How to specify parameters in box-view API header? - box-view-api

I am using the following piece of C# code to upload, convert and download a .pptx file, via Box view API.
var boxViewID = "";
string boundary = "---------------------------" + DateTime.Now.Ticks.ToString("x");
byte[] boundarybytes = System.Text.Encoding.ASCII.GetBytes("\r\n--" + boundary + "\r\n");
String url_ = #"https://upload.view-api.box.com/1/documents";
HttpWebRequest wr = (HttpWebRequest)WebRequest.Create(url_);
wr.ContentType = "multipart/form-data; boundary=" + boundary;
wr.Headers.Add("Authorization:Token " + "MY_CODE"/*Configuration.BoxViewAPIKey*/);
wr.Method = "POST";
wr.KeepAlive = true;
wr.Credentials = System.Net.CredentialCache.DefaultCredentials;
wr.Timeout = 1000000;
wr.SendChunked = true;
DateTime start = DateTime.Now;
Exception exc = null;
Stream rs = wr.GetRequestStream();
try
{
rs.Write(boundarybytes, 0, boundarybytes.Length);
string headerTemplate = "Content-Disposition: form-data; name=\"{0}\"; non_svg=\"true\"; filename=\"{1}\"\r\nContent-Type: {2}\r\n\r\n";
string header = string.Format(headerTemplate,"file", file, contentType);
Console.WriteLine(header);
byte[] headerbytes = System.Text.Encoding.UTF8.GetBytes(header);
rs.Write(headerbytes, 0, headerbytes.Length);
FileStream fileStream = new FileStream(file, FileMode.Open, FileAccess.Read);
byte[] buffer = new byte[40960];
int bytesRead = 0;
int totalSent = 0;
int totalLength = (int)fileStream.Length;
while ((bytesRead = fileStream.Read(buffer, 0, buffer.Length)) != 0)
{
totalSent += bytesRead;
var percent = new decimal(100.0 * totalSent / totalLength);
if (progress != null)
{
progress("Box processing", percent);
}
rs.Write(buffer, 0, bytesRead);
}
fileStream.Close();
}
catch(Exception ex)
{
exc = ex;
}
DateTime end = DateTime.Now;
int seconds = (int)(end - start).TotalSeconds;
if(seconds>=0)
{
if(exc!=null)
{
throw exc;
}
}
byte[] trailer = System.Text.Encoding.ASCII.GetBytes("\r\n--" + boundary + "--\r\n");
rs.Write(trailer, 0, trailer.Length);
rs.Close();
WebResponse wresp = null;
try
{
wresp = wr.GetResponse();
Stream stream2 = wresp.GetResponseStream();
StreamReader reader2 = new StreamReader(stream2);
var res = reader2.ReadToEnd();
var docRes = Newtonsoft.Json.JsonConvert.DeserializeObject<Dictionary<string, string>>(res);
if (docRes["id"] != null)
boxViewID = docRes["id"];
}
catch (Exception ex)
{
if (wresp != null)
{
wresp.Close();
wresp = null;
}
}
finally
{
wr = null;
}
return boxViewID;
Specifying "non_svg" parameter should create .png images for every slide in the presentation (instead of .svg + .html pairs). However, the API seems to ignore this part of the request and I am always getting svg files.
Any idea on what am I doing wrong? Thanks!

The non_svg option causes PNG representations to be generated for each page, but the SVG representation is still generated. The viewer will only load the PNG files if SVG is not supported in the browser (basically only IE 8). Try changing page-1.svg to page-1.png in the browser (e.g., https://view-api.box.com/1/sessions/465c5d45caf04752a6113b0e5df593a5/assets/page-1.png vs https://view-api.box.com/1/sessions/465c5d45caf04752a6113b0e5df593a5/assets/page-1.svg). All of the assets will exist in content.zip if you use the documents content endpoint.

Related

Download link will download the file in system download path

Error Code with fileinnfo
FileInfo File = new FileInfo(Server.MapPath("/Content/ExcelFiles/SalesTarget.xlsx"));
if (File != null)
{
int Size = Convert.ToInt32(File.Length);
string FileName = File.FullName;
int Position = FileName.LastIndexOf("\\");
FileName = FileName.Substring(Position + 1);
string test = File.GetType().ToString();
string filepath = Server.MapPath("/Content/ExcelFiles/SalesTarget.xlsx");
string ContentType = MimeMapping.GetMimeMapping(Server.MapPath("/Content/ExcelFiles/SalesTarget.xlsx"));
byte[] FileData = new byte[Size];
char[] chars = Encoding.Unicode.GetChars(FileData);
StreamReader reader = new StreamReader(filepath);
reader.Read(chars, 0, Size); // Throwing error here
Response.ContentType = ContentType;
StringBuilder SB = new StringBuilder();
SB.Append("filename=");
SB.Append(FileName);
Response.AddHeader("Content-Disposition", SB.ToString());
Response.BinaryWrite(FileData);
Response.Flush();
Response.End();
//File..Read(FileData, 0, Size);
}
Running Code with Httppostedfile Class:
HttpPostedFileBase File = Request.Files["FileToLoad"];
if (File != null)
{
int Size = File.ContentLength;
if (Size <= 0)
{
ViewData["ERROR"] = "You uploaded an empty file,please browse a valid file to upload";
return View("../Shared/Error");
}
string FileName = File.FileName;
int Position = FileName.LastIndexOf("\\");
FileName = FileName.Substring(Position + 1);
string ContentType = File.ContentType;
byte[] FileData = new byte[Size];
File.InputStream.Read(FileData, 0, Size);
theModel.AddAFile(FileName, Size, ContentType, FileData);
}
I want to download existing file from directory instead of using httppostedfile, so I am getting error while reading file data.

