style: add pre-commit, typos and ruff, fix several

.pre-commit-config.yaml

@@ -0,0 +1,65 @@
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0  # Use the ref you want to point at
+    hooks:
+    -   id: check-added-large-files
+    -   id: check-case-conflict
+    -   id: check-executables-have-shebangs
+    -   id: check-merge-conflict
+    -   id: check-toml
+    -   id: check-vcs-permalinks
+    -   id: check-yaml
+    -   id: detect-private-key
+    -   id: end-of-file-fixer
+    -   id: fix-byte-order-marker
+    -   id: mixed-line-ending
+    # -   id: trailing-whitespace
+    # Python-specific
+    - id: check-ast
+    - id: check-docstring-first
+    - id: debug-statements
+
+-   repo: https://github.com/crate-ci/typos
+    rev: v1.16.23
+    hooks:
+    -   id: typos
+        args: []
+
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.7
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format
+
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: 'v1.3.0'
+    hooks:
+    - id: mypy
+      pass_filenames: false
+      args: [--package=guppy]
+      additional_dependencies: [
+        ormsgpack,
+        pydantic,
+      ]
+
+-   repo: local
+    hooks:
+    -   id: cargo-check
+        name: Cargo check
+        entry: bash -c 'cd validator && exec cargo check'
+        pass_filenames: false
+        types: [file, rust]
+        language: system
+    -   id: rust-linting
+        name: Rust linting
+        entry: bash -c 'cd validator && exec cargo fmt --all --'
+        pass_filenames: true
+        types: [file, rust]
+        language: system
+    -   id: rust-clippy
+        name: Rust clippy
+        entry: bash -c 'cd validator && exec cargo clippy --all-targets --all-features -- -Dclippy::all'
+        pass_filenames: false
+        types: [file, rust]
+        language: system

.typos.toml

@@ -0,0 +1,3 @@
+[default.extend-words]
+inot = "inot"
+fle = "fle"

MANIFEST.in

@@ -0,0 +1,12 @@
+include *.toml
+include *.txt
+include *.yaml
+recursive-include examples *.ipynb
+recursive-include guppy *.py
+recursive-include tests *.err
+recursive-include tests *.py
+recursive-include tests *.sh
+recursive-exclude validator *.lock
+recursive-exclude validator *.rs
+recursive-exclude validator *.toml
+exclude .git-blame-ignore-revs

README.md

@@ -30,7 +30,8 @@ pip install -e '.[dev]'
 
 ### Git blame
 
-You can configure Git to ignore formatting commits when using `git blame` by running 
+You can configure Git to ignore formatting commits when using `git blame` by running
+
 ```sh
 git config blame.ignoreRevsFile .git-blame-ignore-revs
 ```
@@ -41,14 +42,14 @@ TODO
 
 ## Testing
 
-First, build the PyO3 Hugr validation library using
+First, build the PyO3 Hugr validation library from the `validator` directory using
+
 ```sh
 maturin develop
 ```
 
