/** Hyphenates a word and returns the first part of it. To get
* the second part of the hyphenated word call <CODE>getHyphenatedWordPost()</CODE>.
* @param word the word to hyphenate
* @param font the font used by this word
* @param fontSize the font size used by this word
* @param remainingWidth the width available to fit this word in
* @return the first part of the hyphenated word including
* the hyphen symbol, if any
*/
virtual public string GetHyphenatedWordPre(string word, BaseFont font, float fontSize, float remainingWidth)
{
post = word;
string hyphen = this.HyphenSymbol;
float hyphenWidth = font.GetWidthPoint(hyphen, fontSize);
if (hyphenWidth > remainingWidth)
{
return("");
}
Hyphenation hyphenation = hyphenator.Hyphenate(word);
if (hyphenation == null)
{
return("");
}
int len = hyphenation.Length;
int k;
for (k = 0; k < len; ++k)
{
if (font.GetWidthPoint(hyphenation.GetPreHyphenText(k), fontSize) + hyphenWidth > remainingWidth)
{
break;
}
}
--k;
if (k < 0)
{
return("");
}
post = hyphenation.GetPostHyphenText(k);
return(hyphenation.GetPreHyphenText(k) + hyphen);
}
public void Dictionary()
{
//ExStart
//ExFor:Hyphenation.IsDictionaryRegistered(String)
//ExFor:Hyphenation.RegisterDictionary(String, String)
//ExFor:Hyphenation.UnregisterDictionary(String)
//ExSummary:Shows how to perform and verify hyphenation dictionary registration.
// Register a dictionary file from the local file system to the "de-CH" locale
Hyphenation.RegisterDictionary("de-CH", MyDir + "hyph_de_CH.dic");
// This method can be used to verify that a language has a matching registered hyphenation dictionary
Assert.True(Hyphenation.IsDictionaryRegistered("de-CH"));
// The dictionary file contains a long list of words in a specified language, and in this case it is German
// These words define a set of rules for hyphenating text (splitting words across lines)
// If we open a document with text of a language matching that of a registered dictionary,
// that dictionary's hyphenation rules will be applied and visible upon saving
Document doc = new Document(MyDir + "German text.docx");
doc.Save(ArtifactsDir + "Hyphenation.Dictionary.Registered.pdf");
// We can also un-register a dictionary to disable these effects on any documents opened after the operation
Hyphenation.UnregisterDictionary("de-CH");
Assert.False(Hyphenation.IsDictionaryRegistered("de-CH"));
doc = new Document(MyDir + "German text.docx");
doc.Save(ArtifactsDir + "Hyphenation.Dictionary.Unregistered.pdf");
//ExEnd
}
[Test] //ExSkip
public void RegisterDictionary()
{
// Set up a callback that tracks warnings that occur during hyphenation dictionary registration
WarningInfoCollection warningInfoCollection = new WarningInfoCollection();
Hyphenation.WarningCallback = warningInfoCollection;
// Register an English (US) hyphenation dictionary by stream
Stream dictionaryStream = new FileStream(MyDir + "hyph_en_US.dic", FileMode.Open, FileAccess.Read);
Hyphenation.RegisterDictionary("en-US", dictionaryStream);
// No warnings detected
Assert.AreEqual(0, warningInfoCollection.Count);
// Open a document with a German locale that might not get automatically hyphenated by Microsoft Word an english machine
Document doc = new Document(MyDir + "German text.docx");
// To hyphenate that document upon saving, we need a hyphenation dictionary for the "de-CH" language code
// This callback will handle the automatic request for that dictionary
Hyphenation.Callback = new CustomHyphenationDictionaryRegister();
// When we save the document, it will be hyphenated according to rules defined by the dictionary known by our callback
doc.Save(ArtifactsDir + "Hyphenation.RegisterDictionary.pdf");
// This dictionary contains two identical patterns, which will trigger a warning
Assert.AreEqual(1, warningInfoCollection.Count);
Assert.AreEqual(WarningType.MinorFormattingLoss, warningInfoCollection[0].WarningType);
Assert.AreEqual(WarningSource.Layout, warningInfoCollection[0].Source);
Assert.AreEqual("Hyphenation dictionary contains duplicate patterns. The only first found pattern will be used. " +
"Content can be wrapped differently.", warningInfoCollection[0].Description);
}
public void Dictionary()
{
//ExStart
//ExFor:Hyphenation.IsDictionaryRegistered(String)
//ExFor:Hyphenation.RegisterDictionary(String, String)
//ExFor:Hyphenation.UnregisterDictionary(String)
//ExSummary:Shows how to register a hyphenation dictionary.
