PHP  
 PHP: Test and Code Coverage Analysis
downloads | QA | documentation | faq | getting help | mailing lists | reporting bugs | php.net sites | links | my php.net 
 

LTP GCOV extension - code coverage report
Current view: directory - mbstring/oniguruma/enc - utf32_be.c
Test: PHP Code Coverage
Date: 2009-11-19 Instrumented lines: 65
Code covered: 0.0 % Executed lines: 0
Legend: not executed executed

       1                 : /**********************************************************************
       2                 :   utf32_be.c -  Oniguruma (regular expression library)
       3                 : **********************************************************************/
       4                 : /*-
       5                 :  * Copyright (c) 2002-2009  K.Kosako  <sndgk393 AT ybb DOT ne DOT jp>
       6                 :  * All rights reserved.
       7                 :  *
       8                 :  * Redistribution and use in source and binary forms, with or without
       9                 :  * modification, are permitted provided that the following conditions
      10                 :  * are met:
      11                 :  * 1. Redistributions of source code must retain the above copyright
      12                 :  *    notice, this list of conditions and the following disclaimer.
      13                 :  * 2. Redistributions in binary form must reproduce the above copyright
      14                 :  *    notice, this list of conditions and the following disclaimer in the
      15                 :  *    documentation and/or other materials provided with the distribution.
      16                 :  *
      17                 :  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
      18                 :  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
      19                 :  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
      20                 :  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
      21                 :  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
      22                 :  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
      23                 :  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
      24                 :  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
      25                 :  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
      26                 :  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
      27                 :  * SUCH DAMAGE.
      28                 :  */
      29                 : 
      30                 : #include "regenc.h"
      31                 : 
      32                 : static int
      33                 : utf32be_mbc_enc_len(const UChar* p)
      34               0 : {
      35               0 :   return 4;
      36                 : }
      37                 : 
      38                 : static int
      39                 : utf32be_is_mbc_newline(const UChar* p, const UChar* end)
      40               0 : {
      41               0 :   if (p + 3 < end) {
      42               0 :     if (*(p+3) == 0x0a && *(p+2) == 0 && *(p+1) == 0 && *p == 0)
      43               0 :       return 1;
      44                 : #ifdef USE_UNICODE_ALL_LINE_TERMINATORS
      45                 :     if ((*(p+3) == 0x0d || *(p+3) == 0x85)
      46                 :         && *(p+2) == 0 && *(p+1) == 0 && *p == 0x00)
      47                 :       return 1;
      48                 :     if (*(p+2) == 0x20 && (*(p+3) == 0x29 || *(p+3) == 0x28)
      49                 :         && *(p+1) == 0 && *p == 0)
      50                 :       return 1;
      51                 : #endif
      52                 :   }
      53               0 :   return 0;
      54                 : }
      55                 : 
      56                 : static OnigCodePoint
      57                 : utf32be_mbc_to_code(const UChar* p, const UChar* end)
      58               0 : {
      59               0 :   return (OnigCodePoint )(((p[0] * 256 + p[1]) * 256 + p[2]) * 256 + p[3]);
      60                 : }
      61                 : 
      62                 : static int
      63                 : utf32be_code_to_mbclen(OnigCodePoint code)
      64               0 : {
      65               0 :   return 4;
      66                 : }
      67                 : 
      68                 : static int
      69                 : utf32be_code_to_mbc(OnigCodePoint code, UChar *buf)
      70               0 : {
      71               0 :   UChar* p = buf;
      72                 : 
      73               0 :   *p++ = (UChar )((code & 0xff000000) >>24);
      74               0 :   *p++ = (UChar )((code & 0xff0000)   >>16);
      75               0 :   *p++ = (UChar )((code & 0xff00)     >> 8);
      76               0 :   *p++ = (UChar ) (code & 0xff);
      77               0 :   return 4;
      78                 : }
      79                 : 
      80                 : static int
      81                 : utf32be_mbc_to_normalize(OnigAmbigType flag, const UChar** pp, const UChar* end,
      82                 :                          UChar* lower)
      83               0 : {
      84               0 :   const UChar* p = *pp;
      85                 : 
      86               0 :   if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
      87               0 :     p += 3;
      88               0 :     if (end > p + 4 &&
      89                 :         (flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0 &&
      90                 :         ((*p == 's' && *(p+4) == 's') ||
      91                 :         ((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
      92                 :          (*p == 'S' && *(p+4) == 'S'))) &&
      93                 :         *(p+3) == 0 && *(p+2) == 0 && *(p+1) == 0) {
      94               0 :       *lower++ = '\0';
      95               0 :       *lower++ = '\0';
      96               0 :       *lower++ = '\0';
      97               0 :       *lower   = 0xdf;
      98               0 :       (*pp) += 8;
      99               0 :       return 4;
     100                 :     }
     101                 : 
     102               0 :     *lower++ = '\0';
     103               0 :     *lower++ = '\0';
     104               0 :     *lower++ = '\0';
