File Manager

X7ROOT File Manager

Current Path: /opt/alt/libicu65/usr/include/unicode

opt / alt / libicu65 / usr / include / unicode /

ðŸ“ ..
ðŸ“„ alphaindex.h(26.48 KB)
ðŸ“„ appendable.h(8.49 KB)
ðŸ“„ basictz.h(9.15 KB)
ðŸ“„ brkiter.h(27.8 KB)
ðŸ“„ bytestream.h(9.6 KB)
ðŸ“„ bytestrie.h(20.77 KB)
ðŸ“„ bytestriebuilder.h(7.08 KB)
ðŸ“„ calendar.h(105.74 KB)
ðŸ“„ caniter.h(7.43 KB)
ðŸ“„ casemap.h(25.33 KB)
ðŸ“„ char16ptr.h(7.22 KB)
ðŸ“„ chariter.h(24.05 KB)
ðŸ“„ choicfmt.h(23.91 KB)
ðŸ“„ coleitr.h(13.76 KB)
ðŸ“„ coll.h(56.23 KB)
ðŸ“„ compactdecimalformat.h(6.88 KB)
ðŸ“„ curramt.h(3.76 KB)
ðŸ“„ currpinf.h(7.3 KB)
ðŸ“„ currunit.h(4.05 KB)
ðŸ“„ datefmt.h(40.67 KB)
ðŸ“„ dbbi.h(1.19 KB)
ðŸ“„ dcfmtsym.h(20.13 KB)
ðŸ“„ decimfmt.h(87.38 KB)
ðŸ“„ docmain.h(6.97 KB)
ðŸ“„ dtfmtsym.h(37.7 KB)
ðŸ“„ dtintrv.h(3.84 KB)
ðŸ“„ dtitvfmt.h(46.63 KB)
ðŸ“„ dtitvinf.h(18.51 KB)
ðŸ“„ dtptngen.h(25.08 KB)
ðŸ“„ dtrule.h(8.68 KB)
ðŸ“„ edits.h(20.74 KB)
ðŸ“„ enumset.h(2.08 KB)
ðŸ“„ errorcode.h(4.84 KB)
ðŸ“„ fieldpos.h(8.69 KB)
ðŸ“„ filteredbrk.h(5.37 KB)
ðŸ“„ fmtable.h(24.42 KB)
ðŸ“„ format.h(12.5 KB)
ðŸ“„ formattedvalue.h(10.27 KB)
ðŸ“„ fpositer.h(3.04 KB)
ðŸ“„ gender.h(3.33 KB)
ðŸ“„ gregocal.h(31.71 KB)
ðŸ“„ icudataver.h(1.03 KB)
ðŸ“„ icuplug.h(11.88 KB)
ðŸ“„ idna.h(12.7 KB)
ðŸ“„ listformatter.h(9.47 KB)
ðŸ“„ localebuilder.h(11.27 KB)
ðŸ“„ localematcher.h(22.5 KB)
ðŸ“„ localpointer.h(19.69 KB)
ðŸ“„ locdspnm.h(7.12 KB)
ðŸ“„ locid.h(47.4 KB)
ðŸ“„ measfmt.h(11.33 KB)
ðŸ“„ measunit.h(93.31 KB)
ðŸ“„ measure.h(4.32 KB)
ðŸ“„ messagepattern.h(33.71 KB)
ðŸ“„ msgfmt.h(44.11 KB)
ðŸ“„ normalizer2.h(34.03 KB)
ðŸ“„ normlzr.h(30.94 KB)
