Directory.CreateDirectory(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]);
}
string Dir = System.Configuration.ConfigurationManager.AppSettings["tmpPath"];
v_strTmpPath = Dir + "\\" + fileName;
this.client.DownloadFile(v_strImgPath, v_strTmpPath);
}
#endregion
#region//删除指定目录下的所有文件夹以及文件
private void DelFillOrDir(string strPath)
{
if (Directory.GetDirectories(strPath).Length > 0 || Directory.GetFiles(strPath).Length > 0)
{
// 获得文件夹数组
string[] strDirs = System.IO.Directory.GetDirectories(strPath); // 获得文件数组
string[] strFiles = System.IO.Directory.GetFiles(strPath); // 遍历所有子文件夹
foreach (string strFile in strFiles)
{
// 删除文件夹
System.IO.File.Delete(strFile);
} // 遍历所有文件
foreach (string strdir in strDirs)
{ // 删除文件
System.IO.Directory.Delete(strdir, true);
}
} // 成功
}
#endregion
#region//删除文件
public static bool DeleteFile(string xmlPath)
{
FileInfo newFile = new FileInfo(xmlPath);
if (newFile.Exists == true)
{
newFile.Delete();
return true;
}
else
{
return false;
}
}
#endregion
#region//删除xml数据
public void DeleteXML(string xpath)
{
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var docc = XDocument.Parse(notebookXml);
var ns = docc.Root.Name.Namespace;
XDocument doc = XDocument.Load(xpath);
string author = "USER-";
XElement xe = (from db in
doc.Element(ns + "Page").Elements(ns + "Outline")
where db.Attribute("author").Value == author
select db).Single() as XElement;
try
{
xe.Remove();
doc.Save(xpath);
}
catch
{
}
}
#region OCR写入Onenote和生成文字整个过程
//string xpath = @"C:\Users\Administrator\Desktop\OCR_Onenote\OnenoteOCR2.1\tmp.xml";
private void fnOCR(string v_strImgPath)
{
ORC(v_strImgPath);
}
public void ORC(string v_strImgPath)
{
FileInfo file = new FileInfo(v_strImgPath);
#region //获取图片的Base64编码
using (MemoryStream ms = new MemoryStream())
{
Bitmap bp = new Bitmap(v_strImgPath);
switch (file.Extension.ToLower())
{
case ".jpg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".jpeg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".gif":
bp.Save(ms, ImageFormat.Gif);
break;
case ".bmp":
bp.Save(ms, ImageFormat.Bmp);
break;
case ".tiff":
bp.Save(ms, ImageFormat.Tiff);
break;
case ".png":
bp.Save(ms, ImageFormat.Png);
break;
case ".emf":
bp.Save(ms, ImageFormat.Emf);
break;
default:
this.labMsg.Content = "不支持的图片格式。";
return;
}
byte[] buffer = ms.GetBuffer();
string _Base64 = Convert.ToBase64String(buffer);
#endregion
//向Onenote2010中插入图片
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
/***************************************************************************************/
string sectionID;
onenoteApp.OpenHierarchy(@"C:\Users\Administrator\Documents\OneNote 笔记本\个人\newfile.one", null, out sectionID, Microsoft.Office.Interop.OneNote.CreateFileType.cftSection);
string pageID = "{A975EE72-19C3-4C80-9C0E-EDA576DAB5C6}{1}{B0}";
onenoteApp.CreateNewPage(sectionID, out pageID, Microsoft.Office.Interop.OneNote.NewPageStyle.npsBlankPageNoTitle);
/********************************************************************************/
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var doc = XDocument.Parse(notebookXml);
var ns = doc.Root.Name.Namespace;
var pageNode = doc.Descendants(ns + "Page").FirstOrDefault();
var existingPageId = pageNode.Attribute("ID").Value;
#region
if (pageNode != null)
{
//Image Type 只支持这些类型:auto|png|emf|jpg
string ImgExtension = file.Extension.ToLower().Substring(1);
switch (ImgExtension)
{
case "jpg":
ImgExtension = "jpg";
break;
case "png":
ImgExtension = "png";
break;
case "emf":
ImgExtension = "emf";
break;
default:
ImgExtension = "auto";
break;
}
#endregion
var page = new XDocument(new XElement(ns + "Page",
new XElement(ns + "Outline",
new XElement(ns + "OEChildren",
new XElement(ns + "OE",
new XElement(ns + "Image",
new XAttribute("format", ImgExtension), new XAttribute("originalPageNumber", "0"),
new XElement(ns + "Position",
new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")),
new XElement(ns + "Size",
