0000: 2f 2a 0a 20 2a 20 74 63 6c 55 74 66 2e 63 20 2d /*. * tclUtf.c -
0010: 2d 0a 20 2a 0a 20 2a 09 52 6f 75 74 69 6e 65 73 -. *. *.Routines
0020: 20 66 6f 72 20 6d 61 6e 69 70 75 6c 61 74 69 6e for manipulatin
0030: 67 20 55 54 46 2d 38 20 73 74 72 69 6e 67 73 2e g UTF-8 strings.
0040: 0a 20 2a 0a 20 2a 20 43 6f 70 79 72 69 67 68 74 . *. * Copyright
0050: 20 28 63 29 20 31 39 39 37 2d 31 39 39 38 20 53 (c) 1997-1998 S
0060: 75 6e 20 4d 69 63 72 6f 73 79 73 74 65 6d 73 2c un Microsystems,
0070: 20 49 6e 63 2e 0a 20 2a 0a 20 2a 20 53 65 65 20 Inc.. *. * See
0080: 74 68 65 20 66 69 6c 65 20 22 6c 69 63 65 6e 73 the file "licens
0090: 65 2e 74 65 72 6d 73 22 20 66 6f 72 20 69 6e 66 e.terms" for inf
00a0: 6f 72 6d 61 74 69 6f 6e 20 6f 6e 20 75 73 61 67 ormation on usag
00b0: 65 20 61 6e 64 20 72 65 64 69 73 74 72 69 62 75 e and redistribu
00c0: 74 69 6f 6e 20 6f 66 0a 20 2a 20 74 68 69 73 20 tion of. * this
00d0: 66 69 6c 65 2c 20 61 6e 64 20 66 6f 72 20 61 20 file, and for a
00e0: 44 49 53 43 4c 41 49 4d 45 52 20 4f 46 20 41 4c DISCLAIMER OF AL
00f0: 4c 20 57 41 52 52 41 4e 54 49 45 53 2e 0a 20 2a L WARRANTIES.. *
0100: 2f 0a 0a 23 69 6e 63 6c 75 64 65 20 22 74 63 6c /..#include "tcl
0110: 49 6e 74 2e 68 22 0a 0a 2f 2a 0a 20 2a 20 49 6e Int.h"../*. * In
0120: 63 6c 75 64 65 20 74 68 65 20 73 74 61 74 69 63 clude the static
0130: 20 63 68 61 72 61 63 74 65 72 20 63 6c 61 73 73 character class
0140: 69 66 69 63 61 74 69 6f 6e 20 74 61 62 6c 65 73 ification tables
0150: 20 61 6e 64 20 6d 61 63 72 6f 73 2e 0a 20 2a 2f and macros.. */
0160: 0a 0a 23 69 6e 63 6c 75 64 65 20 22 74 63 6c 55 ..#include "tclU
0170: 6e 69 44 61 74 61 2e 63 22 0a 0a 2f 2a 0a 20 2a niData.c"../*. *
0180: 20 54 68 65 20 66 6f 6c 6c 6f 77 69 6e 67 20 6d The following m
0190: 61 63 72 6f 73 20 61 72 65 20 75 73 65 64 20 66 acros are used f
01a0: 6f 72 20 66 61 73 74 20 63 68 61 72 61 63 74 65 or fast characte
01b0: 72 20 63 61 74 65 67 6f 72 79 20 74 65 73 74 73 r category tests
01c0: 2e 20 54 68 65 20 78 5f 42 49 54 53 0a 20 2a 20 . The x_BITS. *
01d0: 76 61 6c 75 65 73 20 61 72 65 20 73 68 69 66 74 values are shift
01e0: 65 64 20 72 69 67 68 74 20 62 79 20 74 68 65 20 ed right by the
01f0: 63 61 74 65 67 6f 72 79 20 76 61 6c 75 65 20 74 category value t
0200: 6f 20 64 65 74 65 72 6d 69 6e 65 20 77 68 65 74 o determine whet
0210: 68 65 72 20 74 68 65 0a 20 2a 20 67 69 76 65 6e her the. * given
0220: 20 63 61 74 65 67 6f 72 79 20 69 73 20 69 6e 63 category is inc
0230: 6c 75 64 65 64 20 69 6e 20 74 68 65 20 73 65 74 luded in the set
0240: 2e 0a 20 2a 2f 0a 0a 23 64 65 66 69 6e 65 20 41 .. */..#define A
0250: 4c 50 48 41 5f 42 49 54 53 20 28 28 31 20 3c 3c LPHA_BITS ((1 <<
0260: 20 55 50 50 45 52 43 41 53 45 5f 4c 45 54 54 45 UPPERCASE_LETTE
0270: 52 29 20 7c 20 28 31 20 3c 3c 20 4c 4f 57 45 52 R) | (1 << LOWER
0280: 43 41 53 45 5f 4c 45 54 54 45 52 29 20 5c 0a 09 CASE_LETTER) \..
0290: 7c 20 28 31 20 3c 3c 20 54 49 54 4c 45 43 41 53 | (1 << TITLECAS
02a0: 45 5f 4c 45 54 54 45 52 29 20 7c 20 28 31 20 3c E_LETTER) | (1 <
02b0: 3c 20 4d 4f 44 49 46 49 45 52 5f 4c 45 54 54 45 < MODIFIER_LETTE
02c0: 52 29 20 7c 20 28 31 3c 3c 4f 54 48 45 52 5f 4c R) | (1<<OTHER_L
02d0: 45 54 54 45 52 29 29 0a 0a 23 64 65 66 69 6e 65 ETTER))..#define
02e0: 20 43 4f 4e 54 52 4f 4c 5f 42 49 54 53 20 28 28 CONTROL_BITS ((
02f0: 31 20 3c 3c 20 43 4f 4e 54 52 4f 4c 29 20 7c 20 1 << CONTROL) |
0300: 28 31 20 3c 3c 20 46 4f 52 4d 41 54 29 20 7c 20 (1 << FORMAT) |
0310: 28 31 20 3c 3c 20 50 52 49 56 41 54 45 5f 55 53 (1 << PRIVATE_US
0320: 45 29 29 0a 0a 23 64 65 66 69 6e 65 20 44 49 47 E))..#define DIG
0330: 49 54 5f 42 49 54 53 20 28 31 20 3c 3c 20 44 45 IT_BITS (1 << DE
0340: 43 49 4d 41 4c 5f 44 49 47 49 54 5f 4e 55 4d 42 CIMAL_DIGIT_NUMB
0350: 45 52 29 0a 0a 23 64 65 66 69 6e 65 20 53 50 41 ER)..#define SPA
0360: 43 45 5f 42 49 54 53 20 28 28 31 20 3c 3c 20 53 CE_BITS ((1 << S
0370: 50 41 43 45 5f 53 45 50 41 52 41 54 4f 52 29 20 PACE_SEPARATOR)
0380: 7c 20 28 31 20 3c 3c 20 4c 49 4e 45 5f 53 45 50 | (1 << LINE_SEP
0390: 41 52 41 54 4f 52 29 20 5c 0a 09 7c 20 28 31 20 ARATOR) \..| (1
03a0: 3c 3c 20 50 41 52 41 47 52 41 50 48 5f 53 45 50 << PARAGRAPH_SEP
03b0: 41 52 41 54 4f 52 29 29 0a 0a 23 64 65 66 69 6e ARATOR))..#defin
03c0: 65 20 57 4f 52 44 5f 42 49 54 53 20 28 41 4c 50 e WORD_BITS (ALP
03d0: 48 41 5f 42 49 54 53 20 7c 20 44 49 47 49 54 5f HA_BITS | DIGIT_
03e0: 42 49 54 53 20 7c 20 28 31 20 3c 3c 20 43 4f 4e BITS | (1 << CON
03f0: 4e 45 43 54 4f 52 5f 50 55 4e 43 54 55 41 54 49 NECTOR_PUNCTUATI
0400: 4f 4e 29 29 0a 0a 23 64 65 66 69 6e 65 20 50 55 ON))..#define PU
0410: 4e 43 54 5f 42 49 54 53 20 28 28 31 20 3c 3c 20 NCT_BITS ((1 <<
0420: 43 4f 4e 4e 45 43 54 4f 52 5f 50 55 4e 43 54 55 CONNECTOR_PUNCTU
0430: 41 54 49 4f 4e 29 20 7c 20 5c 0a 09 28 31 20 3c ATION) | \..(1 <
0440: 3c 20 44 41 53 48 5f 50 55 4e 43 54 55 41 54 49 < DASH_PUNCTUATI
0450: 4f 4e 29 20 7c 20 28 31 20 3c 3c 20 4f 50 45 4e ON) | (1 << OPEN
0460: 5f 50 55 4e 43 54 55 41 54 49 4f 4e 29 20 7c 20 _PUNCTUATION) |
0470: 5c 0a 09 28 31 20 3c 3c 20 43 4c 4f 53 45 5f 50 \..(1 << CLOSE_P
0480: 55 4e 43 54 55 41 54 49 4f 4e 29 20 7c 20 28 31 UNCTUATION) | (1
0490: 20 3c 3c 20 49 4e 49 54 49 41 4c 5f 51 55 4f 54 << INITIAL_QUOT
04a0: 45 5f 50 55 4e 43 54 55 41 54 49 4f 4e 29 20 7c E_PUNCTUATION) |
04b0: 20 5c 0a 09 28 31 20 3c 3c 20 46 49 4e 41 4c 5f \..(1 << FINAL_
04c0: 51 55 4f 54 45 5f 50 55 4e 43 54 55 41 54 49 4f QUOTE_PUNCTUATIO
04d0: 4e 29 20 7c 20 28 31 20 3c 3c 20 4f 54 48 45 52 N) | (1 << OTHER
04e0: 5f 50 55 4e 43 54 55 41 54 49 4f 4e 29 29 0a 0a _PUNCTUATION))..
04f0: 23 64 65 66 69 6e 65 20 47 52 41 50 48 5f 42 49 #define GRAPH_BI
0500: 54 53 20 28 57 4f 52 44 5f 42 49 54 53 20 7c 20 TS (WORD_BITS |
0510: 50 55 4e 43 54 5f 42 49 54 53 20 7c 20 5c 0a 09 PUNCT_BITS | \..
0520: 28 31 20 3c 3c 20 4e 4f 4e 5f 53 50 41 43 49 4e (1 << NON_SPACIN
0530: 47 5f 4d 41 52 4b 29 20 7c 20 28 31 20 3c 3c 20 G_MARK) | (1 <<
0540: 45 4e 43 4c 4f 53 49 4e 47 5f 4d 41 52 4b 29 20 ENCLOSING_MARK)
0550: 7c 20 5c 0a 09 28 31 20 3c 3c 20 43 4f 4d 42 49 | \..(1 << COMBI
0560: 4e 49 4e 47 5f 53 50 41 43 49 4e 47 5f 4d 41 52 NING_SPACING_MAR
0570: 4b 29 20 7c 20 28 31 20 3c 3c 20 4c 45 54 54 45 K) | (1 << LETTE
0580: 52 5f 4e 55 4d 42 45 52 29 20 7c 20 5c 0a 09 28 R_NUMBER) | \..(
0590: 31 20 3c 3c 20 4f 54 48 45 52 5f 4e 55 4d 42 45 1 << OTHER_NUMBE
05a0: 52 29 20 7c 20 5c 0a 09 28 31 20 3c 3c 20 4d 41 R) | \..(1 << MA
05b0: 54 48 5f 53 59 4d 42 4f 4c 29 20 7c 20 28 31 20 TH_SYMBOL) | (1
05c0: 3c 3c 20 43 55 52 52 45 4e 43 59 5f 53 59 4d 42 << CURRENCY_SYMB
05d0: 4f 4c 29 20 7c 20 5c 0a 09 28 31 20 3c 3c 20 4d OL) | \..(1 << M
05e0: 4f 44 49 46 49 45 52 5f 53 59 4d 42 4f 4c 29 20 ODIFIER_SYMBOL)
05f0: 7c 20 28 31 20 3c 3c 20 4f 54 48 45 52 5f 53 59 | (1 << OTHER_SY
0600: 4d 42 4f 4c 29 29 0a 0a 2f 2a 0a 20 2a 20 55 6e MBOL))../*. * Un
0610: 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 73 icode characters
0620: 20 6c 65 73 73 20 74 68 61 6e 20 74 68 69 73 20 less than this
0630: 76 61 6c 75 65 20 61 72 65 20 72 65 70 72 65 73 value are repres
0640: 65 6e 74 65 64 20 62 79 20 74 68 65 6d 73 65 6c ented by themsel
0650: 76 65 73 20 69 6e 0a 20 2a 20 55 54 46 2d 38 20 ves in. * UTF-8
0660: 73 74 72 69 6e 67 73 2e 0a 20 2a 2f 0a 0a 23 64 strings.. */..#d
0670: 65 66 69 6e 65 20 55 4e 49 43 4f 44 45 5f 53 45 efine UNICODE_SE
0680: 4c 46 09 30 78 38 30 0a 0a 2f 2a 0a 20 2a 20 54 LF.0x80../*. * T
0690: 68 65 20 66 6f 6c 6c 6f 77 69 6e 67 20 73 74 72 he following str
06a0: 75 63 74 75 72 65 73 20 61 72 65 20 75 73 65 64 uctures are used
06b0: 20 77 68 65 6e 20 6d 61 70 70 69 6e 67 20 62 65 when mapping be
06c0: 74 77 65 65 6e 20 55 6e 69 63 6f 64 65 20 28 55 tween Unicode (U
06d0: 43 53 2d 32 29 20 61 6e 64 0a 20 2a 20 55 54 46 CS-2) and. * UTF
06e0: 2d 38 2e 0a 20 2a 2f 0a 0a 73 74 61 74 69 63 20 -8.. */..static
06f0: 63 6f 6e 73 74 20 75 6e 73 69 67 6e 65 64 20 63 const unsigned c
0700: 68 61 72 20 74 6f 74 61 6c 42 79 74 65 73 5b 32 har totalBytes[2
0710: 35 36 5d 20 3d 20 7b 0a 20 20 20 20 31 2c 31 2c 56] = {. 1,1,
0720: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0730: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0740: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0750: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 0a 20 20 20 1,1,1,1,1,1,.
0760: 20 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 1,1,1,1,1,1,1,1
0770: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0780: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0790: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
07a0: 2c 0a 20 20 20 20 31 2c 31 2c 31 2c 31 2c 31 2c ,. 1,1,1,1,1,
07b0: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
07c0: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
07d0: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
07e0: 31 2c 31 2c 31 2c 0a 20 20 20 20 31 2c 31 2c 31 1,1,1,. 1,1,1
07f0: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0800: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0810: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0820: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 0a 20 20 20 20 ,1,1,1,1,1,.
0830: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0840: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0850: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0860: 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 1,1,1,1,1,1,1,1,
0870: 0a 20 20 20 20 31 2c 31 2c 31 2c 31 2c 31 2c 31 . 1,1,1,1,1,1
0880: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
0890: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
08a0: 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 2c 31 ,1,1,1,1,1,1,1,1
08b0: 2c 31 2c 31 2c 0a 20 20 20 20 32 2c 32 2c 32 2c ,1,1,. 2,2,2,
08c0: 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 2,2,2,2,2,2,2,2,
08d0: 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 2,2,2,2,2,2,2,2,
08e0: 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 32 2c 2,2,2,2,2,2,2,2,
08f0: 32 2c 32 2c 32 2c 32 2c 32 2c 0a 20 20 20 20 33 2,2,2,2,2,. 3
0900: 2c 33 2c 33 2c 33 2c 33 2c 33 2c 33 2c 33 2c 33 ,3,3,3,3,3,3,3,3
0910: 2c 33 2c 33 2c 33 2c 33 2c 33 2c 33 2c 33 2c 0a ,3,3,3,3,3,3,3,.
0920: 20 20 20 20 34 2c 34 2c 34 2c 34 2c 34 2c 34 2c 4,4,4,4,4,4,
0930: 34 2c 34 2c 0a 20 20 20 20 31 2c 31 2c 31 2c 31 4,4,. 1,1,1,1
0940: 2c 31 2c 31 2c 31 2c 31 0a 7d 3b 0a 0c 0a 2f 2a ,1,1,1,1.};.../*
0950: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
0960: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0970: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0980: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0990: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
09a0: 2a 0a 20 2a 20 54 63 6c 55 74 66 43 6f 75 6e 74 *. * TclUtfCount
09b0: 20 2d 2d 0a 20 2a 0a 20 2a 09 46 69 6e 64 20 74 --. *. *.Find t
09c0: 68 65 20 6e 75 6d 62 65 72 20 6f 66 20 62 79 74 he number of byt
09d0: 65 73 20 69 6e 20 74 68 65 20 55 74 66 20 63 68 es in the Utf ch
09e0: 61 72 61 63 74 65 72 20 22 63 68 22 2e 0a 20 2a aracter "ch".. *
09f0: 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 . * Results:. *.
0a00: 54 68 65 20 72 65 74 75 72 6e 20 76 61 6c 75 65 The return value
0a10: 73 20 69 73 20 74 68 65 20 6e 75 6d 62 65 72 20 s is the number
0a20: 6f 66 20 62 79 74 65 73 20 69 6e 20 74 68 65 20 of bytes in the
0a30: 55 74 66 20 63 68 61 72 61 63 74 65 72 20 22 63 Utf character "c
0a40: 68 22 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 h".. *. * Side e
0a50: 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e ffects:. *.None.
0a60: 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *. *----------
0a70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0a80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0a90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0aa0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0ab0: 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 55 74 -. */..int.TclUt
0ac0: 66 43 6f 75 6e 74 28 0a 20 20 20 20 69 6e 74 20 fCount(. int
0ad0: 63 68 29 09 09 09 2f 2a 20 54 68 65 20 55 6e 69 ch).../* The Uni
0ae0: 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 20 77 code character w
0af0: 68 6f 73 65 20 73 69 7a 65 20 69 73 20 72 65 74 hose size is ret
0b00: 75 72 6e 65 64 2e 20 2a 2f 0a 7b 0a 20 20 20 20 urned. */.{.
0b10: 69 66 20 28 28 75 6e 73 69 67 6e 65 64 29 28 63 if ((unsigned)(c
0b20: 68 20 2d 20 31 29 20 3c 20 28 55 4e 49 43 4f 44 h - 1) < (UNICOD
0b30: 45 5f 53 45 4c 46 20 2d 20 31 29 29 20 7b 0a 09 E_SELF - 1)) {..
0b40: 72 65 74 75 72 6e 20 31 3b 0a 20 20 20 20 7d 0a return 1;. }.
0b50: 20 20 20 20 69 66 20 28 63 68 20 3c 3d 20 30 78 if (ch <= 0x
0b60: 37 46 46 29 20 7b 0a 09 72 65 74 75 72 6e 20 32 7FF) {..return 2
0b70: 3b 0a 20 20 20 20 7d 0a 20 20 20 20 69 66 20 28 ;. }. if (
0b80: 28 28 75 6e 73 69 67 6e 65 64 29 28 63 68 20 2d ((unsigned)(ch -
0b90: 20 30 78 31 30 30 30 30 29 20 3c 3d 20 30 78 46 0x10000) <= 0xF
0ba0: 46 46 46 46 29 29 20 7b 0a 09 72 65 74 75 72 6e FFFF)) {..return
0bb0: 20 34 3b 0a 20 20 20 20 7d 0a 20 20 20 20 72 65 4;. }. re
0bc0: 74 75 72 6e 20 33 3b 0a 7d 0a 0a 2f 2a 0a 20 2a turn 3;.}../*. *
0bd0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0be0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0bf0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0c00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0c10: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 -----------. *.
0c20: 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 55 * Tcl_UniCharToU
0c30: 74 66 20 2d 2d 0a 20 2a 0a 20 2a 09 53 74 6f 72 tf --. *. *.Stor
0c40: 65 20 74 68 65 20 67 69 76 65 6e 20 54 63 6c 5f e the given Tcl_
0c50: 55 6e 69 43 68 61 72 20 61 73 20 61 20 73 65 71 UniChar as a seq
0c60: 75 65 6e 63 65 20 6f 66 20 55 54 46 2d 38 20 62 uence of UTF-8 b
0c70: 79 74 65 73 20 69 6e 20 74 68 65 0a 20 2a 09 70 ytes in the. *.p
0c80: 72 6f 76 69 64 65 64 20 62 75 66 66 65 72 2e 20 rovided buffer.
0c90: 45 71 75 69 76 61 6c 65 6e 74 20 74 6f 20 50 6c Equivalent to Pl
0ca0: 61 6e 20 39 20 72 75 6e 65 74 6f 63 68 61 72 28 an 9 runetochar(
0cb0: 29 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 ).. *. * Results
0cc0: 3a 0a 20 2a 09 54 68 65 20 72 65 74 75 72 6e 20 :. *.The return
0cd0: 76 61 6c 75 65 73 20 69 73 20 74 68 65 20 6e 75 values is the nu
0ce0: 6d 62 65 72 20 6f 66 20 62 79 74 65 73 20 69 6e mber of bytes in
0cf0: 20 74 68 65 20 62 75 66 66 65 72 20 74 68 61 74 the buffer that
0d00: 20 77 65 72 65 0a 20 2a 09 63 6f 6e 73 75 6d 65 were. *.consume
0d10: 64 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 d.. *. * Side ef
0d20: 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a fects:. *.None..
0d30: 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *-----------
0d40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0d50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0d60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0d70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
0d80: 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e . */..int.Tcl_Un
0d90: 69 43 68 61 72 54 6f 55 74 66 28 0a 20 20 20 20 iCharToUtf(.
0da0: 69 6e 74 20 63 68 2c 09 09 09 2f 2a 20 54 68 65 int ch,.../* The
0db0: 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 74 6f 20 Tcl_UniChar to
0dc0: 62 65 20 73 74 6f 72 65 64 20 69 6e 20 74 68 65 be stored in the
0dd0: 0a 09 09 09 09 20 2a 20 62 75 66 66 65 72 2e 20 ..... * buffer.
0de0: 2a 2f 0a 20 20 20 20 63 68 61 72 20 2a 62 75 66 */. char *buf
0df0: 29 09 09 09 2f 2a 20 42 75 66 66 65 72 20 69 6e ).../* Buffer in
0e00: 20 77 68 69 63 68 20 74 68 65 20 55 54 46 2d 38 which the UTF-8
0e10: 20 72 65 70 72 65 73 65 6e 74 61 74 69 6f 6e 20 representation
0e20: 6f 66 0a 09 09 09 09 20 2a 20 74 68 65 20 54 63 of..... * the Tc
0e30: 6c 5f 55 6e 69 43 68 61 72 20 69 73 20 73 74 6f l_UniChar is sto
0e40: 72 65 64 2e 20 42 75 66 66 65 72 20 6d 75 73 74 red. Buffer must
0e50: 20 62 65 0a 09 09 09 09 20 2a 20 6c 61 72 67 65 be..... * large
0e60: 20 65 6e 6f 75 67 68 20 74 6f 20 68 6f 6c 64 20 enough to hold
0e70: 74 68 65 20 55 54 46 2d 38 20 63 68 61 72 61 63 the UTF-8 charac
0e80: 74 65 72 0a 09 09 09 09 20 2a 20 28 61 74 20 6d ter..... * (at m
0e90: 6f 73 74 20 34 20 62 79 74 65 73 29 2e 20 2a 2f ost 4 bytes). */
0ea0: 0a 7b 0a 20 20 20 20 69 66 20 28 28 75 6e 73 69 .{. if ((unsi
0eb0: 67 6e 65 64 29 28 63 68 20 2d 20 31 29 20 3c 20 gned)(ch - 1) <
0ec0: 28 55 4e 49 43 4f 44 45 5f 53 45 4c 46 20 2d 20 (UNICODE_SELF -
0ed0: 31 29 29 20 7b 0a 09 62 75 66 5b 30 5d 20 3d 20 1)) {..buf[0] =
0ee0: 28 63 68 61 72 29 20 63 68 3b 0a 09 72 65 74 75 (char) ch;..retu
0ef0: 72 6e 20 31 3b 0a 20 20 20 20 7d 0a 20 20 20 20 rn 1;. }.
0f00: 69 66 20 28 63 68 20 3e 3d 20 30 29 20 7b 0a 09 if (ch >= 0) {..
0f10: 69 66 20 28 63 68 20 3c 3d 20 30 78 37 46 46 29 if (ch <= 0x7FF)
0f20: 20 7b 0a 09 20 20 20 20 62 75 66 5b 31 5d 20 3d {.. buf[1] =
0f30: 20 28 63 68 61 72 29 20 28 28 63 68 20 7c 20 30 (char) ((ch | 0
0f40: 78 38 30 29 20 26 20 30 78 42 46 29 3b 0a 09 20 x80) & 0xBF);..
0f50: 20 20 20 62 75 66 5b 30 5d 20 3d 20 28 63 68 61 buf[0] = (cha
0f60: 72 29 20 28 28 63 68 20 3e 3e 20 36 29 20 7c 20 r) ((ch >> 6) |
0f70: 30 78 43 30 29 3b 0a 09 20 20 20 20 72 65 74 75 0xC0);.. retu
0f80: 72 6e 20 32 3b 0a 09 7d 0a 09 69 66 20 28 63 68 rn 2;..}..if (ch
0f90: 20 3c 3d 20 30 78 46 46 46 46 29 20 7b 0a 09 20 <= 0xFFFF) {..
0fa0: 20 20 20 69 66 20 28 28 63 68 20 26 20 30 78 46 if ((ch & 0xF
0fb0: 38 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 20 800) == 0xD800)
0fc0: 7b 0a 09 09 69 66 20 28 63 68 20 26 20 30 78 30 {...if (ch & 0x0
0fd0: 34 30 30 29 20 7b 0a 09 09 20 20 20 20 2f 2a 20 400) {... /*
0fe0: 4c 6f 77 20 73 75 72 72 6f 67 61 74 65 20 2a 2f Low surrogate */
0ff0: 0a 09 09 20 20 20 20 69 66 20 28 28 28 62 75 66 ... if (((buf
1000: 5b 30 5d 20 26 20 30 78 46 38 29 20 3d 3d 20 30 [0] & 0xF8) == 0
1010: 78 46 30 29 20 26 26 20 28 28 62 75 66 5b 31 5d xF0) && ((buf[1]
1020: 20 26 20 30 78 43 30 29 20 3d 3d 20 30 78 38 30 & 0xC0) == 0x80
1030: 29 0a 09 09 09 20 20 20 20 26 26 20 28 28 62 75 ).... && ((bu
1040: 66 5b 32 5d 20 26 20 30 78 43 46 29 20 3d 3d 20 f[2] & 0xCF) ==
1050: 30 29 29 20 7b 0a 09 09 09 2f 2a 20 50 72 65 76 0)) {..../* Prev
1060: 69 6f 75 73 20 54 63 6c 5f 55 6e 69 43 68 61 72 ious Tcl_UniChar
1070: 20 77 61 73 20 61 20 48 69 67 68 20 73 75 72 72 was a High surr
1080: 6f 67 61 74 65 2c 20 73 6f 20 63 6f 6d 62 69 6e ogate, so combin
1090: 65 20 2a 2f 0a 09 09 09 62 75 66 5b 33 5d 20 3d e */....buf[3] =
10a0: 20 28 63 68 61 72 29 20 28 28 63 68 20 26 20 30 (char) ((ch & 0
10b0: 78 33 46 29 20 7c 20 30 78 38 30 29 3b 0a 09 09 x3F) | 0x80);...
10c0: 09 62 75 66 5b 32 5d 20 7c 3d 20 28 63 68 61 72 .buf[2] |= (char
10d0: 29 20 28 28 28 63 68 20 3e 3e 20 36 29 20 26 20 ) (((ch >> 6) &
10e0: 30 78 30 46 29 20 7c 20 30 78 38 30 29 3b 0a 09 0x0F) | 0x80);..
10f0: 09 09 72 65 74 75 72 6e 20 34 3b 0a 09 09 20 20 ..return 4;...
1100: 20 20 7d 0a 09 09 20 20 20 20 2f 2a 20 50 72 65 }... /* Pre
1110: 76 69 6f 75 73 20 54 63 6c 5f 55 6e 69 43 68 61 vious Tcl_UniCha
1120: 72 20 77 61 73 20 6e 6f 74 20 61 20 48 69 67 68 r was not a High
1130: 20 73 75 72 72 6f 67 61 74 65 2c 20 73 6f 20 6a surrogate, so j
1140: 75 73 74 20 6f 75 74 70 75 74 20 2a 2f 0a 09 09 ust output */...
1150: 7d 20 65 6c 73 65 20 7b 0a 09 09 20 20 20 20 2f } else {... /
1160: 2a 20 48 69 67 68 20 73 75 72 72 6f 67 61 74 65 * High surrogate
1170: 20 2a 2f 0a 09 09 20 20 20 20 63 68 20 2b 3d 20 */... ch +=
1180: 30 78 34 30 3b 0a 09 09 20 20 20 20 2f 2a 20 46 0x40;... /* F
1190: 69 6c 6c 20 62 75 66 66 65 72 20 77 69 74 68 20 ill buffer with
11a0: 73 70 65 63 69 66 69 63 20 33 2d 62 79 74 65 20 specific 3-byte
11b0: 28 69 6e 76 61 6c 69 64 29 20 62 79 74 65 20 63 (invalid) byte c
11c0: 6f 6d 62 69 6e 61 74 69 6f 6e 2c 0a 09 09 20 20 ombination,...
11d0: 20 20 20 20 20 73 6f 20 66 6f 6c 6c 6f 77 69 6e so followin
11e0: 67 20 4c 6f 77 20 73 75 72 72 6f 67 61 74 65 20 g Low surrogate
11f0: 63 61 6e 20 72 65 63 6f 67 6e 69 7a 65 20 69 74 can recognize it
1200: 20 61 6e 64 20 63 6f 6d 62 69 6e 65 20 2a 2f 0a and combine */.
1210: 09 09 20 20 20 20 62 75 66 5b 32 5d 20 3d 20 28 .. buf[2] = (
1220: 63 68 61 72 29 20 28 28 63 68 20 3c 3c 20 34 29 char) ((ch << 4)
1230: 20 26 20 30 78 33 30 29 3b 0a 09 09 20 20 20 20 & 0x30);...
1240: 62 75 66 5b 31 5d 20 3d 20 28 63 68 61 72 29 20 buf[1] = (char)
1250: 28 28 28 63 68 20 3e 3e 20 32 29 20 26 20 30 78 (((ch >> 2) & 0x
1260: 33 46 29 20 7c 20 30 78 38 30 29 3b 0a 09 09 20 3F) | 0x80);...
1270: 20 20 20 62 75 66 5b 30 5d 20 3d 20 28 63 68 61 buf[0] = (cha
1280: 72 29 20 28 28 28 63 68 20 3e 3e 20 38 29 20 26 r) (((ch >> 8) &
1290: 20 30 78 30 37 29 20 7c 20 30 78 46 30 29 3b 0a 0x07) | 0xF0);.
12a0: 09 09 20 20 20 20 72 65 74 75 72 6e 20 30 3b 0a .. return 0;.
12b0: 09 09 7d 0a 09 20 20 20 20 7d 0a 09 20 20 20 20 ..}.. }..
12c0: 67 6f 74 6f 20 74 68 72 65 65 3b 0a 09 7d 0a 09 goto three;..}..
12d0: 69 66 20 28 63 68 20 3c 3d 20 30 78 31 30 46 46 if (ch <= 0x10FF
12e0: 46 46 29 20 7b 0a 09 20 20 20 20 62 75 66 5b 33 FF) {.. buf[3
12f0: 5d 20 3d 20 28 63 68 61 72 29 20 28 28 63 68 20 ] = (char) ((ch
1300: 7c 20 30 78 38 30 29 20 26 20 30 78 42 46 29 3b | 0x80) & 0xBF);
1310: 0a 09 20 20 20 20 62 75 66 5b 32 5d 20 3d 20 28 .. buf[2] = (
1320: 63 68 61 72 29 20 28 28 28 63 68 20 3e 3e 20 36 char) (((ch >> 6
1330: 29 20 7c 20 30 78 38 30 29 20 26 20 30 78 42 46 ) | 0x80) & 0xBF
1340: 29 3b 0a 09 20 20 20 20 62 75 66 5b 31 5d 20 3d );.. buf[1] =
1350: 20 28 63 68 61 72 29 20 28 28 28 63 68 20 3e 3e (char) (((ch >>
1360: 20 31 32 29 20 7c 20 30 78 38 30 29 20 26 20 30 12) | 0x80) & 0
1370: 78 42 46 29 3b 0a 09 20 20 20 20 62 75 66 5b 30 xBF);.. buf[0
1380: 5d 20 3d 20 28 63 68 61 72 29 20 28 28 63 68 20 ] = (char) ((ch
1390: 3e 3e 20 31 38 29 20 7c 20 30 78 46 30 29 3b 0a >> 18) | 0xF0);.
13a0: 09 20 20 20 20 72 65 74 75 72 6e 20 34 3b 0a 09 . return 4;..
13b0: 7d 0a 20 20 20 20 7d 20 65 6c 73 65 20 69 66 20 }. } else if
13c0: 28 63 68 20 3d 3d 20 2d 31 29 20 7b 0a 09 69 66 (ch == -1) {..if
13d0: 20 28 28 28 62 75 66 5b 30 5d 20 26 20 30 78 46 (((buf[0] & 0xF
13e0: 38 29 20 3d 3d 20 30 78 46 30 29 20 26 26 20 28 8) == 0xF0) && (
13f0: 28 62 75 66 5b 31 5d 20 26 20 30 78 43 30 29 20 (buf[1] & 0xC0)
1400: 3d 3d 20 30 78 38 30 29 0a 09 09 26 26 20 28 28 == 0x80)...&& ((
1410: 62 75 66 5b 32 5d 20 26 20 30 78 43 46 29 20 3d buf[2] & 0xCF) =
1420: 3d 20 30 29 29 20 7b 0a 09 20 20 20 20 63 68 20 = 0)) {.. ch
1430: 3d 20 30 78 44 37 43 30 20 2b 20 28 28 62 75 66 = 0xD7C0 + ((buf
1440: 5b 30 5d 20 26 20 30 78 30 37 29 20 3c 3c 20 38 [0] & 0x07) << 8
1450: 29 20 2b 20 28 28 62 75 66 5b 31 5d 20 26 20 30 ) + ((buf[1] & 0
1460: 78 33 46 29 20 3c 3c 20 32 29 0a 09 09 20 20 20 x3F) << 2)...
1470: 20 2b 20 28 28 62 75 66 5b 32 5d 20 26 20 30 78 + ((buf[2] & 0x
1480: 33 30 29 20 3e 3e 20 34 29 3b 0a 09 20 20 20 20 30) >> 4);..
1490: 67 6f 74 6f 20 74 68 72 65 65 3b 0a 09 7d 0a 20 goto three;..}.
14a0: 20 20 20 7d 0a 0a 20 20 20 20 63 68 20 3d 20 30 }.. ch = 0
14b0: 78 46 46 46 44 3b 0a 74 68 72 65 65 3a 0a 20 20 xFFFD;.three:.
14c0: 20 20 62 75 66 5b 32 5d 20 3d 20 28 63 68 61 72 buf[2] = (char
14d0: 29 20 28 28 63 68 20 7c 20 30 78 38 30 29 20 26 ) ((ch | 0x80) &
14e0: 20 30 78 42 46 29 3b 0a 20 20 20 20 62 75 66 5b 0xBF);. buf[
14f0: 31 5d 20 3d 20 28 63 68 61 72 29 20 28 28 28 63 1] = (char) (((c
1500: 68 20 3e 3e 20 36 29 20 7c 20 30 78 38 30 29 20 h >> 6) | 0x80)
1510: 26 20 30 78 42 46 29 3b 0a 20 20 20 20 62 75 66 & 0xBF);. buf
1520: 5b 30 5d 20 3d 20 28 63 68 61 72 29 20 28 28 63 [0] = (char) ((c
1530: 68 20 3e 3e 20 31 32 29 20 7c 20 30 78 45 30 29 h >> 12) | 0xE0)
1540: 3b 0a 20 20 20 20 72 65 74 75 72 6e 20 33 3b 0a ;. return 3;.
1550: 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d }.../*. *-------
1560: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1570: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1580: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1590: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
15a0: 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 ----. *. * Tcl_U
15b0: 6e 69 43 68 61 72 54 6f 55 74 66 44 53 74 72 69 niCharToUtfDStri
15c0: 6e 67 20 2d 2d 0a 20 2a 0a 20 2a 09 43 6f 6e 76 ng --. *. *.Conv
15d0: 65 72 74 20 74 68 65 20 67 69 76 65 6e 20 55 6e ert the given Un
15e0: 69 63 6f 64 65 20 73 74 72 69 6e 67 20 74 6f 20 icode string to
15f0: 55 54 46 2d 38 2e 0a 20 2a 0a 20 2a 20 52 65 73 UTF-8.. *. * Res
1600: 75 6c 74 73 3a 0a 20 2a 09 54 68 65 20 72 65 74 ults:. *.The ret
1610: 75 72 6e 20 76 61 6c 75 65 20 69 73 20 61 20 70 urn value is a p
1620: 6f 69 6e 74 65 72 20 74 6f 20 74 68 65 20 55 54 ointer to the UT
1630: 46 2d 38 20 72 65 70 72 65 73 65 6e 74 61 74 69 F-8 representati
1640: 6f 6e 20 6f 66 20 74 68 65 0a 20 2a 09 55 6e 69 on of the. *.Uni
1650: 63 6f 64 65 20 73 74 72 69 6e 67 2e 20 53 74 6f code string. Sto
1660: 72 61 67 65 20 66 6f 72 20 74 68 65 20 72 65 74 rage for the ret
1670: 75 72 6e 20 76 61 6c 75 65 20 69 73 20 61 70 70 urn value is app
1680: 65 6e 64 65 64 20 74 6f 20 74 68 65 20 65 6e 64 ended to the end
1690: 20 6f 66 0a 20 2a 09 64 73 50 74 72 2e 0a 20 2a of. *.dsPtr.. *
16a0: 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 . * Side effects
16b0: 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a :. *.None.. *. *
16c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
16d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
16e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
16f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1700: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a -----------. */.
1710: 0a 63 68 61 72 20 2a 0a 54 63 6c 5f 55 6e 69 43 .char *.Tcl_UniC
1720: 68 61 72 54 6f 55 74 66 44 53 74 72 69 6e 67 28 harToUtfDString(
1730: 0a 20 20 20 20 63 6f 6e 73 74 20 54 63 6c 5f 55 . const Tcl_U
1740: 6e 69 43 68 61 72 20 2a 75 6e 69 53 74 72 2c 09 niChar *uniStr,.
1750: 2f 2a 20 55 6e 69 63 6f 64 65 20 73 74 72 69 6e /* Unicode strin
1760: 67 20 74 6f 20 63 6f 6e 76 65 72 74 20 74 6f 20 g to convert to
1770: 55 54 46 2d 38 2e 20 2a 2f 0a 20 20 20 20 69 6e UTF-8. */. in
1780: 74 20 75 6e 69 4c 65 6e 67 74 68 2c 09 09 2f 2a t uniLength,../*
1790: 20 4c 65 6e 67 74 68 20 6f 66 20 55 6e 69 63 6f Length of Unico
17a0: 64 65 20 73 74 72 69 6e 67 20 69 6e 20 54 63 6c de string in Tcl
17b0: 5f 55 6e 69 43 68 61 72 73 0a 09 09 09 09 20 2a _UniChars..... *
17c0: 20 28 6d 75 73 74 20 62 65 20 3e 3d 20 30 29 2e (must be >= 0).
17d0: 20 2a 2f 0a 20 20 20 20 54 63 6c 5f 44 53 74 72 */. Tcl_DStr
17e0: 69 6e 67 20 2a 64 73 50 74 72 29 09 09 2f 2a 20 ing *dsPtr)../*
17f0: 55 54 46 2d 38 20 72 65 70 72 65 73 65 6e 74 61 UTF-8 representa
1800: 74 69 6f 6e 20 6f 66 20 73 74 72 69 6e 67 20 69 tion of string i
1810: 73 20 61 70 70 65 6e 64 65 64 0a 09 09 09 09 20 s appended.....
1820: 2a 20 74 6f 20 74 68 69 73 20 70 72 65 76 69 6f * to this previo
1830: 75 73 6c 79 20 69 6e 69 74 69 61 6c 69 7a 65 64 usly initialized
1840: 20 44 53 74 72 69 6e 67 2e 20 2a 2f 0a 7b 0a 20 DString. */.{.
1850: 20 20 20 63 6f 6e 73 74 20 54 63 6c 5f 55 6e 69 const Tcl_Uni
1860: 43 68 61 72 20 2a 77 2c 20 2a 77 45 6e 64 3b 0a Char *w, *wEnd;.
1870: 20 20 20 20 63 68 61 72 20 2a 70 2c 20 2a 73 74 char *p, *st
1880: 72 69 6e 67 3b 0a 20 20 20 20 69 6e 74 20 6f 6c ring;. int ol
1890: 64 4c 65 6e 67 74 68 2c 20 6c 65 6e 20 3d 20 31 dLength, len = 1
18a0: 3b 0a 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 2a ;.. /*. *
18b0: 20 55 54 46 2d 38 20 73 74 72 69 6e 67 20 6c 65 UTF-8 string le
18c0: 6e 67 74 68 20 69 6e 20 62 79 74 65 73 20 77 69 ngth in bytes wi
18d0: 6c 6c 20 62 65 20 3c 3d 20 55 6e 69 63 6f 64 65 ll be <= Unicode
18e0: 20 73 74 72 69 6e 67 20 6c 65 6e 67 74 68 20 2a string length *
18f0: 20 34 2e 0a 20 20 20 20 20 2a 2f 0a 0a 20 20 20 4.. */..
1900: 20 6f 6c 64 4c 65 6e 67 74 68 20 3d 20 54 63 6c oldLength = Tcl
1910: 5f 44 53 74 72 69 6e 67 4c 65 6e 67 74 68 28 64 _DStringLength(d
1920: 73 50 74 72 29 3b 0a 20 20 20 20 54 63 6c 5f 44 sPtr);. Tcl_D
1930: 53 74 72 69 6e 67 53 65 74 4c 65 6e 67 74 68 28 StringSetLength(
1940: 64 73 50 74 72 2c 20 6f 6c 64 4c 65 6e 67 74 68 dsPtr, oldLength
1950: 20 2b 20 28 75 6e 69 4c 65 6e 67 74 68 20 2b 20 + (uniLength +
1960: 31 29 20 2a 20 34 29 3b 0a 20 20 20 20 73 74 72 1) * 4);. str
1970: 69 6e 67 20 3d 20 54 63 6c 5f 44 53 74 72 69 6e ing = Tcl_DStrin
1980: 67 56 61 6c 75 65 28 64 73 50 74 72 29 20 2b 20 gValue(dsPtr) +
1990: 6f 6c 64 4c 65 6e 67 74 68 3b 0a 0a 20 20 20 20 oldLength;..
19a0: 70 20 3d 20 73 74 72 69 6e 67 3b 0a 20 20 20 20 p = string;.
