diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-17 12:02:58 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-17 12:02:58 +0000 |
commit | 698f8c2f01ea549d77d7dc3338a12e04c11057b9 (patch) | |
tree | 173a775858bd501c378080a10dca74132f05bc50 /compiler/rustc_mir_build/src/thir/pattern/usefulness.rs | |
parent | Initial commit. (diff) | |
download | rustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.tar.xz rustc-698f8c2f01ea549d77d7dc3338a12e04c11057b9.zip |
Adding upstream version 1.64.0+dfsg1.upstream/1.64.0+dfsg1
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'compiler/rustc_mir_build/src/thir/pattern/usefulness.rs')
-rw-r--r-- | compiler/rustc_mir_build/src/thir/pattern/usefulness.rs | 978 |
1 files changed, 978 insertions, 0 deletions
diff --git a/compiler/rustc_mir_build/src/thir/pattern/usefulness.rs b/compiler/rustc_mir_build/src/thir/pattern/usefulness.rs new file mode 100644 index 000000000..0a660ef30 --- /dev/null +++ b/compiler/rustc_mir_build/src/thir/pattern/usefulness.rs @@ -0,0 +1,978 @@ +//! Note: tests specific to this file can be found in: +//! +//! - `ui/pattern/usefulness` +//! - `ui/or-patterns` +//! - `ui/consts/const_in_pattern` +//! - `ui/rfc-2008-non-exhaustive` +//! - `ui/half-open-range-patterns` +//! - probably many others +//! +//! I (Nadrieril) prefer to put new tests in `ui/pattern/usefulness` unless there's a specific +//! reason not to, for example if they depend on a particular feature like `or_patterns`. +//! +//! ----- +//! +//! This file includes the logic for exhaustiveness and reachability checking for pattern-matching. +//! Specifically, given a list of patterns for a type, we can tell whether: +//! (a) each pattern is reachable (reachability) +//! (b) the patterns cover every possible value for the type (exhaustiveness) +//! +//! The algorithm implemented here is a modified version of the one described in [this +//! paper](http://moscova.inria.fr/~maranget/papers/warn/index.html). We have however generalized +//! it to accommodate the variety of patterns that Rust supports. We thus explain our version here, +//! without being as rigorous. +//! +//! +//! # Summary +//! +//! The core of the algorithm is the notion of "usefulness". A pattern `q` is said to be *useful* +//! relative to another pattern `p` of the same type if there is a value that is matched by `q` and +//! not matched by `p`. This generalizes to many `p`s: `q` is useful w.r.t. a list of patterns +//! `p_1 .. p_n` if there is a value that is matched by `q` and by none of the `p_i`. We write +//! `usefulness(p_1 .. p_n, q)` for a function that returns a list of such values. The aim of this +//! file is to compute it efficiently. +//! +//! This is enough to compute reachability: a pattern in a `match` expression is reachable iff it +//! is useful w.r.t. the patterns above it: +//! ```rust +//! # fn foo(x: Option<i32>) { +//! match x { +//! Some(_) => {}, +//! None => {}, // reachable: `None` is matched by this but not the branch above +//! Some(0) => {}, // unreachable: all the values this matches are already matched by +//! // `Some(_)` above +//! } +//! # } +//! ``` +//! +//! This is also enough to compute exhaustiveness: a match is exhaustive iff the wildcard `_` +//! pattern is _not_ useful w.r.t. the patterns in the match. The values returned by `usefulness` +//! are used to tell the user which values are missing. +//! ```compile_fail,E0004 +//! # fn foo(x: Option<i32>) { +//! match x { +//! Some(0) => {}, +//! None => {}, +//! // not exhaustive: `_` is useful because it matches `Some(1)` +//! } +//! # } +//! ``` +//! +//! The entrypoint of this file is the [`compute_match_usefulness`] function, which computes +//! reachability for each match branch and exhaustiveness for the whole match. +//! +//! +//! # Constructors and fields +//! +//! Note: we will often abbreviate "constructor" as "ctor". +//! +//! The idea that powers everything that is done in this file is the following: a (matchable) +//! value is made from a constructor applied to a number of subvalues. Examples of constructors are +//! `Some`, `None`, `(,)` (the 2-tuple constructor), `Foo {..