// A hyphenation dictionary contains a list of strings that define hyphenation rules for the dictionary's language.
// When a document contains lines of text in which a word could be split up and continued on the next line,
// hyphenation will look through the dictionary's list of strings for that word's substrings.
// If the dictionary contains a substring, then hyphenation will split the word across two lines
// by the substring, and add a hyphen to the first half.
// Register a dictionary file from the local file system to the "de-CH" locale.
Hyphenation.RegisterDictionary("de-CH", MyDir + "hyph_de_CH.dic");
Assert.True(Hyphenation.IsDictionaryRegistered("de-CH"));
// Open a document containing text with a locale matching that of our dictionary,
// and save it to a fixed-page save format. The text in that document will be hyphenated.
Document doc = new Document(MyDir + "German text.docx");
Assert.True(doc.FirstSection.Body.FirstParagraph.Runs.OfType <Run>().All(
r => r.Font.LocaleId == new CultureInfo("de-CH").LCID));
doc.Save(ArtifactsDir + "Hyphenation.Dictionary.Registered.pdf");
// Re-load the document after un-registering the dictionary,
// and save it to another PDF, which will not have hyphenated text.
Hyphenation.UnregisterDictionary("de-CH");
Assert.False(Hyphenation.IsDictionaryRegistered("de-CH"));
doc = new Document(MyDir + "German text.docx");
doc.Save(ArtifactsDir + "Hyphenation.Dictionary.Unregistered.pdf");
//ExEnd
#if NET462 || NETCOREAPP2_1 || JAVA
Aspose.Pdf.Document pdfDoc = new Aspose.Pdf.Document(ArtifactsDir + "Hyphenation.Dictionary.Registered.pdf");
TextAbsorber textAbsorber = new TextAbsorber();
textAbsorber.Visit(pdfDoc);
Assert.True(textAbsorber.Text.Contains("La ob storen an deinen am sachen. Dop-\r\n" +
"pelte um da am spateren verlogen ge-\r\n" +
"kommen achtzehn blaulich."));
pdfDoc = new Aspose.Pdf.Document(ArtifactsDir + "Hyphenation.Dictionary.Unregistered.pdf");
textAbsorber = new TextAbsorber();
textAbsorber.Visit(pdfDoc);
Assert.True(textAbsorber.Text.Contains("La ob storen an deinen am sachen. \r\n" +
"Doppelte um da am spateren verlogen \r\n" +
"gekommen achtzehn blaulich."));
#endif
}
public void HyphenateWordsOfLanguages()
{
//ExStart:HyphenateWordsOfLanguages
Document doc = new Document(MyDir + "German text.docx");
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
Hyphenation.RegisterDictionary("de-CH", MyDir + "hyph_de_CH.dic");
doc.Save(ArtifactsDir + "WorkingWithHyphenation.HyphenateWordsOfLanguages.pdf");
//ExEnd:HyphenateWordsOfLanguages
}
public void IsDictionaryRegisteredEx()
{
//ExStart
//ExFor:Hyphenation.IsDictionaryRegistered(String)
//ExSummary:Shows how to open check if some dictionary is registered.
