diff --git a/docs/syntax.md b/docs/syntax.md
index ed17e66..b3fe6c8 100644
--- a/docs/syntax.md
+++ b/docs/syntax.md
@@ -86,16 +86,29 @@
 This is not specified using formal grammar or language.
 Any ambiguity is accidental.
 
+### Whitespace
+
+Spaces are the following code points:
+
+- U+0009 HORIZONTAL TAB
+- U+0020 SPACE
+
+New lines are the following code points:
+
+- U+000A LINE FEED
+- U+000B VERTICAL TAB
+- U+000C FORM FEED
+- U+000D CARRIAGE RETURN
+- U+0085 NEXT LINE 
+- U+2028 LINE SEPARATOR
+- U+2029 PARAGRAPH SEPARATOR
+
+Both spaces and new lines are treated as whitespace.
+
 ### Tokens
 
 Syntax in NewLang is formed using alphanumeric tokens separated by whitespace.
 
-Whitespace can be the following Unicode code points:
-
-- U+000A LINE FEED
-- U+0009 HORIZONTAL TAB
-- U+0020 SPACE
-
 For example, the following code snippet:
 
 ```
diff --git a/src/tokenize.py b/src/tokenize.py
index 882d00e..ca99da0 100644
--- a/src/tokenize.py
+++ b/src/tokenize.py
@@ -3,23 +3,30 @@
 
 from src.syntax import Syntax, SyntaxLocation, SyntaxType
 
+# Valid space code points
+spaces = [
+    "\t",  # U+0009 HORIZONTAL TAB
+    " ",  # U+0020 SPACE
+]
 
-# Checks whether a symbol is space
-def is_space(symbol):
-    return symbol == " " or symbol == "\t"
-
-
-# Checks whether a symbol is a new line
-def is_newline(symbol):
-    return symbol == "\n"
+# Valid new line tokens
+newlines = [
+    "\n",  # U+000A LINE FEED
+    "\v",  # U+000B VERTICAL TAB
+    "\f",  # U+000C FORM FEED
+    "\r",  # U+000D CARRIAGE RETURN
+    "\u0085",  # U+0085 NEXT LINE
+    "\u2028",  # U+2028 LINE SEPARATOR
+    "\u2029",  # U+2029 PARAGRAPH SEPARATOR
+]
 
 
 # Checks whether a symbol is general whitespace
 def is_whitespace(symbol):
-    return is_space(symbol) or is_newline(symbol)
+    return symbol in spaces or symbol in newlines
 
 
-# Splits text in non-whitespace and whitespace
+# Splits text in to a list of tokens and whitespace
 def split_tokens(input):
     if input == "":
         return []
@@ -54,7 +61,7 @@
         location = SyntaxLocation(line, offset, filename)
         new = Syntax(t.value, location, SyntaxType.TOKEN)
         new_tokens.append(new)
-        if is_newline(t.value):
+        if t.value in newlines:
             line = line + 1
             offset = 1
         else:
diff --git a/tests/test_syntax.py b/tests/test_syntax.py
index 83dc2da..ef32e9a 100644
--- a/tests/test_syntax.py
+++ b/tests/test_syntax.py
@@ -84,10 +84,28 @@
     return Syntax(value, location, SyntaxType.TOKEN)
 
 
+# Values considered spaces
+valid_spaces = [
+    "\t",  # U+0009 HORIZONTAL TAB
+    " ",  # U+0020 SPACE
+]
+
+# Values reserved for new line use
+valid_newlines = [
+    "\n",  # U+000A LINE FEED
+    "\v",  # U+000B VERTICAL TAB
+    "\f",  # U+000C FORM FEED
+    "\r",  # U+000D CARRIAGE RETURN
+    "\u0085",  # U+0085 NEXT LINE
+    "\u2028",  # U+2028 LINE SEPARATOR
+    "\u2029",  # U+2029 PARAGRAPH SEPARATOR
+]
+
+
 # Draws an unknown token
 @composite
 def draw_token_unknown(draw):
-    reserved = " \n\t"
+    reserved = valid_spaces + valid_newlines
     token = draw(draw_token_random())
     chars = characters(blacklist_characters=reserved)
     value = draw(text(alphabet=chars, min_size=1))
@@ -99,9 +117,8 @@
 # Draws a space token
 @composite
 def draw_token_space(draw):
-    space = " \t"
     token = draw(draw_token_random())
-    value = draw(sampled_from(space))
+    value = draw(sampled_from(valid_spaces))
     return Syntax(value, token.location, SyntaxType.TOKEN)
 
 
@@ -109,7 +126,7 @@
 @composite
 def draw_token_newline(draw):
     token = draw(draw_token_random())
-    value = "\n"
