public virtual void TestWithMultiFilteredRenderListener()
{
PdfDocument pdfDocument = new PdfDocument(new PdfReader(sourceFolder + "test.pdf"));
float x1;
float y1;
float x2;
float y2;
FilteredEventListener listener = new FilteredEventListener();
x1 = 122;
x2 = 22;
y1 = 678.9f;
y2 = 12;
ITextExtractionStrategy region1Listener = listener.AttachEventListener(new LocationTextExtractionStrategy(
), new TextRegionEventFilter(new Rectangle(x1, y1, x2, y2)));
x1 = 156;
x2 = 13;
y1 = 678.9f;
y2 = 12;
ITextExtractionStrategy region2Listener = listener.AttachEventListener(new LocationTextExtractionStrategy(
), new TextRegionEventFilter(new Rectangle(x1, y1, x2, y2)));
PdfCanvasProcessor parser = new PdfCanvasProcessor(new GlyphEventListener(listener));
parser.ProcessPageContent(pdfDocument.GetPage(1));
NUnit.Framework.Assert.AreEqual("Your", region1Listener.GetResultantText());
NUnit.Framework.Assert.AreEqual("dju", region2Listener.GetResultantText());
}
virtual public void TestWithMultiFilteredRenderListener()
{
PdfReader pdfReader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, "test.pdf");
PdfReaderContentParser parser = new PdfReaderContentParser(pdfReader);
float x1, y1, x2, y2;
MultiFilteredRenderListener listener = new MultiFilteredRenderListener();
x1 = 122;
x2 = 144;
y1 = 841.9f - 151;
y2 = 841.9f - 163;
ITextExtractionStrategy region1Listener = listener.AttachRenderListener(
new LocationTextExtractionStrategy(), new RegionTextRenderFilter(new Rectangle(x1, y1, x2, y2)));
x1 = 156;
x2 = 169;
y1 = 841.9f - 151;
y2 = 841.9f - 163;
ITextExtractionStrategy region2Listener = listener.AttachRenderListener(
new LocationTextExtractionStrategy(), new RegionTextRenderFilter(new Rectangle(x1, y1, x2, y2)));
parser.ProcessContent(1, new GlyphRenderListener(listener));
Assert.AreEqual("Your", region1Listener.GetResultantText());
Assert.AreEqual("dju", region2Listener.GetResultantText());
}
/// <summary>Extract text from a specified page using an extraction strategy.</summary>
/// <param name="page">the page for the text to be extracted from</param>
/// <param name="strategy">the strategy to use for extracting text</param>
/// <returns>the extracted text</returns>
public static String GetTextFromPage(PdfPage page, ITextExtractionStrategy strategy)
{
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy);
parser.ProcessPageContent(page);
return(strategy.GetResultantText());
}
/// <summary>Extract text from a specified page using an extraction strategy.</summary>
/// <remarks>
/// Extract text from a specified page using an extraction strategy.
/// Also allows registration of custom IContentOperators that can influence
/// how (and whether or not) the PDF instructions will be parsed.
/// </remarks>
/// <param name="page">the page for the text to be extracted from</param>
/// <param name="strategy">the strategy to use for extracting text</param>
/// <param name="additionalContentOperators">
/// an optional map of custom
/// <see cref="IContentOperator"/>
/// s for rendering instructions
/// </param>
/// <returns>the extracted text</returns>
public static String GetTextFromPage(PdfPage page, ITextExtractionStrategy strategy, IDictionary <String, IContentOperator
> additionalContentOperators)
{
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy, additionalContentOperators);
parser.ProcessPageContent(page);
return(strategy.GetResultantText());
}
public int Ocurrences(string searchTerm)
{
var count = 0;
var totalPages = PdfDocument.GetNumberOfPages();
for (int page = 1; page <= totalPages; page++)
{
FilteredTextEventListener listener = new FilteredTextEventListener(textExtractionStrategy);
var currentPage = PdfDocument.GetPage(page);
new PdfCanvasProcessor(listener).ProcessPageContent(currentPage);