new XAttribute("width", bp.Width.ToString()), new XAttribute("height", bp.Height.ToString())),
new XElement(ns + "Data", _Base64)))))));
page.Root.SetAttributeValue("ID", existingPageId);
//保存图片进入Onenote页面
//注意以下几点:(待解决)
//1,onenote页面自动会生成一个页面,可能造成一直ocr错误。删除默认页面,新建空页
//2,图片存储在新建页面中,通过如下代码实现的,以追加存储方式进行。
onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue);
//线程休眠时间,单位毫秒,若图片很大,则延长休眠时间,保证Onenote OCR完毕
System.Threading.Thread.Sleep(Int32.Parse(System.Configuration.ConfigurationManager.AppSettings["WaitTIme"]));
string pageXml;
onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData);
//获取OCR后的内容
FileStream tmpXml = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Create, FileAccess.ReadWrite);
StreamWriter sw = new StreamWriter(tmpXml);
sw.Write(pageXml);
sw.Flush();
sw.Close();
tmpXml.Close();
//加载xml中的数据
FileStream tmpOnenote = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Open, FileAccess.ReadWrite);
XmlReader reader = XmlReader.Create(tmpOnenote);
XElement rdlc = XElement.Load(reader);
// rdlc.Save(xpath);
/*****************************************************************************************************/
XmlNameTable nameTable = reader.NameTable;
XmlNamespaceManager mgr = new XmlNamespaceManager(nameTable);
mgr.AddNamespace("one", ns.ToString());
StringReader sr = new StringReader(pageXml);
XElement onenote = XElement.Load(sr);
////读取xml中数据,并保存到文本中。
//XDocument doc1 = XDocument.Load(xpath);
var xml = from o in onenote.XPathSelectElements("//one:Image", mgr)
select o.XPathSelectElement("//one:OCRText", mgr).Value;
this.txtOCRed.Text = xml.First().ToString();
/**********************************************************************/
sr.Close();
reader.Close();
tmpOnenote.Close();
//DeleteXML(xpath);
onenoteApp.DeleteHierarchy(existingPageId);
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{46}{B0}");
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{50}{B0}");
}
}
}
#endregion
#endregion
#endregion
#region 系统事件
#region 搜索文件夹中的文件:2014-7-10 17:12:57
//搜索文件夹中的文件
//时间:2014-7-10 14:54:44
//作者:白宁超
ArrayList GetAll(DirectoryInfo dir)
{
try
{
ArrayList FileList = new ArrayList();//定义数组存放图片文件名
FileInfo[] allFile = dir.GetFiles();
foreach (FileInfo fi in allFile)
{
FileList.Add(fi.Name);//遍历图片,并添加到数组
}
DirectoryInfo[] allDir = dir.GetDirectories();
foreach (DirectoryInfo d in allDir)
{
GetAll(d);
}
return FileList;
}
catch (Exception e)
{
labMsg.Content = e.Message + "文件夹选择方式错误,重新选择!!";
return null;
}
}
#endregion
#region 选择遍历文件夹图片
//文件中选择所有文件处理
//时间:2014-7-10 14:54:44
//作者:白宁超
private void btn浏览_Click(object sender, RoutedEventArgs e)
{
txtmulu.Text = null;
FolderBrowserDialog dialog = new FolderBrowserDialog();
dialog.Description = "请选择待处理目录";
if (dialog.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
string foldPath = dialog.SelectedPath;
txtfile.Text = foldPath;
DirectoryInfo d = new DirectoryInfo(@txtfile.Text);
ArrayList Flst = GetAll(d);
foreach (object o in Flst)
{
txtmulu.Text += "正在ORC图片: 【" + o.ToString() + "】\r\n";
}
}
else
{
labMsg.Content = "打开失败!!";
}
#region 上传单个图片 2014-7-10 15:34:17
/*OpenFileDialog ofd = new OpenFileDialog();
ofd.Title = "请选择一个本地图片";
ofd.Multiselect = false;
ofd.Filter = "支持的图片格式(*.jpg,*.jpeg,*.gif,*.bmp,*.png,*.tiff,*.emf)|*.jpg;*.jpeg;*.gif;*.bmp;*.png;*.tiff;*.emf";
if (ofd.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
this.txt本地图片.Text = ofd.FileName;
this.img图片.Source = new BitmapImage(new Uri(ofd.FileName, UriKind.RelativeOrAbsolute));
this.labMsg.Content = "本地图片已成功加载。";
}*/
#endregion
}
#endregion
#region 选择本地图片OCR转化
private void rbtn本地图片_Checked(object sender, RoutedEventArgs e)
{
if (this.IsInitialized)
{
if ((bool)this.rbtn本地图片.IsChecked)
{
this.txtfile.Text = string.Empty;
this.txtfile.IsEnabled = true;
this.btn浏览.IsEnabled = true;
this.txtfile.Focus();
this.txtmulu.Text = null;
}
}
}
#endregion
#region 选择需要输入处理的文件
private void btn浏览_Click_1(object sender, RoutedEventArgs e)
