....................................../////.===Hehe-Here===./////................................................ > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < ------------------------------------------------------------------------------------------------------------------- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////// RIFF¤ WEBPVP8 ˜ ðÑ *ôô>‘HŸK¥¤"§£±¨àð enü¹%½_F‘åè¿2ºQú³íªú`N¿­3ÿƒügµJžaÿ¯ÿ°~¼ÎùnúîÞÖô•òíôÁÉß®Sm¥Ü/ ‡ó˜f£Ùà<˜„xëJ¢Ù€SO3x<ªÔ©4¿+ç¶A`q@Ì“Úñè™ÍÿJÌ´ª-˜ÆtÊÛL]Ïq*‘Ý”ì#ŸÌÏãY]@ê`¿ /ªfkØB4·®£ó z—Üw¥Pxù–ÞLШKÇN¾AkÙTf½è'‰g gÆv›Øuh~ a˜Z— ïj*á¥t d£“uÒ ¨`K˜¹ßþ]b>˜]_ÏÔ6W—è2r4x•íÖ…"ƒÖNîä!¦å Ú}ýxGøÌ —@ ;ÆÚŠ=ɾ1ý8lªË¥ô ^yf®Œ¢u&2©nÙÇ›ñÂñŒ³ aPo['½»øFùà­+4ê“$!lövlüÞ=;N®3ð‚õ›DÉKòÞ>ÄÍ ¥ˆuߤ#ˆ$6ù™¥îЇy’ÍB¼ çxÛ;X"WL£R÷͝*ó-¶Zu}º.s¸sšXqù–DþÿvªhüïwyŸ ¯é³lÀ:KCûÄ£Ëá\…­ ~—ýóî ¼ûûÜTÓüÇy…ŽÆvc»¾×U ñ¸žþоP÷¦ó:Ò¨¨5;Ð#&#ÖúñläÿÁœ GxÉ­/ñ‡áQðìYÉtÒw޼GÔ´zàÒò ð*ëzƒ•4~H]Ø‹f ñÓÈñ`NåWçs'ÆÏW^ø¹!XžµmQ5ÃËoLœÎ: ÞËÍ¥J ù…î èo£ßPÎñ¶ž8.Œ]ʵ~5›ÙË-ù*8ÙÖß±~ ©¹rÓê‚j¶d¸{^Q'˜±Crß ÚH—#¥¥QlÀ×ëã‡DÜ«èî þ&Çæžî;ŽÏºò6ÒLÃXy&ZŒ'j‚¢Ù€IßÚù+–MGi‰*jE€‘JcÜ ÓÌ EÏÚj]o˜ Þr <¾U ûŪæÍ/šÝH¥˜b”¼ ÁñßX GP›ï2›4WŠÏà×£…íÓk†¦H·ÅíMh–*nó÷à]ÁjCº€b7<ب‹¨5車bp2:Á[UªM„QŒçiNMa#<5›áËó¸HýÊ"…×Éw¹¦ì2º–x<›»a±¸3Weü®FÝ⑱ö–î–³|LPÈ~çð~Çå‡|º kD¢µÏàÆAI %1À% ¹Ò – ”ϝS¦‰4&¶£°à Öý”û_Ò Áw°A«Å€?mÇÛgHÉ/8)á¾ÛìáöŽP í¨PŸNÙµº¦‡§Ùš"ÿ«>+ªÕ`Ê÷‡‚ß Õû˜þãÇ-PÍ.¾XV‘€ dÜ"þ4¹ ±Oú‘©t¥¦FªÄÃÄ•b‚znýu½—#cDs˜ÃiÑOˆñ×QO=*IAÊ,¶ŽZƒ;‡wøXè%EÐk:F±Ú” .Ѽ+Áu&Ç`."pÈÉw o&¿dE6‘’EqTuK@Ì¥ã™À(Êk(h‰,H}RÀIXÛš3µ1©_OqÚÒJAñ$ÊÙÜ;D3çŒ[þùœh¬Ã³™ö6ç†NY".Ú‰ï[ªŸŒ '²Ð öø_¨ÂÉ9ué¶³ÒŠõTàîMØ#û¯gN‡bÙ놚X„ö …ÉeüÌ^J ‹€.