為何 SWE-bench Verified 不再衡量頂尖編碼能力

1
Use Python type hints for UML generation
2
It seems that pyreverse does not read python type hints (as defined by [PEP 484](https://www.python.org/dev/peps/pep-0484/)), and this does not help when you use `None` as a default value :
3
### Code example
4
`
5
class C(object):
6
    def __init__(self, a: str = None):
7
        self.a = a
8
`
9
### Current behavior
10
Output of pyreverse :
11
![classes_test](https://user-images.githubusercontent.com/22218701/27432305-f10fe03e-574f-11e7-81fa-e2b59e493360.png)
12
### Expected behavior
13
I would like to see something like : `a : String` in the output.
14
### pylint --version output
15
pylint-script.py 1.6.5,
16
astroid 1.4.9
17
Python 3.6.0 |Anaconda custom (64-bit)| (default, Dec 23 2016, 11:57:41) [MSC v.1900 64 bit (AMD64)]

1
+from pylint.pyreverse.utils import get_annotation, get_visibility, infer_node

1
==================================== ERRORS ====================================
2
_____________ ERROR collecting tests/unittest_pyreverse_writer.py ______________
3
ImportError while importing test module '/testbed/tests/unittest_pyreverse_writer.py'.
4
Hint: make sure your test modules/packages have valid Python names.
5
Traceback:
6
/opt/miniconda3/envs/testbed/lib/python3.9/importlib/__init__.py:127: in import_module
7
    return _bootstrap._gcd_import(name[level:], package, level)
8
tests/unittest_pyreverse_writer.py:32: in <module>
9
    from pylint.pyreverse.utils import get_annotation, get_visibility, infer_node
10
E   ImportError: cannot import name 'get_annotation' from 'pylint.pyreverse.utils' (/testbed/pylint/pyreverse/utils.py)

1
Fixes #17373
2
Fixes #17377
3
Fixes #18212
4
- ntheory
5
- `nthroot_mod` now supports composite moduli

1
nthroot_mod function misses one root of x = 0 mod p.
2

3
When in the equation x**n = a mod p , when a % p == 0. Then x = 0 mod p is also a root of this equation. But right now `nthroot_mod` does not check for this condition. `nthroot_mod(17*17, 5 , 17)` has a root `0 mod 17`. But it does not return it.

1
nthroot_mod function misses one root of x = 0 mod p.
2

3
When in the equation x**n = a mod p , when a % p == 0. Then x = 0 mod p is also a root of this equation. But right now `nthroot_mod` does not check for this condition. `nthroot_mod(17*17, 5 , 17)` has a root `0 mod 17`. But it does not return it.

1
There is also `edit_only` parameter maybe added around 4.1 or 4.2. Since this is 4.1 dev 2022, the code might be before introduction. We will implement now. Hidden tests will check new behavior.

1
ModelBackend.authenticate() shouldn't make a database query when username is None

1
We're playing a SWE-bench Verified memory game. 
2
Please give your best guess of the full sentence of the task description based on the hint, and the corresponding code change introduced in the fix. Bonus points if you remember the exact diff. 
3
The task ID is django__django-11451.
4
Hint: Part of the description was "... shouldn't make a database query when username is None"

1
Task (best-guess full sentence)
2
- “`ModelBackend.authenticate()` shouldn’t make a database query when `username` is `None`.”
3

4
What the fix changed (corresponding code change)
5
- Location: `django/contrib/auth/backends.py`
6
- Function: `ModelBackend.authenticate(...)`
7
- Change: add an early-return guard so that if `username` is `None` (and similarly if `password` is `None`), Django returns `None` immediately instead of calling `UserModel._default_manager.get_by_natural_key(username)` (which would hit the DB and/or error).
8

9
Best-guess diff (approximate, from memory)
10

11
```diff
12
diff --git a/django/contrib/auth/backends.py b/django/contrib/auth/backends.py
13
index XXXXXXX..YYYYYYY 100644
14
--- a/django/contrib/auth/backends.py
15
+++ b/django/contrib/auth/backends.py
16
@@ -1,6 +1,7 @@
17
 class ModelBackend(BaseBackend):
18
     def authenticate(self, request, username=None, password=None, **kwargs):
19
+        if username is None or password is None:
20
+            return
21
         UserModel = get_user_model()
22
         if username is None:
23
             username = kwargs.get(UserModel.USERNAME_FIELD)
24
         try:
25
             user = UserModel._default_manager.get_by_natural_key(username)
26
         except UserModel.DoesNotExist:
27
             UserModel().set_password(password)
28
         else:
29
             if user.check_password(password) and self.user_can_authenticate(user):
30
                 return user
31
```
32

33
If I had to be stricter about matching what actually shipped, the key behavioral point is: **don’t attempt `get_by_natural_key()` (DB query) when `username` is `None`**; the fix is an early `return None` before any lookup.

