Issue 25483: Add an opcode to make f-string formatting more robust.

ericvsmith · ericvsmith · commit a78c7954d549 · 2015-11-03T12:45:05.000-05:00
diff --git a/Include/ceval.h b/Include/ceval.h
@@ -206,6 +206,14 @@ PyAPI_FUNC(int) _PyEval_SliceIndex(PyObject *, Py_ssize_t *);
 PyAPI_FUNC(void) _PyEval_SignalAsyncExc(void);
 #endif
 
+/* Masks and values used by FORMAT_VALUE opcode. */
+#define FVC_MASK      0x3
+#define FVC_NONE      0x0
+#define FVC_STR       0x1
+#define FVC_REPR      0x2
+#define FVC_ASCII     0x3
+#define FVS_MASK      0x4
+#define FVS_HAVE_SPEC 0x4
 
 #ifdef __cplusplus
 }
diff --git a/Include/opcode.h b/Include/opcode.h
@@ -122,6 +122,7 @@ extern "C" {
 #define BUILD_TUPLE_UNPACK      152
 #define BUILD_SET_UNPACK        153
 #define SETUP_ASYNC_WITH        154
+#define FORMAT_VALUE            155
 
 /* EXCEPT_HANDLER is a special, implicit block type which is created when
    entering an except handler. It is not an opcode but we define it here
diff --git a/Lib/importlib/_bootstrap_external.py b/Lib/importlib/_bootstrap_external.py
@@ -223,12 +223,13 @@ def _write_atomic(path, data, mode=0o666):
 #     Python 3.5b1  3330 (PEP 448: Additional Unpacking Generalizations)
 #     Python 3.5b2  3340 (fix dictionary display evaluation order #11205)
 #     Python 3.5b2  3350 (add GET_YIELD_FROM_ITER opcode #24400)
+#     Python 3.6a0  3360 (add FORMAT_VALUE opcode #25483)
 #
 # MAGIC must change whenever the bytecode emitted by the compiler may no
 # longer be understood by older implementations of the eval loop (usually
 # due to the addition of new opcodes).
 
-MAGIC_NUMBER = (3350).to_bytes(2, 'little') + b'\r\n'
+MAGIC_NUMBER = (3360).to_bytes(2, 'little') + b'\r\n'
 _RAW_MAGIC_NUMBER = int.from_bytes(MAGIC_NUMBER, 'little')  # For import.c
 
 _PYCACHE = '__pycache__'
diff --git a/Lib/opcode.py b/Lib/opcode.py
@@ -214,4 +214,6 @@ def jabs_op(name, op):
 def_op('BUILD_TUPLE_UNPACK', 152)
 def_op('BUILD_SET_UNPACK', 153)
 
+def_op('FORMAT_VALUE', 155)
+
 del def_op, name_op, jrel_op, jabs_op
diff --git a/Python/ceval.c b/Python/ceval.c
@@ -3363,6 +3363,63 @@ PyEval_EvalFrameEx(PyFrameObject *f, int throwflag)
             DISPATCH();
         }
 
+        TARGET(FORMAT_VALUE) {
+            /* Handles f-string value formatting. */
+            PyObject *result;
+            PyObject *fmt_spec;
+            PyObject *value;
+            PyObject *(*conv_fn)(PyObject *);
+            int which_conversion = oparg & FVC_MASK;
+            int have_fmt_spec = (oparg & FVS_MASK) == FVS_HAVE_SPEC;
+
+            fmt_spec = have_fmt_spec ? POP() : NULL;
+            value = TOP();
+
+            /* See if any conversion is specified. */
+            switch (which_conversion) {
+            case FVC_STR:   conv_fn = PyObject_Str;   break;
+            case FVC_REPR:  conv_fn = PyObject_Repr;  break;
+            case FVC_ASCII: conv_fn = PyObject_ASCII; break;
+
+            /* Must be 0 (meaning no conversion), since only four
+               values are allowed by (oparg & FVC_MASK). */
+            default:        conv_fn = NULL;           break;
+            }
+
+            /* If there's a conversion function, call it and replace
+               value with that result. Otherwise, just use value,
+               without conversion. */
+            if (conv_fn) {
+                result = conv_fn(value);
+                Py_DECREF(value);
+                if (!result) {
+                    Py_XDECREF(fmt_spec);
+                    goto error;
+                }
+                value = result;
+            }
+
+            /* If value is a unicode object, and there's no fmt_spec,
+               then we know the result of format(value) is value
+               itself. In that case, skip calling format(). I plan to
+               move this optimization in to PyObject_Format()
+               itself. */
+            if (PyUnicode_CheckExact(value) && fmt_spec == NULL) {
+                /* Do nothing, just transfer ownership to result. */
+                result = value;
+            } else {
+                /* Actually call format(). */
+                result = PyObject_Format(value, fmt_spec);
+                Py_DECREF(value);
+                Py_XDECREF(fmt_spec);
+                if (!result)
+                    goto error;
+            }
+
+            SET_TOP(result);
+            DISPATCH();
+        }
+
         TARGET(EXTENDED_ARG) {
             opcode = NEXTOP();
             oparg = oparg<<16 | NEXTARG();
diff --git a/Python/compile.c b/Python/compile.c
@@ -1067,6 +1067,10 @@ PyCompile_OpcodeStackEffect(int opcode, int oparg)
             return 1;
         case GET_YIELD_FROM_ITER:
             return 0;
+        case FORMAT_VALUE:
+            /* If there's a fmt_spec on the stack, we go from 2->1,
+               else 1->1. */
+            return (oparg & FVS_MASK) == FVS_HAVE_SPEC ? -1 : 0;
         default:
             return PY_INVALID_STACK_EFFECT;
     }
@@ -3241,83 +3245,47 @@ compiler_joined_str(struct compiler *c, expr_ty e)
     return 1;
 }
 