}` (the constructor for a struct +//! `Foo`), and `2` (the constructor for the number `2`). This is natural when we think of +//! pattern-matching, and this is the basis for what follows. +//! +//! Some of the ctors listed above might feel weird: `None` and `2` don't take any arguments. +//! That's ok: those are ctors that take a list of 0 arguments; they are the simplest case of +//! ctors. We treat `2` as a ctor because `u64` and other number types behave exactly like a huge +//! `enum`, with one variant for each number. This allows us to see any matchable value as made up +//! from a tree of ctors, each having a set number of children. For example: `Foo { bar: None, +//! baz: Ok(0) }` is made from 4 different ctors, namely `Foo{..}`, `None`, `Ok` and `0`. +//! +//! This idea can be extended to patterns: they are also made from constructors applied to fields. +//! A pattern for a given type is allowed to use all the ctors for values of that type (which we +//! call "value constructors"), but there are also pattern-only ctors. The most important one is +//! the wildcard (`_`), and the others are integer ranges (`0..=10`), variable-length slices (`[x, +//! ..]`), and or-patterns (`Ok(0) | Err(_)`). Examples of valid patterns are `42`, `Some(_)`, `Foo +//! { bar: Some(0) | None, baz: _ }`. Note that a binder in a pattern (e.g. `Some(x)`) matches the +//! same values as a wildcard (e.g. `Some(_)`), so we treat both as wildcards. +//! +//! From this deconstruction we can compute whether a given value matches a given pattern; we +//! simply look at ctors one at a time. Given a pattern `p` and a value `v`, we want to compute +//! `matches!(v, p)`. It's mostly straightforward: we compare the head ctors and when they match +//! we compare their fields recursively. A few representative examples: +//! +//! - `matches!(v, _) := true` +//! - `matches!((v0, v1), (p0, p1)) := matches!(v0, p0) && matches!(v1, p1)` +//! - `matches!(Foo { bar: v0, baz: v1 }, Foo { bar: p0, baz: p1 }) := matches!(v0, p0) && matches!(v1, p1)` +//! - `matches!(Ok(v0), Ok(p0)) := matches!(v0, p0)` +//! - `matches!(Ok(v0), Err(p0)) := false` (incompatible variants) +//! - `matches!(v, 1..=100) := matches!(v, 1) || ... || matches!(v, 100)` +//! - `matches!([v0], [p0, .., p1]) := false` (incompatible lengths) +//! - `matches!([v0, v1, v2], [p0, .., p1]) := matches!(v0, p0) && matches!(v2, p1)` +//! - `matches!(v, p0 | p1) := matches!(v, p0) || matches!(v, p1)` +//! +//! Constructors, fields and relevant operations are defined in the [`super::deconstruct_pat`] module. +//! +//! Note: this constructors/fields distinction may not straightforwardly apply to every Rust type. +//! For example a value of type `Rc<u64>` can't be deconstructed that way, and `&str` has an +//! infinitude of constructors. There are also subtleties with visibility of fields and +//! uninhabitedness and various other things. The constructors idea can be extended to handle most +//! of these subtleties though; caveats are documented where relevant throughout the code. +//! +//! Whether constructors cover each other is computed by [`Constructor::is_covered_by`]. +//! +//! +//! # Specialization +//! +//! Recall that we wish to compute `usefulness(p_1 .. p_n, q)`: given a list of patterns `p_1 .. +//! p_n` and a pattern `q`, all of the same type, we want to find a list of values (called +//! "witnesses") that are matched by `q` and by none of the `p_i`. We obviously don't just +//! enumerate all possible values. From the discussion above we see that we can proceed +//! ctor-by-ctor: for each value ctor of the given type, we ask "is there a value that starts with +//! this constructor and matches `q` and none of the `p_i`?". As we saw above, there's a lot we can +//! say from knowing only the first constructor of our candidate value. +//! +//! Let's take the following example: +//! ```compile_fail,E0004 +//! # enum Enum { Variant1(()), Variant2(Option<bool>, u32)} +//! # fn foo(x: Enum) { +//! match x { +//! Enum::Variant1(_) => {} // `p1` +//! Enum::Variant2(None, 0) => {} // `p2` +//! Enum::Variant2(Some(_), 0) => {} // `q` +//! } +//! # } +//! ``` +//! +//! We can easily see that if our candidate value `v` starts with `Variant1` it will not match `q`. +//! If `v = Variant2(v0, v1)` however, whether or not it matches `p2` and `q` will depend on `v0` +//! and `v1`. In fact, such a `v` will be a witness of usefulness of `q` exactly when the tuple +//! `(v0, v1)` is a witness of usefulness of `q'` in the following reduced match: +//! +//! ```compile_fail,E0004 +//! # fn foo(x: (Option<bool>, u32)) { +//! match x { +//! (None, 0) => {} // `p2'` +//! (Some(_), 0) => {} // `q'` +//! } +//! # } +//! ``` +//! +//! This motivates a new step in computing usefulness, that we call _specialization_. +//! Specialization consist