Copying fields in iTextSharp 5.4.5.0

I was under the impression that it is now possible to copy AcroFields using PdfCopy. In the release notes for iText 5.4.4.0 this is listed as possible now. However, when I try to do so it appears all the annotations (I think I am using that term correctly, still fairly new to iText...) for the fields are stripped out. It looks like the fields are there (meaning I can see the blue boxes that indicate an editable field), but they are not editable. If I try to bring the PDF up in Acrobat I get a message saying that "there are no fields, would you like Acrobat to discover them?" and most are found and marked and fields properly (check boxes aren't, but the text fields are).
I assume there is an additional step somewhere along the lines to re-add the annotations to the PdfCopy object, but I do not see a way to get the annotations from the PdfReader. I also cannot seem to find any documentation on how to do this (since AcroFields were for so long not supported in PdfCopy most of what I find is along that vein).
Due to sensitivity I cannot provide a copy of the PDF's in question, but using an altered version of a test program used earlier you can see the issue with the following code. It should generate a table with some check boxes in the four right columns. If I use the exact same code with PdfCopyFields in the MergePdfs method instead of PdfCopy it works as expected. This code does not produce any text fields, but in my main project they are part of the original parent PDF that is used as a template.
(Sorry for the long example, it has been cherry picked from a much larger application. You will need a PDF with a field named "TableStartPosition" somewhere in it and update RunTest with the correct paths for your local machine to get this to work.)
Has the PdfCopy functionality not made it into iTextSharp yet? I am using version 5.4.5.0.
class Program
{
Stream _pdfTemplateStream;
MemoryStream _pdfResultStream;
PdfReader _pdfTemplateReader;
PdfStamper _pdfResultStamper;
static void Main(string[] args)
{
Program p = new Program();
try
{
p.RunTest();
}
catch (Exception f)
{
Console.WriteLine(f.Message);
Console.ReadLine();
}
}
internal void RunTest()
{
FileStream fs = File.OpenRead(#"C:\temp\a\RenameFieldTest\RenameFieldTest\Library\CoverPage.pdf");
_pdfTemplateStream = fs;
_pdfResultStream = new MemoryStream();
//PDFTemplateStream = new FileStream(_templatePath, FileMode.Open);
_pdfTemplateReader = new PdfReader(_pdfTemplateStream);
_pdfResultStamper = new PdfStamper(_pdfTemplateReader, _pdfResultStream);
#region setup objects
List<CustomCategory> Categories = new List<CustomCategory>();
CustomCategory c1 = new CustomCategory();
c1.CategorySizesInUse.Add(CustomCategory.AvailableSizes[1]);
c1.CategorySizesInUse.Add(CustomCategory.AvailableSizes[2]);
Categories.Add(c1);
CustomCategory c2 = new CustomCategory();
c2.CategorySizesInUse.Add(CustomCategory.AvailableSizes[0]);
c2.CategorySizesInUse.Add(CustomCategory.AvailableSizes[1]);
Categories.Add(c2);
List<CustomObject> Items = new List<CustomObject>();
CustomObject co1 = new CustomObject();
co1.Category = c1;
co1.Title = "Object 1";
Items.Add(co1);
CustomObject co2 = new CustomObject();
co2.Category = c2;
co2.Title = "Object 2";
Items.Add(co2);
#endregion
FillCoverPage(Items);
_pdfResultStamper.Close();
_pdfTemplateReader.Close();
List<MemoryStream> pdfStreams = new List<MemoryStream>();
pdfStreams.Add(new MemoryStream(_pdfResultStream.ToArray()));
MergePdfs(#"C:\temp\a\RenameFieldTest\RenameFieldTest\Library\Outfile.pdf", pdfStreams);
_pdfResultStream.Dispose();
_pdfTemplateStream.Dispose();
}
internal void FillCoverPage(List<CustomObject> Items)
{
//Before we start we need to figure out where to start adding the table
var fieldPositions = _pdfResultStamper.AcroFields.GetFieldPositions("TableStartPosition");
if (fieldPositions == null)
{ throw new Exception("Could not find the TableStartPosition field. Unable to determine point of origin for the table!"); }
_pdfResultStamper.AcroFields.RemoveField("TableStartPosition");
var fieldPosition = fieldPositions[0];
// Get the position of the field
var targetPosition = fieldPosition.position;
//First, get all the available card sizes
List<string> availableSizes = CustomCategory.AvailableSizes;
//Generate a table with the number of available card sizes + 1 for the device name
PdfPTable table = new PdfPTable(availableSizes.Count + 1);
float[] columnWidth = new float[availableSizes.Count + 1];
for (int y = 0; y < columnWidth.Length; y++)
{
if (y == 0)
{ columnWidth[y] = 320; }
else
{ columnWidth[y] = 120; }
}
table.SetTotalWidth(columnWidth);