œ$Æ)βÄeæW#óüßĺŸ€ ÀzwV 9oä»f4V*uB «Ë†¹ì¯žR霓æHXa=&“I4K;¯ç‹h×·"UŠ~<•╪Vêª&ÍSÃÆÅ?ÔqÎ*mTM ˜›µwêd#[C¡©§‘D<©àb†–ÁœøvH/,í:¯( ²£|4-„Æövv„Yͼ™^Á$ˆ„¢Û[6yB.åH*V¨æ?$=˜Ñ€•ñ·­(VlŸ‘ nÀt8W÷´Bûba?q9ú¶Xƒl«ÿ\ù¶’þòUÐj/õ¢Ìµ³g$ƒÎR!¸»|Oߍë’BhîÚÑ¢ñåŒJ„®„£2Ð3•ô02Nt…!£Í]Ïc½Qÿ?ˆ<&ÃA¾Ú,JˆijÌ#5yz„‰Î|ÊŽ5QÏ:‹ÐaóVÔxW—CpeÏzÐïíçôÿÅ_[hãsÐ_/ŽTÝ?BîˆííV$<¿i>²F¬_Eß¿ †bÊŒº­ÿ®Z H“C}”¬,Mp ý/Bá£w>˜YV°aƒúh+cŠ- r/[%|üUMHäQ°X»|û/@|°¥Ð !BÔ Ç¢Ä©š+Õì D«7ìN¶ŽðÔ " ƶ’ÖçtA‰Û×}{tþz­¾GÍ›k¹OEJR$ Â׃ «ëÁ"oÉôž$oUK(Ä)Ãz³Ê-‹êN[Ò3Œñbï8P 4ƒ×q¢bo|?<ÛX¬òÄͰL–±›(™ûG?ýË©ÚÄ–ÂDØÐ_Ç¡ô ¾–ÄÏø ×e8Ë©$ÄF¹Å‹ì[©óìl:F¾f´‹‹Xì²ï®\¬ôùƒ ÿat¥óèÒùHß0äe‚;ü×h:ÆWðHž=Ã8骣"kœ'Y?³}Tûè€>?0l›e1Lòñ„aæKÆw…hÖŠùW…ÈÆÄ0ši·›[pcwËþñiêíY/~-Á5˜!¿†A›™Mÿþ(±“t@â“ö2­´TG5yé]çå僳 .·ÍïçÝ7UÚ±Ð/Nè»,_Ï ùdj7\ï Wì4›„»c¸àešg#ÒÊ⥭áØo5‘?ÌdÝô¯ ¹kzsƒ=´#ëÉK›Ø´±-¥eW?‡çßtòTã…$Ý+qÿ±ƒ÷_3Ô¥í÷:æ–ž<·Ö‡‰Å¢ š‡%Ô—utÌÈìðžgÖÀz²À—ï÷Óîäõ{K'´È÷³yaÏÁjƒô}ž§®æÊydÕÈë5¯èˆõvÕ©ã*çD„ “z„Ó‡^^xÂ3M§A´JG‚öï 3W'ˆ.OvXè¡ÊÕª?5º7†˜(˜Ç¶#çê’¶!ÌdZK§æ 0fãaN]òY³RV ™î$®K2R¨`W!1Ôó\;Ý ýB%qæK•&ÓÈe9È0êI±žeŸß -ú@žQr¦ ö4»M¼Áè¹µmw 9 EÆE_°2ó„ŸXKWÁ×Hóì^´²GѝF©óäR†¦‰ç"V»eØ<3ùd3ÿÚ¤Žú“Gi" —‘_ÙËÎ~Üö¯¥½Î»üŸEÚŽåmÞþí ;ÞólËΦMzA"Âf(´òá;Éï(/7½ûñÌ­cïÕçлþÝz¾-ÍvÑ“pH­–ðÓj$¸Äû¤‚‘ãUBË-n“2åPkS5&‹Â|+g^œ®Ì͆d!OïäîU«c;{Û!ÅŽ«ëZ9Ókóˆ]¯ƒ›né `ÇÒ+tÆš (ØKá¾—=3œ®•vuMñg²\ï Ec€ 05±d™‡×iÇ×›UúvÌ¢£Èþ¡ÕØô¶ßÎA"ß±#Ö²ˆÊŸ¦*Ä~ij|àø.-¼'»Ú¥£h ofº¦‡VsR=N½„Î v˜Z*SÌ{=jÑB‹tê…;’HžH¯8–îDù8ñ¢|Q•bÛçš–‹m³“ê¨ åÏ^m¬Žãþ©ïêO‡½6] µÆ„Ooòü ²x}N¦Ë3ïé¿»€›HA˜m%çÞ/¿í7Fø“‹léUk)É°Œµ8Q8›:ÀŠeT*šõ~ôڝG6 ¢}`ùH­–”¡k ‰P1>š†®9z11!X wKfmÁ¦xÑ,N1Q”–æB¶M…ÒÃv6SMˆhU¬ÊPŽï‘öj=·CŒ¯u¹ƒVIЃsx4’ömÛýcå¡¶7ßŠß 57^\wÒÐÆ k§h,Œý î«q^R½3]J¸ÇðN ‚çU¬ôº^Áì} ³f©Õœ§ˆã:FÄÈ‚é(€™?