private void searchwords()
{
WordFinderConfig wordConfig = new WordFinderConfig();
wordConfig.IgnoreCharGaps = true;
using (WordFinder wordFinder = new WordFinder(PDFDoc, WordFinderVersion.Latest, wordConfig))
{
try // If we run into the security exception we will ask for a password and try again.
{
search_and_highlight(wordFinder);
}
catch (Exception e)
{
int errornumidx = e.ToString().IndexOf("Error number:");
if (errornumidx == -1)
{
throw e;
}
int colidx = e.ToString().IndexOf(": ", errornumidx);
if (colidx == -1)
{
throw e;
}
// We know that the error number we are wanting to find is formatted such as
// "Error number: 1073938472". All we need to do is parse out the next 10
// digits and if they are this number, then this is the exception we want
// to intercept and then ask for the document password.
errornumidx = colidx + 2;
string errornum = e.ToString().Substring(errornumidx, 10);
if (errornum != "1073938472")
{
throw e;
}
else
{
if (passwordenter() == true)
{
search_and_highlight(wordFinder);
}
else
{
/*
* If we null this then the next click of the search button
* will re-prompt us for a password and do the searching
* we are hoping for.
*/
SearchWord = null;
}
}
}
}
}
/**
* search -
*
* Does the actual searching of the wordlist in the document.
* Here we search one page at a time but it would be possible
* to search the entire document at once.
*/
private void search(int PageNum)
{
// create the config for the wordfinder
WordFinderConfig config = new WordFinderConfig();
config.IgnoreCharGaps = true;
// create a wordfinder for the current page
using (WordFinder wordFinder = new WordFinder(dleController.Document, WordFinderVersion.Latest, config))
{
IList <Word> wordsOnCurrentPage = wordsOnCurrentPage = wordFinder.GetWordList(PageNum);
// compare the search string to each word in the wordlist
foreach (Word w in wordsOnCurrentPage)
{
int searchIndex = 0;
// check if the word contains the search string
if (w.Text.ToLower().Contains(searchString.ToLower()))
{
//once we know it contains the search string we need to
// determine where in the word the string is
while (searchIndex < w.Text.Length)
{
int firstOccurence = w.Text.ToLower().IndexOf(searchString.ToLower(), searchIndex);
if (firstOccurence == -1 || firstOccurence >= w.Text.Length)
{
break;
}
// get the quad that should be highlighted by taking the left edge of the match
// and the right edge (determined by taking the top right and bottom right from
// taking the firstOccurence and adding the search string length)
Quad highlightQuad = new Quad(w.CharQuads[firstOccurence].TopLeft, w.CharQuads[firstOccurence + searchString.Length - 1].TopRight, w.CharQuads[firstOccurence].BottomLeft, w.CharQuads[firstOccurence + searchString.Length - 1].BottomRight);
highlightQuads.Insert(0, highlightQuad);
searchIndex = firstOccurence + searchString.Length;
}
}
}
}
if (highlightSelected == ApplicationHighlight.Highlight)
{
dleController.docView.DrawSearchRects(highlightQuads.ToArray());
}
}
static void Main(string[] args)
{
Console.WriteLine("UnderlinesAndHighlights Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = "../../Resources/Sample_Input/sample.pdf";
String sOutput = "../HighlightAndUnderlineAnnotations-out.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
if (args.Length > 1)
{
sOutput = args[1];
}
Document doc = new Document(sInput);
Console.WriteLine("Opened a document " + sInput);
Page docpage = doc.GetPage(0);
//
// Highlight occurrences of the word "cloudy" on the page.
// Underline occurrences of the word "rain" on the page.
//
// For a more in-depth example of using the WordFinder, see the TextExtraction sample.