     105               0 :     if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
     106                 :          ONIGENC_IS_MBC_ASCII(p)) ||
     107                 :         ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
     108                 :          !ONIGENC_IS_MBC_ASCII(p))) {
     109               0 :       *lower = ONIGENC_ISO_8859_1_TO_LOWER_CASE(*p);
     110                 :     }
     111                 :     else {
     112               0 :       *lower = *p;
     113                 :     }
     114                 : 
     115               0 :     (*pp) += 4;
     116               0 :     return 4;  /* return byte length of converted char to lower */
     117                 :   }
     118                 :   else {
     119               0 :     int len = 4;
     120               0 :     if (lower != p) {
     121                 :       int i;
     122               0 :       for (i = 0; i < len; i++) {
     123               0 :         *lower++ = *p++;
     124                 :       }
     125                 :     }
     126               0 :     (*pp) += len;
     127               0 :     return len; /* return byte length of converted char to lower */
     128                 :   }
     129                 : }
     130                 : 
     131                 : static int
     132                 : utf32be_is_mbc_ambiguous(OnigAmbigType flag, const UChar** pp, const UChar* end)
     133               0 : {
     134               0 :   const UChar* p = *pp;
     135                 : 
     136               0 :   (*pp) += 4;
     137                 : 
     138               0 :   if (*(p+2) == 0 && *(p+1) == 0 && *p == 0) {
     139                 :     int c, v;
     140                 : 
     141               0 :     p += 3;
     142               0 :     if ((flag & ONIGENC_AMBIGUOUS_MATCH_COMPOUND) != 0) {
     143               0 :       if (end > p + 4 &&
     144                 :           ((*p == 's' && *(p+4) == 's') ||
     145                 :            ((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
     146                 :             (*p == 'S' && *(p+4) == 'S'))) &&
     147                 :           *(p+3) == 0 && *(p+2) == 0 && *(p+1) == 0) {
     148               0 :         (*pp) += 4;
     149               0 :         return TRUE;
     150                 :       }
     151               0 :       else if (*p == 0xdf) {
     152               0 :         return TRUE;
     153                 :       }
     154                 :     }
     155                 : 
     156               0 :     if (((flag & ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE) != 0 &&
     157                 :          ONIGENC_IS_MBC_ASCII(p)) ||
     158                 :         ((flag & ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE) != 0 &&
     159                 :          !ONIGENC_IS_MBC_ASCII(p))) {
     160               0 :       c = *p;
     161               0 :       v = ONIGENC_IS_UNICODE_ISO_8859_1_CTYPE(c,
     162                 :                        (ONIGENC_CTYPE_UPPER | ONIGENC_CTYPE_LOWER));
     163                 :       if ((v | ONIGENC_CTYPE_LOWER) != 0) {
     164                 :         /* 0xaa, 0xb5, 0xba are lower case letter, but can't convert. */
     165               0 :         if (c >= 0xaa && c <= 0xba)
     166               0 :           return FALSE;
     167                 :         else
     168               0 :           return TRUE;
     169                 :       }
     170                 :       return (v != 0 ? TRUE : FALSE);
     171                 :     }
     172                 :   }
     173                 : 
     174               0 :   return FALSE;
     175                 : }
     176                 : 
     177                 : static UChar*
     178                 : utf32be_left_adjust_char_head(const UChar* start, const UChar* s)
     179               0 : {
     180                 :   int rem;
     181                 : 
     182               0 :   if (s <= start) return (UChar* )s;
     183                 : 
     184               0 :   rem = (s - start) % 4;
     185               0 :   return (UChar* )(s - rem);
     186                 : }
     187                 : 
     188                 : OnigEncodingType OnigEncodingUTF32_BE = {
     189                 :   utf32be_mbc_enc_len,
     190                 :   "UTF-32BE",   /* name */
     191                 :   4,            /* max byte length */
     192                 :   4,            /* min byte length */
     193                 :   (ONIGENC_AMBIGUOUS_MATCH_ASCII_CASE |
     194                 :    ONIGENC_AMBIGUOUS_MATCH_NONASCII_CASE |
     195                 :    ONIGENC_AMBIGUOUS_MATCH_COMPOUND),
     196                 :   {
     197                 :       (OnigCodePoint )'\\'                       /* esc */
     198                 :     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar '.'  */
     199                 :     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anytime '*'  */
     200                 :     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* zero or one time '?' */
     201                 :     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* one or more time '+' */
     202                 :     , (OnigCodePoint )ONIG_INEFFECTIVE_META_CHAR /* anychar anytime */
     203                 :   },
     204                 :   utf32be_is_mbc_newline,
     205                 :   utf32be_mbc_to_code,
     206                 :   utf32be_code_to_mbclen,
     207                 :   utf32be_code_to_mbc,
     208                 :   utf32be_mbc_to_normalize,
     209                 :   utf32be_is_mbc_ambiguous,
     210                 :   onigenc_iso_8859_1_get_all_pair_ambig_codes,
     211                 :   onigenc_ess_tsett_get_all_comp_ambig_codes,
     212                 :   onigenc_unicode_is_code_ctype,
     213                 :   onigenc_unicode_get_ctype_code_range,
     214                 :   utf32be_left_adjust_char_head,
     215                 :   onigenc_always_false_is_allowed_reverse_match
     216                 : };

Generated by: LTP GCOV extension version 1.5

Generated at Thu, 19 Nov 2009 08:20:12 +0000 (5 days ago)

Copyright © 2005-2009 The PHP Group
All rights reserved.