org.mabb.fontverter.pdf

Class PdfFontExtractor

java.lang.Object

org.apache.pdfbox.contentstream.PDFStreamEngine

org.apache.pdfbox.text.PDFTextStripper

org.mabb.fontverter.pdf.PdfFontExtractor

public class PdfFontExtractor
extends org.apache.pdfbox.text.PDFTextStripper

Utility to extract all fonts in a given PDF

Field Summary

Fields inherited from class org.apache.pdfbox.text.PDFTextStripper

charactersByArticle, document, LINE_SEPARATOR, output

Constructor Summary

Constructors

Constructor and Description
PdfFontExtractor()

Method Summary

Modifier and Type	Method and Description
static FVFont	convertFont(org.apache.pdfbox.pdmodel.font.PDFont font, FontVerter.FontFormat format)
static FVFont	convertType0FontToOpenType(org.apache.pdfbox.pdmodel.font.PDType0Font font)
void	extractFontsToDir(byte[] pdf, String path)
void	extractFontsToDir(File pdf, String path)
void	extractFontsToDir(org.apache.pdfbox.pdmodel.PDDocument pdf, File path)
void	extractFontsToDir(org.apache.pdfbox.pdmodel.PDDocument pdf, String path)
List<FVFont>	extractToFVFonts(org.apache.pdfbox.pdmodel.PDDocument pdf)
List<org.apache.pdfbox.pdmodel.font.PDFont>	extractToPDFBoxFonts(org.apache.pdfbox.pdmodel.PDDocument pdf)
FontVerter.FontFormat	getExtractFormat()
static void	main(String[] args)
void	processPage(org.apache.pdfbox.pdmodel.PDPage page)
void	setExtractFormat(FontVerter.FontFormat extractFormat)
protected void	showGlyph(org.apache.pdfbox.util.Matrix arg0, org.apache.pdfbox.pdmodel.font.PDFont arg1, int arg2, String arg3, org.apache.pdfbox.util.Vector arg4)
protected void	tryExtractPageFonts()

Methods inherited from class org.apache.pdfbox.text.PDFTextStripper

endArticle, endDocument, endPage, getAddMoreFormatting, getArticleEnd, getArticleStart, getAverageCharTolerance, getCharactersByArticle, getCurrentPageNo, getDropThreshold, getEndBookmark, getEndPage, getIndentThreshold, getLineSeparator, getListItemPatterns, getOutput, getPageEnd, getPageStart, getParagraphEnd, getParagraphStart, getSeparateByBeads, getSortByPosition, getSpacingTolerance, getStartBookmark, getStartPage, getSuppressDuplicateOverlappingText, getText, getWordSeparator, matchPattern, processPages, processTextPosition, setAddMoreFormatting, setArticleEnd, setArticleStart, setAverageCharTolerance, setDropThreshold, setEndBookmark, setEndPage, setIndentThreshold, setLineSeparator, setListItemPatterns, setPageEnd, setPageStart, setParagraphEnd, setParagraphStart, setShouldSeparateByBeads, setSortByPosition, setSpacingTolerance, setStartBookmark, setStartPage, setSuppressDuplicateOverlappingText, setWordSeparator, startArticle, startArticle, startDocument, startPage, writeCharacters, writeLineSeparator, writePage, writePageEnd, writePageStart, writeParagraphEnd, writeParagraphSeparator, writeParagraphStart, writeString, writeString, writeText, writeWordSeparator

Methods inherited from class org.apache.pdfbox.contentstream.PDFStreamEngine

addOperator, applyTextAdjustment, beginText, endText, getAppearance, getCurrentPage, getGraphicsStackSize, getGraphicsState, getInitialMatrix, getResources, getTextLineMatrix, getTextMatrix, operatorException, processAnnotation, processChildStream, processOperator, processOperator, processSoftMask, processTilingPattern, processTilingPattern, processTransparencyGroup, processType3Stream, registerOperatorProcessor, restoreGraphicsStack, restoreGraphicsState, saveGraphicsStack, saveGraphicsState, setLineDashPattern, setTextLineMatrix, setTextMatrix, showAnnotation, showFontGlyph, showForm, showText, showTextString, showTextStrings, showTransparencyGroup, showType3Glyph, transformedPoint, transformWidth, unsupportedOperator

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

PdfFontExtractor

public PdfFontExtractor()
                 throws IOException

Throws:

IOException

Method Detail

main

public static void main(String[] args)
                 throws IOException

Throws:

IOException

extractFontsToDir

public void extractFontsToDir(File pdf,
                              String path)
                       throws IOException

Throws:

IOException

extractFontsToDir

public void extractFontsToDir(byte[] pdf,
                              String path)
                       throws IOException

Throws:

IOException

extractFontsToDir

public void extractFontsToDir(org.apache.pdfbox.pdmodel.PDDocument pdf,
                              File path)
                       throws IOException

Throws:

IOException

extractFontsToDir

public void extractFontsToDir(org.apache.pdfbox.pdmodel.PDDocument pdf,
                              String path)
                       throws IOException

Throws:

IOException

extractToFVFonts

public List<FVFont> extractToFVFonts(org.apache.pdfbox.pdmodel.PDDocument pdf)
                              throws IOException

Throws:

IOException

extractToPDFBoxFonts

public List<org.apache.pdfbox.pdmodel.font.PDFont> extractToPDFBoxFonts(org.apache.pdfbox.pdmodel.PDDocument pdf)
                                                                 throws IOException

Throws:

IOException

processPage

public void processPage(org.apache.pdfbox.pdmodel.PDPage page)
                 throws IOException

Overrides:

processPage in class org.apache.pdfbox.text.PDFTextStripper

Throws:

IOException

tryExtractPageFonts

protected void tryExtractPageFonts()

convertFont

public static FVFont convertFont(org.apache.pdfbox.pdmodel.font.PDFont font,
                                 FontVerter.FontFormat format)
                          throws IOException

Throws:

IOException

convertType0FontToOpenType

public static FVFont convertType0FontToOpenType(org.apache.pdfbox.pdmodel.font.PDType0Font font)
                                         throws IOException

Throws:

IOException

getExtractFormat

public FontVerter.FontFormat getExtractFormat()

setExtractFormat

public void setExtractFormat(FontVerter.FontFormat extractFormat)

showGlyph

protected void showGlyph(org.apache.pdfbox.util.Matrix arg0,
                         org.apache.pdfbox.pdmodel.font.PDFont arg1,
                         int arg2,
                         String arg3,
                         org.apache.pdfbox.util.Vector arg4)
                  throws IOException

Overrides:

showGlyph in class org.apache.pdfbox.contentstream.PDFStreamEngine

Throws:

IOException