{
txtmulu.Text = null;
FolderBrowserDialog dialog = new FolderBrowserDialog();
dialog.Description = "请选择待处理目录";
if (dialog.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
string foldPath = dialog.SelectedPath;
txtfile.Text = foldPath;
DirectoryInfo d = new DirectoryInfo(@txtfile.Text);
ArrayList Flst = GetAll(d);
foreach (object o in Flst)
{
txtmulu.Text += "正在ORC图片: 【" + o.ToString() + "】\r\n";
}
}
else
{
labMsg.Content = "打开失败!!";
}
#region 上传单个图片 2014-7-10 15:34:17
/*OpenFileDialog ofd = new OpenFileDialog();
ofd.Title = "请选择一个本地图片";
ofd.Multiselect = false;
ofd.Filter = "支持的图片格式(*.jpg,*.jpeg,*.gif,*.bmp,*.png,*.tiff,*.emf)|*.jpg;*.jpeg;*.gif;*.bmp;*.png;*.tiff;*.emf";
if (ofd.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
this.txt本地图片.Text = ofd.FileName;
this.img图片.Source = new BitmapImage(new Uri(ofd.FileName, UriKind.RelativeOrAbsolute));
this.labMsg.Content = "本地图片已成功加载。";
}*/
#endregion
}
#endregion
#region 选择输出文件夹
private void btn输出浏览_Click(object sender, RoutedEventArgs e)
{
FolderBrowserDialog fbd = new FolderBrowserDialog();
fbd.Description = "请选择一个输出目录";
if (fbd.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
this.txt输出目录.Text = fbd.SelectedPath;
DelFillOrDir(this.txt输出目录.Text);
}
}
#endregion
#region 清空输出文件
private void btn清空_Click(object sender, RoutedEventArgs e)
{
OCRtxt.Text = "";
this.OCRtxt.Focus();
}
#endregion
#region ORC转化过程
private void btnOCR_Click(object sender, RoutedEventArgs e)
{
if (this.fn数据验证())
{
OCRtxt.Text = "";
return;
}
try
{
DirectoryInfo dir = new DirectoryInfo(this.txt输出目录.Text);
if ((bool)this.rbtn本地图片.IsChecked)
{
List<string> imgpath = GetImgPath(@txtfile.Text);//获取图片列表
//定义进度条默认值
pb_import.Minimum = 0;
pb_import.Maximum = imgpath.Count();
double i = 0;
txtOCRed.Text = "";
OCRtxt.Text += "******************************************************************************";
foreach (object img in imgpath)
{
this.fnOCR(img.ToString());//遍历处理图片orc
FileInfo file = new FileInfo(img.ToString());
string name = file.Name.Substring(0, file.Name.LastIndexOf("."));
this.__OutputFileName = dir.FullName + @"\" + name + ".txt";
FileStream fs = new FileStream(this.__OutputFileName, FileMode.Create, FileAccess.ReadWrite);
StreamWriter sw = new StreamWriter(fs);
sw.Write(this.txtOCRed.Text);//将this.txtOCRed.Text内容写进txt文件中
sw.Flush();
sw.Close();
fs.Close();
OCRtxt.Text += "成功ORC出: 【" + name + ".txt】" + "\r\n";
//回调UI进度显示
i++;
pb_import.Value = i;
UpdateProgressBarDelegate updatePbDelegate = new UpdateProgressBarDelegate(pb_import.SetValue);
Dispatcher.Invoke(updatePbDelegate, System.Windows.Threading.DispatcherPriority.Background, new object[] { System.Windows.Controls.ProgressBar.ValueProperty, Convert.ToDouble(i + 1) });
Thread.Sleep(1000);
}
}
if (pb_import.Value == pb_import.Maximum)
{
System.Windows.Forms.MessageBox.Show("数据转换完成。");
}
else
{
System.Windows.Forms.MessageBox.Show("数据转换失败。");
}
}
catch (Exception ex)
{
System.Windows.Forms.MessageBox.Show("数据转换失败:" + ex.Message + ex.StackTrace);
this.labMsg.Content = "OCR失败。";
}
finally {
//System.Threading.Thread.CurrentThread.Abort();
Thread.Sleep(3000);
}
}
#endregion
#region//窗体关闭
private void Window_Closing(object sender, System.ComponentModel.CancelEventArgs e)
{
DirectoryInfo dir = new DirectoryInfo(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]);
foreach (FileInfo file in dir.GetFiles())
{
file.Delete();
}
}
#endregion
#endregion
}
}
功能以及操作描述:
- 运行本页面如上图,然后通过选择待处理目录(含中文文字图片),和输出目录,点击ORC即可。
- 在待处理目录下,点击浏览按钮,然后选择相应的文件夹,后台通过判断文件夹是否存在,如果存在进行遍历,读取出所有图片,然后在本页左端文本框对图片进行显示。
- 然后选择输出目录中的浏览按钮,选择处理后的结果存放文件夹,此项必填。否则不执行。在每次操作浏览按钮时,会对选择的文件夹进行清空处理,这样下次操作保持干净数据。
- 完成以上步骤,可以进行ORC操作,操作过程中通过遍历文件夹中图片文件,在一个方面中打开OneNote接口,对图片进行处理。图片处理生成的是一个xml文件,此文件不可视,一个缓存的xml文件,随着程序结束而终止,在处理过程中通过代码解析缓存xml,将文本数据提取到一个txt文件中。同时没执行一张图片,如图左边打印成功执行的文件,同时进度条滚动,结束后进行提示。
- 最后打开对应文件夹里面显示生产数据与对应图片保持一致。规范字体识别率还是可以的
所遇问题以及瓶颈突破:
- 在描述难点之前,我还是先提取出核心ORC代码,下面再做以概述。遍历处理图片