Document doc = new Document(MyDir + "Document.doc");
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
Assert.AreEqual(true, Hyphenation.IsDictionaryRegistered("en-US"));
//ExEnd
}
public void IsDictionaryRegisteredEx()
{
//ExStart
//ExFor:Hyphenation.IsDictionaryRegistered(string)
//ExSummary:Shows how to open check if some dictionary is registered.
Document doc = new Document(MyDir + "Document.doc");
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
Console.WriteLine(Hyphenation.IsDictionaryRegistered("en-US")); // True
//ExEnd
}
public void LoadHyphenationDictionaryForLanguage()
{
//ExStart:LoadHyphenationDictionaryForLanguage
Document doc = new Document(MyDir + "German text.docx");
Stream stream = File.OpenRead(MyDir + "hyph_de_CH.dic");
Hyphenation.RegisterDictionary("de-CH", stream);
doc.Save(ArtifactsDir + "WorkingWithHyphenation.LoadHyphenationDictionaryForLanguage.pdf");
//ExEnd:LoadHyphenationDictionaryForLanguage
}
public void UnregisteredDictionaryEx()
{
//ExStart
//ExFor:Hyphenation.UnregisterDictionary(String)
//ExSummary:Shows how to un-register a dictionary.
Document doc = new Document(MyDir + "Document.doc");
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
Hyphenation.UnregisterDictionary("en-US");
Assert.AreEqual(false, Hyphenation.IsDictionaryRegistered("en-US"));
//ExEnd
}
public void UnregisterDictionaryEx()
{
//ExStart
//ExFor:Hyphenation.UnregisterDictionary(string)
//ExSummary:Shows how to un-register a dictionary
Document doc = new Document(MyDir + "Document.doc");
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
Hyphenation.UnregisterDictionary("en-US");
Console.WriteLine(Hyphenation.IsDictionaryRegistered("en-US")); // False
//ExEnd
}
public static void Run()
{
//ExStart:LoadHyphenationDictionaryForLanguage
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_RenderingAndPrinting();
// Load the documents which store the shapes we want to render.
Document doc = new Document(dataDir + "TestFile RenderShape.doc");
Stream stream = File.OpenRead(dataDir + @"hyph_de_CH.dic");
Hyphenation.RegisterDictionary("de-CH", stream);
dataDir = dataDir + "LoadHyphenationDictionaryForLanguage_out_.pdf";
doc.Save(dataDir);
//ExEnd:LoadHyphenationDictionaryForLanguage
Console.WriteLine("\nHyphenation dictionary for special language loaded successfully.\nFile saved at " + dataDir);
}
public static void Run()
{
//ExStart:HyphenateWordsOfLanguages
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_RenderingAndPrinting();
// Load the documents which store the shapes we want to render.
Document doc = new Document(dataDir + "TestFile RenderShape.doc");
Hyphenation.RegisterDictionary("en-US", dataDir + @"hyph_en_US.dic");
Hyphenation.RegisterDictionary("de-CH", dataDir + @"hyph_de_CH.dic");
dataDir = dataDir + "HyphenateWordsOfLanguages_out_.pdf";
doc.Save(dataDir);
//ExEnd:HyphenateWordsOfLanguages
Console.WriteLine("\nWords of special languages hyphenate successfully.\nFile saved at " + dataDir);
}
public void RegisterDictionaryEx()
{
//ExStart
//ExFor:Hyphenation.RegisterDictionary(String, Stream)
//ExFor:Hyphenation.RegisterDictionary(String, String)
//ExSummary:Shows how to open and register a dictionary from a file.