of filtering a list of patterns for those that match a constructor, and +//! then looking into the constructor's fields. This enables usefulness to be computed recursively. +//! +//! Instead of acting on a single pattern in each row, we will consider a list of patterns for each +//! row, and we call such a list a _pattern-stack_. The idea is that we will specialize the +//! leftmost pattern, which amounts to popping the constructor and pushing its fields, which feels +//! like a stack. We note a pattern-stack simply with `[p_1 ... p_n]`. +//! Here's a sequence of specializations of a list of pattern-stacks, to illustrate what's +//! happening: +//! ```ignore (illustrative) +//! [Enum::Variant1(_)] +//! [Enum::Variant2(None, 0)] +//! [Enum::Variant2(Some(_), 0)] +//! //==>> specialize with `Variant2` +//! [None, 0] +//! [Some(_), 0] +//! //==>> specialize with `Some` +//! [_, 0] +//! //==>> specialize with `true` (say the type was `bool`) +//! [0] +//! //==>> specialize with `0` +//! [] +//! ``` +//! +//! The function `specialize(c, p)` takes a value constructor `c` and a pattern `p`, and returns 0 +//! or more pattern-stacks. If `c` does not match the head constructor of `p`, it returns nothing; +//! otherwise if returns the fields of the constructor. This only returns more than one +//! pattern-stack if `p` has a pattern-only constructor. +//! +//! - Specializing for the wrong constructor returns nothing +//! +//! `specialize(None, Some(p0)) := []` +//! +//! - Specializing for the correct constructor returns a single row with the fields +//! +//! `specialize(Variant1, Variant1(p0, p1, p2)) := [[p0, p1, p2]]` +//! +//! `specialize(Foo{..}, Foo { bar: p0, baz: p1 }) := [[p0, p1]]` +//! +//! - For or-patterns, we specialize each branch and concatenate the results +//! +//! `specialize(c, p0 | p1) := specialize(c, p0) ++ specialize(c, p1)` +//! +//! - We treat the other pattern constructors as if they were a large or-pattern of all the +//! possibilities: +//! +//! `specialize(c, _) := specialize(c, Variant1(_) | Variant2(_, _) | ...)` +//! +//! `specialize(c, 1..=100) := specialize(c, 1 | ... | 100)` +//! +//! `specialize(c, [p0, .., p1]) := specialize(c, [p0, p1] | [p0, _, p1] | [p0, _, _, p1] | ...)` +//! +//! - If `c` is a pattern-only constructor, `specialize` is defined on a case-by-case basis. See +//! the discussion about constructor splitting in [`super::deconstruct_pat`]. +//! +//! +//! We then extend this function to work with pattern-stacks as input, by acting on the first +//! column and keeping the other columns untouched. +//! +//! Specialization for the whole matrix is done in [`Matrix::specialize_constructor`]. Note that +//! or-patterns in the first column are expanded before being stored in the matrix. Specialization +//! for a single patstack is done from a combination of [`Constructor::is_covered_by`] and +//! [`PatStack::pop_head_constructor`]. The internals of how it's done mostly live in the +//! [`Fields`] struct. +//! +//! +//! # Computing usefulness +//! +//! We now have all we need to compute usefulness. The inputs to usefulness are a list of +//! pattern-stacks `p_1 ... p_n` (one per row), and a new pattern_stack `q`. The paper and this +//! file calls the list of patstacks a _matrix_. They must all have the same number of columns and +//! the patterns in a given column must all have the same type. `usefulness` returns a (possibly +//! empty) list of witnesses of usefulness. These witnesses will also be pattern-stacks. +//! +//! - base case: `n_columns == 0`. +//! Since a pattern-stack functions like a tuple of patterns, an empty one functions like the +//! unit type. Thus `q` is useful iff there are no rows above it, i.e. if `n == 0`. +//! +//! - inductive case: `n_columns > 0`. +//! We need a way to list the constructors we want to try. We will be more clever in the next +//! section but for now assume we list all value constructors for the type of the first column. +//! +//! - for each such ctor `c`: +//! +//! - for each `q'` returned by `specialize(c, q)`: +//! +//! - we compute `usefulness(specialize(c, p_1) ... specialize(c, p_n), q')` +//! +//! - for each witness found, we revert specialization by pushing the constructor `c` on top. +//! +//! - We return the concatenation of all the witnesses found, if any. +//! +//! Example: +//! ```ignore (illustrative) +//! [Some(true)] // p_1 +//! [None] // p_2 +//! [Some(_)] // q +//! //==>> try `None`: `specialize(None, q)` returns nothing +//! //==>> try `Some`: `specialize(Some, q)` returns a single row +//! [true] // p_1' +//! [_] // q' +//! //==>> try `true`: `specialize(true, q')` returns a single row +//! [] // p_1'' +//! [] // q'' +//! //==>> base case; `n != 0` so `q''` is not useful. +//! //==>> go back up a step +//! [true] // p_1' +//! [_] // q' +//! //==>> try `false`: `specialize(false, q')` returns a single row +//! [] // q'' +//! //==>> base case; `n == 0` so `q''` is useful. We return the single witness `[]` +//! witnesses: +//! [] +//! //==>> undo the specialization with `false` +//! witnesses: +//! [false] +//! //==>> undo the specialization with `Some` +//! witnesses: +//! [Some(false)] +//! //==>> we have tried all the constructors. The output is the single witness `[Some(false)]`. +//! ``` +//! +//! This computation is done in [`is_useful`]. In practice we don't care about the list of +//! witnesses when computing reachability; we only need to know whether any exist. We do keep the +//! witnesses when computing exhaustiveness to report them to the user. +//! +//! +//! # Making usefulness tractable: constructor splitting +//! +//! We're missing one last detail: which constructors do we list? Naively listing all value +//! constructors cannot work for types like `u64` or `&str`, so we need to be more clever. The +//! first obvious insight is that we only want to list constructors that are covered by the head +//! constructor of `q`. If it's a value constructor, we only try that one. If it's a pattern-only +//! constructor, we use the final clever idea for this algorithm: _constructor splitting_, where we +//! group together constructors that behave the same. +//! +//! The details are not necessary to understand this file, so we explain them in +//! [`super::deconstruct_pat`]. Splitting is done by the [`Constructor::split`] function. + +use self::ArmType::*; +use self::Usefulness::*; + +use super::check_match::{joined_uncovered_patterns, pattern_not_covered_label}; +use super::deconstruct_pat::{Constructor, DeconstructedPat, Fields, SplitWildcard}; + +use rustc_data_structures::captures::Captures; + +use rustc_arena::TypedArena; +use rustc_data_structures::stack::ensure_sufficient_stack; +use rustc_hir::def_id::DefId; +use rustc_hir::HirId; +use rustc_middle::ty::{self, Ty, TyCtxt}; +use rustc_session::lint::builtin::NON_EXHAUSTIVE_OMITTED_PATTERNS; +use rustc_span::{Span, DUMMY_SP}; + +use smallvec::{smallvec, SmallVec}; +use std::fmt; +use std::iter::once; + +pub(crate) struct MatchCheckCtxt<'p, 'tcx> { + pub(crate) tcx: TyCtxt<'tcx>, + /// The module in which the match occurs. This is necessary for + /// checking inhabited-ness of types because whether a type is (visibly) + /// inhabited can depend on whether it was defined in the current module or + /// not. E.g., `struct Foo { _private: ! }` cannot be seen to be empty + /// outside its module and should not be matchable with an empty match statement. + pub(crate) module: DefId, + pub(crate) param_env: ty::ParamEnv<'tcx>, + pub(crate) pattern_arena: &'p TypedArena<DeconstructedPat<'p, 'tcx>>, +} + +impl<'a, 'tcx> MatchCheckCtxt<'a, 'tcx> { + pub(super) fn is_uninhabited(&self, ty: Ty<'tcx>) -> bool { + if self.tcx.features().exhaustive_patterns { + self.tcx.is_ty_uninhabited_from(self.module, ty, self.param_env) + } else { + false + } + } + + /// Returns whether the given type is an enum from another crate declared `#[non_exhaustive]`. + pub(super) fn is_foreign_non_exhaustive_enum(&self, ty: Ty<'tcx>) -> bool { + match ty.kind() { + ty::Adt(def, ..) => { + def.is_enum() && def.is_variant_list_non_exhaustive() && !def.did().is_local() + } + _ => false, + } + } +} + +#[derive(Copy, Clone)] +pub(super) struct PatCtxt<'a, 'p, 'tcx> { + pub(super) cx: &'a MatchCheckCtxt<'p, 'tcx>, + /// Type of the current column under investigation. + pub(super) ty: Ty<'tcx>, + /// Span of the current pattern under investigation. + pub(super) span: Span, + /// Whether the current pattern is the whole pattern as found in a match arm, or if it's a + /// subpattern. + pub(super) is_top_level: bool, + /// Whether the current pattern is from a `non_exhaustive` enum. + pub(super) is_non_exhaustive: bool, +} + +impl<'a, 'p, 'tcx> fmt::Debug for PatCtxt<'a, 'p, 'tcx> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_struct("PatCtxt").field("ty", &self.ty).finish() + } +} + +/// A row of a matrix. Rows of len 1 are very common, which is why `SmallVec[_; 2]` +/// works well. +#[derive(Clone)] +struct