我已经完成了这里建议的解决方案,但我的问题有点不同。在上述链接提供的解决方案中,仅当iTextSharp也用于添加水印时,才能删除水印。就我而言,在某些情况下,我使用 Word 添加水印Microsoft。当我使用以下代码时,水印确实从 PDF 中消失,但是当我将 PDF 转换为 Word 时,水印再次显示为图像。根据我的理解,下面的代码所做的是它将水印的不透明度值更改为 0,因此它消失了。
private static void removeWatermark(string watermarkedFile, string unwatermarkedFile)
{
PdfReader.unethicalreading = true;
PdfReader reader = new PdfReader(watermarkedFile);
reader.RemoveUnusedObjects();
int pageCount = reader.NumberOfPages;
for (int i = 1; i <= pageCount; i++)
{
var page = reader.GetPageN(i);
PdfDictionary resources = page.GetAsDict(PdfName.RESOURCES);
PdfDictionary extGStates = resources.GetAsDict(PdfName.EXTGSTATE);
if (extGStates == null)
continue;
foreach (PdfName name in extGStates.Keys)
{
var obj = extGStates.Get(name);
PdfDictionary extGStateObject = (PdfDictionary)PdfReader.GetPdfObject(obj);
var stateNumber = extGStateObject.Get(PdfName.ca);
if (stateNumber == null)
continue;
var caNumber = (PdfNumber)PdfReader.GetPdfObject(stateNumber);
if (caNumber.FloatValue != 1f)
{
extGStateObject.Remove(PdfName.ca);
extGStateObject.Put(PdfName.ca, new PdfNumber(0f));
}
}
}
using (FileStream fs = new FileStream(unwatermarkedFile, FileMode.Create, FileAccess.Write, FileShare.None))
{
using (PdfStamper stamper = new PdfStamper(reader, fs))
{
stamper.SetFullCompression();
stamper.Close();
}
}
}
有没有办法通过修改代码来删除此水印?
正如 OP 已经提到的,如果您完全控制最初创建水印的过程,您可以按照他在回答 OP 提到的问题时@ChrisHaas解释的那样进行操作。
另一方面,如果您用来创建水印的工具以自己的方式创建水印,您将需要为这些水印定制的方法。
此方法通常需要您编辑一些内容流。 顺便说一下,@ChrisHaas的解决方案也是如此。
为了简化此操作,应首先创建通用内容流编辑功能,然后仅使用此功能来编辑这些水印。
因此,这里首先是一个示例通用内容流编辑器类,然后是基于该类的解决方案来编辑OP的示例水印。
泛型内容流编辑器类
这个PdfContentStreamEditor
类通过跟踪部分图形状态的指令来解析原始内容流指令;这些指令被转发到它的Write
方法,默认情况下,该方法在它们进来时将它们写回来,有效地创建了原始流的相同或至少等效的副本。
要实际编辑流,只需重写此Write
方法,并且仅将结果流中所需的指令转发到基Write
方法。
public class PdfContentStreamEditor : PdfContentStreamProcessor
{
/**
* This method edits the immediate contents of a page, i.e. its content stream.
* It explicitly does not descent into form xobjects, patterns, or annotations.
*/
public void EditPage(PdfStamper pdfStamper, int pageNum)
{
PdfReader pdfReader = pdfStamper.Reader;
PdfDictionary page = pdfReader.GetPageN(pageNum);
byte[] pageContentInput = ContentByteUtils.GetContentBytesForPage(pdfReader, pageNum);
page.Remove(PdfName.CONTENTS);
EditContent(pageContentInput, page.GetAsDict(PdfName.RESOURCES), pdfStamper.GetUnderContent(pageNum));
}
/**
* This method processes the content bytes and outputs to the given canvas.
* It explicitly does not descent into form xobjects, patterns, or annotations.
*/
public void EditContent(byte[] contentBytes, PdfDictionary resources, PdfContentByte canvas)
{
this.canvas = canvas;
ProcessContent(contentBytes, resources);
this.canvas = null;
}
/**
* This method writes content stream operations to the target canvas. The default
* implementation writes them as they come, so it essentially generates identical
* copies of the original instructions the {@link ContentOperatorWrapper} instances
* forward to it.
*
* Override this method to achieve some fancy editing effect.