Document doc = new Document(MyDir + "Document.doc");
// Register by String
Hyphenation.RegisterDictionary("en-US", MyDir + "hyph_en_US.dic");
// Register by stream
Stream dictionaryStream = new FileStream(MyDir + "hyph_de_CH.dic", FileMode.Open);
Hyphenation.RegisterDictionary("de-CH", dictionaryStream);
//ExEnd
}
public void RequestDictionary(string language)
{
Console.Write("Hyphenation dictionary requested: " + language);
if (Hyphenation.IsDictionaryRegistered(language))
{
Console.WriteLine(", is already registered.");
return;
}
if (mHyphenationDictionaryFiles.ContainsKey(language))
{
Hyphenation.RegisterDictionary(language, mHyphenationDictionaryFiles[language]);
Console.WriteLine(", successfully registered.");
return;
}
Console.WriteLine(", no respective dictionary file known by this Callback.");
}
public void SuppressHyphens(bool suppressAutoHyphens)
{
//ExStart
//ExFor:ParagraphFormat.SuppressAutoHyphens
//ExSummary:Shows how to suppress hyphenation for a paragraph.
Hyphenation.RegisterDictionary("de-CH", MyDir + "hyph_de_CH.dic");
Assert.True(Hyphenation.IsDictionaryRegistered("de-CH"));
// Open a document containing text with a locale matching that of our dictionary.
// When we save this document to a fixed page save format, its text will have hyphenation.
Document doc = new Document(MyDir + "German text.docx");
// We can set the "SuppressAutoHyphens" property to "true" to disable hyphenation
// for a specific paragraph while keeping it enabled for the rest of the document.
// The default value for this property is "false",
// which means every paragraph by default uses hyphenation if any is available.
doc.FirstSection.Body.FirstParagraph.ParagraphFormat.SuppressAutoHyphens = suppressAutoHyphens;
doc.Save(ArtifactsDir + "ParagraphFormat.SuppressHyphens.pdf");
//ExEnd
#if NET462 || NETCOREAPP2_1 || JAVA
Aspose.Pdf.Document pdfDoc = new Aspose.Pdf.Document(ArtifactsDir + "ParagraphFormat.SuppressHyphens.pdf");
TextAbsorber textAbsorber = new TextAbsorber();
textAbsorber.Visit(pdfDoc);
if (suppressAutoHyphens)
{
Assert.True(textAbsorber.Text.Contains("La ob storen an deinen am sachen. \r\n" +
"Doppelte um da am spateren verlogen \r\n" +
"gekommen achtzehn blaulich."));
}
else
{
Assert.True(textAbsorber.Text.Contains("La ob storen an deinen am sachen. Dop-\r\n" +
"pelte um da am spateren verlogen ge-\r\n" +
"kommen achtzehn blaulich."));
}
#endif
}
public void RequestDictionary(string language)
{
string dictionaryFolder = MyDir;
string dictionaryFullFileName;
switch (language)
{
case "en-US":
dictionaryFullFileName = Path.Combine(dictionaryFolder, "hyph_en_US.dic");
break;
case "de-CH":
dictionaryFullFileName = Path.Combine(dictionaryFolder, "hyph_de_CH.dic");
break;
default:
throw new Exception($"Missing hyphenation dictionary for {language}.");
}
// Register dictionary for requested language.
