Refactor StmtIf: Formatter and Linter (#5459)

## Summary

Previously, `StmtIf` was defined recursively as
```rust
pub struct StmtIf {
    pub range: TextRange,
    pub test: Box<Expr>,
    pub body: Vec<Stmt>,
    pub orelse: Vec<Stmt>,
}
```
Every `elif` was represented as an `orelse` with a single `StmtIf`. This
means that this representation couldn't differentiate between
```python
if cond1:
    x = 1
else:
    if cond2:
        x = 2
```
and 
```python
if cond1:
    x = 1
elif cond2:
    x = 2
```
It also makes many checks harder than they need to be because we have to
recurse just to iterate over an entire if-elif-else and because we're
lacking nodes and ranges on the `elif` and `else` branches.

We change the representation to a flat

```rust
pub struct StmtIf {
    pub range: TextRange,
    pub test: Box<Expr>,
    pub body: Vec<Stmt>,
    pub elif_else_clauses: Vec<ElifElseClause>,
}

pub struct ElifElseClause {
    pub range: TextRange,
    pub test: Option<Expr>,
    pub body: Vec<Stmt>,
}
```
where `test: Some(_)` represents an `elif` and `test: None` an else.

This representation is different tradeoff, e.g. we need to allocate the
`Vec<ElifElseClause>`, the `elif`s are now different than the `if`s
(which matters in rules where want to check both `if`s and `elif`s) and
the type system doesn't guarantee that the `test: None` else is actually
last. We're also now a bit more inconsistent since all other `else`,
those from `for`, `while` and `try`, still don't have nodes. With the
new representation some things became easier, e.g. finding the `elif`
token (we can use the start of the `ElifElseClause`) and formatting
comments for if-elif-else (no more dangling comments splitting, we only
have to insert the dangling comment after the colon manually and set
`leading_alternate_branch_comments`, everything else is taken of by
having nodes for each branch and the usual placement.rs fixups).

## Merge Plan

This PR requires coordination between the parser repo and the main ruff
repo. I've split the ruff part, into two stacked PRs which have to be
merged together (only the second one fixes all tests), the first for the
formatter to be reviewed by @MichaReiser and the second for the linter
to be reviewed by @charliermarsh.

* MH: Review and merge
astral-sh/RustPython-Parser#20
* MH: Review and merge or move later in stack
astral-sh/RustPython-Parser#21
* MH: Review and approve
astral-sh/RustPython-Parser#22
* MH: Review and approve formatter PR
#5459
* CM: Review and approve linter PR
#5460
* Merge linter PR in formatter PR, fix ecosystem checks (ecosystem
checks can't run on the formatter PR and won't run on the linter PR, so
we need to merge them first)
 * Merge astral-sh/RustPython-Parser#22
 * Create tag in the parser, update linter+formatter PR
 * Merge linter+formatter PR #5459

---------

Co-authored-by: Micha Reiser <micha@reiser.io>

Author: konstin

Cargo.lock

@@ -54,12 +54,12 @@ libcst = { git = "https://github.com/Instagram/LibCST.git", rev = "3cacca1a1029f
 
 # Please tag the RustPython version every time you update its revision here and in fuzz/Cargo.toml
 # Tagging the version ensures that older ruff versions continue to build from source even when we rebase our RustPython fork.
-# Current tag: v0.0.7
-ruff_text_size = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "b996b21ffca562ecb2086f632a6a0b05c245c24a" }
-rustpython-ast = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "b996b21ffca562ecb2086f632a6a0b05c245c24a" , default-features = false, features = ["num-bigint"]}
-rustpython-format = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "b996b21ffca562ecb2086f632a6a0b05c245c24a", default-features = false, features = ["num-bigint"] }
-rustpython-literal = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "b996b21ffca562ecb2086f632a6a0b05c245c24a", default-features = false }
-rustpython-parser = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "b996b21ffca562ecb2086f632a6a0b05c245c24a" , default-features = false, features = ["full-lexer", "num-bigint"] }
+# Current tag: v0.0.9
+ruff_text_size = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "db04fd415774032e1e2ceb03bcbf5305e0d22c8c" }
+rustpython-ast = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "db04fd415774032e1e2ceb03bcbf5305e0d22c8c" , default-features = false, features = ["num-bigint"]}
+rustpython-format = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "db04fd415774032e1e2ceb03bcbf5305e0d22c8c", default-features = false, features = ["num-bigint"] }
+rustpython-literal = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "db04fd415774032e1e2ceb03bcbf5305e0d22c8c", default-features = false }
+rustpython-parser = { git = "https://github.com/astral-sh/RustPython-Parser.git", rev = "db04fd415774032e1e2ceb03bcbf5305e0d22c8c" , default-features = false, features = ["full-lexer", "num-bigint"] }
 