àýÓüè1Gô£¼éj‚OÅñ  #>×—ßtà 0G¥Åa뀐kßhc™À_ÉñÞ#±)GD" YîäË-ÿÙ̪ ¹™a¯´¢E\ÝÒö‚;™„ë]_ p8‰o¡ñ+^÷ 3‘'dT4œŽ ðVë½° :¬víÑ«£tßÚS-3¶“þ2 †üüʨòrš¹M{É_¤`Û¨0ìjœøJ‡:÷ÃáZ˜†@GP&œÑDGÏs¡þ¦þDGú‘1Yá9Ôþ¼ ûø…§÷8&–ÜÑnÄ_m®^üÆ`;ÉVÁJ£?â€-ßê}suÍ2sõA NÌúA磸‘îÿÚ»ƒìö·á¿±tÑÐ"Tÿü˜[@/äj¬€uüªìù¥Ý˜á8Ý´sõj 8@rˆð äþZÇD®ÿUÏ2ùôõrBzÆÏÞž>Ì™xœ“ wiÎ×7_… ¸ \#€MɁV¶¥üÕÿPÔ9Z‡ø§É8#H:ƒ5ÀÝå9ÍIŒ5åKÙŠ÷qÄ>1AÈøžj"µÂд/ªnÀ qªã}"iŸBå˜ÓÛŽ¦…&ݧ;G@—³b¯“•"´4í¨ôM¨åñC‹ïùÉó¯ÓsSH2Ý@ßáM‡ˆKÀªÛUeø/4\gnm¥‹ŸŒ qÄ b9ÞwÒNÏ_4Ég³ú=܆‚´ •â¥õeíþkjz>éÚyU«Íӝ݃6"8/ø{=Ô¢»G¥ äUw°W«,ô—¿ãㆅү¢³xŠUû™yŒ (øSópÐ 9\åTâ»—*oG$/×ÍT†Y¿1¤Þ¢_‡ ¼ „±ÍçèSaÓ 3ÛMÁBkxs‰’R/¡¤ˆÙçª(*õ„üXÌ´ƒ E§´¬EF"Ù”R/ÐNyÆÂ^°?™6¡œïJ·±$§?º>ÖüœcNÌù¯G ‹ñ2ЁBB„^·úìaz¨k:#¨Æ¨8LÎõލ£^§S&cŒÐU€ü(‡F±Š¼&P>8ÙÁ ‰ p5?0ÊÆƒZl¸aô š¼¡}gÿ¶zÆC²¹¬ÎÖG*HB¡O<º2#ñŒAƒ–¡B˜´É$¥›É:FÀÔx¾u?XÜÏÓvN©RS{2ʈãk9rmP¼Qq̳ è¼ÐFׄ^¡Öì fE“F4A…!ì/…¦Lƒ… … $%´¾yã@CI¬ á—3PþBÏNÿ<ý°4Ü ËÃ#ØÍ~âW«rEñw‹eùMMHß²`¬Öó½íf³:‹k˜¯÷}Z!ã¿<¥,\#öµÀ¯aÒNÆIé,Ћ–lŽ#Àæ9ÀÒS·I’½-Ïp Äz¤Š Â* ­íÄ9­< h>׍3ZkËU¹§˜ŒŠ±f­’¤º³Q ÏB?‹#µíÃ¥®@(Gs«†vI¥Mµ‹Á©e~2ú³ÁP4ìÕi‚²Ê^ö@-DþÓàlÜOÍ]n"µã:žpsŽ¢:! Aõ.ç~ÓBûH÷JCÌ]õVƒd «ú´QÙEA–¯¯Œ!.ˆˆëQ±ù œ·Ì!Õâ )ùL„ÅÀlÚè5@B…o´Æ¸XÓ&Û…O«˜”_#‡ƒ„ûÈt!¤ÁÏ›ÎÝŠ?c9 â\>lÓÁVÄÑ™£eØY]:fÝ–—ù+p{™ðè û³”g±OƒÚSù£áÁÊ„ä,ï7š²G ÕÌBk)~ÑiCµ|h#u¤¶îK¨² #²vݯGãeÖ϶ú…¾múÀ¶þÔñ‚Š9'^($¤§ò “š½{éúp÷J›ušS¹áªCÂubÃH9™D™/ZöØÁ‡¦ÝÙŸ·kð*_”.C‹{áXó€‡c¡c€§/šò/&éš÷,àéJþ‰X›fµ“C¨œ®r¬"kL‰Â_q…Z–.ÉL~O µ›zn‚¹À¦Öª7\àHµšÖ %»ÇníV[¥*Õ;ƒ#½¾HK-ÖIÊdÏEÚ#=o÷Óò³´Š: Ç?