walkero
/
pcre2
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity

Add use_length to pcre2test.

This commit is contained in:
Philip.Hazel 2016-11-04 10:53:43 +00:00
parent fb231d30fe
commit 10f4e45e68
3 changed files with 38 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ChangeLog
View File

@ -147,6 +147,8 @@ obsolete these days and in any case had become very haphazard.
21. Make pcre2test -C list valgrind support when it is enabled. 21. Make pcre2test -C list valgrind support when it is enabled.
22. Add the use_length modifier to pcre2test.
Version 10.22 29-July-2016 Version 10.22 29-July-2016
-------------------------- --------------------------

25
doc/pcre2test.1
View File

@ -1,4 +1,4 @@
.TH PCRE2TEST 1 "02 August 2016" "PCRE 10.23" .TH PCRE2TEST 1 "04 November 2016" "PCRE 10.23"
.SH NAME .SH NAME
pcre2test - a program for testing Perl-compatible regular expressions. pcre2test - a program for testing Perl-compatible regular expressions.
.SH SYNOPSIS .SH SYNOPSIS
@ -580,6 +580,7 @@ about the pattern:
pushcopy push a copy onto the stack pushcopy push a copy onto the stack
stackguard=<number> test the stackguard feature stackguard=<number> test the stackguard feature
tables=[0|1|2] select internal tables tables=[0|1|2] select internal tables
use_length do not zero-terminate the pattern
utf8_input treat input as UTF-8 utf8_input treat input as UTF-8
.sp .sp
The effects of these modifiers are described in the following sections. The effects of these modifiers are described in the following sections.
@ -658,6 +659,18 @@ testing that \fBpcre2_compile()\fP behaves correctly in this case (it uses
default values). default values).
. .
. .
.SS "Specifying the pattern's length"
.rs
.sp
By default, patterns are passed to the compiling functions as zero-terminated
strings. When using the POSIX wrapper API, there is no other option. However,
when using PCRE2's native API, patterns can be passed by length instead of
being zero-terminated. The \fBuse_length\fP modifier causes this to happen.
Using a length happens automatically (whether or not \fBuse_length\fP is set)
when \fBhex\fP is set, because patterns specified in hexadecimal may contain
binary zeros.
.
.
.SS "Specifying pattern characters in hexadecimal" .SS "Specifying pattern characters in hexadecimal"
.rs .rs
.sp .sp
@ -679,10 +692,10 @@ Either single or double quotes may be used. There is no way of including
the delimiter within a substring. The \fBhex\fP and \fBexpand\fP modifiers are the delimiter within a substring. The \fBhex\fP and \fBexpand\fP modifiers are
mutually exclusive. mutually exclusive.
.P .P
By default, \fBpcre2test\fP passes patterns as zero-terminated strings to The POSIX API cannot be used with patterns specified in hexadecimal because
\fBpcre2_compile()\fP, giving the length as PCRE2_ZERO_TERMINATED. However, for they may contain binary zeros, which conflicts with \fBregcomp()\fP's
patterns specified with the \fBhex\fP modifier, the actual length of the requirement for a zero-terminated string. Such patterns are always passed to
pattern is passed. \fBpcre2_compile()\fP as a string with a length, not as zero-terminated.
. .
. .
.SS "Specifying wide characters in 16-bit and 32-bit modes" .SS "Specifying wide characters in 16-bit and 32-bit modes"
@ -1734,6 +1747,6 @@ Cambridge, England.
.rs .rs
.sp .sp
.nf .nf
Last updated: 02 August 2016 Last updated: 04 November 2016
Copyright (c) 1997-2016 University of Cambridge. Copyright (c) 1997-2016 University of Cambridge.
.fi .fi

