GIF89a=( õ' 7IAXKgNgYvYx\%wh…hŽth%ˆs%—x¨}9®Œ©€&©‰%¶†(¹–.¹5·œD¹&Çš)ÇŸ5ǘ;Í£*È¡&Õ²)ׯ7×µ<Ñ»4ï°3ø‘HÖ§KͯT÷¨Yÿšqÿ»qÿÔFØ !ù ' !ÿ NETSCAPE2.0 , =( þÀ“pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§gª«ªE¯°¨¬ª±²Œ¹º¹E¾­”´ÂB¶¯ §Åȸ»ÑD¾¿Á•ÄÅ®° ÝH¾ÒLÀÆDÙ«D¶BÝïðÀ¾DÑÑÔTÌÍíH òGö¨A RÎڐ |¥ ٭&ºìE8œ¹kGÔAÞpx­a¶­ã R2XB®åE8I€Õ6Xî:vT)äžþÀq¦è³¥ì仕F~%xñ  4#ZÔ‰O|-4Bs‘X:= QÉ œš lºÒyXJŠGȦ|s hÏíK–3l7·B|¥$'7Jީܪ‰‡àá”Dæn=Pƒ ¤Òëí‰`䌨ljóá¯Éüv>á–Á¼5 ½.69ûϸd«­ºÀûnlv©‹ªîf{¬ÜãPbŸ  l5‘Ž¯pß ´ ˜3aÅùäI«O’ý·‘áÞ‡˜¾Æ‚ÙÏiÇÿ‹Àƒ #öó)pâš Þ½ ‘Ý{ó)vmÞü%D~ 6f s}ŃƒDØW Eþ`‡þ À…L8xá†ç˜{)x`X/> Ì}mø‚–RØ‘*|`D=‚Ø_ ^ð5 !_…'aä“OÚ—7âcð`D”Cx`ÝÂ¥ä‹éY¹—F¼¤¥Š?¡Õ™ n@`} lď’ÄÉ@4>ñd œ à‘vÒxNÃ×™@žd=ˆgsžG±æ ´²æud &p8Qñ)ˆ«lXD©øÜéAžHìySun jª×k*D¤LH] †¦§C™Jä–´Xb~ʪwStŽ6K,°£qÁœ:9ت:¨þªl¨@¡`‚ûÚ ».Û¬¯t‹ÆSÉ[:°=Š‹„‘Nåû”Ìî{¿ÂA ‡Rà›ÀÙ6úë°Ÿð0Ä_ ½;ÃϱîÉì^ÇÛÇ#Ëë¼ôº!±Ä˜íUîÅÇ;0L1óÁµö«p% AÀºU̬ݵ¼á%霼€‡¯Á~`ÏG¯»À× ­²± =4ªnpð3¾¤³¯­ü¾¦îuÙuµÙ®|%2ÊIÿür¦#0·ÔJ``8È@S@5ê¢ ö×Þ^`8EÜ]ý.뜃Âç 7 ú ȉÞj œ½Dç zý¸iþœÑÙûÄë!ˆÞÀl§Ïw‹*DçI€nEX¯¬¼ &A¬Go¼QföõFç°¯;é¦÷îŽêJ°îúôF5¡ÌQ|îúöXªæ»TÁÏyñêï]ê² o óÎC=öõ›ÒÓPB@ D×½œä(>èCÂxŽ`±«Ÿ–JЀ»Û á¤±p+eE0`ëŽ`A Ú/NE€Ø†À9‚@¤à H½7”à‡%B‰`Àl*ƒó‘–‡8 2ñ%¸ —€:Ù1Á‰E¸àux%nP1ð!‘ðC)¾P81lÑɸF#ˆ€{´âé°ÈB„0>±û °b¡Š´±O‚3È–Ù()yRpbµ¨E.Z‘D8ÊH@% òŒx+%Ù˜Æcü »¸˜fõ¬b·d`Fê™8èXH"ÉÈ-±|1Ô6iI, 2““¬$+](A*jÐ QTÂo‰.ÛU슬Œã„Ž`¯SN¡–¶Äåyše¯ª’­¬‚´b¦Éož œ)åyâ@Ì®3 ÎtT̉°&Ø+žLÀf"Ø-|žçÔ>‡Ðv¦Ðžì\‚ Q1)Ž@Žh#aP72”ˆ™¨$‚ !ù " , =( …7IAXG]KgNgYvYxR"k\%w]'}hŽth%ˆg+ˆs%—r.—m3šx3˜x¨}9®€&©€+¨‡7§‰%¶†(¹–.¹œD¹&ǘ;Í•&ײ)×»4ïÌ6ò§KÍ þ@‘pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§g «¬ E ±± ¨­¶°ººE Á´”·®C¬²§Ç¶Œ»ÓDÃÕƷ¯Ê±H½ºM×ÁGÚ¬D¶BËÁ½î½DÓôTÏÛßîG»ôõC×CÌ l&âž:'òtU³6ɹ#·Ø)€'Ü.6±&ëÍÈ» K(8p0N?!æ2"ÛˆNIJX>R¼ÐO‚M '¡¨2¸*Ÿþ>#n↠å@‚<[:¡Iïf’ ¤TÚ˘CdbÜÙ“[«ŽEú5MBo¤×@€`@„€Êt W-3 ¶Ÿ¡BíêäjIÝ…Eò9[T…$íêﯧ„…•s»Óȳ¹€ÅÚdc®UUρ#±Ùïldj?´í¼²`\ŽÁðÞu|3'ÖŒ]ë6 ¶S#²‡˜FKLÈ *N E´‘áäŠ$˜›eÄYD„ºq«.