PatStack<'p, 'tcx> { + pats: SmallVec<[&'p DeconstructedPat<'p, 'tcx>; 2]>, +} + +impl<'p, 'tcx> PatStack<'p, 'tcx> { + fn from_pattern(pat: &'p DeconstructedPat<'p, 'tcx>) -> Self { + Self::from_vec(smallvec![pat]) + } + + fn from_vec(vec: SmallVec<[&'p DeconstructedPat<'p, 'tcx>; 2]>) -> Self { + PatStack { pats: vec } + } + + fn is_empty(&self) -> bool { + self.pats.is_empty() + } + + fn len(&self) -> usize { + self.pats.len() + } + + fn head(&self) -> &'p DeconstructedPat<'p, 'tcx> { + self.pats[0] + } + + fn iter(&self) -> impl Iterator<Item = &DeconstructedPat<'p, 'tcx>> { + self.pats.iter().copied() + } + + // Recursively expand the first pattern into its subpatterns. Only useful if the pattern is an + // or-pattern. Panics if `self` is empty. + fn expand_or_pat<'a>(&'a self) -> impl Iterator<Item = PatStack<'p, 'tcx>> + Captures<'a> { + self.head().iter_fields().map(move |pat| { + let mut new_patstack = PatStack::from_pattern(pat); + new_patstack.pats.extend_from_slice(&self.pats[1..]); + new_patstack + }) + } + + /// This computes `S(self.head().ctor(), self)`. See top of the file for explanations. + /// + /// Structure patterns with a partial wild pattern (Foo { a: 42, .. }) have their missing + /// fields filled with wild patterns. + /// + /// This is roughly the inverse of `Constructor::apply`. + fn pop_head_constructor( + &self, + pcx: &PatCtxt<'_, 'p, 'tcx>, + ctor: &Constructor<'tcx>, + ) -> PatStack<'p, 'tcx> { + // We pop the head pattern and push the new fields extracted from the arguments of + // `self.head()`. + let mut new_fields: SmallVec<[_; 2]> = self.head().specialize(pcx, ctor); + new_fields.extend_from_slice(&self.pats[1..]); + PatStack::from_vec(new_fields) + } +} + +/// Pretty-printing for matrix row. +impl<'p, 'tcx> fmt::Debug for PatStack<'p, 'tcx> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "+")?; + for pat in self.iter() { + write!(f, " {:?} +", pat)?; + } + Ok(()) + } +} + +/// A 2D matrix. +#[derive(Clone)] +pub(super) struct Matrix<'p, 'tcx> { + patterns: Vec<PatStack<'p, 'tcx>>, +} + +impl<'p, 'tcx> Matrix<'p, 'tcx> { + fn empty() -> Self { + Matrix { patterns: vec![] } + } + + /// Number of columns of this matrix. `None` is the matrix is empty. + pub(super) fn column_count(&self) -> Option<usize> { + self.patterns.get(0).map(|r| r.len()) + } + + /// Pushes a new row to the matrix. If the row starts with an or-pattern, this recursively + /// expands it. + fn push(&mut self, row: PatStack<'p, 'tcx>) { + if !row.is_empty() && row.head().is_or_pat() { + self.patterns.extend(row.expand_or_pat()); + } else { + self.patterns.push(row); + } + } + + /// Iterate over the first component of each row + fn heads<'a>( + &'a self, + ) -> impl Iterator<Item = &'p DeconstructedPat<'p, 'tcx>> + Clone + Captures<'a> { + self.patterns.iter().map(|r| r.head()) + } + + /// This computes `S(constructor, self)`. See top of the file for explanations. + fn specialize_constructor( + &self, + pcx: &PatCtxt<'_, 'p, 'tcx>, + ctor: &Constructor<'tcx>, + ) -> Matrix<'p, 'tcx> { + let mut matrix = Matrix::empty(); + for row in &self.patterns { + if ctor.is_covered_by(pcx, row.head().ctor()) { + let new_row = row.pop_head_constructor(pcx, ctor); + matrix.push(new_row); + } + } + matrix + } +} + +/// Pretty-printer for matrices of patterns, example: +/// +/// ```text +/// + _ + [] + +/// + true + [First] + +/// + true + [Second(true)] + +/// + false + [_] + +/// + _ + [_, _, tail @ ..] + +/// ``` +impl<'p, 'tcx> fmt::Debug for Matrix<'p, 'tcx> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + write!(f, "\n")?; + + let Matrix { patterns: m, .. } = self; + let pretty_printed_matrix: Vec<Vec<String>> = + m.iter().map(|row| row.iter().map(|pat| format!("{:?}", pat)).collect()).collect(); + + let column_count = m.iter().map(|row| row.len()).next().unwrap_or(0); + assert!(m.iter().all(|row| row.len() == column_count)); + let column_widths: Vec<usize> = (0..column_count) + .map(|col| pretty_printed_matrix.iter().map(|row| row[col].len()).max().unwrap_or(0)) + .collect(); + + for row in pretty_printed_matrix { + write!(f, "+")?; + for (column, pat_str) in row.into_iter().enumerate() { + write!(f, " ")?; + write!(f, "{:1$}", pat_str, column_widths[column])?; + write!(f, " +")?; + } + write!