list comprehensions. see

http://sourceforge.net/patch/?func=detailpatch&patch_id=100654&group_id=5470

for details.

Doc/ref/ref5.tex

@@ -152,13 +152,22 @@ A list display is a possibly empty series of expressions enclosed in
 square brackets:
 
 \begin{verbatim}
-list_display:   "[" [expression_list] "]"
+list_display:   "[" [expression_list [list_iter]] "]"
+list_iter:   list_for | list_if
+list_for:    "for" expression_list "in" testlist [list_iter]
+list_if:     "if" test [list_iter]
 \end{verbatim}
 
-A list display yields a new list object.  If it has no expression
-list, the list object has no items.  Otherwise, the elements of the
-expression list are evaluated from left to right and inserted in the
-list object in that order.
+A list display yields a new list object.  Its contents are specified
+by providing either a list of expressions or a list comprehension.
+When a comma-separated list of expressions is supplied, its elements are
+evaluated from left to right and placed into the list object in that
+order.  When a list comprehension is supplied, it consists of a
+single expression followed by one or more "for" or "if" clauses.  In this
+case, the elements of the new list are those that would be produced
+by considering each of the "for" or "if" clauses a block, nesting from
+left to right, and evaluating the expression to produce a list element
+each time the innermost block is reached.
 \obindex{list}
 \indexii{empty}{list}
 

Doc/tut/tut.tex

@@ -1753,6 +1753,27 @@ item, then to the result and the next item, and so on.  For example,
 0
 \end{verbatim}
 
+\subsection{List Comprehensions}
+
+List comprehensions provide a concise way to create lists without resorting
+to use of the \func{map()} or \func{filter()} functions.  The resulting
+construct tends often to be clearer than use of those functions.
+
+\begin{verbatim}
+>>> spcs = ["  Apple", " Banana ", "Coco  nut  "]
+>>> print [s.strip() for s in spcs]
+['Apple', 'Banana', 'Coco  nut']
+>>> vec = [2, 4, 6]
+>>> print [3*x for x in vec]
+[6, 12, 18]
+>>> vec1 = [2, 4, 6]
+>>> vec2 = [4, 3, -9]
+>>> print [x*y for x in vec1 for y in vec2]
+[8, 6, -18, 16, 12, -36, 24, 18, -54]
+>>> print [x+y for x in vec1 for y in vec2]
+[6, 5, -7, 8, 7, -5, 10, 9, -3]
+\end{verbatim}
+
 \section{The \keyword{del} statement \label{del}}
 
 There is a way to remove an item from a list given its index instead

Grammar/Grammar

@@ -74,7 +74,8 @@ arith_expr: term (('+'|'-') term)*
 term: factor (('*'|'/'|'%') factor)*
 factor: ('+'|'-'|'~') factor | power
 power: atom trailer* ('**' factor)*
-atom: '(' [testlist] ')' | '[' [testlist] ']' | '{' [dictmaker] '}' | '`' testlist '`' | NAME | NUMBER | STRING+
+atom: '(' [testlist] ')' | '[' [listmaker] ']' | '{' [dictmaker] '}' | '`' testlist '`' | NAME | NUMBER | STRING+
+listmaker: test ( list_iter | (',' test)* [','] )
 lambdef: 'lambda' [varargslist] ':' test
 trailer: '(' [arglist] ')' | '[' subscriptlist ']' | '.' NAME
 subscriptlist: subscript (',' subscript)* [',']
@@ -88,3 +89,7 @@ classdef: 'class' NAME ['(' testlist ')'] ':' suite
 
 arglist: (argument ',')* (argument [',']| '*' test [',' '**' test] | '**' test)
 argument: [test '='] test	# Really [keyword '='] test
+
+list_iter: list_for | list_if
+list_for: 'for' exprlist 'in' testlist [list_iter]
+list_if: 'if' test [list_iter]

Include/graminit.h

@@ -44,14 +44,18 @@
 #define factor 299
 #define power 300
 #define atom 301
-#define lambdef 302
-#define trailer 303
-#define subscriptlist 304
-#define subscript 305
-#define sliceop 306
-#define exprlist 307
-#define testlist 308
-#define dictmaker 309
-#define classdef 310
-#define arglist 311
-#define argument 312
+#define listmaker 302
+#define lambdef 303
+#define trailer 304
+#define subscriptlist 305
+#define subscript 306
+#define sliceop 307
+#define exprlist 308
+#define testlist 309
+#define dictmaker 310
+#define classdef 311
+#define arglist 312
+#define argument 313
+#define list_iter 314
+#define list_for 315
+#define list_if 316

