diff --git a/doc/pcre2jit.3 b/doc/pcre2jit.3 index cc41eec..6b2ada0 100644 --- a/doc/pcre2jit.3 +++ b/doc/pcre2jit.3 @@ -1,4 +1,4 @@ -.TH PCRE2JIT 3 "27 October 2014" "PCRE2 10.00" +.TH PCRE2JIT 3 "02 November 2014" "PCRE2 10.00" .SH NAME PCRE2 - Perl-compatible regular expressions (revised API) .SH "PCRE2 JUST-IN-TIME COMPILER SUPPORT" @@ -349,11 +349,11 @@ processed by \fBpcre2_jit_compile()\fP). The fast path function is called \fBpcre2_jit_match()\fP, and it takes exactly the same arguments as \fBpcre2_match()\fP, plus one additional argument that must either point to a JIT stack or be NULL. In the latter case, if a callback -function has been set up by \fBpcre2_jit_stack_alloc()\fP, it is called. +function has been set up by \fBpcre2_jit_stack_assign()\fP, it is called. Otherwise the system stack is used. The return values are the same as for \fBpcre2_match()\fP, plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial -or complete) is requested that was not compiled. Unsupported option bits are -ignored. +or complete) is requested that was not compiled. Unsupported option bits (for +example, PCRE2_ANCHORED) are ignored. .P When you call \fBpcre2_match()\fP, as well as testing for invalid options, a number of other sanity checks are performed on the arguments. For example, if @@ -386,6 +386,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 27 October 2014 +Last updated: 02 November 2014 Copyright (c) 1997-2014 University of Cambridge. .fi diff --git a/doc/pcre2test.1 b/doc/pcre2test.1 index 04f138a..3977c1e 100644 --- a/doc/pcre2test.1 +++ b/doc/pcre2test.1 @@ -1,4 +1,4 @@ -.TH PCRE2TEST 1 "31 October 2014" "PCRE 10.00" +.TH PCRE2TEST 1 "02 November 2014" "PCRE 10.00" .SH NAME pcre2test - a program for testing Perl-compatible regular expressions. .SH SYNOPSIS @@ -437,6 +437,7 @@ about the pattern: /I info show info about compiled pattern hex pattern is coded in hexadecimal jit[=] use JIT + jitfast use JIT fast path jitverify verify JIT use locale= use this locale memory show memory used @@ -531,6 +532,12 @@ are specified. For more details, see the documentation. See also the \fBjitstack\fP modifier below for a way of setting the size of the JIT stack. .P +If the \fBjitfast\fP modifier is specified, matching is done using the JIT +"fast path" interface (\fBpcre2_jit_match()), which skips some of the sanity +checks that are done by \fBpcre2_match()\fP, and of course does not work when +JIT is not supported. If \fBjitfast\fP is specified without \fBjit\fP, jit=7 is +assumed. +.P If the \fBjitverify\fP modifier is specified, information about the compiled pattern shows whether JIT compilation was or was not successful. If \fBjitverify\fP is specified without \fBjit\fP, jit=7 is assumed. If JIT @@ -847,8 +854,9 @@ current character is CR followed by LF, an advance of two is used. .sp The \fBjitstack\fP modifier provides a way of setting the maximum stack size that is used by the just-in-time optimization code. It is ignored if JIT -optimization is not being used. Providing a stack that is larger than the -default 32K is necessary only for very complicated patterns. +optimization is not being used. The value is a number of kilobytes. Providing a +stack that is larger than the default 32K is necessary only for very +complicated patterns. . . .SS "Setting match and recursion limits" @@ -1165,10 +1173,9 @@ characters. .SH "SEE ALSO" .rs .sp -\fBpcre2\fP(3), \fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcre2api\fP(3), -\fBpcre2callout\fP(3), +\fBpcre2\fP(3), \fBpcre2api\fP(3), \fBpcre2callout\fP(3), \fBpcre2jit\fP, \fBpcre2matching\fP(3), \fBpcre2partial\fP(d), -\fBpcre2pattern\fP(3), \fBpcre2precompile\fP(3). +\fBpcre2pattern\fP(3). . . .SH AUTHOR @@ -1185,6 +1192,6 @@ Cambridge CB2 3QH, England. .rs .sp .nf -Last updated: 31 October 2014 +Last updated: 02 November 2014 Copyright (c) 1997-2014 University of Cambridge. .fi diff --git a/src/pcre2test.c b/src/pcre2test.c index 955de53..0c971c7 100644 --- a/src/pcre2test.c +++ b/src/pcre2test.c @@ -340,12 +340,13 @@ either on a pattern or a data line, so they must all be distinct. */ #define CTL_GLOBAL 0x00001000u #define CTL_HEXPAT 0x00002000u #define CTL_INFO 0x00004000u -#define CTL_JITVERIFY 0x00008000u -#define CTL_MARK 0x00010000u -#define CTL_MEMORY 0x00020000u -#define CTL_PATLEN 0x00040000u -#define CTL_POSIX 0x00080000u -#define CTL_STARTCHAR 0x00100000u +#define CTL_JITFAST 0x00008000u +#define CTL_JITVERIFY 0x00010000u +#define CTL_MARK 0x00020000u +#define CTL_MEMORY 0x00040000u +#define CTL_PATLEN 0x00080000u +#define CTL_POSIX 0x00100000u +#define CTL_STARTCHAR 0x00200000u #define CTL_BSR_SET 0x80000000u /* This is informational */ #define CTL_NL_SET 0x40000000u /* This is informational */ @@ -363,7 +364,6 @@ data line. */ CTL_ALLUSEDTEXT|\ CTL_ALTGLOBAL|\ CTL_GLOBAL|\ - CTL_JITVERIFY|\ CTL_MARK|\ CTL_MEMORY|\ CTL_STARTCHAR) @@ -455,6 +455,7 @@ static modstruct modlist[] = { { "hex", MOD_PAT, MOD_CTL, CTL_HEXPAT, PO(control) }, { "info", MOD_PAT, MOD_CTL, CTL_INFO, PO(control) }, { "jit", MOD_PAT, MOD_IND, 7, PO(jit) }, + { "jitfast", MOD_PAT, MOD_CTL, CTL_JITFAST, PO(control) }, { "jitstack", MOD_DAT, MOD_INT, 0, DO(jitstack) }, { "jitverify", MOD_PAT, MOD_CTL, CTL_JITVERIFY, PO(control) }, { "locale", MOD_PAT, MOD_STR, 0, PO(locale) }, @@ -810,6 +811,17 @@ are supported. */ else if (test_mode == PCRE16_MODE) pcre2_jit_free_unused_memory_16(G(a,16)); \ else pcre2_jit_free_unused_memory_32(G(a,32)) +#define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ + if (test_mode == PCRE8_MODE) \ + a = pcre2_jit_match_8(G(b,8),(PCRE2_SPTR8)c,d,e,f,G(g,8),G(h,8), \ + (pcre2_jit_stack_8 *)i); \ + else if (test_mode == PCRE16_MODE) \ + a = pcre2_jit_match_16(G(b,16),(PCRE2_SPTR16)c,d,e,f,G(g,16),G(h,16), \ + (pcre2_jit_stack_16 *)i); \ + else \ + a = pcre2_jit_match_32(G(b,32),(PCRE2_SPTR32)c,d,e,f,G(g,32),G(h,32), \ + (pcre2_jit_stack_32 *)i) + #define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ if (test_mode == PCRE8_MODE) \ a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_8(b,c,d); \ @@ -1180,6 +1192,14 @@ the three different cases. */ else \ G(pcre2_jit_free_unused_memory_,BITTWO)(G(a,BITTWO)) +#define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ + if (test_mode == G(G(PCRE,BITONE),_MODE)) \ + a = G(pcre2_jit_match_,BITONE)(G(b,BITONE),(G(PCRE2_SPTR,BITONE))c,d,e,f, \ + G(g,BITONE),G(h,BITONE),(G(pcre2_jit_stack_,BITONE) *)i); \ + else \ + a = G(pcre2_jit_match_,BITTWO)(G(b,BITTWO),(G(PCRE2_SPTR,BITTWO))c,d,e,f, \ + G(g,BITTWO),G(h,BITTWO),(G(pcre2_jit_stack_,BITTWO) *)i) + #define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ if (test_mode == G(G(PCRE,BITONE),_MODE)) \ a = (PCRE2_JIT_STACK *)G(pcre2_jit_stack_alloc_,BITONE)(b,c,d); \ @@ -1424,6 +1444,9 @@ the three different cases. */ #define PCRE2_GET_STARTCHAR(a,b) a = pcre2_get_startchar_8(G(b,8)) #define PCRE2_JIT_COMPILE(a,b) pcre2_jit_compile_8(G(a,8),b) #define PCRE2_JIT_FREE_UNUSED_MEMORY(a) pcre2_jit_free_unused_memory_8(G(a,8)) +#define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,(pcre2_jit_stack_8 *)i) \ + a = pcre2_jit_match_8(G(b,8),(PCRE2_SPTR8)c,d,e,f,G(g,8),G(h,8), \ + (pcre2_jit_stack_8 *)i) #define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_8(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ @@ -1500,6 +1523,9 @@ the three different cases. */ #define PCRE2_GET_STARTCHAR(a,b) a = pcre2_get_startchar_16(G(b,16)) #define PCRE2_JIT_COMPILE(a,b) pcre2_jit_compile_16(G(a,16),b) #define PCRE2_JIT_FREE_UNUSED_MEMORY(a) pcre2_jit_free_unused_memory_16(G(a,16)) +#define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ + a = pcre2_jit_match_16(G(b,16),(PCRE2_SPTR16)c,d,e,f,G(g,16),G(h,16), \ + (pcre2_jit_stack_16 *)i) #define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_16(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ @@ -1576,6 +1602,9 @@ the three different cases. */ #define PCRE2_GET_STARTCHAR(a,b) a = pcre2_get_startchar_32(G(b,32)) #define PCRE2_JIT_COMPILE(a,b) pcre2_jit_compile_32(G(a,32),b) #define PCRE2_JIT_FREE_UNUSED_MEMORY(a) pcre2_jit_free_unused_memory_32(G(a,32)) +#define PCRE2_JIT_MATCH(a,b,c,d,e,f,g,h,i) \ + a = pcre2_jit_match_32(G(b,32),(PCRE2_SPTR32)c,d,e,f,G(g,32),G(h,32), \ + (pcre2_jit_stack_32 *)i) #define PCRE2_JIT_STACK_ALLOC(a,b,c,d) \ a = (PCRE2_JIT_STACK *)pcre2_jit_stack_alloc_32(b,c,d); #define PCRE2_JIT_STACK_ASSIGN(a,b,c) \ @@ -3154,7 +3183,7 @@ Returns: nothing static void show_controls(uint32_t controls, const char *before) { -fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", +fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", before, ((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "", ((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "", @@ -3171,6 +3200,7 @@ fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s", ((controls & CTL_GLOBAL) != 0)? " global" : "", ((controls & CTL_HEXPAT) != 0)? " hex" : "", ((controls & CTL_INFO) != 0)? " info" : "", + ((controls & CTL_JITFAST) != 0)? " jitfast" : "", ((controls & CTL_JITVERIFY) != 0)? " jitverify" : "", ((controls & CTL_MARK) != 0)? " mark" : "", ((controls & CTL_MEMORY) != 0)? " memory" : "", @@ -3648,7 +3678,11 @@ patlen = p - buffer - 2; if (!decode_modifiers(p, CTX_PAT, &pat_patctl, NULL)) return PR_SKIP; -if (pat_patctl.jit == 0 && (pat_patctl.control & CTL_JITVERIFY) != 0) +/* Assume full JIT compile for jitverify and/or jitfast if nothing else was +specified. */ + +if (pat_patctl.jit == 0 && + (pat_patctl.control & (CTL_JITVERIFY|CTL_JITFAST)) != 0) pat_patctl.jit = 7; utf = (pat_patctl.options & PCRE2_UTF) != 0; @@ -3959,8 +3993,12 @@ for (;;) PCRE2_SET_RECURSION_LIMIT(dat_context, mid); } - PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, - dat_datctl.options, match_data, dat_context); + if ((pat_patctl.control & CTL_JITFAST) != 0) + PCRE2_JIT_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, + dat_datctl.options, match_data, dat_context, jit_stack); + else + PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, + dat_datctl.options, match_data, dat_context); if (capcount == errnumber) { @@ -4651,8 +4689,12 @@ for (gmatched = 0;; gmatched++) PCRE2_SIZE *ovector; PCRE2_SIZE ovecsave[2]; - jit_was_used = FALSE; ovector = FLD(match_data, ovector); + + /* When matching is via pcre2_match(), we will detect the use of JIT via the + stack callback function. */ + + jit_was_used = (pat_patctl.control & CTL_JITFAST) != 0; /* After the first time round a global loop, save the current ovector[0,1] so that we can check that they do change each time. Otherwise a matching bug @@ -4669,8 +4711,7 @@ for (gmatched = 0;; gmatched++) if (timeitm > 0) { register int i; - clock_t time_taken; - clock_t start_time = clock(); + clock_t start_time, time_taken; if ((dat_datctl.control & CTL_DFA) != 0) { @@ -4681,6 +4722,7 @@ for (gmatched = 0;; gmatched++) } if (dfa_workspace == NULL) dfa_workspace = (int *)malloc(DFA_WS_DIMENSION*sizeof(int)); + start_time = clock(); for (i = 0; i < timeitm; i++) { PCRE2_DFA_MATCH(capcount, compiled_code, pp, ulen, @@ -4688,12 +4730,28 @@ for (gmatched = 0;; gmatched++) dat_context, dfa_workspace, DFA_WS_DIMENSION); } } - else for (i = 0; i < timeitm; i++) + + else if ((pat_patctl.control & CTL_JITFAST) != 0) { - PCRE2_MATCH(capcount, compiled_code, pp, ulen, - dat_datctl.offset, dat_datctl.options | g_notempty, match_data, - dat_context); - } + start_time = clock(); + for (i = 0; i < timeitm; i++) + { + PCRE2_JIT_MATCH(capcount, compiled_code, pp, ulen, + dat_datctl.offset, dat_datctl.options | g_notempty, match_data, + dat_context, jit_stack); + } + } + + else + { + start_time = clock(); + for (i = 0; i < timeitm; i++) + { + PCRE2_MATCH(capcount, compiled_code, pp, ulen, + dat_datctl.offset, dat_datctl.options | g_notempty, match_data, + dat_context); + } + } total_match_time += (time_taken = clock() - start_time); fprintf(outfile, "Match time %.4f milliseconds\n", (((double)time_taken * 1000.0) / (double)timeitm) / @@ -4748,8 +4806,12 @@ for (gmatched = 0;; gmatched++) } else { - PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, - dat_datctl.options | g_notempty, match_data, dat_context); + if ((pat_patctl.control & CTL_JITFAST) != 0) + PCRE2_JIT_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, + dat_datctl.options | g_notempty, match_data, dat_context, jit_stack); + else + PCRE2_MATCH(capcount, compiled_code, pp, ulen, dat_datctl.offset, + dat_datctl.options | g_notempty, match_data, dat_context); if (capcount == 0) { fprintf(outfile, "Matched, but too many substrings\n"); diff --git a/testdata/testinput16 b/testdata/testinput16 index b331b0a..cb8a67c 100644 --- a/testdata/testinput16 +++ b/testdata/testinput16 @@ -22,6 +22,12 @@ ab\=ph xyz +/abcd/jitfast + abcd + ab\=ps + ab\=ph + xyz + /abcd/jit=1 abcd ab\=ps @@ -29,12 +35,25 @@ xyz xyz\=ps +/abcd/jit=1,jitfast + abcd + ab\=ps + ab\=ph + xyz + xyz\=ps + /abcd/jit=2 abcd ab\=ps ab\=ph xyz +/abcd/jit=2,jitfast + abcd + ab\=ps + ab\=ph + xyz + /abcd/jit=3 abcd ab\=ps @@ -108,6 +127,10 @@ /^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/ aabbccddee\=find_limits +/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/jitfast + aabbccddee\=find_limits + aabbccddee\=jitstack=1 + /(a+)*zz/ aaaaaaaaaaaaaz aaaaaaaaaaaaaz\=match_limit=3000 @@ -134,4 +157,16 @@ /(?(R)a*(?1)|((?R))b)/ aaaabcde +# Invalid options disable JIT when called via pcre2_match(), causing the +# match to happen via the interpreter, but for fast JIT invalid options are +# ignored, so an unanchored match happens. + +/abcd/jit + abcd\=anchored + fail abcd\=anchored + +/abcd/jitfast + abcd\=anchored + succeed abcd\=anchored + # End of testinput16 diff --git a/testdata/testoutput16 b/testdata/testoutput16 index 0c02742..1631e9e 100644 --- a/testdata/testoutput16 +++ b/testdata/testoutput16 @@ -38,6 +38,16 @@ Partial match: ab (JIT) xyz No match (JIT) +/abcd/jitfast + abcd + 0: abcd (JIT) + ab\=ps +Partial match: ab (JIT) + ab\=ph +Partial match: ab (JIT) + xyz +No match (JIT) + /abcd/jit=1 abcd 0: abcd (JIT) @@ -50,6 +60,18 @@ No match (JIT) xyz\=ps No match +/abcd/jit=1,jitfast + abcd + 0: abcd (JIT) + ab\=ps +Failed: error -43: bad JIT option + ab\=ph +Failed: error -43: bad JIT option + xyz +No match (JIT) + xyz\=ps +Failed: error -43: bad JIT option + /abcd/jit=2 abcd 0: abcd @@ -60,6 +82,16 @@ Partial match: ab xyz No match +/abcd/jit=2,jitfast + abcd +Failed: error -43: bad JIT option + ab\=ps +Partial match: ab (JIT) + ab\=ph +Failed: error -43: bad JIT option + xyz +Failed: error -43: bad JIT option + /abcd/jit=3 abcd 0: abcd (JIT) @@ -207,6 +239,14 @@ Minimum match limit = 6 2: cc 3: ee +/^(?>(a+))(?>b+)(?>(c+))(?>d+)(?>(e+))/jitfast + aabbccddee\=find_limits +Minimum match limit = 6 + 0: aabbccddee (JIT) + 1: aa + 2: cc + 3: ee + /(a+)*zz/ aaaaaaaaaaaaaz No match (JIT) @@ -261,4 +301,20 @@ Failed: error -44: JIT stack limit reached aaaabcde Failed: error -44: JIT stack limit reached +# Invalid options disable JIT when called via pcre2_match(), causing the +# match to happen via the interpreter, but for fast JIT invalid options are +# ignored, so an unanchored match happens. + +/abcd/jit + abcd\=anchored + 0: abcd + fail abcd\=anchored +No match + +/abcd/jitfast + abcd\=anchored + 0: abcd (JIT) + succeed abcd\=anchored + 0: abcd (JIT) + # End of testinput16