#region foreach (object img in imgpath) { this.fnOCR(img.ToString());//遍历处理图片orc FileInfo file = new FileInfo(img.ToString()); string name = file.Name.Substring(0, file.Name.LastIndexOf(".")); this.__OutputFileName = dir.FullName + @"\" + name + ".txt"; FileStream fs = new FileStream(this.__OutputFileName, FileMode.Create, FileAccess.ReadWrite); StreamWriter sw = new StreamWriter(fs); sw.Write(this.txtOCRed.Text);//将this.txtOCRed.Text内容写进txt文件中 sw.Flush(); sw.Close(); fs.Close(); OCRtxt.Text += "成功ORC出: 【" + name + ".txt】" + "\r\n"; //回调UI进度显示 i++; pb_import.Value = i; UpdateProgressBarDelegate updatePbDelegate = new UpdateProgressBarDelegate(pb_import.SetValue); Dispatcher.Invoke(updatePbDelegate, System.Windows.Threading.DispatcherPriority.Background, new object[] { System.Windows.Controls.ProgressBar.ValueProperty, Convert.ToDouble(i + 1) }); Thread.Sleep(1000); } #endregion
- fnOCR图片处理核心代码:下面截取核心代码,详细见付码
public void ORC(string v_strImgPath) { FileInfo file = new FileInfo(v_strImgPath); //向Onenote2010中插入图片 var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API /***************************************************************************************/ string sectionID; onenoteApp.OpenHierarchy(@"C:\Users\Administrator\Documents\OneNote 笔记本\个人\newfile.one", null, out sectionID, Microsoft.Office.Interop.OneNote.CreateFileType.cftSection); string pageID = "{A975EE72-19C3-4C80-9C0E-EDA576DAB5C6}{1}{B0}"; onenoteApp.CreateNewPage(sectionID, out pageID, Microsoft.Office.Interop.OneNote.NewPageStyle.npsBlankPageNoTitle); /********************************************************************************/ string notebookXml; onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml); var doc = XDocument.Parse(notebookXml); var ns = doc.Root.Name.Namespace; var pageNode = doc.Descendants(ns + "Page").FirstOrDefault(); var existingPageId = pageNode.Attribute("ID").Value; var page = new XDocument(new XElement(ns + "Page", new XElement(ns + "Outline", new XElement(ns + "OEChildren", new XElement(ns + "OE", new XElement(ns + "Image", new XAttribute("format", ImgExtension), new XAttribute("originalPageNumber", "0"), new XElement(ns + "Position", new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")), new XElement(ns + "Size", new XAttribute("width", bp.Width.ToString()), new XAttribute("height", bp.Height.ToString())), new XElement(ns + "Data", _Base64))))))); page.Root.SetAttributeValue("ID", existingPageId); //保存图片进入Onenote页面 //注意以下几点:(待解决) //1,onenote页面自动会生成一个页面,可能造成一直ocr错误。删除默认页面,新建空页 //2,图片存储在新建页面中,通过如下代码实现的,以追加存储方式进行。 onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue); //线程休眠时间,单位毫秒,若图片很大,则延长休眠时间,保证Onenote OCR完毕 System.Threading.Thread.Sleep(Int32.Parse(System.Configuration.ConfigurationManager.AppSettings["WaitTIme"])); string pageXml; onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData); //获取OCR后的内容 FileStream tmpXml = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Create, FileAccess.ReadWrite); StreamWriter sw = new StreamWriter(tmpXml); sw.Write(pageXml); sw.Flush(); sw.Close(); tmpXml.Close(); //加载xml中的数据 FileStream tmpOnenote = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Open, FileAccess.ReadWrite); XmlReader reader = XmlReader.Create(tmpOnenote); XElement rdlc = XElement.Load(reader); /*****************************************************************************************************/ XmlNameTable nameTable = reader.NameTable; XmlNamespaceManager mgr = new XmlNamespaceManager(nameTable); mgr.AddNamespace("one", ns.ToString()); StringReader sr = new StringReader(pageXml); XElement onenote = XElement.Load(sr); ////读取xml中数据,并保存到文本中。 //XDocument doc1 = XDocument.Load(xpath); var xml = from o in onenote.XPathSelectElements("//one:Image", mgr) select o.XPathSelectElement("//one:OCRText", mgr).Value; this.txtOCRed.Text = xml.First().ToString(); /**********************************************************************/ sr.Close(); reader.Close(); tmpOnenote.Close(); onenoteApp.DeleteHierarchy(existingPageId); } } }