*/
protected virtual void Write(PdfContentStreamProcessor processor, PdfLiteral operatorLit, List<PdfObject> operands)
{
int index = 0;
foreach (PdfObject pdfObject in operands)
{
pdfObject.ToPdf(canvas.PdfWriter, canvas.InternalBuffer);
canvas.InternalBuffer.Append(operands.Count > ++index ? (byte) ' ' : (byte) 'n');
}
}
//
// constructor giving the parent a dummy listener to talk to
//
public PdfContentStreamEditor() : base(new DummyRenderListener())
{
}
//
// Overrides of PdfContentStreamProcessor methods
//
public override IContentOperator RegisterContentOperator(String operatorString, IContentOperator newOperator)
{
ContentOperatorWrapper wrapper = new ContentOperatorWrapper();
wrapper.setOriginalOperator(newOperator);
IContentOperator formerOperator = base.RegisterContentOperator(operatorString, wrapper);
return formerOperator is ContentOperatorWrapper ? ((ContentOperatorWrapper)formerOperator).getOriginalOperator() : formerOperator;
}
public override void ProcessContent(byte[] contentBytes, PdfDictionary resources)
{
this.resources = resources;
base.ProcessContent(contentBytes, resources);
this.resources = null;
}
//
// members holding the output canvas and the resources
//
protected PdfContentByte canvas = null;
protected PdfDictionary resources = null;
//
// A content operator class to wrap all content operators to forward the invocation to the editor
//
class ContentOperatorWrapper : IContentOperator
{
public IContentOperator getOriginalOperator()
{
return originalOperator;
}
public void setOriginalOperator(IContentOperator originalOperator)
{
this.originalOperator = originalOperator;
}
public void Invoke(PdfContentStreamProcessor processor, PdfLiteral oper, List<PdfObject> operands)
{
if (originalOperator != null && !"Do".Equals(oper.ToString()))
{
originalOperator.Invoke(processor, oper, operands);
}
((PdfContentStreamEditor)processor).Write(processor, oper, operands);
}
private IContentOperator originalOperator = null;
}
//
// A dummy render listener to give to the underlying content stream processor to feed events to
//
class DummyRenderListener : IRenderListener
{
public void BeginTextBlock() { }
public void RenderText(TextRenderInfo renderInfo) { }
public void EndTextBlock() { }
public void RenderImage(ImageRenderInfo renderInfo) { }
}
}
一些背景:
此类扩展了 iTextSharp 分析器命名空间中的PdfContentStreamProcessor
。此类最初设计为仅分析内容流以返回文本、图像或图形提取的信息。我们利用它来跟踪图形状态的一部分,更准确地说是那些与文本提取相关的图形状态参数。
如果对于特定的编辑任务,还需要预处理的信息,例如当前指令绘制的文本,则可以使用自定义IRenderListener
实现来检索该信息,而不是此处使用的DummyRenderListener
,后者只是忽略它。
此类体系结构的灵感来自 iTextSharp.xtra 额外库中的PdfCleanUpProcessor
。
隐藏OP水印的编辑器
正如OP已经发现的那样,他的水印可以识别为唯一使用ExtGState对象中定义的透明度作为ca值的文档部分。因此,要隐藏水印,我们必须
- 识别与该值相关的图形状态更改,以及
- 当识别的当前 CA 值小于 1 时,不绘制任何东西。
实际上,水印是使用矢量图形操作构建的。因此,我们可以将编辑限制为这些操作。我们甚至可以限制它更改最终绘图指令("笔触"/"填充"/"填充和描边"加上某些变化),以不执行生成透明内容的部分(填充或描边)。
public class TransparentGraphicsRemover : PdfContentStreamEditor
{
protected override void Write(PdfContentStreamProcessor processor, PdfLiteral oper, List<PdfObject> operands)
{
String operatorString = oper.ToString();
if ("gs".Equals(operatorString))
{
updateTransparencyFrom((PdfName) operands[0]);
}
if (operatorMapping.Keys.Contains(operatorString))
{
// Downgrade the drawing operator if transparency is involved
// For details cf. the comment before the operatorMapping declaration
PdfLiteral[] mapping = operatorMapping[operatorString];
int index = 0;
if (strokingAlpha < 1)
index |= 1;
if (nonStrokingAlpha < 1)
index |= 2;
oper = mapping[index];
operands[operands.Count - 1] = oper;
}
base.Write(processor, oper, operands);
}
// The current transparency values; beware: save and restore state operations are ignored!