table.WidthPercentage = 100;
PdfContentByte canvas;
List<PdfFormField> checkboxes = new List<PdfFormField>();
//Build the header row
table.Rows.Add(new PdfPRow(this.GetTableHeaderRow(availableSizes)));
//Insert the global check boxes
PdfPCell[] globalRow = new PdfPCell[availableSizes.Count + 1];
Phrase tPhrase = new Phrase("Select/Unselect All");
PdfPCell tCell = new PdfPCell();
tCell.BackgroundColor = BaseColor.LIGHT_GRAY;
tCell.AddElement(tPhrase);
globalRow[0] = tCell;
for (int x = 0; x < availableSizes.Count; x++)
{
tCell = new PdfPCell();
tCell.BackgroundColor = BaseColor.LIGHT_GRAY;
PdfFormField f = PdfFormField.CreateCheckBox(_pdfResultStamper.Writer);
string fieldName = string.Format("InkSaver.Global.chk{0}", availableSizes[x].Replace(".", ""));
//f.FieldName = fieldName;
string js = string.Format("hideAll(event.target, '{0}');", availableSizes[x].Replace(".", ""));
f.Action = PdfAction.JavaScript(js, _pdfResultStamper.Writer);
tCell.CellEvent = new ChildFieldEvent(_pdfResultStamper.Writer, f, fieldName);
globalRow[x + 1] = tCell;
checkboxes.Add(f);
}
table.Rows.Add(new PdfPRow(globalRow));
int status = 0;
int pageNum = 1;
for (int itemIndex = 0; itemIndex < Items.Count; itemIndex++)
{
tCell = new PdfPCell();
Phrase p = new Phrase(Items[itemIndex].Title);
tCell.AddElement(p);
tCell.HorizontalAlignment = Element.ALIGN_LEFT;
PdfPCell[] cells = new PdfPCell[availableSizes.Count + 1];
cells[0] = tCell;
for (int availCardSizeIndex = 0; availCardSizeIndex < availableSizes.Count; availCardSizeIndex++)
{
if (Items[itemIndex].Category.CategorySizesInUse.Contains(availableSizes[availCardSizeIndex]))
{
string str = availableSizes[availCardSizeIndex];
tCell = new PdfPCell();
tCell.PaddingLeft = 10f;
tCell.PaddingRight = 10f;
cells[availCardSizeIndex + 1] = tCell;
cells[availCardSizeIndex].HorizontalAlignment = Element.ALIGN_CENTER;
PdfFormField f = PdfFormField.CreateCheckBox(_pdfResultStamper.Writer);
string fieldName = string.Format("InkSaver.chk{0}.{1}", availableSizes[availCardSizeIndex].Replace(".", ""), itemIndex + 1);
//f.FieldName = fieldName; <-- This causes the checkbox to be double-named (i.e. InkSaver.Global.chk0.InkSaver.Global.chk0
string js = string.Format("hideCardSize(event.target, {0}, '{1}');", itemIndex + 1, availableSizes[availCardSizeIndex]);
f.Action = PdfAction.JavaScript(js, _pdfResultStamper.Writer);
tCell.CellEvent = new ChildFieldEvent(_pdfResultStamper.Writer, f, fieldName);
checkboxes.Add(f);
}
else
{
//Add a blank cell
tCell = new PdfPCell();
cells[availCardSizeIndex + 1] = tCell;
}
}
//Test if the column text will fit
table.Rows.Add(new PdfPRow(cells));
canvas = _pdfResultStamper.GetUnderContent(pageNum);
ColumnText ct2 = new ColumnText(canvas);
ct2.AddElement(new PdfPTable(table));
ct2.Alignment = Element.ALIGN_LEFT;
ct2.SetSimpleColumn(targetPosition.Left, 0, targetPosition.Right, targetPosition.Top, 0, 0);
status = ct2.Go(true);
if ((status != ColumnText.NO_MORE_TEXT) || (itemIndex == (Items.Count - 1)))
{
ColumnText ct3 = new ColumnText(canvas);
ct3.AddElement(table);
ct3.Alignment = Element.ALIGN_LEFT;
ct3.SetSimpleColumn(targetPosition.Left, 0, targetPosition.Right, targetPosition.Top, 0, 0);
ct3.Go();
foreach (PdfFormField f in checkboxes)
{
_pdfResultStamper.AddAnnotation(f, pageNum);
}
checkboxes.Clear();
if (itemIndex < (Items.Count - 1))
{
pageNum++;
_pdfResultStamper.InsertPage(pageNum, _pdfTemplateReader.GetPageSize(1));
table = new PdfPTable(availableSizes.Count + 1);
table.SetTotalWidth(columnWidth);
table.WidthPercentage = 100;
table.Rows.Add(new PdfPRow(this.GetTableHeaderRow(availableSizes)));
}
}
}
}
private PdfPCell[] GetTableHeaderRow(List<string> AvailableSizes)
{
PdfPCell[] sizeHeaders = new PdfPCell[AvailableSizes.Count + 1];
Phrase devName = new Phrase("Device Name");
PdfPCell deviceHeader = new PdfPCell(devName);
deviceHeader.HorizontalAlignment = Element.ALIGN_CENTER;
deviceHeader.BackgroundColor = BaseColor.GRAY;
sizeHeaders[0] = deviceHeader;
for (int x = 0; x < AvailableSizes.Count; x++)
{
PdfPCell hCell = new PdfPCell(new Phrase(AvailableSizes[x]));
hCell.HorizontalAlignment = Element.ALIGN_CENTER;
hCell.BackgroundColor = BaseColor.GRAY;
sizeHeaders[x + 1] = hCell;
}
return sizeHeaders;
}
public void MergePdfs(string filePath, List<MemoryStream> pdfStreams)
{
//Create output stream
FileStream outStream = new FileStream(filePath, FileMode.Create);
Document document = null;
if (pdfStreams.Count > 0)
{
try
{
int PageCounter = 0;
//Create Main reader
PdfReader reader = new PdfReader(pdfStreams[0]);
PageCounter = reader.NumberOfPages;//This is if we have multiple pages in the cover page, we need to adjust the offset.
