private TreeNode PrintObject(TreeNodeCollection tvDomNodes, PdfObject obj, string objectNumber)
{
var streamType = GetStreamType(obj);
string isIndirect = "Indirect";
if (!obj.IsIndirect())
{
isIndirect = "Direct";
}
var node = tvDomNodes.Add($"{objectNumber} - {obj.GetType().Name} {streamType} {isIndirect}");
node.Tag = obj;
if (streamType.Contains("Image"))
{
node.BackColor = Color.Olive;
}
if (obj.IsDictionary())
{
var dict = obj as PdfDictionary;
foreach (var dictKey in dict.Keys)
{
var dictObj = dict.GetDirectObject(dictKey);
var newNode = PrintObject(node.Nodes, dictObj, dictObj.ToString());
}
}
return(node);
}
/// <summary>
/// Updates the pagination in the footer.
/// </summary>
/// <param name="inputPdf">The pdf to modify.</param>
/// <param name="outputPdf">The pdf created with updated pagination.</param>
public static void UpdateFooterPagination(string inputPdf, string outputPdf)
{
PdfReader reader = new PdfReader(inputPdf);
FileStream fs = new FileStream(outputPdf, FileMode.Create, FileAccess.Write);
int n = reader.NumberOfPages;
for (int i = 1; i <= n; i++)
{
PdfDictionary dict = reader.GetPageN(i);
PdfObject obj = dict.GetDirectObject(PdfName.CONTENTS);
if (obj.GetType() == typeof(PRStream))
{
PRStream stream = (PRStream)obj;
byte[] data = PdfReader.GetStreamBytes(stream);
String oldStr = System.Text.Encoding.UTF8.GetString(data);
//Get the string matching the pagination
String pageString = CommonUtils.MatchRegex(oldStr, @"\[\(Seite \)\]TJ.*\[\(");
//Regex replacement of page string with updated page number
String updatedPageString = Regex.Replace(pageString, @"\[\(\d+\)\]", "[(" + i + ")]");
String newString = Regex.Replace(oldStr, @"\[\(Seite \)\]TJ.*\[\(", updatedPageString, RegexOptions.Singleline);
stream.SetData(System.Text.Encoding.UTF8.GetBytes(newString));
}
}
PdfStamper stamper = new PdfStamper(reader, fs);
stamper.Close();
reader.Close();
}
public IndirectObject CreateInstance(PdfObjectId objectId, PdfObject referencedObject, bool isReadOnly)
{
var objectType = referencedObject.GetType();
var genCtor = ctorCache.GetOrAdd(objectType, GetConstructorForType);
return((IndirectObject)genCtor.Invoke(new object[] { objectId, referencedObject, isReadOnly }));
}
/// <summary>
/// Tests if an object has a end delimiter.
/// </summary>
/// <param name="target">The <see cref="PdfObject"/> to test.</param>
/// <returns>True if object has a end delimiter, otherwise false.</returns>
public static bool HasEndDelimiter(this PdfObject target)
{
if (target == null)
{
throw new ArgumentNullException(nameof(target));
}
return(target.GetType().GetTypeInfo().GetCustomAttribute <HasDelimitersAttribute>()?.AtEnd ?? false);
}
/// <summary>
/// Gets <see cref="HasDelimitersAttribute"/> of object.
/// </summary>
/// <param name="target">The target <see cref="PdfObject"/>.</param>
/// <returns>The objects <see cref="HasDelimitersAttribute"/> or null.</returns>
internal static HasDelimitersAttribute GetHasDelimiterAttibute(this PdfObject target)
{
if (target == null)
{
throw new ArgumentNullException(nameof(target));
}
return(target.GetType().GetTypeInfo().GetCustomAttribute <HasDelimitersAttribute>());
}
void WriteObjectAddress(PdfObject value)
{
if (_layout == PdfWriterLayout.Verbose)
{
WriteRaw(String.Format("{0} {1} obj % {2}\n",
value.ObjectID.ObjectNumber, value.ObjectID.GenerationNumber,
value.GetType().FullName));
}
else
{
WriteRaw(String.Format("{0} {1} obj\n", value.ObjectID.ObjectNumber, value.ObjectID.GenerationNumber));
}
}
/// <summary>
/// Replace texts.
/// TODO: Los textos con formato creado en word introducen caracteres entre las palabras y no lo localiza.
