version 1.1.1.3, 2012/10/09 09:19:17
|
version 1.1.1.4, 2013/07/22 08:25:55
|
Line 58 the definition is next to the definition of the opcode
|
Line 58 the definition is next to the definition of the opcode
|
|
|
const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; |
const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS }; |
|
|
|
/* Tables of horizontal and vertical whitespace characters, suitable for |
|
adding to classes. */ |
|
|
|
const pcre_uint32 PRIV(hspace_list)[] = { HSPACE_LIST }; |
|
const pcre_uint32 PRIV(vspace_list)[] = { VSPACE_LIST }; |
|
|
|
|
|
|
/************************************************* |
/************************************************* |
* Tables for UTF-8 support * |
* Tables for UTF-8 support * |
*************************************************/ |
*************************************************/ |
Line 68 const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
|
Line 74 const pcre_uint8 PRIV(OP_lengths)[] = { OP_LENGTHS };
|
character. */ |
character. */ |
|
|
#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ |
#if (defined SUPPORT_UTF && defined COMPILE_PCRE8) \ |
|| (defined PCRE_INCLUDED && defined SUPPORT_PCRE16) | || (defined PCRE_INCLUDED && (defined SUPPORT_PCRE16 || defined SUPPORT_PCRE32)) |
|
|
/* These tables are also required by pcretest in 16 bit mode. */ | /* These tables are also required by pcretest in 16- or 32-bit mode. */ |
|
|
const int PRIV(utf8_table1)[] = |
const int PRIV(utf8_table1)[] = |
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; |
{ 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; |
Line 92 const pcre_uint8 PRIV(utf8_table4)[] = {
|
Line 98 const pcre_uint8 PRIV(utf8_table4)[] = {
|
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, |
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; |
3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; |
|
|
#endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE16)*/ | #endif /* (SUPPORT_UTF && COMPILE_PCRE8) || (PCRE_INCLUDED && SUPPORT_PCRE[16|32])*/ |
|
|
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
|
|
/* Table to translate from particular type value to the general value. */ |
/* Table to translate from particular type value to the general value. */ |
|
|
const int PRIV(ucp_gentype)[] = { | const pcre_uint32 PRIV(ucp_gentype)[] = { |
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ |
ucp_C, ucp_C, ucp_C, ucp_C, ucp_C, /* Cc, Cf, Cn, Co, Cs */ |
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ |
ucp_L, ucp_L, ucp_L, ucp_L, ucp_L, /* Ll, Lu, Lm, Lo, Lt */ |
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ |
ucp_M, ucp_M, ucp_M, /* Mc, Me, Mn */ |
Line 109 const int PRIV(ucp_gentype)[] = {
|
Line 115 const int PRIV(ucp_gentype)[] = {
|
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ |
ucp_Z, ucp_Z, ucp_Z /* Zl, Zp, Zs */ |
}; |
}; |
|
|
|
/* This table encodes the rules for finding the end of an extended grapheme |
|
cluster. Every code point has a grapheme break property which is one of the |
|
ucp_gbXX values defined in ucp.h. The 2-dimensional table is indexed by the |
|
properties of two adjacent code points. The left property selects a word from |
|
the table, and the right property selects a bit from that word like this: |
|
|
|
ucp_gbtable[left-property] & (1 << right-property) |
|
|
|
The value is non-zero if a grapheme break is NOT permitted between the relevant |
|
two code points. The breaking rules are as follows: |
|
|
|
1. Break at the start and end of text (pretty obviously). |
|
|
|
