ICU-12870 Charset Detector, have docs reference the Compact Encoding Detector.

X-SVN-Rev: 39640

diff --git a/icu4c/source/common/unicode/docmain.h b/icu4c/source/common/unicode/docmain.h
index 478856366c4bb9fcf01c4280cb7805954aaecebd..698e2ae596c42e28072c9cad90bca5819b323872 100644 (file)
--- a/icu4c/source/common/unicode/docmain.h
+++ b/icu4c/source/common/unicode/docmain.h
@@ -98,6 +98,11 @@
  *     <td>C API</td>
  *   </tr>
  *   <tr>
+ *     <td>Codepage Detection</td>
+ *     <td>ucsdet.h</td>
+ *     <td>C API</td>
+ *   </tr>
+ *   <tr>
  *     <td>Unicode Text Compression</td>
  *     <td>ucnv.h<br/>(encoding name "SCSU" or "BOCU-1")</td>
  *     <td>C API</td>

diff --git a/icu4c/source/i18n/unicode/ucsdet.h b/icu4c/source/i18n/unicode/ucsdet.h
index 73f0ab587dad5aedb18372974574a736c962fbdd..0d0bc3186d6a0e5b9ccc0123870840a305fcf58f 100644 (file)
--- a/icu4c/source/i18n/unicode/ucsdet.h
+++ b/icu4c/source/i18n/unicode/ucsdet.h
@@ -45,6 +45,10 @@
  * 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.
+ * <p>
+ * An alternative to the ICU Charset Detector is the
+ * Compact Encoding Detector, https://github.com/google/compact_enc_det.
+ * It often gives more accurate results, especially with short input samples.
  */
  
 
@@ -395,7 +399,7 @@ ucsdet_getDetectableCharsets(const UCharsetDetector *ucsd,  UErrorCode *status);
 /**
   * Enable or disable individual charset encoding.
   * A name of charset encoding must be included in the names returned by
-  * {@link #getAllDetectableCharsets()}.
+  * {@link #ucsdet_getAllDetectableCharsets()}.
   *
   * @param ucsd a Charset detector.
   * @param encoding encoding the name of charset encoding.