bpo-38530: Offer suggestions on AttributeError

Include/internal/pycore_suggestions.h

@@ -0,0 +1,12 @@
+#include "Python.h"
+
+#ifndef Py_INTERNAL_SUGGESTIONS_H
+#define Py_INTERNAL_SUGGESTIONS_H
+
+#ifndef Py_BUILD_CORE
+#  error "this header requires Py_BUILD_CORE define"
+#endif
+
+int _Py_offer_suggestions(PyObject* v, PyObject* name);
+
+#endif /* !Py_INTERNAL_SUGGESTIONS_H */

Lib/test/test_class.py

@@ -516,7 +516,7 @@ class A:
         try:
             A().a # Raised AttributeError: A instance has no attribute 'a'
         except AttributeError as x:
-            if str(x) != "booh":
+            if not str(x).startswith("booh"):
                 self.fail("attribute error for A().a got masked: %s" % x)
 
         class E:
@@ -534,6 +534,30 @@ class I:
         else:
             self.fail("attribute error for I.__init__ got masked")
 
+    def test_getattr_suggestions(self):
+        class A:
+            blech = None
+
+        try:
+            A().bluch
+        except AttributeError as x:
+            self.assertIn("blech", str(x))
+
+        try:
+            A().somethingverywrong
+        except AttributeError as x:
+            self.assertNotIn("blech", str(x))
+
+        # A class with a very big __dict__ will not be consider
+        # for suggestions.
+        for index in range(101):
+            setattr(A, f"index_{index}", None)
+
+        try:
+            A().bluch
+        except AttributeError as x:
+            self.assertNotIn("blech", str(x))
+
     def assertNotOrderable(self, a, b):
         with self.assertRaises(TypeError):
             a < b

Lib/test/test_descr.py

@@ -4582,11 +4582,11 @@ class C(object):
             __getattr__ = descr
 
         self.assertRaises(AttributeError, getattr, A(), "attr")
-        self.assertEqual(descr.counter, 1)
+        self.assertEqual(descr.counter, 3)
         self.assertRaises(AttributeError, getattr, B(), "attr")
-        self.assertEqual(descr.counter, 2)
-        self.assertRaises(AttributeError, getattr, C(), "attr")
         self.assertEqual(descr.counter, 4)
+        self.assertRaises(AttributeError, getattr, C(), "attr")
+        self.assertEqual(descr.counter, 10)
 
         class EvilGetattribute(object):
             # This used to segfault

Lib/unittest/mock.py

@@ -714,6 +714,7 @@ def __dir__(self):
             return object.__dir__(self)
 
         extras = self._mock_methods or []
+        extras = list(extras)
         from_type = dir(type(self))
         from_dict = list(self.__dict__)
         from_child_mocks = [

Makefile.pre.in

@@ -368,6 +368,7 @@ PYTHON_OBJS=	\
 		Python/dtoa.o \
 		Python/formatter_unicode.o \
 		Python/fileutils.o \
+		Python/suggestions.o \
 		Python/$(DYNLOADFILE) \
 		$(LIBOBJS) \
 		$(MACHDEP_OBJS) \
@@ -1086,6 +1087,7 @@ PYTHON_HEADERS= \
 		$(srcdir)/Include/internal/pycore_import.h \
 		$(srcdir)/Include/internal/pycore_initconfig.h \
 		$(srcdir)/Include/internal/pycore_object.h \
+		$(srcdir)/Include/internal/pycore_suggestions.h \
 		$(srcdir)/Include/internal/pycore_pathconfig.h \
 		$(srcdir)/Include/internal/pycore_pyerrors.h \
 		$(srcdir)/Include/internal/pycore_pyhash.h \

Objects/object.c

@@ -6,6 +6,7 @@
 #include "pycore_object.h"
 #include "pycore_pystate.h"
 #include "pycore_context.h"
+#include "pycore_suggestions.h"
 #include "frameobject.h"
 #include "interpreteridobject.h"
 
