Add a function to escape strings for use in regular expressions

base/exports.jl

@@ -443,6 +443,7 @@ export
     findprev,
     match,
     occursin,
+    regex_escape,
     searchsorted,
     searchsortedfirst,
     searchsortedlast,

base/regex.jl

@@ -449,3 +449,27 @@ function hash(r::Regex, h::UInt)
     h = hash(r.compile_options, h)
     h = hash(r.match_options, h)
 end
+
+## escaping ##
+"""
+    regex_escape(s::AbstractString)
+
+Sanitize a string to make it safe for use in regular expression pattern construction. Any
+regular expression metacharacters are escaped along with whitespace.
+
+# Examples
+```jldoctest
+julia> regex_escape("Bang!")
+"Bang\\!"
+
+julia> regex_escape("  ( [ { . ? *")
+"\\ \\ \\(\\ \\[\\ \\{\\ \\.\\ \\?\\ \\*"
+
+julia> regex_escape("/^[a-z0-9_-]{3,16}\$/")
+"/\\^\\[a\\-z0\\-9_\\-\\]\\{3,16\\}\\\$/"
+```
+"""
+function regex_escape(s::AbstractString)
+    res = replace(s, r"([()[\]{}?*+\-|^\$\\.&~#\s=!<>|:])" => s"\\\1")
+    replace(res, "\0" => "\\0")
+end

doc/src/base/strings.md

@@ -31,6 +31,7 @@ Base.isvalid(::Any, ::Any)
 Base.isvalid(::AbstractString, ::Integer)
 Base.match
 Base.eachmatch
+Base.regex_escape
 Base.isless(::AbstractString, ::AbstractString)
 Base.:(==)(::AbstractString, ::AbstractString)
 Base.cmp(::AbstractString, ::AbstractString)

doc/src/manual/strings.md

@@ -936,6 +936,17 @@ ERROR: syntax: invalid escape sequence
 Triple-quoted regex strings, of the form `r"""..."""`, are also supported (and may be convenient
 for regular expressions containing quotation marks or newlines).
 
+The `regex_escape` function allows you to escape a string for use in constructing a regular
+expression.  All whitespace and PCRE metacharacters are escaped.
+
+```julia-repl
+julia> regex_escape("Bang!")
+"Bang\\!"
+
+julia> regex_escape("  ( [ { . ? *")
+"\\ \\ \\(\\ \\[\\ \\{\\ \\.\\ \\?\\ \\*"
+```
+
 ## [Byte Array Literals](@id man-byte-array-literals)
 
 Another useful non-standard string literal is the byte-array string literal: `b"..."`. This

test/regex.jl

@@ -61,3 +61,16 @@ end
 # 'a' flag to disable UCP
 @test match(r"\w+", "Düsseldorf").match == "Düsseldorf"
 @test match(r"\w+"a, "Düsseldorf").match == "D"
+
+# Test escaping strings for use in regular expressions.  We take some regular expressions and
+# make sure we can construct a regular expression from them that matches the original string.
+test_strings = [
+    ".**",
+    raw"/^[a-z0-9_-]{3,16}$/",
+    raw"/^<([a-z]+)([^<]+)*(?:>(.*)<\/\1>|\s+\/>)$/"
+]
+for s in test_strings
+    r = Regex(string("(", regex_escape(s), ")"))
+    m = match(r, s)
+    @test length(m.captures) == 1
+end