ðŸ“„ nounit.h(2.69 KB)
ðŸ“„ numberformatter.h(86.31 KB)
ðŸ“„ numberrangeformatter.h(30.14 KB)
ðŸ“„ numfmt.h(49.81 KB)
ðŸ“„ numsys.h(7.19 KB)
ðŸ“„ parseerr.h(3.08 KB)
ðŸ“„ parsepos.h(5.56 KB)
ðŸ“„ platform.h(28.08 KB)
ðŸ“„ plurfmt.h(25.2 KB)
ðŸ“„ plurrule.h(18.39 KB)
ðŸ“„ ptypes.h(3.49 KB)
ðŸ“„ putil.h(6.33 KB)
ðŸ“„ rbbi.h(26.58 KB)
ðŸ“„ rbnf.h(48.73 KB)
ðŸ“„ rbtz.h(15.6 KB)
ðŸ“„ regex.h(84.36 KB)
ðŸ“„ region.h(9.18 KB)
ðŸ“„ reldatefmt.h(22.62 KB)
ðŸ“„ rep.h(9.37 KB)
ðŸ“„ resbund.h(18.07 KB)
ðŸ“„ schriter.h(6.32 KB)
ðŸ“„ scientificnumberformatter.h(6.4 KB)
ðŸ“„ search.h(22.22 KB)
ðŸ“„ selfmt.h(14.3 KB)
ðŸ“„ simpleformatter.h(12.59 KB)
ðŸ“„ simpletz.h(45.44 KB)
ðŸ“„ smpdtfmt.h(70.97 KB)
ðŸ“„ sortkey.h(11.18 KB)
ðŸ“„ std_string.h(1.05 KB)
ðŸ“„ strenum.h(9.92 KB)
ðŸ“„ stringoptions.h(5.79 KB)
ðŸ“„ stringpiece.h(7.38 KB)
ðŸ“„ stringtriebuilder.h(15.33 KB)
ðŸ“„ stsearch.h(21.3 KB)
ðŸ“„ symtable.h(4.27 KB)
ðŸ“„ tblcoll.h(36.61 KB)
ðŸ“„ timezone.h(41.02 KB)
ðŸ“„ tmunit.h(3.38 KB)
ðŸ“„ tmutamt.h(4.9 KB)
ðŸ“„ tmutfmt.h(7.85 KB)
ðŸ“„ translit.h(65.82 KB)
ðŸ“„ tzfmt.h(42.89 KB)
ðŸ“„ tznames.h(16.85 KB)
ðŸ“„ tzrule.h(35.37 KB)
ðŸ“„ tztrans.h(6.12 KB)
ðŸ“„ ubidi.h(89.56 KB)
ðŸ“„ ubiditransform.h(12.65 KB)
ðŸ“„ ubrk.h(23.97 KB)
ðŸ“„ ucal.h(56.9 KB)
ðŸ“„ ucasemap.h(15.18 KB)
ðŸ“„ ucat.h(5.36 KB)
ðŸ“„ uchar.h(140.56 KB)
ðŸ“„ ucharstrie.h(22.58 KB)
ðŸ“„ ucharstriebuilder.h(7.21 KB)
ðŸ“„ uchriter.h(13.2 KB)
ðŸ“„ uclean.h(11.21 KB)
ðŸ“„ ucnv.h(83.09 KB)
ðŸ“„ ucnv_cb.h(6.59 KB)
ðŸ“„ ucnv_err.h(20.99 KB)
ðŸ“„ ucnvsel.h(6.14 KB)
ðŸ“„ ucol.h(61.46 KB)
ðŸ“„ ucoleitr.h(9.46 KB)
ðŸ“„ uconfig.h(12.07 KB)
ðŸ“„ ucpmap.h(5.53 KB)
