add an interface of prior language information

update javadoc git-svn-id: http://language-detection.googlecode.com/svn/trunk@24 5bf80810-9c81-6ef6-3109-74533bb38634
darek-ai · Sep 29, 2010 · b17525e · b17525e
1 parent 6126150
commit b17525e
Show file tree

Hide file tree

Showing 62 changed files with 587 additions and 278 deletions.
diff --git a/doc/allclasses-frame.html b/doc/allclasses-frame.html
@@ -2,12 +2,12 @@
 <!--NewPage-->
 <HTML>
 <HEAD>
-<!-- Generated by javadoc (build 1.6.0_21) on Tue Sep 28 17:25:34 JST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_21) on Wed Sep 29 19:24:42 JST 2010 -->
 <TITLE>
 All Classes
 </TITLE>
 
-<META NAME="date" CONTENT="2010-09-28">
+<META NAME="date" CONTENT="2010-09-29">
 
 <LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
 

diff --git a/doc/allclasses-noframe.html b/doc/allclasses-noframe.html
@@ -2,12 +2,12 @@
 <!--NewPage-->
 <HTML>
 <HEAD>
-<!-- Generated by javadoc (build 1.6.0_21) on Tue Sep 28 17:25:34 JST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_21) on Wed Sep 29 19:24:42 JST 2010 -->
 <TITLE>
 All Classes
 </TITLE>
 
-<META NAME="date" CONTENT="2010-09-28">
+<META NAME="date" CONTENT="2010-09-29">
 
 <LINK REL ="stylesheet" TYPE="text/css" HREF="stylesheet.css" TITLE="Style">
 

diff --git a/doc/com/cybozu/labs/langdetect/Command.html b/doc/com/cybozu/labs/langdetect/Command.html
@@ -2,12 +2,12 @@
 <!--NewPage-->
 <HTML>
 <HEAD>
-<!-- Generated by javadoc (build 1.6.0_21) on Tue Sep 28 17:25:33 JST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_21) on Wed Sep 29 19:24:41 JST 2010 -->
 <TITLE>
 Command
 </TITLE>
 
-<META NAME="date" CONTENT="2010-09-28">
+<META NAME="date" CONTENT="2010-09-29">
 
 <LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../stylesheet.css" TITLE="Style">
 

diff --git a/doc/com/cybozu/labs/langdetect/Detector.html b/doc/com/cybozu/labs/langdetect/Detector.html
@@ -2,12 +2,12 @@
 <!--NewPage-->
 <HTML>
 <HEAD>
-<!-- Generated by javadoc (build 1.6.0_21) on Tue Sep 28 17:25:34 JST 2010 -->
+<!-- Generated by javadoc (build 1.6.0_21) on Wed Sep 29 19:24:41 JST 2010 -->
 <TITLE>
 Detector
 </TITLE>
 
-<META NAME="date" CONTENT="2010-09-28">
+<META NAME="date" CONTENT="2010-09-29">
 
 <LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../stylesheet.css" TITLE="Style">
 
@@ -101,10 +101,16 @@ <H2>
 </PRE>
 
 <P>
-Language Detector Class
+<A HREF="../../../../com/cybozu/labs/langdetect/Detector.html" title="class in com.cybozu.labs.langdetect"><CODE>Detector</CODE></A> class is to detect language from specified text. 
+ Its instance is able to be constructed via the factory class <A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html" title="class in com.cybozu.labs.langdetect"><CODE>DetectorFactory</CODE></A>.
  <p>
-
- This class is able to be constructed via the factory class <A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html" title="class in com.cybozu.labs.langdetect"><CODE>DetectorFactory</CODE></A>.
+ After appending a target text to the <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html" title="class in com.cybozu.labs.langdetect"><CODE>Detector</CODE></A> instance with <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.io.Reader)"><CODE>append(Reader)</CODE></A> or <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.lang.String)"><CODE>append(String)</CODE></A>,
+ the detector provides the language detection results for target text via <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#detect()"><CODE>detect()</CODE></A> or <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#getProbabilities()"><CODE>getProbabilities()</CODE></A>.
+ <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#detect()"><CODE>detect()</CODE></A> method returns a single language name which has the highest probability.
+ <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#getProbabilities()"><CODE>getProbabilities()</CODE></A> methods returns a list of multiple languages and their probabilities.
+ <p>  
+ The detector has some parameters for language detection.
+ See <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setAlpha(double)"><CODE>setAlpha(double)</CODE></A>, <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setMax_text_length(int)"><CODE>setMax_text_length(int)</CODE></A> and <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setPriorMap(java.util.HashMap)"><CODE>setPriorMap(HashMap)</CODE></A>.
 