è촁ƒs \-ÔjA 9²õ÷å- üúM[Âx(ís÷ì®x€|í¡Ù’p¦‚ ŽkÛTÇDpE@WÜ ²Ç]kŠ1¨ þ€·Yb ÓÁ‰l°*n0 ç™—žzBdОu¾7ĉBl€â‰-ºx~|UåU‰  h*Hœ|e"#"?vpÄiŠe6^ˆ„+qâŠm8 #VÇá ‘å–ÄV„œ|Šè•m"сœn|@›U¶ÆΞ—Špb¥G¨ED”€±Úê2FÌIç? >Éxå Œ± ¡¤„%‘žjŸ‘ꄯ<Ìaà9ijÐ2˜D¦È&›†Z`‚å]wþ¼Â:ç6àB¤7eFJ|õÒ§Õ,¨äàFÇ®cS·Ê¶+B°,‘Þ˜ºNûãØ>PADÌHD¹æž«ÄÀnÌ¥}­#Ë’ë QÀÉSÌÂÇ2ÌXÀ{æk²lQÁ2«ÊðÀ¯w|2Í h‹ÄÂG€,m¾¶ë3ÐÙ6-´ÅE¬L°ÆIij*K½ÀÇqï`DwVÍQXœÚÔpeœ±¬Ñ q˜§Tœ½µƒ°Œìu Â<¶aØ*At¯lmEØ ü ôÛN[P1ÔÛ¦­±$ÜÆ@`ùåDpy¶yXvCAyåB`ŽD¶ 0QwG#¯ æš[^Äþ $ÀÓÝǦ{„L™[±úKÄgÌ;ï£S~¹ìGX.ôgoT.»åˆ°ùŸûù¡?1zö¦Ÿž:ÅgÁ|ìL¹ „®£œŠ‚à0œ]PÁ^p F<"•ç?!,ñ‡N4—…PÄ Á„ö¨Û:Tè@hÀ‹%táÿ:ø-žI<`þ‹p I….)^ 40D#p@ƒj4–؀:²‰1Øâr˜¼F2oW¼#Z†;$Q q” ‘ ÂK¦ñNl#29 !’F@¥Bh·ᏀL!—XFóLH‘Kh¤.«hE&JòG¨¥<™WN!€ÑÙÚˆY„@†>Œž19J" 2,/ &.GXB%ÌRÈ9B6¹W]’î×ÔW¥’IÎ$ ñ‹ÓŒE8YÆ ¼³™ñA5“à®Q.aŸB€&Ø©³ JÁ—! ¦t)K%tœ-¦JF bòNMxLôþ)ÐR¸Ð™‘ èÝ6‘O!THÌ„HÛ ‰ !ù ) , =( …AXKgNgYvYxR"k\%wh…hŽh%ˆg+ˆs%—r.—x3˜x¨}9®€&©€+¨Œ,©‡7§‰%¶†(¹–.¹5·&Çš)ǘ;Í•&×£*Ȳ)ׯ7×»4ï°3øÌ6ò‘HÖ§KÍ»Hó¯T÷¨Yÿ»qÿÇhÿ þÀ”pH,È¤rÉl:ŸÐ¨tJ­Z¯Ø¬vËíz¿à°xL.›Ïè´zÍn»ßð¸|N¯Ûïø¼~Ïïûÿ€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ¡¢£¤¥¦§g ª« E$±²¨ª­ · °²½$E$ÂÕ««D· Í ¿¦Ç¶¸ÌŒ¾³CÃÅÆ E ééH½MÛÂGâªD­ çBêêϾD²ÒaÀà€Š1r­ðÓ¤ ÔožzU!L˜C'¾yW½UGtäÇïÙllê0×àÂuGþ)AÀs[þ·xì ÁxO%ƒûX2ó—  P£n›R/¡ÑšHše+êDm?# —‘Ç£6¡8íJ¡ŸâDiäªM¥Ö„ôj“¬¹£5oQ7°- <‡ *´lãÓŒ2r/a!l)dÈ A™ÈE¢ôÔ͆…ð ;Ö˜c ¡%ß‚’Ùˆâ¸b½—pe~C"BíëÚHïeF2§æŠ8qb t_`urŠeü wÅu3êæPv§h•"ß`íÍxçLĹÜÖ3á  ~Öº“®›¸ÏMDfJÙ °„ÛµáWõ%§œ‚à©–‚X Ó؁)@®Ñ›Eþ´wëuÅSxb8y\mÖzœ¥§ZbºE—ÂLªÌw!y(>¡™wú=Ç|ÅÝs¢d €CÁW)HÜcC$€L Ä7„r.á\{)@ð` @ äXÈ$PD” `šaG:§æˆOˆ72EÐamn]ù"ŒcÊxÑŒ° &dR8`g«iÙŸLR!¦P …d’ä¡“¦ðÎTƒ¦ià|À _ ¥ Qi#¦Šg›Æ ›noMµ ›V ã£)p ç£ÎW…š=Âeªk§†j„ ´®1ß²sÉxéW«jšl|0¯B0Û, \jÛ´›6±¬¶C ÛíWþï|ëÙ‹¸ñzĸV {ì;Ýñn¼òVˆm³I¼³.Ðã¤PN¥ ²µ¼„µCã+¹ÍByî£Ñ¾HŸ›ëê 7ìYÆFTk¨SaoaY$Dµœìï¿Ã29RÈkt Çïfñ ÇÒ:ÀÐSp¹3ÇI¨â¥DZÄ ü9Ïýögñ½­uÔ*3)O‘˜Ö[_hv ,àî×Et Ÿé¶BH€ Õ[ü±64M@ÔSÌM7dÐl5-ÄÙU܍´©zߌ3Ô€3ž„ „ ¶ÛPô½5×g› êÚ˜kN„Ý…0Îj4€Ìë°“#{þÕ3S2çKÜ'ợlø¼Ú2K{° {Û¶?