问题继续描述,未加入如上代码时,暂且不说批处理,即便是单处理。结果是无论加载多少张图片,可以生成对应txt文件,但是对应的所有txt文件里面文本内容始终一样。解决方案分析下: - 是文本生成问题,于是想到每次图片生成清理出前一个xml,但是无论如何找不到xml存在,后来断点调试发现,执行onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue);之后,打开Onenote页面会发现图片出来,说明onenote已经在处理,此刻xml已经生成。接下来 onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData);方法把不可见的xml以字符串形式pageXml显示处理,后面就是对其处理了。证明从xml着手是不能解决问题的。
- 接下来就是想另一个方案:采用接口提供的DeletePageContent方法,但是面临问题在于其需要两个参数(页面序列id,和图片id),对于页面序列id通过断点可以找到,但是图片是随机的,id无法控制。因此此方案失败。
3. 在读取xml中发现this.txtOCRed.Text = xml.First().ToString();那么让去每次读取最后一条数据不就ok?对,,肯定这样,抱着坚定信心解决半日不得解。断点再经调试发现,读取的xml是不可控的,即是缓存中xml以输出参数,输出的字符串的处理。最终还不得解决。为此困惑数日。
4. 那么在生成的缓存xml重新放置到新建的xml中,然后每次读取一条结束,删除本次记录。问题肯定解决的,大喜,于是做出如下构造:
#region//删除xml数据
public void DeleteXML(string xpath)
{
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var docc = XDocument.Parse(notebookXml);
var ns = docc.Root.Name.Namespace;
XDocument doc = XDocument.Load(xpath);
string author = "USER-";
XElement xe = (from db in
doc.Element(ns + "Page").Elements(ns + "Outline")
where db.Attribute("author").Value == author
select db).Single() as XElement;
try
{
xe.Remove();
doc.Save(xpath);
}
catch
{
}
}
#region OCR写入Onenote和生成文字整个过程
//string xpath = @"C:\Users\Administrator\Desktop\OCR_Onenote\OnenoteOCR2.1\tmp.xml";
private void fnOCR(string v_strImgPath)
{
ORC(v_strImgPath);
}
public void ORC(string v_strImgPath)
{
FileInfo file = new FileInfo(v_strImgPath);
#region //获取图片的Base64编码
using (MemoryStream ms = new MemoryStream())
{
Bitmap bp = new Bitmap(v_strImgPath);
switch (file.Extension.ToLower())
{
case ".jpg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".jpeg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".gif":
bp.Save(ms, ImageFormat.Gif);
break;
case ".bmp":
bp.Save(ms, ImageFormat.Bmp);
break;
case ".tiff":
bp.Save(ms, ImageFormat.Tiff);
break;
case ".png":
bp.Save(ms, ImageFormat.Png);
break;
case ".emf":
bp.Save(ms, ImageFormat.Emf);
break;
default:
this.labMsg.Content = "不支持的图片格式。";
return;
}
byte[] buffer = ms.GetBuffer();
string _Base64 = Convert.ToBase64String(buffer);
#endregion
//向Onenote2010中插入图片
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
/***************************************************************************************/
string sectionID;
onenoteApp.OpenHierarchy(@"C:\Users\Administrator\Documents\OneNote 笔记本\个人\newfile.one", null, out sectionID, Microsoft.Office.Interop.OneNote.CreateFileType.cftSection);
string pageID = "{A975EE72-19C3-4C80-9C0E-EDA576DAB5C6}{1}{B0}";
onenoteApp.CreateNewPage(sectionID, out pageID, Microsoft.Office.Interop.OneNote.NewPageStyle.npsBlankPageNoTitle);
/********************************************************************************/
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var doc = XDocument.Parse(notebookXml);
var ns = doc.Root.Name.Namespace;
var pageNode = doc.Descendants(ns + "Page").FirstOrDefault();
var existingPageId = pageNode.Attribute("ID").Value;
#region
if (pageNode != null)
{
//Image Type 只支持这些类型:auto|png|emf|jpg
string ImgExtension = file.Extension.ToLower().Substring(1);
switch (ImgExtension)
{
case "jpg":
ImgExtension = "jpg";
break;
case "png":
ImgExtension = "png";
break;
case "emf":
ImgExtension = "emf";
break;
default:
ImgExtension = "auto";
break;
}
#endregion
var page = new XDocument(new XElement(ns + "Page",
new XElement(ns + "Outline",
new XElement(ns + "OEChildren",
new XElement(ns + "OE",
new XElement(ns + "Image",
new XAttribute("format", ImgExtension), new XAttribute("originalPageNumber", "0"),
new XElement(ns + "Position",
new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")),
new XElement(ns + "Size",
new XAttribute("width", bp.Width.ToString()), new XAttribute("height", bp.Height.ToString())),
new XElement(ns + "Data", _Base64)))))));
page.Root.SetAttributeValue("ID", existingPageId);
//保存图片进入Onenote页面
