File Manager

X7ROOT File Manager

Current Path: /opt/alt/alt-nodejs18/root/usr/include/unicode

opt / alt / alt-nodejs18 / root / usr / include / unicode /

?? ..
?? alphaindex.h(26.54 KB)
?? appendable.h(8.54 KB)
?? basictz.h(9.99 KB)
?? brkiter.h(27.86 KB)
?? bytestream.h(10.75 KB)
?? bytestrie.h(20.8 KB)
?? bytestriebuilder.h(7.48 KB)
?? calendar.h(106.52 KB)
?? caniter.h(7.47 KB)
?? casemap.h(25.42 KB)
?? char16ptr.h(7.22 KB)
?? chariter.h(24.06 KB)
?? choicfmt.h(24 KB)
?? coleitr.h(13.78 KB)
?? coll.h(56.3 KB)
?? compactdecimalformat.h(6.88 KB)
?? curramt.h(3.67 KB)
?? currpinf.h(7.3 KB)
?? currunit.h(4.02 KB)
?? datefmt.h(40.72 KB)
?? dbbi.h(1.19 KB)
?? dcfmtsym.h(20.94 KB)
?? decimfmt.h(87.54 KB)
?? displayoptions.h(7.08 KB)
?? docmain.h(7.3 KB)
?? dtfmtsym.h(38.23 KB)
?? dtintrv.h(3.85 KB)
?? dtitvfmt.h(49.26 KB)
?? dtitvinf.h(18.63 KB)
?? dtptngen.h(28.64 KB)
?? dtrule.h(8.69 KB)
?? edits.h(20.73 KB)
?? enumset.h(2.08 KB)
?? errorcode.h(4.84 KB)
?? fieldpos.h(8.7 KB)
?? filteredbrk.h(5.37 KB)
?? fmtable.h(24.45 KB)
?? format.h(12.5 KB)
?? formattednumber.h(6.15 KB)
?? formattedvalue.h(9.75 KB)
?? fpositer.h(3.03 KB)
?? gender.h(3.35 KB)
?? gregocal.h(30.03 KB)
?? icudataver.h(1.02 KB)
?? icuplug.h(12.1 KB)
?? idna.h(12.71 KB)
?? listformatter.h(8.59 KB)
?? localebuilder.h(11.08 KB)
?? localematcher.h(26.83 KB)
?? localpointer.h(19.44 KB)
?? locdspnm.h(7.12 KB)
?? locid.h(48.27 KB)
?? measfmt.h(11.42 KB)
?? measunit.h(107.38 KB)
?? measure.h(4.69 KB)
?? messagepattern.h(33.72 KB)
?? msgfmt.h(44.21 KB)
?? normalizer2.h(34.73 KB)
?? normlzr.h(30.97 KB)
?? nounit.h(2.25 KB)
?? numberformatter.h(90.03 KB)
?? numberrangeformatter.h(25.32 KB)
?? numfmt.h(50.26 KB)
?? numsys.h(7.23 KB)
?? parseerr.h(3.08 KB)
?? parsepos.h(5.57 KB)
?? platform.h(27.8 KB)
?? plurfmt.h(25.25 KB)
?? plurrule.h(20.64 KB)
?? ptypes.h(3.49 KB)
?? putil.h(6.32 KB)
?? rbbi.h(32.07 KB)
?? rbnf.h(49.92 KB)
?? rbtz.h(15.77 KB)
?? regex.h(84.45 KB)
?? region.h(9.2 KB)
?? reldatefmt.h(22.36 KB)
?? rep.h(9.38 KB)
?? resbund.h(18.11 KB)
?? schriter.h(6.1 KB)
?? scientificnumberformatter.h(6.44 KB)
?? search.h(22.24 KB)
?? selfmt.h(14.35 KB)
?? simpleformatter.h(12.6 KB)
?? simplenumberformatter.h(8.88 KB)
?? simpletz.h(45.65 KB)
?? smpdtfmt.h(71.85 KB)
?? sortkey.h(11.19 KB)
?? std_string.h(1.05 KB)
?? strenum.h(9.96 KB)
?? stringoptions.h(5.79 KB)
?? stringpiece.h(10.05 KB)
?? stringtriebuilder.h(15.5 KB)
?? stsearch.h(21.44 KB)
?? symtable.h(4.28 KB)
?? tblcoll.h(36.94 KB)
?? timezone.h(45.67 KB)
?? tmunit.h(3.4 KB)
?? tmutamt.h(4.91 KB)
?? tmutfmt.h(7.42 KB)
?? translit.h(65.83 KB)
?? tzfmt.h(42.96 KB)
?? tznames.h(16.85 KB)
?? tzrule.h(34.86 KB)
?? tztrans.h(6.13 KB)
?? ubidi.h(89.61 KB)