19b0: 77 45 6e 64 20 3d 20 75 6e 69 53 74 72 20 2b 20 wEnd = uniStr +
19c0: 75 6e 69 4c 65 6e 67 74 68 3b 0a 20 20 20 20 66 uniLength;. f
19d0: 6f 72 20 28 77 20 3d 20 75 6e 69 53 74 72 3b 20 or (w = uniStr;
19e0: 77 20 3c 20 77 45 6e 64 3b 20 29 20 7b 0a 09 69 w < wEnd; ) {..i
19f0: 66 20 28 21 6c 65 6e 20 26 26 20 28 28 2a 77 20 f (!len && ((*w
1a00: 26 20 30 78 46 43 30 30 29 20 21 3d 20 30 78 44 & 0xFC00) != 0xD
1a10: 43 30 30 29 29 20 7b 0a 09 20 20 20 20 2f 2a 20 C00)) {.. /*
1a20: 53 70 65 63 69 61 6c 20 63 61 73 65 20 66 6f 72 Special case for
1a30: 20 68 61 6e 64 6c 69 6e 67 20 75 70 70 65 72 20 handling upper
1a40: 73 75 72 72 6f 67 61 74 65 73 2e 20 2a 2f 0a 09 surrogates. */..
1a50: 20 20 20 20 70 20 2b 3d 20 54 63 6c 5f 55 6e 69 p += Tcl_Uni
1a60: 43 68 61 72 54 6f 55 74 66 28 2d 31 2c 20 70 29 CharToUtf(-1, p)
1a70: 3b 0a 09 7d 0a 09 6c 65 6e 20 3d 20 54 63 6c 5f ;..}..len = Tcl_
1a80: 55 6e 69 43 68 61 72 54 6f 55 74 66 28 2a 77 2c UniCharToUtf(*w,
1a90: 20 70 29 3b 0a 09 70 20 2b 3d 20 6c 65 6e 3b 0a p);..p += len;.
1aa0: 09 77 2b 2b 3b 0a 20 20 20 20 7d 0a 20 20 20 20 .w++;. }.
1ab0: 69 66 20 28 21 6c 65 6e 29 20 7b 0a 09 2f 2a 20 if (!len) {../*
1ac0: 53 70 65 63 69 61 6c 20 63 61 73 65 20 66 6f 72 Special case for
1ad0: 20 68 61 6e 64 6c 69 6e 67 20 75 70 70 65 72 20 handling upper
1ae0: 73 75 72 72 6f 67 61 74 65 73 2e 20 2a 2f 0a 09 surrogates. */..
1af0: 70 20 2b 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 p += Tcl_UniChar
1b00: 54 6f 55 74 66 28 2d 31 2c 20 70 29 3b 0a 20 20 ToUtf(-1, p);.
1b10: 20 20 7d 0a 20 20 20 20 54 63 6c 5f 44 53 74 72 }. Tcl_DStr
1b20: 69 6e 67 53 65 74 4c 65 6e 67 74 68 28 64 73 50 ingSetLength(dsP
1b30: 74 72 2c 20 6f 6c 64 4c 65 6e 67 74 68 20 2b 20 tr, oldLength +
1b40: 28 70 20 2d 20 73 74 72 69 6e 67 29 29 3b 0a 0a (p - string));..
1b50: 20 20 20 20 72 65 74 75 72 6e 20 73 74 72 69 6e return strin
1b60: 67 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d g;.}.../*. *----
1b70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1b80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1b90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1ba0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
1bb0: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 -------. *. * Tc
1bc0: 6c 5f 55 74 66 54 6f 55 6e 69 43 68 61 72 20 2d l_UtfToUniChar -
1bd0: 2d 0a 20 2a 0a 20 2a 09 45 78 74 72 61 63 74 20 -. *. *.Extract
1be0: 74 68 65 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 the Tcl_UniChar
1bf0: 72 65 70 72 65 73 65 6e 74 65 64 20 62 79 20 74 represented by t
1c00: 68 65 20 55 54 46 2d 38 20 73 74 72 69 6e 67 2e he UTF-8 string.
1c10: 20 42 61 64 20 55 54 46 2d 38 0a 20 2a 09 73 65 Bad UTF-8. *.se
1c20: 71 75 65 6e 63 65 73 20 61 72 65 20 63 6f 6e 76 quences are conv
1c30: 65 72 74 65 64 20 74 6f 20 76 61 6c 69 64 20 54 erted to valid T
1c40: 63 6c 5f 55 6e 69 43 68 61 72 73 20 61 6e 64 20 cl_UniChars and
1c50: 70 72 6f 63 65 73 73 69 6e 67 0a 20 2a 09 63 6f processing. *.co
1c60: 6e 74 69 6e 75 65 73 2e 20 45 71 75 69 76 61 6c ntinues. Equival
1c70: 65 6e 74 20 74 6f 20 50 6c 61 6e 20 39 20 63 68 ent to Plan 9 ch
1c80: 61 72 74 6f 72 75 6e 65 28 29 2e 0a 20 2a 0a 20 artorune().. *.
1c90: 2a 09 54 68 65 20 63 61 6c 6c 65 72 20 6d 75 73 *.The caller mus
1ca0: 74 20 65 6e 73 75 72 65 20 74 68 61 74 20 74 68 t ensure that th
1cb0: 65 20 73 6f 75 72 63 65 20 62 75 66 66 65 72 20 e source buffer
1cc0: 69 73 20 6c 6f 6e 67 20 65 6e 6f 75 67 68 20 74 is long enough t
1cd0: 68 61 74 20 74 68 69 73 0a 20 2a 09 72 6f 75 74 hat this. *.rout
1ce0: 69 6e 65 20 64 6f 65 73 20 6e 6f 74 20 72 75 6e ine does not run
1cf0: 20 6f 66 66 20 74 68 65 20 65 6e 64 20 61 6e 64 off the end and
1d00: 20 64 65 72 65 66 65 72 65 6e 63 65 20 6e 6f 6e dereference non
1d10: 2d 65 78 69 73 74 65 6e 74 20 6d 65 6d 6f 72 79 -existent memory
1d20: 0a 20 2a 09 6c 6f 6f 6b 69 6e 67 20 66 6f 72 20 . *.looking for
1d30: 74 72 61 69 6c 20 62 79 74 65 73 2e 20 49 66 20 trail bytes. If
1d40: 74 68 65 20 73 6f 75 72 63 65 20 62 75 66 66 65 the source buffe
1d50: 72 20 69 73 20 6b 6e 6f 77 6e 20 74 6f 20 62 65 r is known to be
1d60: 20 27 5c 30 27 0a 20 2a 09 74 65 72 6d 69 6e 61 '\0'. *.termina
1d70: 74 65 64 2c 20 74 68 69 73 20 63 61 6e 6e 6f 74 ted, this cannot
1d80: 20 68 61 70 70 65 6e 2e 20 4f 74 68 65 72 77 69 happen. Otherwi
1d90: 73 65 2c 20 74 68 65 20 63 61 6c 6c 65 72 20 73 se, the caller s
1da0: 68 6f 75 6c 64 20 63 61 6c 6c 0a 20 2a 09 54 63 hould call. *.Tc
1db0: 6c 5f 55 74 66 43 68 61 72 43 6f 6d 70 6c 65 74 l_UtfCharComplet
1dc0: 65 28 29 20 62 65 66 6f 72 65 20 63 61 6c 6c 69 e() before calli
1dd0: 6e 67 20 74 68 69 73 20 72 6f 75 74 69 6e 65 20 ng this routine
1de0: 74 6f 20 65 6e 73 75 72 65 20 74 68 61 74 0a 20 to ensure that.
1df0: 2a 09 65 6e 6f 75 67 68 20 62 79 74 65 73 20 72 *.enough bytes r
1e00: 65 6d 61 69 6e 20 69 6e 20 74 68 65 20 73 74 72 emain in the str
1e10: 69 6e 67 2e 0a 20 2a 0a 20 2a 09 49 66 20 54 43 ing.. *. *.If TC
1e20: 4c 5f 55 54 46 5f 4d 41 58 20 3d 3d 20 34 2c 20 L_UTF_MAX == 4,
1e30: 73 70 65 63 69 61 6c 20 68 61 6e 64 6c 69 6e 67 special handling
1e40: 20 6f 66 20 53 75 72 72 6f 67 61 74 65 20 70 61 of Surrogate pa
1e50: 69 72 73 20 69 73 20 64 6f 6e 65 3a 0a 20 2a 09 irs is done:. *.
1e60: 46 6f 72 20 61 6e 79 20 55 54 46 2d 38 20 73 74 For any UTF-8 st
1e70: 72 69 6e 67 20 63 6f 6e 74 61 69 6e 69 6e 67 20 ring containing
1e80: 61 20 63 68 61 72 61 63 74 65 72 20 6f 75 74 73 a character outs
1e90: 69 64 65 20 6f 66 20 74 68 65 20 42 4d 50 2c 20 ide of the BMP,
1ea0: 74 68 65 0a 20 2a 09 66 69 72 73 74 20 63 61 6c the. *.first cal
1eb0: 6c 20 74 6f 20 74 68 69 73 20 66 75 6e 63 74 69 l to this functi
1ec0: 6f 6e 20 77 69 6c 6c 20 66 69 6c 6c 20 2a 63 68 on will fill *ch
1ed0: 50 74 72 20 77 69 74 68 20 74 68 65 20 68 69 67 Ptr with the hig
1ee0: 68 20 73 75 72 72 6f 67 61 74 65 0a 20 2a 09 61 h surrogate. *.a
1ef0: 6e 64 20 67 65 6e 65 72 61 74 65 20 61 20 72 65 nd generate a re
1f00: 74 75 72 6e 20 76 61 6c 75 65 20 6f 66 20 30 2e turn value of 0.
1f10: 20 43 61 6c 6c 69 6e 67 20 54 63 6c 5f 55 74 66 Calling Tcl_Utf
1f20: 54 6f 55 6e 69 43 68 61 72 20 61 67 61 69 6e 0a ToUniChar again.
1f30: 20 2a 09 77 69 6c 6c 20 70 72 6f 64 75 63 65 20 *.will produce
1f40: 74 68 65 20 6c 6f 77 20 73 75 72 72 6f 67 61 74 the low surrogat
1f50: 65 20 61 6e 64 20 61 20 72 65 74 75 72 6e 20 76 e and a return v
1f60: 61 6c 75 65 20 6f 66 20 34 2e 20 42 65 63 61 75 alue of 4. Becau
1f70: 73 65 20 2a 63 68 50 74 72 0a 20 2a 09 69 73 20 se *chPtr. *.is
1f80: 75 73 65 64 20 74 6f 20 72 65 6d 65 6d 62 65 72 used to remember
1f90: 20 77 68 65 74 68 65 72 20 74 68 65 20 68 69 67 whether the hig
1fa0: 68 20 73 75 72 72 6f 67 61 74 65 20 69 73 20 61 h surrogate is a
1fb0: 6c 72 65 61 64 79 20 70 72 6f 64 75 63 65 64 2c lready produced,
1fc0: 20 69 74 0a 20 2a 09 69 73 20 72 65 63 6f 6d 6d it. *.is recomm
1fd0: 65 6e 64 65 64 20 74 6f 20 69 6e 69 74 69 61 6c ended to initial
1fe0: 69 7a 65 20 74 68 65 20 76 61 72 69 61 62 6c 65 ize the variable
1ff0: 20 69 74 20 70 6f 69 6e 74 73 20 74 6f 20 61 73 it points to as
2000: 20 30 20 62 65 66 6f 72 65 0a 20 2a 09 74 68 65 0 before. *.the
2010: 20 66 69 72 73 74 20 63 61 6c 6c 20 74 6f 20 54 first call to T
2020: 63 6c 5f 55 74 66 54 6f 55 6e 69 43 68 61 72 20 cl_UtfToUniChar
2030: 69 73 20 64 6f 6e 65 2e 0a 20 2a 0a 20 2a 20 52 is done.. *. * R
2040: 65 73 75 6c 74 73 3a 0a 20 2a 09 2a 63 68 50 74 esults:. *.*chPt
2050: 72 20 69 73 20 66 69 6c 6c 65 64 20 77 69 74 68 r is filled with
2060: 20 74 68 65 20 54 63 6c 5f 55 6e 69 43 68 61 72 the Tcl_UniChar
2070: 2c 20 61 6e 64 20 74 68 65 20 72 65 74 75 72 6e , and the return
2080: 20 76 61 6c 75 65 20 69 73 20 74 68 65 0a 20 2a value is the. *
2090: 09 6e 75 6d 62 65 72 20 6f 66 20 62 79 74 65 73 .number of bytes
20a0: 20 66 72 6f 6d 20 74 68 65 20 55 54 46 2d 38 20 from the UTF-8
20b0: 73 74 72 69 6e 67 20 74 68 61 74 20 77 65 72 65 string that were
20c0: 20 63 6f 6e 73 75 6d 65 64 2e 0a 20 2a 0a 20 2a consumed.. *. *
20d0: 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 Side effects:.
20e0: 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d *.None.. *. *---
20f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2100: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2110: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2120: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2130: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 73 74 --------. */..st
2140: 61 74 69 63 20 63 6f 6e 73 74 20 75 6e 73 69 67 atic const unsig
2150: 6e 65 64 20 73 68 6f 72 74 20 63 70 31 32 35 32 ned short cp1252
2160: 5b 33 32 5d 20 3d 20 7b 0a 20 20 30 78 32 30 61 [32] = {. 0x20a
2170: 63 2c 20 20 20 30 78 38 31 2c 20 30 78 32 30 31 c, 0x81, 0x201
2180: 41 2c 20 30 78 30 31 39 32 2c 20 30 78 32 30 31 A, 0x0192, 0x201
2190: 45 2c 20 30 78 32 30 32 36 2c 20 30 78 32 30 32 E, 0x2026, 0x202
21a0: 30 2c 20 30 78 32 30 32 31 2c 0a 20 20 30 78 30 0, 0x2021,. 0x0
21b0: 32 43 36 2c 20 30 78 32 30 33 30 2c 20 30 78 30 2C6, 0x2030, 0x0
21c0: 31 36 30 2c 20 30 78 32 30 33 39 2c 20 30 78 30 160, 0x2039, 0x0
21d0: 31 35 32 2c 20 20 20 30 78 38 44 2c 20 30 78 30 152, 0x8D, 0x0
21e0: 31 37 44 2c 20 20 20 30 78 38 46 2c 0a 20 20 20 17D, 0x8F,.
21f0: 20 30 78 39 30 2c 20 30 78 32 30 31 38 2c 20 30 0x90, 0x2018, 0
2200: 78 32 30 31 39 2c 20 30 78 32 30 31 43 2c 20 30 x2019, 0x201C, 0
2210: 78 32 30 31 44 2c 20 30 78 32 30 32 32 2c 20 30 x201D, 0x2022, 0
2220: 78 32 30 31 33 2c 20 30 78 32 30 31 34 2c 0a 20 x2013, 0x2014,.
2230: 20 20 30 78 32 44 43 2c 20 30 78 32 31 32 32 2c 0x2DC, 0x2122,
2240: 20 30 78 30 31 36 31 2c 20 30 78 32 30 33 41 2c 0x0161, 0x203A,
2250: 20 30 78 30 31 35 33 2c 20 20 20 30 78 39 44 2c 0x0153, 0x9D,
2260: 20 30 78 30 31 37 45 2c 20 30 78 30 31 37 38 0a 0x017E, 0x0178.
2270: 7d 3b 0a 0a 69 6e 74 0a 54 63 6c 5f 55 74 66 54 };..int.Tcl_UtfT
2280: 6f 55 6e 69 43 68 61 72 28 0a 20 20 20 20 72 65 oUniChar(. re
2290: 67 69 73 74 65 72 20 63 6f 6e 73 74 20 63 68 61 gister const cha
22a0: 72 20 2a 73 72 63 2c 09 2f 2a 20 54 68 65 20 55 r *src,./* The U
22b0: 54 46 2d 38 20 73 74 72 69 6e 67 2e 20 2a 2f 0a TF-8 string. */.
22c0: 20 20 20 20 72 65 67 69 73 74 65 72 20 54 63 6c register Tcl
22d0: 5f 55 6e 69 43 68 61 72 20 2a 63 68 50 74 72 29 _UniChar *chPtr)
22e0: 2f 2a 20 46 69 6c 6c 65 64 20 77 69 74 68 20 74 /* Filled with t
22f0: 68 65 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 72 he Tcl_UniChar r
2300: 65 70 72 65 73 65 6e 74 65 64 20 62 79 0a 09 09 epresented by...
2310: 09 09 20 2a 20 74 68 65 20 55 54 46 2d 38 20 73 .. * the UTF-8 s
2320: 74 72 69 6e 67 2e 20 2a 2f 0a 7b 0a 20 20 20 20 tring. */.{.
2330: 72 65 67 69 73 74 65 72 20 69 6e 74 20 62 79 74 register int byt
2340: 65 3b 0a 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 e;.. /*.
2350: 2a 20 55 6e 72 6f 6c 6c 20 31 20 74 6f 20 33 20 * Unroll 1 to 3
2360: 28 6f 72 20 34 29 20 62 79 74 65 20 55 54 46 2d (or 4) byte UTF-
2370: 38 20 73 65 71 75 65 6e 63 65 73 2e 0a 20 20 20 8 sequences..
2380: 20 20 2a 2f 0a 0a 20 20 20 20 62 79 74 65 20 3d */.. byte =
2390: 20 2a 28 28 75 6e 73 69 67 6e 65 64 20 63 68 61 *((unsigned cha
23a0: 72 20 2a 29 20 73 72 63 29 3b 0a 20 20 20 20 69 r *) src);. i
23b0: 66 20 28 62 79 74 65 20 3c 20 30 78 43 30 29 20 f (byte < 0xC0)
23c0: 7b 0a 09 2f 2a 0a 09 20 2a 20 48 61 6e 64 6c 65 {../*.. * Handle
23d0: 73 20 70 72 6f 70 65 72 6c 79 20 66 6f 72 6d 65 s properly forme
23e0: 64 20 55 54 46 2d 38 20 63 68 61 72 61 63 74 65 d UTF-8 characte
23f0: 72 73 20 62 65 74 77 65 65 6e 20 30 78 30 31 20 rs between 0x01
2400: 61 6e 64 20 30 78 37 46 2e 0a 09 20 2a 20 54 72 and 0x7F... * Tr
2410: 65 61 74 73 20 6e 61 6b 65 64 20 74 72 61 69 6c eats naked trail
2420: 20 62 79 74 65 73 20 30 78 38 30 20 74 6f 20 30 bytes 0x80 to 0
2430: 78 39 46 20 61 73 20 76 61 6c 69 64 20 63 68 61 x9F as valid cha
2440: 72 61 63 74 65 72 73 20 66 72 6f 6d 0a 09 20 2a racters from.. *
2450: 20 74 68 65 20 63 70 31 32 35 32 20 74 61 62 6c the cp1252 tabl
2460: 65 2e 20 53 65 65 3a 20 3c 68 74 74 70 73 3a 2f e. See: <https:/
2470: 2f 65 6e 2e 77 69 6b 69 70 65 64 69 61 2e 6f 72 /en.wikipedia.or
2480: 67 2f 77 69 6b 69 2f 55 54 46 2d 38 3e 0a 09 20 g/wiki/UTF-8>..
2490: 2a 20 41 6c 73 6f 20 74 72 65 61 74 73 20 5c 30 * Also treats \0
24a0: 20 61 6e 64 20 6f 74 68 65 72 20 6e 61 6b 65 64 and other naked
24b0: 20 74 72 61 69 6c 20 62 79 74 65 73 20 30 78 41 trail bytes 0xA
24c0: 30 20 74 6f 20 30 78 42 46 20 61 73 20 76 61 6c 0 to 0xBF as val
24d0: 69 64 0a 09 20 2a 20 63 68 61 72 61 63 74 65 72 id.. * character
24e0: 73 20 72 65 70 72 65 73 65 6e 74 69 6e 67 20 74 s representing t
24f0: 68 65 6d 73 65 6c 76 65 73 2e 0a 09 20 2a 2f 0a hemselves... */.
2500: 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 .#if TCL_UTF_MAX
2510: 20 3c 3d 20 34 0a 09 2f 2a 20 49 66 20 2a 63 68 <= 4../* If *ch
2520: 50 74 72 20 63 6f 6e 74 61 69 6e 73 20 61 20 68 Ptr contains a h
2530: 69 67 68 20 73 75 72 72 6f 67 61 74 65 20 28 70 igh surrogate (p
2540: 72 6f 64 75 63 65 64 20 62 79 20 61 20 70 72 65 roduced by a pre
2550: 76 69 6f 75 73 0a 09 20 2a 20 54 63 6c 5f 55 74 vious.. * Tcl_Ut
2560: 66 54 6f 55 6e 69 43 68 61 72 28 29 20 63 61 6c fToUniChar() cal
2570: 6c 29 20 61 6e 64 20 74 68 65 20 6e 65 78 74 20 l) and the next
2580: 33 20 62 79 74 65 73 20 61 72 65 20 55 54 46 2d 3 bytes are UTF-
2590: 38 20 63 6f 6e 74 69 6e 75 61 74 69 6f 6e 0a 09 8 continuation..
25a0: 20 2a 20 62 79 74 65 73 2c 20 74 68 65 6e 20 77 * bytes, then w
25b0: 65 20 6d 75 73 74 20 70 72 6f 64 75 63 65 20 61 e must produce a
25c0: 20 66 6f 6c 6c 6f 77 2d 75 70 20 6c 6f 77 20 73 follow-up low s
25d0: 75 72 72 6f 67 61 74 65 2e 20 57 65 20 6f 6e 6c urrogate. We onl
25e0: 79 0a 09 20 2a 20 64 6f 20 74 68 61 74 20 69 66 y.. * do that if
25f0: 20 74 68 65 20 68 69 67 68 20 73 75 72 72 6f 67 the high surrog
2600: 61 74 65 20 6d 61 74 63 68 65 73 20 74 68 65 20 ate matches the
2610: 62 69 74 73 20 77 65 20 65 6e 63 6f 75 6e 74 65 bits we encounte
2620: 72 2e 0a 09 20 2a 2f 0a 09 69 66 20 28 28 62 79 r... */..if ((by
2630: 74 65 20 3e 3d 20 30 78 38 30 29 0a 09 09 26 26 te >= 0x80)...&&
2640: 20 28 28 28 28 28 62 79 74 65 20 2d 20 30 78 31 (((((byte - 0x1
2650: 30 29 20 3c 3c 20 32 29 20 26 20 30 78 46 43 29 0) << 2) & 0xFC)
2660: 20 7c 20 30 78 44 38 30 30 29 20 3d 3d 20 28 2a | 0xD800) == (*
2670: 63 68 50 74 72 20 26 20 30 78 46 43 46 43 29 29 chPtr & 0xFCFC))
2680: 0a 09 09 26 26 20 28 28 73 72 63 5b 31 5d 20 26 ...&& ((src[1] &
2690: 20 30 78 46 30 29 20 3d 3d 20 28 28 28 2a 63 68 0xF0) == (((*ch
26a0: 50 74 72 20 3c 3c 20 34 29 20 26 20 30 78 33 30 Ptr << 4) & 0x30
26b0: 29 20 7c 20 30 78 38 30 29 29 0a 09 09 26 26 20 ) | 0x80))...&&
26c0: 28 28 73 72 63 5b 32 5d 20 26 20 30 78 43 30 29 ((src[2] & 0xC0)
26d0: 20 3d 3d 20 30 78 38 30 29 29 20 7b 0a 09 20 20 == 0x80)) {..
26e0: 20 20 2a 63 68 50 74 72 20 3d 20 28 28 73 72 63 *chPtr = ((src
26f0: 5b 31 5d 20 26 20 30 78 30 46 29 20 3c 3c 20 36 [1] & 0x0F) << 6
2700: 29 20 2b 20 28 73 72 63 5b 32 5d 20 26 20 30 78 ) + (src[2] & 0x
2710: 33 46 29 20 2b 20 30 78 44 43 30 30 3b 0a 09 20 3F) + 0xDC00;..
2720: 20 20 20 72 65 74 75 72 6e 20 33 3b 0a 09 7d 0a return 3;..}.
2730: 23 65 6e 64 69 66 0a 09 69 66 20 28 28 75 6e 73 #endif..if ((uns
2740: 69 67 6e 65 64 29 28 62 79 74 65 2d 30 78 38 30 igned)(byte-0x80
2750: 29 20 3c 20 28 75 6e 73 69 67 6e 65 64 29 20 30 ) < (unsigned) 0
2760: 78 32 30 29 20 7b 0a 09 20 20 20 20 2a 63 68 50 x20) {.. *chP
2770: 74 72 20 3d 20 28 54 63 6c 5f 55 6e 69 43 68 61 tr = (Tcl_UniCha
2780: 72 29 20 63 70 31 32 35 32 5b 62 79 74 65 2d 30 r) cp1252[byte-0
2790: 78 38 30 5d 3b 0a 09 7d 20 65 6c 73 65 20 7b 0a x80];..} else {.
27a0: 09 20 20 20 20 2a 63 68 50 74 72 20 3d 20 28 54 . *chPtr = (T
27b0: 63 6c 5f 55 6e 69 43 68 61 72 29 20 62 79 74 65 cl_UniChar) byte
27c0: 3b 0a 09 7d 0a 09 72 65 74 75 72 6e 20 31 3b 0a ;..}..return 1;.
27d0: 20 20 20 20 7d 20 65 6c 73 65 20 69 66 20 28 62 } else if (b
27e0: 79 74 65 20 3c 20 30 78 45 30 29 20 7b 0a 09 69 yte < 0xE0) {..i
27f0: 66 20 28 28 73 72 63 5b 31 5d 20 26 20 30 78 43 f ((src[1] & 0xC
2800: 30 29 20 3d 3d 20 30 78 38 30 29 20 7b 0a 09 20 0) == 0x80) {..
2810: 20 20 20 2f 2a 0a 09 20 20 20 20 20 2a 20 54 77 /*.. * Tw
2820: 6f 2d 62 79 74 65 2d 63 68 61 72 61 63 74 65 72 o-byte-character
2830: 20 6c 65 61 64 2d 62 79 74 65 20 66 6f 6c 6c 6f lead-byte follo
2840: 77 65 64 20 62 79 20 61 20 74 72 61 69 6c 2d 62 wed by a trail-b
2850: 79 74 65 2e 0a 09 20 20 20 20 20 2a 2f 0a 0a 09 yte... */...
2860: 20 20 20 20 2a 63 68 50 74 72 20 3d 20 28 54 63 *chPtr = (Tc
2870: 6c 5f 55 6e 69 43 68 61 72 29 20 28 28 28 62 79 l_UniChar) (((by
2880: 74 65 20 26 20 30 78 31 46 29 20 3c 3c 20 36 29 te & 0x1F) << 6)
2890: 20 7c 20 28 73 72 63 5b 31 5d 20 26 20 30 78 33 | (src[1] & 0x3
28a0: 46 29 29 3b 0a 09 20 20 20 20 69 66 20 28 28 75 F));.. if ((u
28b0: 6e 73 69 67 6e 65 64 29 28 2a 63 68 50 74 72 20 nsigned)(*chPtr
28c0: 2d 20 31 29 20 3e 3d 20 28 55 4e 49 43 4f 44 45 - 1) >= (UNICODE
28d0: 5f 53 45 4c 46 20 2d 20 31 29 29 20 7b 0a 09 09 _SELF - 1)) {...
28e0: 72 65 74 75 72 6e 20 32 3b 0a 09 20 20 20 20 7d return 2;.. }
28f0: 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 41 20 74 ..}.../*.. * A t
2900: 77 6f 2d 62 79 74 65 2d 63 68 61 72 61 63 74 65 wo-byte-characte
2910: 72 20 6c 65 61 64 2d 62 79 74 65 20 6e 6f 74 20 r lead-byte not
2920: 66 6f 6c 6c 6f 77 65 64 20 62 79 20 74 72 61 69 followed by trai
2930: 6c 2d 62 79 74 65 0a 09 20 2a 20 72 65 70 72 65 l-byte.. * repre
2940: 73 65 6e 74 73 20 69 74 73 65 6c 66 2e 0a 09 20 sents itself...
2950: 2a 2f 0a 20 20 20 20 7d 20 65 6c 73 65 20 69 66 */. } else if
2960: 20 28 62 79 74 65 20 3c 20 30 78 46 30 29 20 7b (byte < 0xF0) {
2970: 0a 09 69 66 20 28 28 28 73 72 63 5b 31 5d 20 26 ..if (((src[1] &
2980: 20 30 78 43 30 29 20 3d 3d 20 30 78 38 30 29 20 0xC0) == 0x80)
2990: 26 26 20 28 28 73 72 63 5b 32 5d 20 26 20 30 78 && ((src[2] & 0x
29a0: 43 30 29 20 3d 3d 20 30 78 38 30 29 29 20 7b 0a C0) == 0x80)) {.
29b0: 09 20 20 20 20 2f 2a 0a 09 20 20 20 20 20 2a 20 . /*.. *
29c0: 54 68 72 65 65 2d 62 79 74 65 2d 63 68 61 72 61 Three-byte-chara
29d0: 63 74 65 72 20 6c 65 61 64 20 62 79 74 65 20 66 cter lead byte f
29e0: 6f 6c 6c 6f 77 65 64 20 62 79 20 74 77 6f 20 74 ollowed by two t
29f0: 72 61 69 6c 20 62 79 74 65 73 2e 0a 09 20 20 20 rail bytes...
2a00: 20 20 2a 2f 0a 0a 09 20 20 20 20 2a 63 68 50 74 */... *chPt
2a10: 72 20 3d 20 28 54 63 6c 5f 55 6e 69 43 68 61 72 r = (Tcl_UniChar
2a20: 29 20 28 28 28 62 79 74 65 20 26 20 30 78 30 46 ) (((byte & 0x0F
2a30: 29 20 3c 3c 20 31 32 29 0a 09 09 20 20 20 20 7c ) << 12)... |
2a40: 20 28 28 73 72 63 5b 31 5d 20 26 20 30 78 33 46 ((src[1] & 0x3F
2a50: 29 20 3c 3c 20 36 29 20 7c 20 28 73 72 63 5b 32 ) << 6) | (src[2
2a60: 5d 20 26 20 30 78 33 46 29 29 3b 0a 09 20 20 20 ] & 0x3F));..
2a70: 20 69 66 20 28 2a 63 68 50 74 72 20 3e 20 30 78 if (*chPtr > 0x
2a80: 37 46 46 29 20 7b 0a 09 09 72 65 74 75 72 6e 20 7FF) {...return
2a90: 33 3b 0a 09 20 20 20 20 7d 0a 09 7d 0a 0a 09 2f 3;.. }..}.../
2aa0: 2a 0a 09 20 2a 20 41 20 74 68 72 65 65 2d 62 79 *.. * A three-by
2ab0: 74 65 2d 63 68 61 72 61 63 74 65 72 20 6c 65 61 te-character lea
2ac0: 64 2d 62 79 74 65 20 6e 6f 74 20 66 6f 6c 6c 6f d-byte not follo
2ad0: 77 65 64 20 62 79 20 74 77 6f 20 74 72 61 69 6c wed by two trail
2ae0: 2d 62 79 74 65 73 0a 09 20 2a 20 72 65 70 72 65 -bytes.. * repre
2af0: 73 65 6e 74 73 20 69 74 73 65 6c 66 2e 0a 09 20 sents itself...
2b00: 2a 2f 0a 20 20 20 20 7d 0a 20 20 20 20 65 6c 73 */. }. els
2b10: 65 20 69 66 20 28 62 79 74 65 20 3c 20 30 78 46 e if (byte < 0xF
2b20: 38 29 20 7b 0a 09 69 66 20 28 28 28 73 72 63 5b 8) {..if (((src[
2b30: 31 5d 20 26 20 30 78 43 30 29 20 3d 3d 20 30 78 1] & 0xC0) == 0x
2b40: 38 30 29 20 26 26 20 28 28 73 72 63 5b 32 5d 20 80) && ((src[2]
2b50: 26 20 30 78 43 30 29 20 3d 3d 20 30 78 38 30 29 & 0xC0) == 0x80)
2b60: 20 26 26 20 28 28 73 72 63 5b 33 5d 20 26 20 30 && ((src[3] & 0
2b70: 78 43 30 29 20 3d 3d 20 30 78 38 30 29 29 20 7b xC0) == 0x80)) {
2b80: 0a 09 20 20 20 20 2f 2a 0a 09 20 20 20 20 20 2a .. /*.. *
2b90: 20 46 6f 75 72 2d 62 79 74 65 2d 63 68 61 72 61 Four-byte-chara
2ba0: 63 74 65 72 20 6c 65 61 64 20 62 79 74 65 20 66 cter lead byte f
2bb0: 6f 6c 6c 6f 77 65 64 20 62 79 20 74 68 72 65 65 ollowed by three
2bc0: 20 74 72 61 69 6c 20 62 79 74 65 73 2e 0a 09 20 trail bytes...
2bd0: 20 20 20 20 2a 2f 0a 23 69 66 20 54 43 4c 5f 55 */.#if TCL_U
2be0: 54 46 5f 4d 41 58 20 3c 3d 20 34 0a 09 20 20 20 TF_MAX <= 4..
2bf0: 20 62 79 74 65 20 3d 20 28 28 28 62 79 74 65 20 byte = (((byte
2c00: 26 20 30 78 30 37 29 20 3c 3c 20 38 29 20 7c 20 & 0x07) << 8) |
2c10: 28 28 73 72 63 5b 31 5d 20 26 20 30 78 33 46 29 ((src[1] & 0x3F)
2c20: 20 3c 3c 20 32 29 0a 09 09 20 20 20 20 7c 20 28 << 2)... | (
2c30: 28 73 72 63 5b 32 5d 20 26 20 30 78 33 46 29 20 (src[2] & 0x3F)
2c40: 3e 3e 20 34 29 29 20 2d 20 30 78 34 30 3b 0a 09 >> 4)) - 0x40;..
2c50: 20 20 20 20 69 66 20 28 28 75 6e 73 69 67 6e 65 if ((unsigne
2c60: 64 29 20 62 79 74 65 20 3e 3d 20 30 78 34 30 30 d) byte >= 0x400
2c70: 29 20 7b 0a 09 09 2f 2a 20 6f 75 74 20 6f 66 20 ) {.../* out of
2c80: 72 61 6e 67 65 2c 20 3c 20 30 78 31 30 30 30 30 range, < 0x10000
2c90: 20 6f 72 20 3e 20 30 78 31 30 66 66 66 66 20 2a or > 0x10ffff *
2ca0: 2f 0a 09 20 20 20 20 7d 20 65 6c 73 65 20 7b 0a /.. } else {.
2cb0: 09 09 2f 2a 20 70 72 6f 64 75 63 65 20 68 69 67 ../* produce hig
2cc0: 68 20 73 75 72 72 6f 67 61 74 65 2c 20 61 64 76 h surrogate, adv
2cd0: 61 6e 63 65 20 73 6f 75 72 63 65 20 70 6f 69 6e ance source poin
2ce0: 74 65 72 20 2a 2f 0a 09 09 2a 63 68 50 74 72 20 ter */...*chPtr
2cf0: 3d 20 30 78 44 38 30 30 20 2b 20 62 79 74 65 3b = 0xD800 + byte;
2d00: 0a 09 09 72 65 74 75 72 6e 20 31 3b 0a 09 20 20 ...return 1;..
2d10: 20 20 7d 0a 23 65 6c 73 65 0a 09 20 20 20 20 2a }.#else.. *
2d20: 63 68 50 74 72 20 3d 20 28 54 63 6c 5f 55 6e 69 chPtr = (Tcl_Uni
2d30: 43 68 61 72 29 20 28 28 28 62 79 74 65 20 26 20 Char) (((byte &
2d40: 30 78 30 37 29 20 3c 3c 20 31 38 29 20 7c 20 28 0x07) << 18) | (
2d50: 28 73 72 63 5b 31 5d 20 26 20 30 78 33 46 29 20 (src[1] & 0x3F)
2d60: 3c 3c 20 31 32 29 0a 09 09 20 20 20 20 7c 20 28 << 12)... | (
2d70: 28 73 72 63 5b 32 5d 20 26 20 30 78 33 46 29 20 (src[2] & 0x3F)
2d80: 3c 3c 20 36 29 20 7c 20 28 73 72 63 5b 33 5d 20 << 6) | (src[3]
2d90: 26 20 30 78 33 46 29 29 3b 0a 09 20 20 20 20 69 & 0x3F));.. i
2da0: 66 20 28 28 75 6e 73 69 67 6e 65 64 29 28 2a 63 f ((unsigned)(*c
2db0: 68 50 74 72 20 2d 20 30 78 31 30 30 30 30 29 20 hPtr - 0x10000)
2dc0: 3c 3d 20 30 78 46 46 46 46 46 29 20 7b 0a 09 09 <= 0xFFFFF) {...
2dd0: 72 65 74 75 72 6e 20 34 3b 0a 09 20 20 20 20 7d return 4;.. }
2de0: 0a 23 65 6e 64 69 66 0a 09 7d 0a 0a 09 2f 2a 0a .#endif..}.../*.
2df0: 09 20 2a 20 41 20 66 6f 75 72 2d 62 79 74 65 2d . * A four-byte-
2e00: 63 68 61 72 61 63 74 65 72 20 6c 65 61 64 2d 62 character lead-b
2e10: 79 74 65 20 6e 6f 74 20 66 6f 6c 6c 6f 77 65 64 yte not followed
2e20: 20 62 79 20 74 77 6f 20 74 72 61 69 6c 2d 62 79 by two trail-by
2e30: 74 65 73 0a 09 20 2a 20 72 65 70 72 65 73 65 6e tes.. * represen
2e40: 74 73 20 69 74 73 65 6c 66 2e 0a 09 20 2a 2f 0a ts itself... */.
2e50: 20 20 20 20 7d 0a 0a 20 20 20 20 2a 63 68 50 74 }.. *chPt
2e60: 72 20 3d 20 28 54 63 6c 5f 55 6e 69 43 68 61 72 r = (Tcl_UniChar
2e70: 29 20 62 79 74 65 3b 0a 20 20 20 20 72 65 74 75 ) byte;. retu
2e80: 72 6e 20 31 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d rn 1;.}.../*. *-
2e90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2ea0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2eb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2ec0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
2ed0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a ----------. *. *
2ee0: 20 54 63 6c 5f 55 74 66 54 6f 55 6e 69 43 68 61 Tcl_UtfToUniCha
2ef0: 72 44 53 74 72 69 6e 67 20 2d 2d 0a 20 2a 0a 20 rDString --. *.
2f00: 2a 09 43 6f 6e 76 65 72 74 20 74 68 65 20 55 54 *.Convert the UT
2f10: 46 2d 38 20 73 74 72 69 6e 67 20 74 6f 20 55 6e F-8 string to Un
2f20: 69 63 6f 64 65 2e 0a 20 2a 0a 20 2a 20 52 65 73 icode.. *. * Res
2f30: 75 6c 74 73 3a 0a 20 2a 09 54 68 65 20 72 65 74 ults:. *.The ret
2f40: 75 72 6e 20 76 61 6c 75 65 20 69 73 20 61 20 70 urn value is a p
2f50: 6f 69 6e 74 65 72 20 74 6f 20 74 68 65 20 55 6e ointer to the Un
2f60: 69 63 6f 64 65 20 72 65 70 72 65 73 65 6e 74 61 icode representa
2f70: 74 69 6f 6e 20 6f 66 20 74 68 65 0a 20 2a 09 55 tion of the. *.U
2f80: 54 46 2d 38 20 73 74 72 69 6e 67 2e 20 53 74 6f TF-8 string. Sto
2f90: 72 61 67 65 20 66 6f 72 20 74 68 65 20 72 65 74 rage for the ret
2fa0: 75 72 6e 20 76 61 6c 75 65 20 69 73 20 61 70 70 urn value is app
2fb0: 65 6e 64 65 64 20 74 6f 20 74 68 65 20 65 6e 64 ended to the end
2fc0: 20 6f 66 0a 20 2a 09 64 73 50 74 72 2e 20 54 68 of. *.dsPtr. Th
2fd0: 65 20 55 6e 69 63 6f 64 65 20 73 74 72 69 6e 67 e Unicode string
2fe0: 20 69 73 20 74 65 72 6d 69 6e 61 74 65 64 20 77 is terminated w
2ff0: 69 74 68 20 61 20 55 6e 69 63 6f 64 65 20 4e 55 ith a Unicode NU
3000: 4c 4c 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a LL character.. *
3010: 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 . * Side effects
3020: 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a :. *.None.. *. *
3030: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3040: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3050: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3060: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3070: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a -----------. */.
3080: 0a 54 63 6c 5f 55 6e 69 43 68 61 72 20 2a 0a 54 .Tcl_UniChar *.T
3090: 63 6c 5f 55 74 66 54 6f 55 6e 69 43 68 61 72 44 cl_UtfToUniCharD
30a0: 53 74 72 69 6e 67 28 0a 20 20 20 20 63 6f 6e 73 String(. cons
30b0: 74 20 63 68 61 72 20 2a 73 72 63 2c 09 09 2f 2a t char *src,../*
30c0: 20 55 54 46 2d 38 20 73 74 72 69 6e 67 20 74 6f UTF-8 string to
30d0: 20 63 6f 6e 76 65 72 74 20 74 6f 20 55 6e 69 63 convert to Unic
30e0: 6f 64 65 2e 20 2a 2f 0a 20 20 20 20 69 6e 74 20 ode. */. int
30f0: 6c 65 6e 67 74 68 2c 09 09 09 2f 2a 20 4c 65 6e length,.../* Len
3100: 67 74 68 20 6f 66 20 55 54 46 2d 38 20 73 74 72 gth of UTF-8 str
3110: 69 6e 67 20 69 6e 20 62 79 74 65 73 2c 20 6f 72 ing in bytes, or
3120: 20 2d 31 20 66 6f 72 0a 09 09 09 09 20 2a 20 73 -1 for..... * s
3130: 74 72 6c 65 6e 28 29 2e 20 2a 2f 0a 20 20 20 20 trlen(). */.
3140: 54 63 6c 5f 44 53 74 72 69 6e 67 20 2a 64 73 50 Tcl_DString *dsP
3150: 74 72 29 09 09 2f 2a 20 55 6e 69 63 6f 64 65 20 tr)../* Unicode
3160: 72 65 70 72 65 73 65 6e 74 61 74 69 6f 6e 20 6f representation o
3170: 66 20 73 74 72 69 6e 67 20 69 73 0a 09 09 09 09 f string is.....
3180: 20 2a 20 61 70 70 65 6e 64 65 64 20 74 6f 20 74 * appended to t
3190: 68 69 73 20 70 72 65 76 69 6f 75 73 6c 79 20 69 his previously i
31a0: 6e 69 74 69 61 6c 69 7a 65 64 0a 09 09 09 09 20 nitialized.....
31b0: 2a 20 44 53 74 72 69 6e 67 2e 20 2a 2f 0a 7b 0a * DString. */.{.