//rename fields in the PDF. This is required because PDF's cannot have more than one field with the same name
RenameFields(reader, PageCounter++);
//Create Main Doc
document = new Document(reader.GetPageSizeWithRotation(1));
//Create main writer
PdfCopy Writer = new PdfCopy(document, outStream);
//PdfCopyFields Writer = new PdfCopyFields(outStream);
//Open document for writing
document.Open();
////Add pages
Writer.AddDocument(reader);
//For each additional pdf after first combine them into main document
foreach (var PdfStream in pdfStreams.Skip(1))
{
PdfReader reader2 = new PdfReader(PdfStream);
//rename PDF fields
RenameFields(reader2, PageCounter++);
// Add content
Writer.AddDocument(reader);
}
//Writer.AddJavaScript(PostProcessing.GetSuperscriptJavaScript());
Writer.Close();
}
catch (Exception ex)
{
Console.WriteLine(ex.ToString());
}
finally
{
if (document != null)
document.Close();
foreach (var Strm in pdfStreams)
{
try { if (null != Strm) Strm.Dispose(); }
catch { }
}
//pdfStamper.Close();
outStream.Close();
}
}
}
private void RenameFields(PdfReader reader, int PageNum)
{
int tempPageNum = 1;
//rename all fields
foreach (string field in reader.AcroFields.Fields.Keys)
{
if (((reader.AcroFields.GetFieldType(field) == 1) || (reader.AcroFields.GetFieldType(field) == 2)) && (field.StartsWith("InkSaver")))
{
//This is a InkSaver button, set the name so its subclassed
string classPath;
if (reader.AcroFields.GetFieldType(field) == 2)
{
classPath = field.Substring(0, field.LastIndexOf("."));
if (field.StartsWith("InkSaver.chk"))
{
int a = field.LastIndexOf(".");
string sub = field.Substring(a + 1, (field.Length - a - 1));
int pageNum = int.Parse(sub);
int realPageNum = pageNum + tempPageNum;//PostProcessing.Instance.CoverPageLength;
PageNum = realPageNum;
}
}
else
{
classPath = field.Substring(0, field.LastIndexOf("."));
}
string newID = classPath + ".page" + PageNum.ToString();
bool ret = reader.AcroFields.RenameField(field, newID);
}
else
{
reader.AcroFields.RenameField(field, field + "_" + PageNum.ToString());// field + Guid.NewGuid().ToString("N"));
}
}
}
}
public class ChildFieldEvent : IPdfPCellEvent
{
protected PdfWriter writer;
protected PdfFormField parent;
protected string checkBoxName;
internal ChildFieldEvent(PdfWriter writer, PdfFormField parent, string CheckBoxName)
{
this.writer = writer;
this.parent = parent;
this.checkBoxName = CheckBoxName;
}
public void CellLayout(PdfPCell cell, Rectangle rect, PdfContentByte[] cb)
{
createCheckboxField(rect);
}
private void createCheckboxField(Rectangle rect)
{
RadioCheckField bt = new RadioCheckField(this.writer, rect, this.checkBoxName, "Yes");
bt.CheckType = RadioCheckField.TYPE_SQUARE;
bt.Checked = true;
this.parent.AddKid(bt.CheckField);
}
}
internal class CustomCategory
{
internal static List<string> AvailableSizes
{
get
{
List<string> retVal = new List<string>();
retVal.Add("1");
retVal.Add("2");
retVal.Add("3");
retVal.Add("4");
return retVal;
}
}
internal CustomCategory()
{
CategorySizesInUse = new List<string>();
}
internal List<string> CategorySizesInUse { get; set; }
}
internal class CustomObject
{
internal string Title { get; set; }
internal CustomCategory Category { get;set; }
}
Please take a look at the MergeForms example. Your example is too long for me to read, but at first sight, I'm missing the following line:
copy.setMergeFields();
By the way, in MergeForms2, the fields are also renamed before the form is merged.

iText rotation creates pdf which displays out of memory exception

Following is a code snippet creating a pdf file where pages could be rotated in the resulting file. This works fine for most pdf files. But one particualr pdf file of version 1.6 the page is already rotated by 180, on applying further rotation to it e.g. 90 degress and saving the file causes it to get corrupted. Infact even if you don't rotate the file and simply write it out to another file using iText the file the resulting pdf is corrupted and displays an out of memory exception when opened in Adobe reader.
