CharsetDetector provides a facility for detecting the
+ * charset or encoding of character data in an unknown format.
+ * The input data can either be from an input stream or an array of bytes.
+ * The result of the detection operation is a list of possibly matching
+ * charsets, or, for simple use, you can just ask for a Java Reader that
+ * will will work over the input data.
+ *
+ * Character set detection is at best an imprecise operation. The detection
+ * process will attempt to identify the charset that best matches the characteristics
+ * of the byte data, but the process is partly statistical in nature, and
+ * the results can not be guaranteed to always be correct.
+ *
+ * For best accuracy in charset detection, the input data should be primarily
+ * in a single language, and a minimum of a few hundred bytes worth of plain text
+ * in the language are needed. The detection process will attempt to
+ * ignore html or xml style markup that could otherwise obscure the content.
+ *
+ * Question:Should we have getters corresponding to the setters for inut text
+ * and declared encoding?
+ *
+ * A thought: If we were to create our own type of Java Reader, we could defer
+ * figuring out an actual charset for data that starts out with too much English
+ * only ASCII until the user actually read through to something that didn't look
+ * like 7 bit English. If nothing else ever appeared, we would never need to
+ * actually choose the "real" charset. All assuming that the application just
+ * wants the data, and doesn't care about a char set name.
+ *
+ *
+ */
+public class CharsetDetector {
+
+
+ /**
+ * Constructor
+ */
+ public CharsetDetector() {
+ }
+
+ /**
+ * Set the declared encoding for charset detection.
+ * The declared encoding of an input text is an encoding obtained
+ * from an http header or xml declaration or similar source that
+ * can be provided as additional information to the charset detector.
+ * A match between a declared encoding and a possible detected encoding
+ * will raise the quality of that detected encoding by a small delta,
+ * and will also appear as a "reason" for the match.
+ *
+ * A declared encoding that is incompatible with the input data being
+ * analyzed will not be added to the list of possible encodings.
+ *
+ * @param encoding The declared encoding
+ */
+ public CharsetDetector setDecaredEncoding(String encoding) {
+ return this;
+ }
+
+ /**
+ * Set the input text (byte) data whose charset is to be detected.
+ * @param in the input text of unknown encoding
+ * @return This CharsetDetector
+ */
+ public CharsetDetector setText(byte in[]) {
+ return this;
+ }
+
+ /**
+ * Set the input text (byte) data whose charset is to be detected.
+ *
+ * The input stream that supplies the character data must have markSupported()
+ * == true; the charset detection process will read a small amount of data,
+ * then return the stream to its original position via
+ * the InputStream.reset() operation. The exact amount that will
+ * be read depends on the characteristics of the data itself.
+
+ * @param in the input text of unknown encoding
+ * @return This CharsetDetector
+ */
+ public CharsetDetector setText(InputStream in) {
+ return this;
+ }
+
+
+ /**
+ * Return the charset that best matches the supplied input data.
+ *
+ * Note though, that because the detection
+ * only looks at the start of the input data,
+ * there is a possibility that the returned charset will fail to handle
+ * the full set of input data.
+ *
+ * Raise an exception if
+ * this.setDeclaredEncoding(declaredEncoding).setText(in).detect().getReader();
+ *
+ * For the input stream that supplies the character data, markSupported()
+ * must be true; the charset detection will read a small amount of data,
+ * then return the stream to its original position via
+ * the InputStream.reset() operation. The exact amount that will
+ * be read depends on the characteristics of the data itself.
+ *
+ * Raise an exception if no charsets appear to match the input data.
+ *
+ * @param in The source of the byte data in the unknown charset.
+ *
+ * @param declaredEncoding A declared encoding for the data, if available,
+ * or null or an empty string if none is available.
+ */
+ public Reader getReader(InputStream in, String declaredEncoding) {
+ return null;
+ }
+
+ /**
+ * Autodetect the charset of an inputStream, and return a String
+ * containing the converted input data.