31c0: 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 Tcl_UniChar
31d0: 63 68 20 3d 20 30 2c 20 2a 77 2c 20 2a 77 53 74 ch = 0, *w, *wSt
31e0: 72 69 6e 67 3b 0a 20 20 20 20 63 6f 6e 73 74 20 ring;. const
31f0: 63 68 61 72 20 2a 70 2c 20 2a 65 6e 64 3b 0a 20 char *p, *end;.
3200: 20 20 20 69 6e 74 20 6f 6c 64 4c 65 6e 67 74 68 int oldLength
3210: 3b 0a 0a 20 20 20 20 69 66 20 28 6c 65 6e 67 74 ;.. if (lengt
3220: 68 20 3c 20 30 29 20 7b 0a 09 6c 65 6e 67 74 68 h < 0) {..length
3230: 20 3d 20 73 74 72 6c 65 6e 28 73 72 63 29 3b 0a = strlen(src);.
3240: 20 20 20 20 7d 0a 0a 20 20 20 20 2f 2a 0a 20 20 }.. /*.
3250: 20 20 20 2a 20 55 6e 69 63 6f 64 65 20 73 74 72 * Unicode str
3260: 69 6e 67 20 6c 65 6e 67 74 68 20 69 6e 20 54 63 ing length in Tc
3270: 6c 5f 55 6e 69 43 68 61 72 73 20 77 69 6c 6c 20 l_UniChars will
3280: 62 65 20 3c 3d 20 55 54 46 2d 38 20 73 74 72 69 be <= UTF-8 stri
3290: 6e 67 20 6c 65 6e 67 74 68 20 69 6e 0a 20 20 20 ng length in.
32a0: 20 20 2a 20 62 79 74 65 73 2e 0a 20 20 20 20 20 * bytes..
32b0: 2a 2f 0a 0a 20 20 20 20 6f 6c 64 4c 65 6e 67 74 */.. oldLengt
32c0: 68 20 3d 20 54 63 6c 5f 44 53 74 72 69 6e 67 4c h = Tcl_DStringL
32d0: 65 6e 67 74 68 28 64 73 50 74 72 29 3b 0a 0a 20 ength(dsPtr);..
32e0: 20 20 20 54 63 6c 5f 44 53 74 72 69 6e 67 53 65 Tcl_DStringSe
32f0: 74 4c 65 6e 67 74 68 28 64 73 50 74 72 2c 0a 09 tLength(dsPtr,..
3300: 20 20 20 20 6f 6c 64 4c 65 6e 67 74 68 20 2b 20 oldLength +
3310: 28 69 6e 74 29 20 28 28 6c 65 6e 67 74 68 20 2b (int) ((length +
3320: 20 31 29 20 2a 20 73 69 7a 65 6f 66 28 54 63 6c 1) * sizeof(Tcl
3330: 5f 55 6e 69 43 68 61 72 29 29 29 3b 0a 20 20 20 _UniChar)));.
3340: 20 77 53 74 72 69 6e 67 20 3d 20 28 54 63 6c 5f wString = (Tcl_
3350: 55 6e 69 43 68 61 72 20 2a 29 20 28 54 63 6c 5f UniChar *) (Tcl_
3360: 44 53 74 72 69 6e 67 56 61 6c 75 65 28 64 73 50 DStringValue(dsP
3370: 74 72 29 20 2b 20 6f 6c 64 4c 65 6e 67 74 68 29 tr) + oldLength)
3380: 3b 0a 0a 20 20 20 20 77 20 3d 20 77 53 74 72 69 ;.. w = wStri
3390: 6e 67 3b 0a 20 20 20 20 70 20 3d 20 73 72 63 3b ng;. p = src;
33a0: 0a 20 20 20 20 65 6e 64 20 3d 20 73 72 63 20 2b . end = src +
33b0: 20 6c 65 6e 67 74 68 20 2d 20 34 3b 0a 20 20 20 length - 4;.
33c0: 20 77 68 69 6c 65 20 28 70 20 3c 20 65 6e 64 29 while (p < end)
33d0: 20 7b 0a 09 70 20 2b 3d 20 54 63 6c 55 74 66 54 {..p += TclUtfT
33e0: 6f 55 6e 69 43 68 61 72 28 70 2c 20 26 63 68 29 oUniChar(p, &ch)
33f0: 3b 0a 09 2a 77 2b 2b 20 3d 20 63 68 3b 0a 20 20 ;..*w++ = ch;.
3400: 20 20 7d 0a 20 20 20 20 65 6e 64 20 2b 3d 20 34 }. end += 4
3410: 3b 0a 20 20 20 20 77 68 69 6c 65 20 28 70 20 3c ;. while (p <
3420: 20 65 6e 64 29 20 7b 0a 09 69 66 20 28 54 63 6c end) {..if (Tcl
3430: 5f 55 74 66 43 68 61 72 43 6f 6d 70 6c 65 74 65 _UtfCharComplete
3440: 28 70 2c 20 65 6e 64 2d 70 29 29 20 7b 0a 09 20 (p, end-p)) {..
3450: 20 20 20 70 20 2b 3d 20 54 63 6c 55 74 66 54 6f p += TclUtfTo
3460: 55 6e 69 43 68 61 72 28 70 2c 20 26 63 68 29 3b UniChar(p, &ch);
3470: 0a 09 7d 20 65 6c 73 65 20 69 66 20 28 28 75 6e ..} else if ((un
3480: 73 69 67 6e 65 64 29 28 28 55 43 48 41 52 28 2a signed)((UCHAR(*
3490: 70 29 2d 30 78 38 30 29 29 20 3c 20 28 75 6e 73 p)-0x80)) < (uns
34a0: 69 67 6e 65 64 29 20 30 78 32 30 29 20 7b 0a 09 igned) 0x20) {..
34b0: 20 20 20 20 63 68 20 3d 20 28 54 63 6c 5f 55 6e ch = (Tcl_Un
34c0: 69 43 68 61 72 29 20 63 70 31 32 35 32 5b 55 43 iChar) cp1252[UC
34d0: 48 41 52 28 2a 70 2b 2b 29 2d 30 78 38 30 5d 3b HAR(*p++)-0x80];
34e0: 0a 09 7d 20 65 6c 73 65 20 7b 0a 09 20 20 20 20 ..} else {..
34f0: 63 68 20 3d 20 55 43 48 41 52 28 2a 70 2b 2b 29 ch = UCHAR(*p++)
3500: 3b 0a 09 7d 0a 09 2a 77 2b 2b 20 3d 20 63 68 3b ;..}..*w++ = ch;
3510: 0a 20 20 20 20 7d 0a 20 20 20 20 2a 77 20 3d 20 . }. *w =
3520: 27 5c 30 27 3b 0a 20 20 20 20 54 63 6c 5f 44 53 '\0';. Tcl_DS
3530: 74 72 69 6e 67 53 65 74 4c 65 6e 67 74 68 28 64 tringSetLength(d
3540: 73 50 74 72 2c 0a 09 20 20 20 20 6f 6c 64 4c 65 sPtr,.. oldLe
3550: 6e 67 74 68 20 2b 20 28 28 63 68 61 72 20 2a 29 ngth + ((char *)
3560: 20 77 20 2d 20 28 63 68 61 72 20 2a 29 20 77 53 w - (char *) wS
3570: 74 72 69 6e 67 29 29 3b 0a 0a 20 20 20 20 72 65 tring));.. re
3580: 74 75 72 6e 20 77 53 74 72 69 6e 67 3b 0a 7d 0a turn wString;.}.
3590: 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d ../*. *---------
35a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
35b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
35c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
35d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
35e0: 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 74 66 --. *. * Tcl_Utf
35f0: 43 68 61 72 43 6f 6d 70 6c 65 74 65 20 2d 2d 0a CharComplete --.
3600: 20 2a 0a 20 2a 09 44 65 74 65 72 6d 69 6e 65 20 *. *.Determine
3610: 69 66 20 74 68 65 20 55 54 46 2d 38 20 73 74 72 if the UTF-8 str
3620: 69 6e 67 20 6f 66 20 74 68 65 20 67 69 76 65 6e ing of the given
3630: 20 6c 65 6e 67 74 68 20 69 73 20 6c 6f 6e 67 20 length is long
3640: 65 6e 6f 75 67 68 20 74 6f 20 62 65 0a 20 2a 09 enough to be. *.
3650: 64 65 63 6f 64 65 64 20 62 79 20 54 63 6c 5f 55 decoded by Tcl_U
3660: 74 66 54 6f 55 6e 69 43 68 61 72 28 29 2e 20 54 tfToUniChar(). T
3670: 68 69 73 20 64 6f 65 73 20 6e 6f 74 20 65 6e 73 his does not ens
3680: 75 72 65 20 74 68 61 74 20 74 68 65 20 55 54 46 ure that the UTF
3690: 2d 38 0a 20 2a 09 73 74 72 69 6e 67 20 69 73 20 -8. *.string is
36a0: 70 72 6f 70 65 72 6c 79 20 66 6f 72 6d 65 64 2e properly formed.
36b0: 20 45 71 75 69 76 61 6c 65 6e 74 20 74 6f 20 50 Equivalent to P
36c0: 6c 61 6e 20 39 20 66 75 6c 6c 72 75 6e 65 28 29 lan 9 fullrune()
36d0: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
36e0: 0a 20 2a 09 54 68 65 20 72 65 74 75 72 6e 20 76 . *.The return v
36f0: 61 6c 75 65 20 69 73 20 30 20 69 66 20 74 68 65 alue is 0 if the
3700: 20 73 74 72 69 6e 67 20 69 73 20 6e 6f 74 20 6c string is not l
3710: 6f 6e 67 20 65 6e 6f 75 67 68 2c 20 6e 6f 6e 2d ong enough, non-
3720: 7a 65 72 6f 0a 20 2a 09 6f 74 68 65 72 77 69 73 zero. *.otherwis
3730: 65 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 e.. *. * Side ef
3740: 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a fects:. *.None..
3750: 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *-----------
3760: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3770: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3780: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3790: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
37a0: 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 74 . */..int.Tcl_Ut
37b0: 66 43 68 61 72 43 6f 6d 70 6c 65 74 65 28 0a 20 fCharComplete(.
37c0: 20 20 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 73 const char *s
37d0: 72 63 2c 09 09 2f 2a 20 53 74 72 69 6e 67 20 74 rc,../* String t
37e0: 6f 20 63 68 65 63 6b 20 69 66 20 66 69 72 73 74 o check if first
37f0: 20 66 65 77 20 62 79 74 65 73 20 63 6f 6e 74 61 few bytes conta
3800: 69 6e 0a 09 09 09 09 20 2a 20 61 20 63 6f 6d 70 in..... * a comp
3810: 6c 65 74 65 20 55 54 46 2d 38 20 63 68 61 72 61 lete UTF-8 chara
3820: 63 74 65 72 2e 20 2a 2f 0a 20 20 20 20 69 6e 74 cter. */. int
3830: 20 6c 65 6e 67 74 68 29 09 09 09 2f 2a 20 4c 65 length).../* Le
3840: 6e 67 74 68 20 6f 66 20 61 62 6f 76 65 20 73 74 ngth of above st
3850: 72 69 6e 67 20 69 6e 20 62 79 74 65 73 2e 20 2a ring in bytes. *
3860: 2f 0a 7b 0a 20 20 20 20 72 65 74 75 72 6e 20 6c /.{. return l
3870: 65 6e 67 74 68 20 3e 3d 20 74 6f 74 61 6c 42 79 ength >= totalBy
3880: 74 65 73 5b 28 75 6e 73 69 67 6e 65 64 20 63 68 tes[(unsigned ch
3890: 61 72 29 2a 73 72 63 5d 3b 0a 7d 0a 0c 0a 2f 2a ar)*src];.}.../*
38a0: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
38b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
38c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
38d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
38e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
38f0: 2a 0a 20 2a 20 54 63 6c 5f 4e 75 6d 55 74 66 43 *. * Tcl_NumUtfC
3900: 68 61 72 73 20 2d 2d 0a 20 2a 0a 20 2a 09 52 65 hars --. *. *.Re
3910: 74 75 72 6e 73 20 74 68 65 20 6e 75 6d 62 65 72 turns the number
3920: 20 6f 66 20 63 68 61 72 61 63 74 65 72 73 20 28 of characters (
3930: 6e 6f 74 20 62 79 74 65 73 29 20 69 6e 20 74 68 not bytes) in th
3940: 65 20 55 54 46 2d 38 20 73 74 72 69 6e 67 2c 20 e UTF-8 string,
3950: 6e 6f 74 0a 20 2a 09 69 6e 63 6c 75 64 69 6e 67 not. *.including
3960: 20 74 68 65 20 74 65 72 6d 69 6e 61 74 69 6e 67 the terminating
3970: 20 4e 55 4c 4c 20 62 79 74 65 2e 20 54 68 69 73 NULL byte. This
3980: 20 69 73 20 65 71 75 69 76 61 6c 65 6e 74 20 74 is equivalent t
3990: 6f 20 50 6c 61 6e 20 39 0a 20 2a 09 75 74 66 6c o Plan 9. *.utfl
39a0: 65 6e 28 29 20 61 6e 64 20 75 74 66 6e 6c 65 6e en() and utfnlen
39b0: 28 29 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 ().. *. * Result
39c0: 73 3a 0a 20 2a 09 41 73 20 61 62 6f 76 65 2e 0a s:. *.As above..
39d0: 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 *. * Side effec
39e0: 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a ts:. *.None.. *.
39f0: 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *--------------
3a00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3a10: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3a20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3a30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a -------------. *
3a40: 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 4e 75 6d 55 74 /..int.Tcl_NumUt
3a50: 66 43 68 61 72 73 28 0a 20 20 20 20 72 65 67 69 fChars(. regi
3a60: 73 74 65 72 20 63 6f 6e 73 74 20 63 68 61 72 20 ster const char
3a70: 2a 73 72 63 2c 09 2f 2a 20 54 68 65 20 55 54 46 *src,./* The UTF
3a80: 2d 38 20 73 74 72 69 6e 67 20 74 6f 20 6d 65 61 -8 string to mea
3a90: 73 75 72 65 2e 20 2a 2f 0a 20 20 20 20 69 6e 74 sure. */. int
3aa0: 20 6c 65 6e 67 74 68 29 09 09 09 2f 2a 20 54 68 length).../* Th
3ab0: 65 20 6c 65 6e 67 74 68 20 6f 66 20 74 68 65 20 e length of the
3ac0: 73 74 72 69 6e 67 20 69 6e 20 62 79 74 65 73 2c string in bytes,
3ad0: 20 6f 72 20 2d 31 0a 09 09 09 09 20 2a 20 66 6f or -1..... * fo
3ae0: 72 20 73 74 72 6c 65 6e 28 73 74 72 69 6e 67 29 r strlen(string)
3af0: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 . */.{. Tcl_U
3b00: 6e 69 43 68 61 72 20 63 68 20 3d 20 30 3b 0a 20 niChar ch = 0;.
3b10: 20 20 20 72 65 67 69 73 74 65 72 20 69 6e 74 20 register int
3b20: 69 20 3d 20 30 3b 0a 0a 20 20 20 20 2f 2a 0a 20 i = 0;.. /*.
3b30: 20 20 20 20 2a 20 54 68 65 20 73 65 70 61 72 61 * The separa
3b40: 74 65 20 69 6d 70 6c 65 6d 65 6e 74 61 74 69 6f te implementatio
3b50: 6e 73 20 61 72 65 20 66 61 73 74 65 72 2e 0a 20 ns are faster..
3b60: 20 20 20 20 2a 0a 20 20 20 20 20 2a 20 53 69 6e *. * Sin
3b70: 63 65 20 74 68 69 73 20 69 73 20 61 20 74 69 6d ce this is a tim
3b80: 65 2d 73 65 6e 73 69 74 69 76 65 20 66 75 6e 63 e-sensitive func
3b90: 74 69 6f 6e 2c 20 77 65 20 61 6c 73 6f 20 64 6f tion, we also do
3ba0: 20 74 68 65 20 63 68 65 63 6b 20 66 6f 72 20 74 the check for t
3bb0: 68 65 0a 20 20 20 20 20 2a 20 73 69 6e 67 6c 65 he. * single
3bc0: 2d 62 79 74 65 20 63 68 61 72 20 63 61 73 65 20 -byte char case
3bd0: 73 70 65 63 69 61 6c 6c 79 2e 0a 20 20 20 20 20 specially..
3be0: 2a 2f 0a 0a 20 20 20 20 69 66 20 28 6c 65 6e 67 */.. if (leng
3bf0: 74 68 20 3c 20 30 29 20 7b 0a 09 77 68 69 6c 65 th < 0) {..while
3c00: 20 28 2a 73 72 63 20 21 3d 20 27 5c 30 27 29 20 (*src != '\0')
3c10: 7b 0a 09 20 20 20 20 73 72 63 20 2b 3d 20 54 63 {.. src += Tc
3c20: 6c 55 74 66 54 6f 55 6e 69 43 68 61 72 28 73 72 lUtfToUniChar(sr
3c30: 63 2c 20 26 63 68 29 3b 0a 09 20 20 20 20 69 2b c, &ch);.. i+
3c40: 2b 3b 0a 09 7d 0a 09 69 66 20 28 69 20 3c 20 30 +;..}..if (i < 0
3c50: 29 20 69 20 3d 20 49 4e 54 5f 4d 41 58 3b 20 2f ) i = INT_MAX; /
3c60: 2a 20 42 75 67 20 5b 32 37 33 38 34 32 37 5d 20 * Bug [2738427]
3c70: 2a 2f 0a 20 20 20 20 7d 20 65 6c 73 65 20 7b 0a */. } else {.
3c80: 09 72 65 67 69 73 74 65 72 20 63 6f 6e 73 74 20 .register const
3c90: 63 68 61 72 20 2a 65 6e 64 50 74 72 20 3d 20 73 char *endPtr = s
3ca0: 72 63 20 2b 20 6c 65 6e 67 74 68 20 2d 20 34 3b rc + length - 4;
3cb0: 0a 0a 09 77 68 69 6c 65 20 28 73 72 63 20 3c 20 ...while (src <
3cc0: 65 6e 64 50 74 72 29 20 7b 0a 09 20 20 20 20 73 endPtr) {.. s
3cd0: 72 63 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e rc += TclUtfToUn
3ce0: 69 43 68 61 72 28 73 72 63 2c 20 26 63 68 29 3b iChar(src, &ch);
3cf0: 0a 09 20 20 20 20 69 2b 2b 3b 0a 09 7d 0a 09 65 .. i++;..}..e
3d00: 6e 64 50 74 72 20 2b 3d 20 34 3b 0a 09 77 68 69 ndPtr += 4;..whi
3d10: 6c 65 20 28 28 73 72 63 20 3c 20 65 6e 64 50 74 le ((src < endPt
3d20: 72 29 20 26 26 20 54 63 6c 5f 55 74 66 43 68 61 r) && Tcl_UtfCha
3d30: 72 43 6f 6d 70 6c 65 74 65 28 73 72 63 2c 20 65 rComplete(src, e
3d40: 6e 64 50 74 72 20 2d 20 73 72 63 29 29 20 7b 0a ndPtr - src)) {.
3d50: 09 20 20 20 20 73 72 63 20 2b 3d 20 54 63 6c 55 . src += TclU
3d60: 74 66 54 6f 55 6e 69 43 68 61 72 28 73 72 63 2c tfToUniChar(src,
3d70: 20 26 63 68 29 3b 0a 09 20 20 20 20 69 2b 2b 3b &ch);.. i++;
3d80: 0a 09 7d 0a 09 69 66 20 28 73 72 63 20 3c 20 65 ..}..if (src < e
3d90: 6e 64 50 74 72 29 20 7b 0a 09 20 20 20 20 69 20 ndPtr) {.. i
3da0: 2b 3d 20 65 6e 64 50 74 72 20 2d 20 73 72 63 3b += endPtr - src;
3db0: 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 20 20 72 65 ..}. }. re
3dc0: 74 75 72 6e 20 69 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 turn i;.}.../*.
3dd0: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
3de0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3df0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3e00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3e10: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a ------------. *.
3e20: 20 2a 20 54 63 6c 5f 55 74 66 46 69 6e 64 46 69 * Tcl_UtfFindFi
3e30: 72 73 74 20 2d 2d 0a 20 2a 0a 20 2a 09 52 65 74 rst --. *. *.Ret
3e40: 75 72 6e 73 20 61 20 70 6f 69 6e 74 65 72 20 74 urns a pointer t
3e50: 6f 20 74 68 65 20 66 69 72 73 74 20 6f 63 63 75 o the first occu
3e60: 72 61 6e 63 65 20 6f 66 20 74 68 65 20 67 69 76 rance of the giv
3e70: 65 6e 20 55 6e 69 63 6f 64 65 20 63 68 61 72 61 en Unicode chara
3e80: 63 74 65 72 0a 20 2a 09 69 6e 20 74 68 65 20 4e cter. *.in the N
3e90: 55 4c 4c 2d 74 65 72 6d 69 6e 61 74 65 64 20 55 ULL-terminated U
3ea0: 54 46 2d 38 20 73 74 72 69 6e 67 2e 20 54 68 65 TF-8 string. The
3eb0: 20 4e 55 4c 4c 20 74 65 72 6d 69 6e 61 74 6f 72 NULL terminator
3ec0: 20 69 73 20 63 6f 6e 73 69 64 65 72 65 64 0a 20 is considered.
3ed0: 2a 09 70 61 72 74 20 6f 66 20 74 68 65 20 55 54 *.part of the UT
3ee0: 46 2d 38 20 73 74 72 69 6e 67 2e 20 45 71 75 69 F-8 string. Equi
3ef0: 76 61 6c 65 6e 74 20 74 6f 20 50 6c 61 6e 20 39 valent to Plan 9
3f00: 20 75 74 66 72 75 6e 65 28 29 2e 0a 20 2a 0a 20 utfrune().. *.
3f10: 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 41 73 * Results:. *.As
3f20: 20 61 62 6f 76 65 2e 20 49 66 20 74 68 65 20 55 above. If the U
3f30: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
3f40: 20 64 6f 65 73 20 6e 6f 74 20 65 78 69 73 74 20 does not exist
3f50: 69 6e 20 74 68 65 20 67 69 76 65 6e 20 73 74 72 in the given str
3f60: 69 6e 67 2c 0a 20 2a 09 74 68 65 20 72 65 74 75 ing,. *.the retu
3f70: 72 6e 20 76 61 6c 75 65 20 69 73 20 4e 55 4c 4c rn value is NULL
3f80: 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 .. *. * Side eff
3f90: 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 ects:. *.None..
3fa0: 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *------------
3fb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3fc0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3fd0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
3fe0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a ---------------.
3ff0: 20 2a 2f 0a 0a 63 6f 6e 73 74 20 63 68 61 72 20 */..const char
4000: 2a 0a 54 63 6c 5f 55 74 66 46 69 6e 64 46 69 72 *.Tcl_UtfFindFir
4010: 73 74 28 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 st(. const ch
4020: 61 72 20 2a 73 72 63 2c 09 09 2f 2a 20 54 68 65 ar *src,../* The
4030: 20 55 54 46 2d 38 20 73 74 72 69 6e 67 20 74 6f UTF-8 string to
4040: 20 62 65 20 73 65 61 72 63 68 65 64 2e 20 2a 2f be searched. */
4050: 0a 20 20 20 20 69 6e 74 20 63 68 29 09 09 09 2f . int ch).../
4060: 2a 20 54 68 65 20 55 6e 69 63 6f 64 65 20 63 68 * The Unicode ch
4070: 61 72 61 63 74 65 72 20 74 6f 20 73 65 61 72 63 aracter to searc
4080: 68 20 66 6f 72 2e 20 2a 2f 0a 7b 0a 20 20 20 20 h for. */.{.
4090: 69 6e 74 20 6c 65 6e 2c 20 66 75 6c 6c 63 68 61 int len, fullcha
40a0: 72 3b 0a 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 r;. Tcl_UniCh
40b0: 61 72 20 66 69 6e 64 20 3d 20 30 3b 0a 0a 20 20 ar find = 0;..
40c0: 20 20 77 68 69 6c 65 20 28 31 29 20 7b 0a 09 6c while (1) {..l
40d0: 65 6e 20 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 en = TclUtfToUni
40e0: 43 68 61 72 28 73 72 63 2c 20 26 66 69 6e 64 29 Char(src, &find)
40f0: 3b 0a 09 66 75 6c 6c 63 68 61 72 20 3d 20 66 69 ;..fullchar = fi
4100: 6e 64 3b 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f nd;.#if TCL_UTF_
4110: 4d 41 58 20 3c 3d 20 34 0a 09 69 66 20 28 28 6c MAX <= 4..if ((l
4120: 65 6e 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 en == 1) && ((ch
4130: 20 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 & 0xFC00) == 0x
4140: 44 38 30 30 29 29 20 7b 0a 09 20 20 20 20 6c 65 D800)) {.. le
4150: 6e 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 n += TclUtfToUni
4160: 43 68 61 72 28 73 72 63 20 2b 20 6c 65 6e 2c 20 Char(src + len,
4170: 26 66 69 6e 64 29 3b 0a 09 20 20 20 20 66 75 6c &find);.. ful
4180: 6c 63 68 61 72 20 3d 20 28 28 28 66 75 6c 6c 63 lchar = (((fullc
4190: 68 61 72 20 26 20 30 78 33 66 66 29 20 3c 3c 20 har & 0x3ff) <<
41a0: 31 30 29 20 7c 20 28 66 69 6e 64 20 26 20 30 78 10) | (find & 0x
41b0: 33 66 66 29 29 20 2b 20 30 78 31 30 30 30 30 3b 3ff)) + 0x10000;
41c0: 0a 09 7d 0a 23 65 6e 64 69 66 0a 09 69 66 20 28 ..}.#endif..if (
41d0: 66 75 6c 6c 63 68 61 72 20 3d 3d 20 63 68 29 20 fullchar == ch)
41e0: 7b 0a 09 20 20 20 20 72 65 74 75 72 6e 20 73 72 {.. return sr
41f0: 63 3b 0a 09 7d 0a 09 69 66 20 28 2a 73 72 63 20 c;..}..if (*src
4200: 3d 3d 20 27 5c 30 27 29 20 7b 0a 09 20 20 20 20 == '\0') {..
4210: 72 65 74 75 72 6e 20 4e 55 4c 4c 3b 0a 09 7d 0a return NULL;..}.
4220: 09 73 72 63 20 2b 3d 20 6c 65 6e 3b 0a 20 20 20 .src += len;.
4230: 20 7d 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d }.}.../*. *----
4240: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4250: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4260: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4270: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4280: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 -------. *. * Tc
4290: 6c 5f 55 74 66 46 69 6e 64 4c 61 73 74 20 2d 2d l_UtfFindLast --
42a0: 0a 20 2a 0a 20 2a 09 52 65 74 75 72 6e 73 20 61 . *. *.Returns a
42b0: 20 70 6f 69 6e 74 65 72 20 74 6f 20 74 68 65 20 pointer to the
42c0: 6c 61 73 74 20 6f 63 63 75 72 61 6e 63 65 20 6f last occurance o
42d0: 66 20 74 68 65 20 67 69 76 65 6e 20 55 6e 69 63 f the given Unic
42e0: 6f 64 65 20 63 68 61 72 61 63 74 65 72 0a 20 2a ode character. *
42f0: 09 69 6e 20 74 68 65 20 4e 55 4c 4c 2d 74 65 72 .in the NULL-ter
4300: 6d 69 6e 61 74 65 64 20 55 54 46 2d 38 20 73 74 minated UTF-8 st
4310: 72 69 6e 67 2e 20 54 68 65 20 4e 55 4c 4c 20 74 ring. The NULL t
4320: 65 72 6d 69 6e 61 74 6f 72 20 69 73 20 63 6f 6e erminator is con
4330: 73 69 64 65 72 65 64 0a 20 2a 09 70 61 72 74 20 sidered. *.part
4340: 6f 66 20 74 68 65 20 55 54 46 2d 38 20 73 74 72 of the UTF-8 str
4350: 69 6e 67 2e 20 45 71 75 69 76 61 6c 65 6e 74 20 ing. Equivalent
4360: 74 6f 20 50 6c 61 6e 20 39 20 75 74 66 72 72 75 to Plan 9 utfrru
4370: 6e 65 28 29 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 ne().. *. * Resu
4380: 6c 74 73 3a 0a 20 2a 09 41 73 20 61 62 6f 76 65 lts:. *.As above
4390: 2e 20 49 66 20 74 68 65 20 55 6e 69 63 6f 64 65 . If the Unicode
43a0: 20 63 68 61 72 61 63 74 65 72 20 64 6f 65 73 20 character does
43b0: 6e 6f 74 20 65 78 69 73 74 20 69 6e 20 74 68 65 not exist in the
43c0: 20 67 69 76 65 6e 20 73 74 72 69 6e 67 2c 20 74 given string, t
43d0: 68 65 0a 20 2a 09 72 65 74 75 72 6e 20 76 61 6c he. *.return val
43e0: 75 65 20 69 73 20 4e 55 4c 4c 2e 0a 20 2a 0a 20 ue is NULL.. *.
43f0: 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a * Side effects:.
4400: 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d *.None.. *. *--
4410: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4420: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4430: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4440: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4450: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 63 ---------. */..c
4460: 6f 6e 73 74 20 63 68 61 72 20 2a 0a 54 63 6c 5f onst char *.Tcl_
4470: 55 74 66 46 69 6e 64 4c 61 73 74 28 0a 20 20 20 UtfFindLast(.
4480: 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 73 72 63 const char *src
4490: 2c 09 09 2f 2a 20 54 68 65 20 55 54 46 2d 38 20 ,../* The UTF-8
44a0: 73 74 72 69 6e 67 20 74 6f 20 62 65 20 73 65 61 string to be sea
44b0: 72 63 68 65 64 2e 20 2a 2f 0a 20 20 20 20 69 6e rched. */. in
44c0: 74 20 63 68 29 09 09 09 2f 2a 20 54 68 65 20 55 t ch).../* The U
44d0: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
44e0: 20 74 6f 20 73 65 61 72 63 68 20 66 6f 72 2e 20 to search for.
44f0: 2a 2f 0a 7b 0a 20 20 20 20 69 6e 74 20 6c 65 6e */.{. int len
4500: 2c 20 66 75 6c 6c 63 68 61 72 3b 0a 20 20 20 20 , fullchar;.
4510: 54 63 6c 5f 55 6e 69 43 68 61 72 20 66 69 6e 64 Tcl_UniChar find
4520: 20 3d 20 30 3b 0a 20 20 20 20 63 6f 6e 73 74 20 = 0;. const
4530: 63 68 61 72 20 2a 6c 61 73 74 3b 0a 0a 20 20 20 char *last;..
4540: 20 6c 61 73 74 20 3d 20 4e 55 4c 4c 3b 0a 20 20 last = NULL;.
4550: 20 20 77 68 69 6c 65 20 28 31 29 20 7b 0a 09 6c while (1) {..l
4560: 65 6e 20 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 en = TclUtfToUni
4570: 43 68 61 72 28 73 72 63 2c 20 26 66 69 6e 64 29 Char(src, &find)
4580: 3b 0a 09 66 75 6c 6c 63 68 61 72 20 3d 20 66 69 ;..fullchar = fi
4590: 6e 64 3b 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f nd;.#if TCL_UTF_
45a0: 4d 41 58 20 3c 3d 20 34 0a 09 69 66 20 28 28 6c MAX <= 4..if ((l
45b0: 65 6e 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 en == 1) && ((ch
45c0: 20 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 & 0xFC00) == 0x
45d0: 44 38 30 30 29 29 20 7b 0a 09 20 20 20 20 6c 65 D800)) {.. le
45e0: 6e 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 n += TclUtfToUni
45f0: 43 68 61 72 28 73 72 63 20 2b 20 6c 65 6e 2c 20 Char(src + len,
4600: 26 66 69 6e 64 29 3b 0a 09 20 20 20 20 66 75 6c &find);.. ful
4610: 6c 63 68 61 72 20 3d 20 28 28 28 66 75 6c 6c 63 lchar = (((fullc
4620: 68 61 72 20 26 20 30 78 33 66 66 29 20 3c 3c 20 har & 0x3ff) <<
4630: 31 30 29 20 7c 20 28 66 69 6e 64 20 26 20 30 78 10) | (find & 0x
4640: 33 66 66 29 29 20 2b 20 30 78 31 30 30 30 30 3b 3ff)) + 0x10000;
4650: 0a 09 7d 0a 23 65 6e 64 69 66 0a 09 69 66 20 28 ..}.#endif..if (
4660: 66 75 6c 6c 63 68 61 72 20 3d 3d 20 63 68 29 20 fullchar == ch)
4670: 7b 0a 09 20 20 20 20 6c 61 73 74 20 3d 20 73 72 {.. last = sr
4680: 63 3b 0a 09 7d 0a 09 69 66 20 28 2a 73 72 63 20 c;..}..if (*src
4690: 3d 3d 20 27 5c 30 27 29 20 7b 0a 09 20 20 20 20 == '\0') {..
46a0: 62 72 65 61 6b 3b 0a 09 7d 0a 09 73 72 63 20 2b break;..}..src +
46b0: 3d 20 6c 65 6e 3b 0a 20 20 20 20 7d 0a 20 20 20 = len;. }.
46c0: 20 72 65 74 75 72 6e 20 6c 61 73 74 3b 0a 7d 0a return last;.}.
46d0: 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d ../*. *---------
46e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
46f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4700: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4710: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4720: 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 74 66 --. *. * Tcl_Utf
4730: 4e 65 78 74 20 2d 2d 0a 20 2a 0a 20 2a 09 47 69 Next --. *. *.Gi
4740: 76 65 6e 20 61 20 70 6f 69 6e 74 65 72 20 74 6f ven a pointer to
4750: 20 73 6f 6d 65 20 63 75 72 72 65 6e 74 20 6c 6f some current lo
4760: 63 61 74 69 6f 6e 20 69 6e 20 61 20 55 54 46 2d cation in a UTF-
4770: 38 20 73 74 72 69 6e 67 2c 20 6d 6f 76 65 0a 20 8 string, move.
4780: 2a 09 66 6f 72 77 61 72 64 20 6f 6e 65 20 63 68 *.forward one ch
4790: 61 72 61 63 74 65 72 2e 20 54 68 65 20 63 61 6c aracter. The cal
47a0: 6c 65 72 20 6d 75 73 74 20 65 6e 73 75 72 65 20 ler must ensure
47b0: 74 68 61 74 20 74 68 65 79 20 61 72 65 20 6e 6f that they are no
47c0: 74 20 61 73 6b 69 6e 67 0a 20 2a 09 66 6f 72 20 t asking. *.for
47d0: 74 68 65 20 6e 65 78 74 20 63 68 61 72 61 63 74 the next charact
47e0: 65 72 20 61 66 74 65 72 20 74 68 65 20 6c 61 73 er after the las
47f0: 74 20 63 68 61 72 61 63 74 65 72 20 69 6e 20 74 t character in t
4800: 68 65 20 73 74 72 69 6e 67 2e 0a 20 2a 0a 20 2a he string.. *. *
4810: 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 54 68 65 Results:. *.The
4820: 20 72 65 74 75 72 6e 20 76 61 6c 75 65 20 69 73 return value is
4830: 20 74 68 65 20 70 6f 69 6e 74 65 72 20 74 6f 20 the pointer to
4840: 74 68 65 20 6e 65 78 74 20 63 68 61 72 61 63 74 the next charact
4850: 65 72 20 69 6e 20 74 68 65 20 55 54 46 2d 38 0a er in the UTF-8.
4860: 20 2a 09 73 74 72 69 6e 67 2e 0a 20 2a 0a 20 2a *.string.. *. *
4870: 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 Side effects:.
4880: 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d *.None.. *. *---
4890: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
48a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
48b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
48c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
48d0: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 63 6f --------. */..co
48e0: 6e 73 74 20 63 68 61 72 20 2a 0a 54 63 6c 5f 55 nst char *.Tcl_U
48f0: 74 66 4e 65 78 74 28 0a 20 20 20 20 63 6f 6e 73 tfNext(. cons
4900: 74 20 63 68 61 72 20 2a 73 72 63 29 09 09 2f 2a t char *src)../*
4910: 20 54 68 65 20 63 75 72 72 65 6e 74 20 6c 6f 63 The current loc
4920: 61 74 69 6f 6e 20 69 6e 20 74 68 65 20 73 74 72 ation in the str
4930: 69 6e 67 2e 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 ing. */.{. Tc
4940: 6c 5f 55 6e 69 43 68 61 72 20 63 68 20 3d 20 30 l_UniChar ch = 0
4950: 3b 0a 20 20 20 20 69 6e 74 20 6c 65 6e 20 3d 20 ;. int len =
4960: 54 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 72 28 TclUtfToUniChar(
4970: 73 72 63 2c 20 26 63 68 29 3b 0a 0a 23 69 66 20 src, &ch);..#if
4980: 54 43 4c 5f 55 54 46 5f 4d 41 58 20 3c 3d 20 34 TCL_UTF_MAX <= 4
4990: 0a 20 20 20 20 69 66 20 28 28 6c 65 6e 20 3d 3d . if ((len ==
49a0: 20 31 29 20 26 26 20 28 28 63 68 20 26 20 30 78 1) && ((ch & 0x
49b0: 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 FC00) == 0xD800)
49c0: 29 20 7b 0a 20 20 20 20 20 20 6c 65 6e 20 2b 3d ) {. len +=
49d0: 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 72 TclUtfToUniChar
49e0: 28 73 72 63 20 2b 20 6c 65 6e 2c 20 26 63 68 29 (src + len, &ch)
49f0: 3b 0a 20 20 20 20 7d 0a 23 65 6e 64 69 66 0a 20 ;. }.#endif.
4a00: 20 20 20 72 65 74 75 72 6e 20 73 72 63 20 2b 20 return src +
4a10: 6c 65 6e 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d len;.}.../*. *--
4a20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4a30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4a40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4a50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4a60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 ---------. *. *
4a70: 54 63 6c 5f 55 74 66 50 72 65 76 20 2d 2d 0a 20 Tcl_UtfPrev --.
4a80: 2a 0a 20 2a 09 47 69 76 65 6e 20 61 20 70 6f 69 *. *.Given a poi
4a90: 6e 74 65 72 20 74 6f 20 73 6f 6d 65 20 63 75 72 nter to some cur
4aa0: 72 65 6e 74 20 6c 6f 63 61 74 69 6f 6e 20 69 6e rent location in
4ab0: 20 61 20 55 54 46 2d 38 20 73 74 72 69 6e 67 2c a UTF-8 string,
4ac0: 20 6d 6f 76 65 0a 20 2a 09 62 61 63 6b 77 61 72 move. *.backwar
4ad0: 64 73 20 6f 6e 65 20 63 68 61 72 61 63 74 65 72 ds one character
4ae0: 2e 20 54 68 69 73 20 77 6f 72 6b 73 20 63 6f 72 . This works cor
4af0: 72 65 63 74 6c 79 20 77 68 65 6e 20 74 68 65 20 rectly when the
4b00: 70 6f 69 6e 74 65 72 20 69 73 20 69 6e 0a 20 2a pointer is in. *
4b10: 09 74 68 65 20 6d 69 64 64 6c 65 20 6f 66 20 61 .the middle of a
4b20: 20 55 54 46 2d 38 20 63 68 61 72 61 63 74 65 72 UTF-8 character
4b30: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
4b40: 0a 20 2a 09 54 68 65 20 72 65 74 75 72 6e 20 76 . *.The return v
4b50: 61 6c 75 65 20 69 73 20 61 20 70 6f 69 6e 74 65 alue is a pointe
4b60: 72 20 74 6f 20 74 68 65 20 70 72 65 76 69 6f 75 r to the previou
4b70: 73 20 63 68 61 72 61 63 74 65 72 20 69 6e 20 74 s character in t
4b80: 68 65 20 55 54 46 2d 38 0a 20 2a 09 73 74 72 69 he UTF-8. *.stri
4b90: 6e 67 2e 20 49 66 20 74 68 65 20 63 75 72 72 65 ng. If the curre
4ba0: 6e 74 20 6c 6f 63 61 74 69 6f 6e 20 77 61 73 20 nt location was
4bb0: 61 6c 72 65 61 64 79 20 61 74 20 74 68 65 20 62 already at the b
4bc0: 65 67 69 6e 6e 69 6e 67 20 6f 66 20 74 68 65 0a eginning of the.
4bd0: 20 2a 09 73 74 72 69 6e 67 2c 20 74 68 65 20 72 *.string, the r
4be0: 65 74 75 72 6e 20 76 61 6c 75 65 20 77 69 6c 6c eturn value will
4bf0: 20 61 6c 73 6f 20 62 65 20 61 20 70 6f 69 6e 74 also be a point
4c00: 65 72 20 74 6f 20 74 68 65 20 62 65 67 69 6e 6e er to the beginn
4c10: 69 6e 67 20 6f 66 0a 20 2a 09 74 68 65 20 73 74 ing of. *.the st
4c20: 72 69 6e 67 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 ring.. *. * Side
4c30: 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e effects:. *.Non
4c40: 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d e.. *. *--------
4c50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4c60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4c70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4c80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4c90: 2d 2d 2d 0a 20 2a 2f 0a 0a 63 6f 6e 73 74 20 63 ---. */..const c
4ca0: 68 61 72 20 2a 0a 54 63 6c 5f 55 74 66 50 72 65 har *.Tcl_UtfPre
4cb0: 76 28 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 61 v(. const cha
4cc0: 72 20 2a 73 72 63 2c 09 09 2f 2a 20 54 68 65 20 r *src,../* The
4cd0: 63 75 72 72 65 6e 74 20 6c 6f 63 61 74 69 6f 6e current location
4ce0: 20 69 6e 20 74 68 65 20 73 74 72 69 6e 67 2e 20 in the string.
4cf0: 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 61 */. const cha
4d00: 72 20 2a 73 74 61 72 74 29 09 09 2f 2a 20 50 6f r *start)../* Po
4d10: 69 6e 74 65 72 20 74 6f 20 74 68 65 20 62 65 67 inter to the beg
4d20: 69 6e 6e 69 6e 67 20 6f 66 20 74 68 65 20 73 74 inning of the st
4d30: 72 69 6e 67 2c 20 74 6f 0a 09 09 09 09 20 2a 20 ring, to..... *
4d40: 61 76 6f 69 64 20 67 6f 69 6e 67 20 62 61 63 6b avoid going back
4d50: 77 61 72 64 73 20 74 6f 6f 20 66 61 72 2e 20 2a wards too far. *
4d60: 2f 0a 7b 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 /.{. const ch
4d70: 61 72 20 2a 6c 6f 6f 6b 3b 0a 20 20 20 20 69 6e ar *look;. in
4d80: 74 20 69 2c 20 62 79 74 65 3b 0a 0a 20 20 20 20 t i, byte;..
4d90: 6c 6f 6f 6b 20 3d 20 2d 2d 73 72 63 3b 0a 20 20 look = --src;.