ðŸ“„ ucptrie.h(22.46 KB)
ðŸ“„ ucsdet.h(14.67 KB)
ðŸ“„ ucurr.h(16.12 KB)
ðŸ“„ udat.h(60.88 KB)
ðŸ“„ udata.h(15.56 KB)
ðŸ“„ udateintervalformat.h(10.03 KB)
ðŸ“„ udatpg.h(26.01 KB)
ðŸ“„ udisplaycontext.h(5.89 KB)
ðŸ“„ uenum.h(7.78 KB)
ðŸ“„ ufieldpositer.h(4.36 KB)
ðŸ“„ uformattable.h(10.94 KB)
ðŸ“„ uformattedvalue.h(12.14 KB)
ðŸ“„ ugender.h(2 KB)
ðŸ“„ uidna.h(33.37 KB)
ðŸ“„ uiter.h(22.77 KB)
ðŸ“„ uldnames.h(10.45 KB)
ðŸ“„ ulistformatter.h(8.83 KB)
ðŸ“„ uloc.h(52.54 KB)
ðŸ“„ ulocdata.h(11.26 KB)
ðŸ“„ umachine.h(14.53 KB)
ðŸ“„ umisc.h(1.33 KB)
ðŸ“„ umsg.h(24.23 KB)
ðŸ“„ umutablecptrie.h(8.24 KB)
ðŸ“„ unifilt.h(3.96 KB)
ðŸ“„ unifunct.h(4.04 KB)
ðŸ“„ unimatch.h(6.1 KB)
ðŸ“„ unirepl.h(3.38 KB)
ðŸ“„ uniset.h(64.9 KB)
ðŸ“„ unistr.h(170.43 KB)
ðŸ“„ unorm.h(20.52 KB)
ðŸ“„ unorm2.h(24.66 KB)
ðŸ“„ unum.h(53.62 KB)
ðŸ“„ unumberformatter.h(25.36 KB)
ðŸ“„ unumsys.h(7.21 KB)
ðŸ“„ uobject.h(10.68 KB)
ðŸ“„ upluralrules.h(7.88 KB)
ðŸ“„ uregex.h(72.05 KB)
ðŸ“„ uregion.h(9.84 KB)
ðŸ“„ ureldatefmt.h(17.26 KB)
ðŸ“„ urename.h(130.97 KB)
ðŸ“„ urep.h(5.38 KB)
ðŸ“„ ures.h(36.54 KB)
ðŸ“„ uscript.h(26.87 KB)
ðŸ“„ usearch.h(38.12 KB)
ðŸ“„ uset.h(40 KB)
ðŸ“„ usetiter.h(9.55 KB)
ðŸ“„ ushape.h(18 KB)
ðŸ“„ uspoof.h(65.9 KB)
ðŸ“„ usprep.h(8.14 KB)
ðŸ“„ ustdio.h(38.54 KB)
ðŸ“„ ustream.h(1.89 KB)
ðŸ“„ ustring.h(72.47 KB)
ðŸ“„ ustringtrie.h(3.15 KB)
ðŸ“„ utext.h(58.13 KB)
ðŸ“„ utf.h(7.86 KB)
ðŸ“„ utf16.h(23.32 KB)
ðŸ“„ utf32.h(763 B)
ðŸ“„ utf8.h(30.96 KB)
ðŸ“„ utf_old.h(45.83 KB)
ðŸ“„ utmscale.h(13.78 KB)
ðŸ“„ utrace.h(15.73 KB)
ðŸ“„ utrans.h(25.52 KB)
ðŸ“„ utypes.h(30.74 KB)
ðŸ“„ uvernum.h(6.67 KB)
ðŸ“„ uversion.h(6 KB)
ðŸ“„ vtzone.h(20.3 KB)