@@ -930,6 +931,7 @@ PyObject *
 PyObject_GetAttr(PyObject *v, PyObject *name)
 {
     PyTypeObject *tp = Py_TYPE(v);
+    PyObject* result = NULL;
 
     if (!PyUnicode_Check(name)) {
         PyErr_Format(PyExc_TypeError,
@@ -938,17 +940,30 @@ PyObject_GetAttr(PyObject *v, PyObject *name)
         return NULL;
     }
     if (tp->tp_getattro != NULL)
-        return (*tp->tp_getattro)(v, name);
-    if (tp->tp_getattr != NULL) {
+        result = (*tp->tp_getattro)(v, name);
+    else if (tp->tp_getattr != NULL) {
         const char *name_str = PyUnicode_AsUTF8(name);
         if (name_str == NULL)
             return NULL;
-        return (*tp->tp_getattr)(v, (char *)name_str);
+        result = (*tp->tp_getattr)(v, (char *)name_str);
+    } else {
+        PyErr_Format(PyExc_AttributeError,
+                    "'%.50s' object has no attribute '%U'",
+                    tp->tp_name, name);
     }
-    PyErr_Format(PyExc_AttributeError,
-                 "'%.50s' object has no attribute '%U'",
-                 tp->tp_name, name);
-    return NULL;
+
+    // xxx use thread local storage for this thing
+    static int should_offer_suggestions = 1;
+    if (!result && should_offer_suggestions && PyErr_ExceptionMatches(PyExc_AttributeError)) {
+        should_offer_suggestions = 0;
+        int ret = _Py_offer_suggestions(v, name);
+        should_offer_suggestions = 1;
+        if (ret == -1) {
+            return NULL;
+        }
+   }
+
+    return result;
 }
 
 int

PCbuild/pythoncore.vcxproj

@@ -179,6 +179,7 @@
     <ClInclude Include="..\Include\internal\pycore_traceback.h" />
     <ClInclude Include="..\Include\internal\pycore_tupleobject.h" />
     <ClInclude Include="..\Include\internal\pycore_warnings.h" />
+    <ClInclude Include="..\Include\internal\pycore_suggestions.h" />
     <ClInclude Include="..\Include\interpreteridobject.h" />
     <ClInclude Include="..\Include\intrcheck.h" />
     <ClInclude Include="..\Include\iterobject.h" />
@@ -462,6 +463,7 @@
     <ClCompile Include="..\Python\dtoa.c" />
     <ClCompile Include="..\Python\Python-ast.c" />
     <ClCompile Include="..\Python\pythonrun.c" />
+    <ClCompile Include="..\Python\suggestions.c" />
     <ClCompile Include="..\Python\structmember.c" />
     <ClCompile Include="..\Python\symtable.c" />
     <ClCompile Include="..\Python\sysmodule.c" />