28
src/pcre2test.c
View File

@ -418,7 +418,7 @@ so many of them that they are split into two fields. */
#define CTL_FULLBINCODE 0x00001000u #define CTL_FULLBINCODE 0x00001000u
#define CTL_GETALL 0x00002000u #define CTL_GETALL 0x00002000u
#define CTL_GLOBAL 0x00004000u #define CTL_GLOBAL 0x00004000u
#define CTL_HEXPAT 0x00008000u #define CTL_HEXPAT 0x00008000u /* Same word as USE_LENGTH */
#define CTL_INFO 0x00010000u #define CTL_INFO 0x00010000u
#define CTL_JITFAST 0x00020000u #define CTL_JITFAST 0x00020000u
#define CTL_JITVERIFY 0x00040000u #define CTL_JITVERIFY 0x00040000u
@ -430,9 +430,10 @@ so many of them that they are split into two fields. */
#define CTL_PUSH 0x01000000u #define CTL_PUSH 0x01000000u
#define CTL_PUSHCOPY 0x02000000u #define CTL_PUSHCOPY 0x02000000u
#define CTL_STARTCHAR 0x04000000u #define CTL_STARTCHAR 0x04000000u
#define CTL_UTF8_INPUT 0x08000000u #define CTL_USE_LENGTH 0x08000000u /* Same word as HEXPAT */
#define CTL_ZERO_TERMINATE 0x10000000u #define CTL_UTF8_INPUT 0x10000000u
/* Spare 0x20000000u */ #define CTL_ZERO_TERMINATE 0x20000000u
#define CTL_NL_SET 0x40000000u /* Informational */ #define CTL_NL_SET 0x40000000u /* Informational */
#define CTL_BSR_SET 0x80000000u /* Informational */ #define CTL_BSR_SET 0x80000000u /* Informational */
@ -620,6 +621,7 @@ static modstruct modlist[] = {
{ "tables", MOD_PAT, MOD_INT, 0, PO(tables_id) }, { "tables", MOD_PAT, MOD_INT, 0, PO(tables_id) },
{ "ucp", MOD_PATP, MOD_OPT, PCRE2_UCP, PO(options) }, { "ucp", MOD_PATP, MOD_OPT, PCRE2_UCP, PO(options) },
{ "ungreedy", MOD_PAT, MOD_OPT, PCRE2_UNGREEDY, PO(options) }, { "ungreedy", MOD_PAT, MOD_OPT, PCRE2_UNGREEDY, PO(options) },
{ "use_length", MOD_PAT, MOD_CTL, CTL_USE_LENGTH, PO(control) },
{ "use_offset_limit", MOD_PAT, MOD_OPT, PCRE2_USE_OFFSET_LIMIT, PO(options) }, { "use_offset_limit", MOD_PAT, MOD_OPT, PCRE2_USE_OFFSET_LIMIT, PO(options) },
{ "utf", MOD_PATP, MOD_OPT, PCRE2_UTF, PO(options) }, { "utf", MOD_PATP, MOD_OPT, PCRE2_UTF, PO(options) },
{ "utf8_input", MOD_PAT, MOD_CTL, CTL_UTF8_INPUT, PO(control) }, { "utf8_input", MOD_PAT, MOD_CTL, CTL_UTF8_INPUT, PO(control) },
@ -649,7 +651,8 @@ static modstruct modlist[] = {
#define PUSH_SUPPORTED_COMPILE_CONTROLS ( \ #define PUSH_SUPPORTED_COMPILE_CONTROLS ( \
CTL_BINCODE|CTL_CALLOUT_INFO|CTL_FULLBINCODE|CTL_HEXPAT|CTL_INFO| \ CTL_BINCODE|CTL_CALLOUT_INFO|CTL_FULLBINCODE|CTL_HEXPAT|CTL_INFO| \
CTL_JITVERIFY|CTL_MEMORY|CTL_PUSH|CTL_PUSHCOPY|CTL_BSR_SET|CTL_NL_SET) CTL_JITVERIFY|CTL_MEMORY|CTL_PUSH|CTL_PUSHCOPY|CTL_BSR_SET|CTL_NL_SET| \
CTL_USE_LENGTH)
#define PUSH_SUPPORTED_COMPILE_CONTROLS2 (0) #define PUSH_SUPPORTED_COMPILE_CONTROLS2 (0)
@ -661,7 +664,7 @@ static modstruct modlist[] = {
/* Controls that are forbidden with #pop or #popcopy. */ /* Controls that are forbidden with #pop or #popcopy. */
#define NOTPOP_CONTROLS (CTL_HEXPAT|CTL_POSIX|CTL_POSIX_NOSUB|CTL_PUSH| \ #define NOTPOP_CONTROLS (CTL_HEXPAT|CTL_POSIX|CTL_POSIX_NOSUB|CTL_PUSH| \
CTL_PUSHCOPY) CTL_PUSHCOPY|CTL_USE_LENGTH)
/* Pattern controls that are mutually exclusive. At present these are all in /* Pattern controls that are mutually exclusive. At present these are all in