Hyphenation.RegisterDictionary(language, dictionaryFullFileName);
}
private IEnumerable <string> _GetSentence(string message)
{
var splitSymbol = new string[] { Environment.NewLine };
var tempText = Hyphenation.GetAdjustmentTextList(message, _UI.Sentence);
var textList = tempText.Split(splitSymbol, StringSplitOptions.None);
var dirty = true;
string newText;
int count = 0;
while (dirty && count < 30)
{
count++;
newText = string.Empty;
for (int i = 0; i < textList.Length; i++)
{
dirty = false;
if (i % 2 == 0 && textList[i].FirstOrDefault() != '「')
{
textList[i] = "「" + textList[i];
dirty = true;
}
if (i != 0 && (i + 1) % 2 == 0 && textList[i].LastOrDefault() != '」')
{
textList[i] += "」";
dirty = true;
}
}
for (int i = 0; i < textList.Length; i++)
{
newText += textList[i];
}
tempText = Hyphenation.GetAdjustmentTextList(newText, _UI.Sentence);
textList = tempText.Split(splitSymbol, StringSplitOptions.None);
}
return(textList);
}
private void ManipulatePdf(string dest)
{
// See hyphenation example of specified word in console
// For the correct run of sample, please, add an itext.hyph dependency,
// which could be found on the following web-page: https://mvnrepository.com/artifact/com.itextpdf/hyph
Hyphenation s = Hyphenator.Hyphenate("de", "DE", "Leistungsscheinziffer", 2, 2);
Console.Out.WriteLine(s);
PdfDocument pdfDoc = new PdfDocument(new PdfWriter(dest));
Document doc = new Document(pdfDoc);
doc.SetMargins(0, 0, 0, 0);
Table table = new Table(UnitValue.CreatePercentArray(1)).SetFixedLayout();
table.SetWidth(UnitValue.CreatePercentValue(10));
Text text = new Text("Leistungsscheinziffer");
text.SetHyphenation(new HyphenationConfig("de", "DE", 2, 2));
table.AddCell(new Cell().Add(new Paragraph(text)));
Paragraph paragraph = new Paragraph();
paragraph.SetHyphenation(new HyphenationConfig("de", "DE", 2, 2));
paragraph.Add("Leistungsscheinziffer");
table.AddCell(new Cell().Add(paragraph));
// soft hyphens
table.AddCell(new Cell().Add(new Paragraph("Le\u00adistun\u00ADgssch\u00ADeinziffe\u00ADr").SetHyphenation
(new HyphenationConfig(3, 2))));
doc.Add(table);
doc.Close();
}
protected internal override void decompose()
{
// get the hyphenation points
Hyphenation hyphens = hyphenator.hyphenate(termAtt.Buffer(), 0, termAtt.Length(), 1, 1);
// No hyphen points found -> exit
if (hyphens == null)
{
return;
}
int[] hyp = hyphens.HyphenationPoints;
for (int i = 0; i < hyp.Length; ++i)
{
int remaining = hyp.Length - i;
int start = hyp[i];
CompoundToken longestMatchToken = null;
for (int j = 1; j < remaining; j++)
{
int partLength = hyp[i + j] - start;
// if the part is longer than maxSubwordSize we
// are done with this round
if (partLength > this.maxSubwordSize)
{
break;
}
// we only put subwords to the token stream
// that are longer than minPartSize
if (partLength < this.minSubwordSize)
{
// BOGUS/BROKEN/FUNKY/WACKO: somehow we have negative 'parts' according to the
// calculation above, and we rely upon minSubwordSize being >=0 to filter them out...
continue;
}
// check the dictionary
if (dictionary == null || dictionary.Contains(termAtt.Buffer(), start, partLength))
{
if (this.onlyLongestMatch)
{
if (longestMatchToken != null)
{
if (longestMatchToken.txt.Length() < partLength)
{
longestMatchToken = new CompoundToken(this, start, partLength);
}
}
else
{
longestMatchToken = new CompoundToken(this, start, partLength);
}
}
else
{
tokens.AddLast(new CompoundToken(this, start, partLength));
}
}
else if (dictionary.contains(termAtt.buffer(), start, partLength - 1))
{
// check the dictionary again with a word that is one character
// shorter
// to avoid problems with genitive 's characters and other binding
// characters
if (this.onlyLongestMatch)
{
if (longestMatchToken != null)
{
if (longestMatchToken.txt.Length() < partLength - 1)
{
longestMatchToken = new CompoundToken(this, start, partLength - 1);
}
}
else
{
longestMatchToken = new CompoundToken(this, start, partLength - 1);
}
}
else
{
tokens.AddLast(new CompoundToken(this, start, partLength - 1));
}
}
}
if (this.onlyLongestMatch && longestMatchToken != null)
{
tokens.AddLast(longestMatchToken);
}
}
}