Lib/test/output/test_grammar

@@ -45,3 +45,10 @@ selectors
 
 atoms
 classdef
+['Apple', 'Banana', 'Coco  nut']
+[3, 6, 9, 12, 15]
+[3, 4, 5]
+[(1, 'Apple'), (1, 'Banana'), (1, 'Coconut'), (2, 'Apple'), (2, 'Banana'), (2, 'Coconut'), (3, 'Apple'), (3, 'Banana'), (3, 'Coconut'), (4, 'Apple'), (4, 'Banana'), (4, 'Coconut'), (5, 'Apple'), (5, 'Banana'), (5, 'Coconut')]
+[(1, 'Banana'), (1, 'Coconut'), (2, 'Banana'), (2, 'Coconut'), (3, 'Banana'), (3, 'Coconut'), (4, 'Banana'), (4, 'Coconut'), (5, 'Banana'), (5, 'Coconut')]
+good: got a SyntaxError as expected
+[('Boeing', 'Airliner'), ('Boeing', 'Engine'), ('Ford', 'Engine'), ('Macdonalds', 'Cheeseburger')]

Lib/test/test_grammar.py

@@ -542,3 +542,43 @@ class C:
 	def meth1(self): pass
 	def meth2(self, arg): pass
 	def meth3(self, a1, a2): pass
+
+# list comprehension tests
+nums = [1, 2, 3, 4, 5]
+strs = ["Apple", "Banana", "Coconut"]
+spcs = ["  Apple", " Banana ", "Coco  nut  "]
+
+print [s.strip() for s in spcs]
+print [3 * x for x in nums]
+print [x for x in nums if x > 2]
+print [(i, s) for i in nums for s in strs]
+print [(i, s) for i in nums for s in [f for f in strs if "n" in f]]
+try:
+    eval("[i, s for i in nums for s in strs]")
+    print "FAIL: should have raised a SyntaxError!"
+except SyntaxError:
+    print "good: got a SyntaxError as expected"
+
+suppliers = [
+  (1, "Boeing"),
+  (2, "Ford"),
+  (3, "Macdonalds")
+]
+
+parts = [
+  (10, "Airliner"),
+  (20, "Engine"),
+  (30, "Cheeseburger")
+]
+
+suppart = [
+  (1, 10), (1, 20), (2, 20), (3, 30)
+]
+
+print [
+  (sname, pname)
+    for (sno, sname) in suppliers
+      for (pno, pname) in parts
+        for (sp_sno, sp_pno) in suppart
+          if sno == sp_sno and pno == sp_pno
+]

Python/compile.c

@@ -294,6 +294,7 @@ struct compiling {
 #ifdef PRIVATE_NAME_MANGLING
 	char *c_private;	/* for private name mangling */
 #endif
+	int c_tmpname;		/* temporary local name counter */
 };
 
 
@@ -368,8 +369,10 @@ static int com_addconst(struct compiling *, PyObject *);
 static int com_addname(struct compiling *, PyObject *);
 static void com_addopname(struct compiling *, int, node *);
 static void com_list(struct compiling *, node *, int);
+static void com_list_iter(struct compiling *, node *, node *, char *);
 static int com_argdefs(struct compiling *, node *);
 static int com_newlocal(struct compiling *, char *);
+static void com_assign(struct compiling *, node *, int);
 static PyCodeObject *icompile(struct _node *, struct compiling *);
 static PyCodeObject *jcompile(struct _node *, char *,
 			      struct compiling *);
@@ -419,6 +422,7 @@ com_init(struct compiling *c, char *filename)
 	c->c_last_addr = 0;
 	c->c_last_line = 0;
 	c-> c_lnotab_next = 0;
+	c->c_tmpname = 0;
 	return 1;
 	