4da0: 20 20 66 6f 72 20 28 69 20 3d 20 30 3b 20 69 20 for (i = 0; i
4db0: 3c 20 34 3b 20 69 2b 2b 29 20 7b 0a 09 69 66 20 < 4; i++) {..if
4dc0: 28 6c 6f 6f 6b 20 3c 20 73 74 61 72 74 29 20 7b (look < start) {
4dd0: 0a 09 20 20 20 20 69 66 20 28 73 72 63 20 3c 20 .. if (src <
4de0: 73 74 61 72 74 29 20 7b 0a 09 09 73 72 63 20 3d start) {...src =
4df0: 20 73 74 61 72 74 3b 0a 09 20 20 20 20 7d 0a 09 start;.. }..
4e00: 20 20 20 20 62 72 65 61 6b 3b 0a 09 7d 0a 09 62 break;..}..b
4e10: 79 74 65 20 3d 20 2a 28 28 75 6e 73 69 67 6e 65 yte = *((unsigne
4e20: 64 20 63 68 61 72 20 2a 29 20 6c 6f 6f 6b 29 3b d char *) look);
4e30: 0a 09 69 66 20 28 62 79 74 65 20 3c 20 30 78 38 ..if (byte < 0x8
4e40: 30 29 20 7b 0a 09 20 20 20 20 62 72 65 61 6b 3b 0) {.. break;
4e50: 0a 09 7d 0a 09 69 66 20 28 62 79 74 65 20 3e 3d ..}..if (byte >=
4e60: 20 30 78 43 30 29 20 7b 0a 09 20 20 20 20 72 65 0xC0) {.. re
4e70: 74 75 72 6e 20 6c 6f 6f 6b 3b 0a 09 7d 0a 09 6c turn look;..}..l
4e80: 6f 6f 6b 2d 2d 3b 0a 20 20 20 20 7d 0a 20 20 20 ook--;. }.
4e90: 20 72 65 74 75 72 6e 20 73 72 63 3b 0a 7d 0a 0c return src;.}..
4ea0: 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ./*. *----------
4eb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4ec0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4ed0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4ee0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4ef0: 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 -. *. * Tcl_UniC
4f00: 68 61 72 41 74 49 6e 64 65 78 20 2d 2d 0a 20 2a harAtIndex --. *
4f10: 0a 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 . *.Returns the
4f20: 54 63 6c 5f 55 6e 69 43 68 61 72 20 72 65 70 72 Tcl_UniChar repr
4f30: 65 73 65 6e 74 65 64 20 61 74 20 74 68 65 20 73 esented at the s
4f40: 70 65 63 69 66 69 65 64 20 63 68 61 72 61 63 74 pecified charact
4f50: 65 72 0a 20 2a 09 28 6e 6f 74 20 62 79 74 65 29 er. *.(not byte)
4f60: 20 70 6f 73 69 74 69 6f 6e 20 69 6e 20 74 68 65 position in the
4f70: 20 55 54 46 2d 38 20 73 74 72 69 6e 67 2e 0a 20 UTF-8 string..
4f80: 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a *. * Results:. *
4f90: 09 41 73 20 61 62 6f 76 65 2e 0a 20 2a 0a 20 2a .As above.. *. *
4fa0: 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 Side effects:.
4fb0: 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d *.None.. *. *---
4fc0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4fd0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4fe0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
4ff0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5000: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e --------. */..in
5010: 74 0a 54 63 6c 5f 55 6e 69 43 68 61 72 41 74 49 t.Tcl_UniCharAtI
5020: 6e 64 65 78 28 0a 20 20 20 20 72 65 67 69 73 74 ndex(. regist
5030: 65 72 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 73 er const char *s
5040: 72 63 2c 09 2f 2a 20 54 68 65 20 55 54 46 2d 38 rc,./* The UTF-8
5050: 20 73 74 72 69 6e 67 20 74 6f 20 64 65 72 65 66 string to deref
5060: 65 72 65 6e 63 65 2e 20 2a 2f 0a 20 20 20 20 72 erence. */. r
5070: 65 67 69 73 74 65 72 20 69 6e 74 20 69 6e 64 65 egister int inde
5080: 78 29 09 09 2f 2a 20 54 68 65 20 70 6f 73 69 74 x)../* The posit
5090: 69 6f 6e 20 6f 66 20 74 68 65 20 64 65 73 69 72 ion of the desir
50a0: 65 64 20 63 68 61 72 61 63 74 65 72 2e 20 2a 2f ed character. */
50b0: 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 .{. Tcl_UniCh
50c0: 61 72 20 63 68 20 3d 20 30 3b 0a 20 20 20 20 69 ar ch = 0;. i
50d0: 6e 74 20 66 75 6c 6c 63 68 61 72 20 3d 20 30 3b nt fullchar = 0;
50e0: 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 .#if TCL_UTF_MAX
50f0: 20 3c 3d 20 34 0a 09 69 6e 74 20 6c 65 6e 20 3d <= 4..int len =
5100: 20 30 3b 0a 23 65 6e 64 69 66 0a 0a 20 20 20 20 0;.#endif..
5110: 77 68 69 6c 65 20 28 69 6e 64 65 78 2d 2d 20 3e while (index-- >
5120: 3d 20 30 29 20 7b 0a 23 69 66 20 54 43 4c 5f 55 = 0) {.#if TCL_U
5130: 54 46 5f 4d 41 58 20 3c 3d 20 34 0a 09 73 72 63 TF_MAX <= 4..src
5140: 20 2b 3d 20 28 6c 65 6e 20 3d 20 54 63 6c 55 74 += (len = TclUt
5150: 66 54 6f 55 6e 69 43 68 61 72 28 73 72 63 2c 20 fToUniChar(src,
5160: 26 63 68 29 29 3b 0a 23 65 6c 73 65 0a 09 73 72 &ch));.#else..sr
5170: 63 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 c += TclUtfToUni
5180: 43 68 61 72 28 73 72 63 2c 20 26 63 68 29 3b 0a Char(src, &ch);.
5190: 23 65 6e 64 69 66 0a 20 20 20 20 7d 0a 20 20 20 #endif. }.
51a0: 20 66 75 6c 6c 63 68 61 72 20 3d 20 63 68 3b 0a fullchar = ch;.
51b0: 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 #if TCL_UTF_MAX
51c0: 3c 3d 20 34 0a 20 20 20 20 69 66 20 28 28 6c 65 <= 4. if ((le
51d0: 6e 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 20 n == 1) && ((ch
51e0: 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 & 0xFC00) == 0xD
51f0: 38 30 30 29 29 20 7b 0a 09 2f 2a 20 49 66 20 6c 800)) {../* If l
5200: 61 73 74 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 ast Tcl_UniChar
5210: 77 61 73 20 61 6e 20 75 70 70 65 72 20 73 75 72 was an upper sur
5220: 72 6f 67 61 74 65 2c 20 63 6f 6d 62 69 6e 65 20 rogate, combine
5230: 77 69 74 68 20 6c 6f 77 65 72 20 73 75 72 72 6f with lower surro
5240: 67 61 74 65 20 2a 2f 0a 09 28 76 6f 69 64 29 54 gate */..(void)T
5250: 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 72 28 73 clUtfToUniChar(s
5260: 72 63 20 2b 20 6c 65 6e 2c 20 26 63 68 29 3b 0a rc + len, &ch);.
5270: 09 66 75 6c 6c 63 68 61 72 20 3d 20 28 28 28 66 .fullchar = (((f
5280: 75 6c 6c 63 68 61 72 20 26 20 30 78 33 66 66 29 ullchar & 0x3ff)
5290: 20 3c 3c 20 31 30 29 20 7c 20 28 63 68 20 26 20 << 10) | (ch &
52a0: 30 78 33 66 66 29 29 20 2b 20 30 78 31 30 30 30 0x3ff)) + 0x1000
52b0: 30 3b 0a 20 20 20 20 7d 0a 23 65 6e 64 69 66 0a 0;. }.#endif.
52c0: 20 20 20 20 72 65 74 75 72 6e 20 66 75 6c 6c 63 return fullc
52d0: 68 61 72 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d har;.}.../*. *--
52e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
52f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5300: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5310: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5320: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 ---------. *. *
5330: 54 63 6c 5f 55 74 66 41 74 49 6e 64 65 78 20 2d Tcl_UtfAtIndex -
5340: 2d 0a 20 2a 0a 20 2a 09 52 65 74 75 72 6e 73 20 -. *. *.Returns
5350: 61 20 70 6f 69 6e 74 65 72 20 74 6f 20 74 68 65 a pointer to the
5360: 20 73 70 65 63 69 66 69 65 64 20 63 68 61 72 61 specified chara
5370: 63 74 65 72 20 28 6e 6f 74 20 62 79 74 65 29 20 cter (not byte)
5380: 70 6f 73 69 74 69 6f 6e 20 69 6e 0a 20 2a 09 74 position in. *.t
5390: 68 65 20 55 54 46 2d 38 20 73 74 72 69 6e 67 2e he UTF-8 string.
53a0: 20 49 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 If TCL_UTF_MAX
53b0: 3c 3d 20 34 2c 20 63 68 61 72 61 63 74 65 72 73 <= 4, characters
53c0: 20 3e 20 55 2b 46 46 46 46 20 63 6f 75 6e 74 20 > U+FFFF count
53d0: 61 73 0a 20 2a 09 32 20 70 6f 73 69 74 69 6f 6e as. *.2 position
53e0: 73 2c 20 62 75 74 20 74 68 65 6e 20 74 68 65 20 s, but then the
53f0: 70 6f 69 6e 74 65 72 20 73 68 6f 75 6c 64 20 6e pointer should n
5400: 65 76 65 72 20 62 65 20 70 6c 61 63 65 64 20 62 ever be placed b
5410: 65 74 77 65 65 6e 0a 20 2a 09 74 68 65 20 74 77 etween. *.the tw
5420: 6f 20 70 6f 73 69 74 69 6f 6e 73 2e 0a 20 2a 0a o positions.. *.
5430: 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 41 * Results:. *.A
5440: 73 20 61 62 6f 76 65 2e 0a 20 2a 0a 20 2a 20 53 s above.. *. * S
5450: 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 ide effects:. *.
5460: 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d None.. *. *-----
5470: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5480: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5490: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
54a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
54b0: 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 63 6f 6e 73 ------. */..cons
54c0: 74 20 63 68 61 72 20 2a 0a 54 63 6c 5f 55 74 66 t char *.Tcl_Utf
54d0: 41 74 49 6e 64 65 78 28 0a 20 20 20 20 72 65 67 AtIndex(. reg
54e0: 69 73 74 65 72 20 63 6f 6e 73 74 20 63 68 61 72 ister const char
54f0: 20 2a 73 72 63 2c 09 2f 2a 20 54 68 65 20 55 54 *src,./* The UT
5500: 46 2d 38 20 73 74 72 69 6e 67 2e 20 2a 2f 0a 20 F-8 string. */.
5510: 20 20 20 72 65 67 69 73 74 65 72 20 69 6e 74 20 register int
5520: 69 6e 64 65 78 29 09 09 2f 2a 20 54 68 65 20 70 index)../* The p
5530: 6f 73 69 74 69 6f 6e 20 6f 66 20 74 68 65 20 64 osition of the d
5540: 65 73 69 72 65 64 20 63 68 61 72 61 63 74 65 72 esired character
5550: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 . */.{. Tcl_U
5560: 6e 69 43 68 61 72 20 63 68 20 3d 20 30 3b 0a 20 niChar ch = 0;.
5570: 20 20 20 69 6e 74 20 6c 65 6e 20 3d 20 30 3b 0a int len = 0;.
5580: 0a 20 20 20 20 77 68 69 6c 65 20 28 69 6e 64 65 . while (inde
5590: 78 2d 2d 20 3e 20 30 29 20 7b 0a 09 6c 65 6e 20 x-- > 0) {..len
55a0: 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 = TclUtfToUniCha
55b0: 72 28 73 72 63 2c 20 26 63 68 29 3b 0a 09 73 72 r(src, &ch);..sr
55c0: 63 20 2b 3d 20 6c 65 6e 3b 0a 20 20 20 20 7d 0a c += len;. }.
55d0: 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 #if TCL_UTF_MAX
55e0: 3c 3d 20 34 0a 20 20 20 20 69 66 20 28 28 6c 65 <= 4. if ((le
55f0: 6e 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 20 n == 1) && ((ch
5600: 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 & 0xFC00) == 0xD
5610: 38 30 30 29 29 20 7b 0a 09 2f 2a 20 49 6e 64 65 800)) {../* Inde
5620: 78 20 70 6f 69 6e 74 73 20 61 74 20 63 68 61 72 x points at char
5630: 61 63 74 65 72 20 66 6f 6c 6c 6f 77 69 6e 67 20 acter following
5640: 48 69 67 68 20 53 75 72 72 6f 67 61 74 65 20 2a High Surrogate *
5650: 2f 0a 09 73 72 63 20 2b 3d 20 54 63 6c 55 74 66 /..src += TclUtf
5660: 54 6f 55 6e 69 43 68 61 72 28 73 72 63 2c 20 26 ToUniChar(src, &
5670: 63 68 29 3b 0a 20 20 20 20 7d 0a 23 65 6e 64 69 ch);. }.#endi
5680: 66 0a 20 20 20 20 72 65 74 75 72 6e 20 73 72 63 f. return src
5690: 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d ;.}.../*. *-----
56a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
56b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
56c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
56d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
56e0: 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c ------. *. * Tcl
56f0: 5f 55 74 66 42 61 63 6b 73 6c 61 73 68 20 2d 2d _UtfBackslash --
5700: 0a 20 2a 0a 20 2a 09 46 69 67 75 72 65 20 6f 75 . *. *.Figure ou
5710: 74 20 68 6f 77 20 74 6f 20 68 61 6e 64 6c 65 20 t how to handle
5720: 61 20 62 61 63 6b 73 6c 61 73 68 20 73 65 71 75 a backslash sequ
5730: 65 6e 63 65 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 ence.. *. * Resu
5740: 6c 74 73 3a 0a 20 2a 09 53 74 6f 72 65 73 20 74 lts:. *.Stores t
5750: 68 65 20 62 79 74 65 73 20 72 65 70 72 65 73 65 he bytes represe
5760: 6e 74 65 64 20 62 79 20 74 68 65 20 62 61 63 6b nted by the back
5770: 73 6c 61 73 68 20 73 65 71 75 65 6e 63 65 20 69 slash sequence i
5780: 6e 20 64 73 74 20 61 6e 64 0a 20 2a 09 72 65 74 n dst and. *.ret
5790: 75 72 6e 73 20 74 68 65 20 6e 75 6d 62 65 72 20 urns the number
57a0: 6f 66 20 62 79 74 65 73 20 77 72 69 74 74 65 6e of bytes written
57b0: 20 74 6f 20 64 73 74 2e 20 41 74 20 6d 6f 73 74 to dst. At most
57c0: 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 62 79 74 TCL_UTF_MAX byt
57d0: 65 73 0a 20 2a 09 61 72 65 20 77 72 69 74 74 65 es. *.are writte
57e0: 6e 20 74 6f 20 64 73 74 3b 20 64 73 74 20 6d 75 n to dst; dst mu
57f0: 73 74 20 68 61 76 65 20 62 65 65 6e 20 6c 61 72 st have been lar
5800: 67 65 20 65 6e 6f 75 67 68 20 74 6f 20 61 63 63 ge enough to acc
5810: 65 70 74 20 74 68 6f 73 65 0a 20 2a 09 62 79 74 ept those. *.byt
5820: 65 73 2e 20 49 66 20 72 65 61 64 50 74 72 20 69 es. If readPtr i
5830: 73 6e 27 74 20 4e 55 4c 4c 20 74 68 65 6e 20 69 sn't NULL then i
5840: 74 20 69 73 20 66 69 6c 6c 65 64 20 69 6e 20 77 t is filled in w
5850: 69 74 68 20 61 20 63 6f 75 6e 74 20 6f 66 20 74 ith a count of t
5860: 68 65 0a 20 2a 09 6e 75 6d 62 65 72 20 6f 66 20 he. *.number of
5870: 62 79 74 65 73 20 69 6e 20 74 68 65 20 62 61 63 bytes in the bac
5880: 6b 73 6c 61 73 68 20 73 65 71 75 65 6e 63 65 2e kslash sequence.
5890: 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 . *. * Side effe
58a0: 63 74 73 3a 0a 20 2a 09 54 68 65 20 6d 61 78 69 cts:. *.The maxi
58b0: 6d 75 6d 20 6e 75 6d 62 65 72 20 6f 66 20 62 79 mum number of by
58c0: 74 65 73 20 69 74 20 74 61 6b 65 73 20 74 6f 20 tes it takes to
58d0: 72 65 70 72 65 73 65 6e 74 20 61 20 55 6e 69 63 represent a Unic
58e0: 6f 64 65 20 63 68 61 72 61 63 74 65 72 0a 20 2a ode character. *
58f0: 09 69 6e 20 55 54 46 2d 38 20 69 73 20 67 75 61 .in UTF-8 is gua
5900: 72 61 6e 74 65 65 64 20 74 6f 20 62 65 20 6c 65 ranteed to be le
5910: 73 73 20 74 68 61 6e 20 74 68 65 20 6e 75 6d 62 ss than the numb
5920: 65 72 20 6f 66 20 62 79 74 65 73 20 75 73 65 64 er of bytes used
5930: 20 74 6f 0a 20 2a 09 65 78 70 72 65 73 73 20 74 to. *.express t
5940: 68 65 20 62 61 63 6b 73 6c 61 73 68 20 73 65 71 he backslash seq
5950: 75 65 6e 63 65 20 74 68 61 74 20 72 65 70 72 65 uence that repre
5960: 73 65 6e 74 73 20 74 68 61 74 20 55 6e 69 63 6f sents that Unico
5970: 64 65 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a de character.. *
5980: 09 49 66 20 74 68 65 20 74 61 72 67 65 74 20 62 .If the target b
5990: 75 66 66 65 72 20 69 6e 74 6f 20 77 68 69 63 68 uffer into which
59a0: 20 74 68 65 20 63 61 6c 6c 65 72 20 69 73 20 67 the caller is g
59b0: 6f 69 6e 67 20 74 6f 20 73 74 6f 72 65 20 74 68 oing to store th
59c0: 65 20 62 79 74 65 73 0a 20 2a 09 74 68 61 74 20 e bytes. *.that
59d0: 72 65 70 72 65 73 65 6e 74 20 74 68 65 20 55 6e represent the Un
59e0: 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 20 icode character
59f0: 69 73 20 61 74 20 6c 65 61 73 74 20 61 73 20 6c is at least as l
5a00: 61 72 67 65 20 61 73 20 74 68 65 0a 20 2a 09 73 arge as the. *.s
5a10: 6f 75 72 63 65 20 62 75 66 66 65 72 20 66 72 6f ource buffer fro
5a20: 6d 20 77 68 69 63 68 20 74 68 65 20 62 61 63 6b m which the back
5a30: 73 6c 61 73 68 65 64 20 73 65 71 75 65 6e 63 65 slashed sequence
5a40: 20 77 61 73 20 65 78 74 72 61 63 74 65 64 2c 20 was extracted,
5a50: 6e 6f 0a 20 2a 09 62 75 66 66 65 72 20 6f 76 65 no. *.buffer ove
5a60: 72 72 75 6e 73 20 73 68 6f 75 6c 64 20 6f 63 63 rruns should occ
5a70: 75 72 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d ur.. *. *-------
5a80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5a90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5aa0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5ab0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5ac0: 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 ----. */..int.Tc
5ad0: 6c 5f 55 74 66 42 61 63 6b 73 6c 61 73 68 28 0a l_UtfBackslash(.
5ae0: 20 20 20 20 63 6f 6e 73 74 20 63 68 61 72 20 2a const char *
5af0: 73 72 63 2c 09 09 2f 2a 20 50 6f 69 6e 74 73 20 src,../* Points
5b00: 74 6f 20 74 68 65 20 62 61 63 6b 73 6c 61 73 68 to the backslash
5b10: 20 63 68 61 72 61 63 74 65 72 20 6f 66 20 61 0a character of a.
5b20: 09 09 09 09 20 2a 20 62 61 63 6b 73 6c 61 73 68 .... * backslash
5b30: 20 73 65 71 75 65 6e 63 65 2e 20 2a 2f 0a 20 20 sequence. */.
5b40: 20 20 69 6e 74 20 2a 72 65 61 64 50 74 72 2c 09 int *readPtr,.
5b50: 09 2f 2a 20 46 69 6c 6c 20 69 6e 20 77 69 74 68 ./* Fill in with
5b60: 20 6e 75 6d 62 65 72 20 6f 66 20 63 68 61 72 61 number of chara
5b70: 63 74 65 72 73 20 72 65 61 64 20 66 72 6f 6d 0a cters read from.
5b80: 09 09 09 09 20 2a 20 73 72 63 2c 20 75 6e 6c 65 .... * src, unle
5b90: 73 73 20 4e 55 4c 4c 2e 20 2a 2f 0a 20 20 20 20 ss NULL. */.
5ba0: 63 68 61 72 20 2a 64 73 74 29 09 09 09 2f 2a 20 char *dst).../*
5bb0: 46 69 6c 6c 65 64 20 77 69 74 68 20 74 68 65 20 Filled with the
5bc0: 62 79 74 65 73 20 72 65 70 72 65 73 65 6e 74 65 bytes represente
5bd0: 64 20 62 79 20 74 68 65 0a 09 09 09 09 20 2a 20 d by the..... *
5be0: 62 61 63 6b 73 6c 61 73 68 20 73 65 71 75 65 6e backslash sequen
5bf0: 63 65 2e 20 2a 2f 0a 7b 0a 23 64 65 66 69 6e 65 ce. */.{.#define
5c00: 20 4c 49 4e 45 5f 4c 45 4e 47 54 48 20 31 32 38 LINE_LENGTH 128
5c10: 0a 20 20 20 20 69 6e 74 20 6e 75 6d 52 65 61 64 . int numRead
5c20: 3b 0a 20 20 20 20 69 6e 74 20 72 65 73 75 6c 74 ;. int result
5c30: 3b 0a 0a 20 20 20 20 72 65 73 75 6c 74 20 3d 20 ;.. result =
5c40: 54 63 6c 50 61 72 73 65 42 61 63 6b 73 6c 61 73 TclParseBackslas
5c50: 68 28 73 72 63 2c 20 4c 49 4e 45 5f 4c 45 4e 47 h(src, LINE_LENG
5c60: 54 48 2c 20 26 6e 75 6d 52 65 61 64 2c 20 64 73 TH, &numRead, ds
5c70: 74 29 3b 0a 20 20 20 20 69 66 20 28 6e 75 6d 52 t);. if (numR
5c80: 65 61 64 20 3d 3d 20 4c 49 4e 45 5f 4c 45 4e 47 ead == LINE_LENG
5c90: 54 48 29 20 7b 0a 09 2f 2a 0a 09 20 2a 20 57 65 TH) {../*.. * We
5ca0: 20 61 74 65 20 61 20 77 68 6f 6c 65 20 6c 69 6e ate a whole lin
5cb0: 65 2e 20 50 61 79 20 74 68 65 20 70 72 69 63 65 e. Pay the price
5cc0: 20 6f 66 20 61 20 73 74 72 6c 65 6e 28 29 0a 09 of a strlen()..
5cd0: 20 2a 2f 0a 0a 09 72 65 73 75 6c 74 20 3d 20 54 */...result = T
5ce0: 63 6c 50 61 72 73 65 42 61 63 6b 73 6c 61 73 68 clParseBackslash
5cf0: 28 73 72 63 2c 20 28 69 6e 74 29 73 74 72 6c 65 (src, (int)strle
5d00: 6e 28 73 72 63 29 2c 20 26 6e 75 6d 52 65 61 64 n(src), &numRead
5d10: 2c 20 64 73 74 29 3b 0a 20 20 20 20 7d 0a 20 20 , dst);. }.
5d20: 20 20 69 66 20 28 72 65 61 64 50 74 72 20 21 3d if (readPtr !=
5d30: 20 4e 55 4c 4c 29 20 7b 0a 09 2a 72 65 61 64 50 NULL) {..*readP
5d40: 74 72 20 3d 20 6e 75 6d 52 65 61 64 3b 0a 20 20 tr = numRead;.
5d50: 20 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 72 }. return r
5d60: 65 73 75 6c 74 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a esult;.}.../*. *
5d70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5d80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5d90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5da0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5db0: 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c ------. *. * Tcl
5dc0: 5f 55 74 66 54 6f 55 70 70 65 72 20 2d 2d 0a 20 _UtfToUpper --.
5dd0: 2a 0a 20 2a 09 43 6f 6e 76 65 72 74 20 6c 6f 77 *. *.Convert low
5de0: 65 72 63 61 73 65 20 63 68 61 72 61 63 74 65 72 ercase character
5df0: 73 20 74 6f 20 75 70 70 65 72 63 61 73 65 20 63 s to uppercase c
5e00: 68 61 72 61 63 74 65 72 73 20 69 6e 20 61 20 55 haracters in a U
5e10: 54 46 20 73 74 72 69 6e 67 0a 20 2a 09 69 6e 20 TF string. *.in
5e20: 70 6c 61 63 65 2e 20 54 68 65 20 63 6f 6e 76 65 place. The conve
5e30: 72 73 69 6f 6e 20 6d 61 79 20 73 68 72 69 6e 6b rsion may shrink
5e40: 20 74 68 65 20 55 54 46 20 73 74 72 69 6e 67 2e the UTF string.
5e50: 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a . *. * Results:.
5e60: 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 6e *.Returns the n
5e70: 75 6d 62 65 72 20 6f 66 20 62 79 74 65 73 20 69 umber of bytes i
5e80: 6e 20 74 68 65 20 72 65 73 75 6c 74 69 6e 67 20 n the resulting
5e90: 73 74 72 69 6e 67 20 65 78 63 6c 75 64 69 6e 67 string excluding
5ea0: 20 74 68 65 0a 20 2a 09 74 72 61 69 6c 69 6e 67 the. *.trailing
5eb0: 20 6e 75 6c 6c 2e 0a 20 2a 0a 20 2a 20 53 69 64 null.. *. * Sid
5ec0: 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 57 72 e effects:. *.Wr
5ed0: 69 74 65 73 20 61 20 74 65 72 6d 69 6e 61 74 69 ites a terminati
5ee0: 6e 67 20 6e 75 6c 6c 20 61 66 74 65 72 20 74 68 ng null after th
5ef0: 65 20 6c 61 73 74 20 63 6f 6e 76 65 72 74 65 64 e last converted
5f00: 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 character.. *.
5f10: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
5f20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5f30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5f40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
5f50: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 -------. */..int
5f60: 0a 54 63 6c 5f 55 74 66 54 6f 55 70 70 65 72 28 .Tcl_UtfToUpper(
5f70: 0a 20 20 20 20 63 68 61 72 20 2a 73 74 72 29 09 . char *str).
5f80: 09 09 2f 2a 20 53 74 72 69 6e 67 20 74 6f 20 63 ../* String to c
5f90: 6f 6e 76 65 72 74 20 69 6e 20 70 6c 61 63 65 2e onvert in place.
5fa0: 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 6e */.{. Tcl_Un
5fb0: 69 43 68 61 72 20 63 68 20 3d 20 30 3b 0a 20 20 iChar ch = 0;.
5fc0: 20 20 69 6e 74 20 75 70 43 68 61 72 3b 0a 20 20 int upChar;.
5fd0: 20 20 63 68 61 72 20 2a 73 72 63 2c 20 2a 64 73 char *src, *ds
5fe0: 74 3b 0a 20 20 20 20 69 6e 74 20 62 79 74 65 73 t;. int bytes
5ff0: 3b 0a 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 2a ;.. /*. *
6000: 20 49 74 65 72 61 74 65 20 6f 76 65 72 20 74 68 Iterate over th
6010: 65 20 73 74 72 69 6e 67 20 75 6e 74 69 6c 20 77 e string until w
6020: 65 20 68 69 74 20 74 68 65 20 74 65 72 6d 69 6e e hit the termin
6030: 61 74 69 6e 67 20 6e 75 6c 6c 2e 0a 20 20 20 20 ating null..
6040: 20 2a 2f 0a 0a 20 20 20 20 73 72 63 20 3d 20 64 */.. src = d
6050: 73 74 20 3d 20 73 74 72 3b 0a 20 20 20 20 77 68 st = str;. wh
6060: 69 6c 65 20 28 2a 73 72 63 29 20 7b 0a 09 62 79 ile (*src) {..by
6070: 74 65 73 20 3d 20 54 63 6c 55 74 66 54 6f 55 6e tes = TclUtfToUn
6080: 69 43 68 61 72 28 73 72 63 2c 20 26 63 68 29 3b iChar(src, &ch);
6090: 0a 09 75 70 43 68 61 72 20 3d 20 63 68 3b 0a 23 ..upChar = ch;.#
60a0: 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 3c if TCL_UTF_MAX <
60b0: 3d 20 34 0a 09 69 66 20 28 28 62 79 74 65 73 20 = 4..if ((bytes
60c0: 3d 3d 20 31 29 20 26 26 20 28 28 63 68 20 26 20 == 1) && ((ch &
60d0: 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 0xFC00) == 0xD80
60e0: 30 29 29 20 7b 0a 09 20 20 20 20 62 79 74 65 73 0)) {.. bytes
60f0: 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 += TclUtfToUniC
6100: 68 61 72 28 73 72 63 20 2b 20 62 79 74 65 73 2c har(src + bytes,
6110: 20 26 63 68 29 3b 0a 09 20 20 20 20 2f 2a 20 43 &ch);.. /* C
6120: 6f 6d 62 69 6e 65 20 73 75 72 72 6f 67 61 74 65 ombine surrogate
6130: 73 20 2a 2f 0a 09 20 20 20 20 75 70 43 68 61 72 s */.. upChar
6140: 20 3d 20 28 28 28 75 70 43 68 61 72 20 26 20 30 = (((upChar & 0
6150: 78 33 66 66 29 20 3c 3c 20 31 30 29 20 7c 20 28 x3ff) << 10) | (
6160: 63 68 20 26 20 30 78 33 66 66 29 29 20 2b 20 30 ch & 0x3ff)) + 0
6170: 78 31 30 30 30 30 3b 0a 09 7d 0a 23 65 6e 64 69 x10000;..}.#endi
6180: 66 0a 09 75 70 43 68 61 72 20 3d 20 54 63 6c 5f f..upChar = Tcl_
6190: 55 6e 69 43 68 61 72 54 6f 55 70 70 65 72 28 75 UniCharToUpper(u
61a0: 70 43 68 61 72 29 3b 0a 0a 09 2f 2a 0a 09 20 2a pChar);.../*.. *
61b0: 20 54 6f 20 6b 65 65 70 20 62 61 64 6c 79 20 66 To keep badly f
61c0: 6f 72 6d 65 64 20 55 74 66 20 73 74 72 69 6e 67 ormed Utf string
61d0: 73 20 66 72 6f 6d 20 67 65 74 74 69 6e 67 20 69 s from getting i
61e0: 6e 66 6c 61 74 65 64 20 62 79 20 74 68 65 0a 09 nflated by the..
61f0: 20 2a 20 63 6f 6e 76 65 72 73 69 6f 6e 20 28 74 * conversion (t
6200: 68 65 72 65 62 79 20 63 61 75 73 69 6e 67 20 61 hereby causing a
6210: 20 73 65 67 66 61 75 6c 74 29 2c 20 6f 6e 6c 79 segfault), only
6220: 20 63 6f 70 79 20 74 68 65 20 75 70 70 65 72 20 copy the upper
6230: 63 61 73 65 0a 09 20 2a 20 63 68 61 72 20 74 6f case.. * char to
6240: 20 64 73 74 20 69 66 20 69 74 73 20 73 69 7a 65 dst if its size
6250: 20 69 73 20 3c 3d 20 74 68 65 20 6f 72 69 67 69 is <= the origi
6260: 6e 61 6c 20 63 68 61 72 2e 0a 09 20 2a 2f 0a 0a nal char... */..
6270: 09 69 66 20 28 28 62 79 74 65 73 20 3c 20 54 63 .if ((bytes < Tc
6280: 6c 55 74 66 43 6f 75 6e 74 28 75 70 43 68 61 72 lUtfCount(upChar
6290: 29 29 20 7c 7c 20 28 28 75 70 43 68 61 72 20 26 )) || ((upChar &
62a0: 20 30 78 46 38 30 30 29 20 3d 3d 20 30 78 44 38 0xF800) == 0xD8
62b0: 30 30 29 29 20 7b 0a 09 20 20 20 20 6d 65 6d 63 00)) {.. memc
62c0: 70 79 28 64 73 74 2c 20 73 72 63 2c 20 28 73 69 py(dst, src, (si
62d0: 7a 65 5f 74 29 20 62 79 74 65 73 29 3b 0a 09 20 ze_t) bytes);..
62e0: 20 20 20 64 73 74 20 2b 3d 20 62 79 74 65 73 3b dst += bytes;
62f0: 0a 09 7d 20 65 6c 73 65 20 7b 0a 09 20 20 20 20 ..} else {..
6300: 64 73 74 20 2b 3d 20 54 63 6c 5f 55 6e 69 43 68 dst += Tcl_UniCh
6310: 61 72 54 6f 55 74 66 28 75 70 43 68 61 72 2c 20 arToUtf(upChar,
6320: 64 73 74 29 3b 0a 09 7d 0a 09 73 72 63 20 2b 3d dst);..}..src +=
6330: 20 62 79 74 65 73 3b 0a 20 20 20 20 7d 0a 20 20 bytes;. }.
6340: 20 20 2a 64 73 74 20 3d 20 27 5c 30 27 3b 0a 20 *dst = '\0';.
6350: 20 20 20 72 65 74 75 72 6e 20 28 64 73 74 20 2d return (dst -
6360: 20 73 74 72 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a str);.}.../*. *
6370: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6380: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6390: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
63a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
63b0: 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c ------. *. * Tcl
63c0: 5f 55 74 66 54 6f 4c 6f 77 65 72 20 2d 2d 0a 20 _UtfToLower --.
63d0: 2a 0a 20 2a 09 43 6f 6e 76 65 72 74 20 75 70 70 *. *.Convert upp
63e0: 65 72 63 61 73 65 20 63 68 61 72 61 63 74 65 72 ercase character
63f0: 73 20 74 6f 20 6c 6f 77 65 72 63 61 73 65 20 63 s to lowercase c
6400: 68 61 72 61 63 74 65 72 73 20 69 6e 20 61 20 55 haracters in a U
6410: 54 46 20 73 74 72 69 6e 67 0a 20 2a 09 69 6e 20 TF string. *.in
6420: 70 6c 61 63 65 2e 20 54 68 65 20 63 6f 6e 76 65 place. The conve
6430: 72 73 69 6f 6e 20 6d 61 79 20 73 68 72 69 6e 6b rsion may shrink
6440: 20 74 68 65 20 55 54 46 20 73 74 72 69 6e 67 2e the UTF string.
6450: 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a . *. * Results:.
6460: 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 6e *.Returns the n
6470: 75 6d 62 65 72 20 6f 66 20 62 79 74 65 73 20 69 umber of bytes i
6480: 6e 20 74 68 65 20 72 65 73 75 6c 74 69 6e 67 20 n the resulting
6490: 73 74 72 69 6e 67 20 65 78 63 6c 75 64 69 6e 67 string excluding
64a0: 20 74 68 65 0a 20 2a 09 74 72 61 69 6c 69 6e 67 the. *.trailing
64b0: 20 6e 75 6c 6c 2e 0a 20 2a 0a 20 2a 20 53 69 64 null.. *. * Sid
64c0: 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 57 72 e effects:. *.Wr
64d0: 69 74 65 73 20 61 20 74 65 72 6d 69 6e 61 74 69 ites a terminati
64e0: 6e 67 20 6e 75 6c 6c 20 61 66 74 65 72 20 74 68 ng null after th
64f0: 65 20 6c 61 73 74 20 63 6f 6e 76 65 72 74 65 64 e last converted
6500: 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 character.. *.
6510: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
6520: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6530: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6540: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6550: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 -------. */..int
6560: 0a 54 63 6c 5f 55 74 66 54 6f 4c 6f 77 65 72 28 .Tcl_UtfToLower(
6570: 0a 20 20 20 20 63 68 61 72 20 2a 73 74 72 29 09 . char *str).
6580: 09 09 2f 2a 20 53 74 72 69 6e 67 20 74 6f 20 63 ../* String to c
6590: 6f 6e 76 65 72 74 20 69 6e 20 70 6c 61 63 65 2e onvert in place.
65a0: 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 6e */.{. Tcl_Un
65b0: 69 43 68 61 72 20 63 68 20 3d 20 30 3b 0a 20 20 iChar ch = 0;.
65c0: 20 20 69 6e 74 20 6c 6f 77 43 68 61 72 3b 0a 20 int lowChar;.
65d0: 20 20 20 63 68 61 72 20 2a 73 72 63 2c 20 2a 64 char *src, *d
65e0: 73 74 3b 0a 20 20 20 20 69 6e 74 20 62 79 74 65 st;. int byte
65f0: 73 3b 0a 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 s;.. /*.
6600: 2a 20 49 74 65 72 61 74 65 20 6f 76 65 72 20 74 * Iterate over t
6610: 68 65 20 73 74 72 69 6e 67 20 75 6e 74 69 6c 20 he string until
6620: 77 65 20 68 69 74 20 74 68 65 20 74 65 72 6d 69 we hit the termi
6630: 6e 61 74 69 6e 67 20 6e 75 6c 6c 2e 0a 20 20 20 nating null..
6640: 20 20 2a 2f 0a 0a 20 20 20 20 73 72 63 20 3d 20 */.. src =
6650: 64 73 74 20 3d 20 73 74 72 3b 0a 20 20 20 20 77 dst = str;. w
6660: 68 69 6c 65 20 28 2a 73 72 63 29 20 7b 0a 09 62 hile (*src) {..b
6670: 79 74 65 73 20 3d 20 54 63 6c 55 74 66 54 6f 55 ytes = TclUtfToU
6680: 6e 69 43 68 61 72 28 73 72 63 2c 20 26 63 68 29 niChar(src, &ch)
6690: 3b 0a 09 6c 6f 77 43 68 61 72 20 3d 20 63 68 3b ;..lowChar = ch;
66a0: 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 .#if TCL_UTF_MAX
66b0: 20 3c 3d 20 34 0a 09 69 66 20 28 28 62 79 74 65 <= 4..if ((byte
66c0: 73 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 20 s == 1) && ((ch
66d0: 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 & 0xFC00) == 0xD
66e0: 38 30 30 29 29 20 7b 0a 09 20 20 20 20 62 79 74 800)) {.. byt
66f0: 65 73 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e es += TclUtfToUn
6700: 69 43 68 61 72 28 73 72 63 20 2b 20 62 79 74 65 iChar(src + byte
6710: 73 2c 20 26 63 68 29 3b 0a 09 20 20 20 20 2f 2a s, &ch);.. /*
6720: 20 43 6f 6d 62 69 6e 65 20 73 75 72 72 6f 67 61 Combine surroga
6730: 74 65 73 20 2a 2f 0a 09 20 20 20 20 6c 6f 77 43 tes */.. lowC
6740: 68 61 72 20 3d 20 28 28 28 6c 6f 77 43 68 61 72 har = (((lowChar
6750: 20 26 20 30 78 33 66 66 29 20 3c 3c 20 31 30 29 & 0x3ff) << 10)
6760: 20 7c 20 28 63 68 20 26 20 30 78 33 66 66 29 29 | (ch & 0x3ff))
6770: 20 2b 20 30 78 31 30 30 30 30 3b 0a 09 7d 0a 23 + 0x10000;..}.#
6780: 65 6e 64 69 66 0a 09 6c 6f 77 43 68 61 72 20 3d endif..lowChar =
6790: 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f Tcl_UniCharToLo
67a0: 77 65 72 28 6c 6f 77 43 68 61 72 29 3b 0a 0a 09 wer(lowChar);...
67b0: 2f 2a 0a 09 20 2a 20 54 6f 20 6b 65 65 70 20 62 /*.. * To keep b
67c0: 61 64 6c 79 20 66 6f 72 6d 65 64 20 55 74 66 20 adly formed Utf
67d0: 73 74 72 69 6e 67 73 20 66 72 6f 6d 20 67 65 74 strings from get
67e0: 74 69 6e 67 20 69 6e 66 6c 61 74 65 64 20 62 79 ting inflated by
67f0: 20 74 68 65 0a 09 20 2a 20 63 6f 6e 76 65 72 73 the.. * convers
6800: 69 6f 6e 20 28 74 68 65 72 65 62 79 20 63 61 75 ion (thereby cau
6810: 73 69 6e 67 20 61 20 73 65 67 66 61 75 6c 74 29 sing a segfault)
6820: 2c 20 6f 6e 6c 79 20 63 6f 70 79 20 74 68 65 20 , only copy the
6830: 6c 6f 77 65 72 20 63 61 73 65 0a 09 20 2a 20 63 lower case.. * c
6840: 68 61 72 20 74 6f 20 64 73 74 20 69 66 20 69 74 har to dst if it
6850: 73 20 73 69 7a 65 20 69 73 20 3c 3d 20 74 68 65 s size is <= the
6860: 20 6f 72 69 67 69 6e 61 6c 20 63 68 61 72 2e 0a original char..
6870: 09 20 2a 2f 0a 0a 09 69 66 20 28 28 62 79 74 65 . */...if ((byte
6880: 73 20 3c 20 54 63 6c 55 74 66 43 6f 75 6e 74 28 s < TclUtfCount(
6890: 6c 6f 77 43 68 61 72 29 29 20 7c 7c 20 28 28 6c lowChar)) || ((l
68a0: 6f 77 43 68 61 72 20 26 20 30 78 46 38 30 30 29 owChar & 0xF800)
68b0: 20 3d 3d 20 30 78 44 38 30 30 29 29 20 7b 0a 09 == 0xD800)) {..
68c0: 20 20 20 20 6d 65 6d 63 70 79 28 64 73 74 2c 20 memcpy(dst,
68d0: 73 72 63 2c 20 28 73 69 7a 65 5f 74 29 20 62 79 src, (size_t) by
68e0: 74 65 73 29 3b 0a 09 20 20 20 20 64 73 74 20 2b tes);.. dst +
68f0: 3d 20 62 79 74 65 73 3b 0a 09 7d 20 65 6c 73 65 = bytes;..} else
6900: 20 7b 0a 09 20 20 20 20 64 73 74 20 2b 3d 20 54 {.. dst += T
6910: 63 6c 5f 55 6e 69 43 68 61 72 54 6f 55 74 66 28 cl_UniCharToUtf(
6920: 6c 6f 77 43 68 61 72 2c 20 64 73 74 29 3b 0a 09 lowChar, dst);..
6930: 7d 0a 09 73 72 63 20 2b 3d 20 62 79 74 65 73 3b }..src += bytes;
6940: 0a 20 20 20 20 7d 0a 20 20 20 20 2a 64 73 74 20 . }. *dst
6950: 3d 20 27 5c 30 27 3b 0a 20 20 20 20 72 65 74 75 = '\0';. retu
6960: 72 6e 20 28 64 73 74 20 2d 20 73 74 72 29 3b 0a rn (dst - str);.