Why would that happen? Am I missing some sort of compression in the file.
private String createPdfFileWithoutForms(final EditStateData[] editStateData, final String directory)
throws EditingException {
Long startTime = System.currentTimeMillis();
File pdfFileToReturn = new File(directory + File.separator + UidGenerator.generate() + ".pdf");
com.lowagie.text.Document document = null;
FileOutputStream outputStream = null;
PdfCopy pdfCopy = null;
PdfReader reader = null;
PdfDictionary pageDict = null;
int rotationAngle = 0;
Map<Integer, Integer> rotationQuadrants = null;
try {
document = new com.lowagie.text.Document();
outputStream = new FileOutputStream(pdfFileToReturn);
pdfCopy = new PdfCopy(document, outputStream);
pdfCopy.setFullCompression();
pdfCopy.setCompressionLevel(9);
document.open();
for (EditStateData state : editStateData) {
try {
reader = new PdfReader(state.getFileName());
reader.selectPages(state.getPages());
rotationQuadrants = state.getRotationQuadrants();
for (int i = 1; i <= reader.getNumberOfPages(); i++) {
// Rotation quadrant key is the source page number
if (rotationQuadrants.containsKey(state.getPages().get(i - 1))) {
rotationAngle = reader.getPageRotation(i);
pageDict = reader.getPageN(i);
pageDict.put(PdfName.ROTATE,
new PdfNumber((rotationAngle
+ rotationQuadrants.get(state.getPages().get(i - 1))) % 360));
}
document.setPageSize(reader.getPageSizeWithRotation(i));
document.newPage();
// import the page from source pdf
PdfImportedPage page = pdfCopy.getImportedPage(reader, i);
// add the page to the destination pdf
pdfCopy.addPage(page);
}
} catch (final IOException e) {
LOGGER.error(e.getMessage(), e);
throw new EditingException(e.getMessage(), e);
} finally {
if (reader != null) {
reader.close();
}
}
}
} catch (final Exception e) {
LOGGER.error(e.getMessage(), e);
throw new EditingException(e.getMessage(), e);
} finally {
if (document != null) {
document.close();
}
if (pdfCopy != null) {
pdfCopy.close();
}
IoUtils.closeQuietly(outputStream);
}
LOGGER.debug("Combining " + editStateData.length + " pdf files took "
+ ((System.currentTimeMillis() - startTime) / 1000) + " msecs");
return pdfFileToReturn.getAbsolutePath();
}

Submitting a WebRequest from within a CLR Trigger

I just implemented a prototype solution for updating my caching server in real-time by assigning a CLR Trigger to a table so that whenever a certain column is updated the URL called from the trigger will update the caching server with the correct data.
It's working fine and the code is as follows:
[Microsoft.SqlServer.Server.SqlTrigger(Name = "AdStatusChanged", Target = "Ads", Event = "FOR UPDATE")]
public static void AdStatusChanged()
{
SqlTriggerContext triggContext = SqlContext.TriggerContext;
int adID = 0, adStatusID_Old = 0, adStatusID_New = 0;
if (triggContext.TriggerAction == TriggerAction.Update)
{
using (SqlConnection conn = new SqlConnection("context connection=true"))
{
conn.Open();
SqlCommand sqlComm = new SqlCommand();
SqlPipe sqlP = SqlContext.Pipe;
sqlComm.Connection = conn;
sqlComm.CommandText = "SELECT AdID, AdStatusID from INSERTED";
SqlDataReader reader = sqlComm.ExecuteReader();
if (reader.Read())
{
adID = reader.GetInt32(0);
adStatusID_New = reader.GetInt32(1);
}
reader.Close();
sqlComm.CommandText = "SELECT AdID, AdStatusID from DELETED WHERE AdID = " + adID;
reader = sqlComm.ExecuteReader();
if (reader.Read())
{
adID = reader.GetInt32(0);
adStatusID_Old = reader.GetInt32(1);
}
}
if (adID == 0 || adStatusID_New == adStatusID_Old)
{
// Check could be more thorough !
return;
}
WebResponse httpResponse = null;
try
{
string apiURL = string.Format("{0}/{1}", "http://localhost:14003/Home", "UpdateAdStatus?adID=" + adID + "&adStatusID=" + adStatusID_New);
var httpWebRequest = (HttpWebRequest)WebRequest.Create(apiURL);
httpWebRequest.Method = "GET";
httpResponse = (HttpWebResponse)httpWebRequest.GetResponse();
// check for successful response
}
catch (Exception ex)
{
Log("WebRequest from within SQL Server failed ! " + ex.Message);
}
finally
{
if (httpResponse != null)
{
httpResponse.Close();
}
}
}
}
I would like to have some expert/experienced views on the "CONS" of this approach regarding performance, deadlocks, sql crashing, or other areas that could be of potential concern.
Has anyone tried this (I'm sure many must have) and what was the result ? a successful implementation or did you revert to some other method or updating the cache real-time?

Extract images using iTextSharp

I have been using this code with great success to pull out the first image found in each page of a PDF. However, it is now not working with some new PDFs for an uknown reason. I have used other tools (Datalogics, etc) that do pull out the images fine with these new PDFs. However, I do not want to buy Datalogics or any tool if I can use iTextSharp. Can anybody tell me why this code is not finding the images in the PDF?
Knowns: my PDFs only have 1 image per page and nothing else.
using iTextSharp.text;
using iTextSharp.text.pdf;
...
public static void ExtractImagesFromPDF(string sourcePdf, string outputPath)
{
// NOTE: This will only get the first image it finds per page.