Editing: ucsdet.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 **********************************************************************
 *   Copyright (C) 2005-2013, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 *   file name:  ucsdet.h
 *   encoding:   UTF-8
 *   indentation:4
 *
 *   created on: 2005Aug04
 *   created by: Andy Heninger
 *
 *   ICU Character Set Detection, API for C
 *
 *   Draft version 18 Oct 2005
 *
 */

#ifndef __UCSDET_H
#define __UCSDET_H

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/localpointer.h"
#include "unicode/uenum.h"

/**
 * \file 
 * \brief C API: Charset Detection API
 *
 * This API provides a facility for detecting the
 * charset or encoding of character data in an unknown text format.
 * The input data can be from an array of bytes.
 * 
 * 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.
 * 
 * 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
  * @stable ICU 3.6
  */
typedef struct UCharsetDetector UCharsetDetector;

struct UCharsetMatch;
/**
  *  Opaque structure representing a match that was identified
  *  from a charset detection operation.
  *  @stable ICU 3.6
  */
typedef struct UCharsetMatch UCharsetMatch;

/**
  *  Open a charset detector.
  *
  *  @param status Any error conditions occurring during the open
  *                operation are reported back in this variable.
  *  @return the newly opened charset detector.
  *  @stable ICU 3.6
  */
U_STABLE UCharsetDetector * U_EXPORT2
ucsdet_open(UErrorCode   *status);

/**
  * Close a charset detector.  All storage and any other resources
  *   owned by this charset detector will be released.  Failure to
  *   close a charset detector when finished with it can result in
  *   memory leaks in the application.
  *
  *  @param ucsd  The charset detector to be closed.
  *  @stable ICU 3.6
  */
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

/**
  * Set the input byte data whose charset is to detected.
  *
  * Ownership of the input  text byte array remains with the caller.
  * The input string must not be altered or deleted until the charset
  * detector is either closed or reset to refer to different input text.
  *
  * @param ucsd   the charset detector to be used.
  * @param textIn the input text of unknown encoding.   .
  * @param len    the length of the input text, or -1 if the text
  *               is NUL terminated.
  * @param status any error conditions are reported back in this variable.
  *
  * @stable ICU 3.6
  */
U_STABLE void U_EXPORT2
ucsdet_setText(UCharsetDetector *ucsd, const char *textIn, int32_t len, UErrorCode *status);

/** Set the declared encoding for charset detection.
 *  The declared encoding of an input text is an encoding obtained
 *  by the user from an http header or xml declaration or similar source that
 *  can be provided as an additional hint to the charset detector.
 *
 *  How and whether the declared encoding will be used during the
 *  detection process is TBD.
 *
 * @param ucsd      the charset detector to be used.
 * @param encoding  an encoding for the current data obtained from
 *                  a header or declaration or other source outside
 *                  of the byte data itself.
 * @param length    the length of the encoding name, or -1 if the name string
 *                  is NUL terminated.
 * @param status    any error conditions are reported back in this variable.
 *
 * @stable ICU 3.6
 */
U_STABLE void U_EXPORT2
ucsdet_setDeclaredEncoding(UCharsetDetector *ucsd, const char *encoding, int32_t length, UErrorCode *status);

/**
 * 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.
 * 
 * The returned UCharsetMatch object is owned by the UCharsetDetector.
 * It will remain valid until the detector input is reset, or until
 * the detector is closed.
 * 
 * The function will fail if
 * <ul>
 * <li>no charset appears to match the data.</li>
 * <li>no input text has been provided</li>
 * </ul>
 *
 * @param ucsd the charset detector to be used.
 * @param status any error conditions are reported back in this variable.
 * @return a UCharsetMatch representing the best matching charset,
 * or NULL if no charset matches the byte data.
 *
 * @stable ICU 3.6
 */
U_STABLE const UCharsetMatch * U_EXPORT2
ucsdet_detect(UCharsetDetector *ucsd, UErrorCode *status);

/**
 * Find all charset matches that appear to be consistent with the input,
 * returning an array of results. The results are ordered with the
 * best quality match first.
 *
 * Because the detection only looks at a limited amount of the
 * input byte data, some of the returned charsets may fail to handle
 * the all of input data.
 * 
 * The returned UCharsetMatch objects are owned by the UCharsetDetector.
 * They will remain valid until the detector is closed or modified
 * 
 * 
 * Return an error if 
 * <ul>
 * <li>no charsets appear to match the input data.</li>
 * <li>no input text has been provided</li>
 * </ul>
 * 
 * @param ucsd the charset detector to be used.
 * @param matchesFound pointer to a variable that will be set to the
 * number of charsets identified that are consistent with
 * the input data. Output only.
 * @param status any error conditions are reported back in this variable.
 * @return A pointer to an array of pointers to UCharSetMatch objects.
 * 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.
 * @stable ICU 3.6
 */
U_STABLE const UCharsetMatch ** U_EXPORT2
ucsdet_detectAll(UCharsetDetector *ucsd, int32_t *matchesFound, UErrorCode *status);

