diff --git a/ChangeLog b/ChangeLog index 6156b24..d276feb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -255,6 +255,10 @@ This lifts a restriction on the number of branches in a group (more than about 38. Add the "-ac" command line option to pcre2test as a synonym for "-pattern auto_callout". +39. In a library with Unicode support, incorrect data was compiled for a +pattern with PCRE2_UCP set without PCRE2_UTF if a class required all wide +characters to match (for example, /[\s[:^ascii:]]/). + Version 10.22 29-July-2016 -------------------------- diff --git a/src/pcre2_compile.c b/src/pcre2_compile.c index 9dc9c98..fce226b 100644 --- a/src/pcre2_compile.c +++ b/src/pcre2_compile.c @@ -4927,9 +4927,13 @@ for (;; pptr++) automatically handled by the use of OP_CLASS or OP_NCLASS, but an explicit range is needed for OP_XCLASS. Setting a flag here causes the range to be generated later when it is known that - OP_XCLASS is required. */ + OP_XCLASS is required. In the 8-bit library this is relevant only in + utf mode, since no wide characters can exist otherwise. */ default: +#if PCRE2_CODE_UNIT_WIDTH == 8 + if (utf) +#endif match_all_or_no_wide_chars |= local_negate; break; } @@ -5217,6 +5221,8 @@ for (;; pptr++) all wide characters (depending on whether the whole class is or is not negated). This requirement is indicated by match_all_or_no_wide_chars being true. We do this by including an explicit range, which works in both cases. + This applies only in UTF and 16-bit and 32-bit non-UTF modes, since there + cannot be any wide characters in 8-bit non-UTF mode. When there *are* properties in a positive UTF-8 or any 16-bit or 32_bit class where \S etc is present without PCRE2_UCP, causing an extended class diff --git a/testdata/testinput10 b/testdata/testinput10 index a1806ae..85d2005 100644 --- a/testdata/testinput10 +++ b/testdata/testinput10 @@ -456,4 +456,6 @@ /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/utf +/[\s[:^ascii:]]/B,ucp + # End of testinput10 diff --git a/testdata/testinput12 b/testdata/testinput12 index 5b29f41..c3b2bfc 100644 --- a/testdata/testinput12 +++ b/testdata/testinput12 @@ -358,4 +358,6 @@ \= Expect no match 123 +/[\s[:^ascii:]]/B,ucp + # End of testinput12 diff --git a/testdata/testoutput10 b/testdata/testoutput10 index 3c35f0b..31b7d00 100644 --- a/testdata/testoutput10 +++ b/testdata/testoutput10 @@ -1567,4 +1567,12 @@ No match /(*:*++++++++++++''''''''''''''''''''+''+++'+++x+++++++++++++++++++++++++++++++++++(++++++++++++++++++++:++++++%++:''''''''''''''''''''''''+++++++++++++++++++++++++++++++++++++++++++++++++++++-++++++++k+++++++''''+++'+++++++++++++++++++++++''''++++++++++++':ƿ)/utf Failed: error 176 at offset 259: name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) +/[\s[:^ascii:]]/B,ucp +------------------------------------------------------------------ + Bra + [\x80-\xff\p{Xsp}] + Ket + End +------------------------------------------------------------------ + # End of testinput10 diff --git a/testdata/testoutput12-16 b/testdata/testoutput12-16 index f0f2230..3b5a0cd 100644 --- a/testdata/testoutput12-16 +++ b/testdata/testoutput12-16 @@ -1407,4 +1407,12 @@ Subject length lower bound = 2 123 No match +/[\s[:^ascii:]]/B,ucp +------------------------------------------------------------------ + Bra + [\x80-\xff\p{Xsp}\x{100}-\x{ffff}] + Ket + End +------------------------------------------------------------------ + # End of testinput12 diff --git a/testdata/testoutput12-32 b/testdata/testoutput12-32 index 3718b27..1496159 100644 --- a/testdata/testoutput12-32 +++ b/testdata/testoutput12-32 @@ -1401,4 +1401,12 @@ Failed: error -28: UTF-32 error: code points greater than 0x10ffff are not defin 123 No match +/[\s[:^ascii:]]/B,ucp +------------------------------------------------------------------ + Bra + [\x80-\xff\p{Xsp}\x{100}-\x{ffffffff}] + Ket + End +------------------------------------------------------------------ + # End of testinput12