-from the `validator` directory.
-
 Run tests using
+
 ```sh
 pytest -v
 ```
@@ -59,6 +60,7 @@ Integration test cases can be exported to a directory using
 pytest --export-test-cases=guppy-exports
 
 ```
+
 which will create a directory `./guppy-exports` populated with hugr modules serialised in msgpack.
 
 ## Packaging

guppy/ast_util.py

@@ -1,19 +1,19 @@
 import ast
-from typing import Any, TypeVar, Generic, Union, Optional, TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, Generic, Optional, TypeVar
 
 if TYPE_CHECKING:
     from guppy.gtypes import GuppyType
 
-AstNode = Union[
-    ast.AST,
-    ast.operator,
-    ast.expr,
-    ast.arg,
-    ast.stmt,
-    ast.Name,
-    ast.keyword,
-    ast.FunctionDef,
-]
+AstNode = (
+    ast.AST
+    | ast.operator
+    | ast.expr
+    | ast.arg
+    | ast.stmt
+    | ast.Name
+    | ast.keyword
+    | ast.FunctionDef
+)
 
 T = TypeVar("T", covariant=True)
 
@@ -114,7 +114,9 @@ def set_location_from(node: ast.AST, loc: ast.AST) -> None:
     node.end_col_offset = loc.end_col_offset
 
     source, file, line_offset = get_source(loc), get_file(loc), get_line_offset(loc)
-    assert source is not None and file is not None and line_offset is not None
+    assert source is not None
+    assert file is not None
+    assert line_offset is not None
     annotate_location(node, source, file, line_offset)
 
 
@@ -126,7 +128,7 @@ def annotate_location(
     setattr(node, "source", source)
 
     if recurse:
-        for field, value in ast.iter_fields(node):
+        for _field, value in ast.iter_fields(node):
             if isinstance(value, list):
                 for item in value:
                     if isinstance(item, ast.AST):
@@ -135,7 +137,7 @@ def annotate_location(
                 annotate_location(value, source, file, line_offset, recurse)
 
 
-def get_file(node: AstNode) -> Optional[str]:
+def get_file(node: AstNode) -> str | None:
     """Tries to retrieve a file annotation from an AST node."""
     try:
         file = getattr(node, "file")
@@ -144,7 +146,7 @@ def get_file(node: AstNode) -> Optional[str]:
         return None
 
 
-def get_source(node: AstNode) -> Optional[str]:
+def get_source(node: AstNode) -> str | None:
     """Tries to retrieve a source annotation from an AST node."""
     try:
         source = getattr(node, "source")
@@ -153,7 +155,7 @@ def get_source(node: AstNode) -> Optional[str]:
         return None
 
 
-def get_line_offset(node: AstNode) -> Optional[int]:
+def get_line_offset(node: AstNode) -> int | None:
     """Tries to retrieve a line offset annotation from an AST node."""
     try:
         line_offset = getattr(node, "line_offset")

guppy/cfg/analysis.py

@@ -1,9 +1,9 @@
 from abc import ABC, abstractmethod
-from typing import TypeVar, Generic, Iterable
+from collections.abc import Iterable
+from typing import Generic, TypeVar
 
 from guppy.cfg.bb import BB
 
-
 # Type variable for the lattice domain
 T = TypeVar("T")
 
@@ -21,20 +21,17 @@ def eq(self, t1: T, t2: T, /) -> bool:
     @abstractmethod
     def initial(self) -> T:
         """Initial lattice value"""
-        pass
 
     @abstractmethod
     def join(self, *ts: T) -> T:
         """Lattice join operation"""
-        pass
 
     @abstractmethod
     def run(self, bbs: Iterable[BB]) -> Result[T]:
         """Runs the analysis pass.
 
         Returns a mapping from basic blocks to lattice values at the start of each BB.
         """
-        pass
 
 
 class ForwardAnalysis(Analysis[T], ABC, Generic[T]):
@@ -43,7 +40,6 @@ class ForwardAnalysis(Analysis[T], ABC, Generic[T]):
     @abstractmethod
     def apply_bb(self, val_before: T, bb: BB, /) -> T:
         """Transformation a basic block applies to a lattice value"""
-        pass
 
     def run(self, bbs: Iterable[BB]) -> Result[T]:
         """Runs the analysis pass.
@@ -69,7 +65,6 @@ class BackwardAnalysis(Analysis[T], ABC, Generic[T]):
     @abstractmethod
     def apply_bb(self, val_after: T, bb: BB, /) -> T:
         """Transformation a basic block applies to a lattice value"""
-        pass
 
     def run(self, bbs: Iterable[BB]) -> Result[T]:
         """Runs the analysis pass.
@@ -106,7 +101,7 @@ def eq(self, live1: LivenessDomain, live2: LivenessDomain) -> bool:
         return live1.keys() == live2.keys()
 
     def initial(self) -> LivenessDomain:
-        return dict()
+        return {}
 
     def join(self, *ts: LivenessDomain) -> LivenessDomain:
         res: LivenessDomain = {}

guppy/cfg/bb.py

@@ -1,7 +1,8 @@
 import ast
 from abc import ABC
 from dataclasses import dataclass, field
-from typing import Optional, TYPE_CHECKING, Union
+from typing import TYPE_CHECKING
+
 from typing_extensions import Self
 
 from guppy.ast_util import AstNode, name_nodes_in_ast
@@ -34,9 +35,14 @@ def update_used(self, node: ast.AST) -> None:
                 self.used[name.id] = name
 
 
-BBStatement = Union[
-    ast.Assign, ast.AugAssign, ast.AnnAssign, ast.Expr, ast.Return, NestedFunctionDef
-]
+BBStatement = (
+    ast.Assign
+    | ast.AugAssign
+    | ast.AnnAssign
+    | ast.Expr
+    | ast.Return
+    | NestedFunctionDef
+)
 
 
 @dataclass(eq=False)  # Disable equality to recover hash from `object`
@@ -57,10 +63,10 @@ class BB(ABC):
 
     # If the BB has multiple successors, we need a predicate to decide to which one to
     # jump to
-    branch_pred: Optional[ast.expr] = None
+    branch_pred: ast.expr | None = None
 
     # Information about assigned/used variables in the BB
-    _vars: Optional[VariableStats] = None
+    _vars: VariableStats | None = None
 
     @property
     def vars(self) -> VariableStats:
@@ -123,9 +129,7 @@ def visit_NestedFunctionDef(self, node: NestedFunctionDef) -> None:
         # Only store used *external* variables: things defined in the current BB, as
         # well as the function name and argument names should not be included
         assigned_before_in_bb = (
-            self.stats.assigned.keys()
-            | {node.name}
-            | set(a.arg for a in node.args.args)
+            self.stats.assigned.keys() | {node.name} | {a.arg for a in node.args.args}
         )
         self.stats.used |= {
             x: using_bb.vars.used[x]