6970: 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d }.../*. *-------
6980: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6990: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
69a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
69b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a ---------------.
69c0: 20 2a 0a 20 2a 20 54 63 6c 5f 55 74 66 54 6f 54 *. * Tcl_UtfToT
69d0: 69 74 6c 65 20 2d 2d 0a 20 2a 0a 20 2a 09 43 68 itle --. *. *.Ch
69e0: 61 6e 67 65 73 20 74 68 65 20 66 69 72 73 74 20 anges the first
69f0: 63 68 61 72 61 63 74 65 72 20 6f 66 20 61 20 55 character of a U
6a00: 54 46 20 73 74 72 69 6e 67 20 74 6f 20 74 69 74 TF string to tit
6a10: 6c 65 20 63 61 73 65 20 6f 72 20 75 70 70 65 72 le case or upper
6a20: 63 61 73 65 0a 20 2a 09 61 6e 64 20 74 68 65 20 case. *.and the
6a30: 72 65 73 74 20 6f 66 20 74 68 65 20 73 74 72 69 rest of the stri
6a40: 6e 67 20 74 6f 20 6c 6f 77 65 72 63 61 73 65 2e ng to lowercase.
6a50: 20 54 68 65 20 63 6f 6e 76 65 72 73 69 6f 6e 20 The conversion
6a60: 68 61 70 70 65 6e 73 20 69 6e 0a 20 2a 09 70 6c happens in. *.pl
6a70: 61 63 65 20 61 6e 64 20 6d 61 79 20 73 68 72 69 ace and may shri
6a80: 6e 6b 20 74 68 65 20 55 54 46 20 73 74 72 69 6e nk the UTF strin
6a90: 67 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 g.. *. * Results
6aa0: 3a 0a 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 :. *.Returns the
6ab0: 20 6e 75 6d 62 65 72 20 6f 66 20 62 79 74 65 73 number of bytes
6ac0: 20 69 6e 20 74 68 65 20 72 65 73 75 6c 74 69 6e in the resultin
6ad0: 67 20 73 74 72 69 6e 67 20 65 78 63 6c 75 64 69 g string excludi
6ae0: 6e 67 20 74 68 65 0a 20 2a 09 74 72 61 69 6c 69 ng the. *.traili
6af0: 6e 67 20 6e 75 6c 6c 2e 0a 20 2a 0a 20 2a 20 53 ng null.. *. * S
6b00: 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 ide effects:. *.
6b10: 57 72 69 74 65 73 20 61 20 74 65 72 6d 69 6e 61 Writes a termina
6b20: 74 69 6e 67 20 6e 75 6c 6c 20 61 66 74 65 72 20 ting null after
6b30: 74 68 65 20 6c 61 73 74 20 63 6f 6e 76 65 72 74 the last convert
6b40: 65 64 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a ed character.. *
6b50: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
6b60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6b70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6b80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
6b90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 ---------. */..i
6ba0: 6e 74 0a 54 63 6c 5f 55 74 66 54 6f 54 69 74 6c nt.Tcl_UtfToTitl
6bb0: 65 28 0a 20 20 20 20 63 68 61 72 20 2a 73 74 72 e(. char *str
6bc0: 29 09 09 09 2f 2a 20 53 74 72 69 6e 67 20 74 6f ).../* String to
6bd0: 20 63 6f 6e 76 65 72 74 20 69 6e 20 70 6c 61 63 convert in plac
6be0: 65 2e 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f e. */.{. Tcl_
6bf0: 55 6e 69 43 68 61 72 20 63 68 20 3d 20 30 3b 0a UniChar ch = 0;.
6c00: 20 20 20 20 69 6e 74 20 74 69 74 6c 65 43 68 61 int titleCha
6c10: 72 2c 20 6c 6f 77 43 68 61 72 3b 0a 20 20 20 20 r, lowChar;.
6c20: 63 68 61 72 20 2a 73 72 63 2c 20 2a 64 73 74 3b char *src, *dst;
6c30: 0a 20 20 20 20 69 6e 74 20 62 79 74 65 73 3b 0a . int bytes;.
6c40: 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 2a 20 43 . /*. * C
6c50: 61 70 69 74 61 6c 69 7a 65 20 74 68 65 20 66 69 apitalize the fi
6c60: 72 73 74 20 63 68 61 72 61 63 74 65 72 20 61 6e rst character an
6c70: 64 20 74 68 65 6e 20 6c 6f 77 65 72 63 61 73 65 d then lowercase
6c80: 20 74 68 65 20 72 65 73 74 20 6f 66 20 74 68 65 the rest of the
6c90: 0a 20 20 20 20 20 2a 20 63 68 61 72 61 63 74 65 . * characte
6ca0: 72 73 20 75 6e 74 69 6c 20 77 65 20 67 65 74 20 rs until we get
6cb0: 74 6f 20 61 20 6e 75 6c 6c 2e 0a 20 20 20 20 20 to a null..
6cc0: 2a 2f 0a 0a 20 20 20 20 73 72 63 20 3d 20 64 73 */.. src = ds
6cd0: 74 20 3d 20 73 74 72 3b 0a 0a 20 20 20 20 69 66 t = str;.. if
6ce0: 20 28 2a 73 72 63 29 20 7b 0a 09 62 79 74 65 73 (*src) {..bytes
6cf0: 20 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 68 = TclUtfToUniCh
6d00: 61 72 28 73 72 63 2c 20 26 63 68 29 3b 0a 09 74 ar(src, &ch);..t
6d10: 69 74 6c 65 43 68 61 72 20 3d 20 63 68 3b 0a 23 itleChar = ch;.#
6d20: 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 3c if TCL_UTF_MAX <
6d30: 3d 20 34 0a 09 69 66 20 28 28 62 79 74 65 73 20 = 4..if ((bytes
6d40: 3d 3d 20 31 29 20 26 26 20 28 28 63 68 20 26 20 == 1) && ((ch &
6d50: 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 0xFC00) == 0xD80
6d60: 30 29 29 20 7b 0a 09 20 20 20 20 62 79 74 65 73 0)) {.. bytes
6d70: 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 += TclUtfToUniC
6d80: 68 61 72 28 73 72 63 20 2b 20 62 79 74 65 73 2c har(src + bytes,
6d90: 20 26 63 68 29 3b 0a 09 20 20 20 20 2f 2a 20 43 &ch);.. /* C
6da0: 6f 6d 62 69 6e 65 20 73 75 72 72 6f 67 61 74 65 ombine surrogate
6db0: 73 20 2a 2f 0a 09 20 20 20 20 74 69 74 6c 65 43 s */.. titleC
6dc0: 68 61 72 20 3d 20 28 28 28 74 69 74 6c 65 43 68 har = (((titleCh
6dd0: 61 72 20 26 20 30 78 33 66 66 29 20 3c 3c 20 31 ar & 0x3ff) << 1
6de0: 30 29 20 7c 20 28 63 68 20 26 20 30 78 33 66 66 0) | (ch & 0x3ff
6df0: 29 29 20 2b 20 30 78 31 30 30 30 30 3b 0a 09 7d )) + 0x10000;..}
6e00: 0a 23 65 6e 64 69 66 0a 09 74 69 74 6c 65 43 68 .#endif..titleCh
6e10: 61 72 20 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 ar = Tcl_UniChar
6e20: 54 6f 54 69 74 6c 65 28 74 69 74 6c 65 43 68 61 ToTitle(titleCha
6e30: 72 29 3b 0a 0a 09 69 66 20 28 28 62 79 74 65 73 r);...if ((bytes
6e40: 20 3c 20 54 63 6c 55 74 66 43 6f 75 6e 74 28 74 < TclUtfCount(t
6e50: 69 74 6c 65 43 68 61 72 29 29 20 7c 7c 20 28 28 itleChar)) || ((
6e60: 74 69 74 6c 65 43 68 61 72 20 26 20 30 78 46 38 titleChar & 0xF8
6e70: 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 29 20 00) == 0xD800))
6e80: 7b 0a 09 20 20 20 20 6d 65 6d 63 70 79 28 64 73 {.. memcpy(ds
6e90: 74 2c 20 73 72 63 2c 20 28 73 69 7a 65 5f 74 29 t, src, (size_t)
6ea0: 20 62 79 74 65 73 29 3b 0a 09 20 20 20 20 64 73 bytes);.. ds
6eb0: 74 20 2b 3d 20 62 79 74 65 73 3b 0a 09 7d 20 65 t += bytes;..} e
6ec0: 6c 73 65 20 7b 0a 09 20 20 20 20 64 73 74 20 2b lse {.. dst +
6ed0: 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 55 = Tcl_UniCharToU
6ee0: 74 66 28 74 69 74 6c 65 43 68 61 72 2c 20 64 73 tf(titleChar, ds
6ef0: 74 29 3b 0a 09 7d 0a 09 73 72 63 20 2b 3d 20 62 t);..}..src += b
6f00: 79 74 65 73 3b 0a 20 20 20 20 7d 0a 20 20 20 20 ytes;. }.
6f10: 77 68 69 6c 65 20 28 2a 73 72 63 29 20 7b 0a 09 while (*src) {..
6f20: 62 79 74 65 73 20 3d 20 54 63 6c 55 74 66 54 6f bytes = TclUtfTo
6f30: 55 6e 69 43 68 61 72 28 73 72 63 2c 20 26 63 68 UniChar(src, &ch
6f40: 29 3b 0a 09 6c 6f 77 43 68 61 72 20 3d 20 63 68 );..lowChar = ch
6f50: 3b 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 ;.#if TCL_UTF_MA
6f60: 58 20 3c 3d 20 34 0a 09 69 66 20 28 28 62 79 74 X <= 4..if ((byt
6f70: 65 73 20 3d 3d 20 31 29 20 26 26 20 28 28 63 68 es == 1) && ((ch
6f80: 20 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 & 0xFC00) == 0x
6f90: 44 38 30 30 29 29 20 7b 0a 09 20 20 20 20 62 79 D800)) {.. by
6fa0: 74 65 73 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 tes += TclUtfToU
6fb0: 6e 69 43 68 61 72 28 73 72 63 20 2b 20 62 79 74 niChar(src + byt
6fc0: 65 73 2c 20 26 63 68 29 3b 0a 09 20 20 20 20 2f es, &ch);.. /
6fd0: 2a 20 43 6f 6d 62 69 6e 65 20 73 75 72 72 6f 67 * Combine surrog
6fe0: 61 74 65 73 20 2a 2f 0a 09 20 20 20 20 6c 6f 77 ates */.. low
6ff0: 43 68 61 72 20 3d 20 28 28 28 6c 6f 77 43 68 61 Char = (((lowCha
7000: 72 20 26 20 30 78 33 66 66 29 20 3c 3c 20 31 30 r & 0x3ff) << 10
7010: 29 20 7c 20 28 63 68 20 26 20 30 78 33 66 66 29 ) | (ch & 0x3ff)
7020: 29 20 2b 20 30 78 31 30 30 30 30 3b 0a 09 7d 0a ) + 0x10000;..}.
7030: 23 65 6e 64 69 66 0a 09 2f 2a 20 53 70 65 63 69 #endif../* Speci
7040: 61 6c 20 65 78 63 65 70 74 69 6f 6e 20 66 6f 72 al exception for
7050: 20 47 65 6f 72 67 69 61 6e 20 41 73 6f 6d 74 61 Georgian Asomta
7060: 76 72 75 6c 69 20 63 68 61 72 73 2c 20 6e 6f 20 vruli chars, no
7070: 74 69 74 6c 65 63 61 73 65 2e 20 2a 2f 0a 09 69 titlecase. */..i
7080: 66 20 28 28 75 6e 73 69 67 6e 65 64 29 28 6c 6f f ((unsigned)(lo
7090: 77 43 68 61 72 20 2d 20 30 78 31 43 39 30 29 20 wChar - 0x1C90)
70a0: 3e 3d 20 30 78 33 30 29 20 7b 0a 09 20 20 20 20 >= 0x30) {..
70b0: 6c 6f 77 43 68 61 72 20 3d 20 54 63 6c 5f 55 6e lowChar = Tcl_Un
70c0: 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 6c 6f 77 iCharToLower(low
70d0: 43 68 61 72 29 3b 0a 09 7d 0a 0a 09 69 66 20 28 Char);..}...if (
70e0: 28 62 79 74 65 73 20 3c 20 54 63 6c 55 74 66 43 (bytes < TclUtfC
70f0: 6f 75 6e 74 28 6c 6f 77 43 68 61 72 29 29 20 7c ount(lowChar)) |
7100: 7c 20 28 28 6c 6f 77 43 68 61 72 20 26 20 30 78 | ((lowChar & 0x
7110: 46 38 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 F800) == 0xD800)
7120: 29 20 7b 0a 09 20 20 20 20 6d 65 6d 63 70 79 28 ) {.. memcpy(
7130: 64 73 74 2c 20 73 72 63 2c 20 28 73 69 7a 65 5f dst, src, (size_
7140: 74 29 20 62 79 74 65 73 29 3b 0a 09 20 20 20 20 t) bytes);..
7150: 64 73 74 20 2b 3d 20 62 79 74 65 73 3b 0a 09 7d dst += bytes;..}
7160: 20 65 6c 73 65 20 7b 0a 09 20 20 20 20 64 73 74 else {.. dst
7170: 20 2b 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 += Tcl_UniCharT
7180: 6f 55 74 66 28 6c 6f 77 43 68 61 72 2c 20 64 73 oUtf(lowChar, ds
7190: 74 29 3b 0a 09 7d 0a 09 73 72 63 20 2b 3d 20 62 t);..}..src += b
71a0: 79 74 65 73 3b 0a 20 20 20 20 7d 0a 20 20 20 20 ytes;. }.
71b0: 2a 64 73 74 20 3d 20 27 5c 30 27 3b 0a 20 20 20 *dst = '\0';.
71c0: 20 72 65 74 75 72 6e 20 28 64 73 74 20 2d 20 73 return (dst - s
71d0: 74 72 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d tr);.}.../*. *--
71e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
71f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7200: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7210: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7220: 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 70 55 ----. *. * TclpU
7230: 74 66 4e 63 6d 70 32 20 2d 2d 0a 20 2a 0a 20 2a tfNcmp2 --. *. *
7240: 09 43 6f 6d 70 61 72 65 20 61 74 20 6d 6f 73 74 .Compare at most
7250: 20 6e 75 6d 42 79 74 65 73 20 62 79 74 65 73 20 numBytes bytes
7260: 6f 66 20 75 74 66 2d 38 20 73 74 72 69 6e 67 73 of utf-8 strings
7270: 20 63 73 20 61 6e 64 20 63 74 2e 20 42 6f 74 68 cs and ct. Both
7280: 20 63 73 20 61 6e 64 0a 20 2a 09 63 74 20 61 72 cs and. *.ct ar
7290: 65 20 61 73 73 75 6d 65 64 20 74 6f 20 62 65 20 e assumed to be
72a0: 61 74 20 6c 65 61 73 74 20 6e 75 6d 42 79 74 65 at least numByte
72b0: 73 20 62 79 74 65 73 20 6c 6f 6e 67 2e 0a 20 2a s bytes long.. *
72c0: 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 . * Results:. *.
72d0: 52 65 74 75 72 6e 20 3c 30 20 69 66 20 63 73 20 Return <0 if cs
72e0: 3c 20 63 74 2c 20 30 20 69 66 20 63 73 20 3d 3d < ct, 0 if cs ==
72f0: 20 63 74 2c 20 6f 72 20 3e 30 20 69 66 20 63 73 ct, or >0 if cs
7300: 20 3e 20 63 74 2e 0a 20 2a 0a 20 2a 20 53 69 64 > ct.. *. * Sid
7310: 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f e effects:. *.No
7320: 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d ne.. *. *-------
7330: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7340: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7350: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7360: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a ---------------.
7370: 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 70 55 74 66 */..int.TclpUtf
7380: 4e 63 6d 70 32 28 0a 20 20 20 20 63 6f 6e 73 74 Ncmp2(. const
7390: 20 63 68 61 72 20 2a 63 73 2c 09 09 2f 2a 20 55 char *cs,../* U
73a0: 54 46 20 73 74 72 69 6e 67 20 74 6f 20 63 6f 6d TF string to com
73b0: 70 61 72 65 20 74 6f 20 63 74 2e 20 2a 2f 0a 20 pare to ct. */.
73c0: 20 20 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 63 const char *c
73d0: 74 2c 09 09 2f 2a 20 55 54 46 20 73 74 72 69 6e t,../* UTF strin
73e0: 67 20 63 73 20 69 73 20 63 6f 6d 70 61 72 65 64 g cs is compared
73f0: 20 74 6f 2e 20 2a 2f 0a 20 20 20 20 75 6e 73 69 to. */. unsi
7400: 67 6e 65 64 20 6c 6f 6e 67 20 6e 75 6d 42 79 74 gned long numByt
7410: 65 73 29 09 2f 2a 20 4e 75 6d 62 65 72 20 6f 66 es)./* Number of
7420: 20 2a 62 79 74 65 73 2a 20 74 6f 20 63 6f 6d 70 *bytes* to comp
7430: 61 72 65 2e 20 2a 2f 0a 7b 0a 20 20 20 20 2f 2a are. */.{. /*
7440: 0a 20 20 20 20 20 2a 20 57 65 20 63 61 6e 27 74 . * We can't
7450: 20 73 69 6d 70 6c 79 20 63 61 6c 6c 20 27 6d 65 simply call 'me
7460: 6d 63 6d 70 28 63 73 2c 20 63 74 2c 20 6e 75 6d mcmp(cs, ct, num
7470: 42 79 74 65 73 29 3b 27 20 62 65 63 61 75 73 65 Bytes);' because
7480: 20 77 65 20 6e 65 65 64 20 74 6f 0a 20 20 20 20 we need to.
7490: 20 2a 20 63 68 65 63 6b 20 66 6f 72 20 54 63 6c * check for Tcl
74a0: 27 73 20 5c 78 43 30 5c 78 38 30 20 6e 6f 6e 2d 's \xC0\x80 non-
74b0: 75 74 66 2d 38 20 6e 75 6c 6c 20 65 6e 63 6f 64 utf-8 null encod
74c0: 69 6e 67 2e 20 4f 74 68 65 72 77 69 73 65 20 75 ing. Otherwise u
74d0: 74 66 2d 38 20 6c 65 78 65 73 0a 20 20 20 20 20 tf-8 lexes.
74e0: 2a 20 66 69 6e 65 20 69 6e 20 74 68 65 20 73 74 * fine in the st
74f0: 72 63 6d 70 20 6d 61 6e 6e 65 72 2e 0a 20 20 20 rcmp manner..
7500: 20 20 2a 2f 0a 0a 20 20 20 20 72 65 67 69 73 74 */.. regist
7510: 65 72 20 69 6e 74 20 72 65 73 75 6c 74 20 3d 20 er int result =
7520: 30 3b 0a 0a 20 20 20 20 66 6f 72 20 28 20 3b 20 0;.. for ( ;
7530: 6e 75 6d 42 79 74 65 73 20 21 3d 20 30 3b 20 6e numBytes != 0; n
7540: 75 6d 42 79 74 65 73 2d 2d 2c 20 63 73 2b 2b 2c umBytes--, cs++,
7550: 20 63 74 2b 2b 29 20 7b 0a 09 69 66 20 28 2a 63 ct++) {..if (*c
7560: 73 20 21 3d 20 2a 63 74 29 20 7b 0a 09 20 20 20 s != *ct) {..
7570: 20 72 65 73 75 6c 74 20 3d 20 55 43 48 41 52 28 result = UCHAR(
7580: 2a 63 73 29 20 2d 20 55 43 48 41 52 28 2a 63 74 *cs) - UCHAR(*ct
7590: 29 3b 0a 09 20 20 20 20 62 72 65 61 6b 3b 0a 09 );.. break;..
75a0: 7d 0a 20 20 20 20 7d 0a 20 20 20 20 69 66 20 28 }. }. if (
75b0: 6e 75 6d 42 79 74 65 73 20 26 26 20 28 28 55 43 numBytes && ((UC
75c0: 48 41 52 28 2a 63 73 29 20 3d 3d 20 30 78 43 30 HAR(*cs) == 0xC0
75d0: 29 20 7c 7c 20 28 55 43 48 41 52 28 2a 63 74 29 ) || (UCHAR(*ct)
75e0: 20 3d 3d 20 30 78 43 30 29 29 29 20 7b 0a 09 75 == 0xC0))) {..u
75f0: 6e 73 69 67 6e 65 64 20 63 68 61 72 20 63 31 2c nsigned char c1,
7600: 20 63 32 3b 0a 0a 09 63 31 20 3d 20 28 28 55 43 c2;...c1 = ((UC
7610: 48 41 52 28 2a 63 73 29 20 3d 3d 20 30 78 43 30 HAR(*cs) == 0xC0
7620: 29 20 26 26 20 28 55 43 48 41 52 28 63 73 5b 31 ) && (UCHAR(cs[1
7630: 5d 29 20 3d 3d 20 30 78 38 30 29 29 20 3f 20 30 ]) == 0x80)) ? 0
7640: 20 3a 20 55 43 48 41 52 28 2a 63 73 29 3b 0a 09 : UCHAR(*cs);..
7650: 63 32 20 3d 20 28 28 55 43 48 41 52 28 2a 63 74 c2 = ((UCHAR(*ct
7660: 29 20 3d 3d 20 30 78 43 30 29 20 26 26 20 28 55 ) == 0xC0) && (U
7670: 43 48 41 52 28 63 74 5b 31 5d 29 20 3d 3d 20 30 CHAR(ct[1]) == 0
7680: 78 38 30 29 29 20 3f 20 30 20 3a 20 55 43 48 41 x80)) ? 0 : UCHA
7690: 52 28 2a 63 74 29 3b 0a 09 72 65 73 75 6c 74 20 R(*ct);..result
76a0: 3d 20 28 63 31 20 2d 20 63 32 29 3b 0a 20 20 20 = (c1 - c2);.
76b0: 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 72 65 }. return re
76c0: 73 75 6c 74 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d sult;.}.../*. *-
76d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
76e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
76f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7700: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7710: 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f -----. *. * Tcl_
7720: 55 74 66 4e 63 6d 70 20 2d 2d 0a 20 2a 0a 20 2a UtfNcmp --. *. *
7730: 09 43 6f 6d 70 61 72 65 20 61 74 20 6d 6f 73 74 .Compare at most
7740: 20 6e 75 6d 43 68 61 72 73 20 55 54 46 20 63 68 numChars UTF ch
7750: 61 72 73 20 6f 66 20 73 74 72 69 6e 67 20 63 73 ars of string cs
7760: 20 74 6f 20 73 74 72 69 6e 67 20 63 74 2e 20 42 to string ct. B
7770: 6f 74 68 20 63 73 0a 20 2a 09 61 6e 64 20 63 74 oth cs. *.and ct
7780: 20 61 72 65 20 61 73 73 75 6d 65 64 20 74 6f 20 are assumed to
7790: 62 65 20 61 74 20 6c 65 61 73 74 20 6e 75 6d 43 be at least numC
77a0: 68 61 72 73 20 55 54 46 20 63 68 61 72 73 20 6c hars UTF chars l
77b0: 6f 6e 67 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c ong.. *. * Resul
77c0: 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e 20 3c 30 ts:. *.Return <0
77d0: 20 69 66 20 63 73 20 3c 20 63 74 2c 20 30 20 69 if cs < ct, 0 i
77e0: 66 20 63 73 20 3d 3d 20 63 74 2c 20 6f 72 20 3e f cs == ct, or >
77f0: 30 20 69 66 20 63 73 20 3e 20 63 74 2e 0a 20 2a 0 if cs > ct.. *
7800: 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 . * Side effects
7810: 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a :. *.None.. *. *
7820: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7830: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7840: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7850: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7860: 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a ------. */..int.
7870: 54 63 6c 5f 55 74 66 4e 63 6d 70 28 0a 20 20 20 Tcl_UtfNcmp(.
7880: 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 63 73 2c const char *cs,
7890: 09 09 2f 2a 20 55 54 46 20 73 74 72 69 6e 67 20 ../* UTF string
78a0: 74 6f 20 63 6f 6d 70 61 72 65 20 74 6f 20 63 74 to compare to ct
78b0: 2e 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 63 . */. const c
78c0: 68 61 72 20 2a 63 74 2c 09 09 2f 2a 20 55 54 46 har *ct,../* UTF
78d0: 20 73 74 72 69 6e 67 20 63 73 20 69 73 20 63 6f string cs is co
78e0: 6d 70 61 72 65 64 20 74 6f 2e 20 2a 2f 0a 20 20 mpared to. */.
78f0: 20 20 75 6e 73 69 67 6e 65 64 20 6c 6f 6e 67 20 unsigned long
7900: 6e 75 6d 43 68 61 72 73 29 09 2f 2a 20 4e 75 6d numChars)./* Num
7910: 62 65 72 20 6f 66 20 55 54 46 20 63 68 61 72 73 ber of UTF chars
7920: 20 74 6f 20 63 6f 6d 70 61 72 65 2e 20 2a 2f 0a to compare. */.
7930: 7b 0a 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 61 {. Tcl_UniCha
7940: 72 20 63 68 31 20 3d 20 30 2c 20 63 68 32 20 3d r ch1 = 0, ch2 =
7950: 20 30 3b 0a 0a 20 20 20 20 2f 2a 0a 20 20 20 20 0;.. /*.
7960: 20 2a 20 43 61 6e 6e 6f 74 20 75 73 65 20 27 6d * Cannot use 'm
7970: 65 6d 63 6d 70 28 63 73 2c 20 63 74 2c 20 6e 29 emcmp(cs, ct, n)
7980: 3b 27 20 61 73 20 62 79 74 65 20 72 65 70 72 65 ;' as byte repre
7990: 73 65 6e 74 61 74 69 6f 6e 20 6f 66 20 5c 75 30 sentation of \u0
79a0: 30 30 30 20 28 74 68 65 0a 20 20 20 20 20 2a 20 000 (the. *
79b0: 70 61 69 72 20 6f 66 20 62 79 74 65 73 20 30 78 pair of bytes 0x
79c0: 43 30 2c 30 78 38 30 29 20 69 73 20 6c 61 72 67 C0,0x80) is larg
79d0: 65 72 20 74 68 61 6e 20 62 79 74 65 20 72 65 70 er than byte rep
79e0: 72 65 73 65 6e 74 61 74 69 6f 6e 20 6f 66 20 5c resentation of \
79f0: 75 30 30 30 31 0a 20 20 20 20 20 2a 20 28 74 68 u0001. * (th
7a00: 65 20 62 79 74 65 20 30 78 30 31 2e 29 0a 20 20 e byte 0x01.).
7a10: 20 20 20 2a 2f 0a 0a 20 20 20 20 77 68 69 6c 65 */.. while
7a20: 20 28 6e 75 6d 43 68 61 72 73 2d 2d 20 3e 20 30 (numChars-- > 0
7a30: 29 20 7b 0a 09 2f 2a 0a 09 20 2a 20 6e 20 6d 75 ) {../*.. * n mu
7a40: 73 74 20 62 65 20 69 6e 74 65 72 70 72 65 74 65 st be interprete
7a50: 64 20 61 73 20 63 68 61 72 73 2c 20 6e 6f 74 20 d as chars, not
7a60: 62 79 74 65 73 2e 20 54 68 69 73 20 73 68 6f 75 bytes. This shou
7a70: 6c 64 20 62 65 20 63 61 6c 6c 65 64 0a 09 20 2a ld be called.. *
7a80: 20 6f 6e 6c 79 20 77 68 65 6e 20 62 6f 74 68 20 only when both
7a90: 73 74 72 69 6e 67 73 20 61 72 65 20 6f 66 20 61 strings are of a
7aa0: 74 20 6c 65 61 73 74 20 6e 20 63 68 61 72 73 20 t least n chars
7ab0: 6c 6f 6e 67 20 28 6e 6f 20 6e 65 65 64 20 66 6f long (no need fo
7ac0: 72 20 5c 30 0a 09 20 2a 20 63 68 65 63 6b 29 0a r \0.. * check).
7ad0: 09 20 2a 2f 0a 0a 09 63 73 20 2b 3d 20 54 63 6c . */...cs += Tcl
7ae0: 55 74 66 54 6f 55 6e 69 43 68 61 72 28 63 73 2c UtfToUniChar(cs,
7af0: 20 26 63 68 31 29 3b 0a 09 63 74 20 2b 3d 20 54 &ch1);..ct += T
7b00: 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 72 28 63 clUtfToUniChar(c
7b10: 74 2c 20 26 63 68 32 29 3b 0a 09 69 66 20 28 63 t, &ch2);..if (c
7b20: 68 31 20 21 3d 20 63 68 32 29 20 7b 0a 23 69 66 h1 != ch2) {.#if
7b30: 20 54 43 4c 5f 55 54 46 5f 4d 41 58 20 3c 3d 20 TCL_UTF_MAX <=
7b40: 34 0a 09 20 20 20 20 2f 2a 20 53 75 72 72 6f 67 4.. /* Surrog
7b50: 61 74 65 73 20 61 6c 77 61 79 73 20 72 65 70 6f ates always repo
7b60: 72 74 20 68 69 67 68 65 72 20 74 68 61 6e 20 6e rt higher than n
7b70: 6f 6e 2d 73 75 72 72 6f 67 61 74 65 73 20 2a 2f on-surrogates */
7b80: 0a 09 20 20 20 20 69 66 20 28 28 28 63 68 31 20 .. if (((ch1
7b90: 26 20 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 & 0xFC00) == 0xD
7ba0: 38 30 30 29 29 20 7b 0a 09 20 20 20 20 69 66 20 800)) {.. if
7bb0: 28 28 63 68 32 20 26 20 30 78 46 43 30 30 29 20 ((ch2 & 0xFC00)
7bc0: 21 3d 20 30 78 44 38 30 30 29 20 7b 0a 09 09 72 != 0xD800) {...r
7bd0: 65 74 75 72 6e 20 63 68 31 3b 0a 09 20 20 20 20 eturn ch1;..
7be0: 7d 0a 09 20 20 20 20 7d 20 65 6c 73 65 20 69 66 }.. } else if
7bf0: 20 28 28 63 68 32 20 26 20 30 78 46 43 30 30 29 ((ch2 & 0xFC00)
7c00: 20 3d 3d 20 30 78 44 38 30 30 29 20 7b 0a 09 09 == 0xD800) {...
7c10: 72 65 74 75 72 6e 20 2d 63 68 32 3b 0a 09 20 20 return -ch2;..
7c20: 20 20 7d 0a 23 65 6e 64 69 66 0a 09 20 20 20 20 }.#endif..
7c30: 72 65 74 75 72 6e 20 28 63 68 31 20 2d 20 63 68 return (ch1 - ch
7c40: 32 29 3b 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 20 2);..}. }.
7c50: 20 72 65 74 75 72 6e 20 30 3b 0a 7d 0a 0c 0a 2f return 0;.}.../
7c60: 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *------------
7c70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7c80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7c90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7ca0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a ----------. *. *
7cb0: 20 54 63 6c 5f 55 74 66 4e 63 61 73 65 63 6d 70 Tcl_UtfNcasecmp
7cc0: 20 2d 2d 0a 20 2a 0a 20 2a 09 43 6f 6d 70 61 72 --. *. *.Compar
7cd0: 65 20 61 74 20 6d 6f 73 74 20 6e 75 6d 43 68 61 e at most numCha
7ce0: 72 73 20 55 54 46 20 63 68 61 72 73 20 6f 66 20 rs UTF chars of
7cf0: 73 74 72 69 6e 67 20 63 73 20 74 6f 20 73 74 72 string cs to str
7d00: 69 6e 67 20 63 74 20 63 61 73 65 0a 20 2a 09 69 ing ct case. *.i
7d10: 6e 73 65 6e 73 69 74 69 76 65 2e 20 42 6f 74 68 nsensitive. Both
7d20: 20 63 73 20 61 6e 64 20 63 74 20 61 72 65 20 61 cs and ct are a
7d30: 73 73 75 6d 65 64 20 74 6f 20 62 65 20 61 74 20 ssumed to be at
7d40: 6c 65 61 73 74 20 6e 75 6d 43 68 61 72 73 20 55 least numChars U
7d50: 54 46 0a 20 2a 09 63 68 61 72 73 20 6c 6f 6e 67 TF. *.chars long
7d60: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
7d70: 0a 20 2a 09 52 65 74 75 72 6e 20 3c 30 20 69 66 . *.Return <0 if
7d80: 20 63 73 20 3c 20 63 74 2c 20 30 20 69 66 20 63 cs < ct, 0 if c
7d90: 73 20 3d 3d 20 63 74 2c 20 6f 72 20 3e 30 20 69 s == ct, or >0 i
7da0: 66 20 63 73 20 3e 20 63 74 2e 0a 20 2a 0a 20 2a f cs > ct.. *. *
7db0: 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 Side effects:.
7dc0: 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d *.None.. *. *---
7dd0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7de0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7df0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7e00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
7e10: 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c ---. */..int.Tcl
7e20: 5f 55 74 66 4e 63 61 73 65 63 6d 70 28 0a 20 20 _UtfNcasecmp(.
7e30: 20 20 63 6f 6e 73 74 20 63 68 61 72 20 2a 63 73 const char *cs
7e40: 2c 09 09 2f 2a 20 55 54 46 20 73 74 72 69 6e 67 ,../* UTF string
7e50: 20 74 6f 20 63 6f 6d 70 61 72 65 20 74 6f 20 63 to compare to c
7e60: 74 2e 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 t. */. const
7e70: 63 68 61 72 20 2a 63 74 2c 09 09 2f 2a 20 55 54 char *ct,../* UT
7e80: 46 20 73 74 72 69 6e 67 20 63 73 20 69 73 20 63 F string cs is c
7e90: 6f 6d 70 61 72 65 64 20 74 6f 2e 20 2a 2f 0a 20 ompared to. */.
7ea0: 20 20 20 75 6e 73 69 67 6e 65 64 20 6c 6f 6e 67 unsigned long
7eb0: 20 6e 75 6d 43 68 61 72 73 29 09 2f 2a 20 4e 75 numChars)./* Nu
7ec0: 6d 62 65 72 20 6f 66 20 55 54 46 20 63 68 61 72 mber of UTF char
7ed0: 73 20 74 6f 20 63 6f 6d 70 61 72 65 2e 20 2a 2f s to compare. */
7ee0: 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 .{. Tcl_UniCh
7ef0: 61 72 20 63 68 31 20 3d 20 30 2c 20 63 68 32 20 ar ch1 = 0, ch2
7f00: 3d 20 30 3b 0a 0a 20 20 20 20 77 68 69 6c 65 20 = 0;.. while
7f10: 28 6e 75 6d 43 68 61 72 73 2d 2d 20 3e 20 30 29 (numChars-- > 0)
7f20: 20 7b 0a 09 2f 2a 0a 09 20 2a 20 6e 20 6d 75 73 {../*.. * n mus
7f30: 74 20 62 65 20 69 6e 74 65 72 70 72 65 74 65 64 t be interpreted
7f40: 20 61 73 20 63 68 61 72 73 2c 20 6e 6f 74 20 62 as chars, not b
7f50: 79 74 65 73 2e 0a 09 20 2a 20 54 68 69 73 20 73 ytes... * This s
7f60: 68 6f 75 6c 64 20 62 65 20 63 61 6c 6c 65 64 20 hould be called
7f70: 6f 6e 6c 79 20 77 68 65 6e 20 62 6f 74 68 20 73 only when both s
7f80: 74 72 69 6e 67 73 20 61 72 65 20 6f 66 0a 09 20 trings are of..
7f90: 2a 20 61 74 20 6c 65 61 73 74 20 6e 20 63 68 61 * at least n cha
7fa0: 72 73 20 6c 6f 6e 67 20 28 6e 6f 20 6e 65 65 64 rs long (no need
7fb0: 20 66 6f 72 20 5c 30 20 63 68 65 63 6b 29 0a 09 for \0 check)..
7fc0: 20 2a 2f 0a 09 63 73 20 2b 3d 20 54 63 6c 55 74 */..cs += TclUt
7fd0: 66 54 6f 55 6e 69 43 68 61 72 28 63 73 2c 20 26 fToUniChar(cs, &
7fe0: 63 68 31 29 3b 0a 09 63 74 20 2b 3d 20 54 63 6c ch1);..ct += Tcl
7ff0: 55 74 66 54 6f 55 6e 69 43 68 61 72 28 63 74 2c UtfToUniChar(ct,
8000: 20 26 63 68 32 29 3b 0a 09 69 66 20 28 63 68 31 &ch2);..if (ch1
8010: 20 21 3d 20 63 68 32 29 20 7b 0a 23 69 66 20 54 != ch2) {.#if T
8020: 43 4c 5f 55 54 46 5f 4d 41 58 20 3c 3d 20 34 0a CL_UTF_MAX <= 4.
8030: 09 20 20 20 20 2f 2a 20 53 75 72 72 6f 67 61 74 . /* Surrogat
8040: 65 73 20 61 6c 77 61 79 73 20 72 65 70 6f 72 74 es always report
8050: 20 68 69 67 68 65 72 20 74 68 61 6e 20 6e 6f 6e higher than non
8060: 2d 73 75 72 72 6f 67 61 74 65 73 20 2a 2f 0a 09 -surrogates */..
8070: 20 20 20 20 69 66 20 28 28 28 63 68 31 20 26 20 if (((ch1 &
8080: 30 78 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 0xFC00) == 0xD80
8090: 30 29 29 20 7b 0a 09 20 20 20 20 69 66 20 28 28 0)) {.. if ((
80a0: 63 68 32 20 26 20 30 78 46 43 30 30 29 20 21 3d ch2 & 0xFC00) !=
80b0: 20 30 78 44 38 30 30 29 20 7b 0a 09 09 72 65 74 0xD800) {...ret
80c0: 75 72 6e 20 63 68 31 3b 0a 09 20 20 20 20 7d 0a urn ch1;.. }.
80d0: 09 20 20 20 20 7d 20 65 6c 73 65 20 69 66 20 28 . } else if (
80e0: 28 63 68 32 20 26 20 30 78 46 43 30 30 29 20 3d (ch2 & 0xFC00) =
80f0: 3d 20 30 78 44 38 30 30 29 20 7b 0a 09 09 72 65 = 0xD800) {...re
8100: 74 75 72 6e 20 2d 63 68 32 3b 0a 09 20 20 20 20 turn -ch2;..
8110: 7d 0a 23 65 6e 64 69 66 0a 09 20 20 20 20 63 68 }.#endif.. ch
8120: 31 20 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 1 = Tcl_UniCharT
8130: 6f 4c 6f 77 65 72 28 63 68 31 29 3b 0a 09 20 20 oLower(ch1);..
8140: 20 20 63 68 32 20 3d 20 54 63 6c 5f 55 6e 69 43 ch2 = Tcl_UniC
8150: 68 61 72 54 6f 4c 6f 77 65 72 28 63 68 32 29 3b harToLower(ch2);
8160: 0a 09 20 20 20 20 69 66 20 28 63 68 31 20 21 3d .. if (ch1 !=
8170: 20 63 68 32 29 20 7b 0a 09 09 72 65 74 75 72 6e ch2) {...return
8180: 20 28 63 68 31 20 2d 20 63 68 32 29 3b 0a 09 20 (ch1 - ch2);..
8190: 20 20 20 7d 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 }..}. }.
81a0: 20 20 72 65 74 75 72 6e 20 30 3b 0a 7d 0a 0a 2f return 0;.}../
81b0: 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *------------
81c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
81d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
81e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
81f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a ----------. *. *
8200: 20 54 63 6c 5f 55 74 66 43 6d 70 20 2d 2d 0a 20 Tcl_UtfCmp --.
8210: 2a 0a 20 2a 09 43 6f 6d 70 61 72 65 20 55 54 46 *. *.Compare UTF
8220: 20 63 68 61 72 73 20 6f 66 20 73 74 72 69 6e 67 chars of string
8230: 20 63 73 20 74 6f 20 73 74 72 69 6e 67 20 63 74 cs to string ct
8240: 20 63 61 73 65 20 73 65 6e 73 69 74 69 76 65 6c case sensitivel
8250: 79 2e 0a 20 2a 09 52 65 70 6c 61 63 65 6d 65 6e y.. *.Replacemen
8260: 74 20 66 6f 72 20 73 74 72 63 6d 70 20 69 6e 20 t for strcmp in
8270: 54 63 6c 20 63 6f 72 65 2c 20 69 6e 20 70 6c 61 Tcl core, in pla
8280: 63 65 73 20 77 68 65 72 65 20 55 54 46 2d 38 20 ces where UTF-8
8290: 73 68 6f 75 6c 64 0a 20 2a 09 62 65 20 68 61 6e should. *.be han
82a0: 64 6c 65 64 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 dled.. *. * Resu
82b0: 6c 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e 20 3c lts:. *.Return <
82c0: 30 20 69 66 20 63 73 20 3c 20 63 74 2c 20 30 20 0 if cs < ct, 0
82d0: 69 66 20 63 73 20 3d 3d 20 63 74 2c 20 6f 72 20 if cs == ct, or
82e0: 3e 30 20 69 66 20 63 73 20 3e 20 63 74 2e 0a 20 >0 if cs > ct..
82f0: 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 *. * Side effect
8300: 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 s:. *.None.. *.
8310: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
8320: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8330: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8340: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8350: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 -------. */..int
8360: 0a 54 63 6c 55 74 66 43 6d 70 28 0a 20 20 20 20 .TclUtfCmp(.
8370: 63 6f 6e 73 74 20 63 68 61 72 20 2a 63 73 2c 09 const char *cs,.
8380: 09 2f 2a 20 55 54 46 20 73 74 72 69 6e 67 20 74 ./* UTF string t
8390: 6f 20 63 6f 6d 70 61 72 65 20 74 6f 20 63 74 2e o compare to ct.
83a0: 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 */. const ch
83b0: 61 72 20 2a 63 74 29 09 09 2f 2a 20 55 54 46 20 ar *ct)../* UTF
83c0: 73 74 72 69 6e 67 20 63 73 20 69 73 20 63 6f 6d string cs is com
83d0: 70 61 72 65 64 20 74 6f 2e 20 2a 2f 0a 7b 0a 20 pared to. */.{.
83e0: 20 20 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 63 Tcl_UniChar c
83f0: 68 31 20 3d 20 30 2c 20 63 68 32 20 3d 20 30 3b h1 = 0, ch2 = 0;
8400: 0a 0a 20 20 20 20 77 68 69 6c 65 20 28 2a 63 73 .. while (*cs
8410: 20 26 26 20 2a 63 74 29 20 7b 0a 09 63 73 20 2b && *ct) {..cs +
8420: 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 68 61 = TclUtfToUniCha
8430: 72 28 63 73 2c 20 26 63 68 31 29 3b 0a 09 63 74 r(cs, &ch1);..ct
8440: 20 2b 3d 20 54 63 6c 55 74 66 54 6f 55 6e 69 43 += TclUtfToUniC
8450: 68 61 72 28 63 74 2c 20 26 63 68 32 29 3b 0a 09 har(ct, &ch2);..