   fail:
@@ -941,18 +945,116 @@ parsestrplus(node *n)
 }
 
 static void
-com_list_constructor(struct compiling *c, node *n)
+com_list_for(struct compiling *c, node *n, node *e, char *t)
 {
-	int len;
-	int i;
-	if (TYPE(n) != testlist)
-		REQ(n, exprlist);
-	/* exprlist: expr (',' expr)* [',']; likewise for testlist */
-	len = (NCH(n) + 1) / 2;
-	for (i = 0; i < NCH(n); i += 2)
-		com_node(c, CHILD(n, i));
-	com_addoparg(c, BUILD_LIST, len);
-	com_pop(c, len-1);
+	PyObject *v;
+	int anchor = 0;
+	int save_begin = c->c_begin;
+
+	/* list_iter: for v in expr [list_iter] */
+	com_node(c, CHILD(n, 3)); /* expr */
+	v = PyInt_FromLong(0L);
+	if (v == NULL)
+		c->c_errors++;
+	com_addoparg(c, LOAD_CONST, com_addconst(c, v));
+	com_push(c, 1);
+	Py_XDECREF(v);
+	c->c_begin = c->c_nexti;
+	com_addoparg(c, SET_LINENO, n->n_lineno);
+	com_addfwref(c, FOR_LOOP, &anchor);
+	com_push(c, 1);
+	com_assign(c, CHILD(n, 1), OP_ASSIGN);
+	c->c_loops++;
+	com_list_iter(c, n, e, t);
+	c->c_loops--;
+	com_addoparg(c, JUMP_ABSOLUTE, c->c_begin);
+	c->c_begin = save_begin;
+	com_backpatch(c, anchor);
+	com_pop(c, 2); /* FOR_LOOP has popped these */
+}  
+
+static void
+com_list_if(struct compiling *c, node *n, node *e, char *t)
+{
+	int anchor = 0;
+	int a = 0;
+	/* list_iter: 'if' test [list_iter] */
+	com_addoparg(c, SET_LINENO, n->n_lineno);
+	com_node(c, CHILD(n, 1));
+	com_addfwref(c, JUMP_IF_FALSE, &a);
+	com_addbyte(c, POP_TOP);
+	com_pop(c, 1);
+	com_list_iter(c, n, e, t);
+	com_addfwref(c, JUMP_FORWARD, &anchor);
+	com_backpatch(c, a);
+	/* We jump here with an extra entry which we now pop */
+	com_addbyte(c, POP_TOP);
+	com_backpatch(c, anchor);
+}
+
+static void
+com_list_iter(struct compiling *c,
+	      node *p,		/* parent of list_iter node */
+	      node *e,		/* element expression node */
+	      char *t		/* name of result list temp local */)
+{
+	/* list_iter is the last child in a listmaker, list_for, or list_if */
+	node *n = CHILD(p, NCH(p)-1);
+	if (TYPE(n) == list_iter) {
+		n = CHILD(n, 0);
+		switch (TYPE(n)) {
+		case list_for: 
+			com_list_for(c, n, e, t);
+			break;
+		case list_if:
+			com_list_if(c, n, e, t);
+			break;
+		default:
+			com_error(c, PyExc_SystemError,
+				  "invalid list_iter node type");
+		}
+	}
+	else {
+		com_addopnamestr(c, LOAD_NAME, t);
+		com_push(c, 1);
+		com_node(c, e);
+		com_addoparg(c, CALL_FUNCTION, 1);
+		com_addbyte(c, POP_TOP);
+		com_pop(c, 2);
+	}
+}
+
+static void
+com_list_comprehension(struct compiling *c, node *n)
+{
+	/* listmaker: test list_iter */
+	char tmpname[12];
+	sprintf(tmpname, "__%d__", ++c->c_tmpname);
+	com_addoparg(c, BUILD_LIST, 0);
+	com_addbyte(c, DUP_TOP); /* leave the result on the stack */
+	com_push(c, 2);
+	com_addopnamestr(c, LOAD_ATTR, "append");
+	com_addopnamestr(c, STORE_NAME, tmpname);
+	com_pop(c, 1);
+	com_list_iter(c, n, CHILD(n, 0), tmpname);
+	com_addopnamestr(c, DELETE_NAME, tmpname);
+	--c->c_tmpname;
+}
+
+static void
+com_listmaker(struct compiling *c, node *n)
+{
+	/* listmaker: test ( list_iter | (',' test)* [','] ) */
+	if (TYPE(CHILD(n, 1)) == list_iter)
+		com_list_comprehension(c, n);
+	else {
+		int len = 0;
+		int i;
+		for (i = 0; i < NCH(n); i += 2, len++)
+			com_node(c, CHILD(n, i));
+		com_addoparg(c, BUILD_LIST, len);
+		com_pop(c, len-1);
+	}
 }
 
 static void
@@ -990,18 +1092,18 @@ com_atom(struct compiling *c, node *n)
 		else
 			com_node(c, CHILD(n, 1));
 		break;
-	case LSQB:
+	case LSQB: /* '[' [listmaker] ']' */
 		if (TYPE(CHILD(n, 1)) == RSQB) {
 			com_addoparg(c, BUILD_LIST, 0);
 			com_push(c, 1);
 		}
 		else
-			com_list_constructor(c, CHILD(n, 1));
+			com_listmaker(c, CHILD(n, 1));
 		break;
 	case LBRACE: /* '{' [dictmaker] '}' */
 		com_addoparg(c, BUILD_MAP, 0);
 		com_push(c, 1);
-		if (TYPE(CHILD(n, 1)) != RBRACE)
+		if (TYPE(CHILD(n, 1)) == dictmaker)
 			com_dictmaker(c, CHILD(n, 1));
 		break;
 	case BACKQUOTE:
@@ -1743,6 +1845,19 @@ com_assign_sequence(struct compiling *c, node *n, int assigning)
 		com_assign(c, CHILD(n, i), assigning);
 }
 
+static void
+com_assign_list(struct compiling *c, node *n, int assigning)
+{
+	int i;
+	if (assigning) {
+		i = (NCH(n)+1)/2;
+		com_addoparg(c, UNPACK_SEQUENCE, i);
+		com_push(c, i-1);
+	}
+	for (i = 0; i < NCH(n); i += 2)
+		com_assign(c, CHILD(n, i), assigning);
+}
+
 static void
 com_assign_name(struct compiling *c, node *n, int assigning)
 {