Python/suggestions.c

@@ -0,0 +1,176 @@
+#include "Python.h"
+
+#include "pycore_suggestions.h"
+
+#define MAX_GETATTR_PREDICT_DIST 3
+#define MAX_GETATTR_PREDICT_ITEMS 100
+#define MAX_GETATTR_STRING_SIZE 20
+
+static size_t
+distance(const char *string1, const char *string2)
+{
+    Py_ssize_t len1 = strlen(string1);
+    Py_ssize_t len2 = strlen(string2);
+    Py_ssize_t i;
+    Py_ssize_t half;
+    size_t *row;
+    size_t *end;
+
+    /* Get rid of the common prefix */
+    while (len1 > 0 && len2 > 0 && *string1 == *string2) {
+        len1--;
+        len2--;
+        string1++;
+        string2++;
+    }
+
+    /* strip common suffix */
+    while (len1 > 0 && len2 > 0 && string1[len1-1] == string2[len2-1]) {
+        len1--;
+        len2--;
+    }
+
+    /* catch trivial cases */
+    if (len1 == 0) {
+        return len2;
+    }
+    if (len2 == 0) {
+        return len1;
+    }
+
+    /* make the inner cycle (i.e. string2) the longer one */
+    if (len1 > len2) {
+        size_t nx = len1;
+        const char *sx = string1;
+        len1 = len2;
+        len2 = nx;
+        string1 = string2;
+        string2 = sx;
+    }
+    /* check len1 == 1 separately */
+    if (len1 == 1) {
+        return len2 - (memchr(string2, *string1, len2) != NULL);
+    }
+    len1++;
+    len2++;
+    half = len1 >> 1;
+
+    /* initalize first row */
+    row = (size_t*)PyMem_Malloc(len2*sizeof(size_t));
+    if (!row) {
+        return (size_t)(-1);
+    }
+    end = row + len2 - 1;
+    for (i = 0; i < len2 - half; i++) {
+        row[i] = i;
+    }
+
+    /* We don't have to scan two corner triangles (of size len1/2)
+     * in the matrix because no best path can go throught them. This is
+     * not true when len1 == len2 == 2 so the memchr() special case above is
+     * necessary */
+    row[0] = len1 - half - 1;
+    for (i = 1; i < len1; i++) {
+        size_t *p;
+        const char char1 = string1[i - 1];
+        const char *char2p;
+        size_t D, x;
+        /* skip the upper triangle */
+        if (i >= len1 - half) {
+            size_t offset = i - (len1 - half);
+            size_t c3;
+
+            char2p = string2 + offset;
+            p = row + offset;
+            c3 = *(p++) + (char1 != *(char2p++));
+            x = *p;
+            x++;
+            D = x;
+            if (x > c3)
+              x = c3;
+            *(p++) = x;
+        }
+        else {
+            p = row + 1;
+            char2p = string2;
+            D = x = i;
+        }
+        /* skip the lower triangle */
+        if (i <= half + 1) {
+            end = row + len2 + i - half - 2;
+        }
+        /* main */
+        while (p <= end) {
+            size_t c3 = --D + (char1 != *(char2p++));
+            x++;
+            if (x > c3)
+              x = c3;
+            D = *p;
+            D++;
+            if (x > D)
+              x = D;
+            *(p++) = x;
+        }
+        /* lower triangle sentinel */
+        if (i <= half) {
+            size_t c3 = --D + (char1 != *char2p);
+            x++;
+            if (x > c3)
+              x = c3;
+            *p = x;
+        }
+    }
+    i = *end;
+    PyMem_Free(row);
+    return i;
+}
+
+int _Py_offer_suggestions(PyObject* v, PyObject* name){
+    PyObject *oldexceptiontype, *oldexceptionvalue, *oldtraceback;
+    PyErr_Fetch(&oldexceptiontype, &oldexceptionvalue, &oldtraceback);
+    if (Py_EnterRecursiveCall(" while getting the __dir__ of an object")) {
+        return -1;
+    }
+    PyObject* dir = PyObject_Dir(v);
+    Py_LeaveRecursiveCall();
+    PyObject* newexceptionvalue = oldexceptionvalue;
+    if (dir) {
+        if (!PyList_CheckExact(dir)) {
+            return -1;
+        }
+        PyObject* suggestion = NULL;
+        Py_ssize_t dir_size = PyList_GET_SIZE(dir);
+        if (dir_size <= MAX_GETATTR_PREDICT_ITEMS) {
+            int suggestion_distance = PyUnicode_GetLength(name);
+            for(int i = 0; i < dir_size; ++i) {
+                PyObject *item = PyList_GET_ITEM(dir, i);
+                const char *name_str = PyUnicode_AsUTF8(name);
+                if (name_str == NULL) {
+                    PyErr_Clear();
+                    continue;
+                }
+                int current_distance = distance(PyUnicode_AsUTF8(name),
+                                                PyUnicode_AsUTF8(item));
+                if (current_distance > MAX_GETATTR_PREDICT_DIST){
+                    continue;
+                }
+                if (!suggestion || current_distance < suggestion_distance) {
+                    suggestion = item;
+                    suggestion_distance = current_distance;
+                }       
+            }
+        }
+        if (suggestion) {
+            newexceptionvalue = PyUnicode_FromFormat("%S\n\nDid you mean: %U?",
+                                                     oldexceptionvalue,
+                                                     suggestion);
+            Py_DECREF(oldexceptionvalue);
+        }
+        Py_DECREF(dir);
+    }
+    PyErr_Clear();
+    PyErr_Restore(oldexceptiontype, newexceptionvalue, oldtraceback);
+    return 0;
+}
+
+