//
List <Quad> cloudyQuads = new List <Quad>();
List <Quad> rainQuads = new List <Quad>();
WordFinderConfig wfc = new WordFinderConfig();
WordFinder wf = new WordFinder(doc, WordFinderVersion.Latest, wfc);
IList <Word> words = wf.GetWordList(docpage.PageNumber);
foreach (Word w in words)
{
// Store the Quads of all "Cloudy" words in a list for later use in
// creating the annotation.
if (w.Text.ToLower().Equals("cloudy") ||
((w.Attributes & WordAttributeFlags.HasTrailingPunctuation) == WordAttributeFlags.HasTrailingPunctuation &&
w.Text.ToLower().StartsWith("cloudy")))
{
cloudyQuads.AddRange(w.Quads);
}
// Store the Quads of all "Rain" words
if (w.Text.ToLower().Equals("rain") ||
((w.Attributes & WordAttributeFlags.HasTrailingPunctuation) == WordAttributeFlags.HasTrailingPunctuation &&
w.Text.ToLower().StartsWith("rain")))
{
rainQuads.AddRange(w.Quads);
}
}
HighlightAnnotation highlights = new HighlightAnnotation(docpage, cloudyQuads);
highlights.Color = new Color(1.0, 0.75, 1.0);
highlights.NormalAppearance = highlights.GenerateAppearance();
UnderlineAnnotation underlines = new UnderlineAnnotation(docpage, rainQuads);
underlines.Color = new Color(0.0, 0.0, 0.0);
underlines.NormalAppearance = underlines.GenerateAppearance();
// Read back the text that was annotated.
Console.WriteLine("Cloudy text: {0}", highlights.GetAnnotatedText(true));
Console.WriteLine("Rainy text: {0}", underlines.GetAnnotatedText(false));
doc.Save(SaveFlags.Full, sOutput);
}
}
static void Main(string[] args)
{
Console.WriteLine("RegexTextSearch Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/RegexTextSearch.pdf";
String sOutput = "RegexTextSearch-out.pdf";
// Highlight occurrences of the phrases that match this regular expression.
// Uncomment only the one you are interested in seeing displayed with highlights.
// Phone numbers
String sRegex = "((1-)?(\\()?\\d{3}(\\))?(\\s)?(-)?\\d{3}-\\d{4})";
// Email addresses
//String sRegex = "(\\b[\\w.!#$%&'*+\\/=?^`{|}~-]+@[\\w-]+(?:\\.[\\w-]+)*\\b)";
// URLs
//String sRegex = "((https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|www\\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9]+\\.[^\\s]{2,}|www\\.[a-zA-Z0-9]+\\.[^\\s]{2,}))";
if (args.Length > 0)
{
sInput = args[0];
}
using (Document doc = new Document(sInput))
{
int nPages = doc.NumPages;
Console.WriteLine("Input file: " + sInput);
WordFinderConfig wordConfig = new WordFinderConfig();
// Need to set this to true so phrases will be concatenated properly
wordConfig.NoHyphenDetection = true;
// Create a DocTextFinder with the default wordfinder parameters
using (DocTextFinder docTextFinder =
new DocTextFinder(doc, wordConfig))
{
// Retrieve the phrases matching a regular expression
IList <DocTextFinderMatch> docMatches =
docTextFinder.GetMatchList(0, nPages - 1, sRegex);
foreach (DocTextFinderMatch wInfo in docMatches)
{
// Show the matching phrase
Console.WriteLine(wInfo.MatchString);
// Get the quads
IList <DocTextFinderQuadInfo> QuadInfo = wInfo.QuadInfo;
// Iterate through the quad info and create highlights
foreach (DocTextFinderQuadInfo qInfo in QuadInfo)
{
Page docpage = doc.GetPage(qInfo.PageNum);
// Highlight the matched string words
var highlight = new HighlightAnnotation(docpage, qInfo.Quads);
highlight.NormalAppearance = highlight.GenerateAppearance();
}
}
// Save the document with the highlighted matched strings
doc.Save(SaveFlags.Full, sOutput);
}
}
}
}
static void Main(string[] args)
{
Console.WriteLine("RegexExtractText Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/RegexExtractText.pdf";
String sOutput = "../RegexExtractText-out.json";
// Uncomment only one regular expression you are interested in seeing the match information of (as a JSON file).
// Phone numbers
String sRegex = "((1-)?(\\()?\\d{3}(\\))?(\\s)?(-)?\\d{3}-\\d{4})";
// Email addresses
//String sRegex = "(\\b[\\w.!#$%&'*+\\/=?^`{|}~-]+@[\\w-]+(?:\\.[\\w-]+)*\\b)";
// URLs
//String sRegex = "((https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|www\\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9]+\\.[^\\s]{2,}|www\\.[a-zA-Z0-9]+\\.[^\\s]{2,}))";
if (args.Length > 0)
{
sInput = args[0];
}
using (Document doc = new Document(sInput))
{
int nPages = doc.NumPages;
Console.WriteLine("Input file: " + sInput);
// This will hold the JSON stream that we will print to the output JSON file.
