bracketed comments

Author: manfred-kaiser

README.md

@@ -18,7 +18,8 @@ FEATURES
 
 -   Supports all of the base Sieve spec from RFC 5228, except for
     features still listed under TODO below
-    - multiline strings (since version 0.2.2)
+    -   multiline strings (since version 0.2.2)
+    -   bracketed comments (since version 0.2.4)
 -   Extensions supported:
     -   regex (draft-ietf-sieve-regex-01)
     -   body (RFC 5173)
@@ -72,7 +73,6 @@ TODO
 -   Base spec features not yet implemented:
     -   encoded characters (section 2.4.2.4)
     -   multi-line strings (section 2.4.2)
-    -   bracketed comments (section 2.3)
     -   message uniqueness (section 2.10.3)
     -   envelope test (section 5.4)
     -   handle message loops (section 10)

docs/index.rst

@@ -11,6 +11,7 @@ FEATURES
     features still listed under TODO below
 
     - multiline strings (since version 0.2.2)
+    - bracketed comments (since version 0.2.4)
 
 -   Extensions supported:
 
@@ -76,7 +77,6 @@ TODO
 -   Base spec features not yet implemented:
 
     -   encoded characters (section 2.4.2.4)
-    -   bracketed comments (section 2.3)
     -   message uniqueness (section 2.10.3)
     -   envelope test (section 5.4)
     -   handle message loops (section 10)

sifter/grammar/lexer.py

@@ -47,16 +47,16 @@ def t_HASH_COMMENT(self, t: 'LexToken') -> Optional['LexToken']:
 
     # section 2.3
     def t_BRACKET_COMMENT(self, t: 'LexToken') -> Optional['LexToken']:
-        r'/\*.*\*/'
-        # TODO: Bracketed comments begin with the token "/*" and end with "*/"
+        r'/\*[\r\n\S\s.]*?\*/'
+        # Bracketed comments begin with the token "/*" and end with "*/"
         # outside of a string.  Bracketed comments may span multiple lines.
         # Bracketed comments do not nest.
         return None
 
     # section 2.4.2
     def t_MULTILINE_STRING(self, t: 'LexToken') -> Optional['LexToken']:
         r'text:\s?(?:\#.*)\r?\n(?P<multilinetext>[\r\n\S\s.]*?\r?\n)\.\r?\n'
-        # TODO: For entering larger amounts of text, such as an email message,
+        # For entering larger amounts of text, such as an email message,
         # a multi-line form is allowed.  It starts with the keyword "text:",
         # followed by a CRLF, and ends with the sequence of a CRLF, a single
         # period, and another CRLF.  The CRLF before the final period is

tests/evaluation_4.rules

@@ -2,6 +2,5 @@ require "reject";
 
 if header "from" "coyote@desert.example.org"
   {
-    reject "I do not accept messages from this address."
-;
+    reject "I do not accept messages from this address.";
   }

tests/evaluation_5.rules

@@ -1,8 +1,10 @@
 require "reject";
 
-if header "from" "coyote@desert.example.org"
+#testcomment1
+
+if header "from" "coyote@desert.example.org" # testcomment2
   {
-    reject text: # testcomment
+    reject text: # testcomment3
 I do not accept messages from
 this address.
 ..

tests/evaluation_6.rules

@@ -0,0 +1,10 @@
+require "reject";
+
+if header "from" "coyote@desert.example.org" /*
+This is a comment
+  {
+    reject "not evaluated, because comment.";
+  }
+*/{
+    reject "I do not accept messages from this address.";
+}

tests/test_evaluation.py

@@ -26,6 +26,7 @@ def test_evaulation():
         ("evaluation_3.msg", "evaluation_3.rules", [('keep', None)]),
         ("evaluation_1.msg", "evaluation_4.rules", [('reject', 'I do not accept messages from this address.')]),
         ("evaluation_1.msg", "evaluation_5.rules", [('reject', 'I do not accept messages from\nthis address.\n.\n')]),
+        ("evaluation_1.msg", "evaluation_6.rules", [('reject', 'I do not accept messages from this address.')]),
     )
 
     for messagefile, rulefile, evaluated_rules in EVAL_RESULTS: