我需要在现有的pdf文件中搜索一个单词,并且希望能够突出显示文本或单词
并保存pdf文件
我有一个想法,使用PdfAnnotation.CreateMarkup可以找到文本的位置,然后我们可以添加背景色...但是我不知道如何实现:(
请帮帮我吧
LocationTextExtractionStrategy
。祝你好运!如果你真的找到了如何做到这一点,请在这里发布,有几个人正在想确切地知道你在想什么!我已经找到了如何做到这一点,万一有人需要从PDF文档中获取带有位置(坐标)的单词或句子,你可以在这个示例项目这里找到它。我使用了VB.NET 2010。记得在此项目中添加对iTextSharp DLL的引用。
我添加了自己的TextExtraction策略类,基于Class LocationTextExtractionStrategy。我专注于TextChunks,因为它们已经具有这些坐标。
有一些已知的限制,例如:
Test.Form1 formBuilder = new Test.Form1();
string[] fields = new string[] { "%AccountNumber%", "%MeterNumber%", "%EmailFieldHolder%", "%AddressFieldHolder%", "%EmptyFieldHolder%", "%CityStateZipFieldHolder%", "%emptyFieldHolder1%", "%emptyFieldHolder2%", "%emptyFieldHolder3%", "%emptyFieldHolder4%", "%emptyFieldHolder5%", "%emptyFieldHolder6%", "%emptyFieldHolder7%", "%emptyFieldHolder8%", "%SiteNameFieldHolder%", "%SiteNameFieldHolderWithExtraSpace%" };
//int a = 0;
for (int a = 0; a < fields.Length; )
{
string[] fieldNames = fields[a].Split('%');
string[] fieldName = Regex.Split(fieldNames[1], "Field");
formBuilder.PDFTextGetter(fields[a], StringComparison.CurrentCultureIgnoreCase, htmlToPdf, finalhtmlToPdf, fieldName[0]);
File.Delete(htmlToPdf);
System.Array.Clear(fieldNames, 0, 2);
System.Array.Clear(fieldName, 0, 1);
a++;
if (a == fields.Length)
{
break;
}
string[] fieldNames1 = fields[a].Split('%');
string[] fieldName1 = Regex.Split(fieldNames1[1], "Field");
formBuilder.PDFTextGetter(fields[a], StringComparison.CurrentCultureIgnoreCase, finalhtmlToPdf, htmlToPdf, fieldName1[0]);
File.Delete(finalhtmlToPdf);
System.Array.Clear(fieldNames1, 0, 2);
System.Array.Clear(fieldName1, 0, 1);
a++;
}
在您的示例中,它会将PDFTextGetter函数在两个文件之间来回传递,直到我获得最终产品。它运行得非常好,如果没有您最初的项目,这是不可能的,所以非常感谢您。我还修改了您的VB代码,使其可以进行文本字段映射,如下所示:
For Each rect As iTextSharp.text.Rectangle In MatchesFound
cb.Rectangle(rect.Left, rect.Bottom + 1, rect.Width, rect.Height + 4)
Dim field As New TextField(stamper.Writer, rect, FieldName & Fields)
Dim form = stamper.AcroFields
Dim fieldKeys = form.Fields.Keys
stamper.AddAnnotation(field.GetTextField(), page)
Fields += 1
Next
我想分享一下,我是如何以你的项目为骨架完成我的工作的。它甚至可以按照我需要的方式递增字段名称。我还不得不向你的函数添加一个新参数,但这里不值得列举。再次感谢你提供的这个绝佳起点。
感谢Jcis!