DocTextFinderJson result = new DocTextFinderJson();
result.documentJson = new List <MatchObject>();
WordFinderConfig wordConfig = new WordFinderConfig();
// Need to set this to true so phrases will be concatenated properly.
wordConfig.NoHyphenDetection = true;
// Create a DocTextFinder with the default wordfinder parameters.
using (DocTextFinder docTextFinder =
new DocTextFinder(doc, wordConfig))
{
// Retrieve the phrases matching a regular expression.
IList <DocTextFinderMatch> docMatches =
docTextFinder.GetMatchList(0, nPages - 1, sRegex);
// Iterate through the matches and add match information to the DocTextFinderJson object.
foreach (DocTextFinderMatch wInfo in docMatches)
{
// This object will store the match phrase and an array of quads for the match.
MatchObject matchObject = new MatchObject();
// This list will store the page number and quad location for each match quad.
List <MatchQuadInformation> matchQuadInformationList = new List <MatchQuadInformation>();
// Set the match phrase in the matchObject.
matchObject.matchPhrase = wInfo.MatchString;
// Get the quads.
IList <DocTextFinderQuadInfo> QuadInfo = wInfo.QuadInfo;
foreach (DocTextFinderQuadInfo qInfo in QuadInfo)
{
MatchQuadInformation temp = new MatchQuadInformation();
temp.pageNumber = qInfo.PageNum;
// Iterate through the quads and insert the quad information into the matchQuadInformation object.
foreach (Quad quad in qInfo.Quads)
{
QuadLocation quadLocation = new QuadLocation();
quadLocation.topLeft = new TopLeft();
quadLocation.bottomLeft = new BottomLeft();
quadLocation.topRight = new TopRight();
quadLocation.bottomRight = new BottomRight();
quadLocation.topLeft.x = quad.TopLeft.H;
quadLocation.topLeft.y = quad.TopLeft.V;
quadLocation.bottomLeft.x = quad.BottomLeft.H;
quadLocation.bottomLeft.y = quad.BottomLeft.V;
quadLocation.topRight.x = quad.TopRight.H;
quadLocation.topRight.y = quad.TopRight.V;
quadLocation.bottomRight.x = quad.BottomRight.H;
quadLocation.bottomRight.y = quad.BottomRight.V;
temp.quadLocation = quadLocation;
matchQuadInformationList.Add(temp);
}
}
matchObject.matchQuads = matchQuadInformationList;
result.documentJson.Add(matchObject);
}
// Save the output JSON file.
Console.WriteLine("Writing JSON to " + sOutput);
string json = JsonConvert.SerializeObject(result.documentJson, Formatting.Indented);
System.IO.File.WriteAllText(sOutput, json);
}
}
}
}
static void Main(string[] args)
{
Console.WriteLine("ListWords Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = "../../Resources/Sample_Input/sample.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
Console.WriteLine("Input file: " + sInput);
Document doc = new Document(sInput);
int nPages = doc.NumPages;
WordFinderConfig wordConfig = new WordFinderConfig();
wordConfig.IgnoreCharGaps = true;
wordConfig.IgnoreLineGaps = false;
wordConfig.NoAnnots = true;
wordConfig.NoEncodingGuess = true; // leave non-Roman single-byte font alone
// Std Roman treatment for custom encoding; overrides the noEncodingGuess option
wordConfig.UnknownToStdEnc = false;
wordConfig.DisableTaggedPDF = true; // legacy mode WordFinder creation
wordConfig.NoXYSort = false;
wordConfig.PreserveSpaces = false;
wordConfig.NoLigatureExp = false;
wordConfig.NoHyphenDetection = false;
wordConfig.TrustNBSpace = false;
wordConfig.NoExtCharOffset = false; // text extraction efficiency
wordConfig.NoStyleInfo = false; // text extraction efficiency
WordFinder wordFinder = new WordFinder(doc, WordFinderVersion.Latest, wordConfig);
IList <Word> pageWords = null;
for (int i = 0; i < nPages; i++)
{
pageWords = wordFinder.GetWordList(i);
foreach (Word wInfo in pageWords)
{
string s = wInfo.Text;
IList <Quad> QuadList = wInfo.Quads;
foreach (Quad Q in QuadList)
{
Console.WriteLine(Q);
}
foreach (StyleTransition st in wInfo.StyleTransitions)
{
Console.WriteLine(st);
}
IList <StyleTransition> styleList = wInfo.StyleTransitions;
foreach (StyleTransition st in styleList)
{
Console.WriteLine(st);
}
Console.WriteLine(wInfo.Attributes);
Console.WriteLine(s);
}
}
Console.WriteLine("Pages=" + nPages);
}
}
static void Main(string[] args)
{
Console.WriteLine("TextExtract Sample:");
// ReSharper disable once UnusedVariable
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
// This is a tagged PDF.