(f, "\n")?; + } + Ok(()) + } +} + +/// This carries the results of computing usefulness, as described at the top of the file. When +/// checking usefulness of a match branch, we use the `NoWitnesses` variant, which also keeps track +/// of potential unreachable sub-patterns (in the presence of or-patterns). When checking +/// exhaustiveness of a whole match, we use the `WithWitnesses` variant, which carries a list of +/// witnesses of non-exhaustiveness when there are any. +/// Which variant to use is dictated by `ArmType`. +#[derive(Debug)] +enum Usefulness<'p, 'tcx> { + /// If we don't care about witnesses, simply remember if the pattern was useful. + NoWitnesses { useful: bool }, + /// Carries a list of witnesses of non-exhaustiveness. If empty, indicates that the whole + /// pattern is unreachable. + WithWitnesses(Vec<Witness<'p, 'tcx>>), +} + +impl<'p, 'tcx> Usefulness<'p, 'tcx> { + fn new_useful(preference: ArmType) -> Self { + match preference { + // A single (empty) witness of reachability. + FakeExtraWildcard => WithWitnesses(vec![Witness(vec![])]), + RealArm => NoWitnesses { useful: true }, + } + } + + fn new_not_useful(preference: ArmType) -> Self { + match preference { + FakeExtraWildcard => WithWitnesses(vec![]), + RealArm => NoWitnesses { useful: false }, + } + } + + fn is_useful(&self) -> bool { + match self { + Usefulness::NoWitnesses { useful } => *useful, + Usefulness::WithWitnesses(witnesses) => !witnesses.is_empty(), + } + } + + /// Combine usefulnesses from two branches. This is an associative operation. + fn extend(&mut self, other: Self) { + match (&mut *self, other) { + (WithWitnesses(_), WithWitnesses(o)) if o.is_empty() => {} + (WithWitnesses(s), WithWitnesses(o)) if s.is_empty() => *self = WithWitnesses(o), + (WithWitnesses(s), WithWitnesses(o)) => s.extend(o), + (NoWitnesses { useful: s_useful }, NoWitnesses { useful: o_useful }) => { + *s_useful = *s_useful || o_useful + } + _ => unreachable!(), + } + } + + /// After calculating usefulness after a specialization, call this to reconstruct a usefulness + /// that makes sense for the matrix pre-specialization. This new usefulness can then be merged + /// with the results of specializing with the other constructors. + fn apply_constructor( + self, + pcx: &PatCtxt<'_, 'p, 'tcx>, + matrix: &Matrix<'p, 'tcx>, // used to compute missing ctors + ctor: &Constructor<'tcx>, + ) -> Self { + match self { + NoWitnesses { .. } => self, + WithWitnesses(ref witnesses) if witnesses.is_empty() => self, + WithWitnesses(witnesses) => { + let new_witnesses = if let Constructor::Missing { .. } = ctor { + // We got the special `Missing` constructor, so each of the missing constructors + // gives a new pattern that is not caught by the match. We list those patterns. + let new_patterns = if pcx.is_non_exhaustive { + // Here we don't want the user to try to list all variants, we want them to add + // a wildcard, so we only suggest that. + vec![DeconstructedPat::wildcard(pcx.ty)] + } else { + let mut split_wildcard = SplitWildcard::new(pcx); + split_wildcard.split(pcx, matrix.heads().map(DeconstructedPat::ctor)); + + // This lets us know if we skipped any variants because they are marked + // `doc(hidden)` or they are unstable feature gate (only stdlib types). + let mut hide_variant_show_wild = false; + // Construct for each missing constructor a "wild" version of this + // constructor, that matches everything that can be built with + // it. For example, if `ctor` is a `Constructor::Variant` for + // `Option::Some`, we get the pattern `Some(_)`. + let mut new: Vec<DeconstructedPat<'_, '_>> = split_wildcard + .iter_missing(pcx) + .filter_map(|missing_ctor| { + // Check if this variant is marked `doc(hidden)` + if missing_ctor.is_doc_hidden_variant(pcx) + || missing_ctor.is_unstable_variant(pcx) + { + hide_variant_show_wild = true; + return None; + } + Some(DeconstructedPat::wild_from_ctor(pcx, missing_ctor.clone())) + }) + .collect(); + + if hide_variant_show_wild { + new.push(DeconstructedPat::wildcard(pcx.ty)); + } + + new + }; + + witnesses + .into_iter() + .flat_map(|witness| { + new_patterns.iter().map(move |pat| { + Witness( + witness + .0 + .iter() + .chain(once(pat)) + .map(DeconstructedPat::clone_and_forget_reachability) + .collect(), + ) + }) + }) + .collect() + } else { + witnesses + .into_iter() + .map(|witness| witness.apply_constructor(pcx, &ctor)) + .collect() + }; + WithWitnesses(new_witnesses) + } + } + } +} + +#[derive(Copy, Clone, Debug)] +enum ArmType { + FakeExtraWildcard, + RealArm, +} + +/// A witness of non-exhaustiveness for error reporting, represented +/// as a list of patterns (in reverse order of construction) with +/// wildcards inside to represent