žm𸧠ËI¼nEò='êüóºè^üæÃ_Û=°óž‚ì#Oý¿Í'¡½áo..ÏYìnüñCœO±Áa¿¢Kô½o,üÄËbö²çºíï{ËC Ú— "”Ï{ËK ÍÒw„õ±Oz dÕ¨à:$ ƒô—«v»] A#ð «€¿šéz)Rx׿ˆ¥‚d``èw-îyÏf×K!ð€þ­Ð|ìPľ„=Ì`ý(f” 'Pa ¥ÐBJa%Ðâf§„%Š¡}FàáÝ×6>ÉäŠG"éŽè=ø!oŠ°^FP¼Ø©Q„ÀCÙÁ`(Ž\ÄÝ® ©Â$<n@dÄ E#ììUÒI! ‚#lù‹`k¦ÐÇ'Rró’ZýNBÈMF Í[¤+‹ðɈ-áwj¨¥þ8¾rá ,VÂh„"|½œ=×G_¦Ñ™EØ 0i*%̲˜Æda0mV‚k¾)›;„&6 p>ÓjK “¦Ç# âDÂ:ûc?:R Ó¬fÞéI-Ì“•Ã<ä=™Ï7˜3œ¨˜c2ŒW ,ˆ”8(T™P‰F¡Jhç"‚ ; 403WebShell
403Webshell
Server IP : 172.67.177.218  /  Your IP : 216.73.216.195
Web Server : LiteSpeed
System : Linux premium229.web-hosting.com 4.18.0-553.45.1.lve.el8.x86_64 #1 SMP Wed Mar 26 12:08:09 UTC 2025 x86_64
User : akhalid ( 749)
PHP Version : 8.3.22
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /opt/alt/alt-nodejs22/root/usr/include/unicode/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :

[ Back ]     

Current File : /opt/alt/alt-nodejs22/root/usr/include/unicode/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.
 * <p>
 * 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.
 * <p>
 * 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.
 * <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
  * @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.
 * <p>
 * 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.
 * <p>
 * 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.
 *  <p>
 *  The returned UCharsetMatch objects are owned by the UCharsetDetector.
 *  They will remain valid until the detector is closed or modified
 *  
 * <p>
 * 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.
  *
  *  <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.
  *  @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 */

Youez - 2016 - github.com/yon3zu
LinuXploit