float strokingAlpha = 1;
float nonStrokingAlpha = 1;
void updateTransparencyFrom(PdfName gsName)
{
PdfDictionary extGState = getGraphicsStateDictionary(gsName);
if (extGState != null)
{
PdfNumber number = extGState.GetAsNumber(PdfName.ca);
if (number != null)
nonStrokingAlpha = number.FloatValue;
number = extGState.GetAsNumber(PdfName.CA);
if (number != null)
strokingAlpha = number.FloatValue;
}
}
PdfDictionary getGraphicsStateDictionary(PdfName gsName)
{
PdfDictionary extGStates = resources.GetAsDict(PdfName.EXTGSTATE);
return extGStates.GetAsDict(gsName);
}
//
// Map from an operator name to an array of operations it becomes depending
// on the current graphics state:
//
// * [0] the operation in case of no transparency
// * [1] the operation in case of stroking transparency
// * [2] the operation in case of non-stroking transparency
// * [3] the operation in case of stroking and non-stroking transparency
//
Dictionary<String, PdfLiteral[]> operatorMapping = new Dictionary<String, PdfLiteral[]>();
public TransparentGraphicsRemover()
{
PdfLiteral _S = new PdfLiteral("S");
PdfLiteral _s = new PdfLiteral("s");
PdfLiteral _f = new PdfLiteral("f");
PdfLiteral _fStar = new PdfLiteral("f*");
PdfLiteral _B = new PdfLiteral("B");
PdfLiteral _BStar = new PdfLiteral("B*");
PdfLiteral _b = new PdfLiteral("b");
PdfLiteral _bStar = new PdfLiteral("b*");
PdfLiteral _n = new PdfLiteral("n");
operatorMapping["S"] = new PdfLiteral[]{ _S, _n, _S, _n };
operatorMapping["s"] = new PdfLiteral[]{ _s, _n, _s, _n };
operatorMapping["f"] = new PdfLiteral[]{ _f, _f, _n, _n };
operatorMapping["F"] = new PdfLiteral[]{ _f, _f, _n, _n };
operatorMapping["f*"] = new PdfLiteral[]{ _fStar, _fStar, _n, _n };
operatorMapping["B"] = new PdfLiteral[]{ _B, _f, _S, _n };
operatorMapping["B*"] = new PdfLiteral[]{ _BStar, _fStar, _S, _n };
operatorMapping["b"] = new PdfLiteral[] { _b, _f, _s, _n };
operatorMapping["b*"] = new PdfLiteral[]{ _bStar, _fStar, _s, _n };
}
}
注意:此示例编辑器非常简单:
- 它只考虑由 ExtGState 参数 ca 和 CA 创建的透明度,特别是忽略掩码。
- 它不会查找保存或还原图形状态的操作。
这些限制可以轻松解除,但需要的代码多于堆栈溢出答案。
像这样将此编辑器应用于 OP 的示例文件
string source = @"test3.pdf";
string dest = @"test3-noTransparency.pdf";
using (PdfReader pdfReader = new PdfReader(source))
using (PdfStamper pdfStamper = new PdfStamper(pdfReader, new FileStream(dest, FileMode.Create, FileAccess.Write)))
{
PdfContentStreamEditor editor = new TransparentGraphicsRemover();
for (int i = 1; i <= pdfReader.NumberOfPages; i++)
{
editor.EditPage(pdfStamper, i);
}
}
生成没有水印的 PDF 文件。
我没有OP将内容导出为word的工具,NitroPDF和Foxit,所以我无法执行最终测试。Adobe Acrobat(版本9.5)至少在导出到Word时不包含水印。
如果OP的工具在导出的Word文件中仍有水印痕迹,则可以轻松改进此类,以便在透明度处于活动状态时实际删除路径创建和绘制操作。
在爪哇中也是如此
我开始在Java中为iText实现它,后来才意识到OP在他的脑海中包含了.Net中的iTextSharp。以下是等效的 Java 类:
public class PdfContentStreamEditor extends PdfContentStreamProcessor
{
/**
* This method edits the immediate contents of a page, i.e. its content stream.
* It explicitly does not descent into form xobjects, patterns, or annotations.