//注意以下几点:(待解决)
//1,onenote页面自动会生成一个页面,可能造成一直ocr错误。删除默认页面,新建空页
//2,图片存储在新建页面中,通过如下代码实现的,以追加存储方式进行。
onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue);
//线程休眠时间,单位毫秒,若图片很大,则延长休眠时间,保证Onenote OCR完毕
System.Threading.Thread.Sleep(Int32.Parse(System.Configuration.ConfigurationManager.AppSettings["WaitTIme"]));
string pageXml;
onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData);
//获取OCR后的内容
FileStream tmpXml = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Create, FileAccess.ReadWrite);
StreamWriter sw = new StreamWriter(tmpXml);
sw.Write(pageXml);
sw.Flush();
sw.Close();
tmpXml.Close();
//加载xml中的数据
FileStream tmpOnenote = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Open, FileAccess.ReadWrite);
XmlReader reader = XmlReader.Create(tmpOnenote);
XElement rdlc = XElement.Load(reader);
// rdlc.Save(xpath);
/*****************************************************************************************************/
XmlNameTable nameTable = reader.NameTable;
XmlNamespaceManager mgr = new XmlNamespaceManager(nameTable);
mgr.AddNamespace("one", ns.ToString());
StringReader sr = new StringReader(pageXml);
XElement onenote = XElement.Load(sr);
////读取xml中数据,并保存到文本中。
//XDocument doc1 = XDocument.Load(xpath);
var xml = from o in onenote.XPathSelectElements("//one:Image", mgr)
select o.XPathSelectElement("//one:OCRText", mgr).Value;
this.txtOCRed.Text = xml.First().ToString();
/**********************************************************************/
sr.Close();
reader.Close();
tmpOnenote.Close();
//DeleteXML(xpath);
onenoteApp.DeleteHierarchy(existingPageId);
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{46}{B0}");
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{50}{B0}");
}
}
}
#endregion
#endregion
结果还是无济于事,关键还是缓存的xml无法清理。
解决方案:搞定凌晨,无意间打开几篇英文文章(文章看不懂,只看代码),发现其原理在于图片处理过程中,催毁原始页面,新建页面即可。
1 2 3 4 5 6 7 |
|
调用API中创建页面方法CreateNewPage,pageID通过断点可以调试到,sectionID找到本地的地址即可。然后在执行一条数据结束时,调用onenoteApp.DeleteHierarchy(existingPageId)即可。
止于此核心问题解决,下面总结下所用的文件相关操作:
1 、验证文件夹是否存在,以及是否为空
#region 验证文件夹是否存在,以及是否为空 :2014-7-10 17:12:57
//验证文件夹是否存在,以及是否为空
//时间:2014-7-10 14:54:44
//作者:白宁超
private bool fn数据验证()
{
if ((bool)this.rbtn本地图片.IsChecked)
{
if (!Directory.Exists(this.txtfile.Text))
{
this.labMsg.Content = "目录不存在,重新选择!";
this.txtfile.Focus();
return true;
}
System.IO.DirectoryInfo di = new System.IO.DirectoryInfo(@txtfile.Text);
if (di.GetFiles().Length + di.GetDirectories().Length == 0)
{
this.labMsg.Content = "目录为空!";
this.txtfile.Focus();
return true;
}
}
if (!Directory.Exists(this.txt输出目录.Text))
{
this.labMsg.Content = "输出目录不存在,请重新选择。";
this.txt输出目录.Focus();
return true;
}
return false;
}
#endregion
2、遍历出文件中图片路径
#region 遍历出文件中图片路径
//文件中选择所有文件处理
//时间:2014-7-10 17:17:29
//作者:白宁超
public List<string> GetImgPath(string Filepath)
{
DirectoryInfo d = new DirectoryInfo(Filepath);
ArrayList Flst = GetAll(d); //存放图片完整路径
List<string> imgpath = new List<string>();
foreach (object o in Flst)
{
imgpath.Add(@txtfile.Text + "\\" + o.ToString());
}
return imgpath;//返回图片路径集合
}
#endregion
3、获取图片的过程
#region 获取图片的过程
private void fnStartDownload(string v_strImgPath, string v_strOutputDir, out string v_strTmpPath)
{
int n = v_strImgPath.LastIndexOf('/');
string URLAddress = v_strImgPath.Substring(0, n);
string fileName = v_strImgPath.Substring(n + 1, v_strImgPath.Length - n - 1);
this.__OutputFileName = v_strOutputDir + "\\" + fileName.Substring(0, fileName.LastIndexOf(".")) + ".txt";
if (!Directory.Exists(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]))
{
Directory.CreateDirectory(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]);
}
string Dir = System.Configuration.ConfigurationManager.AppSettings["tmpPath"];
v_strTmpPath = Dir + "\\" + fileName;
this.client.DownloadFile(v_strImgPath, v_strTmpPath);
}
#endregion
4、删除指定目录下的所有文件夹以及文件
#region//删除指定目录下的所有文件夹以及文件
private void DelFillOrDir(string strPath)
{
