Class TextExtractor.Word
TextExtractor.Word object represents a word on a PDF page. Each word contains a sequence of characters in one or more styles (see TextExtractor.Style).
Inheritance
Namespace: pdftron.PDF
Assembly: PDFNetAndroid.dll
Syntax
public class Word : IDisposableConstructors
Word()
Declaration
public Word()Methods
Dispose()
Declaration
public void Dispose()Dispose(Boolean)
Declaration
protected virtual void Dispose(bool disposing)Parameters
| Type | Name | Description |
|---|---|---|
| System.Boolean | disposing |
Equals(Object)
Checks whether this Word object is the same as the opject specified.
Declaration
public override bool Equals(Object o)Parameters
| Type | Name | Description |
|---|---|---|
| Object | o | specified object |
Returns
| Type | Description |
|---|---|
| System.Boolean | true if equals to the specified object |
Finalize()
Releases all resources used by the Word
Declaration
protected void Finalize()GetBBox()
Gets the b box.
Declaration
public Rect GetBBox()Returns
| Type | Description |
|---|---|
| Rect | The bounding box for this word (in unrotated page coordinates). |
Remarks
To account for the effect of page '/Rotate' attribute, transform all points using page.GetDefaultMatrix().
GetCharStyle(Int32)
Gets the char style.
Declaration
public TextExtractor.Style GetCharStyle(Int32 char_idx)Parameters
| Type | Name | Description |
|---|---|---|
| Int32 | char_idx | The index of a character in this word. |
Returns
| Type | Description |
|---|---|
| TextExtractor.Style | The style associated with a given character. |
GetCurrentNum()
Gets the index of this word of the current line. A word that starts the line will return 0, whereas the last word in the line will return (line.GetNumWords()-1).
Declaration
public Int32 GetCurrentNum()Returns
| Type | Description |
|---|---|
| Int32 | the index of this word of the current line |
GetGlyphQuad(Int32)
Gets the glyph from index
Declaration
public double[] GetGlyphQuad(Int32 glyph_idx)Parameters
| Type | Name | Description |
|---|---|---|
| Int32 | glyph_idx | The index of a glyph in this word. |
Returns
| Type | Description |
|---|---|
| System.Double[] | The quadrilateral representing a tight bounding box for a given glyph in the word (in unrotated page coordinates). |
GetNextWord()
Gets the next object
Declaration
public TextExtractor.Word GetNextWord()Returns
| Type | Description |
|---|---|
| TextExtractor.Word | the next object |
GetNumGlyphs()
Gets the num glyphs.
Declaration
public Int32 GetNumGlyphs()Returns
| Type | Description |
|---|---|
| Int32 | The number of glyphs in this word. |
GetQuad()
return The quadrilateral representing a tight bounding box for this word (in unrotated page coordinates).
Declaration
public double[] GetQuad()Returns
| Type | Description |
|---|---|
| System.Double[] | the quad |
GetString()
Gets Unicode string
Declaration
public String GetString()Returns
| Type | Description |
|---|---|
| String | the content of this word represented as a Unicode string. |
GetStringLen()
Gets the number of chars in the string.
Declaration
public Int32 GetStringLen()Returns
| Type | Description |
|---|---|
| Int32 | the number of characters in this word. |
GetStyle()
Gets predominant style for this word.
Declaration
public TextExtractor.Style GetStyle()Returns
| Type | Description |
|---|---|
| TextExtractor.Style | the style |
IsValid()
Checks if valid word
Declaration
public bool IsValid()Returns
| Type | Description |
|---|---|
| System.Boolean | true if this is a valid word, false otherwise. |
op_Assign(TextExtractor.Word)
Assignment operator
Declaration
public TextExtractor.Word op_Assign(TextExtractor.Word r)Parameters
| Type | Name | Description |
|---|---|---|
| TextExtractor.Word | r | a given |
Returns
| Type | Description |
|---|---|
| TextExtractor.Word |
|
Set(TextExtractor.Word)
Sets value to given Word object
Declaration
public void Set(TextExtractor.Word r)Parameters
| Type | Name | Description |
|---|---|---|
| TextExtractor.Word | r | a given |
Operators
Equality(TextExtractor.Word, TextExtractor.Word)
Equality operator check whether two Word objects are the same.
Declaration
public static Boolean operator ==(TextExtractor.Word l, TextExtractor.Word r)Parameters
| Type | Name | Description |
|---|---|---|
| TextExtractor.Word | l |
|
| TextExtractor.Word | r |
|
Returns
| Type | Description |
|---|---|
| Boolean | true if both |
Inequality(TextExtractor.Word, TextExtractor.Word)
Inequality operator check whether two Word objects are different.
Declaration
public static Boolean operator !=(TextExtractor.Word l, TextExtractor.Word r)Parameters
| Type | Name | Description |
|---|---|---|
| TextExtractor.Word | l |
|
| TextExtractor.Word | r |
|
Returns
| Type | Description |
|---|---|
| Boolean | true if both |