*/
public void editPage(PdfStamper pdfStamper, int pageNum) throws IOException
{
PdfReader pdfReader = pdfStamper.getReader();
PdfDictionary page = pdfReader.getPageN(pageNum);
byte[] pageContentInput = ContentByteUtils.getContentBytesForPage(pdfReader, pageNum);
page.remove(PdfName.CONTENTS);
editContent(pageContentInput, page.getAsDict(PdfName.RESOURCES), pdfStamper.getUnderContent(pageNum));
}
/**
* This method processes the content bytes and outputs to the given canvas.
* It explicitly does not descent into form xobjects, patterns, or annotations.
*/
public void editContent(byte[] contentBytes, PdfDictionary resources, PdfContentByte canvas)
{
this.canvas = canvas;
processContent(contentBytes, resources);
this.canvas = null;
}
/**
* <p>
* This method writes content stream operations to the target canvas. The default
* implementation writes them as they come, so it essentially generates identical
* copies of the original instructions the {@link ContentOperatorWrapper} instances
* forward to it.
* </p>
* <p>
* Override this method to achieve some fancy editing effect.
* </p>
*/
protected void write(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException
{
int index = 0;
for (PdfObject object : operands)
{
object.toPdf(canvas.getPdfWriter(), canvas.getInternalBuffer());
canvas.getInternalBuffer().append(operands.size() > ++index ? (byte) ' ' : (byte) 'n');
}
}
//
// constructor giving the parent a dummy listener to talk to
//
public PdfContentStreamEditor()
{
super(new DummyRenderListener());
}
//
// Overrides of PdfContentStreamProcessor methods
//
@Override
public ContentOperator registerContentOperator(String operatorString, ContentOperator operator)
{
ContentOperatorWrapper wrapper = new ContentOperatorWrapper();
wrapper.setOriginalOperator(operator);
ContentOperator formerOperator = super.registerContentOperator(operatorString, wrapper);
return formerOperator instanceof ContentOperatorWrapper ? ((ContentOperatorWrapper)formerOperator).getOriginalOperator() : formerOperator;
}
@Override
public void processContent(byte[] contentBytes, PdfDictionary resources)
{
this.resources = resources;
super.processContent(contentBytes, resources);
this.resources = null;
}
//
// members holding the output canvas and the resources
//
protected PdfContentByte canvas = null;
protected PdfDictionary resources = null;
//
// A content operator class to wrap all content operators to forward the invocation to the editor
//
class ContentOperatorWrapper implements ContentOperator
{
public ContentOperator getOriginalOperator()
{
return originalOperator;
}
public void setOriginalOperator(ContentOperator originalOperator)
{
this.originalOperator = originalOperator;
}
@Override
public void invoke(PdfContentStreamProcessor processor, PdfLiteral operator, ArrayList<PdfObject> operands) throws Exception
{
if (originalOperator != null && !"Do".equals(operator.toString()))
{
originalOperator.invoke(processor, operator, operands);
}
write(processor, operator, operands);
}
private ContentOperator originalOperator = null;
}
//
// A dummy render listener to give to the underlying content stream processor to feed events to
//
static class DummyRenderListener implements RenderListener
{
@Override
public void beginTextBlock() { }
@Override
public void renderText(TextRenderInfo renderInfo) { }
@Override
public void endTextBlock() { }
@Override
public void renderImage(ImageRenderInfo renderInfo) { }
}
}
(PdfContentStreamEditor.java)
public class TransparentGraphicsRemover extends PdfContentStreamEditor
{
@Override
protected void write(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException
{
String operatorString = operator.toString();
if ("gs".equals(operatorString))
{
updateTransparencyFrom((PdfName) operands.get(0));
}
PdfLiteral[] mapping = operatorMapping.get(operatorString);
if (mapping != null)
{
int index = 0;
if (strokingAlpha < 1)
index |= 1;
if (nonStrokingAlpha < 1)
index |= 2;
operator = mapping[index];
operands.set(operands.size() - 1, operator);
}
super.write(processor, operator, operands);
}
// The current transparency values; beware: save and restore state operations are ignored!