2. Do not break between a CR and LF; otherwise, break before and after |
|
controls. |
|
|
|
3. Do not break Hangul syllable sequences, the rules for which are: |
|
|
|
L may be followed by L, V, LV or LVT |
|
LV or V may be followed by V or T |
|
LVT or T may be followed by T |
|
|
|
4. Do not break before extending characters. |
|
|
|
The next two rules are only for extended grapheme clusters (but that's what we |
|
are implementing). |
|
|
|
5. Do not break before SpacingMarks. |
|
|
|
6. Do not break after Prepend characters. |
|
|
|
7. Otherwise, break everywhere. |
|
*/ |
|
|
|
const pcre_uint32 PRIV(ucp_gbtable[]) = { |
|
(1<<ucp_gbLF), /* 0 CR */ |
|
0, /* 1 LF */ |
|
0, /* 2 Control */ |
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 3 Extend */ |
|
(1<<ucp_gbExtend)|(1<<ucp_gbPrepend)| /* 4 Prepend */ |
|
(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| |
|
(1<<ucp_gbV)|(1<<ucp_gbT)|(1<<ucp_gbLV)| |
|
(1<<ucp_gbLVT)|(1<<ucp_gbOther), |
|
|
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark), /* 5 SpacingMark */ |
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbL)| /* 6 L */ |
|
(1<<ucp_gbL)|(1<<ucp_gbV)|(1<<ucp_gbLV)|(1<<ucp_gbLVT), |
|
|
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 7 V */ |
|
(1<<ucp_gbT), |
|
|
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 8 T */ |
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbV)| /* 9 LV */ |
|
(1<<ucp_gbT), |
|
|
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark)|(1<<ucp_gbT), /* 10 LVT */ |
|
(1<<ucp_gbRegionalIndicator), /* 11 RegionalIndicator */ |
|
(1<<ucp_gbExtend)|(1<<ucp_gbSpacingMark) /* 12 Other */ |
|
}; |
|
|
#ifdef SUPPORT_JIT |
#ifdef SUPPORT_JIT |
/* This table reverses PRIV(ucp_gentype). We can save the cost |
/* This table reverses PRIV(ucp_gentype). We can save the cost |
of a memory load. */ |
of a memory load. */ |
Line 280 strings to make sure that UTF-8 support works on EBCDI
|
Line 346 strings to make sure that UTF-8 support works on EBCDI
|
#define STRING_Xan0 STR_X STR_a STR_n "\0" |
#define STRING_Xan0 STR_X STR_a STR_n "\0" |
#define STRING_Xps0 STR_X STR_p STR_s "\0" |
#define STRING_Xps0 STR_X STR_p STR_s "\0" |
#define STRING_Xsp0 STR_X STR_s STR_p "\0" |
#define STRING_Xsp0 STR_X STR_s STR_p "\0" |
|
#define STRING_Xuc0 STR_X STR_u STR_c "\0" |
#define STRING_Xwd0 STR_X STR_w STR_d "\0" |
#define STRING_Xwd0 STR_X STR_w STR_d "\0" |
#define STRING_Yi0 STR_Y STR_i "\0" |
#define STRING_Yi0 STR_Y STR_i "\0" |
#define STRING_Z0 STR_Z "\0" |
#define STRING_Z0 STR_Z "\0" |
Line 427 const char PRIV(utt_names)[] =
|
Line 494 const char PRIV(utt_names)[] =
|
STRING_Xan0 |
STRING_Xan0 |
STRING_Xps0 |
STRING_Xps0 |
STRING_Xsp0 |
STRING_Xsp0 |
|
STRING_Xuc0 |
STRING_Xwd0 |
STRING_Xwd0 |
STRING_Yi0 |
STRING_Yi0 |
STRING_Z0 |
STRING_Z0 |
Line 574 const ucp_type_table PRIV(utt)[] = {
|
Line 642 const ucp_type_table PRIV(utt)[] = {
|
{ 1011, PT_ALNUM, 0 }, |
{ 1011, PT_ALNUM, 0 }, |
{ 1015, PT_PXSPACE, 0 }, |
{ 1015, PT_PXSPACE, 0 }, |
{ 1019, PT_SPACE, 0 }, |
{ 1019, PT_SPACE, 0 }, |
{ 1023, PT_WORD, 0 }, | { 1023, PT_UCNC, 0 }, |
{ 1027, PT_SC, ucp_Yi }, | { 1027, PT_WORD, 0 }, |
{ 1030, PT_GC, ucp_Z }, | { 1031, PT_SC, ucp_Yi }, |
{ 1032, PT_PC, ucp_Zl }, | { 1034, PT_GC, ucp_Z }, |
{ 1035, PT_PC, ucp_Zp }, | { 1036, PT_PC, ucp_Zl }, |
{ 1038, PT_PC, ucp_Zs } | { 1039, PT_PC, ucp_Zp }, |
| { 1042, PT_PC, ucp_Zs } |
}; |
}; |
|
|
const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table); |
const int PRIV(utt_size) = sizeof(PRIV(utt)) / sizeof(ucp_type_table); |