if (RemoveDiacritics(textExtractionStrategy.GetResultantText().ToLowerInvariant())
.Contains(RemoveDiacritics(searchTerm.ToLowerInvariant())))
{
count++;
}
}
return(count);
}
/**
* This class delegates this call
* @see com.itextpdf.text.pdf.parser.TextExtractionStrategy#getResultantText()
*/
public virtual String GetResultantText()
{
return(deleg.GetResultantText());
}
public string GetResultantText()
{
return(deleg.GetResultantText());
}
static int Main(string[] args)
{
#region var declaration
bool verbose = false;
bool datedFileNames = false;
bool showRegexMatches = false;
string inputFilename = "";
bool inputFileExists;
string extension;
bool isPDF = false;
string outputDirname = "";
bool outputDirExsists = false;
uint splitType = 0x0;
string keySplitRegex = "";
#endregion
#region arg intake
// intake args and load values in to scope
var result = Parser.Default.ParseArguments <Options>(args);
result.WithParsed <Options>(o =>
{
inputFilename = o.inputFilename;
outputDirname = o.outputDirname;
if (o.verbose)
{
verbose = true;
}
if (o.datedFileNames)
{
datedFileNames = true;
}
if (o.showRegexMatches)
{
showRegexMatches = true;
}
if (!String.IsNullOrEmpty(o.keySplitRegex) && o.keySplitRegex.Length > 0)
{
splitType = splitType | 0x1;
keySplitRegex = o.keySplitRegex;
}
});
#endregion
#region verify input
// input file location
if (verbose)
{
Console.WriteLine("Input File:\t" + inputFilename);
}
inputFileExists = File.Exists(inputFilename);
if (verbose)
{
Console.WriteLine(inputFileExists ? "File exists:\tTrue" : "File exists:\tFalse");
}
if (!inputFileExists)
{
if (verbose)
{
Console.WriteLine("Input File does not exsist; Exiting with error code 1.");
}
#if DEBUG
Console.ReadKey();
#endif
return(1);
}
// input file format
extension = System.IO.Path.GetExtension(inputFilename).ToLower();
if (verbose)
{
Console.WriteLine("File format:\t" + extension);
}
isPDF = string.Equals(extension, ".pdf");
if (verbose)
{
Console.WriteLine(isPDF ? "Correct Format:\tTrue" : "Correct Format:\tFalse");
}
if (!isPDF)
{
if (verbose)
{
Console.WriteLine("Input File is not a PDF; Exiting with error code 2.");
}
#if DEBUG
Console.ReadKey();
#endif
return(2);
}
// output directory exsistance
if (verbose)
{
Console.WriteLine("Output to:\t" + outputDirname);
}
outputDirExsists = Directory.Exists(outputDirname);
if (verbose)
{
Console.WriteLine(outputDirExsists ? "Output valid:\tTrue" : "Output valid:\tFalse");
}
if (!outputDirExsists)
{
if (verbose)
{
Console.WriteLine("Output dir does not exsist; Exiting with error code 3.");
}
#if DEBUG
Console.ReadKey();
#endif
return(3);
}
#endregion
// Split
switch (splitType)
{
case 0x1: // key match
if (verbose)
{
Console.WriteLine("split type:\tKey");
}
if (verbose)
{
Console.WriteLine("Key regex:\t" + keySplitRegex);
}
Regex regex = new Regex(keySplitRegex, RegexOptions.Compiled | RegexOptions.Multiline);
PdfReader reader = new PdfReader(inputFilename);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
string regexKeyMatch = "";
int docPageStart = 1;
string newDocName = "";
for (int page = 1; page <= reader.NumberOfPages; page++)
{
if (showRegexMatches)
{
Console.WriteLine("Page: " + page);
}
ITextExtractionStrategy strategy = parser.ProcessContent
(page, new SimpleTextExtractionStrategy());
int matchCount = 0;
Match match = regex.Match(strategy.GetResultantText());
{
if (showRegexMatches)
{
Console.WriteLine("Match: " + (++matchCount));
}
for (int x = 1; x <= 2; x++)
{
Group group = match.Groups[x];
if (showRegexMatches)
{
Console.WriteLine("Group " + x + " = '" + group + "'");
}
CaptureCollection cc = group.Captures;
for (int y = 0; y < cc.Count; y++)
{
Capture capture = cc[y];
string captureS = capture.ToString();