elements that can take any inhabitant +/// of the type as a value. +/// +/// A witness against a list of patterns should have the same types +/// and length as the pattern matched against. Because Rust `match` +/// is always against a single pattern, at the end the witness will +/// have length 1, but in the middle of the algorithm, it can contain +/// multiple patterns. +/// +/// For example, if we are constructing a witness for the match against +/// +/// ```compile_fail,E0004 +/// # #![feature(type_ascription)] +/// struct Pair(Option<(u32, u32)>, bool); +/// # fn foo(p: Pair) { +/// match (p: Pair) { +/// Pair(None, _) => {} +/// Pair(_, false) => {} +/// } +/// # } +/// ``` +/// +/// We'll perform the following steps: +/// 1. Start with an empty witness +/// `Witness(vec![])` +/// 2. Push a witness `true` against the `false` +/// `Witness(vec![true])` +/// 3. Push a witness `Some(_)` against the `None` +/// `Witness(vec![true, Some(_)])` +/// 4. Apply the `Pair` constructor to the witnesses +/// `Witness(vec![Pair(Some(_), true)])` +/// +/// The final `Pair(Some(_), true)` is then the resulting witness. +#[derive(Debug)] +pub(crate) struct Witness<'p, 'tcx>(Vec<DeconstructedPat<'p, 'tcx>>); + +impl<'p, 'tcx> Witness<'p, 'tcx> { + /// Asserts that the witness contains a single pattern, and returns it. + fn single_pattern(self) -> DeconstructedPat<'p, 'tcx> { + assert_eq!(self.0.len(), 1); + self.0.into_iter().next().unwrap() + } + + /// Constructs a partial witness for a pattern given a list of + /// patterns expanded by the specialization step. + /// + /// When a pattern P is discovered to be useful, this function is used bottom-up + /// to reconstruct a complete witness, e.g., a pattern P' that covers a subset + /// of values, V, where each value in that set is not covered by any previously + /// used patterns and is covered by the pattern P'. Examples: + /// + /// left_ty: tuple of 3 elements + /// pats: [10, 20, _] => (10, 20, _) + /// + /// left_ty: struct X { a: (bool, &'static str), b: usize} + /// pats: [(false, "foo"), 42] => X { a: (false, "foo"), b: 42 } + fn apply_constructor(mut self, pcx: &PatCtxt<'_, 'p, 'tcx>, ctor: &Constructor<'tcx>) -> Self { + let pat = { + let len = self.0.len(); + let arity = ctor.arity(pcx); + let pats = self.0.drain((len - arity)..).rev(); + let fields = Fields::from_iter(pcx.cx, pats); + DeconstructedPat::new(ctor.clone(), fields, pcx.ty, DUMMY_SP) + }; + + self.0.push(pat); + + self + } +} + +/// Report that a match of a `non_exhaustive` enum marked with `non_exhaustive_omitted_patterns` +/// is not exhaustive enough. +/// +/// NB: The partner lint for structs lives in `compiler/rustc_typeck/src/check/pat.rs`. +fn lint_non_exhaustive_omitted_patterns<'p, 'tcx>( + cx: &MatchCheckCtxt<'p, 'tcx>, + scrut_ty: Ty<'tcx>, + sp: Span, + hir_id: HirId, + witnesses: Vec<DeconstructedPat<'p, 'tcx>>, +) { + let joined_patterns = joined_uncovered_patterns(cx, &witnesses); + cx.tcx.struct_span_lint_hir(NON_EXHAUSTIVE_OMITTED_PATTERNS, hir_id, sp, |build| { + let mut lint = build.build("some variants are not matched explicitly"); + lint.span_label(sp, pattern_not_covered_label(&witnesses, &joined_patterns)); + lint.help( + "ensure that all variants are matched explicitly by adding the suggested match arms", + ); + lint.note(&format!( + "the matched value is of type `{}` and the `non_exhaustive_omitted_patterns` attribute was found", + scrut_ty, + )); + lint.emit(); + }); +} + +/// Algorithm from <http://moscova.inria.fr/~maranget/papers/warn/index.html>. +/// The algorithm from the paper has been modified to correctly handle empty +/// types. The changes are: +/// (0) We don't exit early if the pattern matrix has zero rows. We just +/// continue to recurse over columns. +/// (1) all_constructors will only return constructors that are statically +/// possible. E.g., it will only return `Ok` for `Result<T, !>`. +/// +/// This finds whether a (row) vector `v` of patterns is 'useful' in relation +/// to a set of such vectors `m` - this is defined as there being a set of +/// inputs that will match `v` but not any of the sets in `m`. +/// +/// All the patterns at each column of the `matrix ++ v` matrix must have the same type. +/// +/// This is used both for reachability checking (if a pattern isn't useful in +/// relation to preceding patterns, it is not reachable) and exhaustiveness +/// checking (if a wildcard pattern is useful in relation to a matrix, the +/// matrix isn't exhaustive). +/// +/// `is_under_guard` is used to inform if the pattern has a guard. If it +/// has one it must not be inserted into the matrix. This shouldn't be +/// relied on for soundness. +#[instrument(level = "debug", skip(cx, matrix, hir_id))] +fn is_useful<'p, 'tcx>( + cx: &MatchCheckCtxt<'p, 'tcx>, + matrix: &Matrix<'p, 'tcx>, + v: &PatStack<'p, 'tcx>, + witness_preference: ArmType, + hir_id: HirId, + is_under_guard: bool, + is_top_level: bool, +) -> Usefulness<'p, 'tcx> { + debug!