{¾+9›–‘OEáU·S€˜j"ÄaÜ ŒÛWt› á–c#a»pÔZÞdŽtWê=9éöÊ¢µ~ ë ;Öe‡Œ®:bî3±ýê¢wà¼îpêñ¹¾4 zc¾ðÖÿzdêŒÑÒŝÀ‰s6¤í³ÎÙB¿OZ”+F¤á‡3@Ñëäg©·Ž ˆèª<ù@É{&S„œÕúÀA)‰h:YÀ5^ÂÓŒ°õäU\ ùËÍû#²?Xe¬tu‰^zÒÔãë¼ÛWtEtû …‚g¶Úüâî*moGè¨7%u!]PhÏd™Ý%Îx: VÒ¦ôÊD3ÀŽKÛËãvÆî…N¯ä>Eró–ð`5 Œ%u5XkñÌ*NU%¶áœÊ:Qÿú»“úzyÏ6å-၇¾ ´ ÒÊ]y žO‘w2Äøæ…H’²f±ÎÇ.ª|¥'gîV•Ü .̘¯€šòü¤U~Ù†*¢!?ò wý,}´°ÔÞnïoKq5µb!áÓ3"vAßH¡³¡·G(ÐÎ0Îò¼MG!/ài®@—¬04*`…«é8ªøøló“ˆÊ”èù¤…ßÊoÿé'ËuÌÖ5×È¡§ˆˆfŽë9}hìâ_!!¯  B&Ëö¶‰ÀAÙNVŸ Wh›¸®XÑJì¨ú“¿÷3uj²˜¨ÍÎìë±aúŠÝå¯ð*Ó¨ôJ“yºØ)m°WýOè68†ŸÏ2—‰Ïüꪫٚ¥‹l1 ø ÏÄFjêµvÌbü¦èÝx:X±¢H=MÐß—,ˆÉÇ´(9ú¾^ÅÚ4¿m‡$âX‘å%(AlZo@½¨UOÌÕ”1ø¸jÎÀÃÃ_ µ‘Ü.œº¦Ut: Æï’!=¯uwû#,“pþÇúŒø(é@?³ü¥‘Mo §—s@Œ#)§ŒùkL}NOÆêA›¸~r½¼ÙA—HJ«eˆÖ´*¡ÓpÌŸö.m<-"³ûÈ$¬_6­åf£ïÚâj1y§ÕJ½@dÞÁr&Í\Z%D£Íñ·AZ Û³øüd/ªAi†/Й~  ‡âĮҮÏh§°b—›Û«mJžòG'[ÈYýŒ¦9psl ýÁ ®±f¦x,‰½tN ‚Xª9 ÙÖH.«Lo0×?͹m¡å†Ѽ+›2ƒF ±Ê8 7Hցϓ²Æ–m9…òŸï]Â1äN†VLâCˆU .ÿ‰Ts +ÅÎx(%¦u]6AF Š ØF鈄‘ |¢¶c±soŒ/t[a¾–û:s·`i햍ê›ËchÈ…8ßÀUÜewŒðNOƒõD%q#éû\9¤x¹&UE×G¥ Í—™$ð E6-‡¼!ýpãÔM˜ Âsìe¯ñµK¢Ç¡ùôléœ4Ö£”À Š®Ðc ^¨À}ÙËŸ§›ºê{ÊuÉC ×Sr€¤’fÉ*j!úÓ’Gsùìoîßîn%ò· àc Wp÷$¨˜)û»H ×8ŽÒ€Zj¤3ÀÙºY'Ql¦py{-6íÔCeiØp‘‡XÊîÆUߢ܂ž£Xé¼Y8þ©ëgñß}é.ÎógÒ„ÃØËø¯»™§Xýy M%@NŠ À(~áÐvu7&•,Ù˜ó€uP‡^^®=_E„jt’ 403WebShell
403Webshell
Server IP : 198.54.125.254  /  Your IP : 216.73.217.14
Web Server : LiteSpeed
System : Linux premium80.web-hosting.com 4.18.0-553.44.1.lve.el8.x86_64 #1 SMP Thu Mar 13 14:29:12 UTC 2025 x86_64
User : vivegvwr ( 1774)
PHP Version : 8.2.30
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /opt/alt/libicu/usr/share/doc/alt-libicu-devel/samples/ugrep/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :


