+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
- * Copyright (C) 2005-2006, International Business Machines
+ * Copyright (C) 2005-2013, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
* file name: ucsdet.h
- * encoding: US-ASCII
+ * encoding: UTF-8
* indentation:4
*
* created on: 2005Aug04
#include "unicode/utypes.h"
#if !UCONFIG_NO_CONVERSION
+
+#include "unicode/localpointer.h"
#include "unicode/uenum.h"
/**
* 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.
*/
struct UCharsetDetector;
/**
* Structure representing a charset detector
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
typedef struct UCharsetDetector UCharsetDetector;
/**
* Opaque structure representing a match that was identified
* from a charset detection operation.
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
typedef struct UCharsetMatch UCharsetMatch;
* @param status Any error conditions occurring during the open
* operation are reported back in this variable.
* @return the newly opened charset detector.
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT UCharsetDetector * U_EXPORT2
+U_STABLE UCharsetDetector * U_EXPORT2
ucsdet_open(UErrorCode *status);
/**
* memory leaks in the application.
*
* @param ucsd The charset detector to be closed.
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
ucsdet_close(UCharsetDetector *ucsd);
+#if U_SHOW_CPLUSPLUS_API
+
+U_NAMESPACE_BEGIN
+
+/**
+ * \class LocalUCharsetDetectorPointer
+ * "Smart pointer" class, closes a UCharsetDetector via ucsdet_close().
+ * For most methods see the LocalPointerBase base class.
+ *
+ * @see LocalPointerBase
+ * @see LocalPointer
+ * @stable ICU 4.4
+ */
+U_DEFINE_LOCAL_OPEN_POINTER(LocalUCharsetDetectorPointer, UCharsetDetector, ucsdet_close);
+
+U_NAMESPACE_END
+
+#endif // U_SHOW_CPLUSPLUS_API
+
/**
* Set the input byte data whose charset is to detected.
*
* is NUL terminated.
* @param status any error conditions are reported back in this variable.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status);
* is NUL terminated.
* @param status any error conditions are reported back in this variable.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT void U_EXPORT2
+U_STABLE void U_EXPORT2
ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status);
* @return a UCharsetMatch representing the best matching charset,
* or NULL if no charset matches the byte data.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT const UCharsetMatch * U_EXPORT2
+U_STABLE const UCharsetMatch * U_EXPORT2
ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status);
* This array, and the UCharSetMatch instances to which it refers,
* are owned by the UCharsetDetector, and will remain valid until
* the detector is closed or modified.
- * @draft ICU 3.4
+ * @stable ICU 3.6
*/
-U_DRAFT const UCharsetMatch ** U_EXPORT2
+U_STABLE const UCharsetMatch ** U_EXPORT2
ucsdet_detectAll(UCharsetDetector *ucsd, int32_t *matchesFound, UErrorCode *status);
* @param status Any error conditions are reported back in this variable.
* @return The name of the matching charset.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT const char * U_EXPORT2
+U_STABLE const char * U_EXPORT2
ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status);
/**
* @param status Any error conditions are reported back in this variable.
* @return A confidence number for the charset match.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT int32_t U_EXPORT2
+U_STABLE int32_t U_EXPORT2
ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status);
/**
* @return The RFC 3066 code for the language of the input data, or
* an empty string if the language could not be determined.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT const char * U_EXPORT2
+U_STABLE const char * U_EXPORT2
ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status);
* @param status Any error conditions are reported back in this variable.
* @return The number of UChars in the output string.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT int32_t U_EXPORT2
+U_STABLE int32_t U_EXPORT2
ucsdet_getUChars(const UCharsetMatch *ucsm,
UChar *buf, int32_t cap, UErrorCode *status);
* The returned UEnumeration provides access to the names of
* the charsets.
*
+ * <p>
* The state of the Charset detector that is passed in does not
* affect the result of this function, but requiring a valid, open
* charset detector as a parameter insures that the charset detection
* service has been safely initialized and that the required detection
* data is available.
*
+ * <p>
+ * <b>Note:</b> Multiple different charset encodings in a same family may use
+ * a single shared name in this implementation. For example, this method returns
+ * an array including "ISO-8859-1" (ISO Latin 1), but not including "windows-1252"
+ * (Windows Latin 1). However, actual detection result could be "windows-1252"
+ * when the input data matches Latin 1 code points with any points only available
+ * in "windows-1252".
+ *
* @param ucsd a Charset detector.
* @param status Any error conditions are reported back in this variable.
* @return an iterator providing access to the detectable charset names.
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-
-U_DRAFT UEnumeration * U_EXPORT2
+U_STABLE UEnumeration * U_EXPORT2
ucsdet_getAllDetectableCharsets(const UCharsetDetector *ucsd, UErrorCode *status);
-
/**
* Test whether input filtering is enabled for this charset detector.
* Input filtering removes text that appears to be HTML or xml
* markup from the input before applying the code page detection
- * heuristics.
+ * heuristics. Apple addition per <rdar://problem/48093252>: Will also
+ * remove text that appears to be CSS declaration blocks.
*
* @param ucsd The charset detector to check.
* @return TRUE if filtering is enabled.
- * @draft ICU 3.4
+ * @stable ICU 3.6
*/
-U_DRAFT UBool U_EXPORT2
+
+U_STABLE UBool U_EXPORT2
ucsdet_isInputFilterEnabled(const UCharsetDetector *ucsd);
* Enable filtering of input text. If filtering is enabled,
* text within angle brackets ("<" and ">") will be removed
* before detection, which will remove most HTML or xml markup.
+ * Apple addition per <rdar://problem/48093252>: Will also
+ * remove text between '{' and '}', e.g. CSS declaration blocks.
*
* @param ucsd the charset detector to be modified.
* @param filter <code>true</code> to enable input text filtering.
* @return The previous setting.
*
- * @draft ICU 3.6
+ * @stable ICU 3.6
*/
-U_DRAFT UBool U_EXPORT2
+U_STABLE UBool U_EXPORT2
ucsdet_enableInputFilter(UCharsetDetector *ucsd, UBool filter);
+#ifndef U_HIDE_INTERNAL_API
+/**
+ * Get an iterator over the set of detectable charsets -
+ * over the charsets that are enabled by the specified charset detector.
+ *
+ * The returned UEnumeration provides access to the names of
+ * the charsets.
+ *
+ * @param ucsd a Charset detector.
+ * @param status Any error conditions are reported back in this variable.
+ * @return an iterator providing access to the detectable charset names by
+ * the specified charset detector.
+ * @internal
+ */
+U_INTERNAL UEnumeration * U_EXPORT2
+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 #ucsdet_getAllDetectableCharsets()}.
+ *
+ * @param ucsd a Charset detector.
+ * @param encoding encoding the name of charset encoding.
+ * @param enabled <code>TRUE</code> to enable, or <code>FALSE</code> to disable the
+ * charset encoding.
+ * @param status receives the return status. When the name of charset encoding
+ * is not supported, U_ILLEGAL_ARGUMENT_ERROR is set.
+ * @internal
+ */
+U_INTERNAL void U_EXPORT2
+ucsdet_setDetectableCharset(UCharsetDetector *ucsd, const char *encoding, UBool enabled, UErrorCode *status);
+#endif /* U_HIDE_INTERNAL_API */
+
#endif
#endif /* __UCSDET_H */
projects / apple / icu.git / blobdiff