if (Directory.GetDirectories(strPath).Length > 0 || Directory.GetFiles(strPath).Length > 0)
{
// 获得文件夹数组
string[] strDirs = System.IO.Directory.GetDirectories(strPath); // 获得文件数组
string[] strFiles = System.IO.Directory.GetFiles(strPath); // 遍历所有子文件夹
foreach (string strFile in strFiles)
{
// 删除文件夹
System.IO.File.Delete(strFile);
} // 遍历所有文件
foreach (string strdir in strDirs)
{ // 删除文件
System.IO.Directory.Delete(strdir, true);
}
} // 成功
}
#endregion
5、删除文件
#region//删除文件
public static bool DeleteFile(string xmlPath)
{
FileInfo newFile = new FileInfo(xmlPath);
if (newFile.Exists == true)
{
newFile.Delete();
return true;
}
else
{
return false;
}
}
#endregion
6、删除xml数据
#region//删除xml数据
public void DeleteXML(string xpath)
{
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var docc = XDocument.Parse(notebookXml);
var ns = docc.Root.Name.Namespace;
XDocument doc = XDocument.Load(xpath);
string author = "USER-";
XElement xe = (from db in
doc.Element(ns + "Page").Elements(ns + "Outline")
where db.Attribute("author").Value == author
select db).Single() as XElement;
try
{
xe.Remove();
doc.Save(xpath);
}
catch
{
}
}
#region OCR写入Onenote和生成文字整个过程
//string xpath = @"C:\Users\Administrator\Desktop\OCR_Onenote\OnenoteOCR2.1\tmp.xml";
private void fnOCR(string v_strImgPath)
{
ORC(v_strImgPath);
}
public void ORC(string v_strImgPath)
{
FileInfo file = new FileInfo(v_strImgPath);
#region //获取图片的Base64编码
using (MemoryStream ms = new MemoryStream())
{
Bitmap bp = new Bitmap(v_strImgPath);
switch (file.Extension.ToLower())
{
case ".jpg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".jpeg":
bp.Save(ms, ImageFormat.Jpeg);
break;
case ".gif":
bp.Save(ms, ImageFormat.Gif);
break;
case ".bmp":
bp.Save(ms, ImageFormat.Bmp);
break;
case ".tiff":
bp.Save(ms, ImageFormat.Tiff);
break;
case ".png":
bp.Save(ms, ImageFormat.Png);
break;
case ".emf":
bp.Save(ms, ImageFormat.Emf);
break;
default:
this.labMsg.Content = "不支持的图片格式。";
return;
}
byte[] buffer = ms.GetBuffer();
string _Base64 = Convert.ToBase64String(buffer);
#endregion
//向Onenote2010中插入图片
var onenoteApp = new Microsoft.Office.Interop.OneNote.Application(); //onenote提供的API
/***************************************************************************************/
string sectionID;
onenoteApp.OpenHierarchy(@"C:\Users\Administrator\Documents\OneNote 笔记本\个人\newfile.one", null, out sectionID, Microsoft.Office.Interop.OneNote.CreateFileType.cftSection);
string pageID = "{A975EE72-19C3-4C80-9C0E-EDA576DAB5C6}{1}{B0}";
onenoteApp.CreateNewPage(sectionID, out pageID, Microsoft.Office.Interop.OneNote.NewPageStyle.npsBlankPageNoTitle);
/********************************************************************************/
string notebookXml;
onenoteApp.GetHierarchy(null, Microsoft.Office.Interop.OneNote.HierarchyScope.hsPages, out notebookXml);
var doc = XDocument.Parse(notebookXml);
var ns = doc.Root.Name.Namespace;
var pageNode = doc.Descendants(ns + "Page").FirstOrDefault();
var existingPageId = pageNode.Attribute("ID").Value;
#region
if (pageNode != null)
{
//Image Type 只支持这些类型:auto|png|emf|jpg
string ImgExtension = file.Extension.ToLower().Substring(1);
switch (ImgExtension)
{
case "jpg":
ImgExtension = "jpg";
break;
case "png":
ImgExtension = "png";
break;
case "emf":
ImgExtension = "emf";
break;
default:
ImgExtension = "auto";
break;
}
#endregion
var page = new XDocument(new XElement(ns + "Page",
new XElement(ns + "Outline",
new XElement(ns + "OEChildren",
new XElement(ns + "OE",
new XElement(ns + "Image",
new XAttribute("format", ImgExtension), new XAttribute("originalPageNumber", "0"),
new XElement(ns + "Position",
new XAttribute("x", "0"), new XAttribute("y", "0"), new XAttribute("z", "0")),
new XElement(ns + "Size",
new XAttribute("width", bp.Width.ToString()), new XAttribute("height", bp.Height.ToString())),
new XElement(ns + "Data", _Base64)))))));
page.Root.SetAttributeValue("ID", existingPageId);
//保存图片进入Onenote页面
//注意以下几点:(待解决)
//1,onenote页面自动会生成一个页面,可能造成一直ocr错误。删除默认页面,新建空页