8460: 69 66 20 28 63 68 31 20 21 3d 20 63 68 32 29 20 if (ch1 != ch2)
8470: 7b 0a 23 69 66 20 54 43 4c 5f 55 54 46 5f 4d 41 {.#if TCL_UTF_MA
8480: 58 20 3c 3d 20 34 0a 09 20 20 20 20 2f 2a 20 53 X <= 4.. /* S
8490: 75 72 72 6f 67 61 74 65 73 20 61 6c 77 61 79 73 urrogates always
84a0: 20 72 65 70 6f 72 74 20 68 69 67 68 65 72 20 74 report higher t
84b0: 68 61 6e 20 6e 6f 6e 2d 73 75 72 72 6f 67 61 74 han non-surrogat
84c0: 65 73 20 2a 2f 0a 09 20 20 20 20 69 66 20 28 28 es */.. if ((
84d0: 28 63 68 31 20 26 20 30 78 46 43 30 30 29 20 3d (ch1 & 0xFC00) =
84e0: 3d 20 30 78 44 38 30 30 29 29 20 7b 0a 09 20 20 = 0xD800)) {..
84f0: 20 20 69 66 20 28 28 63 68 32 20 26 20 30 78 46 if ((ch2 & 0xF
8500: 43 30 30 29 20 21 3d 20 30 78 44 38 30 30 29 20 C00) != 0xD800)
8510: 7b 0a 09 09 72 65 74 75 72 6e 20 63 68 31 3b 0a {...return ch1;.
8520: 09 20 20 20 20 7d 0a 09 20 20 20 20 7d 20 65 6c . }.. } el
8530: 73 65 20 69 66 20 28 28 63 68 32 20 26 20 30 78 se if ((ch2 & 0x
8540: 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 FC00) == 0xD800)
8550: 20 7b 0a 09 09 72 65 74 75 72 6e 20 2d 63 68 32 {...return -ch2
8560: 3b 0a 09 20 20 20 20 7d 0a 23 65 6e 64 69 66 0a ;.. }.#endif.
8570: 09 20 20 20 20 72 65 74 75 72 6e 20 63 68 31 20 . return ch1
8580: 2d 20 63 68 32 3b 0a 09 7d 0a 20 20 20 20 7d 0a - ch2;..}. }.
8590: 20 20 20 20 72 65 74 75 72 6e 20 55 43 48 41 52 return UCHAR
85a0: 28 2a 63 73 29 20 2d 20 55 43 48 41 52 28 2a 63 (*cs) - UCHAR(*c
85b0: 74 29 3b 0a 7d 0a 0a 0c 0a 2f 2a 0a 20 2a 2d 2d t);.}..../*. *--
85c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
85d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
85e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
85f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8600: 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 55 74 ----. *. * TclUt
8610: 66 43 61 73 65 63 6d 70 20 2d 2d 0a 20 2a 0a 20 fCasecmp --. *.
8620: 2a 09 43 6f 6d 70 61 72 65 20 55 54 46 20 63 68 *.Compare UTF ch
8630: 61 72 73 20 6f 66 20 73 74 72 69 6e 67 20 63 73 ars of string cs
8640: 20 74 6f 20 73 74 72 69 6e 67 20 63 74 20 63 61 to string ct ca
8650: 73 65 20 69 6e 73 65 6e 73 69 74 69 76 65 6c 79 se insensitively
8660: 2e 0a 20 2a 09 52 65 70 6c 61 63 65 6d 65 6e 74 .. *.Replacement
8670: 20 66 6f 72 20 73 74 72 63 61 73 65 63 6d 70 20 for strcasecmp
8680: 69 6e 20 54 63 6c 20 63 6f 72 65 2c 20 69 6e 20 in Tcl core, in
8690: 70 6c 61 63 65 73 20 77 68 65 72 65 20 55 54 46 places where UTF
86a0: 2d 38 20 73 68 6f 75 6c 64 0a 20 2a 09 62 65 20 -8 should. *.be
86b0: 68 61 6e 64 6c 65 64 2e 0a 20 2a 0a 20 2a 20 52 handled.. *. * R
86c0: 65 73 75 6c 74 73 3a 0a 20 2a 09 52 65 74 75 72 esults:. *.Retur
86d0: 6e 20 3c 30 20 69 66 20 63 73 20 3c 20 63 74 2c n <0 if cs < ct,
86e0: 20 30 20 69 66 20 63 73 20 3d 3d 20 63 74 2c 20 0 if cs == ct,
86f0: 6f 72 20 3e 30 20 69 66 20 63 73 20 3e 20 63 74 or >0 if cs > ct
8700: 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 .. *. * Side eff
8710: 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 ects:. *.None..
8720: 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *------------
8730: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8740: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8750: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8760: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a ----------. */..
8770: 69 6e 74 0a 54 63 6c 55 74 66 43 61 73 65 63 6d int.TclUtfCasecm
8780: 70 28 0a 20 20 20 20 63 6f 6e 73 74 20 63 68 61 p(. const cha
8790: 72 20 2a 63 73 2c 09 09 2f 2a 20 55 54 46 20 73 r *cs,../* UTF s
87a0: 74 72 69 6e 67 20 74 6f 20 63 6f 6d 70 61 72 65 tring to compare
87b0: 20 74 6f 20 63 74 2e 20 2a 2f 0a 20 20 20 20 63 to ct. */. c
87c0: 6f 6e 73 74 20 63 68 61 72 20 2a 63 74 29 09 09 onst char *ct)..
87d0: 2f 2a 20 55 54 46 20 73 74 72 69 6e 67 20 63 73 /* UTF string cs
87e0: 20 69 73 20 63 6f 6d 70 61 72 65 64 20 74 6f 2e is compared to.
87f0: 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 6c 5f 55 6e */.{. Tcl_Un
8800: 69 43 68 61 72 20 63 68 31 20 3d 20 30 2c 20 63 iChar ch1 = 0, c
8810: 68 32 20 3d 20 30 3b 0a 0a 20 20 20 20 77 68 69 h2 = 0;.. whi
8820: 6c 65 20 28 2a 63 73 20 26 26 20 2a 63 74 29 20 le (*cs && *ct)
8830: 7b 0a 09 63 73 20 2b 3d 20 54 63 6c 55 74 66 54 {..cs += TclUtfT
8840: 6f 55 6e 69 43 68 61 72 28 63 73 2c 20 26 63 68 oUniChar(cs, &ch
8850: 31 29 3b 0a 09 63 74 20 2b 3d 20 54 63 6c 55 74 1);..ct += TclUt
8860: 66 54 6f 55 6e 69 43 68 61 72 28 63 74 2c 20 26 fToUniChar(ct, &
8870: 63 68 32 29 3b 0a 09 69 66 20 28 63 68 31 20 21 ch2);..if (ch1 !
8880: 3d 20 63 68 32 29 20 7b 0a 23 69 66 20 54 43 4c = ch2) {.#if TCL
8890: 5f 55 54 46 5f 4d 41 58 20 3c 3d 20 34 0a 09 20 _UTF_MAX <= 4..
88a0: 20 20 20 2f 2a 20 53 75 72 72 6f 67 61 74 65 73 /* Surrogates
88b0: 20 61 6c 77 61 79 73 20 72 65 70 6f 72 74 20 68 always report h
88c0: 69 67 68 65 72 20 74 68 61 6e 20 6e 6f 6e 2d 73 igher than non-s
88d0: 75 72 72 6f 67 61 74 65 73 20 2a 2f 0a 09 20 20 urrogates */..
88e0: 20 20 69 66 20 28 28 28 63 68 31 20 26 20 30 78 if (((ch1 & 0x
88f0: 46 43 30 30 29 20 3d 3d 20 30 78 44 38 30 30 29 FC00) == 0xD800)
8900: 29 20 7b 0a 09 20 20 20 20 69 66 20 28 28 63 68 ) {.. if ((ch
8910: 32 20 26 20 30 78 46 43 30 30 29 20 21 3d 20 30 2 & 0xFC00) != 0
8920: 78 44 38 30 30 29 20 7b 0a 09 09 72 65 74 75 72 xD800) {...retur
8930: 6e 20 63 68 31 3b 0a 09 20 20 20 20 7d 0a 09 20 n ch1;.. }..
8940: 20 20 20 7d 20 65 6c 73 65 20 69 66 20 28 28 63 } else if ((c
8950: 68 32 20 26 20 30 78 46 43 30 30 29 20 3d 3d 20 h2 & 0xFC00) ==
8960: 30 78 44 38 30 30 29 20 7b 0a 09 09 72 65 74 75 0xD800) {...retu
8970: 72 6e 20 2d 63 68 32 3b 0a 09 20 20 20 20 7d 0a rn -ch2;.. }.
8980: 23 65 6e 64 69 66 0a 09 20 20 20 20 63 68 31 20 #endif.. ch1
8990: 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c = Tcl_UniCharToL
89a0: 6f 77 65 72 28 63 68 31 29 3b 0a 09 20 20 20 20 ower(ch1);..
89b0: 63 68 32 20 3d 20 54 63 6c 5f 55 6e 69 43 68 61 ch2 = Tcl_UniCha
89c0: 72 54 6f 4c 6f 77 65 72 28 63 68 32 29 3b 0a 09 rToLower(ch2);..
89d0: 20 20 20 20 69 66 20 28 63 68 31 20 21 3d 20 63 if (ch1 != c
89e0: 68 32 29 20 7b 0a 09 09 72 65 74 75 72 6e 20 63 h2) {...return c
89f0: 68 31 20 2d 20 63 68 32 3b 0a 09 20 20 20 20 7d h1 - ch2;.. }
8a00: 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 20 20 72 65 ..}. }. re
8a10: 74 75 72 6e 20 55 43 48 41 52 28 2a 63 73 29 20 turn UCHAR(*cs)
8a20: 2d 20 55 43 48 41 52 28 2a 63 74 29 3b 0a 7d 0a - UCHAR(*ct);.}.
8a30: 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d .../*. *--------
8a40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8a50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8a60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8a70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
8a80: 2a 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 *. * Tcl_UniChar
8a90: 54 6f 55 70 70 65 72 20 2d 2d 0a 20 2a 0a 20 2a ToUpper --. *. *
8aa0: 09 43 6f 6d 70 75 74 65 20 74 68 65 20 75 70 70 .Compute the upp
8ab0: 65 72 63 61 73 65 20 65 71 75 69 76 61 6c 65 6e ercase equivalen
8ac0: 74 20 6f 66 20 74 68 65 20 67 69 76 65 6e 20 55 t of the given U
8ad0: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
8ae0: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
8af0: 0a 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 . *.Returns the
8b00: 75 70 70 65 72 63 61 73 65 20 55 6e 69 63 6f 64 uppercase Unicod
8b10: 65 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a e character.. *.
8b20: 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 3a * Side effects:
8b30: 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d . *.None.. *. *-
8b40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8b50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8b60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8b70: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8b80: 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 -----. */..int.T
8b90: 63 6c 5f 55 6e 69 43 68 61 72 54 6f 55 70 70 65 cl_UniCharToUppe
8ba0: 72 28 0a 20 20 20 20 69 6e 74 20 63 68 29 09 09 r(. int ch)..
8bb0: 09 2f 2a 20 55 6e 69 63 6f 64 65 20 63 68 61 72 ./* Unicode char
8bc0: 61 63 74 65 72 20 74 6f 20 63 6f 6e 76 65 72 74 acter to convert
8bd0: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 21 . */.{. if (!
8be0: 55 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 UNICODE_OUT_OF_R
8bf0: 41 4e 47 45 28 63 68 29 29 20 7b 0a 09 69 6e 74 ANGE(ch)) {..int
8c00: 20 69 6e 66 6f 20 3d 20 47 65 74 55 6e 69 43 68 info = GetUniCh
8c10: 61 72 49 6e 66 6f 28 63 68 29 3b 0a 0a 09 69 66 arInfo(ch);...if
8c20: 20 28 47 65 74 43 61 73 65 54 79 70 65 28 69 6e (GetCaseType(in
8c30: 66 6f 29 20 26 20 30 78 30 34 29 20 7b 0a 09 20 fo) & 0x04) {..
8c40: 20 20 20 63 68 20 2d 3d 20 47 65 74 44 65 6c 74 ch -= GetDelt
8c50: 61 28 69 6e 66 6f 29 3b 0a 09 7d 0a 20 20 20 20 a(info);..}.
8c60: 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 63 68 20 }. return ch
8c70: 26 20 30 78 31 46 46 46 46 46 3b 0a 7d 0a 0c 0a & 0x1FFFFF;.}...
8c80: 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d /*. *-----------
8c90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8ca0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8cb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8cc0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 -----------. *.
8cd0: 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c * Tcl_UniCharToL
8ce0: 6f 77 65 72 20 2d 2d 0a 20 2a 0a 20 2a 09 43 6f ower --. *. *.Co
8cf0: 6d 70 75 74 65 20 74 68 65 20 6c 6f 77 65 72 63 mpute the lowerc
8d00: 61 73 65 20 65 71 75 69 76 61 6c 65 6e 74 20 6f ase equivalent o
8d10: 66 20 74 68 65 20 67 69 76 65 6e 20 55 6e 69 63 f the given Unic
8d20: 6f 64 65 20 63 68 61 72 61 63 74 65 72 2e 0a 20 ode character..
8d30: 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a *. * Results:. *
8d40: 09 52 65 74 75 72 6e 73 20 74 68 65 20 6c 6f 77 .Returns the low
8d50: 65 72 63 61 73 65 20 55 6e 69 63 6f 64 65 20 63 ercase Unicode c
8d60: 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 2a 20 haracter.. *. *
8d70: 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a Side effects:. *
8d80: 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d .None.. *. *----
8d90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8da0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8db0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8dc0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8dd0: 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f --. */..int.Tcl_
8de0: 55 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 0a UniCharToLower(.
8df0: 20 20 20 20 69 6e 74 20 63 68 29 09 09 09 2f 2a int ch).../*
8e00: 20 55 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 Unicode charact
8e10: 65 72 20 74 6f 20 63 6f 6e 76 65 72 74 2e 20 2a er to convert. *
8e20: 2f 0a 7b 0a 20 20 20 20 69 66 20 28 21 55 4e 49 /.{. if (!UNI
8e30: 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 4e 47 CODE_OUT_OF_RANG
8e40: 45 28 63 68 29 29 20 7b 0a 09 69 6e 74 20 69 6e E(ch)) {..int in
8e50: 66 6f 20 3d 20 47 65 74 55 6e 69 43 68 61 72 49 fo = GetUniCharI
8e60: 6e 66 6f 28 63 68 29 3b 0a 09 69 6e 74 20 6d 6f nfo(ch);..int mo
8e70: 64 65 20 3d 20 47 65 74 43 61 73 65 54 79 70 65 de = GetCaseType
8e80: 28 69 6e 66 6f 29 3b 0a 0a 09 69 66 20 28 28 6d (info);...if ((m
8e90: 6f 64 65 20 26 20 30 78 30 32 29 20 26 26 20 28 ode & 0x02) && (
8ea0: 6d 6f 64 65 20 21 3d 20 30 78 37 29 29 20 7b 0a mode != 0x7)) {.
8eb0: 09 20 20 20 20 63 68 20 2b 3d 20 47 65 74 44 65 . ch += GetDe
8ec0: 6c 74 61 28 69 6e 66 6f 29 3b 0a 09 7d 0a 20 20 lta(info);..}.
8ed0: 20 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 63 }. return c
8ee0: 68 20 26 20 30 78 31 46 46 46 46 46 3b 0a 7d 0a h & 0x1FFFFF;.}.
8ef0: 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d ../*. *---------
8f00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8f10: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8f20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
8f30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a -------------. *
8f40: 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 . * Tcl_UniCharT
8f50: 6f 54 69 74 6c 65 20 2d 2d 0a 20 2a 0a 20 2a 09 oTitle --. *. *.
8f60: 43 6f 6d 70 75 74 65 20 74 68 65 20 74 69 74 6c Compute the titl
8f70: 65 63 61 73 65 20 65 71 75 69 76 61 6c 65 6e 74 ecase equivalent
8f80: 20 6f 66 20 74 68 65 20 67 69 76 65 6e 20 55 6e of the given Un
8f90: 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 2e icode character.
8fa0: 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a . *. * Results:.
8fb0: 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 74 *.Returns the t
8fc0: 69 74 6c 65 63 61 73 65 20 55 6e 69 63 6f 64 65 itlecase Unicode
8fd0: 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 character.. *.
8fe0: 2a 20 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a * Side effects:.
8ff0: 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d *.None.. *. *--
9000: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9010: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9020: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9030: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9040: 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 ----. */..int.Tc
9050: 6c 5f 55 6e 69 43 68 61 72 54 6f 54 69 74 6c 65 l_UniCharToTitle
9060: 28 0a 20 20 20 20 69 6e 74 20 63 68 29 09 09 09 (. int ch)...
9070: 2f 2a 20 55 6e 69 63 6f 64 65 20 63 68 61 72 61 /* Unicode chara
9080: 63 74 65 72 20 74 6f 20 63 6f 6e 76 65 72 74 2e cter to convert.
9090: 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 21 55 */.{. if (!U
90a0: 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 NICODE_OUT_OF_RA
90b0: 4e 47 45 28 63 68 29 29 20 7b 0a 09 69 6e 74 20 NGE(ch)) {..int
90c0: 69 6e 66 6f 20 3d 20 47 65 74 55 6e 69 43 68 61 info = GetUniCha
90d0: 72 49 6e 66 6f 28 63 68 29 3b 0a 09 69 6e 74 20 rInfo(ch);..int
90e0: 6d 6f 64 65 20 3d 20 47 65 74 43 61 73 65 54 79 mode = GetCaseTy
90f0: 70 65 28 69 6e 66 6f 29 3b 0a 0a 09 69 66 20 28 pe(info);...if (
9100: 6d 6f 64 65 20 26 20 30 78 31 29 20 7b 0a 09 20 mode & 0x1) {..
9110: 20 20 20 2f 2a 0a 09 20 20 20 20 20 2a 20 53 75 /*.. * Su
9120: 62 74 72 61 63 74 20 6f 72 20 61 64 64 20 6f 6e btract or add on
9130: 65 20 64 65 70 65 6e 64 69 6e 67 20 6f 6e 20 74 e depending on t
9140: 68 65 20 6f 72 69 67 69 6e 61 6c 20 63 61 73 65 he original case
9150: 2e 0a 09 20 20 20 20 20 2a 2f 0a 0a 09 20 20 20 ... */...
9160: 20 69 66 20 28 6d 6f 64 65 20 21 3d 20 30 78 37 if (mode != 0x7
9170: 29 20 7b 0a 09 09 63 68 20 2b 3d 20 28 28 6d 6f ) {...ch += ((mo
9180: 64 65 20 26 20 30 78 34 29 20 3f 20 2d 31 20 3a de & 0x4) ? -1 :
9190: 20 31 29 3b 0a 09 20 20 20 20 7d 0a 09 7d 20 65 1);.. }..} e
91a0: 6c 73 65 20 69 66 20 28 6d 6f 64 65 20 3d 3d 20 lse if (mode ==
91b0: 30 78 34 29 20 7b 0a 09 20 20 20 20 63 68 20 2d 0x4) {.. ch -
91c0: 3d 20 47 65 74 44 65 6c 74 61 28 69 6e 66 6f 29 = GetDelta(info)
91d0: 3b 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 20 20 72 ;..}. }. r
91e0: 65 74 75 72 6e 20 63 68 20 26 20 30 78 31 46 46 eturn ch & 0x1FF
91f0: 46 46 46 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d FFF;.}.../*. *--
9200: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9210: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9220: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9230: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9240: 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 ----. *. * Tcl_U
9250: 6e 69 43 68 61 72 4c 65 6e 20 2d 2d 0a 20 2a 0a niCharLen --. *.
9260: 20 2a 09 46 69 6e 64 20 74 68 65 20 6c 65 6e 67 *.Find the leng
9270: 74 68 20 6f 66 20 61 20 55 6e 69 43 68 61 72 20 th of a UniChar
9280: 73 74 72 69 6e 67 2e 20 54 68 65 20 73 74 72 20 string. The str
9290: 69 6e 70 75 74 20 6d 75 73 74 20 62 65 20 6e 75 input must be nu
92a0: 6c 6c 0a 20 2a 09 74 65 72 6d 69 6e 61 74 65 64 ll. *.terminated
92b0: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
92c0: 0a 20 2a 09 52 65 74 75 72 6e 73 20 74 68 65 20 . *.Returns the
92d0: 6c 65 6e 67 74 68 20 6f 66 20 73 74 72 20 69 6e length of str in
92e0: 20 55 6e 69 43 68 61 72 73 20 28 6e 6f 74 20 62 UniChars (not b
92f0: 79 74 65 73 29 2e 0a 20 2a 0a 20 2a 20 53 69 64 ytes).. *. * Sid
9300: 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f e effects:. *.No
9310: 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d ne.. *. *-------
9320: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9330: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9340: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9350: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a ---------------.
9360: 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 */..int.Tcl_Uni
9370: 43 68 61 72 4c 65 6e 28 0a 20 20 20 20 63 6f 6e CharLen(. con
9380: 73 74 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 2a st Tcl_UniChar *
9390: 75 6e 69 53 74 72 29 09 2f 2a 20 55 6e 69 63 6f uniStr)./* Unico
93a0: 64 65 20 73 74 72 69 6e 67 20 74 6f 20 66 69 6e de string to fin
93b0: 64 20 6c 65 6e 67 74 68 20 6f 66 2e 20 2a 2f 0a d length of. */.
93c0: 7b 0a 20 20 20 20 69 6e 74 20 6c 65 6e 20 3d 20 {. int len =
93d0: 30 3b 0a 0a 20 20 20 20 77 68 69 6c 65 20 28 2a 0;.. while (*
93e0: 75 6e 69 53 74 72 20 21 3d 20 27 5c 30 27 29 20 uniStr != '\0')
93f0: 7b 0a 09 6c 65 6e 2b 2b 3b 0a 09 75 6e 69 53 74 {..len++;..uniSt
9400: 72 2b 2b 3b 0a 20 20 20 20 7d 0a 20 20 20 20 72 r++;. }. r
9410: 65 74 75 72 6e 20 6c 65 6e 3b 0a 7d 0a 0c 0a 2f eturn len;.}.../
9420: 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *. *------------
9430: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9440: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9450: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9460: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a ----------. *. *
9470: 20 54 63 6c 5f 55 6e 69 43 68 61 72 4e 63 6d 70 Tcl_UniCharNcmp
9480: 20 2d 2d 0a 20 2a 0a 20 2a 09 43 6f 6d 70 61 72 --. *. *.Compar
9490: 65 20 61 74 20 6d 6f 73 74 20 6e 75 6d 43 68 61 e at most numCha
94a0: 72 73 20 75 6e 69 63 68 61 72 73 20 6f 66 20 73 rs unichars of s
94b0: 74 72 69 6e 67 20 75 63 73 20 74 6f 20 73 74 72 tring ucs to str
94c0: 69 6e 67 20 75 63 74 2e 0a 20 2a 09 42 6f 74 68 ing uct.. *.Both
94d0: 20 75 63 73 20 61 6e 64 20 75 63 74 20 61 72 65 ucs and uct are
94e0: 20 61 73 73 75 6d 65 64 20 74 6f 20 62 65 20 61 assumed to be a
94f0: 74 20 6c 65 61 73 74 20 6e 75 6d 43 68 61 72 73 t least numChars
9500: 20 75 6e 69 63 68 61 72 73 20 6c 6f 6e 67 2e 0a unichars long..
9510: 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 *. * Results:.
9520: 2a 09 52 65 74 75 72 6e 20 3c 30 20 69 66 20 75 *.Return <0 if u
9530: 63 73 20 3c 20 75 63 74 2c 20 30 20 69 66 20 75 cs < uct, 0 if u
9540: 63 73 20 3d 3d 20 75 63 74 2c 20 6f 72 20 3e 30 cs == uct, or >0
9550: 20 69 66 20 75 63 73 20 3e 20 75 63 74 2e 0a 20 if ucs > uct..
9560: 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 *. * Side effect
9570: 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 s:. *.None.. *.
9580: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
9590: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
95a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
95b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
95c0: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 -------. */..int
95d0: 0a 54 63 6c 5f 55 6e 69 43 68 61 72 4e 63 6d 70 .Tcl_UniCharNcmp
95e0: 28 0a 20 20 20 20 63 6f 6e 73 74 20 54 63 6c 5f (. const Tcl_
95f0: 55 6e 69 43 68 61 72 20 2a 75 63 73 2c 09 2f 2a UniChar *ucs,./*
9600: 20 55 6e 69 63 6f 64 65 20 73 74 72 69 6e 67 20 Unicode string
9610: 74 6f 20 63 6f 6d 70 61 72 65 20 74 6f 20 75 63 to compare to uc
9620: 74 2e 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 t. */. const
9630: 54 63 6c 5f 55 6e 69 43 68 61 72 20 2a 75 63 74 Tcl_UniChar *uct
9640: 2c 09 2f 2a 20 55 6e 69 63 6f 64 65 20 73 74 72 ,./* Unicode str
9650: 69 6e 67 20 75 63 73 20 69 73 20 63 6f 6d 70 61 ing ucs is compa
9660: 72 65 64 20 74 6f 2e 20 2a 2f 0a 20 20 20 20 75 red to. */. u
9670: 6e 73 69 67 6e 65 64 20 6c 6f 6e 67 20 6e 75 6d nsigned long num
9680: 43 68 61 72 73 29 09 2f 2a 20 4e 75 6d 62 65 72 Chars)./* Number
9690: 20 6f 66 20 75 6e 69 63 68 61 72 73 20 74 6f 20 of unichars to
96a0: 63 6f 6d 70 61 72 65 2e 20 2a 2f 0a 7b 0a 23 69 compare. */.{.#i
96b0: 66 64 65 66 20 57 4f 52 44 53 5f 42 49 47 45 4e fdef WORDS_BIGEN
96c0: 44 49 41 4e 0a 20 20 20 20 2f 2a 0a 20 20 20 20 DIAN. /*.
96d0: 20 2a 20 57 65 20 61 72 65 20 64 65 66 69 6e 69 * We are defini
96e0: 74 65 6c 79 20 6f 6e 20 61 20 62 69 67 2d 65 6e tely on a big-en
96f0: 64 69 61 6e 20 6d 61 63 68 69 6e 65 3b 20 6d 65 dian machine; me
9700: 6d 63 6d 70 28 29 20 69 73 20 73 61 66 65 0a 20 mcmp() is safe.
9710: 20 20 20 20 2a 2f 0a 0a 20 20 20 20 72 65 74 75 */.. retu
9720: 72 6e 20 6d 65 6d 63 6d 70 28 75 63 73 2c 20 75 rn memcmp(ucs, u
9730: 63 74 2c 20 6e 75 6d 43 68 61 72 73 2a 73 69 7a ct, numChars*siz
9740: 65 6f 66 28 54 63 6c 5f 55 6e 69 43 68 61 72 29 eof(Tcl_UniChar)
9750: 29 3b 0a 0a 23 65 6c 73 65 20 2f 2a 20 21 57 4f );..#else /* !WO
9760: 52 44 53 5f 42 49 47 45 4e 44 49 41 4e 20 2a 2f RDS_BIGENDIAN */
9770: 0a 20 20 20 20 2f 2a 0a 20 20 20 20 20 2a 20 57 . /*. * W
9780: 65 20 63 61 6e 27 74 20 73 69 6d 70 6c 79 20 63 e can't simply c
9790: 61 6c 6c 20 6d 65 6d 63 6d 70 28 29 20 62 65 63 all memcmp() bec
97a0: 61 75 73 65 20 74 68 61 74 20 69 73 20 6e 6f 74 ause that is not
97b0: 20 6c 65 78 69 63 61 6c 6c 79 20 63 6f 72 72 65 lexically corre
97c0: 63 74 2e 0a 20 20 20 20 20 2a 2f 0a 0a 20 20 20 ct.. */..
97d0: 20 66 6f 72 20 28 20 3b 20 6e 75 6d 43 68 61 72 for ( ; numChar
97e0: 73 20 21 3d 20 30 3b 20 75 63 73 2b 2b 2c 20 75 s != 0; ucs++, u
97f0: 63 74 2b 2b 2c 20 6e 75 6d 43 68 61 72 73 2d 2d ct++, numChars--
9800: 29 20 7b 0a 09 69 66 20 28 2a 75 63 73 20 21 3d ) {..if (*ucs !=
9810: 20 2a 75 63 74 29 20 7b 0a 09 20 20 20 20 72 65 *uct) {.. re
9820: 74 75 72 6e 20 28 2a 75 63 73 20 2d 20 2a 75 63 turn (*ucs - *uc
9830: 74 29 3b 0a 09 7d 0a 20 20 20 20 7d 0a 20 20 20 t);..}. }.
9840: 20 72 65 74 75 72 6e 20 30 3b 0a 23 65 6e 64 69 return 0;.#endi
9850: 66 20 2f 2a 20 57 4f 52 44 53 5f 42 49 47 45 4e f /* WORDS_BIGEN
9860: 44 49 41 4e 20 2a 2f 0a 7d 0a 0c 0a 2f 2a 0a 20 DIAN */.}.../*.
9870: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
9880: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9890: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
98a0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
98b0: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 -------. *. * Tc
98c0: 6c 5f 55 6e 69 43 68 61 72 4e 63 61 73 65 63 6d l_UniCharNcasecm
98d0: 70 20 2d 2d 0a 20 2a 0a 20 2a 09 43 6f 6d 70 61 p --. *. *.Compa
98e0: 72 65 20 61 74 20 6d 6f 73 74 20 6e 75 6d 43 68 re at most numCh
98f0: 61 72 73 20 75 6e 69 63 68 61 72 73 20 6f 66 20 ars unichars of
9900: 73 74 72 69 6e 67 20 75 63 73 20 74 6f 20 73 74 string ucs to st
9910: 72 69 6e 67 20 75 63 74 20 63 61 73 65 0a 20 2a ring uct case. *
9920: 09 69 6e 73 65 6e 73 69 74 69 76 65 2e 20 42 6f .insensitive. Bo
9930: 74 68 20 75 63 73 20 61 6e 64 20 75 63 74 20 61 th ucs and uct a
9940: 72 65 20 61 73 73 75 6d 65 64 20 74 6f 20 62 65 re assumed to be
9950: 20 61 74 20 6c 65 61 73 74 20 6e 75 6d 43 68 61 at least numCha
9960: 72 73 0a 20 2a 09 75 6e 69 63 68 61 72 73 20 6c rs. *.unichars l
9970: 6f 6e 67 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c ong.. *. * Resul
9980: 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e 20 3c 30 ts:. *.Return <0
9990: 20 69 66 20 75 63 73 20 3c 20 75 63 74 2c 20 30 if ucs < uct, 0
99a0: 20 69 66 20 75 63 73 20 3d 3d 20 75 63 74 2c 20 if ucs == uct,
99b0: 6f 72 20 3e 30 20 69 66 20 75 63 73 20 3e 20 75 or >0 if ucs > u
99c0: 63 74 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 ct.. *. * Side e
99d0: 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e ffects:. *.None.
99e0: 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *. *----------
99f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9a00: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9a10: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9a20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f ------------. */
9a30: 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 43 68 61 ..int.Tcl_UniCha
9a40: 72 4e 63 61 73 65 63 6d 70 28 0a 20 20 20 20 63 rNcasecmp(. c
9a50: 6f 6e 73 74 20 54 63 6c 5f 55 6e 69 43 68 61 72 onst Tcl_UniChar
9a60: 20 2a 75 63 73 2c 09 2f 2a 20 55 6e 69 63 6f 64 *ucs,./* Unicod
9a70: 65 20 73 74 72 69 6e 67 20 74 6f 20 63 6f 6d 70 e string to comp
9a80: 61 72 65 20 74 6f 20 75 63 74 2e 20 2a 2f 0a 20 are to uct. */.
9a90: 20 20 20 63 6f 6e 73 74 20 54 63 6c 5f 55 6e 69 const Tcl_Uni
9aa0: 43 68 61 72 20 2a 75 63 74 2c 09 2f 2a 20 55 6e Char *uct,./* Un
9ab0: 69 63 6f 64 65 20 73 74 72 69 6e 67 20 75 63 73 icode string ucs
9ac0: 20 69 73 20 63 6f 6d 70 61 72 65 64 20 74 6f 2e is compared to.
9ad0: 20 2a 2f 0a 20 20 20 20 75 6e 73 69 67 6e 65 64 */. unsigned
9ae0: 20 6c 6f 6e 67 20 6e 75 6d 43 68 61 72 73 29 09 long numChars).
9af0: 2f 2a 20 4e 75 6d 62 65 72 20 6f 66 20 75 6e 69 /* Number of uni
9b00: 63 68 61 72 73 20 74 6f 20 63 6f 6d 70 61 72 65 chars to compare
9b10: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 66 6f 72 20 28 . */.{. for (
9b20: 20 3b 20 6e 75 6d 43 68 61 72 73 20 21 3d 20 30 ; numChars != 0
9b30: 3b 20 6e 75 6d 43 68 61 72 73 2d 2d 2c 20 75 63 ; numChars--, uc
9b40: 73 2b 2b 2c 20 75 63 74 2b 2b 29 20 7b 0a 09 69 s++, uct++) {..i
9b50: 66 20 28 2a 75 63 73 20 21 3d 20 2a 75 63 74 29 f (*ucs != *uct)
9b60: 20 7b 0a 09 20 20 20 20 54 63 6c 5f 55 6e 69 43 {.. Tcl_UniC
9b70: 68 61 72 20 6c 63 73 20 3d 20 54 63 6c 5f 55 6e har lcs = Tcl_Un
9b80: 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a 75 63 iCharToLower(*uc
9b90: 73 29 3b 0a 09 20 20 20 20 54 63 6c 5f 55 6e 69 s);.. Tcl_Uni
9ba0: 43 68 61 72 20 6c 63 74 20 3d 20 54 63 6c 5f 55 Char lct = Tcl_U
9bb0: 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a 75 niCharToLower(*u
9bc0: 63 74 29 3b 0a 0a 09 20 20 20 20 69 66 20 28 6c ct);... if (l
9bd0: 63 73 20 21 3d 20 6c 63 74 29 20 7b 0a 09 09 72 cs != lct) {...r
9be0: 65 74 75 72 6e 20 28 6c 63 73 20 2d 20 6c 63 74 eturn (lcs - lct
9bf0: 29 3b 0a 09 20 20 20 20 7d 0a 09 7d 0a 20 20 20 );.. }..}.
9c00: 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 30 3b }. return 0;
9c10: 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d .}.../*. *------
9c20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9c30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9c40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9c50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9c60: 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 68 . *. * Tcl_UniCh
9c70: 61 72 49 73 41 6c 6e 75 6d 20 2d 2d 0a 20 2a 0a arIsAlnum --. *.
9c80: 20 2a 09 54 65 73 74 20 69 66 20 61 20 63 68 61 *.Test if a cha
9c90: 72 61 63 74 65 72 20 69 73 20 61 6e 20 61 6c 70 racter is an alp
9ca0: 68 61 6e 75 6d 65 72 69 63 20 55 6e 69 63 6f 64 hanumeric Unicod
9cb0: 65 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a e character.. *.
9cc0: 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 52 * Results:. *.R
9cd0: 65 74 75 72 6e 73 20 31 20 69 66 20 63 68 61 72 eturns 1 if char
9ce0: 61 63 74 65 72 20 69 73 20 61 6c 70 68 61 6e 75 acter is alphanu
9cf0: 6d 65 72 69 63 2e 0a 20 2a 0a 20 2a 20 53 69 64 meric.. *. * Sid
9d00: 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f e effects:. *.No
9d10: 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d ne.. *. *-------
9d20: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9d30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9d40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9d50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a ---------------.
9d60: 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 */..int.Tcl_Uni
9d70: 43 68 61 72 49 73 41 6c 6e 75 6d 28 0a 20 20 20 CharIsAlnum(.
9d80: 20 69 6e 74 20 63 68 29 09 09 09 2f 2a 20 55 6e int ch).../* Un
9d90: 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 20 icode character
9da0: 74 6f 20 74 65 73 74 2e 20 2a 2f 0a 7b 0a 20 20 to test. */.{.
9db0: 20 20 69 66 20 28 55 4e 49 43 4f 44 45 5f 4f 55 if (UNICODE_OU
9dc0: 54 5f 4f 46 5f 52 41 4e 47 45 28 63 68 29 29 20 T_OF_RANGE(ch))
9dd0: 7b 0a 09 72 65 74 75 72 6e 20 30 3b 0a 20 20 20 {..return 0;.
9de0: 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 28 28 }. return ((
9df0: 28 41 4c 50 48 41 5f 42 49 54 53 20 7c 20 44 49 (ALPHA_BITS | DI
9e00: 47 49 54 5f 42 49 54 53 29 20 3e 3e 20 47 65 74 GIT_BITS) >> Get
9e10: 43 61 74 65 67 6f 72 79 28 63 68 29 29 20 26 20 Category(ch)) &
9e20: 31 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 1);.}.../*. *---
9e30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9e40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9e50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9e60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9e70: 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 6e ---. *. * Tcl_Un
9e80: 69 43 68 61 72 49 73 41 6c 70 68 61 20 2d 2d 0a iCharIsAlpha --.
9e90: 20 2a 0a 20 2a 09 54 65 73 74 20 69 66 20 61 20 *. *.Test if a
9ea0: 63 68 61 72 61 63 74 65 72 20 69 73 20 61 6e 20 character is an
9eb0: 61 6c 70 68 61 62 65 74 69 63 20 55 6e 69 63 6f alphabetic Unico
9ec0: 64 65 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a de character.. *
9ed0: 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 . * Results:. *.
9ee0: 52 65 74 75 72 6e 73 20 31 20 69 66 20 63 68 61 Returns 1 if cha
9ef0: 72 61 63 74 65 72 20 69 73 20 61 6c 70 68 61 62 racter is alphab
9f00: 65 74 69 63 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 etic.. *. * Side
9f10: 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e effects:. *.Non
9f20: 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d e.. *. *--------
9f30: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9f40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9f50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
9f60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
9f70: 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 43 */..int.Tcl_UniC
9f80: 68 61 72 49 73 41 6c 70 68 61 28 0a 20 20 20 20 harIsAlpha(.
9f90: 69 6e 74 20 63 68 29 09 09 09 2f 2a 20 55 6e 69 int ch).../* Uni
9fa0: 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 20 74 code character t
9fb0: 6f 20 74 65 73 74 2e 20 2a 2f 0a 7b 0a 20 20 20 o test. */.{.
9fc0: 20 69 66 20 28 55 4e 49 43 4f 44 45 5f 4f 55 54 if (UNICODE_OUT
9fd0: 5f 4f 46 5f 52 41 4e 47 45 28 63 68 29 29 20 7b _OF_RANGE(ch)) {
9fe0: 0a 09 72 65 74 75 72 6e 20 30 3b 0a 20 20 20 20 ..return 0;.