/// </summary>
public void Replace()
{
using (FileStream stream = new FileStream(_pathSource, FileMode.Open))
{
using (PdfReader pdfReader = new PdfReader(stream))
{
for (int x = 1; x <= pdfReader.NumberOfPages; x++)
{
using (FileStream streamDest = new FileStream(_pathDest, FileMode.Create))
{
PdfDictionary dict = pdfReader.GetPageN(x);
PdfObject obj = dict.GetDirectObject(PdfName.CONTENTS);
if (obj.GetType() == typeof(PRStream))
{
ReplacePRStream(obj);
}
if (obj.GetType() == typeof(PdfArray))
{
foreach (var r in (PdfArray)obj)
{
PRIndirectReference ir = (PRIndirectReference)r;
PdfObject refdObj = pdfReader.GetPdfObject(ir.Number);
if (refdObj.IsStream())
{
ReplacePRStream(refdObj);
}
}
}
using (PdfStamper stamper = new PdfStamper(pdfReader, streamDest))
{
}
}
}
}
}
}
public static void Test_TraceObjects(string file)
{
Trace.WriteLine($"pdf \"{file}\"");
using (PdfReader pdfReader = new PdfReader(file))
{
int objectCount = pdfReader.XrefSize;
for (int i = 0; i < objectCount; i++)
{
PdfObject obj = pdfReader.GetPdfObject(i);
//if (obj != null)
if (obj is PdfDictionary)
{
PdfDictionary objDic = (PdfDictionary)obj;
string type = null;
if (objDic.Contains(PdfName.TYPE))
{
type = objDic.Get(PdfName.TYPE).ToString();
}
string subtype = null;
if (objDic.Contains(PdfName.SUBTYPE))
{
subtype = objDic.Get(PdfName.SUBTYPE).ToString();
}
Trace.WriteLine($"object {i + 1,3} object type {obj.GetType()} dictionary type {type} subtype {subtype}");
}
else if (obj != null)
{
Trace.WriteLine($"object {i + 1,3} object type {obj.GetType()}");
}
else
{
Trace.WriteLine($"object {i + 1,3} null");
}
}
}
}
internal override void SetObject(PdfItem value)
{
PdfObject obj = (PdfObject)value;
this.tbxObjectID.Text = PdfInternals.GetObjectID(obj).ToString();
this.txtType.Text = obj.GetType().Name;
this.lvKeys.Items.Clear();
ListViewItem item = new ListViewItem(
new string[3] {
ExplorerProcess.GetTypeName(obj), value.ToString(), value.GetType().Name
});
this.lvKeys.Items.Add(item);
}
/**
* Gets the content bytes from a content object, which may be a reference
* a stream or an array.
* @param contentObject the object to read bytes from
* @return the content bytes
* @throws IOException
*/
public static byte[] GetContentBytesFromContentObject(PdfObject contentObject)
{
byte[] result;
switch (contentObject.Type)
{
case PdfObject.INDIRECT:
PRIndirectReference refi = (PRIndirectReference)contentObject;
PdfObject directObject = PdfReader.GetPdfObject(refi);
result = GetContentBytesFromContentObject(directObject);
break;
case PdfObject.STREAM:
PRStream stream = (PRStream)PdfReader.GetPdfObject(contentObject);
result = PdfReader.GetStreamBytes(stream);
break;
case PdfObject.ARRAY:
// Stitch together all content before calling ProcessContent(), because
// ProcessContent() resets state.
MemoryStream allBytes = new MemoryStream();
PdfArray contentArray = (PdfArray)contentObject;
ListIterator <PdfObject> iter = contentArray.GetListIterator();
while (iter.HasNext())
{
PdfObject element = iter.Next();
byte[] b;
allBytes.Write(b = GetContentBytesFromContentObject(element), 0, b.Length);
allBytes.WriteByte((byte)' ');
}
result = allBytes.ToArray();
break;
default:
String msg = "Unable to handle Content of type " + contentObject.GetType();
throw new InvalidOperationException(msg);
}
return(result);
}
public static string GetTypeName(PdfObject obj)
{
if (obj is PdfDictionary)
{
return("dictionary");
}
if (obj is PdfArray)
{
return("array");
}
if (obj is PdfBooleanObject)
{
return("boolean");
}
if (obj is PdfIntegerObject)
{
return("integer");
}
if (obj is PdfRealObject)
{
return("real");
}
if (obj is PdfStringObject)
{
return("string");
}
if (obj is PdfNameObject)
{
return("name");
}
if (obj is PdfNullObject)
{
return("null");
}
throw new NotImplementedException("TODO: " + obj.GetType().FullName);
}
public static MemoryStream RemoveText(MemoryStream streamInput, string watermarkText)
{
string content;
PRStream stream;
PdfArray contentarray;
PdfReader reader = new PdfReader(streamInput.ToArray());
string DEST = "D:\\WebMes Projects\\NewYueWebMES\\YueWebMES.Service\\WebMES.API\\Attachments\\fa1.pdf";
//reader.RemoveUnusedObjects();
for (var i = 1; i <= reader.NumberOfPages; i++)
{