String sInput = Library.ResourceDirectory + "Sample_Input/pdf_intro.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
// This is an untagged PDF.
//Resources/Sample_Input/constitution.pdf"
Document doc = new Document(sInput);
Console.WriteLine("Input file: " + sInput);
// Determine if the PDF is tagged. We'll use a slightly different set of rules
// for parsing tagged and untagged PDFs.
//
// We'll determine if the PDF is tagged by examining the MarkInfo
// dictionary of the document. First, check for the existence of the MarkInfo dict.
bool docIsTagged = false;
PDFDict markInfoDict;
PDFBoolean markedEntry;
if ((markInfoDict = (PDFDict)doc.Root.Get("MarkInfo")) != null)
{
if ((markedEntry = (PDFBoolean)markInfoDict.Get("Marked")) != null)
{
if (markedEntry.Value)
{
docIsTagged = true;
}
}
}
WordFinderConfig wordConfig = new WordFinderConfig();
wordConfig.IgnoreCharGaps = false;
wordConfig.IgnoreLineGaps = false;
wordConfig.NoAnnots = false;
wordConfig.NoEncodingGuess = false;
// Std Roman treatment for custom encoding; overrides the noEncodingGuess option
wordConfig.UnknownToStdEnc = false;
wordConfig.DisableTaggedPDF = false; // legacy mode WordFinder creation
wordConfig.NoXYSort = true;
wordConfig.PreserveSpaces = false;
wordConfig.NoLigatureExp = false;
wordConfig.NoHyphenDetection = false;
wordConfig.TrustNBSpace = false;
wordConfig.NoExtCharOffset = false; // text extraction efficiency
wordConfig.NoStyleInfo = false; // text extraction efficiency
WordFinder wordFinder = new WordFinder(doc, WordFinderVersion.Latest, wordConfig);
if (docIsTagged)
{
ExtractTextTagged(doc, wordFinder);
}
else
{
ExtractTextUntagged(doc, wordFinder);
}
}
}
static void Main(string[] args)
{
Console.WriteLine("Redactions Sample:");
// ReSharper disable once UnusedVariable
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/sample.pdf";
String sOutput1 = "Redactions-out.pdf";
String sOutput2 = "Redactions-out-applied.pdf";
if (args.Length > 0)
{
sInput = args[0];
}
Console.WriteLine("Input file: " + sInput);
Document doc = new Document(sInput);
Page docpage = doc.GetPage(0);
//
// Redact occurrences of the word "rain" on the page.
// Redact occurrences of the word "cloudy" on the page, changing the display details.
//
// For a more in-depth example of using the WordFinder, see the TextExtract sample.
//
// The TextExtract sample is described here.