//2,图片存储在新建页面中,通过如下代码实现的,以追加存储方式进行。
onenoteApp.UpdatePageContent(page.ToString(), DateTime.MinValue);
//线程休眠时间,单位毫秒,若图片很大,则延长休眠时间,保证Onenote OCR完毕
System.Threading.Thread.Sleep(Int32.Parse(System.Configuration.ConfigurationManager.AppSettings["WaitTIme"]));
string pageXml;
onenoteApp.GetPageContent(existingPageId, out pageXml, Microsoft.Office.Interop.OneNote.PageInfo.piBinaryData);
//获取OCR后的内容
FileStream tmpXml = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Create, FileAccess.ReadWrite);
StreamWriter sw = new StreamWriter(tmpXml);
sw.Write(pageXml);
sw.Flush();
sw.Close();
tmpXml.Close();
//加载xml中的数据
FileStream tmpOnenote = new FileStream(System.Configuration.ConfigurationManager.AppSettings["tmpPath"] + @"\tmp.xml", FileMode.Open, FileAccess.ReadWrite);
XmlReader reader = XmlReader.Create(tmpOnenote);
XElement rdlc = XElement.Load(reader);
// rdlc.Save(xpath);
/*****************************************************************************************************/
XmlNameTable nameTable = reader.NameTable;
XmlNamespaceManager mgr = new XmlNamespaceManager(nameTable);
mgr.AddNamespace("one", ns.ToString());
StringReader sr = new StringReader(pageXml);
XElement onenote = XElement.Load(sr);
////读取xml中数据,并保存到文本中。
//XDocument doc1 = XDocument.Load(xpath);
var xml = from o in onenote.XPathSelectElements("//one:Image", mgr)
select o.XPathSelectElement("//one:OCRText", mgr).Value;
this.txtOCRed.Text = xml.First().ToString();
/**********************************************************************/
sr.Close();
reader.Close();
tmpOnenote.Close();
//DeleteXML(xpath);
onenoteApp.DeleteHierarchy(existingPageId);
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{46}{B0}");
//onenoteApp.DeletePageContent(existingPageId, "{242BE490-7BF9-43D5-B719-3999E7631259}{50}{B0}");
}
}
}
#endregion
#endregion
7、搜索文件夹中的文件
#region 搜索文件夹中的文件:2014-7-10 17:12:57
//搜索文件夹中的文件
//时间:2014-7-10 14:54:44
//作者:白宁超
ArrayList GetAll(DirectoryInfo dir)
{
try
{
ArrayList FileList = new ArrayList();//定义数组存放图片文件名
FileInfo[] allFile = dir.GetFiles();
foreach (FileInfo fi in allFile)
{
FileList.Add(fi.Name);//遍历图片,并添加到数组
}
DirectoryInfo[] allDir = dir.GetDirectories();
foreach (DirectoryInfo d in allDir)
{
GetAll(d);
}
return FileList;
}
catch (Exception e)
{
labMsg.Content = e.Message + "文件夹选择方式错误,重新选择!!";
return null;
}
}
#endregion
8、选择遍历文件夹图片
private void btn浏览_Click(object sender, RoutedEventArgs e)
{
txtmulu.Text = null;
FolderBrowserDialog dialog = new FolderBrowserDialog();
dialog.Description = "请选择待处理目录";
if (dialog.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
string foldPath = dialog.SelectedPath;
txtfile.Text = foldPath;
DirectoryInfo d = new DirectoryInfo(@txtfile.Text);
ArrayList Flst = GetAll(d);
foreach (object o in Flst)
{
txtmulu.Text += "正在ORC图片: 【" + o.ToString() + "】\r\n";
}
}
else
{
labMsg.Content = "打开失败!!";
}
#region 上传单个图片 2014-7-10 15:34:17
/*OpenFileDialog ofd = new OpenFileDialog();
ofd.Title = "请选择一个本地图片";
ofd.Multiselect = false;
ofd.Filter = "支持的图片格式(*.jpg,*.jpeg,*.gif,*.bmp,*.png,*.tiff,*.emf)|*.jpg;*.jpeg;*.gif;*.bmp;*.png;*.tiff;*.emf";
if (ofd.ShowDialog() == System.Windows.Forms.DialogResult.OK)
{
this.txt本地图片.Text = ofd.FileName;
this.img图片.Source = new BitmapImage(new Uri(ofd.FileName, UriKind.RelativeOrAbsolute));
this.labMsg.Content = "本地图片已成功加载。";
}*/
#endregion
}
9、窗体关闭
private void Window_Closing(object sender, System.ComponentModel.CancelEventArgs e)
{
DirectoryInfo dir = new DirectoryInfo(System.Configuration.ConfigurationManager.AppSettings["tmpPath"]);
foreach (FileInfo file in dir.GetFiles())
{
file.Delete();
}
}
【补充】orc前后结果对照:应部分园友建议,更为直观
- 整体orc结果:
- 具体orc结果:
【篇末】:程序中使用遍历文件,文件夹清空处理,文件的删除,文件的查找,文件夹的判空,重点在于图片的OneNote处理等操作,完成了批处理。可以自动执行批文件夹中图片,生成新的文本文件与图片名一致。现在不足之处,对文件夹的文件类型筛选为执行图片类型没有处理,容错不足,这个自己用文件放入纯图片可以,另外有时候进程处理不稳定,估计加入进度条原因。待版本2再做改进。下一节介绍文本文件处理入库(Oracle)。特别wpf中DataGrid的使用,如何在wpf中完成分页,简单的集合类型数据库分页可以,但是数据库连接如何分页?