[ Back ]     

Current File : /opt/alt/libicu/usr/share/doc/alt-libicu-devel/samples/ugrep/ugrep.cpp
/*************************************************************************
*
*   © 2016 and later: Unicode, Inc. and others.
*   License & terms of use: http://www.unicode.org/copyright.html#License
*
**************************************************************************
**************************************************************************
*
*   Copyright (C) 2002-2010, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
***************************************************************************
*/

//
//   ugrep  - an ICU sample program illustrating the use of ICU Regular Expressions.
//
//            The use of the ICU Regex API all occurs within the main()
//            function.  The rest of the code deals with opening files,
//            encoding conversions, printing results, etc.
//
//            This is not a full-featured grep program.  The command line options
//            have been kept to a minimum to avoid complicating the sample code.
//



#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include "unicode/utypes.h"
#include "unicode/ustring.h"
#include "unicode/regex.h"
#include "unicode/ucnv.h"
#include "unicode/uclean.h"

using namespace icu;

//
//  The following variables contain parameters that may be set from the command line.
//
const char *pattern = NULL;     // The regular expression
int        firstFileNum;        //  argv index of the first file name
UBool      displayFileName = FALSE;
UBool      displayLineNum  = FALSE;


//
//  Info regarding the file currently being processed
//
const char *fileName;      
int         fileLen;              // Length, in UTF-16 Code Units.  

