Revert "Enable PCRE UTF-8 validity string checks (JuliaLang#26731)" (J…

…uliaLang#28259) This reverts commit 627173b.
tekverkp · Jul 25, 2018 · 1033b88 · 1033b88
1 parent 68744d9
commit 1033b88
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 18 deletions.
diff --git a/base/regex.jl b/base/regex.jl
@@ -4,8 +4,8 @@
 
 include("pcre.jl")
 
-const DEFAULT_COMPILER_OPTS = PCRE.UTF | PCRE.ALT_BSUX | PCRE.UCP
-const DEFAULT_MATCH_OPTS = zero(UInt32)
+const DEFAULT_COMPILER_OPTS = PCRE.UTF | PCRE.NO_UTF_CHECK | PCRE.ALT_BSUX | PCRE.UCP
+const DEFAULT_MATCH_OPTS = PCRE.NO_UTF_CHECK
 
 mutable struct Regex
  pattern::String

diff --git a/test/regex.jl b/test/regex.jl
@@ -58,22 +58,6 @@ end
 # Proper unicode handling
 @test match(r"∀∀", "∀x∀∀∀").match == "∀∀"
 
-@test_throws ErrorException match(r"a", "\xe2\x88") # 1 byte missing at end
-@test_throws ErrorException match(r"a", "\xe2\x08\x80") # byte 2 top bits not 0x80
-@test_throws ErrorException match(r"a", "\xf8\x89\x89\x80\x80") # 5-byte character is not allowed (RFC 3629)
-@test_throws ErrorException match(r"a", "\xf4\x9f\xbf\xbf") # code points greater than 0x10ffff are not defined
-@test_throws ErrorException match(r"a", "\Udfff") # code points 0xd800-0xdfff are not defined
-@test_throws ErrorException match(r"a", "\xc0\x80") # overlong 2-byte sequence
-@test_throws ErrorException match(r"a", "\xff") # illegal byte (0xfe or 0xff)
-
-@test_throws ErrorException Regex("\xe2\x88") # 1 byte missing at end
-@test_throws ErrorException Regex("\xe2\x08\x80") # byte 2 top bits not 0x80
-@test_throws ErrorException Regex("\xf8\x89\x89\x80\x80") # 5-byte character is not allowed (RFC 3629)
-@test_throws ErrorException Regex("\xf4\x9f\xbf\xbf") # code points greater than 0x10ffff are not defined
-@test_throws ErrorException Regex("\Udfff") # code points 0xd800-0xdfff are not defined
-@test_throws ErrorException Regex("\xc0\x80") # overlong 2-byte sequence
-@test_throws ErrorException Regex("\xff") # illegal byte (0xfe or 0xff)
-
 # 'a' flag to disable UCP
 @test match(r"\w+", "Düsseldorf").match == "Düsseldorf"
 @test match(r"\w+"a, "Düsseldorf").match == "D"