bugfix for regex matches ending with non-ASCII (#26831)

Ref #26831 (cherry picked from commit aed8a84)
JuliaLang · Apr 27, 2018 · 9aedbcb · 9aedbcb
1 parent 17b5f3a
commit 9aedbcb
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/base/regex.jl b/base/regex.jl
@@ -335,7 +335,7 @@ function next(itr::RegexMatchIterator, prev_match)
             offset = prev_match.offset
         end
     else
-        offset = prev_match.offset + endof(prev_match.match)
+        offset = prev_match.offset + sizeof(prev_match.match)
     end
 
     opts_nonempty = UInt32(PCRE.ANCHORED | PCRE.NOTEMPTY_ATSTART)

diff --git a/test/regex.jl b/test/regex.jl
@@ -26,6 +26,14 @@ target = """71.163.72.113 - - [30/Jul/2014:16:40:55 -0700] "GET emptymind.org/th
 pat = r"""([\d\.]+) ([\w.-]+) ([\w.-]+) (\[.+\]) "([^"\r\n]*|[^"\r\n\[]*\[.+\][^"]+|[^"\r\n]+.[^"]+)" (\d{3}) (\d+|-) ("(?:[^"]|\")+)"? ("(?:[^"]|\")+)"?"""
 match(pat, target)
 
+# issue #26829
+@test map(m -> m.match, eachmatch(r"^$|\S", "ö")) == ["ö"]
+
+# issue #26199
+@test map(m -> m.match, eachmatch(r"(\p{L}+)", "Tú")) == ["Tú"]
+@test map(m -> m.match, eachmatch(r"(\p{L}+)", "Tú lees.")) == ["Tú", "lees"]
+@test map(m -> m.match, eachmatch(r"(\p{L}+)", "¿Cuál es tu pregunta?")) == ["Cuál", "es", "tu", "pregunta"]
+
 # Issue 9545 (32 bit)
 buf = PipeBuffer()
 show(buf, r"")