UChar      *ucharBuf = 0;         // Buffer, holds converted file.  (Simple minded program, always reads
                                  //   the whole file at once.

char       *charBuf = 0;          // Buffer, for original, unconverted file data.


//
//  Info regarding the line currently being processed
//
int      lineStart;     // Index of first char of the current line in the file buffer
int      lineEnd;       // Index of char following the new line sequence for the current line
int      lineNum;

//
//  Converter, used on output to convert Unicode data back to char *
//             so that it will display in non-Unicode terminal windows.
//
UConverter  *outConverter = 0;

//
//  Function forward declarations
//
void processOptions(int argc, const char **argv);
void nextLine(int start);
void printMatch();
void printUsage();
void readFile(const char *name);



//------------------------------------------------------------------------------------------
//
//   main          for ugrep
//
//           Structurally, all use of the ICU Regular Expression API is in main(),
//           and all of the supporting stuff necessary to make a running program, but
//           not directly related to regular expressions, is factored out into these other
//           functions.
//
//------------------------------------------------------------------------------------------
int main(int argc, const char** argv) {
    UBool     matchFound = FALSE;

    //
    //  Process the command line options.
    //
    processOptions(argc, argv);

    //
    // Create a RegexPattern object from the user supplied pattern string.
    //
    UErrorCode status = U_ZERO_ERROR;   // All ICU operations report success or failure
                                        //   in a status variable.

    UParseError    parseErr;            // In the event of a syntax error in the regex pattern,
                                        //   this struct will contain the position of the
                                        //   error.

    RegexPattern  *rePat = RegexPattern::compile(pattern, parseErr, status);
                                        // Note that C++ is doing an automatic conversion
                                        //  of the (char *) pattern to a temporary
                                        //  UnicodeString object.
    if (U_FAILURE(status)) {
        fprintf(stderr, "ugrep:  error in pattern: \"%s\" at position %d\n",
            u_errorName(status), parseErr.offset);
        exit(-1);
    }

    //
    // Create a RegexMatcher from the newly created pattern.
    //
    UnicodeString empty;
    RegexMatcher *matcher = rePat->matcher(empty, status);
    if (U_FAILURE(status)) {
        fprintf(stderr, "ugrep:  error in creating RegexMatcher: \"%s\"\n",
            u_errorName(status));
        exit(-1);
    }

    //
    // Loop, processing each of the input files.
    //
    for (int fileNum=firstFileNum; fileNum < argc; fileNum++) {
        readFile(argv[fileNum]);

        //
        //  Loop through the lines of a file, trying to match the regex pattern on each.
        //
        for (nextLine(0); lineStart<fileLen; nextLine(lineEnd)) {
            UnicodeString s(FALSE, ucharBuf+lineStart, lineEnd-lineStart);
            matcher->reset(s);
            if (matcher->find()) {
                matchFound = TRUE;
                printMatch();
            }
        }
    }

    //
    //  Clean up
    //
    delete matcher;
    delete rePat;
    free(ucharBuf);
    free(charBuf);
    ucnv_close(outConverter);
    
    u_cleanup();       // shut down ICU, release any cached data it owns.

    return matchFound? 0: 1;
}



//------------------------------------------------------------------------------------------
//
//   doOptions          Run through the command line options, and set
//                      the global variables accordingly.
//
//                      exit without returning if an error occurred and
//                      ugrep should not proceed further.
//
//------------------------------------------------------------------------------------------
void processOptions(int argc, const char **argv) {
    int            optInd;
    UBool          doUsage   = FALSE;
    UBool          doVersion = FALSE;
    const char    *arg;


    for(optInd = 1; optInd < argc; ++optInd) {
        arg = argv[optInd];
        
