Fix is_whitespace guard to include 0x9-0xd

Author: kipcole9

CHANGELOG.md

@@ -1,3 +1,11 @@
+# Changelog for Unicode Guards v0.1.1
+
+This is the changelog for Unicode Guards v0.1.1 released on February 25th, 2020.  For older changelogs please consult the release tag on [GitHub](https://github.com/elixir-unicode/unicode_guards/tags)
+
+### Bug Fixes
+
+* Corrects `is_whitespace/1` to include the expected characters in the range `0x9-0xd`. These comprise carriage return, newline, vertical tab and tab which are commonly considered by regex engines to be whitespace.
+
 # Changelog for Unicode Guards v0.1.0
 
 This is the changelog for Unicode Guards v0.1.0 released on November 23rd, 2019.  For older changelogs please consult the release tag on [GitHub](https://github.com/elixir-unicode/unicode_guards/tags)

lib/unicode_guards.ex

@@ -64,7 +64,21 @@ defmodule Unicode.Guards do
   Guards whether a UTF8 codepoint is a whitespace symbol
   character.
 
+  This includes the Unicode set `Zs` plus the characters in the range `0x9`-`0xd`
+  which incudes tab, newline and carriage return.
+
+  """
+  defguard is_whitespace(codepoint)
+    when is_integer(codepoint) and match?(codepoint, "[[\u0009-\u000d][:Zs:]]")
+
+    @doc """
+  Guards whether a UTF8 codepoint is a unicode separator symbol
+  character.
+
+  This includes the Unicode set `Zs` plus the characters.
+
   """
-  defguard is_whitespace(codepoint) when is_integer(codepoint) and match?(codepoint, "[[:Zs:]]")
+  defguard is_separator(codepoint)
+    when is_integer(codepoint) and match?(codepoint, "[[:Zs:]]")
 
 end

mix.exs

@@ -1,7 +1,7 @@
 defmodule Unicode.Guards.MixProject do
   use Mix.Project
 
-  @version "0.1.0"
+  @version "0.1.1"
 
   def project do
     [

mix.lock

@@ -3,9 +3,9 @@
   "deep_merge": {:hex, :deep_merge, "1.0.0", "b4aa1a0d1acac393bdf38b2291af38cb1d4a52806cf7a4906f718e1feb5ee961", [:mix], [], "hexpm"},
   "earmark": {:hex, :earmark, "1.4.2", "3aa0bd23bc4c61cf2f1e5d752d1bb470560a6f8539974f767a38923bb20e1d7f", [:mix], [], "hexpm"},
   "ex_doc": {:hex, :ex_doc, "0.21.2", "caca5bc28ed7b3bdc0b662f8afe2bee1eedb5c3cf7b322feeeb7c6ebbde089d6", [:mix], [{:earmark, "~> 1.3.3 or ~> 1.4", [hex: :earmark, repo: "hexpm", optional: false]}, {:makeup_elixir, "~> 0.14", [hex: :makeup_elixir, repo: "hexpm", optional: false]}], "hexpm"},
-  "ex_unicode": {:hex, :ex_unicode, "1.1.0", "95e8ed3fb3a3688a365c85a60e2aa79a20426ed3d2ca1516389324f71efca842", [:mix], [], "hexpm"},
+  "ex_unicode": {:hex, :ex_unicode, "1.3.1", "df5fc25569b3437fe98452e002b1463c0f98984a19945debe32c5239e73083d0", [:mix], [], "hexpm"},
   "makeup": {:hex, :makeup, "1.0.0", "671df94cf5a594b739ce03b0d0316aa64312cee2574b6a44becb83cd90fb05dc", [:mix], [{:nimble_parsec, "~> 0.5.0", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm"},
   "makeup_elixir": {:hex, :makeup_elixir, "0.14.0", "cf8b7c66ad1cff4c14679698d532f0b5d45a3968ffbcbfd590339cb57742f1ae", [:mix], [{:makeup, "~> 1.0", [hex: :makeup, repo: "hexpm", optional: false]}], "hexpm"},
-  "nimble_parsec": {:hex, :nimble_parsec, "0.5.2", "1d71150d5293d703a9c38d4329da57d3935faed2031d64bc19e77b654ef2d177", [:mix], [], "hexpm"},
-  "unicode_set": {:hex, :unicode_set, "0.1.0", "d32d23953702baeb89da0486cad22eeb8817bb8050571250248da443ba73983a", [:mix], [{:ex_unicode, "~> 1.1", [hex: :ex_unicode, repo: "hexpm", optional: false]}, {:nimble_parsec, "~> 0.5", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm"},
+  "nimble_parsec": {:hex, :nimble_parsec, "0.5.3", "def21c10a9ed70ce22754fdeea0810dafd53c2db3219a0cd54cf5526377af1c6", [:mix], [], "hexpm"},
+  "unicode_set": {:hex, :unicode_set, "0.4.2", "627e5ffce656dbd652b23115bf91beee7f2348d2a30dda3c66001367144f2d9a", [:mix], [{:ex_unicode, "~> 1.3", [hex: :ex_unicode, repo: "hexpm", optional: false]}, {:nimble_parsec, "~> 0.5", [hex: :nimble_parsec, repo: "hexpm", optional: false]}], "hexpm"},
 }

test/unicode_guards_test.exs

@@ -17,6 +17,9 @@ defmodule Unicode.GuardsTest do
     assert Guards.lower("a") == :lower
     assert Guards.digit("3") == :digit
     assert Guards.whitespace(" ") == :whitespace
+    assert Guards.whitespace("\n") == :whitespace
+    assert Guards.whitespace("\t") == :whitespace
+    assert Guards.whitespace("\r") == :whitespace
     assert Guards.currency("$") == :currency
   end
 end