?? ubiditransform.h(12.71 KB)
?? ubrk.h(24.43 KB)
?? ucal.h(64.28 KB)
?? ucasemap.h(15.21 KB)
?? ucat.h(5.35 KB)
?? uchar.h(145.7 KB)
?? ucharstrie.h(22.56 KB)
?? ucharstriebuilder.h(7.48 KB)
?? uchriter.h(13.42 KB)
?? uclean.h(11.21 KB)
?? ucnv.h(83.46 KB)
?? ucnv_cb.h(6.58 KB)
?? ucnv_err.h(20.98 KB)
?? ucnvsel.h(6.24 KB)
?? ucol.h(62.7 KB)
?? ucoleitr.h(9.82 KB)
?? uconfig.h(12.31 KB)
?? ucpmap.h(5.54 KB)
?? ucptrie.h(22.51 KB)
?? ucsdet.h(14.69 KB)
?? ucurr.h(16.72 KB)
?? udat.h(62.36 KB)
?? udata.h(15.63 KB)
?? udateintervalformat.h(11.93 KB)
?? udatpg.h(30.13 KB)
?? udisplaycontext.h(5.94 KB)
?? udisplayoptions.h(8.86 KB)
?? uenum.h(7.79 KB)
?? ufieldpositer.h(4.41 KB)
?? uformattable.h(10.97 KB)
?? uformattednumber.h(8.09 KB)
?? uformattedvalue.h(12.25 KB)
?? ugender.h(2.06 KB)
?? uidna.h(33.43 KB)
?? uiter.h(22.75 KB)
?? uldnames.h(10.48 KB)
?? ulistformatter.h(10.78 KB)
?? uloc.h(54.66 KB)
?? ulocale.h(6.35 KB)
?? ulocbuilder.h(16.72 KB)
?? ulocdata.h(11.3 KB)
?? umachine.h(15 KB)
?? umisc.h(1.34 KB)
?? umsg.h(24.25 KB)
?? umutablecptrie.h(8.3 KB)
?? unifilt.h(4 KB)
?? unifunct.h(4.05 KB)
?? unimatch.h(6.1 KB)
?? unirepl.h(3.38 KB)
?? uniset.h(66.85 KB)
?? unistr.h(171.35 KB)
?? unorm.h(20.55 KB)
?? unorm2.h(25.71 KB)
?? unum.h(55.16 KB)
?? unumberformatter.h(19.68 KB)
?? unumberoptions.h(5.23 KB)
?? unumberrangeformatter.h(15.35 KB)
?? unumsys.h(7.26 KB)
?? uobject.h(10.66 KB)
?? upluralrules.h(8.79 KB)
?? uregex.h(71.99 KB)
?? uregion.h(9.81 KB)
?? ureldatefmt.h(16.98 KB)
?? urename.h(140.82 KB)
?? urep.h(5.38 KB)
?? ures.h(36.65 KB)
?? uscript.h(27.8 KB)
?? usearch.h(39.21 KB)
?? uset.h(45.61 KB)
?? usetiter.h(9.63 KB)
?? ushape.h(18 KB)
?? usimplenumberformatter.h(7.46 KB)
?? uspoof.h(80.32 KB)
?? usprep.h(8.19 KB)
?? ustdio.h(38.56 KB)
?? ustream.h(1.89 KB)
?? ustring.h(72.13 KB)
?? ustringtrie.h(3.15 KB)
?? utext.h(58.1 KB)
?? utf.h(7.87 KB)
?? utf16.h(23.35 KB)
?? utf32.h(763 B)
?? utf8.h(30.83 KB)
?? utf_old.h(45.8 KB)
?? utmscale.h(13.78 KB)
?? utrace.h(17.18 KB)
?? utrans.h(25.54 KB)
?? utypes.h(31.06 KB)
?? uvernum.h(6.33 KB)
?? uversion.h(5.99 KB)
?? vtzone.h(20.69 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/uenum.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

/**
 * \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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI  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_CAPI 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_CAPI  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_CAPI 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_CAPI 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_CAPI 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