protected static class AbstractTextAnalyzer.DefaultTextStripper
extends org.apache.pdfbox.text.PDFTextStripper
Modifier and Type | Field and Description |
---|---|
protected Set<TextInfo> |
infoSet
文本信息列表
|
protected org.apache.commons.logging.Log |
log
日志
|
protected Integer |
pageIndex
页面索引
|
Constructor and Description |
---|
DefaultTextStripper(Integer pageIndex,
org.apache.commons.logging.Log log)
有参构造
|
DefaultTextStripper(Integer pageIndex,
String wordSeparator,
org.apache.commons.logging.Log log)
有参构造
|
Modifier and Type | Method and Description |
---|---|
protected float |
computeFontHeight(PDFont arg0) |
protected String |
getFontName(String fontName)
获取字体名称
|
protected void |
showGlyph(org.apache.pdfbox.util.Matrix arg0,
PDFont arg1,
int arg2,
org.apache.pdfbox.util.Vector arg3) |
protected void |
writeString(String content,
List<org.apache.pdfbox.text.TextPosition> textPositions)
写入字符串
|
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, 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, writeText, writeWordSeparator
addOperator, applyTextAdjustment, beginMarkedContentSequence, beginText, decreaseLevel, endMarkedContentSequence, endText, getAppearance, getCurrentPage, getGraphicsStackSize, getGraphicsState, getInitialMatrix, getLevel, getResources, getTextLineMatrix, getTextMatrix, increaseLevel, operatorException, processAnnotation, processChildStream, processOperator, processOperator, processSoftMask, processTilingPattern, processTilingPattern, processTransparencyGroup, processType3Stream, restoreGraphicsStack, restoreGraphicsState, saveGraphicsStack, saveGraphicsState, setLineDashPattern, setTextLineMatrix, setTextMatrix, showAnnotation, showFontGlyph, showForm, showText, showTextString, showTextStrings, showTransparencyGroup, showType3Glyph, transformedPoint, transformWidth, unsupportedOperator
protected org.apache.commons.logging.Log log
protected Integer pageIndex
public DefaultTextStripper(Integer pageIndex, org.apache.commons.logging.Log log)
pageIndex
- 页面索引log
- 日志protected void writeString(String content, List<org.apache.pdfbox.text.TextPosition> textPositions)
writeString
in class org.apache.pdfbox.text.PDFTextStripper
content
- 文本内容textPositions
- 文本坐标列表protected String getFontName(String fontName)
fontName
- 字体名称protected void showGlyph(org.apache.pdfbox.util.Matrix arg0, PDFont arg1, int arg2, org.apache.pdfbox.util.Vector arg3) throws IOException
showGlyph
in class org.apache.pdfbox.contentstream.PDFStreamEngine
IOException
protected float computeFontHeight(PDFont arg0) throws IOException
IOException
Copyright © 2024. All rights reserved.