the first control word. Note that CTL_POSIX_NOSUB is always accompanied by the first control word. Note that CTL_POSIX_NOSUB is always accompanied by
@ -671,6 +674,7 @@ static uint32_t exclusive_pat_controls[] = {
CTL_POSIX | CTL_HEXPAT, CTL_POSIX | CTL_HEXPAT,
CTL_POSIX | CTL_PUSH, CTL_POSIX | CTL_PUSH,
CTL_POSIX | CTL_PUSHCOPY, CTL_POSIX | CTL_PUSHCOPY,
CTL_POSIX | CTL_USE_LENGTH,
CTL_EXPAND | CTL_HEXPAT }; CTL_EXPAND | CTL_HEXPAT };
/* Data controls that are mutually exclusive. At present these are all in the /* Data controls that are mutually exclusive. At present these are all in the
@ -3681,7 +3685,7 @@ Returns: nothing
static void static void
show_controls(uint32_t controls, uint32_t controls2, const char *before) show_controls(uint32_t controls, uint32_t controls2, 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%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%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
before, before,
((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "", ((controls & CTL_AFTERTEXT) != 0)? " aftertext" : "",
((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "", ((controls & CTL_ALLAFTERTEXT) != 0)? " allaftertext" : "",
@ -3716,6 +3720,7 @@ fprintf(outfile, "%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s
((controls2 & CTL2_SUBSTITUTE_OVERFLOW_LENGTH) != 0)? " substitute_overflow_length" : "", ((controls2 & CTL2_SUBSTITUTE_OVERFLOW_LENGTH) != 0)? " substitute_overflow_length" : "",
((controls2 & CTL2_SUBSTITUTE_UNKNOWN_UNSET) != 0)? " substitute_unknown_unset" : "", ((controls2 & CTL2_SUBSTITUTE_UNKNOWN_UNSET) != 0)? " substitute_unknown_unset" : "",
((controls2 & CTL2_SUBSTITUTE_UNSET_EMPTY) != 0)? " substitute_unset_empty" : "", ((controls2 & CTL2_SUBSTITUTE_UNSET_EMPTY) != 0)? " substitute_unset_empty" : "",
((controls & CTL_USE_LENGTH) != 0)? " use_length" : "",
((controls & CTL_UTF8_INPUT) != 0)? " utf8_input" : "", ((controls & CTL_UTF8_INPUT) != 0)? " utf8_input" : "",
((controls & CTL_ZERO_TERMINATE) != 0)? " zero_terminate" : ""); ((controls & CTL_ZERO_TERMINATE) != 0)? " zero_terminate" : "");
} }
@ -4976,12 +4981,13 @@ switch(errorcode)
} }
/* The pattern is now in pbuffer[8|16|32], with the length in code units in /* The pattern is now in pbuffer[8|16|32], with the length in code units in
patlen. By default, however, we pass a zero-terminated pattern. The length is patlen. By default we pass a zero-terminated pattern, but a length is passed if
passed only if we had a hex pattern. When valgrind is supported, arrange for "use_length" was specified or this is a hex pattern (which might contain binary
the unused part of the buffer to be marked as no access. */ zeros). When valgrind is supported, arrange for the unused part of the buffer
to be marked as no access. */
valgrind_access_length = patlen; valgrind_access_length = patlen;
if ((pat_patctl.control & CTL_HEXPAT) == 0) if ((pat_patctl.control & (CTL_HEXPAT|CTL_USE_LENGTH)) == 0)
{ {
patlen = PCRE2_ZERO_TERMINATED; patlen = PCRE2_ZERO_TERMINATED;
valgrind_access_length += 1; /* For the terminating zero */ valgrind_access_length += 1; /* For the terminating zero */