/**
 *  Get the name of the charset represented by a UCharsetMatch.
 *
 *  The storage for the returned name string is owned by the
 *  UCharsetMatch, and will remain valid while the UCharsetMatch
 *  is valid.
 *
 *  The name returned is suitable for use with the ICU conversion APIs.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        The name of the matching charset.
 *
 *  @stable ICU 3.6
 */
U_STABLE const char * U_EXPORT2
ucsdet_getName(const UCharsetMatch *ucsm, UErrorCode *status);

/**
 *  Get a confidence number for the quality of the match of the byte
 *  data with the charset.  Confidence numbers range from zero to 100,
 *  with 100 representing complete confidence and zero representing
 *  no confidence.
 *
 *  The confidence values are somewhat arbitrary.  They define an
 *  an ordering within the results for any single detection operation
 *  but are not generally comparable between the results for different input.
 *
 *  A confidence value of ten does have a general meaning - it is used
 *  for charsets that can represent the input data, but for which there
 *  is no other indication that suggests that the charset is the correct one.
 *  Pure 7 bit ASCII data, for example, is compatible with a
 *  great many charsets, most of which will appear as possible matches
 *  with a confidence of 10.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        A confidence number for the charset match.
 *
 *  @stable ICU 3.6
 */
U_STABLE int32_t U_EXPORT2
ucsdet_getConfidence(const UCharsetMatch *ucsm, UErrorCode *status);

/**
 *  Get the RFC 3066 code for the language of the input data.
 *
 *  The Charset Detection service is intended primarily for detecting
 *  charsets, not language.  For some, but not all, charsets, a language is
 *  identified as a byproduct of the detection process, and that is what
 *  is returned by this function.
 *
 *  CAUTION:
 *    1.  Language information is not available for input data encoded in
 *        all charsets. In particular, no language is identified
 *        for UTF-8 input data.
 *
 *    2.  Closely related languages may sometimes be confused.
 *
 *  If more accurate language detection is required, a linguistic
 *  analysis package should be used.
 *
 *  The storage for the returned name string is owned by the
 *  UCharsetMatch, and will remain valid while the UCharsetMatch
 *  is valid.
 *
 *  @param ucsm    The charset match object.
 *  @param status  Any error conditions are reported back in this variable.
 *  @return        The RFC 3066 code for the language of the input data, or
 *                 an empty string if the language could not be determined.
 *
 *  @stable ICU 3.6
 */
U_STABLE const char * U_EXPORT2
ucsdet_getLanguage(const UCharsetMatch *ucsm, UErrorCode *status);

/**
  *  Get the entire input text as a UChar string, placing it into
  *  a caller-supplied buffer.  A terminating
  *  NUL character will be appended to the buffer if space is available.
  *
  *  The number of UChars in the output string, not including the terminating
  *  NUL, is returned. 
  *
  *  If the supplied buffer is smaller than required to hold the output,
  *  the contents of the buffer are undefined.  The full output string length
  *  (in UChars) is returned as always, and can be used to allocate a buffer
  *  of the correct size.
  *
  *
  * @param ucsm    The charset match object.
  * @param buf     A UChar buffer to be filled with the converted text data.
  * @param cap     The capacity of the buffer in UChars.
  * @param status  Any error conditions are reported back in this variable.
  * @return        The number of UChars in the output string.
  *
  * @stable ICU 3.6
  */
U_STABLE  int32_t U_EXPORT2
ucsdet_getUChars(const UCharsetMatch *ucsm,
                 UChar *buf, int32_t cap, UErrorCode *status);

/**
 * Get an iterator over the set of all detectable charsets - 
 * over the charsets that are known to the charset detection
 * service.
 *
 * The returned UEnumeration provides access to the names of
 * the charsets.
 *
 * 
 * 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.
 *
 * 
 * Note: 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.
 * @stable ICU 3.6
 */
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.
  *
  *  @param ucsd  The charset detector to check.
  *  @return TRUE if filtering is enabled.
  *  @stable ICU 3.6
  */

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.
 *
 * @param ucsd the charset detector to be modified.
 * @param filter <code>true</code> to enable input text filtering.
 * @return The previous setting.
 *
 * @stable ICU 3.6
 */
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 */

X7ROOT File Manager

Editing: ucsdet.h

Upload File

Create Folder