+    value = draw(sampled_from(valid_newlines))
     return Syntax(value, token.location, SyntaxType.TOKEN)
 
 
diff --git a/tests/test_tokenize.py b/tests/test_tokenize.py
index 3089c87..f6275e9 100644
--- a/tests/test_tokenize.py
+++ b/tests/test_tokenize.py
@@ -18,6 +18,8 @@
     draw_token_newline,
     draw_token_space,
     draw_token_unknown,
+    valid_spaces,
+    valid_newlines,
 )
 
 
@@ -55,11 +57,21 @@
 
 # Test that the tokenizer can split tokens properly
 # We expect the following behaviour:
-# - Whitespace is a tab, space or new line
+# - Whitespace is any of the following Unicode sequences:
+#   U+0009 HORIZONTAL TAB
+#   U+000A LINE FEED
+#   U+000B VERTICAL TAB
+#   U+000C FORM FEED
+#   U+000D CARRIAGE RETURN
+#   U+000D U+000A CARRIAGE RETURN then LINE FEED
+#   U+0020 SPACE
+#   U+0085 NEXT LINE
+#   U+2028 LINE SEPARATOR
+#   U+2029 PARAGRAPH SEPARATOR
 # - Non-whitespace is anything else
 # - Whitespace and non-whitespace are separated in to tokens
-# - Whitespace characters are split in to multiple tokens
-# - Non-whitespace characters are combined in to a single token
+# - Whitespace sequences are split in to multiple tokens
+# - Non-whitespace code points are combined in to a single token
 # - Each token location is line 1 offset 1 of file ""
 @given(draw_tokens_to_split())
 def test_tokenize_split_tokens(test_data):
@@ -79,7 +91,7 @@
         location = SyntaxLocation(line, offset, filename)
         new = Syntax(t.value, location, SyntaxType.TOKEN)
         located.append(new)
-        if t.value == "\n":
+        if t.value in valid_newlines:
             line = line + 1
             offset = 1
         else:
@@ -89,13 +101,21 @@
 
 # Test that the tokenizer can determine locations
 # We expect the following behaviour:
+# - New line tokens are tokens with one of the following Unicode values:
+#   U+000A LINE FEED
+#   U+000B VERTICAL TAB
+#   U+000C FORM FEED
+#   U+000D CARRIAGE RETURN
+#   U+0085 NEXT LINE
+#   U+2028 LINE SEPARATOR
+#   U+2029 PARAGRAPH SEPARATOR
 # - Only the token location is modified
 # - Each token's location filename is the generated filename
-# - A location's line is equal to 1 plus the number of tokens with the
-#   value '\n' before the token
-# - A location's offset is equal to 1 plus the count of previous token's
-#   value code points 'before' it, where 'before' is defined as any
-#   token between the last '\n' (or start of file) before the token
+# - A token's line is equal to 1 plus the number of new line tokens
+#   before the token
+# - A token's offset is equal to 1 plus the sum of previous token's
+#   value lengths 'before' it, where 'before' is defined as any
+#   token between the last new line token (or start of file) before the token
 #   and the token itself
 @given(draw_tokens_locations())
 def test_tokenize_locations(test_data):
@@ -109,7 +129,9 @@
     input = draw(lists(draw_token_classified()))
     syntax = []
     for s in input:
-        if s.type != SyntaxType.TOKEN or s.value not in ["\t", "\n", " "]:
+        if s.type != SyntaxType.TOKEN or (
+            s.value not in valid_spaces and s.value not in valid_newlines
+        ):
             syntax.append(s)
     return (input, syntax)
 
@@ -120,7 +142,13 @@
 # - Tokens with the following following values are removed from the output:
 #   U+0009 HORIZONTAL TAB
 #   U+000A LINE FEED
+#   U+000B VERTICAL TAB
+#   U+000C FORM FEED
+#   U+000D CARRIAGE RETURN
 #   U+0020 SPACE
+#   U+0085 NEXT LINE
+#   U+2028 LINE SEPARATOR
+#   U+2029 PARAGRAPH SEPARATOR
 @given(draw_tokens_whitespace())
 def test_tokenize_strip_whitespace(test_data):
     (input, syntax) = test_data