  <pre>
  import java.util.ArrayList;
@@ -113,15 +119,15 @@ <H2>
  import com.cybozu.labs.langdetect.Language;
 
  class LangDetectSample {
-     public void init(String profileDirectory) {
+     public void init(String profileDirectory) throws LangDetectException {
          DetectorFactory.loadProfile(profileDirectory);
      }
-     public String detect(String text) {
+     public String detect(String text) throws LangDetectException {
          Detector detector = DetectorFactory.create();
          detector.append(text);
          return detector.detect();
      }
-     public ArrayList<Language> detectLangs(String text) {
+     public ArrayList<Language> detectLangs(String text) throws LangDetectException {
          Detector detector = DetectorFactory.create();
          detector.append(text);
          return detector.getProbabilities();
@@ -148,11 +154,10 @@ <H2>
 <B>Constructor Summary</B></FONT></TH>
 </TR>
 <TR BGCOLOR="white" CLASS="TableRowColor">
-<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#Detector(java.util.HashMap, java.util.ArrayList)">Detector</A></B>(java.util.HashMap&lt;java.lang.String,java.util.HashMap&lt;java.lang.String,java.lang.Double&gt;&gt;&nbsp;p_ik,
-         java.util.ArrayList&lt;java.lang.String&gt;&nbsp;langlist)</CODE>
+<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#Detector(com.cybozu.labs.langdetect.DetectorFactory)">Detector</A></B>(<A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html" title="class in com.cybozu.labs.langdetect">DetectorFactory</A>&nbsp;factory)</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Constructor.</TD>
 </TR>
 </TABLE>
 &nbsp;
@@ -167,26 +172,26 @@ <H2>
 <TR BGCOLOR="white" CLASS="TableRowColor">
 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
 <CODE>&nbsp;void</CODE></FONT></TD>
-<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.io.Reader)">append</A></B>(java.io.Reader&nbsp;is)</CODE>
+<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.io.Reader)">append</A></B>(java.io.Reader&nbsp;reader)</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Append the target text for language detection.</TD>
 </TR>
 <TR BGCOLOR="white" CLASS="TableRowColor">
 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
 <CODE>&nbsp;void</CODE></FONT></TD>
-<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.lang.String)">append</A></B>(java.lang.String&nbsp;buf)</CODE>
+<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#append(java.lang.String)">append</A></B>(java.lang.String&nbsp;text)</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Append the target text for language detection.</TD>
 </TR>
 <TR BGCOLOR="white" CLASS="TableRowColor">
 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
 <CODE>&nbsp;java.lang.String</CODE></FONT></TD>
 <TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#detect()">detect</A></B>()</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Detect language of the target text and return the language name which has the highest probability.</TD>
 </TR>
 <TR BGCOLOR="white" CLASS="TableRowColor">
 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
@@ -202,15 +207,31 @@ <H2>
 <TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setAlpha(double)">setAlpha</A></B>(double&nbsp;alpha)</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Set smoothing parameter.</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setMax_text_length(int)">setMax_text_length</A></B>(int&nbsp;max_text_length)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Specify max size of target text to use for language detection.</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setPriorMap(java.util.HashMap)">setPriorMap</A></B>(java.util.HashMap&lt;java.lang.String,java.lang.Double&gt;&nbsp;priorMap)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Set prior information about language probabilities.</TD>
 </TR>
 <TR BGCOLOR="white" CLASS="TableRowColor">
 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
 <CODE>&nbsp;void</CODE></FONT></TD>
 <TD><CODE><B><A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setVerbose()">setVerbose</A></B>()</CODE>
 
 <BR>
-&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Set Verbose Mode(use for debug).</TD>
 </TR>
 </TABLE>
 &nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
@@ -235,14 +256,16 @@ <H2>
 </TR>
 </TABLE>
 
-<A NAME="Detector(java.util.HashMap, java.util.ArrayList)"><!-- --></A><H3>
+<A NAME="Detector(com.cybozu.labs.langdetect.DetectorFactory)"><!-- --></A><H3>
 Detector</H3>
 <PRE>
-public <B>Detector</B>(java.util.HashMap&lt;java.lang.String,java.util.HashMap&lt;java.lang.String,java.lang.Double&gt;&gt;&nbsp;p_ik,
-                java.util.ArrayList&lt;java.lang.String&gt;&nbsp;langlist)</PRE>
+public <B>Detector</B>(<A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html" title="class in com.cybozu.labs.langdetect">DetectorFactory</A>&nbsp;factory)</PRE>
 <DL>
+<DD>Constructor.
+ Detector instance can be constructed via <A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html#create()"><CODE>DetectorFactory.create()</CODE></A>.
+<P>
 <DL>
-<DT><B>Parameters:</B><DD><CODE>p_ik</CODE> - <DD><CODE>langlist</CODE> - </DL>
+<DT><B>Parameters:</B><DD><CODE>factory</CODE> - <A HREF="../../../../com/cybozu/labs/langdetect/DetectorFactory.html" title="class in com.cybozu.labs.langdetect"><CODE>DetectorFactory</CODE></A> instance (only DetectorFactory inside)</DL>
 </DL>
 