 [profile.release]
 lto = "fat"

Cargo.toml

@@ -97,3 +97,10 @@ def f():
 # variable name).
 for line_ in range(self.header_lines):
     fp.readline()
+
+# Regression test: visitor didn't walk the elif test
+for key, value in current_crawler_tags.items():
+    if key:
+        pass
+    elif wanted_tag_value != value:
+        pass

crates/ruff/resources/test/fixtures/flake8_bugbear/B007.py

@@ -100,6 +100,14 @@
     ):
         print("Bad module!")
 
+# SIM102
+# Regression test for https://github.com/apache/airflow/blob/145b16caaa43f0c42bffd97344df916c602cddde/airflow/configuration.py#L1161
+if a:
+    if b:
+        if c:
+            print("if")
+elif d:
+    print("elif")
 
 # OK
 if a:

crates/ruff/resources/test/fixtures/flake8_simplify/SIM102.py

@@ -23,7 +23,7 @@
 else:
     b = 2
 
-# OK (false negative)
+# SIM108
 if True:
     pass
 else:

crates/ruff/resources/test/fixtures/flake8_simplify/SIM108.py

@@ -94,3 +94,10 @@ def foo(p):
     errors = 1
 else:
     errors = 1
+
+if a:
+    # Ignore branches with diverging comments because it means we're repeating
+    # the bodies because we have different reasons for each branch
+    x = 1
+elif c:
+    x = 1

crates/ruff/resources/test/fixtures/flake8_simplify/SIM114.py

@@ -84,3 +84,15 @@
     return "D"
 elif func_name == "move":
     return "MV"
+
+# OK
+def no_return_in_else(platform):
+    if platform == "linux":
+        return "auditwheel repair -w {dest_dir} {wheel}"
+    elif platform == "macos":
+        return "delocate-wheel --require-archs {delocate_archs} -w {dest_dir} -v {wheel}"
+    elif platform == "windows":
+        return ""
+    else:
+        msg = f"Unknown platform: {platform!r}"
+        raise ValueError(msg)

crates/ruff/resources/test/fixtures/flake8_simplify/SIM116.py

@@ -38,6 +38,15 @@
 else:
     vars[idx] = "defaultß9💣2ℝ6789ß9💣2ℝ6789ß9💣2ℝ6789ß9💣2ℝ6789ß9💣2ℝ6789"
 
+# SIM401
+if foo():
+    pass
+else:
+    if key in a_dict:
+        vars[idx] = a_dict[key]
+    else:
+        vars[idx] = "default"
+
 ###
 # Negative cases
 ###
@@ -105,12 +114,3 @@
     vars[idx] = a_dict[key]
 else:
     vars[idx] = "default"
-
-# OK (false negative for nested else)
-if foo():
-    pass
-else:
-    if key in a_dict:
-        vars[idx] = a_dict[key]
-    else:
-        vars[idx] = "default"

crates/ruff/resources/test/fixtures/flake8_simplify/SIM401.py

@@ -1,6 +1,11 @@
 if (1, 2):
     pass
 
+if (3, 4):
+    pass
+elif foo:
+    pass
+
 for _ in range(5):
     if True:
         pass

