doc.html
来自「网络爬虫开源代码」· HTML 代码 · 共 314 行
HTML
314 行
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><!--NewPage--><HTML><HEAD><!-- Generated by javadoc (build 1.5.0_07) on Sun May 06 17:59:51 GMT 2007 --><TITLE>Doc (Heritrix 1.12.1)</TITLE><META NAME="keywords" CONTENT="org.archive.util.ms.Doc class"><LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../stylesheet.css" TITLE="Style"><SCRIPT type="text/javascript">function windowTitle(){ parent.document.title="Doc (Heritrix 1.12.1)";}</SCRIPT><NOSCRIPT></NOSCRIPT></HEAD><BODY BGCOLOR="white" onload="windowTitle();"><!-- ========= START OF TOP NAVBAR ======= --><A NAME="navbar_top"><!-- --></A><A HREF="#skip-navbar_top" title="Skip navigation links"></A><TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""><TR><TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"><A NAME="navbar_top_firstrow"><!-- --></A><TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> <TR ALIGN="center" VALIGN="top"> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/Doc.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../org/archive/util/ms/DefaultEntry.html" title="class in org.archive.util.ms"><B>PREV CLASS</B></A> <A HREF="../../../../org/archive/util/ms/Entry.html" title="interface in org.archive.util.ms"><B>NEXT CLASS</B></A></FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../index.html?org/archive/util/ms/Doc.html" target="_top"><B>FRAMES</B></A> <A HREF="Doc.html" target="_top"><B>NO FRAMES</B></A> <SCRIPT type="text/javascript"> <!-- if(window==top) { document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>'); } //--></SCRIPT><NOSCRIPT> <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A></NOSCRIPT></FONT></TD></TR><TR><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> SUMMARY: NESTED | FIELD | CONSTR | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: FIELD | CONSTR | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_top"></A><!-- ========= END OF TOP NAVBAR ========= --><HR><!-- ======== START OF CLASS DATA ======== --><H2><FONT SIZE="-1">org.archive.util.ms</FONT><BR>Class Doc</H2><PRE>java.lang.Object <IMG SRC="../../../../resources/inherit.gif" ALT="extended by "><B>org.archive.util.ms.Doc</B></PRE><HR><DL><DT><PRE>public class <B>Doc</B><DT>extends java.lang.Object</DL></PRE><P>Reads .doc files.<P><P><DL><DT><B>Author:</B></DT> <DD>pjack</DD></DL><HR><P><!-- ========== METHOD SUMMARY =========== --><A NAME="method_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Method Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../org/archive/util/ms/Doc.html#getText(org.archive.util.ms.BlockFileSystem, int)">getText</A></B>(<A HREF="../../../../org/archive/util/ms/BlockFileSystem.html" title="interface in org.archive.util.ms">BlockFileSystem</A> wordDoc, int cacheSize)</CODE><BR> Returns the text for the given .doc file.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../org/archive/util/ms/Doc.html#getText(java.io.File)">getText</A></B>(java.io.File doc)</CODE><BR> Returns the text of the given .doc file.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../org/archive/util/ms/Doc.html#getText(org.archive.io.SeekInputStream)">getText</A></B>(<A HREF="../../../../org/archive/io/SeekInputStream.html" title="class in org.archive.io">SeekInputStream</A> doc)</CODE><BR> Returns the text of the given .doc file.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../org/archive/util/ms/Doc.html#getText(java.lang.String)">getText</A></B>(java.lang.String docFilename)</CODE><BR> Returns the text of the .doc file with the given file name.</TD></TR></TABLE> <A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor"><TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD></TR></TABLE> <P><!-- ============ METHOD DETAIL ========== --><A NAME="method_detail"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2"><B>Method Detail</B></FONT></TH></TR></TABLE><A NAME="getText(java.lang.String)"><!-- --></A><H3>getText</H3><PRE>public static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A> <B>getText</B>(java.lang.String docFilename) throws java.io.IOException</PRE><DL><DD>Returns the text of the .doc file with the given file name.