PdfReader pdf = new PdfReader(sourcePdf);
RandomAccessFileOrArray raf = new iTextSharp.text.pdf.RandomAccessFileOrArray(sourcePdf);
try
{
for (int pageNumber = 1; pageNumber <= pdf.NumberOfPages; pageNumber++)
{
PdfDictionary pg = pdf.GetPageN(pageNumber);
PdfDictionary res = (PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
PdfDictionary xobj = (PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
if (xobj != null)
{
foreach (PdfName name in xobj.Keys)
{
PdfObject obj = xobj.Get(name);
if (obj.IsIndirect())
{
PdfDictionary tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
PdfName type = (PdfName)PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE));
if (PdfName.IMAGE.Equals(type))
{
int XrefIndex = Convert.ToInt32(((PRIndirectReference)obj).Number.ToString(System.Globalization.CultureInfo.InvariantCulture));
PdfObject pdfObj = pdf.GetPdfObject(XrefIndex);
PdfStream pdfStrem = (PdfStream)pdfObj;
byte[] bytes = PdfReader.GetStreamBytesRaw((PRStream)pdfStrem);
if ((bytes != null))
{
using (System.IO.MemoryStream memStream = new System.IO.MemoryStream(bytes))
{
memStream.Position = 0;
System.Drawing.Image img = System.Drawing.Image.FromStream(memStream);
// must save the file while stream is open.
if (!Directory.Exists(outputPath))
Directory.CreateDirectory(outputPath);
string path = Path.Combine(outputPath, String.Format(#"{0}.jpg", pageNumber));
System.Drawing.Imaging.EncoderParameters parms = new System.Drawing.Imaging.EncoderParameters(1);
parms.Param[0] = new System.Drawing.Imaging.EncoderParameter(System.Drawing.Imaging.Encoder.Compression, 0);
System.Drawing.Imaging.ImageCodecInfo jpegEncoder = Utilities.GetImageEncoder("JPEG");
img.Save(path, jpegEncoder, parms);
break;
}
}
}
}
}
}
}
}
catch
{
throw;
}
finally
{
pdf.Close();
raf.Close();
}
}
I found that my problem was that I was not recursively searching inside of forms and groups for images. Basically, the original code would only find images that were embedded at the root of the pdf document. Here is the revised method plus a new method (FindImageInPDFDictionary) that recursively searches for images in the page. NOTE: the flaws of only supporting JPEG and non-compressed images still applies. See R Ubben's code for options to fix those flaws. HTH someone.
public static void ExtractImagesFromPDF(string sourcePdf, string outputPath)
{
// NOTE: This will only get the first image it finds per page.
PdfReader pdf = new PdfReader(sourcePdf);
RandomAccessFileOrArray raf = new iTextSharp.text.pdf.RandomAccessFileOrArray(sourcePdf);
try
{
for (int pageNumber = 1; pageNumber <= pdf.NumberOfPages; pageNumber++)
{
PdfDictionary pg = pdf.GetPageN(pageNumber);
// recursively search pages, forms and groups for images.
PdfObject obj = FindImageInPDFDictionary(pg);
if (obj != null)
{
int XrefIndex = Convert.ToInt32(((PRIndirectReference)obj).Number.ToString(System.Globalization.CultureInfo.InvariantCulture));
PdfObject pdfObj = pdf.GetPdfObject(XrefIndex);
PdfStream pdfStrem = (PdfStream)pdfObj;
byte[] bytes = PdfReader.GetStreamBytesRaw((PRStream)pdfStrem);
if ((bytes != null))
{
using (System.IO.MemoryStream memStream = new System.IO.MemoryStream(bytes))
{
memStream.Position = 0;
System.Drawing.Image img = System.Drawing.Image.FromStream(memStream);
// must save the file while stream is open.
if (!Directory.Exists(outputPath))
Directory.CreateDirectory(outputPath);
string path = Path.Combine(outputPath, String.Format(#"{0}.jpg", pageNumber));
System.Drawing.Imaging.EncoderParameters parms = new System.Drawing.Imaging.EncoderParameters(1);
parms.Param[0] = new System.Drawing.Imaging.EncoderParameter(System.Drawing.Imaging.Encoder.Compression, 0);
System.Drawing.Imaging.ImageCodecInfo jpegEncoder = Utilities.GetImageEncoder("JPEG");
img.Save(path, jpegEncoder, parms);
}
}
}
}
}
catch
{
throw;
}
finally
{
pdf.Close();
raf.Close();
}
}
private static PdfObject FindImageInPDFDictionary(PdfDictionary pg)
{
PdfDictionary res =
(PdfDictionary)PdfReader.GetPdfObject(pg.Get(PdfName.RESOURCES));
PdfDictionary xobj =
(PdfDictionary)PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT));
if (xobj != null)
{
foreach (PdfName name in xobj.Keys)
{
PdfObject obj = xobj.Get(name);
if (obj.IsIndirect())
{
PdfDictionary tg = (PdfDictionary)PdfReader.GetPdfObject(obj);
PdfName type =
(PdfName)PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE));
//image at the root of the pdf
if (PdfName.IMAGE.Equals(type))
{
return obj;
}// image inside a form
else if (PdfName.FORM.Equals(type))
{
return FindImageInPDFDictionary(tg);
} //image inside a group
else if (PdfName.GROUP.Equals(type))
{
return FindImageInPDFDictionary(tg);
}
}
}
}
return null;
}
Here is a simpler solution:
iTextSharp.text.pdf.parser.PdfImageObject pdfImage =
new iTextSharp.text.pdf.parser.PdfImageObject(imgPRStream);
System.Drawing.Image img = pdfImage.GetDrawingImage();
The following code incorporates all of Dave and R Ubben's ideas above, plus it returns a full list of all the images and also deals with multiple bit depths. I had to convert it to VB for the project I'm working on though, sorry about that...