        /* version info */
        if(strcmp(arg, "-V") == 0 || strcmp(arg, "--version") == 0) {
            doVersion = TRUE;
        }
        /* usage info */
        else if(strcmp(arg, "--help") == 0) {
            doUsage = TRUE;
        }
        else if(strcmp(arg, "-n") == 0 || strcmp(arg, "--line-number") == 0) {
            displayLineNum = TRUE;
        }
        /* POSIX.1 says all arguments after -- are not options */
        else if(strcmp(arg, "--") == 0) {
            /* skip the -- */
            ++optInd;
            break;
        }
        /* unrecognized option */
        else if(strncmp(arg, "-", strlen("-")) == 0) {
            printf("ugrep: invalid option -- %s\n", arg+1);
            doUsage = TRUE;
        }
        /* done with options */
        else {
            break;
        }
    }

    if (doUsage) {
        printUsage();
        exit(0);
    }

    if (doVersion) {
        printf("ugrep version 0.01\n");
        if (optInd == argc) {
            exit(0);
        }
    }

    int  remainingArgs = argc-optInd;     // pattern file ...
    if (remainingArgs < 2) {
        fprintf(stderr, "ugrep:  files or pattern are missing.\n");
        printUsage();
        exit(1);
    }

    if (remainingArgs > 2) {
        // More than one file to be processed.   Display file names with match output.
        displayFileName = TRUE;
    }

    pattern      = argv[optInd];
    firstFileNum = optInd+1;
}

//------------------------------------------------------------------------------------------
//
//   printUsage
//
//------------------------------------------------------------------------------------------
void printUsage() {
    printf("ugrep [options] pattern file...\n"
        "     -V or --version     display version information\n"
        "     --help              display this help and exit\n"
        "     --                  stop further option processing\n"
        "-n,  --line-number       Prefix each line of output with the line number within its input file.\n"
        );
    exit(0);
}

//------------------------------------------------------------------------------------------
//
//    readFile          Read a file into memory, and convert it to Unicode.
//
//                      Since this is just a demo program, take the simple minded approach
//                      of always reading the whole file at once.  No intelligent buffering
//                      is done.
//
//------------------------------------------------------------------------------------------
void readFile(const char *name) {

    //
    //  Initialize global file variables
    //
    fileName = name;
    fileLen  = 0;      // zero length prevents processing in case of errors.


    //
    //  Open the file and determine its size.
    //
    FILE *file = fopen(name, "rb");
    if (file == 0 ) {
        fprintf(stderr, "ugrep: Could not open file \"%s\"\n", fileName);
        return;
    }
    fseek(file, 0, SEEK_END);
    int rawFileLen = ftell(file);
    fseek(file, 0, SEEK_SET);
    

    //
    //   Read in the file
    //
    charBuf    = (char *)realloc(charBuf, rawFileLen+1);   // Need error checking...
    int t = static_cast<int>(fread(charBuf, 1, rawFileLen, file));
    if (t != rawFileLen)  {
        fprintf(stderr, "Error reading file \"%s\"\n", fileName);
        fclose(file);
        return;
    }
    charBuf[rawFileLen]=0;
    fclose(file);

    //
    // Look for a Unicode Signature (BOM) in the data
    //
    int32_t        signatureLength;
    const char *   charDataStart = charBuf;
    UErrorCode     status        = U_ZERO_ERROR;
    const char*    encoding      = ucnv_detectUnicodeSignature(
                           charDataStart, rawFileLen, &signatureLength, &status);
    if (U_FAILURE(status)) {
        fprintf(stderr, "ugrep: ICU Error \"%s\" from ucnv_detectUnicodeSignature()\n",
            u_errorName(status));
        return;
    }
    if(encoding!=NULL ){
        charDataStart  += signatureLength;
        rawFileLen     -= signatureLength;
    }

    //
    // Open a converter to take the file to UTF-16
    //
    UConverter* conv;
    conv = ucnv_open(encoding, &status);
    if (U_FAILURE(status)) {
        fprintf(stderr, "ugrep: ICU Error \"%s\" from ucnv_open()\n", u_errorName(status));
        return;
    }