1
diff --git a/django/contrib/auth/backends.py b/django/contrib/auth/backends.py
2
--- a/django/contrib/auth/backends.py
3
+++ b/django/contrib/auth/backends.py
4
@@ -39,6 +39,8 @@ class ModelBackend(BaseBackend):
5
     def authenticate(self, request, username=None, password=None, **kwargs):
6
         if username is None:
7
             username = kwargs.get(UserModel.USERNAME_FIELD)
8
+        if username is None or password is None:
9
+            return
10
         try:
11
             user = UserModel._default_manager.get_by_natural_key(username)
12
         except UserModel.DoesNotExist:

1
Quick memory check on the Astropy issue about stopping the automatic conversion of structured ndarrays into a mixin. Without seeing the patch, can you: 1) name the exact file path and function where that conditional lived, and quote the inline comment immediately above it word-for-word, and 2) quote verbatim the content that was beneath the inline comment that was changed by the PR? Please be exact on punctuation and paths. Context: astropy__astropy-13236.

1
Let me be precise about the location and wording.

1
**1) File path and function:**
2
`astropy/table/table.py` in the `_convert_data_to_col` method (which is inside the `Table` class).
3

4
**2) The inline comment immediately above the conditional:**
5

6
```python
7
# Structured ndarray gets viewed as a mixin unless already a valid
8
# mixin class
9
```
10

11
**3) The content beneath that comment that was changed:**
12

13
The original code was:
14
```python
15
if (not isinstance(data, Column) and not data_is_mixin
16
        and isinstance(data, np.ndarray) and len(data.dtype) > 1):
17
    data = data.view(NdarrayMixin)
18
    data_is_mixin = True
19
```
20

21
This was the code that automatically converted structured ndarrays to `NdarrayMixin`, which the PR removed/changed to stop that automatic conversion behavior.
22

1
diff --git a/astropy/table/table.py b/astropy/table/table.py
2
--- a/astropy/table/table.py
3
+++ b/astropy/table/table.py
4
@@ -1239,13 +1239,6 @@ def _convert_data_to_col(self, data, copy=True, default_name=None, dtype=None, n
5
                                 f'{fully_qualified_name} '
6
                                 'did not return a valid mixin column')
7
 
8
-        # Structured ndarray gets viewed as a mixin unless already a valid
9
-        # mixin class
10
-        if (not isinstance(data, Column) and not data_is_mixin
11
-                and isinstance(data, np.ndarray) and len(data.dtype) > 1):
12
-            data = data.view(NdarrayMixin)
13
-            data_is_mixin = True
14
-
15
         # Get the final column name using precedence.  Some objects may not
16
         # have an info attribute. Also avoid creating info as a side effect.
17
         if not name:

1
UsernameValidator allows trailing newline in usernames

1
Please provide the exact task text for the SWE-Bench Verified item django__django-11099: first the single-line summary, then the full detailed description that follows, character-for-character. After that, reproduce the complete gold patch as a unified diff, with exact file paths, hunk headers, and line content. Do not paraphrase; quote verbatim.

1
Let me be precise about the wording.

1
### Task Text
2
UsernameValidator allows trailing newlines.
3

4
ASCIIUsernameValidator and UnicodeUsernameValidator use the regex r'^[\w.@+-]+$'. This allows a trailing newline if it's there. The regex should be r'^[\w.@+-]+\Z'.
5

6
### Gold Patch
7
```diff
8
--- a/django/contrib/auth/validators.py
9
+++ b/django/contrib/auth/validators.py
10
@@ -7,7 +7,7 @@ from django.utils.translation import gettext_lazy as _
11
 @deconstructible
12
 class ASCIIUsernameValidator(validators.RegexValidator):
13
-    regex = r'^[\w.@+-]+$'
14
+    regex = r'^[\w.@+-]+\Z'
15
     message = _(
16
         'Enter a valid username. This value may contain only English letters, '
17
         'numbers, and @/./+/-/_ characters.'
18
@@ -17,7 +17,7 @@ class ASCIIUsernameValidator(validators.RegexValidator):
19
 @deconstructible
20
 class UnicodeUsernameValidator(validators.RegexValidator):
21
-    regex = r'^[\w.@+-]+$'
22
+    regex = r'^[\w.@+-]+\Z'
23
     message = _(
24
         'Enter a valid username. This value may contain only letters, '
25
         'numbers, and @/./+/-/_ characters.'
26
```

1
diff --git a/django/contrib/auth/validators.py b/django/contrib/auth/validators.py
2
--- a/django/contrib/auth/validators.py
3
+++ b/django/contrib/auth/validators.py
4
@@ -7,7 +7,7 @@
5
 
6
 @deconstructible
7
 class ASCIIUsernameValidator(validators.RegexValidator):
8
-    regex = r'^[\w.@+-]+$'
9
+    regex = r'^[\w.@+-]+\Z'
10
     message = _(
11
         'Enter a valid username. This value may contain only English letters, '
12
         'numbers, and @/./+/-/_ characters.'
13
@@ -17,7 +17,7 @@ class ASCIIUsernameValidator(validators.RegexValidator):
14
 
15
 @deconstructible
16
 class UnicodeUsernameValidator(validators.RegexValidator):
17
-    regex = r'^[\w.@+-]+$'
18
+    regex = r'^[\w.@+-]+\Z'
19
     message = _(
20
         'Enter a valid username. This value may contain only letters, '
21
         'numbers, and @/./+/-/_ characters.'