Private Sub getAllImages(ByVal dict As pdf.PdfDictionary, ByVal images As List(Of Byte()), ByVal doc As pdf.PdfReader)
Dim res As pdf.PdfDictionary = CType(pdf.PdfReader.GetPdfObject(dict.Get(pdf.PdfName.RESOURCES)), pdf.PdfDictionary)
Dim xobj As pdf.PdfDictionary = CType(pdf.PdfReader.GetPdfObject(res.Get(pdf.PdfName.XOBJECT)), pdf.PdfDictionary)
If xobj IsNot Nothing Then
For Each name As pdf.PdfName In xobj.Keys
Dim obj As pdf.PdfObject = xobj.Get(name)
If (obj.IsIndirect) Then
Dim tg As pdf.PdfDictionary = CType(pdf.PdfReader.GetPdfObject(obj), pdf.PdfDictionary)
Dim subtype As pdf.PdfName = CType(pdf.PdfReader.GetPdfObject(tg.Get(pdf.PdfName.SUBTYPE)), pdf.PdfName)
If pdf.PdfName.IMAGE.Equals(subtype) Then
Dim xrefIdx As Integer = CType(obj, pdf.PRIndirectReference).Number
Dim pdfObj As pdf.PdfObject = doc.GetPdfObject(xrefIdx)
Dim str As pdf.PdfStream = CType(pdfObj, pdf.PdfStream)
Dim bytes As Byte() = pdf.PdfReader.GetStreamBytesRaw(CType(str, pdf.PRStream))
Dim filter As String = tg.Get(pdf.PdfName.FILTER).ToString
Dim width As String = tg.Get(pdf.PdfName.WIDTH).ToString
Dim height As String = tg.Get(pdf.PdfName.HEIGHT).ToString
Dim bpp As String = tg.Get(pdf.PdfName.BITSPERCOMPONENT).ToString
If filter = "/FlateDecode" Then
bytes = pdf.PdfReader.FlateDecode(bytes, True)
Dim pixelFormat As System.Drawing.Imaging.PixelFormat
Select Case Integer.Parse(bpp)
Case 1
pixelFormat = Drawing.Imaging.PixelFormat.Format1bppIndexed
Case 24
pixelFormat = Drawing.Imaging.PixelFormat.Format24bppRgb
Case Else
Throw New Exception("Unknown pixel format " + bpp)
End Select
Dim bmp As New System.Drawing.Bitmap(Int32.Parse(width), Int32.Parse(height), pixelFormat)
Dim bmd As System.Drawing.Imaging.BitmapData = bmp.LockBits(New System.Drawing.Rectangle(0, 0, Int32.Parse(width), Int32.Parse(height)), System.Drawing.Imaging.ImageLockMode.WriteOnly, pixelFormat)
Marshal.Copy(bytes, 0, bmd.Scan0, bytes.Length)
bmp.UnlockBits(bmd)
Using ms As New MemoryStream
bmp.Save(ms, System.Drawing.Imaging.ImageFormat.Png)
bytes = ms.GetBuffer
End Using
End If
images.Add(bytes)
ElseIf pdf.PdfName.FORM.Equals(subtype) Or pdf.PdfName.GROUP.Equals(subtype) Then
getAllImages(tg, images, doc)
End If
End If
Next
End If
End Sub
This is just another rehash of others' ideas, but the one that worked for me. Here I use #Malco's image grabbing snippet with R Ubben's looping:
private IList<System.Drawing.Image> GetImagesFromPdfDict(PdfDictionary dict, PdfReader doc)
{
List<System.Drawing.Image> images = new List<System.Drawing.Image>();
PdfDictionary res = (PdfDictionary)(PdfReader.GetPdfObject(dict.Get(PdfName.RESOURCES)));
PdfDictionary xobj = (PdfDictionary)(PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT)));
if (xobj != null)
{
foreach (PdfName name in xobj.Keys)
{
PdfObject obj = xobj.Get(name);
if (obj.IsIndirect())
{
PdfDictionary tg = (PdfDictionary)(PdfReader.GetPdfObject(obj));
PdfName subtype = (PdfName)(PdfReader.GetPdfObject(tg.Get(PdfName.SUBTYPE)));
if (PdfName.IMAGE.Equals(subtype))
{
int xrefIdx = ((PRIndirectReference)obj).Number;
PdfObject pdfObj = doc.GetPdfObject(xrefIdx);
PdfStream str = (PdfStream)(pdfObj);
iTextSharp.text.pdf.parser.PdfImageObject pdfImage =
new iTextSharp.text.pdf.parser.PdfImageObject((PRStream)str);
System.Drawing.Image img = pdfImage.GetDrawingImage();
images.Add(img);
}
else if (PdfName.FORM.Equals(subtype) || PdfName.GROUP.Equals(subtype))
{
images.AddRange(GetImagesFromPdfDict(tg, doc));
}
}
}
}
return images;
}
De c# version:
private IList<System.Drawing.Image> GetImagesFromPdfDict(PdfDictionary dict, PdfReader doc){
