Add set literals (closes #827)

docs/tutorial.rst

@@ -198,6 +198,8 @@ Hy.  Let's experiment with this in the hy interpreter::
   {'dog': 'bark', 'cat': 'meow'}
   => (, 1 2 3)
   (1, 2, 3)
+  => #{3 1 2}
+  {1, 2, 3}
 
 If you are familiar with other Lisps, you may be interested that Hy
 supports the Common Lisp method of quoting:

hy/__init__.py

@@ -31,6 +31,7 @@
 from hy.models.float import HyFloat  # NOQA
 from hy.models.dict import HyDict  # NOQA
 from hy.models.list import HyList  # NOQA
+from hy.models.set import HySet  # NOQA
 from hy.models.cons import HyCons  # NOQA
 
 

hy/compiler.py

@@ -32,6 +32,7 @@
 from hy.models.symbol import HySymbol
 from hy.models.float import HyFloat
 from hy.models.list import HyList
+from hy.models.set import HySet
 from hy.models.dict import HyDict
 from hy.models.cons import HyCons
 
@@ -628,7 +629,7 @@ def _render_quoted_form(self, form, level):
         name = form.__class__.__name__
         imports = set([name])
 
-        if isinstance(form, (HyList, HyDict)):
+        if isinstance(form, (HyList, HyDict, HySet)):
             if not form:
                 contents = HyList()
             else:
@@ -1974,6 +1975,31 @@ def compile_list(self, expression):
                         col_offset=expression.start_column)
         return ret
 
+    @builds(HySet)
+    def compile_set(self, expression):
+        elts, ret, _ = self._compile_collect(expression)
+        if PY27:
+            ret += ast.Set(elts=elts,
+                           ctx=ast.Load(),
+                           lineno=expression.start_line,
+                           col_offset=expression.start_column)
+        else:
+            ret += ast.Call(func=ast.Name(id='set',
+                                          ctx=ast.Load(),
+                                          lineno=expression.start_line,
+                                          col_offset=expression.start_column),
+                            args=[
+                                ast.List(elts=elts,
+                                         ctx=ast.Load(),
+                                         lineno=expression.start_line,
+                                         col_offset=expression.start_column)],
+                            keywords=[],
+                            starargs=None,
+                            kwargs=None,
+                            lineno=expression.start_line,
+                            col_offset=expression.start_column)
+        return ret
+
     @builds("lambda")
     @builds("fn")
     @checkargs(min=1)

hy/lex/lexer.py

@@ -35,12 +35,13 @@
 lg.add('RBRACKET', r'\]')
 lg.add('LCURLY', r'\{')
 lg.add('RCURLY', r'\}')
+lg.add('HLCURLY', r'#\{')
 lg.add('QUOTE', r'\'%s' % end_quote)
 lg.add('QUASIQUOTE', r'`%s' % end_quote)
 lg.add('UNQUOTESPLICE', r'~@%s' % end_quote)
 lg.add('UNQUOTE', r'~%s' % end_quote)
 lg.add('HASHBANG', r'#!.*[^\r\n]')
-lg.add('HASHREADER', r'#.')
+lg.add('HASHREADER', r'#[^{]')
 
 # A regexp which matches incomplete strings, used to support
 # multi-line strings in the interpreter

hy/lex/parser.py

@@ -31,6 +31,7 @@
 from hy.models.integer import HyInteger
 from hy.models.keyword import HyKeyword
 from hy.models.list import HyList
+from hy.models.set import HySet
 from hy.models.string import HyString
 from hy.models.symbol import HySymbol
 
@@ -152,6 +153,7 @@ def list_contents_single(p):
 @pg.production("term : paren")
 @pg.production("term : dict")
 @pg.production("term : list")
+@pg.production("term : set")
 @pg.production("term : string")
 def term(p):
     return p[0]
@@ -190,6 +192,18 @@ def hash_reader(p):
     return HyExpression([HySymbol("dispatch_reader_macro"), str_object, expr])
 
 
+@pg.production("set : HLCURLY list_contents RCURLY")
+@set_boundaries
+def t_set(p):
+    return HySet(p[1])
+
+
+@pg.production("set : HLCURLY RCURLY")
+@set_boundaries
+def empty_set(p):
+    return HySet([])
+
+
 @pg.production("dict : LCURLY list_contents RCURLY")
 @set_boundaries
 def t_dict(p):

hy/models/set.py

@@ -0,0 +1,36 @@
+# Copyright (c) 2013 Paul Tagliamonte <paultag@debian.org>
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+# FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+# DEALINGS IN THE SOFTWARE.
+
+from hy.models.list import HyList
+from functools import reduce
+
+
+class HySet(HyList):
+    """
+    Hy set (actually a list that pretends to be a set)
+    """
+
+    def __init__(self, items):
+        items = sorted(items)
+        items = list(reduce(lambda r, v: v in r and r or r+[v], items, []))
+        super(HySet, self).__init__(items)
+
+    def __repr__(self):
+        return "#{%s}" % (" ".join([repr(x) for x in self]))

tests/lex/test_lex.py

@@ -27,6 +27,7 @@
 from hy.models.string import HyString
 from hy.models.dict import HyDict
 from hy.models.list import HyList
+from hy.models.set import HySet
 from hy.models.cons import HyCons
 
 from hy.lex import LexException, PrematureEndOfInput, tokenize
@@ -202,6 +203,21 @@ def test_dicts():
     ])]
 
 
+def test_sets():
+    """ Ensure that we can tokenize a set. """
+    objs = tokenize("#{1 2}")
+    assert objs == [HySet([HyInteger(1), HyInteger(2)])]
+    objs = tokenize("(bar #{foo bar baz})")
+    assert objs == [HyExpression([HySymbol("bar"),
+                                  HySet(["foo", "bar", "baz"])])]
+
+    objs = tokenize("#{(foo bar) (baz quux)}")
+    assert objs == [HySet([
+        HyExpression([HySymbol("foo"), HySymbol("bar")]),
+        HyExpression([HySymbol("baz"), HySymbol("quux")])
+    ])]
+
+
 def test_nospace():
     """ Ensure we can tokenize without spaces if we have to """
     entry = tokenize("(foo(one two))")[0]

tests/models/test_set.py

@@ -0,0 +1,8 @@
+from hy.models.set import HySet
+
+
+hyset = HySet([3, 1, 2, 2])
+
+
+def test_set():
+    assert hyset == [1, 2, 3]

tests/native_tests/language.hy

@@ -23,6 +23,12 @@
   (assert (= {1 2 3 4} {1 (+ 1 1) 3 (+ 2 2)})))
 
 
+(defn test-sets []
+  "NATIVE: test sets work right"
+  (assert (= #{1 2 3 4} (| #{1 2} #{3 4})))
+  (assert (= #{} (set))))
+
+
 (defn test-setv-get []
   "NATIVE: test setv works on a get expression"
   (setv foo [0 1 2])