public class PDF2HTMLImportStripper
extends org.apache.pdfbox.text.PDFTextStripper
| Constructor and Description |
|---|
PDF2HTMLImportStripper(org.apache.pdfbox.pdmodel.PDDocument document) |
| Modifier and Type | Method and Description |
|---|---|
void |
drawHTMLFields() |
String |
getHTML() |
com.hp.gagawa.java.Node |
getHTMLBase() |
com.alibaba.fastjson.JSONArray |
getOnValues(org.apache.pdfbox.pdmodel.interactive.form.PDButton pdField) |
ArrayList<String> |
getPageImages() |
protected void |
processOperator(org.apache.pdfbox.contentstream.operator.Operator operator,
List<org.apache.pdfbox.cos.COSBase> operands) |
protected void |
processTextPosition(org.apache.pdfbox.text.TextPosition text) |
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) |
void |
stripPage(int page,
String img) |
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, processPage, processPages, 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, writeWordSeparatoraddOperator, applyTextAdjustment, beginText, endText, getAppearance, getCurrentPage, getGraphicsStackSize, getGraphicsState, getInitialMatrix, getResources, getTextLineMatrix, getTextMatrix, operatorException, processAnnotation, processChildStream, processOperator, processSoftMask, processTilingPattern, processTilingPattern, processTransparencyGroup, processType3Stream, registerOperatorProcessor, restoreGraphicsStack, restoreGraphicsState, saveGraphicsStack, saveGraphicsState, setLineDashPattern, setTextLineMatrix, setTextMatrix, showAnnotation, showFontGlyph, showForm, showText, showTextString, showTextStrings, showTransparencyGroup, showType3Glyph, transformedPoint, transformWidth, unsupportedOperatorpublic PDF2HTMLImportStripper(org.apache.pdfbox.pdmodel.PDDocument document)
throws IOException
IOExceptionpublic String getHTML()
public com.hp.gagawa.java.Node getHTMLBase()
protected void processOperator(org.apache.pdfbox.contentstream.operator.Operator operator,
List<org.apache.pdfbox.cos.COSBase> operands)
throws IOException
processOperator in class org.apache.pdfbox.contentstream.PDFStreamEngineIOExceptionpublic void stripPage(int page,
String img)
throws IOException
IOExceptionpublic com.alibaba.fastjson.JSONArray getOnValues(org.apache.pdfbox.pdmodel.interactive.form.PDButton pdField)
public void drawHTMLFields()
protected void processTextPosition(org.apache.pdfbox.text.TextPosition text)
processTextPosition in class org.apache.pdfbox.text.PDFTextStripperprotected 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
showGlyph in class org.apache.pdfbox.contentstream.PDFStreamEngineIOExceptionCopyright © 2020 XIMA MEDIA GmbH. All rights reserved.