// http://dev.datalogics.com/adobe-pdf-library/sample-program-descriptions/net-sample-programs/extracting-text-from-pdf-files
//
List <Quad> cloudyQuads = new List <Quad>();
List <Quad> rainQuads = new List <Quad>();
WordFinderConfig wordConfig = new WordFinderConfig();
WordFinder wf = new WordFinder(doc, WordFinderVersion.Latest, wordConfig);
IList <Word> words = wf.GetWordList(docpage.PageNumber);
foreach (Word w in words)
{
Console.WriteLine(" " + w.Text.ToLower());
// Store the Quads of all "Cloudy" words in a list for later use in
// creating the redaction object.
if (w.Text.ToLower().Equals("cloudy") ||
((w.Attributes & WordAttributeFlags.HasTrailingPunctuation) ==
WordAttributeFlags.HasTrailingPunctuation &&
w.Text.ToLower().StartsWith("cloudy")))
{
cloudyQuads.AddRange(w.Quads);
}
// Store the Quads of all "Rain" words
if (w.Text.ToLower().Equals("rain") ||
((w.Attributes & WordAttributeFlags.HasTrailingPunctuation) ==
WordAttributeFlags.HasTrailingPunctuation &&
w.Text.ToLower().StartsWith("rain")))
{
rainQuads.AddRange(w.Quads);
}
}
Console.WriteLine("Found Cloudy instances: " + cloudyQuads.Count);
Color red = new Color(1.0, 0.0, 0.0);
Color white = new Color(1.0);
Redaction not_cloudy = new Redaction(docpage, cloudyQuads, red);
/* fill the "normal" appearance with 20% red */
not_cloudy.FillNormal = true;
not_cloudy.SetFillColor(red, 0.25);
Console.WriteLine("Found rain instances: " + rainQuads.Count);
Redaction no_rain = new Redaction(docpage, rainQuads);
no_rain.InternalColor = new Color(0.0, 1.0, 0.0);
/* Fill the redaction with the word "rain", drawn in white */
no_rain.OverlayText = "rain";
no_rain.Repeat = true;
no_rain.ScaleToFit = true;
no_rain.TextColor = white;
no_rain.FontFace = "CourierStd";
no_rain.FontSize = 8.0;
doc.Save(SaveFlags.Full, sOutput1);
Console.WriteLine("Wrote a pdf doc with unapplied redactions.");
// actually all the redactions in the document
doc.ApplyRedactions();
doc.Save(SaveFlags.Full, sOutput2);
Console.WriteLine("Wrote a redacted pdf doc.");
}
}
static void Main(string[] args)
{
Console.WriteLine("AddRegexRedaction Sample:");
using (Library lib = new Library())
{
Console.WriteLine("Initialized the library.");
String sInput = Library.ResourceDirectory + "Sample_Input/AddRegexRedaction.pdf";
String sOutput1 = "AddRegexRedaction-out.pdf";
String sOutput2 = "AddRegexRedaction-out-applied.pdf";
// Highlight and redact occurrences of the phrases that match this regular expression.
// Uncomment only the one you are interested in seeing displayed redacted.
// Phone numbers
String sRegex = "((1-)?(\\()?\\d{3}(\\))?(\\s)?(-)?\\d{3}-\\d{4})";
// Email addresses
//String sRegex = "(\\b[\\w.!#$%&'*+\\/=?^`{|}~-]+@[\\w-]+(?:\\.[\\w-]+)*\\b)";
// URLs
//String sRegex = "((https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|www\\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\\.[^\\s]{2,}|https?:\\/\\/(?:www\\.|(?!www))[a-zA-Z0-9]+\\.[^\\s]{2,}|www\\.[a-zA-Z0-9]+\\.[^\\s]{2,}))";
if (args.Length > 0)
{
sInput = args[0];
}
using (Document doc = new Document(sInput))
{
int nPages = doc.NumPages;
Console.WriteLine("Input file: " + sInput);
// Create a WordFinder configuration
WordFinderConfig wordConfig = new WordFinderConfig();
// Need to set this to true so phrases will be concatenated properly
wordConfig.NoHyphenDetection = true;
// Create a DocTextFinder with the default wordfinder parameters
using (DocTextFinder docTextFinder =
new DocTextFinder(doc, wordConfig))
{
// Retrieve the phrases and words matching a regular expression
IList <DocTextFinderMatch> docMatches =
docTextFinder.GetMatchList(0, nPages - 1, sRegex);
// Redaction color will be red
Color red = new Color(1.0, 0.0, 0.0);
foreach (DocTextFinderMatch wInfo in docMatches)
{
// Show the matching phrase
Console.WriteLine(wInfo.MatchString);
// Get the quads