9ff0: 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 28 28 41 }. return ((A
a000: 4c 50 48 41 5f 42 49 54 53 20 3e 3e 20 47 65 74 LPHA_BITS >> Get
a010: 43 61 74 65 67 6f 72 79 28 63 68 29 29 20 26 20 Category(ch)) &
a020: 31 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 1);.}.../*. *---
a030: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a040: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a050: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a060: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a070: 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 6e ---. *. * Tcl_Un
a080: 69 43 68 61 72 49 73 43 6f 6e 74 72 6f 6c 20 2d iCharIsControl -
a090: 2d 0a 20 2a 0a 20 2a 09 54 65 73 74 20 69 66 20 -. *. *.Test if
a0a0: 61 20 63 68 61 72 61 63 74 65 72 20 69 73 20 61 a character is a
a0b0: 20 55 6e 69 63 6f 64 65 20 63 6f 6e 74 72 6f 6c Unicode control
a0c0: 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 character.. *.
a0d0: 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 52 65 * Results:. *.Re
a0e0: 74 75 72 6e 73 20 6e 6f 6e 2d 7a 65 72 6f 20 69 turns non-zero i
a0f0: 66 20 63 68 61 72 61 63 74 65 72 20 69 73 20 61 f character is a
a100: 20 63 6f 6e 74 72 6f 6c 2e 0a 20 2a 0a 20 2a 20 control.. *. *
a110: 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a Side effects:. *
a120: 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d .None.. *. *----
a130: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a140: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a150: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a160: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a170: 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f --. */..int.Tcl_
a180: 55 6e 69 43 68 61 72 49 73 43 6f 6e 74 72 6f 6c UniCharIsControl
a190: 28 0a 20 20 20 20 69 6e 74 20 63 68 29 09 09 09 (. int ch)...
a1a0: 2f 2a 20 55 6e 69 63 6f 64 65 20 63 68 61 72 61 /* Unicode chara
a1b0: 63 74 65 72 20 74 6f 20 74 65 73 74 2e 20 2a 2f cter to test. */
a1c0: 0a 7b 0a 20 20 20 20 69 66 20 28 55 4e 49 43 4f .{. if (UNICO
a1d0: 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 4e 47 45 28 DE_OUT_OF_RANGE(
a1e0: 63 68 29 29 20 7b 0a 09 63 68 20 26 3d 20 30 78 ch)) {..ch &= 0x
a1f0: 31 46 46 46 46 46 3b 0a 09 69 66 20 28 28 63 68 1FFFFF;..if ((ch
a200: 20 3d 3d 20 30 78 45 30 30 30 31 29 20 7c 7c 20 == 0xE0001) ||
a210: 28 28 63 68 20 3e 3d 20 30 78 45 30 30 32 30 29 ((ch >= 0xE0020)
a220: 20 26 26 20 28 63 68 20 3c 3d 20 30 78 45 30 30 && (ch <= 0xE00
a230: 37 66 29 29 29 20 7b 0a 09 20 20 20 20 72 65 74 7f))) {.. ret
a240: 75 72 6e 20 31 3b 0a 09 7d 0a 09 69 66 20 28 28 urn 1;..}..if ((
a250: 63 68 20 3e 3d 20 30 78 46 30 30 30 30 29 20 26 ch >= 0xF0000) &
a260: 26 20 28 28 63 68 20 26 20 30 78 46 46 46 46 29 & ((ch & 0xFFFF)
a270: 20 3c 3d 20 30 78 46 46 46 44 29 29 20 7b 0a 09 <= 0xFFFD)) {..
a280: 20 20 20 20 72 65 74 75 72 6e 20 31 3b 0a 09 7d return 1;..}
a290: 0a 09 72 65 74 75 72 6e 20 30 3b 0a 20 20 20 20 ..return 0;.
a2a0: 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 28 28 43 }. return ((C
a2b0: 4f 4e 54 52 4f 4c 5f 42 49 54 53 20 3e 3e 20 47 ONTROL_BITS >> G
a2c0: 65 74 43 61 74 65 67 6f 72 79 28 63 68 29 29 20 etCategory(ch))
a2d0: 26 20 31 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d & 1);.}.../*. *-
a2e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a2f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a300: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a310: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a320: 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f -----. *. * Tcl_
a330: 55 6e 69 43 68 61 72 49 73 44 69 67 69 74 20 2d UniCharIsDigit -
a340: 2d 0a 20 2a 0a 20 2a 09 54 65 73 74 20 69 66 20 -. *. *.Test if
a350: 61 20 63 68 61 72 61 63 74 65 72 20 69 73 20 61 a character is a
a360: 20 6e 75 6d 65 72 69 63 20 55 6e 69 63 6f 64 65 numeric Unicode
a370: 20 63 68 61 72 61 63 74 65 72 2e 0a 20 2a 0a 20 character.. *.
a380: 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 52 65 * Results:. *.Re
a390: 74 75 72 6e 73 20 6e 6f 6e 2d 7a 65 72 6f 20 69 turns non-zero i
a3a0: 66 20 63 68 61 72 61 63 74 65 72 20 69 73 20 61 f character is a
a3b0: 20 64 69 67 69 74 2e 0a 20 2a 0a 20 2a 20 53 69 digit.. *. * Si
a3c0: 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e de effects:. *.N
a3d0: 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d one.. *. *------
a3e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a3f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a400: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a410: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a420: 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e . */..int.Tcl_Un
a430: 69 43 68 61 72 49 73 44 69 67 69 74 28 0a 20 20 iCharIsDigit(.
a440: 20 20 69 6e 74 20 63 68 29 09 09 09 2f 2a 20 55 int ch).../* U
a450: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
a460: 20 74 6f 20 74 65 73 74 2e 20 2a 2f 0a 7b 0a 20 to test. */.{.
a470: 20 20 20 69 66 20 28 55 4e 49 43 4f 44 45 5f 4f if (UNICODE_O
a480: 55 54 5f 4f 46 5f 52 41 4e 47 45 28 63 68 29 29 UT_OF_RANGE(ch))
a490: 20 7b 0a 09 72 65 74 75 72 6e 20 30 3b 0a 20 20 {..return 0;.
a4a0: 20 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 28 }. return (
a4b0: 47 65 74 43 61 74 65 67 6f 72 79 28 63 68 29 20 GetCategory(ch)
a4c0: 3d 3d 20 44 45 43 49 4d 41 4c 5f 44 49 47 49 54 == DECIMAL_DIGIT
a4d0: 5f 4e 55 4d 42 45 52 29 3b 0a 7d 0a 0c 0a 2f 2a _NUMBER);.}.../*
a4e0: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
a4f0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a500: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a510: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a520: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 ---------. *. *
a530: 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 47 72 61 Tcl_UniCharIsGra
a540: 70 68 20 2d 2d 0a 20 2a 0a 20 2a 09 54 65 73 74 ph --. *. *.Test
a550: 20 69 66 20 61 20 63 68 61 72 61 63 74 65 72 20 if a character
a560: 69 73 20 61 6e 79 20 55 6e 69 63 6f 64 65 20 70 is any Unicode p
a570: 72 69 6e 74 20 63 68 61 72 61 63 74 65 72 20 65 rint character e
a580: 78 63 65 70 74 20 73 70 61 63 65 2e 0a 20 2a 0a xcept space.. *.
a590: 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 52 * Results:. *.R
a5a0: 65 74 75 72 6e 73 20 6e 6f 6e 2d 7a 65 72 6f 20 eturns non-zero
a5b0: 69 66 20 63 68 61 72 61 63 74 65 72 20 69 73 20 if character is
a5c0: 70 72 69 6e 74 61 62 6c 65 2c 20 62 75 74 20 6e printable, but n
a5d0: 6f 74 20 73 70 61 63 65 2e 0a 20 2a 0a 20 2a 20 ot space.. *. *
a5e0: 53 69 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a Side effects:. *
a5f0: 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d .None.. *. *----
a600: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a610: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a620: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a630: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a640: 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f --. */..int.Tcl_
a650: 55 6e 69 43 68 61 72 49 73 47 72 61 70 68 28 0a UniCharIsGraph(.
a660: 20 20 20 20 69 6e 74 20 63 68 29 09 09 09 2f 2a int ch).../*
a670: 20 55 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 Unicode charact
a680: 65 72 20 74 6f 20 74 65 73 74 2e 20 2a 2f 0a 7b er to test. */.{
a690: 0a 20 20 20 20 69 66 20 28 55 4e 49 43 4f 44 45 . if (UNICODE
a6a0: 5f 4f 55 54 5f 4f 46 5f 52 41 4e 47 45 28 63 68 _OUT_OF_RANGE(ch
a6b0: 29 29 20 7b 0a 09 63 68 20 26 3d 20 30 78 31 46 )) {..ch &= 0x1F
a6c0: 46 46 46 46 3b 0a 09 72 65 74 75 72 6e 20 28 63 FFFF;..return (c
a6d0: 68 20 3e 3d 20 30 78 45 30 31 30 30 29 20 26 26 h >= 0xE0100) &&
a6e0: 20 28 63 68 20 3c 3d 20 30 78 45 30 31 45 46 29 (ch <= 0xE01EF)
a6f0: 3b 0a 20 20 20 20 7d 0a 20 20 20 20 72 65 74 75 ;. }. retu
a700: 72 6e 20 28 28 47 52 41 50 48 5f 42 49 54 53 20 rn ((GRAPH_BITS
a710: 3e 3e 20 47 65 74 43 61 74 65 67 6f 72 79 28 63 >> GetCategory(c
a720: 68 29 29 20 26 20 31 29 3b 0a 7d 0a 0c 0a 2f 2a h)) & 1);.}.../*
a730: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
a740: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a750: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a760: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a770: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 ---------. *. *
a780: 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 4c 6f 77 Tcl_UniCharIsLow
a790: 65 72 20 2d 2d 0a 20 2a 0a 20 2a 09 54 65 73 74 er --. *. *.Test
a7a0: 20 69 66 20 61 20 63 68 61 72 61 63 74 65 72 20 if a character
a7b0: 69 73 20 61 20 6c 6f 77 65 72 63 61 73 65 20 55 is a lowercase U
a7c0: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
a7d0: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
a7e0: 0a 20 2a 09 52 65 74 75 72 6e 73 20 6e 6f 6e 2d . *.Returns non-
a7f0: 7a 65 72 6f 20 69 66 20 63 68 61 72 61 63 74 65 zero if characte
a800: 72 20 69 73 20 6c 6f 77 65 72 63 61 73 65 2e 0a r is lowercase..
a810: 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 *. * Side effec
a820: 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a ts:. *.None.. *.
a830: 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *--------------
a840: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a850: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a860: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a870: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e --------. */..in
a880: 74 0a 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 4c t.Tcl_UniCharIsL
a890: 6f 77 65 72 28 0a 20 20 20 20 69 6e 74 20 63 68 ower(. int ch
a8a0: 29 09 09 09 2f 2a 20 55 6e 69 63 6f 64 65 20 63 ).../* Unicode c
a8b0: 68 61 72 61 63 74 65 72 20 74 6f 20 74 65 73 74 haracter to test
a8c0: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 55 . */.{. if (U
a8d0: 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 NICODE_OUT_OF_RA
a8e0: 4e 47 45 28 63 68 29 29 20 7b 0a 09 72 65 74 75 NGE(ch)) {..retu
a8f0: 72 6e 20 30 3b 0a 20 20 20 20 7d 0a 20 20 20 20 rn 0;. }.
a900: 72 65 74 75 72 6e 20 28 47 65 74 43 61 74 65 67 return (GetCateg
a910: 6f 72 79 28 63 68 29 20 3d 3d 20 4c 4f 57 45 52 ory(ch) == LOWER
a920: 43 41 53 45 5f 4c 45 54 54 45 52 29 3b 0a 7d 0a CASE_LETTER);.}.
a930: 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d ../*. *---------
a940: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a950: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a960: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
a970: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a -------------. *
a980: 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 49 . * Tcl_UniCharI
a990: 73 50 72 69 6e 74 20 2d 2d 0a 20 2a 0a 20 2a 09 sPrint --. *. *.
a9a0: 54 65 73 74 20 69 66 20 61 20 63 68 61 72 61 63 Test if a charac
a9b0: 74 65 72 20 69 73 20 61 20 55 6e 69 63 6f 64 65 ter is a Unicode
a9c0: 20 70 72 69 6e 74 20 63 68 61 72 61 63 74 65 72 print character
a9d0: 2e 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a .. *. * Results:
a9e0: 0a 20 2a 09 52 65 74 75 72 6e 73 20 6e 6f 6e 2d . *.Returns non-
a9f0: 7a 65 72 6f 20 69 66 20 63 68 61 72 61 63 74 65 zero if characte
aa00: 72 20 69 73 20 70 72 69 6e 74 61 62 6c 65 2e 0a r is printable..
aa10: 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 *. * Side effec
aa20: 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a ts:. *.None.. *.
aa30: 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *--------------
aa40: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aa50: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aa60: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aa70: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e --------. */..in
aa80: 74 0a 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 50 t.Tcl_UniCharIsP
aa90: 72 69 6e 74 28 0a 20 20 20 20 69 6e 74 20 63 68 rint(. int ch
aaa0: 29 09 09 09 2f 2a 20 55 6e 69 63 6f 64 65 20 63 ).../* Unicode c
aab0: 68 61 72 61 63 74 65 72 20 74 6f 20 74 65 73 74 haracter to test
aac0: 2e 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 55 . */.{. if (U
aad0: 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 NICODE_OUT_OF_RA
aae0: 4e 47 45 28 63 68 29 29 20 7b 0a 09 63 68 20 26 NGE(ch)) {..ch &
aaf0: 3d 20 30 78 31 46 46 46 46 46 3b 0a 09 72 65 74 = 0x1FFFFF;..ret
ab00: 75 72 6e 20 28 63 68 20 3e 3d 20 30 78 45 30 31 urn (ch >= 0xE01
ab10: 30 30 29 20 26 26 20 28 63 68 20 3c 3d 20 30 78 00) && (ch <= 0x
ab20: 45 30 31 45 46 29 3b 0a 20 20 20 20 7d 0a 20 20 E01EF);. }.
ab30: 20 20 72 65 74 75 72 6e 20 28 28 28 47 52 41 50 return (((GRAP
ab40: 48 5f 42 49 54 53 7c 53 50 41 43 45 5f 42 49 54 H_BITS|SPACE_BIT
ab50: 53 29 20 3e 3e 20 47 65 74 43 61 74 65 67 6f 72 S) >> GetCategor
ab60: 79 28 63 68 29 29 20 26 20 31 29 3b 0a 7d 0a 0c y(ch)) & 1);.}..
ab70: 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ./*. *----------
ab80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
ab90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aba0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
abb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a ------------. *.
abc0: 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 * Tcl_UniCharIs
abd0: 50 75 6e 63 74 20 2d 2d 0a 20 2a 0a 20 2a 09 54 Punct --. *. *.T
abe0: 65 73 74 20 69 66 20 61 20 63 68 61 72 61 63 74 est if a charact
abf0: 65 72 20 69 73 20 61 20 55 6e 69 63 6f 64 65 20 er is a Unicode
ac00: 70 75 6e 63 74 75 61 74 69 6f 6e 20 63 68 61 72 punctuation char
ac10: 61 63 74 65 72 2e 0a 20 2a 0a 20 2a 20 52 65 73 acter.. *. * Res
ac20: 75 6c 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e 73 ults:. *.Returns
ac30: 20 6e 6f 6e 2d 7a 65 72 6f 20 69 66 20 63 68 61 non-zero if cha
ac40: 72 61 63 74 65 72 20 69 73 20 70 75 6e 63 74 2e racter is punct.
ac50: 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 . *. * Side effe
ac60: 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a cts:. *.None.. *
ac70: 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *-------------
ac80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
ac90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aca0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
acb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 ---------. */..i
acc0: 6e 74 0a 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 nt.Tcl_UniCharIs
acd0: 50 75 6e 63 74 28 0a 20 20 20 20 69 6e 74 20 63 Punct(. int c
ace0: 68 29 09 09 09 2f 2a 20 55 6e 69 63 6f 64 65 20 h).../* Unicode
acf0: 63 68 61 72 61 63 74 65 72 20 74 6f 20 74 65 73 character to tes
ad00: 74 2e 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 t. */.{. if (
ad10: 55 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 UNICODE_OUT_OF_R
ad20: 41 4e 47 45 28 63 68 29 29 20 7b 0a 09 72 65 74 ANGE(ch)) {..ret
ad30: 75 72 6e 20 30 3b 0a 20 20 20 20 7d 0a 20 20 20 urn 0;. }.
ad40: 20 72 65 74 75 72 6e 20 28 28 50 55 4e 43 54 5f return ((PUNCT_
ad50: 42 49 54 53 20 3e 3e 20 47 65 74 43 61 74 65 67 BITS >> GetCateg
ad60: 6f 72 79 28 63 68 29 29 20 26 20 31 29 3b 0a 7d ory(ch)) & 1);.}
ad70: 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d .../*. *--------
ad80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
ad90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
ada0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
adb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
adc0: 2a 0a 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 *. * Tcl_UniChar
add0: 49 73 53 70 61 63 65 20 2d 2d 0a 20 2a 0a 20 2a IsSpace --. *. *
ade0: 09 54 65 73 74 20 69 66 20 61 20 63 68 61 72 61 .Test if a chara
adf0: 63 74 65 72 20 69 73 20 61 20 77 68 69 74 65 73 cter is a whites
ae00: 70 61 63 65 20 55 6e 69 63 6f 64 65 20 63 68 61 pace Unicode cha
ae10: 72 61 63 74 65 72 2e 0a 20 2a 0a 20 2a 20 52 65 racter.. *. * Re
ae20: 73 75 6c 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e sults:. *.Return
ae30: 73 20 6e 6f 6e 2d 7a 65 72 6f 20 69 66 20 63 68 s non-zero if ch
ae40: 61 72 61 63 74 65 72 20 69 73 20 61 20 73 70 61 aracter is a spa
ae50: 63 65 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 65 ce.. *. * Side e
ae60: 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 2e ffects:. *.None.
ae70: 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d . *. *----------
ae80: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
ae90: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aea0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
aeb0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f ------------. */
aec0: 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 43 68 61 ..int.Tcl_UniCha
aed0: 72 49 73 53 70 61 63 65 28 0a 20 20 20 20 69 6e rIsSpace(. in
aee0: 74 20 63 68 29 09 09 09 2f 2a 20 55 6e 69 63 6f t ch).../* Unico
aef0: 64 65 20 63 68 61 72 61 63 74 65 72 20 74 6f 20 de character to
af00: 74 65 73 74 2e 20 2a 2f 0a 7b 0a 20 20 20 20 2f test. */.{. /
af10: 2a 20 49 67 6e 6f 72 65 20 75 70 70 65 72 20 31 * Ignore upper 1
af20: 31 20 62 69 74 73 2e 20 2a 2f 0a 20 20 20 20 63 1 bits. */. c
af30: 68 20 26 3d 20 30 78 31 46 46 46 46 46 3b 0a 0a h &= 0x1FFFFF;..
af40: 20 20 20 20 2f 2a 0a 20 20 20 20 20 2a 20 49 66 /*. * If
af50: 20 74 68 65 20 63 68 61 72 61 63 74 65 72 20 69 the character i
af60: 73 20 77 69 74 68 69 6e 20 74 68 65 20 66 69 72 s within the fir
af70: 73 74 20 31 32 37 20 63 68 61 72 61 63 74 65 72 st 127 character
af80: 73 2c 20 6a 75 73 74 20 75 73 65 20 74 68 65 0a s, just use the.
af90: 20 20 20 20 20 2a 20 73 74 61 6e 64 61 72 64 20 * standard
afa0: 43 20 66 75 6e 63 74 69 6f 6e 2c 20 6f 74 68 65 C function, othe
afb0: 72 77 69 73 65 20 63 6f 6e 73 75 6c 74 20 74 68 rwise consult th
afc0: 65 20 55 6e 69 63 6f 64 65 20 74 61 62 6c 65 2e e Unicode table.
afd0: 0a 20 20 20 20 20 2a 2f 0a 0a 20 20 20 20 69 66 . */.. if
afe0: 20 28 63 68 20 3c 20 30 78 38 30 29 20 7b 0a 09 (ch < 0x80) {..
aff0: 72 65 74 75 72 6e 20 54 63 6c 49 73 53 70 61 63 return TclIsSpac
b000: 65 50 72 6f 63 28 28 63 68 61 72 29 20 63 68 29 eProc((char) ch)
b010: 3b 0a 20 20 20 20 7d 20 65 6c 73 65 20 69 66 20 ;. } else if
b020: 28 55 4e 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f (UNICODE_OUT_OF_
b030: 52 41 4e 47 45 28 63 68 29 29 20 7b 0a 09 72 65 RANGE(ch)) {..re
b040: 74 75 72 6e 20 30 3b 0a 20 20 20 20 7d 20 65 6c turn 0;. } el
b050: 73 65 20 69 66 20 28 63 68 20 3d 3d 20 30 78 30 se if (ch == 0x0
b060: 30 38 35 20 7c 7c 20 63 68 20 3d 3d 20 30 78 31 085 || ch == 0x1
b070: 38 30 45 20 7c 7c 20 63 68 20 3d 3d 20 30 78 32 80E || ch == 0x2
b080: 30 30 42 0a 09 20 20 20 20 7c 7c 20 63 68 20 3d 00B.. || ch =
b090: 3d 20 30 78 32 30 32 46 20 7c 7c 20 63 68 20 3d = 0x202F || ch =
b0a0: 3d 20 30 78 32 30 36 30 20 7c 7c 20 63 68 20 3d = 0x2060 || ch =
b0b0: 3d 20 30 78 46 45 46 46 29 20 7b 0a 09 72 65 74 = 0xFEFF) {..ret
b0c0: 75 72 6e 20 31 3b 0a 20 20 20 20 7d 20 65 6c 73 urn 1;. } els
b0d0: 65 20 7b 0a 09 72 65 74 75 72 6e 20 28 28 53 50 e {..return ((SP
b0e0: 41 43 45 5f 42 49 54 53 20 3e 3e 20 47 65 74 43 ACE_BITS >> GetC
b0f0: 61 74 65 67 6f 72 79 28 63 68 29 29 20 26 20 31 ategory(ch)) & 1
b100: 29 3b 0a 20 20 20 20 7d 0a 7d 0a 0c 0a 2f 2a 0a );. }.}.../*.
b110: 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *--------------
b120: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b130: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b140: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b150: 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 --------. *. * T
b160: 63 6c 5f 55 6e 69 43 68 61 72 49 73 55 70 70 65 cl_UniCharIsUppe
b170: 72 20 2d 2d 0a 20 2a 0a 20 2a 09 54 65 73 74 20 r --. *. *.Test
b180: 69 66 20 61 20 63 68 61 72 61 63 74 65 72 20 69 if a character i
b190: 73 20 61 20 75 70 70 65 72 63 61 73 65 20 55 6e s a uppercase Un
b1a0: 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 2e icode character.
b1b0: 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a . *. * Results:.
b1c0: 20 2a 09 52 65 74 75 72 6e 73 20 6e 6f 6e 2d 7a *.Returns non-z
b1d0: 65 72 6f 20 69 66 20 63 68 61 72 61 63 74 65 72 ero if character
b1e0: 20 69 73 20 75 70 70 65 72 63 61 73 65 2e 0a 20 is uppercase..
b1f0: 2a 0a 20 2a 20 53 69 64 65 20 65 66 66 65 63 74 *. * Side effect
b200: 73 3a 0a 20 2a 09 4e 6f 6e 65 2e 0a 20 2a 0a 20 s:. *.None.. *.
b210: 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d *---------------
b220: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b230: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b240: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b250: 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 2f 0a 0a 69 6e 74 -------. */..int
b260: 0a 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 55 70 .Tcl_UniCharIsUp
b270: 70 65 72 28 0a 20 20 20 20 69 6e 74 20 63 68 29 per(. int ch)
b280: 09 09 09 2f 2a 20 55 6e 69 63 6f 64 65 20 63 68 .../* Unicode ch
b290: 61 72 61 63 74 65 72 20 74 6f 20 74 65 73 74 2e aracter to test.
b2a0: 20 2a 2f 0a 7b 0a 20 20 20 20 69 66 20 28 55 4e */.{. if (UN
b2b0: 49 43 4f 44 45 5f 4f 55 54 5f 4f 46 5f 52 41 4e ICODE_OUT_OF_RAN
b2c0: 47 45 28 63 68 29 29 20 7b 0a 09 72 65 74 75 72 GE(ch)) {..retur
b2d0: 6e 20 30 3b 0a 20 20 20 20 7d 0a 20 20 20 20 72 n 0;. }. r
b2e0: 65 74 75 72 6e 20 28 47 65 74 43 61 74 65 67 6f eturn (GetCatego
b2f0: 72 79 28 63 68 29 20 3d 3d 20 55 50 50 45 52 43 ry(ch) == UPPERC
b300: 41 53 45 5f 4c 45 54 54 45 52 29 3b 0a 7d 0a 0c ASE_LETTER);.}..
b310: 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ./*. *----------
b320: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b330: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b340: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b350: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a 0a ------------. *.
b360: 20 2a 20 54 63 6c 5f 55 6e 69 43 68 61 72 49 73 * Tcl_UniCharIs
b370: 57 6f 72 64 43 68 61 72 20 2d 2d 0a 20 2a 0a 20 WordChar --. *.
b380: 2a 09 54 65 73 74 20 69 66 20 61 20 63 68 61 72 *.Test if a char
b390: 61 63 74 65 72 20 69 73 20 61 6c 70 68 61 6e 75 acter is alphanu
b3a0: 6d 65 72 69 63 20 6f 72 20 61 20 63 6f 6e 6e 65 meric or a conne
b3b0: 63 74 6f 72 20 70 75 6e 63 74 75 61 74 69 6f 6e ctor punctuation
b3c0: 20 6d 61 72 6b 2e 0a 20 2a 0a 20 2a 20 52 65 73 mark.. *. * Res
b3d0: 75 6c 74 73 3a 0a 20 2a 09 52 65 74 75 72 6e 73 ults:. *.Returns
b3e0: 20 31 20 69 66 20 63 68 61 72 61 63 74 65 72 20 1 if character
b3f0: 69 73 20 61 20 77 6f 72 64 20 63 68 61 72 61 63 is a word charac
b400: 74 65 72 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 ter.. *. * Side
b410: 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 effects:. *.None
b420: 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d .. *. *---------
b430: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b440: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b450: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b460: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a -------------. *
b470: 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e 69 43 68 /..int.Tcl_UniCh
b480: 61 72 49 73 57 6f 72 64 43 68 61 72 28 0a 20 20 arIsWordChar(.
b490: 20 20 69 6e 74 20 63 68 29 09 09 09 2f 2a 20 55 int ch).../* U
b4a0: 6e 69 63 6f 64 65 20 63 68 61 72 61 63 74 65 72 nicode character
b4b0: 20 74 6f 20 74 65 73 74 2e 20 2a 2f 0a 7b 0a 20 to test. */.{.
b4c0: 20 20 20 69 66 20 28 55 4e 49 43 4f 44 45 5f 4f if (UNICODE_O
b4d0: 55 54 5f 4f 46 5f 52 41 4e 47 45 28 63 68 29 29 UT_OF_RANGE(ch))
b4e0: 20 7b 0a 09 72 65 74 75 72 6e 20 30 3b 0a 20 20 {..return 0;.
b4f0: 20 20 7d 0a 20 20 20 20 72 65 74 75 72 6e 20 28 }. return (
b500: 28 57 4f 52 44 5f 42 49 54 53 20 3e 3e 20 47 65 (WORD_BITS >> Ge
b510: 74 43 61 74 65 67 6f 72 79 28 63 68 29 29 20 26 tCategory(ch)) &
b520: 20 31 29 3b 0a 7d 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 1);.}.../*. *--
b530: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b540: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b550: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b560: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b570: 2d 2d 2d 2d 0a 20 2a 0a 20 2a 20 54 63 6c 5f 55 ----. *. * Tcl_U
b580: 6e 69 43 68 61 72 43 61 73 65 4d 61 74 63 68 20 niCharCaseMatch
b590: 2d 2d 0a 20 2a 0a 20 2a 09 53 65 65 20 69 66 20 --. *. *.See if
b5a0: 61 20 70 61 72 74 69 63 75 6c 61 72 20 55 6e 69 a particular Uni
b5b0: 63 6f 64 65 20 73 74 72 69 6e 67 20 6d 61 74 63 code string matc
b5c0: 68 65 73 20 61 20 70 61 72 74 69 63 75 6c 61 72 hes a particular
b5d0: 20 70 61 74 74 65 72 6e 2e 0a 20 2a 09 41 6c 6c pattern.. *.All
b5e0: 6f 77 73 20 63 61 73 65 20 69 6e 73 65 6e 73 69 ows case insensi
b5f0: 74 69 76 69 74 79 2e 20 54 68 69 73 20 69 73 20 tivity. This is
b600: 74 68 65 20 55 6e 69 63 6f 64 65 20 65 71 75 69 the Unicode equi
b610: 76 61 6c 65 6e 74 20 6f 66 20 74 68 65 20 63 68 valent of the ch
b620: 61 72 2a 0a 20 2a 09 54 63 6c 5f 53 74 72 69 6e ar*. *.Tcl_Strin
b630: 67 43 61 73 65 4d 61 74 63 68 2e 20 54 68 65 20 gCaseMatch. The
b640: 55 6e 69 43 68 61 72 20 73 74 72 69 6e 67 73 20 UniChar strings
b650: 6d 75 73 74 20 62 65 20 4e 55 4c 4c 2d 74 65 72 must be NULL-ter
b660: 6d 69 6e 61 74 65 64 2e 0a 20 2a 09 54 68 69 73 minated.. *.This
b670: 20 68 61 73 20 6e 6f 20 70 72 6f 76 69 73 69 6f has no provisio
b680: 6e 20 66 6f 72 20 63 6f 75 6e 74 65 64 20 55 6e n for counted Un
b690: 69 43 68 61 72 20 73 74 72 69 6e 67 73 2c 20 74 iChar strings, t
b6a0: 68 75 73 20 73 68 6f 75 6c 64 20 6e 6f 74 20 62 hus should not b
b6b0: 65 0a 20 2a 09 75 73 65 64 20 77 68 65 72 65 20 e. *.used where
b6c0: 4e 55 4c 4c 73 20 61 72 65 20 65 78 70 65 63 74 NULLs are expect
b6d0: 65 64 20 69 6e 20 74 68 65 20 55 6e 69 43 68 61 ed in the UniCha
b6e0: 72 20 73 74 72 69 6e 67 2e 20 55 73 65 0a 20 2a r string. Use. *
b6f0: 09 54 63 6c 55 6e 69 43 68 61 72 4d 61 74 63 68 .TclUniCharMatch
b700: 20 77 68 65 72 65 20 70 6f 73 73 69 62 6c 65 2e where possible.
b710: 0a 20 2a 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a . *. * Results:.
b720: 20 2a 09 54 68 65 20 72 65 74 75 72 6e 20 76 61 *.The return va
b730: 6c 75 65 20 69 73 20 31 20 69 66 20 73 74 72 69 lue is 1 if stri
b740: 6e 67 20 6d 61 74 63 68 65 73 20 70 61 74 74 65 ng matches patte
b750: 72 6e 2c 20 61 6e 64 20 30 20 6f 74 68 65 72 77 rn, and 0 otherw
b760: 69 73 65 2e 20 54 68 65 0a 20 2a 09 6d 61 74 63 ise. The. *.matc
b770: 68 69 6e 67 20 6f 70 65 72 61 74 69 6f 6e 20 70 hing operation p
b780: 65 72 6d 69 74 73 20 74 68 65 20 66 6f 6c 6c 6f ermits the follo
b790: 77 69 6e 67 20 73 70 65 63 69 61 6c 20 63 68 61 wing special cha
b7a0: 72 61 63 74 65 72 73 20 69 6e 20 74 68 65 0a 20 racters in the.
b7b0: 2a 09 70 61 74 74 65 72 6e 3a 20 2a 3f 5c 5b 5d *.pattern: *?\[]
b7c0: 20 28 73 65 65 20 74 68 65 20 6d 61 6e 75 61 6c (see the manual
b7d0: 20 65 6e 74 72 79 20 66 6f 72 20 64 65 74 61 69 entry for detai
b7e0: 6c 73 20 6f 6e 20 77 68 61 74 20 74 68 65 73 65 ls on what these
b7f0: 20 6d 65 61 6e 29 2e 0a 20 2a 0a 20 2a 20 53 69 mean).. *. * Si
b800: 64 65 20 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e de effects:. *.N
b810: 6f 6e 65 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d one.. *. *------
b820: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b830: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b840: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b850: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
b860: 0a 20 2a 2f 0a 0a 69 6e 74 0a 54 63 6c 5f 55 6e . */..int.Tcl_Un
b870: 69 43 68 61 72 43 61 73 65 4d 61 74 63 68 28 0a iCharCaseMatch(.
b880: 20 20 20 20 63 6f 6e 73 74 20 54 63 6c 5f 55 6e const Tcl_Un
b890: 69 43 68 61 72 20 2a 75 6e 69 53 74 72 2c 09 2f iChar *uniStr,./
b8a0: 2a 20 55 6e 69 63 6f 64 65 20 53 74 72 69 6e 67 * Unicode String
b8b0: 2e 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 54 . */. const T
b8c0: 63 6c 5f 55 6e 69 43 68 61 72 20 2a 75 6e 69 50 cl_UniChar *uniP
b8d0: 61 74 74 65 72 6e 2c 0a 09 09 09 09 2f 2a 20 50 attern,...../* P
b8e0: 61 74 74 65 72 6e 2c 20 77 68 69 63 68 20 6d 61 attern, which ma
b8f0: 79 20 63 6f 6e 74 61 69 6e 20 73 70 65 63 69 61 y contain specia
b900: 6c 0a 09 09 09 09 20 2a 20 63 68 61 72 61 63 74 l..... * charact
b910: 65 72 73 2e 20 2a 2f 0a 20 20 20 20 69 6e 74 20 ers. */. int
b920: 6e 6f 63 61 73 65 29 09 09 09 2f 2a 20 30 20 66 nocase).../* 0 f
b930: 6f 72 20 63 61 73 65 20 73 65 6e 73 69 74 69 76 or case sensitiv
b940: 65 2c 20 31 20 66 6f 72 20 69 6e 73 65 6e 73 69 e, 1 for insensi
b950: 74 69 76 65 20 2a 2f 0a 7b 0a 20 20 20 20 54 63 tive */.{. Tc
b960: 6c 5f 55 6e 69 43 68 61 72 20 63 68 31 20 3d 20 l_UniChar ch1 =
b970: 30 2c 20 70 3b 0a 0a 20 20 20 20 77 68 69 6c 65 0, p;.. while
b980: 20 28 31 29 20 7b 0a 09 70 20 3d 20 2a 75 6e 69 (1) {..p = *uni
b990: 50 61 74 74 65 72 6e 3b 0a 0a 09 2f 2a 0a 09 20 Pattern;.../*..
b9a0: 2a 20 53 65 65 20 69 66 20 77 65 27 72 65 20 61 * See if we're a
b9b0: 74 20 74 68 65 20 65 6e 64 20 6f 66 20 62 6f 74 t the end of bot
b9c0: 68 20 74 68 65 20 70 61 74 74 65 72 6e 20 61 6e h the pattern an
b9d0: 64 20 74 68 65 20 73 74 72 69 6e 67 2e 20 49 66 d the string. If
b9e0: 20 73 6f 2c 0a 09 20 2a 20 77 65 20 73 75 63 63 so,.. * we succ
b9f0: 65 65 64 65 64 2e 20 49 66 20 77 65 27 72 65 20 eeded. If we're
ba00: 61 74 20 74 68 65 20 65 6e 64 20 6f 66 20 74 68 at the end of th
ba10: 65 20 70 61 74 74 65 72 6e 20 62 75 74 20 6e 6f e pattern but no
ba20: 74 20 61 74 20 74 68 65 20 65 6e 64 0a 09 20 2a t at the end.. *
ba30: 20 6f 66 20 74 68 65 20 73 74 72 69 6e 67 2c 20 of the string,
ba40: 77 65 20 66 61 69 6c 65 64 2e 0a 09 20 2a 2f 0a we failed... */.
ba50: 0a 09 69 66 20 28 70 20 3d 3d 20 30 29 20 7b 0a ..if (p == 0) {.
ba60: 09 20 20 20 20 72 65 74 75 72 6e 20 28 2a 75 6e . return (*un
ba70: 69 53 74 72 20 3d 3d 20 30 29 3b 0a 09 7d 0a 09 iStr == 0);..}..
ba80: 69 66 20 28 28 2a 75 6e 69 53 74 72 20 3d 3d 20 if ((*uniStr ==
ba90: 30 29 20 26 26 20 28 70 20 21 3d 20 27 2a 27 29 0) && (p != '*')
baa0: 29 20 7b 0a 09 20 20 20 20 72 65 74 75 72 6e 20 ) {.. return
bab0: 30 3b 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 43 0;..}.../*.. * C
bac0: 68 65 63 6b 20 66 6f 72 20 61 20 22 2a 22 20 61 heck for a "*" a
bad0: 73 20 74 68 65 20 6e 65 78 74 20 70 61 74 74 65 s the next patte
bae0: 72 6e 20 63 68 61 72 61 63 74 65 72 2e 20 49 74 rn character. It
baf0: 20 6d 61 74 63 68 65 73 20 61 6e 79 0a 09 20 2a matches any.. *
bb00: 20 73 75 62 73 74 72 69 6e 67 2e 20 57 65 20 68 substring. We h
bb10: 61 6e 64 6c 65 20 74 68 69 73 20 62 79 20 73 6b andle this by sk
bb20: 69 70 70 69 6e 67 20 61 6c 6c 20 74 68 65 20 63 ipping all the c
bb30: 68 61 72 61 63 74 65 72 73 20 75 70 20 74 6f 20 haracters up to
bb40: 74 68 65 0a 09 20 2a 20 6e 65 78 74 20 6d 61 74 the.. * next mat
bb50: 63 68 69 6e 67 20 6f 6e 65 20 69 6e 20 74 68 65 ching one in the
bb60: 20 70 61 74 74 65 72 6e 2c 20 61 6e 64 20 74 68 pattern, and th
bb70: 65 6e 20 63 61 6c 6c 69 6e 67 20 6f 75 72 73 65 en calling ourse
bb80: 6c 76 65 73 0a 09 20 2a 20 72 65 63 75 72 73 69 lves.. * recursi
bb90: 76 65 6c 79 20 66 6f 72 20 65 61 63 68 20 70 6f vely for each po
bba0: 73 74 66 69 78 20 6f 66 20 73 74 72 69 6e 67 2c stfix of string,
bbb0: 20 75 6e 74 69 6c 20 65 69 74 68 65 72 20 77 65 until either we
bbc0: 20 6d 61 74 63 68 20 6f 72 20 77 65 0a 09 20 2a match or we.. *
bbd0: 20 72 65 61 63 68 20 74 68 65 20 65 6e 64 20 6f reach the end o
bbe0: 66 20 74 68 65 20 73 74 72 69 6e 67 2e 0a 09 20 f the string...
bbf0: 2a 2f 0a 0a 09 69 66 20 28 70 20 3d 3d 20 27 2a */...if (p == '*
bc00: 27 29 20 7b 0a 09 20 20 20 20 2f 2a 0a 09 20 20 ') {.. /*..
bc10: 20 20 20 2a 20 53 6b 69 70 20 61 6c 6c 20 73 75 * Skip all su
bc20: 63 63 65 73 73 69 76 65 20 2a 27 73 20 69 6e 20 ccessive *'s in
bc30: 74 68 65 20 70 61 74 74 65 72 6e 0a 09 20 20 20 the pattern..
bc40: 20 20 2a 2f 0a 0a 09 20 20 20 20 77 68 69 6c 65 */... while
bc50: 20 28 2a 28 2b 2b 75 6e 69 50 61 74 74 65 72 6e (*(++uniPattern
bc60: 29 20 3d 3d 20 27 2a 27 29 20 7b 0a 09 09 2f 2a ) == '*') {.../*
bc70: 20 65 6d 70 74 79 20 62 6f 64 79 20 2a 2f 0a 09 empty body */..
bc80: 20 20 20 20 7d 0a 09 20 20 20 20 70 20 3d 20 2a }.. p = *
bc90: 75 6e 69 50 61 74 74 65 72 6e 3b 0a 09 20 20 20 uniPattern;..
bca0: 20 69 66 20 28 70 20 3d 3d 20 30 29 20 7b 0a 09 if (p == 0) {..
bcb0: 09 72 65 74 75 72 6e 20 31 3b 0a 09 20 20 20 20 .return 1;..
bcc0: 7d 0a 09 20 20 20 20 69 66 20 28 6e 6f 63 61 73 }.. if (nocas
bcd0: 65 29 20 7b 0a 09 09 70 20 3d 20 54 63 6c 5f 55 e) {...p = Tcl_U
bce0: 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 70 29 niCharToLower(p)
bcf0: 3b 0a 09 20 20 20 20 7d 0a 09 20 20 20 20 77 68 ;.. }.. wh
bd00: 69 6c 65 20 28 31 29 20 7b 0a 09 09 2f 2a 0a 09 ile (1) {.../*..
bd10: 09 20 2a 20 4f 70 74 69 6d 69 7a 61 74 69 6f 6e . * Optimization
bd20: 20 66 6f 72 20 6d 61 74 63 68 69 6e 67 20 2d 20 for matching -
bd30: 63 72 75 69 73 65 20 74 68 72 6f 75 67 68 20 74 cruise through t
bd40: 68 65 20 73 74 72 69 6e 67 0a 09 09 20 2a 20 71 he string... * q
bd50: 75 69 63 6b 6c 79 20 69 66 20 74 68 65 20 6e 65 uickly if the ne
bd60: 78 74 20 63 68 61 72 20 69 6e 20 74 68 65 20 70 xt char in the p
bd70: 61 74 74 65 72 6e 20 69 73 6e 27 74 20 61 20 73 attern isn't a s
bd80: 70 65 63 69 61 6c 0a 09 09 20 2a 20 63 68 61 72 pecial... * char
bd90: 61 63 74 65 72 0a 09 09 20 2a 2f 0a 0a 09 09 69 acter... */....i
bda0: 66 20 28 28 70 20 21 3d 20 27 5b 27 29 20 26 26 f ((p != '[') &&
bdb0: 20 28 70 20 21 3d 20 27 3f 27 29 20 26 26 20 28 (p != '?') && (
bdc0: 70 20 21 3d 20 27 5c 5c 27 29 29 20 7b 0a 09 09 p != '\\')) {...
bdd0: 20 20 20 20 69 66 20 28 6e 6f 63 61 73 65 29 20 if (nocase)
bde0: 7b 0a 09 09 09 77 68 69 6c 65 20 28 2a 75 6e 69 {....while (*uni
bdf0: 53 74 72 20 26 26 20 28 70 20 21 3d 20 2a 75 6e Str && (p != *un
be00: 69 53 74 72 29 0a 09 09 09 09 26 26 20 28 70 20 iStr).....&& (p
be10: 21 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f != Tcl_UniCharTo
be20: 4c 6f 77 65 72 28 2a 75 6e 69 53 74 72 29 29 29 Lower(*uniStr)))
be30: 20 7b 0a 09 09 09 20 20 20 20 75 6e 69 53 74 72 {.... uniStr
be40: 2b 2b 3b 0a 09 09 09 7d 0a 09 09 20 20 20 20 7d ++;....}... }
be50: 20 65 6c 73 65 20 7b 0a 09 09 09 77 68 69 6c 65 else {....while
be60: 20 28 2a 75 6e 69 53 74 72 20 26 26 20 28 70 20 (*uniStr && (p
be70: 21 3d 20 2a 75 6e 69 53 74 72 29 29 20 7b 0a 09 != *uniStr)) {..
be80: 09 09 20 20 20 20 75 6e 69 53 74 72 2b 2b 3b 0a .. uniStr++;.
be90: 09 09 09 7d 0a 09 09 20 20 20 20 7d 0a 09 09 7d ...}... }...}
bea0: 0a 09 09 69 66 20 28 54 63 6c 5f 55 6e 69 43 68 ...if (Tcl_UniCh
beb0: 61 72 43 61 73 65 4d 61 74 63 68 28 75 6e 69 53 arCaseMatch(uniS
bec0: 74 72 2c 20 75 6e 69 50 61 74 74 65 72 6e 2c 20 tr, uniPattern,
bed0: 6e 6f 63 61 73 65 29 29 20 7b 0a 09 09 20 20 20 nocase)) {...
bee0: 20 72 65 74 75 72 6e 20 31 3b 0a 09 09 7d 0a 09 return 1;...}..
bef0: 09 69 66 20 28 2a 75 6e 69 53 74 72 20 3d 3d 20 .if (*uniStr ==
bf00: 30 29 20 7b 0a 09 09 20 20 20 20 72 65 74 75 72 0) {... retur
bf10: 6e 20 30 3b 0a 09 09 7d 0a 09 09 75 6e 69 53 74 n 0;...}...uniSt
bf20: 72 2b 2b 3b 0a 09 20 20 20 20 7d 0a 09 7d 0a 0a r++;.. }..}..
bf30: 09 2f 2a 0a 09 20 2a 20 43 68 65 63 6b 20 66 6f ./*.. * Check fo
bf40: 72 20 61 20 22 3f 22 20 61 73 20 74 68 65 20 6e r a "?" as the n
bf50: 65 78 74 20 70 61 74 74 65 72 6e 20 63 68 61 72 ext pattern char
bf60: 61 63 74 65 72 2e 20 49 74 20 6d 61 74 63 68 65 acter. It matche
bf70: 73 20 61 6e 79 0a 09 20 2a 20 73 69 6e 67 6c 65 s any.. * single
bf80: 20 63 68 61 72 61 63 74 65 72 2e 0a 09 20 2a 2f character... */
bf90: 0a 0a 09 69 66 20 28 70 20 3d 3d 20 27 3f 27 29 ...if (p == '?')
bfa0: 20 7b 0a 09 20 20 20 20 75 6e 69 50 61 74 74 65 {.. uniPatte
bfb0: 72 6e 2b 2b 3b 0a 09 20 20 20 20 75 6e 69 53 74 rn++;.. uniSt
bfc0: 72 2b 2b 3b 0a 09 20 20 20 20 63 6f 6e 74 69 6e r++;.. contin
bfd0: 75 65 3b 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 ue;..}.../*.. *
bfe0: 43 68 65 63 6b 20 66 6f 72 20 61 20 22 5b 22 20 Check for a "["
bff0: 61 73 20 74 68 65 20 6e 65 78 74 20 70 61 74 74 as the next patt
c000: 65 72 6e 20 63 68 61 72 61 63 74 65 72 2e 20 49 ern character. I
c010: 74 20 69 73 20 66 6f 6c 6c 6f 77 65 64 20 62 79 t is followed by
c020: 20 61 0a 09 20 2a 20 6c 69 73 74 20 6f 66 20 63 a.. * list of c
c030: 68 61 72 61 63 74 65 72 73 20 74 68 61 74 20 61 haracters that a
c040: 72 65 20 61 63 63 65 70 74 61 62 6c 65 2c 20 6f re acceptable, o
c050: 72 20 62 79 20 61 20 72 61 6e 67 65 20 28 74 77 r by a range (tw
c060: 6f 0a 09 20 2a 20 63 68 61 72 61 63 74 65 72 73 o.. * characters
c070: 20 73 65 70 61 72 61 74 65 64 20 62 79 20 22 2d separated by "-
c080: 22 29 2e 0a 09 20 2a 2f 0a 0a 09 69 66 20 28 70 ")... */...if (p
c090: 20 3d 3d 20 27 5b 27 29 20 7b 0a 09 20 20 20 20 == '[') {..