PdfDictionary dictionary = reader.GetPageN(i);//获取页
try
{
PdfObject pdfObj = dictionary.GetDirectObject(PdfName.CONTENTS);
if (pdfObj.GetType() == typeof(PRStream))
{
PRStream pst = (PRStream)pdfObj;
byte[] data = PdfReader.GetStreamBytes(pst);
content = System.Text.Encoding.ASCII.GetString(data);//获取pdf页内的文字内容
content = content.Replace(watermarkText, "");
pst.SetData(System.Text.Encoding.Default.GetBytes(content));
}
}
catch (Exception ex)
{
}
//contentarray = page.GetAsArray(PdfName.CONTENTS);
//if (contentarray != null)
//{
// //Loop through content
// for (int j = 0; j < contentarray.Size; j++)
// {
// //Get the raw byte stream
// stream = (PRStream)contentarray.GetAsStream(j);
// //Convert to a string. NOTE, you might need a different encoding here
// content = System.Text.Encoding.ASCII.GetString(PdfReader.GetStreamBytes(stream));//获取pdf页内的文字内容
// //Look for the OCG token in the stream as well as our watermarked text
// if (content.IndexOf("/OC") >= 0 || content.IndexOf(watermarkText) >= 0)//如果pdf内容包含水印文字
// {
// //Remove it by giving it zero length and zero data
// content = content.Replace(watermarkText, "");//替换水印文字为空
// byte[] byteArray = System.Text.Encoding.Default.GetBytes(content);//转换为byte[]
// stream.Put(PdfName.LENGTH, new PdfNumber(byteArray.Length));//重新指定大小
// stream.SetData(byteArray);//重新赋值
// }
// }
//}
}
//PdfStamper stamper = new PdfStamper(reader, new FileStream(DEST, FileMode.Create, FileAccess.ReadWrite));
MemoryStream mstream = new MemoryStream();
PdfStamper stamper = new PdfStamper(reader, mstream);
stamper.Close();
reader.Close();
return(mstream);
}
private void CreateRawContent(List <byte> rawContent, PdfObject pdfObject)
{
Type pdfObjectType = pdfObject.GetType();
if (pdfObjectType == typeof(PdfName))
{
rawContent.AddRange(pdfObject.GetBytes());
}
else if (pdfObjectType == typeof(PdfLiteral))
{
string t = pdfObject.ToString();
if (t == "EMC" || t == "BMC" || t == "BDC")
{
rawContent.Add(BYTE_SPACE);
}
rawContent.AddRange(pdfObject.GetBytes());
if (t == "BT")
{
rawContent.AddRange(BYTES_LINE_BREAK_WINDOWS);
}
if (t == "EMC" || t == "BMC" || t == "BDC")
{
rawContent.Add(BYTE_SPACE);
}
}
else if (pdfObjectType == typeof(PdfNumber))
{
rawContent.AddRange(pdfObject.GetBytes());
}
else if (pdfObjectType == typeof(PdfString))
{
rawContent.Add(BYTE_ROUND_OPENING_BRACKET);
byte[] objectBuffer = pdfObject.GetBytes();
foreach (byte objectByte in objectBuffer)
{
switch (objectByte)
{
case BYTE_CARRIAGE_RETURN:
{
rawContent.AddRange(BYTES_REVERSE_SOLIDUS_AND_CHAR_r);
break;
}
case BYTE_LINE_FEED:
{
rawContent.AddRange(BYTES_REVERSE_SOLIDUS_AND_CHAR_n);
break;
}
case BYTE_HORIZONTAL_TAB:
{
rawContent.AddRange(BYTES_REVERSE_SOLIDUS_AND_CHAR_t);
break;
}
case BYTE_BACKSPACE:
{
rawContent.AddRange(BYTES_REVERSE_SOLIDUS_AND_CHAR_b);
break;
}
case BYTE_FORM_FEED:
{
rawContent.AddRange(BYTES_REVERSE_SOLIDUS_AND_CHAR_f);
break;
}
case BYTE_ROUND_OPENING_BRACKET:
case BYTE_ROUND_CLOSING_BRACKET:
case BYTE_REVERSE_SOLIDUS:
{
rawContent.Add(BYTE_ESCAPE_CHAR);
rawContent.Add(objectByte);
break;
}
default:
{
rawContent.Add(objectByte);
break;
}
}
}
rawContent.Add(BYTE_ROUND_CLOSING_BRACKET);
}
else if (pdfObjectType == typeof(PdfDictionary))
{
rawContent.AddRange(BYTES_DOUBLE_ANGLE_OPENING_BRACKETS);
PdfDictionary dict = pdfObject as PdfDictionary;
foreach (PdfObject key in dict.Keys)
{
CreateRawContent(rawContent, key);
PdfName keyName = key as PdfName;
this.CreateRawContent(rawContent, dict.Get(keyName));
}
rawContent.AddRange(BYTES_DOUBLE_ANGLE_CLOSING_BRACKETS);
}
else if (pdfObjectType == typeof(PdfArray))
{
rawContent.Add(BYTE_SQUARE_OPENING_BRACKET);
PdfArray pa = pdfObject as PdfArray;
foreach (PdfObject obj in pa.ArrayList)
{
this.CreateRawContent(rawContent, obj);
}
rawContent.Add(BYTE_SQUARE_CLOSING_BRACKET);
}
else
{
rawContent.AddRange(pdfObject.GetBytes());
}
rawContent.Add(BYTE_SPACE);
}
void WriteObjectAddress(PdfObject value)
{
if (this.layout == PdfWriterLayout.Verbose)
this.WriteRaw(String.Format("{0} {1} obj % {2}\n",
value.ObjectID.ObjectNumber, value.ObjectID.GenerationNumber,
value.GetType().FullName));
else
this.WriteRaw(String.Format("{0} {1} obj\n", value.ObjectID.ObjectNumber, value.ObjectID.GenerationNumber));
}