IList <DocTextFinderQuadInfo> QuadInfo = wInfo.QuadInfo;
// Iterate through the quad info and create highlights
foreach (DocTextFinderQuadInfo qInfo in QuadInfo)
{
Page docpage = doc.GetPage(qInfo.PageNum);
Redaction red_fill = new Redaction(docpage, qInfo.Quads, red);
/* fill the "normal" appearance with 25% red */
red_fill.FillNormal = true;
red_fill.SetFillColor(red, 0.25);
}
}
}
// Save the document with the highlighted matched strings
doc.Save(SaveFlags.Full, sOutput1);
Console.WriteLine("Wrote a PDF document with unapplied redactions.");
// Apply all the redactions in the document
doc.ApplyRedactions();
// Save the document with the redacted matched strings
doc.Save(SaveFlags.Full, sOutput2);
Console.WriteLine("Wrote a redacted PDF document.");
}
}
}
/* This function is copied primarily from the TextExtract sample,
* but modified to skip writing out the text that it finds
*/
static void FindTextUntagged(Document doc, String splitTextString, List <int> listOfPageNumsToSplit)
{
// setup the WordFinderConfig
WordFinderConfig wordConfig = new WordFinderConfig();
wordConfig.IgnoreCharGaps = false;
wordConfig.IgnoreLineGaps = false;
wordConfig.NoAnnots = false;
wordConfig.NoEncodingGuess = false;
// Std Roman treatment for custom encoding; overrides the noEncodingGuess option
wordConfig.UnknownToStdEnc = false;
wordConfig.DisableTaggedPDF = false; // legacy mode WordFinder creation
wordConfig.NoXYSort = true;
wordConfig.PreserveSpaces = false;
wordConfig.NoLigatureExp = false;
wordConfig.NoHyphenDetection = false;
wordConfig.TrustNBSpace = false;
wordConfig.NoExtCharOffset = false; // text extraction efficiency
wordConfig.NoStyleInfo = false; // text extraction efficiency
WordFinder wordFinder = new WordFinder(doc, WordFinderVersion.Latest, wordConfig);
int nPages = doc.NumPages;
IList <Word> pageWords = null;
for (int i = 0; i < nPages; i++)
{
pageWords = wordFinder.GetWordList(i);
String textToExtract = "";
// By default, this searches the entire page word list.
// You could limit it to the first X (e.g. 200) number of words as shown below if you know that the
// search string will fall within a certain number of words. If you wanted to only look within
// a specific quadrant of a page (e.g. lower right corner), you would need to get the bounding box
// of each Word and compare that to your target area.
int wordLoop = Math.Min(pageWords.Count, 200);
for (int wordnum = 0; wordnum < pageWords.Count; wordnum++)
//for (int wordnum = 0; wordnum < wordLoop; wordnum++) // limit by the fixt X number of Words
{
Word wInfo;
wInfo = pageWords[wordnum];
string s = wInfo.Text;
// Check for hyphenated words that break across a line.
if (((wInfo.Attributes & WordAttributeFlags.HasSoftHyphen) == WordAttributeFlags.HasSoftHyphen) &&
((wInfo.Attributes & WordAttributeFlags.LastWordOnLine) == WordAttributeFlags.LastWordOnLine))
{
// For the purposes of this sample, we'll remove all hyphens. In practice, you may need to check
// words against a dictionary to determine if the hyphenated word is actually one word or two.
string[] splitstrs = s.Split(new Char[] { '-', '\u00ad' });
textToExtract += splitstrs[0] + splitstrs[1];
}
else
{
textToExtract += s;
}
// Check for space adjacency and add a space if necessary.
if ((wInfo.Attributes & WordAttributeFlags.AdjacentToSpace) == WordAttributeFlags.AdjacentToSpace)
{
textToExtract += " ";
}
// Check for a line break and add one if necessary
if ((wInfo.Attributes & WordAttributeFlags.LastWordOnLine) == WordAttributeFlags.LastWordOnLine)
{
textToExtract += "\n";
}
}
//
if (textToExtract.ToUpper().Contains(splitTextString))
{
Console.WriteLine("Found " + splitTextString + " on page " + i);
listOfPageNumsToSplit.Add(i);
}
// Release requested WordList
for (int wordnum = 0; wordnum < pageWords.Count; wordnum++)
{
pageWords[wordnum].Dispose();
}
}
}