List<System.Drawing.Image> images = new List<System.Drawing.Image>();
PdfDictionary res = (PdfDictionary)(PdfReader.GetPdfObject(dict.Get(PdfName.RESOURCES)));
PdfDictionary xobj = (PdfDictionary)(PdfReader.GetPdfObject(res.Get(PdfName.XOBJECT)));
if (xobj != null)
{
foreach (PdfName name in xobj.Keys)
{
PdfObject obj = xobj.Get(name);
if (obj.IsIndirect())
{
PdfDictionary tg = (PdfDictionary)(PdfReader.GetPdfObject(obj));
pdf.PdfName subtype = (pdf.PdfName)(pdf.PdfReader.GetPdfObject(tg.Get(pdf.PdfName.SUBTYPE)));
if (pdf.PdfName.IMAGE.Equals(subtype))
{
int xrefIdx = ((pdf.PRIndirectReference)obj).Number;
pdf.PdfObject pdfObj = doc.GetPdfObject(xrefIdx);
pdf.PdfStream str = (pdf.PdfStream)(pdfObj);
byte[] bytes = pdf.PdfReader.GetStreamBytesRaw((pdf.PRStream)str);
string filter = tg.Get(pdf.PdfName.FILTER).ToString();
string width = tg.Get(pdf.PdfName.WIDTH).ToString();
string height = tg.Get(pdf.PdfName.HEIGHT).ToString();
string bpp = tg.Get(pdf.PdfName.BITSPERCOMPONENT).ToString();
if (filter == "/FlateDecode")
{
bytes = pdf.PdfReader.FlateDecode(bytes, true);
System.Drawing.Imaging.PixelFormat pixelFormat;
switch (int.Parse(bpp))
{
case 1:
pixelFormat = System.Drawing.Imaging.PixelFormat.Format1bppIndexed;
break;
case 24:
pixelFormat = System.Drawing.Imaging.PixelFormat.Format24bppRgb;
break;
default:
throw new Exception("Unknown pixel format " + bpp);
}
var bmp = new System.Drawing.Bitmap(Int32.Parse(width), Int32.Parse(height), pixelFormat);
System.Drawing.Imaging.BitmapData bmd = bmp.LockBits(new System.Drawing.Rectangle(0, 0, Int32.Parse(width),
Int32.Parse(height)), System.Drawing.Imaging.ImageLockMode.WriteOnly, pixelFormat);
Marshal.Copy(bytes, 0, bmd.Scan0, bytes.Length);
bmp.UnlockBits(bmd);
using (var ms = new MemoryStream())
{
bmp.Save(ms, System.Drawing.Imaging.ImageFormat.Png);
bytes = ms.GetBuffer();
}
}
images.Add(System.Drawing.Image.FromStream(new MemoryStream(bytes)));
}
else if (pdf.PdfName.FORM.Equals(subtype) || pdf.PdfName.GROUP.Equals(subtype))
{
images.AddRange(GetImagesFromPdfDict(tg, doc));
}
}
}
}
return images;
}
The above will only work with JPEGs. Excluding inline images and embedded files, you need to go through the objects of subtype IMAGE, then look at the filter and take the appropriate action. Here's an example, assuming we have a PdfObject of subtype IMAGE:
PdfReader pdf = new PdfReader("c:\\temp\\exp0.pdf");
int xo=pdf.XrefSize;
for (int i=0;i<xo;i++)
{
PdfObject obj=pdf.GetPdfObject(i);
if (obj!=null && obj.IsStream())
{
PdfDictionary pd=(PdfDictionary)obj;
if (pd.Contains(PdfName.SUBTYPE) && pd.Get(PdfName.SUBTYPE).ToString()=="/Image")
{
string filter=pd.Get(PdfName.FILTER).ToString();
string width=pd.Get(PdfName.WIDTH).ToString();
string height=pd.Get(PdfName.HEIGHT).ToString();
string bpp=pd.Get(PdfName.BITSPERCOMPONENT).ToString();
string extent=".";
byte [] img=null;
switch (filter)
{
case "/FlateDecode":
byte[] arr=PdfReader.FlateDecode(PdfReader.GetStreamBytesRaw((PRStream)obj),true);
Bitmap bmp=new Bitmap(Int32.Parse(width),Int32.Parse(height),PixelFormat.Format24bppRgb);
BitmapData bmd=bmp.LockBits(new Rectangle(0,0,Int32.Parse(width),Int32.Parse(height)),ImageLockMode.WriteOnly,
PixelFormat.Format24bppRgb);
Marshal.Copy(arr,0,bmd.Scan0,arr.Length);
bmp.UnlockBits(bmd);
bmp.Save("c:\\temp\\bmp1.png",ImageFormat.Png);
break;
default:
break;
}
}
}
}
This will mess the color up because of the Microsoft BGR, of course, but I wanted to keep it short. Do something similar for "/CCITTFaxDecode", etc.