    //
    // Convert the file data to UChar.
    //  Preflight first to determine required buffer size.
    //
    uint32_t destCap = ucnv_toUChars(conv,
                       NULL,           //  dest,
                       0,              //  destCapacity,
                       charDataStart,
                       rawFileLen,
                       &status);
    if (status != U_BUFFER_OVERFLOW_ERROR) {
        fprintf(stderr, "ugrep: ucnv_toUChars: ICU Error \"%s\"\n", u_errorName(status));
        return;
    };
    
    status = U_ZERO_ERROR;
    ucharBuf = (UChar *)realloc(ucharBuf, (destCap+1) * sizeof(UChar));
    ucnv_toUChars(conv,
        ucharBuf,           //  dest,
        destCap+1,
        charDataStart,
        rawFileLen,
        &status);
    if (U_FAILURE(status)) {
        fprintf(stderr, "ugrep: ucnv_toUChars: ICU Error \"%s\"\n", u_errorName(status));
        return;
    };
    ucnv_close(conv);
    
    //
    //  Successful conversion.  Set the global size variables so that
    //     the rest of the processing will proceed for this file.
    //
    fileLen = destCap;
}
    
    
    


//------------------------------------------------------------------------------------------
//
//   nextLine           Advance the line index variables, starting at the
//                      specified position in the input file buffer, by
//                      scanning forward until the next end-of-line.
//
//                      Need to take into account all of the possible Unicode
//                      line ending sequences.
//
//------------------------------------------------------------------------------------------
void nextLine(int  startPos) {
    if (startPos == 0) {
        lineNum = 0;
    } else {
        lineNum++;
    }
    lineStart = lineEnd = startPos;

    for (;;) {
        if (lineEnd >= fileLen) {
            return;
        }
        UChar c = ucharBuf[lineEnd];
        lineEnd++;
        if (c == 0x0a   ||       // Line Feed
            c == 0x0c   ||       // Form Feed
            c == 0x0d   ||       // Carriage Return
            c == 0x85   ||       // Next Line
            c == 0x2028 ||       // Line Separator
            c == 0x2029)         // Paragraph separator
        { 
            break;
        }
    }

    // Check for CR/LF sequence, and advance over the LF if we're in the middle of one.
    if (lineEnd < fileLen           &&
        ucharBuf[lineEnd-1] == 0x0d &&
        ucharBuf[lineEnd]   == 0x0a) 
    {
        lineEnd++;
    }
}


//------------------------------------------------------------------------------------------
//
//   printMatch         Called when a matching line has been located.
//                      Print out the line from the file with the match, after
//                         converting it back to the default code page.
//
//------------------------------------------------------------------------------------------
void printMatch() {
    char                buf[2000];
    UErrorCode         status       = U_ZERO_ERROR;

    // If we haven't already created a converter for output, do it now.
    if (outConverter == 0) {
        outConverter = ucnv_open(NULL, &status);
        if (U_FAILURE(status)) {
            fprintf(stderr, "ugrep:  Error opening default converter: \"%s\"\n",
                u_errorName(status));
            exit(-1);
        }
    };

    // Convert the line to be printed back to the default 8 bit code page.
    //   If the line is too long for our buffer, just truncate it.
    ucnv_fromUChars(outConverter,
                    buf,                   // destination buffer for conversion
                    sizeof(buf),           // capacity of destination buffer
                    &ucharBuf[lineStart],   // Input to conversion
                    lineEnd-lineStart,     // number of UChars to convert
                    &status);
    buf[sizeof(buf)-1] = 0;                // Add null for use in case of too long lines.
                                           // The converter null-terminates its output unless
                                           //   the buffer completely fills.
   
    if (displayFileName) {
        printf("%s:", fileName);
    }
    if (displayLineNum) {
        printf("%d:", lineNum);
    }
    printf("%s", buf);
}
    

Youez - 2016 - github.com/yon3zu
LinuXploit