c0a0: 54 63 6c 5f 55 6e 69 43 68 61 72 20 73 74 61 72 Tcl_UniChar star
c0b0: 74 43 68 61 72 2c 20 65 6e 64 43 68 61 72 3b 0a tChar, endChar;.
c0c0: 0a 09 20 20 20 20 75 6e 69 50 61 74 74 65 72 6e .. uniPattern
c0d0: 2b 2b 3b 0a 09 20 20 20 20 63 68 31 20 3d 20 28 ++;.. ch1 = (
c0e0: 6e 6f 63 61 73 65 20 3f 20 54 63 6c 5f 55 6e 69 nocase ? Tcl_Uni
c0f0: 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a 75 6e 69 CharToLower(*uni
c100: 53 74 72 29 20 3a 20 2a 75 6e 69 53 74 72 29 3b Str) : *uniStr);
c110: 0a 09 20 20 20 20 75 6e 69 53 74 72 2b 2b 3b 0a .. uniStr++;.
c120: 09 20 20 20 20 77 68 69 6c 65 20 28 31 29 20 7b . while (1) {
c130: 0a 09 09 69 66 20 28 28 2a 75 6e 69 50 61 74 74 ...if ((*uniPatt
c140: 65 72 6e 20 3d 3d 20 27 5d 27 29 20 7c 7c 20 28 ern == ']') || (
c150: 2a 75 6e 69 50 61 74 74 65 72 6e 20 3d 3d 20 30 *uniPattern == 0
c160: 29 29 20 7b 0a 09 09 20 20 20 20 72 65 74 75 72 )) {... retur
c170: 6e 20 30 3b 0a 09 09 7d 0a 09 09 73 74 61 72 74 n 0;...}...start
c180: 43 68 61 72 20 3d 20 28 6e 6f 63 61 73 65 20 3f Char = (nocase ?
c190: 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f Tcl_UniCharToLo
c1a0: 77 65 72 28 2a 75 6e 69 50 61 74 74 65 72 6e 29 wer(*uniPattern)
c1b0: 0a 09 09 09 3a 20 2a 75 6e 69 50 61 74 74 65 72 ....: *uniPatter
c1c0: 6e 29 3b 0a 09 09 75 6e 69 50 61 74 74 65 72 6e n);...uniPattern
c1d0: 2b 2b 3b 0a 09 09 69 66 20 28 2a 75 6e 69 50 61 ++;...if (*uniPa
c1e0: 74 74 65 72 6e 20 3d 3d 20 27 2d 27 29 20 7b 0a ttern == '-') {.
c1f0: 09 09 20 20 20 20 75 6e 69 50 61 74 74 65 72 6e .. uniPattern
c200: 2b 2b 3b 0a 09 09 20 20 20 20 69 66 20 28 2a 75 ++;... if (*u
c210: 6e 69 50 61 74 74 65 72 6e 20 3d 3d 20 30 29 20 niPattern == 0)
c220: 7b 0a 09 09 09 72 65 74 75 72 6e 20 30 3b 0a 09 {....return 0;..
c230: 09 20 20 20 20 7d 0a 09 09 20 20 20 20 65 6e 64 . }... end
c240: 43 68 61 72 20 3d 20 28 6e 6f 63 61 73 65 20 3f Char = (nocase ?
c250: 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f Tcl_UniCharToLo
c260: 77 65 72 28 2a 75 6e 69 50 61 74 74 65 72 6e 29 wer(*uniPattern)
c270: 0a 09 09 09 20 20 20 20 3a 20 2a 75 6e 69 50 61 .... : *uniPa
c280: 74 74 65 72 6e 29 3b 0a 09 09 20 20 20 20 75 6e ttern);... un
c290: 69 50 61 74 74 65 72 6e 2b 2b 3b 0a 09 09 20 20 iPattern++;...
c2a0: 20 20 69 66 20 28 28 28 73 74 61 72 74 43 68 61 if (((startCha
c2b0: 72 20 3c 3d 20 63 68 31 29 20 26 26 20 28 63 68 r <= ch1) && (ch
c2c0: 31 20 3c 3d 20 65 6e 64 43 68 61 72 29 29 0a 09 1 <= endChar))..
c2d0: 09 09 20 20 20 20 7c 7c 20 28 28 65 6e 64 43 68 .. || ((endCh
c2e0: 61 72 20 3c 3d 20 63 68 31 29 20 26 26 20 28 63 ar <= ch1) && (c
c2f0: 68 31 20 3c 3d 20 73 74 61 72 74 43 68 61 72 29 h1 <= startChar)
c300: 29 29 20 7b 0a 09 09 09 2f 2a 0a 09 09 09 20 2a )) {..../*.... *
c310: 20 4d 61 74 63 68 65 73 20 72 61 6e 67 65 73 20 Matches ranges
c320: 6f 66 20 66 6f 72 6d 20 5b 61 2d 7a 5d 20 6f 72 of form [a-z] or
c330: 20 5b 7a 2d 61 5d 2e 0a 09 09 09 20 2a 2f 0a 09 [z-a]..... */..
c340: 09 09 62 72 65 61 6b 3b 0a 09 09 20 20 20 20 7d ..break;... }
c350: 0a 09 09 7d 20 65 6c 73 65 20 69 66 20 28 73 74 ...} else if (st
c360: 61 72 74 43 68 61 72 20 3d 3d 20 63 68 31 29 20 artChar == ch1)
c370: 7b 0a 09 09 20 20 20 20 62 72 65 61 6b 3b 0a 09 {... break;..
c380: 09 7d 0a 09 20 20 20 20 7d 0a 09 20 20 20 20 77 .}.. }.. w
c390: 68 69 6c 65 20 28 2a 75 6e 69 50 61 74 74 65 72 hile (*uniPatter
c3a0: 6e 20 21 3d 20 27 5d 27 29 20 7b 0a 09 09 69 66 n != ']') {...if
c3b0: 20 28 2a 75 6e 69 50 61 74 74 65 72 6e 20 3d 3d (*uniPattern ==
c3c0: 20 30 29 20 7b 0a 09 09 20 20 20 20 75 6e 69 50 0) {... uniP
c3d0: 61 74 74 65 72 6e 2d 2d 3b 0a 09 09 20 20 20 20 attern--;...
c3e0: 62 72 65 61 6b 3b 0a 09 09 7d 0a 09 09 75 6e 69 break;...}...uni
c3f0: 50 61 74 74 65 72 6e 2b 2b 3b 0a 09 20 20 20 20 Pattern++;..
c400: 7d 0a 09 20 20 20 20 75 6e 69 50 61 74 74 65 72 }.. uniPatter
c410: 6e 2b 2b 3b 0a 09 20 20 20 20 63 6f 6e 74 69 6e n++;.. contin
c420: 75 65 3b 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 ue;..}.../*.. *
c430: 49 66 20 74 68 65 20 6e 65 78 74 20 70 61 74 74 If the next patt
c440: 65 72 6e 20 63 68 61 72 61 63 74 65 72 20 69 73 ern character is
c450: 20 27 5c 27 2c 20 6a 75 73 74 20 73 74 72 69 70 '\', just strip
c460: 20 6f 66 66 20 74 68 65 20 27 5c 27 20 73 6f 20 off the '\' so
c470: 77 65 0a 09 20 2a 20 64 6f 20 65 78 61 63 74 20 we.. * do exact
c480: 6d 61 74 63 68 69 6e 67 20 6f 6e 20 74 68 65 20 matching on the
c490: 63 68 61 72 61 63 74 65 72 20 74 68 61 74 20 66 character that f
c4a0: 6f 6c 6c 6f 77 73 2e 0a 09 20 2a 2f 0a 0a 09 69 ollows... */...i
c4b0: 66 20 28 70 20 3d 3d 20 27 5c 5c 27 29 20 7b 0a f (p == '\\') {.
c4c0: 09 20 20 20 20 69 66 20 28 2a 28 2b 2b 75 6e 69 . if (*(++uni
c4d0: 50 61 74 74 65 72 6e 29 20 3d 3d 20 27 5c 30 27 Pattern) == '\0'
c4e0: 29 20 7b 0a 09 09 72 65 74 75 72 6e 20 30 3b 0a ) {...return 0;.
c4f0: 09 20 20 20 20 7d 0a 09 7d 0a 0a 09 2f 2a 0a 09 . }..}.../*..
c500: 20 2a 20 54 68 65 72 65 27 73 20 6e 6f 20 73 70 * There's no sp
c510: 65 63 69 61 6c 20 63 68 61 72 61 63 74 65 72 2e ecial character.
c520: 20 4a 75 73 74 20 6d 61 6b 65 20 73 75 72 65 20 Just make sure
c530: 74 68 61 74 20 74 68 65 20 6e 65 78 74 20 62 79 that the next by
c540: 74 65 73 20 6f 66 0a 09 20 2a 20 65 61 63 68 20 tes of.. * each
c550: 73 74 72 69 6e 67 20 6d 61 74 63 68 2e 0a 09 20 string match...
c560: 2a 2f 0a 0a 09 69 66 20 28 6e 6f 63 61 73 65 29 */...if (nocase)
c570: 20 7b 0a 09 20 20 20 20 69 66 20 28 54 63 6c 5f {.. if (Tcl_
c580: 55 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a UniCharToLower(*
c590: 75 6e 69 53 74 72 29 20 21 3d 0a 09 09 20 20 20 uniStr) !=...
c5a0: 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f Tcl_UniCharToLo
c5b0: 77 65 72 28 2a 75 6e 69 50 61 74 74 65 72 6e 29 wer(*uniPattern)
c5c0: 29 20 7b 0a 09 09 72 65 74 75 72 6e 20 30 3b 0a ) {...return 0;.
c5d0: 09 20 20 20 20 7d 0a 09 7d 20 65 6c 73 65 20 69 . }..} else i
c5e0: 66 20 28 2a 75 6e 69 53 74 72 20 21 3d 20 2a 75 f (*uniStr != *u
c5f0: 6e 69 50 61 74 74 65 72 6e 29 20 7b 0a 09 20 20 niPattern) {..
c600: 20 20 72 65 74 75 72 6e 20 30 3b 0a 09 7d 0a 09 return 0;..}..
c610: 75 6e 69 53 74 72 2b 2b 3b 0a 09 75 6e 69 50 61 uniStr++;..uniPa
c620: 74 74 65 72 6e 2b 2b 3b 0a 20 20 20 20 7d 0a 7d ttern++;. }.}
c630: 0a 0c 0a 2f 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d .../*. *--------
c640: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c650: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c660: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c670: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 --------------.
c680: 2a 0a 20 2a 20 54 63 6c 55 6e 69 43 68 61 72 4d *. * TclUniCharM
c690: 61 74 63 68 20 2d 2d 0a 20 2a 0a 20 2a 09 53 65 atch --. *. *.Se
c6a0: 65 20 69 66 20 61 20 70 61 72 74 69 63 75 6c 61 e if a particula
c6b0: 72 20 55 6e 69 63 6f 64 65 20 73 74 72 69 6e 67 r Unicode string
c6c0: 20 6d 61 74 63 68 65 73 20 61 20 70 61 72 74 69 matches a parti
c6d0: 63 75 6c 61 72 20 70 61 74 74 65 72 6e 2e 0a 20 cular pattern..
c6e0: 2a 09 41 6c 6c 6f 77 73 20 63 61 73 65 20 69 6e *.Allows case in
c6f0: 73 65 6e 73 69 74 69 76 69 74 79 2e 20 54 68 69 sensitivity. Thi
c700: 73 20 69 73 20 74 68 65 20 55 6e 69 63 6f 64 65 s is the Unicode
c710: 20 65 71 75 69 76 61 6c 65 6e 74 20 6f 66 20 74 equivalent of t
c720: 68 65 20 63 68 61 72 2a 0a 20 2a 09 54 63 6c 5f he char*. *.Tcl_
c730: 53 74 72 69 6e 67 43 61 73 65 4d 61 74 63 68 2e StringCaseMatch.
c740: 20 54 68 69 73 20 76 61 72 69 61 6e 74 20 6f 66 This variant of
c750: 20 54 63 6c 5f 55 6e 69 43 68 61 72 43 61 73 65 Tcl_UniCharCase
c760: 4d 61 74 63 68 20 75 73 65 73 20 63 6f 75 6e 74 Match uses count
c770: 65 64 0a 20 2a 09 53 74 72 69 6e 67 73 2c 20 73 ed. *.Strings, s
c780: 6f 20 65 6d 62 65 64 64 65 64 20 4e 55 4c 4c 73 o embedded NULLs
c790: 20 61 72 65 20 61 6c 6c 6f 77 65 64 2e 0a 20 2a are allowed.. *
c7a0: 0a 20 2a 20 52 65 73 75 6c 74 73 3a 0a 20 2a 09 . * Results:. *.
c7b0: 54 68 65 20 72 65 74 75 72 6e 20 76 61 6c 75 65 The return value
c7c0: 20 69 73 20 31 20 69 66 20 73 74 72 69 6e 67 20 is 1 if string
c7d0: 6d 61 74 63 68 65 73 20 70 61 74 74 65 72 6e 2c matches pattern,
c7e0: 20 61 6e 64 20 30 20 6f 74 68 65 72 77 69 73 65 and 0 otherwise
c7f0: 2e 20 54 68 65 0a 20 2a 09 6d 61 74 63 68 69 6e . The. *.matchin
c800: 67 20 6f 70 65 72 61 74 69 6f 6e 20 70 65 72 6d g operation perm
c810: 69 74 73 20 74 68 65 20 66 6f 6c 6c 6f 77 69 6e its the followin
c820: 67 20 73 70 65 63 69 61 6c 20 63 68 61 72 61 63 g special charac
c830: 74 65 72 73 20 69 6e 20 74 68 65 0a 20 2a 09 70 ters in the. *.p
c840: 61 74 74 65 72 6e 3a 20 2a 3f 5c 5b 5d 20 28 73 attern: *?\[] (s
c850: 65 65 20 74 68 65 20 6d 61 6e 75 61 6c 20 65 6e ee the manual en
c860: 74 72 79 20 66 6f 72 20 64 65 74 61 69 6c 73 20 try for details
c870: 6f 6e 20 77 68 61 74 20 74 68 65 73 65 20 6d 65 on what these me
c880: 61 6e 29 2e 0a 20 2a 0a 20 2a 20 53 69 64 65 20 an).. *. * Side
c890: 65 66 66 65 63 74 73 3a 0a 20 2a 09 4e 6f 6e 65 effects:. *.None
c8a0: 2e 0a 20 2a 0a 20 2a 2d 2d 2d 2d 2d 2d 2d 2d 2d .. *. *---------
c8b0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c8c0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c8d0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d ----------------
c8e0: 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 2d 0a 20 2a -------------. *
c8f0: 2f 0a 0a 69 6e 74 0a 54 63 6c 55 6e 69 43 68 61 /..int.TclUniCha
c900: 72 4d 61 74 63 68 28 0a 20 20 20 20 63 6f 6e 73 rMatch(. cons
c910: 74 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 2a 73 t Tcl_UniChar *s
c920: 74 72 69 6e 67 2c 09 2f 2a 20 55 6e 69 63 6f 64 tring,./* Unicod
c930: 65 20 53 74 72 69 6e 67 2e 20 2a 2f 0a 20 20 20 e String. */.
c940: 20 69 6e 74 20 73 74 72 4c 65 6e 2c 09 09 09 2f int strLen,.../
c950: 2a 20 4c 65 6e 67 74 68 20 6f 66 20 53 74 72 69 * Length of Stri
c960: 6e 67 20 2a 2f 0a 20 20 20 20 63 6f 6e 73 74 20 ng */. const
c970: 54 63 6c 5f 55 6e 69 43 68 61 72 20 2a 70 61 74 Tcl_UniChar *pat
c980: 74 65 72 6e 2c 09 2f 2a 20 50 61 74 74 65 72 6e tern,./* Pattern
c990: 2c 20 77 68 69 63 68 20 6d 61 79 20 63 6f 6e 74 , which may cont
c9a0: 61 69 6e 20 73 70 65 63 69 61 6c 0a 09 09 09 09 ain special.....
c9b0: 20 2a 20 63 68 61 72 61 63 74 65 72 73 2e 20 2a * characters. *
c9c0: 2f 0a 20 20 20 20 69 6e 74 20 70 74 6e 4c 65 6e /. int ptnLen
c9d0: 2c 09 09 09 2f 2a 20 4c 65 6e 67 74 68 20 6f 66 ,.../* Length of
c9e0: 20 50 61 74 74 65 72 6e 20 2a 2f 0a 20 20 20 20 Pattern */.
c9f0: 69 6e 74 20 6e 6f 63 61 73 65 29 09 09 09 2f 2a int nocase).../*
ca00: 20 30 20 66 6f 72 20 63 61 73 65 20 73 65 6e 73 0 for case sens
ca10: 69 74 69 76 65 2c 20 31 20 66 6f 72 20 69 6e 73 itive, 1 for ins
ca20: 65 6e 73 69 74 69 76 65 20 2a 2f 0a 7b 0a 20 20 ensitive */.{.
ca30: 20 20 63 6f 6e 73 74 20 54 63 6c 5f 55 6e 69 43 const Tcl_UniC
ca40: 68 61 72 20 2a 73 74 72 69 6e 67 45 6e 64 2c 20 har *stringEnd,
ca50: 2a 70 61 74 74 65 72 6e 45 6e 64 3b 0a 20 20 20 *patternEnd;.
ca60: 20 54 63 6c 5f 55 6e 69 43 68 61 72 20 70 3b 0a Tcl_UniChar p;.
ca70: 0a 20 20 20 20 73 74 72 69 6e 67 45 6e 64 20 3d . stringEnd =
ca80: 20 73 74 72 69 6e 67 20 2b 20 73 74 72 4c 65 6e string + strLen
ca90: 3b 0a 20 20 20 20 70 61 74 74 65 72 6e 45 6e 64 ;. patternEnd
caa0: 20 3d 20 70 61 74 74 65 72 6e 20 2b 20 70 74 6e = pattern + ptn
cab0: 4c 65 6e 3b 0a 0a 20 20 20 20 77 68 69 6c 65 20 Len;.. while
cac0: 28 31 29 20 7b 0a 09 2f 2a 0a 09 20 2a 20 53 65 (1) {../*.. * Se
cad0: 65 20 69 66 20 77 65 27 72 65 20 61 74 20 74 68 e if we're at th
cae0: 65 20 65 6e 64 20 6f 66 20 62 6f 74 68 20 74 68 e end of both th
caf0: 65 20 70 61 74 74 65 72 6e 20 61 6e 64 20 74 68 e pattern and th
cb00: 65 20 73 74 72 69 6e 67 2e 20 49 66 20 73 6f 2c e string. If so,
cb10: 0a 09 20 2a 20 77 65 20 73 75 63 63 65 65 64 65 .. * we succeede
cb20: 64 2e 20 49 66 20 77 65 27 72 65 20 61 74 20 74 d. If we're at t
cb30: 68 65 20 65 6e 64 20 6f 66 20 74 68 65 20 70 61 he end of the pa
cb40: 74 74 65 72 6e 20 62 75 74 20 6e 6f 74 20 61 74 ttern but not at
cb50: 20 74 68 65 20 65 6e 64 0a 09 20 2a 20 6f 66 20 the end.. * of
cb60: 74 68 65 20 73 74 72 69 6e 67 2c 20 77 65 20 66 the string, we f
cb70: 61 69 6c 65 64 2e 0a 09 20 2a 2f 0a 0a 09 69 66 ailed... */...if
cb80: 20 28 70 61 74 74 65 72 6e 20 3d 3d 20 70 61 74 (pattern == pat
cb90: 74 65 72 6e 45 6e 64 29 20 7b 0a 09 20 20 20 20 ternEnd) {..
cba0: 72 65 74 75 72 6e 20 28 73 74 72 69 6e 67 20 3d return (string =
cbb0: 3d 20 73 74 72 69 6e 67 45 6e 64 29 3b 0a 09 7d = stringEnd);..}
cbc0: 0a 09 70 20 3d 20 2a 70 61 74 74 65 72 6e 3b 0a ..p = *pattern;.
cbd0: 09 69 66 20 28 28 73 74 72 69 6e 67 20 3d 3d 20 .if ((string ==
cbe0: 73 74 72 69 6e 67 45 6e 64 29 20 26 26 20 28 70 stringEnd) && (p
cbf0: 20 21 3d 20 27 2a 27 29 29 20 7b 0a 09 20 20 20 != '*')) {..
cc00: 20 72 65 74 75 72 6e 20 30 3b 0a 09 7d 0a 0a 09 return 0;..}...
cc10: 2f 2a 0a 09 20 2a 20 43 68 65 63 6b 20 66 6f 72 /*.. * Check for
cc20: 20 61 20 22 2a 22 20 61 73 20 74 68 65 20 6e 65 a "*" as the ne
cc30: 78 74 20 70 61 74 74 65 72 6e 20 63 68 61 72 61 xt pattern chara
cc40: 63 74 65 72 2e 20 49 74 20 6d 61 74 63 68 65 73 cter. It matches
cc50: 20 61 6e 79 0a 09 20 2a 20 73 75 62 73 74 72 69 any.. * substri
cc60: 6e 67 2e 20 57 65 20 68 61 6e 64 6c 65 20 74 68 ng. We handle th
cc70: 69 73 20 62 79 20 73 6b 69 70 70 69 6e 67 20 61 is by skipping a
cc80: 6c 6c 20 74 68 65 20 63 68 61 72 61 63 74 65 72 ll the character
cc90: 73 20 75 70 20 74 6f 20 74 68 65 0a 09 20 2a 20 s up to the.. *
cca0: 6e 65 78 74 20 6d 61 74 63 68 69 6e 67 20 6f 6e next matching on
ccb0: 65 20 69 6e 20 74 68 65 20 70 61 74 74 65 72 6e e in the pattern
ccc0: 2c 20 61 6e 64 20 74 68 65 6e 20 63 61 6c 6c 69 , and then calli
ccd0: 6e 67 20 6f 75 72 73 65 6c 76 65 73 0a 09 20 2a ng ourselves.. *
cce0: 20 72 65 63 75 72 73 69 76 65 6c 79 20 66 6f 72 recursively for
ccf0: 20 65 61 63 68 20 70 6f 73 74 66 69 78 20 6f 66 each postfix of
cd00: 20 73 74 72 69 6e 67 2c 20 75 6e 74 69 6c 20 65 string, until e
cd10: 69 74 68 65 72 20 77 65 20 6d 61 74 63 68 20 6f ither we match o
cd20: 72 20 77 65 0a 09 20 2a 20 72 65 61 63 68 20 74 r we.. * reach t
cd30: 68 65 20 65 6e 64 20 6f 66 20 74 68 65 20 73 74 he end of the st
cd40: 72 69 6e 67 2e 0a 09 20 2a 2f 0a 0a 09 69 66 20 ring... */...if
cd50: 28 70 20 3d 3d 20 27 2a 27 29 20 7b 0a 09 20 20 (p == '*') {..
cd60: 20 20 2f 2a 0a 09 20 20 20 20 20 2a 20 53 6b 69 /*.. * Ski
cd70: 70 20 61 6c 6c 20 73 75 63 63 65 73 73 69 76 65 p all successive
cd80: 20 2a 27 73 20 69 6e 20 74 68 65 20 70 61 74 74 *'s in the patt
cd90: 65 72 6e 2e 0a 09 20 20 20 20 20 2a 2f 0a 0a 09 ern... */...
cda0: 20 20 20 20 77 68 69 6c 65 20 28 2a 28 2b 2b 70 while (*(++p
cdb0: 61 74 74 65 72 6e 29 20 3d 3d 20 27 2a 27 29 20 attern) == '*')
cdc0: 7b 0a 09 09 2f 2a 20 65 6d 70 74 79 20 62 6f 64 {.../* empty bod
cdd0: 79 20 2a 2f 0a 09 20 20 20 20 7d 0a 09 20 20 20 y */.. }..
cde0: 20 69 66 20 28 70 61 74 74 65 72 6e 20 3d 3d 20 if (pattern ==
cdf0: 70 61 74 74 65 72 6e 45 6e 64 29 20 7b 0a 09 09 patternEnd) {...
ce00: 72 65 74 75 72 6e 20 31 3b 0a 09 20 20 20 20 7d return 1;.. }
ce10: 0a 09 20 20 20 20 70 20 3d 20 2a 70 61 74 74 65 .. p = *patte
ce20: 72 6e 3b 0a 09 20 20 20 20 69 66 20 28 6e 6f 63 rn;.. if (noc
ce30: 61 73 65 29 20 7b 0a 09 09 70 20 3d 20 54 63 6c ase) {...p = Tcl
ce40: 5f 55 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 _UniCharToLower(
ce50: 70 29 3b 0a 09 20 20 20 20 7d 0a 09 20 20 20 20 p);.. }..
ce60: 77 68 69 6c 65 20 28 31 29 20 7b 0a 09 09 2f 2a while (1) {.../*
ce70: 0a 09 09 20 2a 20 4f 70 74 69 6d 69 7a 61 74 69 ... * Optimizati
ce80: 6f 6e 20 66 6f 72 20 6d 61 74 63 68 69 6e 67 20 on for matching
ce90: 2d 20 63 72 75 69 73 65 20 74 68 72 6f 75 67 68 - cruise through
cea0: 20 74 68 65 20 73 74 72 69 6e 67 0a 09 09 20 2a the string... *
ceb0: 20 71 75 69 63 6b 6c 79 20 69 66 20 74 68 65 20 quickly if the
cec0: 6e 65 78 74 20 63 68 61 72 20 69 6e 20 74 68 65 next char in the
ced0: 20 70 61 74 74 65 72 6e 20 69 73 6e 27 74 20 61 pattern isn't a
cee0: 20 73 70 65 63 69 61 6c 0a 09 09 20 2a 20 63 68 special... * ch
cef0: 61 72 61 63 74 65 72 2e 0a 09 09 20 2a 2f 0a 0a aracter.... */..
cf00: 09 09 69 66 20 28 28 70 20 21 3d 20 27 5b 27 29 ..if ((p != '[')
cf10: 20 26 26 20 28 70 20 21 3d 20 27 3f 27 29 20 26 && (p != '?') &
cf20: 26 20 28 70 20 21 3d 20 27 5c 5c 27 29 29 20 7b & (p != '\\')) {
cf30: 0a 09 09 20 20 20 20 69 66 20 28 6e 6f 63 61 73 ... if (nocas
cf40: 65 29 20 7b 0a 09 09 09 77 68 69 6c 65 20 28 28 e) {....while ((
cf50: 73 74 72 69 6e 67 20 3c 20 73 74 72 69 6e 67 45 string < stringE
cf60: 6e 64 29 20 26 26 20 28 70 20 21 3d 20 2a 73 74 nd) && (p != *st
cf70: 72 69 6e 67 29 0a 09 09 09 09 26 26 20 28 70 20 ring).....&& (p
cf80: 21 3d 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f != Tcl_UniCharTo
cf90: 4c 6f 77 65 72 28 2a 73 74 72 69 6e 67 29 29 29 Lower(*string)))
cfa0: 20 7b 0a 09 09 09 20 20 20 20 73 74 72 69 6e 67 {.... string
cfb0: 2b 2b 3b 0a 09 09 09 7d 0a 09 09 20 20 20 20 7d ++;....}... }
cfc0: 20 65 6c 73 65 20 7b 0a 09 09 09 77 68 69 6c 65 else {....while
cfd0: 20 28 28 73 74 72 69 6e 67 20 3c 20 73 74 72 69 ((string < stri
cfe0: 6e 67 45 6e 64 29 20 26 26 20 28 70 20 21 3d 20 ngEnd) && (p !=
cff0: 2a 73 74 72 69 6e 67 29 29 20 7b 0a 09 09 09 20 *string)) {....
d000: 20 20 20 73 74 72 69 6e 67 2b 2b 3b 0a 09 09 09 string++;....
d010: 7d 0a 09 09 20 20 20 20 7d 0a 09 09 7d 0a 09 09 }... }...}...
d020: 69 66 20 28 54 63 6c 55 6e 69 43 68 61 72 4d 61 if (TclUniCharMa
d030: 74 63 68 28 73 74 72 69 6e 67 2c 20 73 74 72 69 tch(string, stri
d040: 6e 67 45 6e 64 20 2d 20 73 74 72 69 6e 67 2c 0a ngEnd - string,.
d050: 09 09 09 70 61 74 74 65 72 6e 2c 20 70 61 74 74 ...pattern, patt
d060: 65 72 6e 45 6e 64 20 2d 20 70 61 74 74 65 72 6e ernEnd - pattern
d070: 2c 20 6e 6f 63 61 73 65 29 29 20 7b 0a 09 09 20 , nocase)) {...
d080: 20 20 20 72 65 74 75 72 6e 20 31 3b 0a 09 09 7d return 1;...}
d090: 0a 09 09 69 66 20 28 73 74 72 69 6e 67 20 3d 3d ...if (string ==
d0a0: 20 73 74 72 69 6e 67 45 6e 64 29 20 7b 0a 09 09 stringEnd) {...
d0b0: 20 20 20 20 72 65 74 75 72 6e 20 30 3b 0a 09 09 return 0;...
d0c0: 7d 0a 09 09 73 74 72 69 6e 67 2b 2b 3b 0a 09 20 }...string++;..
d0d0: 20 20 20 7d 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a }..}.../*.. *
d0e0: 20 43 68 65 63 6b 20 66 6f 72 20 61 20 22 3f 22 Check for a "?"
d0f0: 20 61 73 20 74 68 65 20 6e 65 78 74 20 70 61 74 as the next pat
d100: 74 65 72 6e 20 63 68 61 72 61 63 74 65 72 2e 20 tern character.
d110: 49 74 20 6d 61 74 63 68 65 73 20 61 6e 79 0a 09 It matches any..
d120: 20 2a 20 73 69 6e 67 6c 65 20 63 68 61 72 61 63 * single charac
d130: 74 65 72 2e 0a 09 20 2a 2f 0a 0a 09 69 66 20 28 ter... */...if (
d140: 70 20 3d 3d 20 27 3f 27 29 20 7b 0a 09 20 20 20 p == '?') {..
d150: 20 70 61 74 74 65 72 6e 2b 2b 3b 0a 09 20 20 20 pattern++;..
d160: 20 73 74 72 69 6e 67 2b 2b 3b 0a 09 20 20 20 20 string++;..
d170: 63 6f 6e 74 69 6e 75 65 3b 0a 09 7d 0a 0a 09 2f continue;..}.../
d180: 2a 0a 09 20 2a 20 43 68 65 63 6b 20 66 6f 72 20 *.. * Check for
d190: 61 20 22 5b 22 20 61 73 20 74 68 65 20 6e 65 78 a "[" as the nex
d1a0: 74 20 70 61 74 74 65 72 6e 20 63 68 61 72 61 63 t pattern charac
d1b0: 74 65 72 2e 20 49 74 20 69 73 20 66 6f 6c 6c 6f ter. It is follo
d1c0: 77 65 64 20 62 79 20 61 0a 09 20 2a 20 6c 69 73 wed by a.. * lis
d1d0: 74 20 6f 66 20 63 68 61 72 61 63 74 65 72 73 20 t of characters
d1e0: 74 68 61 74 20 61 72 65 20 61 63 63 65 70 74 61 that are accepta
d1f0: 62 6c 65 2c 20 6f 72 20 62 79 20 61 20 72 61 6e ble, or by a ran
d200: 67 65 20 28 74 77 6f 0a 09 20 2a 20 63 68 61 72 ge (two.. * char
d210: 61 63 74 65 72 73 20 73 65 70 61 72 61 74 65 64 acters separated
d220: 20 62 79 20 22 2d 22 29 2e 0a 09 20 2a 2f 0a 0a by "-")... */..
d230: 09 69 66 20 28 70 20 3d 3d 20 27 5b 27 29 20 7b .if (p == '[') {
d240: 0a 09 20 20 20 20 54 63 6c 5f 55 6e 69 43 68 61 .. Tcl_UniCha
d250: 72 20 63 68 31 2c 20 73 74 61 72 74 43 68 61 72 r ch1, startChar
d260: 2c 20 65 6e 64 43 68 61 72 3b 0a 0a 09 20 20 20 , endChar;...
d270: 20 70 61 74 74 65 72 6e 2b 2b 3b 0a 09 20 20 20 pattern++;..
d280: 20 63 68 31 20 3d 20 28 6e 6f 63 61 73 65 20 3f ch1 = (nocase ?
d290: 20 54 63 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f Tcl_UniCharToLo
d2a0: 77 65 72 28 2a 73 74 72 69 6e 67 29 20 3a 20 2a wer(*string) : *
d2b0: 73 74 72 69 6e 67 29 3b 0a 09 20 20 20 20 73 74 string);.. st
d2c0: 72 69 6e 67 2b 2b 3b 0a 09 20 20 20 20 77 68 69 ring++;.. whi
d2d0: 6c 65 20 28 31 29 20 7b 0a 09 09 69 66 20 28 28 le (1) {...if ((
d2e0: 2a 70 61 74 74 65 72 6e 20 3d 3d 20 27 5d 27 29 *pattern == ']')
d2f0: 20 7c 7c 20 28 70 61 74 74 65 72 6e 20 3d 3d 20 || (pattern ==
d300: 70 61 74 74 65 72 6e 45 6e 64 29 29 20 7b 0a 09 patternEnd)) {..
d310: 09 20 20 20 20 72 65 74 75 72 6e 20 30 3b 0a 09 . return 0;..
d320: 09 7d 0a 09 09 73 74 61 72 74 43 68 61 72 20 3d .}...startChar =
d330: 20 28 6e 6f 63 61 73 65 20 3f 20 54 63 6c 5f 55 (nocase ? Tcl_U
d340: 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a 70 niCharToLower(*p
d350: 61 74 74 65 72 6e 29 20 3a 20 2a 70 61 74 74 65 attern) : *patte
d360: 72 6e 29 3b 0a 09 09 70 61 74 74 65 72 6e 2b 2b rn);...pattern++
d370: 3b 0a 09 09 69 66 20 28 2a 70 61 74 74 65 72 6e ;...if (*pattern
d380: 20 3d 3d 20 27 2d 27 29 20 7b 0a 09 09 20 20 20 == '-') {...
d390: 20 70 61 74 74 65 72 6e 2b 2b 3b 0a 09 09 20 20 pattern++;...
d3a0: 20 20 69 66 20 28 70 61 74 74 65 72 6e 20 3d 3d if (pattern ==
d3b0: 20 70 61 74 74 65 72 6e 45 6e 64 29 20 7b 0a 09 patternEnd) {..
d3c0: 09 09 72 65 74 75 72 6e 20 30 3b 0a 09 09 20 20 ..return 0;...
d3d0: 20 20 7d 0a 09 09 20 20 20 20 65 6e 64 43 68 61 }... endCha
d3e0: 72 20 3d 20 28 6e 6f 63 61 73 65 20 3f 20 54 63 r = (nocase ? Tc
d3f0: 6c 5f 55 6e 69 43 68 61 72 54 6f 4c 6f 77 65 72 l_UniCharToLower
d400: 28 2a 70 61 74 74 65 72 6e 29 0a 09 09 09 20 20 (*pattern)....
d410: 20 20 3a 20 2a 70 61 74 74 65 72 6e 29 3b 0a 09 : *pattern);..
d420: 09 20 20 20 20 70 61 74 74 65 72 6e 2b 2b 3b 0a . pattern++;.
d430: 09 09 20 20 20 20 69 66 20 28 28 28 73 74 61 72 .. if (((star
d440: 74 43 68 61 72 20 3c 3d 20 63 68 31 29 20 26 26 tChar <= ch1) &&
d450: 20 28 63 68 31 20 3c 3d 20 65 6e 64 43 68 61 72 (ch1 <= endChar
d460: 29 29 0a 09 09 09 20 20 20 20 7c 7c 20 28 28 65 )).... || ((e
d470: 6e 64 43 68 61 72 20 3c 3d 20 63 68 31 29 20 26 ndChar <= ch1) &
d480: 26 20 28 63 68 31 20 3c 3d 20 73 74 61 72 74 43 & (ch1 <= startC
d490: 68 61 72 29 29 29 20 7b 0a 09 09 09 2f 2a 0a 09 har))) {..../*..
d4a0: 09 09 20 2a 20 4d 61 74 63 68 65 73 20 72 61 6e .. * Matches ran
d4b0: 67 65 73 20 6f 66 20 66 6f 72 6d 20 5b 61 2d 7a ges of form [a-z
d4c0: 5d 20 6f 72 20 5b 7a 2d 61 5d 2e 0a 09 09 09 20 ] or [z-a].....
d4d0: 2a 2f 0a 09 09 09 62 72 65 61 6b 3b 0a 09 09 20 */....break;...
d4e0: 20 20 20 7d 0a 09 09 7d 20 65 6c 73 65 20 69 66 }...} else if
d4f0: 20 28 73 74 61 72 74 43 68 61 72 20 3d 3d 20 63 (startChar == c
d500: 68 31 29 20 7b 0a 09 09 20 20 20 20 62 72 65 61 h1) {... brea
d510: 6b 3b 0a 09 09 7d 0a 09 20 20 20 20 7d 0a 09 20 k;...}.. }..
d520: 20 20 20 77 68 69 6c 65 20 28 2a 70 61 74 74 65 while (*patte
d530: 72 6e 20 21 3d 20 27 5d 27 29 20 7b 0a 09 09 69 rn != ']') {...i
d540: 66 20 28 70 61 74 74 65 72 6e 20 3d 3d 20 70 61 f (pattern == pa
d550: 74 74 65 72 6e 45 6e 64 29 20 7b 0a 09 09 20 20 tternEnd) {...
d560: 20 20 70 61 74 74 65 72 6e 2d 2d 3b 0a 09 09 20 pattern--;...
d570: 20 20 20 62 72 65 61 6b 3b 0a 09 09 7d 0a 09 09 break;...}...
d580: 70 61 74 74 65 72 6e 2b 2b 3b 0a 09 20 20 20 20 pattern++;..
d590: 7d 0a 09 20 20 20 20 70 61 74 74 65 72 6e 2b 2b }.. pattern++
d5a0: 3b 0a 09 20 20 20 20 63 6f 6e 74 69 6e 75 65 3b ;.. continue;
d5b0: 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 49 66 20 ..}.../*.. * If
d5c0: 74 68 65 20 6e 65 78 74 20 70 61 74 74 65 72 6e the next pattern
d5d0: 20 63 68 61 72 61 63 74 65 72 20 69 73 20 27 5c character is '\
d5e0: 27 2c 20 6a 75 73 74 20 73 74 72 69 70 20 6f 66 ', just strip of
d5f0: 66 20 74 68 65 20 27 5c 27 20 73 6f 20 77 65 0a f the '\' so we.
d600: 09 20 2a 20 64 6f 20 65 78 61 63 74 20 6d 61 74 . * do exact mat
d610: 63 68 69 6e 67 20 6f 6e 20 74 68 65 20 63 68 61 ching on the cha
d620: 72 61 63 74 65 72 20 74 68 61 74 20 66 6f 6c 6c racter that foll
d630: 6f 77 73 2e 0a 09 20 2a 2f 0a 0a 09 69 66 20 28 ows... */...if (
d640: 70 20 3d 3d 20 27 5c 5c 27 29 20 7b 0a 09 20 20 p == '\\') {..
d650: 20 20 69 66 20 28 2b 2b 70 61 74 74 65 72 6e 20 if (++pattern
d660: 3d 3d 20 70 61 74 74 65 72 6e 45 6e 64 29 20 7b == patternEnd) {
d670: 0a 09 09 72 65 74 75 72 6e 20 30 3b 0a 09 20 20 ...return 0;..
d680: 20 20 7d 0a 09 7d 0a 0a 09 2f 2a 0a 09 20 2a 20 }..}.../*.. *
d690: 54 68 65 72 65 27 73 20 6e 6f 20 73 70 65 63 69 There's no speci
d6a0: 61 6c 20 63 68 61 72 61 63 74 65 72 2e 20 4a 75 al character. Ju
d6b0: 73 74 20 6d 61 6b 65 20 73 75 72 65 20 74 68 61 st make sure tha
d6c0: 74 20 74 68 65 20 6e 65 78 74 20 62 79 74 65 73 t the next bytes
d6d0: 20 6f 66 0a 09 20 2a 20 65 61 63 68 20 73 74 72 of.. * each str
d6e0: 69 6e 67 20 6d 61 74 63 68 2e 0a 09 20 2a 2f 0a ing match... */.
d6f0: 0a 09 69 66 20 28 6e 6f 63 61 73 65 29 20 7b 0a ..if (nocase) {.
d700: 09 20 20 20 20 69 66 20 28 54 63 6c 5f 55 6e 69 . if (Tcl_Uni
d710: 43 68 61 72 54 6f 4c 6f 77 65 72 28 2a 73 74 72 CharToLower(*str
d720: 69 6e 67 29 20 21 3d 20 54 63 6c 5f 55 6e 69 43 ing) != Tcl_UniC
d730: 68 61 72 54 6f 4c 6f 77 65 72 28 2a 70 61 74 74 harToLower(*patt
d740: 65 72 6e 29 29 20 7b 0a 09 09 72 65 74 75 72 6e ern)) {...return
d750: 20 30 3b 0a 09 20 20 20 20 7d 0a 09 7d 20 65 6c 0;.. }..} el
d760: 73 65 20 69 66 20 28 2a 73 74 72 69 6e 67 20 21 se if (*string !
d770: 3d 20 2a 70 61 74 74 65 72 6e 29 20 7b 0a 09 20 = *pattern) {..
d780: 20 20 20 72 65 74 75 72 6e 20 30 3b 0a 09 7d 0a return 0;..}.
d790: 09 73 74 72 69 6e 67 2b 2b 3b 0a 09 70 61 74 74 .string++;..patt
d7a0: 65 72 6e 2b 2b 3b 0a 20 20 20 20 7d 0a 7d 0a 0c ern++;. }.}..
d7b0: 0a 2f 2a 0a 20 2a 20 4c 6f 63 61 6c 20 56 61 72 ./*. * Local Var
d7c0: 69 61 62 6c 65 73 3a 0a 20 2a 20 6d 6f 64 65 3a iables:. * mode:
d7d0: 20 63 0a 20 2a 20 63 2d 62 61 73 69 63 2d 6f 66 c. * c-basic-of
d7e0: 66 73 65 74 3a 20 34 0a 20 2a 20 66 69 6c 6c 2d fset: 4. * fill-
d7f0: 63 6f 6c 75 6d 6e 3a 20 37 38 0a 20 2a 20 45 6e column: 78. * En
d800: 64 3a 0a 20 2a 2f 0a d:. */.