<P><DD><DL><DT><B>Parameters:</B><DD><CODE>docFilename</CODE> - the name of the file whose text to return<DT><B>Returns:</B><DD>the text of that file<DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE> - if an IO error occurs</DL></DD></DL><HR><A NAME="getText(java.io.File)"><!-- --></A><H3>getText</H3><PRE>public static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A> <B>getText</B>(java.io.File doc) throws java.io.IOException</PRE><DL><DD>Returns the text of the given .doc file.<P><DD><DL><DT><B>Parameters:</B><DD><CODE>doc</CODE> - the .doc file whose text to return<DT><B>Returns:</B><DD>the text of that file<DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE> - if an IO error occurs</DL></DD></DL><HR><A NAME="getText(org.archive.io.SeekInputStream)"><!-- --></A><H3>getText</H3><PRE>public static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A> <B>getText</B>(<A HREF="../../../../org/archive/io/SeekInputStream.html" title="class in org.archive.io">SeekInputStream</A> doc) throws java.io.IOException</PRE><DL><DD>Returns the text of the given .doc file.<P><DD><DL><DT><B>Parameters:</B><DD><CODE>doc</CODE> - the .doc file whose text to return<DT><B>Returns:</B><DD>the text of that file<DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE> - if an IO error occurs</DL></DD></DL><HR><A NAME="getText(org.archive.util.ms.BlockFileSystem, int)"><!-- --></A><H3>getText</H3><PRE>public static <A HREF="../../../../org/archive/io/SeekReader.html" title="class in org.archive.io">SeekReader</A> <B>getText</B>(<A HREF="../../../../org/archive/util/ms/BlockFileSystem.html" title="interface in org.archive.util.ms">BlockFileSystem</A> wordDoc, int cacheSize) throws java.io.IOException</PRE><DL><DD>Returns the text for the given .doc file. The given cacheSize refers to the number of the .doc file's piece table entries to cache. Most .doc files only have 1 piece table entry; however, a "fast-saved" .doc file might have several. A cacheSize of 20 should be ample for most .doc files in the world. Since piece table entries are small -- only 12 bytes each -- caching them prevents many otherwise necessary file pointer repositionings.<P><DD><DL><DT><B>Parameters:</B><DD><CODE>wordDoc</CODE> - the .doc file as a BlockFileSystem<DD><CODE>cacheSize</CODE> - the number of piece table entries to cache<DT><B>Returns:</B><DD>a reader that will return the text in the file<DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE> - if an IO error occurs</DL></DD></DL><!-- ========= END OF CLASS DATA ========= --><HR><!-- ======= START OF BOTTOM NAVBAR ====== --><A NAME="navbar_bottom"><!-- --></A><A HREF="#skip-navbar_bottom" title="Skip navigation links"></A><TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""><TR><TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"><A NAME="navbar_bottom_firstrow"><!-- --></A><TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> <TR ALIGN="center" VALIGN="top"> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="class-use/Doc.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../org/archive/util/ms/DefaultEntry.html" title="class in org.archive.util.ms"><B>PREV CLASS</B></A> <A HREF="../../../../org/archive/util/ms/Entry.html" title="interface in org.archive.util.ms"><B>NEXT CLASS</B></A></FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../index.html?org/archive/util/ms/Doc.html" target="_top"><B>FRAMES</B></A> <A HREF="Doc.html" target="_top"><B>NO FRAMES</B></A> <SCRIPT type="text/javascript"> <!-- if(window==top) { document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>'); } //--></SCRIPT><NOSCRIPT> <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A></NOSCRIPT></FONT></TD></TR><TR><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> SUMMARY: NESTED | FIELD | CONSTR | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: FIELD | CONSTR | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_bottom"></A><!-- ======== END OF BOTTOM NAVBAR ======= --><HR>Copyright © 2003-2007 Internet Archive. All Rights Reserved.</BODY></HTML>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?