+ *
+ * This is a convenience method that is equivalent to
+ * this.setDeclaredEncoding(declaredEncoding).setText(in).detect().getString();
+ *
+ * Raise an exception if no charsets appear to match the input data.
+ *
+ * @param in The source of the byte data in the unknown charset.
+ *
+ * @param declaredEncoding A declared encoding for the data, if available,
+ * or null or an empty string if none is available.
+ */
+ public String getString(byte[] in, String declaredEncoding) {
+ return null;
+ }
+
+
+ /**
+ * Get the names of all char sets that can be recognized by the char set detector.
+ *
+ * @return an array of the names of all charsets that can be recognized
+ * by the charset detector.
+ */
+ public static String[] getAllDetectableCharsets() {
+ return null;
+ }
+
+
+}
diff --git a/icu4j/src/com/ibm/icu/text/CharsetMatch.java b/icu4j/src/com/ibm/icu/text/CharsetMatch.java
new file mode 100644
index 00000000000..50aa60ffd96
--- /dev/null
+++ b/icu4j/src/com/ibm/icu/text/CharsetMatch.java
@@ -0,0 +1,104 @@
+/**
+*******************************************************************************
+* Copyright (C) 2005, International Business Machines Corporation and *
+* others. All Rights Reserved. *
+*******************************************************************************
+*/
+package com.ibm.icu.text;
+
+import java.io.InputStream;
+import java.io.Reader;
+
+
+/**
+ * This class represents a charset that has been identified by a CharsetDetector
+ * as a possible encoding for a set of input data. From an instance of this
+ * class, you can ask for a confidence level in the charset identification,
+ * or for Java Reader or String to access the original byte data in Unicode form.
+ *
+ * Instances of this class are created only by CharsetDetectors.
+ */
+public class CharsetMatch {
+
+
+ /**
+ * Create a java.io.Reader for reading the Unicode character data corresponding
+ * to the original byte data supplied to the Charset detect operation.
+ *
+ * @return the Reader for the Unicode character data.
+ */
+ public Reader getReader() {
+ return null;
+ }
+
+
+
+ /**
+ * Create a Java String from Unicode character data corresponding
+ * to the original byte data supplied to the Charset detect operation.
+ *
+ * @return a String created from the converted input data.
+ */
+ public String getString() {
+ return null;
+
+ }
+ /**
+ * Create a Java String from Unicode character data corresponding
+ * to the original byte data supplied to the Charset detect operation.
+ * The length of the returned string is limited to the specified size;
+ * the string will be trunctated to this length if necessary. A limit value of
+ * zero or less is ignored, and treated as no limit.
+ *
+ * @param maxLength The maximium length of the String to be created.
+ * @return a String created from the converted input data.
+ */
+ public String getString(int maxLength) {
+ return null;
+
+ }
+
+ /**
+ * Get an indication of the confidence in the charset detected.
+ * Confidence values range from 0-100, with larger numbers indicating
+ * a better match of the input data to the characteristics of the
+ * charset.
+ *
+ * @return the confidence in the charset match
+ */
+ public int getConfidence() {
+ return 0;
+ }
+
+ /**
+ * Return an indication of what it was about input data that
+ * that caused this charset to be considered as a possible match.
+ * + * TODO: create a list of enum-like constants for the possible types of matches. + * + * @return the type of match found for this charset. + */ + public int getMatchType() { + return 0; + } + + + + /** + * Get the name of the detected charset. + * The name will be one that can be used with other APIs on the + * platform that accept charset names. It is the "Canonical name" + * as defined by the class java.nio.charset.Charset; for + * charsets that are registered with the IANA charset registry, + * this is the MIME-preferred registerd name. + * + * @see java.nio.charset.Charset + * @see java.io.InputStreamReader + * + * @return The name of the charset. + */ + public String getName() { + return ""; + } + +}