crates/ruff/resources/test/fixtures/pyflakes/F634.py

@@ -0,0 +1,15 @@
+# Regression test for branch detection from
+# https://github.com/pypa/build/blob/5800521541e5e749d4429617420d1ef8cdb40b46/src/build/_importlib.py
+import sys
+
+if sys.version_info < (3, 8):
+    import importlib_metadata as metadata
+elif sys.version_info < (3, 9, 10) or (3, 10, 0) <= sys.version_info < (3, 10, 2):
+    try:
+        import importlib_metadata as metadata
+    except ModuleNotFoundError:
+        from importlib import metadata
+else:
+    from importlib import metadata
+
+__all__ = ["metadata"]

crates/ruff/resources/test/fixtures/pyflakes/F811_25.py

@@ -47,3 +47,17 @@ def not_ok1():
             pass
         else:
             pass
+
+
+# Regression test for https://github.com/apache/airflow/blob/f1e1cdcc3b2826e68ba133f350300b5065bbca33/airflow/models/dag.py#L1737
+def not_ok2():
+    if True:
+        print(1)
+    elif True:
+        print(2)
+    else:
+        if True:
+            print(3)
+        else:
+            print(4)
+

crates/ruff/resources/test/fixtures/pylint/collapsible_else_if.py

@@ -7,28 +7,28 @@
 
 if True:
     if foo:
-        pass
+        print()
     elif sys.version_info < (3, 3):
         cmd = [sys.executable, "-m", "test.regrtest"]
 
 if True:
     if foo:
-        pass
+        print()
     elif sys.version_info < (3, 3):
         cmd = [sys.executable, "-m", "test.regrtest"]
     elif foo:
         cmd = [sys.executable, "-m", "test", "-j0"]
 
     if foo:
-        pass
+        print()
     elif sys.version_info < (3, 3):
         cmd = [sys.executable, "-m", "test.regrtest"]
 
     if sys.version_info < (3, 3):
         cmd = [sys.executable, "-m", "test.regrtest"]
 
     if foo:
-        pass
+        print()
     elif sys.version_info < (3, 3):
         cmd = [sys.executable, "-m", "test.regrtest"]
     else:

crates/ruff/resources/test/fixtures/pyupgrade/UP036_4.py

@@ -230,6 +230,15 @@ def incorrect_multi_conditional(arg1, arg2):
         raise Exception("...")  # should be typeerror
 
 
+def multiple_is_instance_checks(some_arg):
+    if isinstance(some_arg, str):
+        pass
+    elif isinstance(some_arg, int):
+        pass
+    else:
+        raise Exception("...")   # should be typeerror
+
+
 class MyCustomTypeValidation(Exception):
     pass
 
@@ -296,6 +305,17 @@ def multiple_ifs(some_args):
                 pass
 
 
+def else_body(obj):
+    if isinstance(obj, datetime.timedelta):
+        return "TimeDelta"
+    elif isinstance(obj, relativedelta.relativedelta):
+        return "RelativeDelta"
+    elif isinstance(obj, CronExpression):
+        return "CronExpression"
+    else:
+        raise Exception(f"Unknown object type: {obj.__class__.__name__}")
+
+
 def early_return():
     if isinstance(this, some_type):
         if x in this:

crates/ruff/resources/test/fixtures/tryceratops/TRY004.py

@@ -190,12 +190,24 @@ fn is_lone_child(child: &Stmt, parent: &Stmt) -> bool {
         }
         Stmt::For(ast::StmtFor { body, orelse, .. })
         | Stmt::AsyncFor(ast::StmtAsyncFor { body, orelse, .. })
-        | Stmt::While(ast::StmtWhile { body, orelse, .. })
-        | Stmt::If(ast::StmtIf { body, orelse, .. }) => {
+        | Stmt::While(ast::StmtWhile { body, orelse, .. }) => {
             if is_only(body, child) || is_only(orelse, child) {
                 return true;
             }
         }
+        Stmt::If(ast::StmtIf {
+            body,
+            elif_else_clauses,
+            ..
+        }) => {
+            if is_only(body, child)
+                || elif_else_clauses
+                    .iter()
+                    .any(|ast::ElifElseClause { body, .. }| is_only(body, child))
+            {
+                return true;
+            }
+        }
         Stmt::Try(ast::StmtTry {
             body,
             handlers,