 <!-- ============ METHOD DETAIL ========== -->
@@ -260,6 +283,8 @@ <H2>
 <PRE>
 public void <B>setVerbose</B>()</PRE>
 <DL>
+<DD>Set Verbose Mode(use for debug).
+<P>
 <DD><DL>
 </DL>
 </DD>
@@ -271,33 +296,72 @@ <H2>
 <PRE>
 public void <B>setAlpha</B>(double&nbsp;alpha)</PRE>
 <DL>
+<DD>Set smoothing parameter.
+ The default value is 0.5(i.e. Expected Likelihood Estimate).
+<P>
 <DD><DL>
-<DT><B>Parameters:</B><DD><CODE>alpha</CODE> - </DL>
+<DT><B>Parameters:</B><DD><CODE>alpha</CODE> - the smoothing parameter</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="setPriorMap(java.util.HashMap)"><!-- --></A><H3>
+setPriorMap</H3>
+<PRE>
+public void <B>setPriorMap</B>(java.util.HashMap&lt;java.lang.String,java.lang.Double&gt;&nbsp;priorMap)</PRE>
+<DL>
+<DD>Set prior information about language probabilities.
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>priorMap</CODE> - the priorMap to set</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="setMax_text_length(int)"><!-- --></A><H3>
+setMax_text_length</H3>
+<PRE>
+public void <B>setMax_text_length</B>(int&nbsp;max_text_length)</PRE>
+<DL>
+<DD>Specify max size of target text to use for language detection.
+ The default value is 10000(10KB).
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>max_text_length</CODE> - the max_text_length to set</DL>
 </DD>
 </DL>
 <HR>
 
 <A NAME="append(java.io.Reader)"><!-- --></A><H3>
 append</H3>
 <PRE>
-public void <B>append</B>(java.io.Reader&nbsp;is)
+public void <B>append</B>(java.io.Reader&nbsp;reader)
             throws java.io.IOException</PRE>
 <DL>
+<DD>Append the target text for language detection.
+ This method read the text from specified input reader.
+ If the total size of target text exceeds the limit size specified by <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setMax_text_length(int)"><CODE>setMax_text_length(int)</CODE></A>,
+ the rest is cut down.
+<P>
 <DD><DL>
-<DT><B>Parameters:</B><DD><CODE>is</CODE> - 
+<DT><B>Parameters:</B><DD><CODE>reader</CODE> - the input reader (BufferedReader as usual)
 <DT><B>Throws:</B>
-<DD><CODE>java.io.IOException</CODE></DL>
+<DD><CODE>java.io.IOException</CODE> - Can't read the reader.</DL>
 </DD>
 </DL>
 <HR>
 
 <A NAME="append(java.lang.String)"><!-- --></A><H3>
 append</H3>
 <PRE>
-public void <B>append</B>(java.lang.String&nbsp;buf)</PRE>
+public void <B>append</B>(java.lang.String&nbsp;text)</PRE>
 <DL>
+<DD>Append the target text for language detection.
+ If the total size of target text exceeds the limit size specified by <A HREF="../../../../com/cybozu/labs/langdetect/Detector.html#setMax_text_length(int)"><CODE>setMax_text_length(int)</CODE></A>,
+ the rest is cut down.
+<P>
 <DD><DL>
-<DT><B>Parameters:</B><DD><CODE>buf</CODE> - </DL>
+<DT><B>Parameters:</B><DD><CODE>text</CODE> - the target text to append</DL>
 </DD>
 </DL>
 <HR>
@@ -308,6 +372,8 @@ <H2>
 public java.lang.String <B>detect</B>()
                         throws <A HREF="../../../../com/cybozu/labs/langdetect/LangDetectException.html" title="class in com.cybozu.labs.langdetect">LangDetectException</A></PRE>
 <DL>
+<DD>Detect language of the target text and return the language name which has the highest probability.
+<P>
 <DD><DL>
 
 <DT><B>Returns:</B><DD>detected language name which has most probability.