经过几个小时的研究和思考,我找到了你的解决方案,它帮助我解决了我的问题。
有两个小错误。
第一个:在读取器之前必须关闭印章机,否则会抛出异常。
Public Sub PDFTextGetter(ByVal pSearch As String, ByVal SC As StringComparison, ByVal SourceFile As String, ByVal DestinationFile As String)
Dim stamper As iTextSharp.text.pdf.PdfStamper = Nothing
Dim cb As iTextSharp.text.pdf.PdfContentByte = Nothing
Me.Cursor = Cursors.WaitCursor
If File.Exists(SourceFile) Then
Dim pReader As New PdfReader(SourceFile)
stamper = New iTextSharp.text.pdf.PdfStamper(pReader, New System.IO.FileStream(DestinationFile, FileMode.Create))
PB.Value = 0 : PB.Maximum = pReader.NumberOfPages
For page As Integer = 1 To pReader.NumberOfPages
Dim strategy As myLocationTextExtractionStrategy = New myLocationTextExtractionStrategy
'cb = stamper.GetUnderContent(page)
cb = stamper.GetOverContent(page)
Dim state As New PdfGState()
state.FillOpacity = 0.3F
cb.SetGState(state)
'Send some data contained in PdfContentByte, looks like the first is always cero for me and the second 100, but i'm not sure if this could change in some cases
strategy.UndercontentCharacterSpacing = cb.CharacterSpacing
strategy.UndercontentHorizontalScaling = cb.HorizontalScaling
'It's not really needed to get the text back, but we have to call this line ALWAYS,
'because it triggers the process that will get all chunks from PDF into our strategy Object
Dim currentText As String = PdfTextExtractor.GetTextFromPage(pReader, page, strategy)
'The real getter process starts in the following line
Dim MatchesFound As List(Of iTextSharp.text.Rectangle) = strategy.GetTextLocations(pSearch, SC)
'Set the fill color of the shapes, I don't use a border because it would make the rect bigger
'but maybe using a thin border could be a solution if you see the currect rect is not big enough to cover all the text it should cover
cb.SetColorFill(BaseColor.PINK)
'MatchesFound contains all text with locations, so do whatever you want with it, this highlights them using PINK color:
For Each rect As iTextSharp.text.Rectangle In MatchesFound
' cb.Rectangle(rect.Left, rect.Bottom, rect.Width, rect.Height)
cb.SaveState()
cb.SetColorFill(BaseColor.YELLOW)
cb.Rectangle(rect.Left, rect.Bottom, rect.Width, rect.Height)
cb.Fill()
cb.RestoreState()
Next
'cb.Fill()
PB.Value = PB.Value + 1
Next
stamper.Close()
pReader.Close()
End If
Me.Cursor = Cursors.Default
End Sub
Public Function GetTextLocations(ByVal pSearchString As String, ByVal pStrComp As System.StringComparison) As List(Of iTextSharp.text.Rectangle)
Dim FoundMatches As New List(Of iTextSharp.text.Rectangle)
Dim sb As New StringBuilder()
Dim ThisLineChunks As List(Of TextChunk) = New List(Of TextChunk)
Dim bStart As Boolean, bEnd As Boolean
Dim FirstChunk As TextChunk = Nothing, LastChunk As TextChunk = Nothing
Dim sTextInUsedChunks As String = vbNullString
' For Each chunk As TextChunk In locationalResult
For j As Integer = 0 To locationalResult.Count - 1
Dim chunk As TextChunk = locationalResult(j)
If chunk.text.Contains(pSearchString) Then
Thread.Sleep(1)
End If
If ThisLineChunks.Count > 0 AndAlso (Not chunk.SameLine(ThisLineChunks.Last) Or j = locationalResult.Count - 1) Then
If sb.ToString.IndexOf(pSearchString, pStrComp) > -1 Then
Dim sLine As String = sb.ToString
'Check how many times the Search String is present in this line:
Dim iCount As Integer = 0
Dim lPos As Integer
lPos = sLine.IndexOf(pSearchString, 0, pStrComp)
Do While lPos > -1
iCount += 1
If lPos + pSearchString.Length > sLine.Length Then Exit Do Else lPos = lPos + pSearchString.Length
lPos = sLine.IndexOf(pSearchString, lPos, pStrComp)
Loop
'Process each match found in this Text line:
Dim curPos As Integer = 0
For i As Integer = 1 To iCount
Dim sCurrentText As String, iFromChar As Integer, iToChar As Integer
iFromChar = sLine.IndexOf(pSearchString, curPos, pStrComp)
curPos = iFromChar
iToChar = iFromChar + pSearchString.Length - 1
sCurrentText = vbNullString
sTextInUsedChunks = vbNullString
FirstChunk = Nothing
LastChunk = Nothing
'Get first and last Chunks corresponding to this match found, from all Chunks in this line
For Each chk As TextChunk In ThisLineChunks
sCurrentText = sCurrentText & chk.text
'Check if we entered the part where we had found a matching String then get this Chunk (First Chunk)
If Not bStart AndAlso sCurrentText.Length - 1 >= iFromChar Then
FirstChunk = chk
bStart = True
End If
'Keep getting Text from Chunks while we are in the part where the matching String had been found
If bStart And Not bEnd Then
sTextInUsedChunks = sTextInUsedChunks & chk.text
End If
'If we get out the matching String part then get this Chunk (last Chunk)
If Not bEnd AndAlso sCurrentText.Length - 1 >= iToChar Then
LastChunk = chk
bEnd = True
End If
'If we already have first and last Chunks enclosing the Text where our String pSearchString has been found
'then it's time to get the rectangle, GetRectangleFromText Function below this Function, there we extract the pSearchString locations
If bStart And bEnd Then
FoundMatches.Add(GetRectangleFromText(FirstChunk, LastChunk, pSearchString, sTextInUsedChunks, iFromChar, iToChar, pStrComp))
curPos = curPos + pSearchString.Length
bStart = False : bEnd = False
Exit For
End If
Next
Next
End If
sb.Clear()
ThisLineChunks.Clear()
End If
ThisLineChunks.Add(chunk)
sb.Append(chunk.text)
Next
Return FoundMatches
End Function