if (!string.Equals(captureS, regexKeyMatch))
{
// if not first instance print last doc
if (page > 1)
{
ExtractPages(inputFilename, outputDirname + newDocName, docPageStart, (page - 1));
}
// reset the count
regexKeyMatch = captureS;
if (datedFileNames)
{
newDocName = DateTime.Now.ToString("yyyyMMdd") + "_" + captureS + ".pdf";
}
else
{
newDocName = captureS + ".pdf";
}
docPageStart = page;
if (verbose)
{
System.Console.WriteLine("New document at page:\t" + docPageStart);
}
}
if (showRegexMatches)
{
System.Console.WriteLine("Capture " + y + " = '" + capture + "', Position=" + capture.Index);
}
}
}
match = match.NextMatch();
}
}
break;
default:
if (verbose)
{
Console.WriteLine("No valid split type selected; Exiting with error code 4.");
}
#if DEBUG
Console.ReadKey();
#endif
return(4);
}
#if DEBUG
Console.ReadKey();
#endif
return(0);
}
public bool ReadPdf(string pdfFile, ref Documents doc, ref int pages)
{
bool success = false;
try
{
if (pdfFile.ToLower().Contains("pdf"))
{
StringBuilder textBuilder = new StringBuilder();
PdfReader r = new PdfReader(pdfFile);
pages = r.NumberOfPages;
for (int i = 1; i <= pages; i++)
{
PdfReaderContentParser parser = new PdfReaderContentParser(r);
ITextExtractionStrategy st = parser.ProcessContent <SimpleTextExtractionStrategy>(i, new SimpleTextExtractionStrategy());
string text = st.GetResultantText().Trim('\r', '\n', '\t', (char)32, (char)160);
if (!string.IsNullOrEmpty(text))
{
doc.DocBodyDic.Add(i, text);
}
else
{
text = PdfTextExtractor.GetTextFromPage(r, i).Trim('\r', '\n', '\t', (char)32, (char)160);
if (!string.IsNullOrEmpty(text))
{
doc.DocBodyDic.Add(i, text);
}
}
}
r.Close();
success = true;
}
else if (pdfFile.ToLower().Contains("doc"))
{
MsWord.Application newApp = null;
MsWord.Document msdoc = null;
try
{
int retry = 2;
while (retry > 0)
{
try
{
//newApp = (MsWord.Application)Marshal.GetActiveObject("Word.Application");
newApp = newApp == null ? new MsWord.Application() : newApp;
System.Threading.Thread.Sleep(1000);
//msdoc = newApp.ActiveDocument;
msdoc = newApp.Documents.Open(pdfFile);
System.Threading.Thread.Sleep(1000);
object nothing = Missing.Value;
MsWord.WdStatistic stat = MsWord.WdStatistic.wdStatisticPages;
int num = msdoc.ComputeStatistics(stat, ref nothing);
for (int i = 1; i <= num; i++)
{
if (doc.DocBodyDic.ContainsKey(i))
{
continue;
}
object objWhat = MsWord.WdGoToItem.wdGoToPage;
object objWhich = MsWord.WdGoToDirection.wdGoToAbsolute;
object objPage = (object)i;
MsWord.Range range1 = msdoc.GoTo(ref objWhat, ref objWhich, ref objPage, ref nothing);
MsWord.Range range2 = range1.GoToNext(MsWord.WdGoToItem.wdGoToPage);
object objStart = range1.Start;
object objEnd = range2.Start;
if (range1.Start == range2.Start)
{
objEnd = msdoc.Characters.Count;
}
Console.ForegroundColor = ConsoleColor.Red;
Console.WriteLine("DEBUG: Path: {0}, {1}-{2}........", pdfFile, objStart, objEnd);
Console.ResetColor();
if ((int)objStart <= (int)objEnd)
{
string innerText = msdoc.Range(ref objStart, ref objEnd).Text;
doc.DocBodyDic.Add(i, innerText);
}
}
success = true;
break;
}
catch (Exception ex)
{
Console.ForegroundColor = ConsoleColor.Red;
Console.WriteLine("Retry to read word {0}, Exception: {1}..", pdfFile, ex.ToString());
Console.ResetColor();
System.Threading.Thread.Sleep(1000);
retry--;
}
finally
{
if (newApp != null)
{
newApp.NormalTemplate.Saved = true;
if (msdoc != null)
{
msdoc.Close(false);
}
newApp.Quit();
}
}
}
}
catch (Exception e)
{
}
}
}
catch (Exception ex)
{
}
return(success);
}
/**
* This class delegates this call
* @see com.itextpdf.text.pdf.parser.TextExtractionStrategy#getResultantText()
*/
public virtual String GetResultantText(string lineposition)
{
return(deleg.GetResultantText(lineposition));
}