float strokingAlpha = 1;
float nonStrokingAlpha = 1;
void updateTransparencyFrom(PdfName gsName)
{
PdfDictionary extGState = getGraphicsStateDictionary(gsName);
if (extGState != null)
{
PdfNumber number = extGState.getAsNumber(PdfName.ca);
if (number != null)
nonStrokingAlpha = number.floatValue();
number = extGState.getAsNumber(PdfName.CA);
if (number != null)
strokingAlpha = number.floatValue();
}
}
PdfDictionary getGraphicsStateDictionary(PdfName gsName)
{
PdfDictionary extGStates = resources.getAsDict(PdfName.EXTGSTATE);
return extGStates.getAsDict(gsName);
}
//
// Map from an operator name to an array of operations it becomes depending
// on the current graphics state:
//
// * [0] the operation in case of no transparency
// * [1] the operation in case of stroking transparency
// * [2] the operation in case of non-stroking transparency
// * [3] the operation in case of stroking and non-stroking transparency
//
static Map<String, PdfLiteral[]> operatorMapping = new HashMap<String, PdfLiteral[]>();
static
{
PdfLiteral _S = new PdfLiteral("S");
PdfLiteral _s = new PdfLiteral("s");
PdfLiteral _f = new PdfLiteral("f");
PdfLiteral _fStar = new PdfLiteral("f*");
PdfLiteral _B = new PdfLiteral("B");
PdfLiteral _BStar = new PdfLiteral("B*");
PdfLiteral _b = new PdfLiteral("b");
PdfLiteral _bStar = new PdfLiteral("b*");
PdfLiteral _n = new PdfLiteral("n");
operatorMapping.put("S", new PdfLiteral[]{ _S, _n, _S, _n });
operatorMapping.put("s", new PdfLiteral[]{ _s, _n, _s, _n });
operatorMapping.put("f", new PdfLiteral[]{ _f, _f, _n, _n });
operatorMapping.put("F", new PdfLiteral[]{ _f, _f, _n, _n });
operatorMapping.put("f*", new PdfLiteral[]{ _fStar, _fStar, _n, _n });
operatorMapping.put("B", new PdfLiteral[]{ _B, _f, _S, _n });
operatorMapping.put("B*", new PdfLiteral[]{ _BStar, _fStar, _S, _n });
operatorMapping.put("b", new PdfLiteral[]{ _b, _f, _s, _n });
operatorMapping.put("b*", new PdfLiteral[]{ _bStar, _fStar, _s, _n });
}
}
(透明图形卸妆.java)
@Test
public void testRemoveTransparentGraphicsTest3() throws IOException, DocumentException
{
try ( InputStream resource = getClass().getResourceAsStream("test3.pdf");
OutputStream result = new FileOutputStream(new File(RESULT_FOLDER, "test3-noTransparency.pdf")))
{
PdfReader pdfReader = new PdfReader(resource);
PdfStamper pdfStamper = new PdfStamper(pdfReader, result);
PdfContentStreamEditor editor = new TransparentGraphicsRemover();
for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
{
editor.editPage(pdfStamper, i);
}
pdfStamper.close();
}
}
(摘自EditPageContent.java)
这是更改颜色(超链接等)的代码。
PdfCanvasEditor editor = new PdfCanvasEditor() {
@Override
protected void write(PdfCanvasProcessor processor, PdfLiteral operator, List<PdfObject> operands)
{
String operatorString = operator.toString();
if (SET_FILL_RGB.equals(operatorString) && operands.size() == 4) {
if (isApproximatelyEqual(operands.get(0), 0) &&
isApproximatelyEqual(operands.get(1), 0) &&
isApproximatelyEqual(operands.get(2), 1)) {
super.write(processor, new PdfLiteral("g"), Arrays.asList(new PdfNumber(0), new PdfLiteral("g")));
return;
}
}
if (SET_STROKE_RGB.equals(operatorString) && operands.size() == 4) {
if (isApproximatelyEqual(operands.get(0), 0) &&
isApproximatelyEqual(operands.get(1), 0) &&
isApproximatelyEqual(operands.get(2), 1)) {
super.write(processor, new PdfLiteral("G"), Arrays.asList(new PdfNumber(0), new PdfLiteral("G")));
return;
}
}
super.write(processor, operator, operands);
}
boolean isApproximatelyEqual(PdfObject number, float reference) {
return number instanceof PdfNumber && Math.abs(reference - ((PdfNumber)number).floatValue()) < 0.01f;
}
final String SET_FILL_RGB = "rg";
final String SET_STROKE_RGB = "RG";
};
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++) {
editor.editPage(pdfDocument, i);
}
}