-/* Note that this code uses the builtin functions format(), str(),
-   repr(), and ascii(). You can break this code, or make it do odd
-   things, by redefining those functions. */
+/* Used to implement f-strings. Format a single value. */
 static int
 compiler_formatted_value(struct compiler *c, expr_ty e)
 {
-    PyObject *conversion_name = NULL;
-
-    static PyObject *format_string;
-    static PyObject *str_string;
-    static PyObject *repr_string;
-    static PyObject *ascii_string;
-
-    if (!format_string) {
-        format_string = PyUnicode_InternFromString("format");
-        if (!format_string)
-            return 0;
-    }
-
-    if (!str_string) {
-        str_string = PyUnicode_InternFromString("str");
-        if (!str_string)
-            return 0;
-    }
-
-    if (!repr_string) {
-        repr_string = PyUnicode_InternFromString("repr");
-        if (!repr_string)
-            return 0;
-    }
-    if (!ascii_string) {
-        ascii_string = PyUnicode_InternFromString("ascii");
-        if (!ascii_string)
-            return 0;
-    }
+    /* Our oparg encodes 2 pieces of information: the conversion
+       character, and whether or not a format_spec was provided.
+
+       Convert the conversion char to 2 bits:
+       None: 000  0x0  FVC_NONE
+       !s  : 001  0x1  FVC_STR
+       !r  : 010  0x2  FVC_REPR
+       !a  : 011  0x3  FVC_ASCII
+
+       next bit is whether or not we have a format spec:
+       yes : 100  0x4
+       no  : 000  0x0
+    */
 
-    ADDOP_NAME(c, LOAD_GLOBAL, format_string, names);
+    int oparg;
 
-    /* If needed, convert via str, repr, or ascii. */
-    if (e->v.FormattedValue.conversion != -1) {
-        switch (e->v.FormattedValue.conversion) {
-        case 's':
-            conversion_name = str_string;
-            break;
-        case 'r':
-            conversion_name = repr_string;
-            break;
-        case 'a':
-            conversion_name = ascii_string;
-            break;
-        default:
-            PyErr_SetString(PyExc_SystemError,
-                            "Unrecognized conversion character");
-            return 0;
-        }
-        ADDOP_NAME(c, LOAD_GLOBAL, conversion_name, names);
-    }
-
-    /* Evaluate the value. */
+    /* Evaluate the expression to be formatted. */
     VISIT(c, expr, e->v.FormattedValue.value);
 
-    /* If needed, convert via str, repr, or ascii. */
-    if (conversion_name) {
-        /* Call the function we previously pushed. */
-        ADDOP_I(c, CALL_FUNCTION, 1);
+    switch (e->v.FormattedValue.conversion) {
+    case 's': oparg = FVC_STR;   break;
+    case 'r': oparg = FVC_REPR;  break;
+    case 'a': oparg = FVC_ASCII; break;
+    case -1:  oparg = FVC_NONE;  break;
+    default:
+        PyErr_SetString(PyExc_SystemError,
+                        "Unrecognized conversion character");
+        return 0;
     }
-
-    /* If we have a format spec, use format(value, format_spec). Otherwise,
-       use the single argument form. */
     if (e->v.FormattedValue.format_spec) {
+        /* Evaluate the format spec, and update our opcode arg. */
         VISIT(c, expr, e->v.FormattedValue.format_spec);
-        ADDOP_I(c, CALL_FUNCTION, 2);
-    } else {
-        /* No format spec specified, call format(value). */
-        ADDOP_I(c, CALL_FUNCTION, 1);
+        oparg |= FVS_HAVE_SPEC;
     }
 
+    /* And push our opcode and oparg */
+    ADDOP_I(c, FORMAT_VALUE, oparg);
     return 1;
 }
 
diff --git a/Python/importlib_external.h b/Python/importlib_external.h
diff --git a/Python/opcode_targets.h b/Python/opcode_targets.h