(?matrix, ?v); + let Matrix { patterns: rows, .. } = matrix; + + // The base case. We are pattern-matching on () and the return value is + // based on whether our matrix has a row or not. + // NOTE: This could potentially be optimized by checking rows.is_empty() + // first and then, if v is non-empty, the return value is based on whether + // the type of the tuple we're checking is inhabited or not. + if v.is_empty() { + let ret = if rows.is_empty() { + Usefulness::new_useful(witness_preference) + } else { + Usefulness::new_not_useful(witness_preference) + }; + debug!(?ret); + return ret; + } + + debug_assert!(rows.iter().all(|r| r.len() == v.len())); + + // If the first pattern is an or-pattern, expand it. + let mut ret = Usefulness::new_not_useful(witness_preference); + if v.head().is_or_pat() { + debug!("expanding or-pattern"); + // We try each or-pattern branch in turn. + let mut matrix = matrix.clone(); + for v in v.expand_or_pat() { + debug!(?v); + let usefulness = ensure_sufficient_stack(|| { + is_useful(cx, &matrix, &v, witness_preference, hir_id, is_under_guard, false) + }); + debug!(?usefulness); + ret.extend(usefulness); + // If pattern has a guard don't add it to the matrix. + if !is_under_guard { + // We push the already-seen patterns into the matrix in order to detect redundant + // branches like `Some(_) | Some(0)`. + matrix.push(v); + } + } + } else { + let ty = v.head().ty(); + let is_non_exhaustive = cx.is_foreign_non_exhaustive_enum(ty); + debug!("v.head: {:?}, v.span: {:?}", v.head(), v.head().span()); + let pcx = &PatCtxt { cx, ty, span: v.head().span(), is_top_level, is_non_exhaustive }; + + let v_ctor = v.head().ctor(); + debug!(?v_ctor); + if let Constructor::IntRange(ctor_range) = &v_ctor { + // Lint on likely incorrect range patterns (#63987) + ctor_range.lint_overlapping_range_endpoints( + pcx, + matrix.heads(), + matrix.column_count().unwrap_or(0), + hir_id, + ) + } + // We split the head constructor of `v`. + let split_ctors = v_ctor.split(pcx, matrix.heads().map(DeconstructedPat::ctor)); + let is_non_exhaustive_and_wild = is_non_exhaustive && v_ctor.is_wildcard(); + // For each constructor, we compute whether there's a value that starts with it that would + // witness the usefulness of `v`. + let start_matrix = &matrix; + for ctor in split_ctors { + debug!("specialize({:?})", ctor); + // We cache the result of `Fields::wildcards` because it is used a lot. + let spec_matrix = start_matrix.specialize_constructor(pcx, &ctor); + let v = v.pop_head_constructor(pcx, &ctor); + let usefulness = ensure_sufficient_stack(|| { + is_useful(cx, &spec_matrix, &v, witness_preference, hir_id, is_under_guard, false) + }); + let usefulness = usefulness.apply_constructor(pcx, start_matrix, &ctor); + + // When all the conditions are met we have a match with a `non_exhaustive` enum + // that has the potential to trigger the `non_exhaustive_omitted_patterns` lint. + // To understand the workings checkout `Constructor::split` and `SplitWildcard::new/into_ctors` + if is_non_exhaustive_and_wild + // We check that the match has a wildcard pattern and that that wildcard is useful, + // meaning there are variants that are covered by the wildcard. Without the check + // for `witness_preference` the lint would trigger on `if let NonExhaustiveEnum::A = foo {}` + && usefulness.is_useful() && matches!(witness_preference, RealArm) + && matches!( + &ctor, + Constructor::Missing { nonexhaustive_enum_missing_real_variants: true } + ) + { + let patterns = { + let mut split_wildcard = SplitWildcard::new(pcx); + split_wildcard.split(pcx, matrix.heads().map(DeconstructedPat::ctor)); + // Construct for each missing constructor a "wild" version of this + // constructor, that matches everything that can be built with + // it. For example, if `ctor` is a `Constructor::Variant` for + // `Option::Some`, we get the pattern `Some(_)`. + split_wildcard + .iter_missing(pcx) + // Filter out the `NonExhaustive` because we want to list only real + // variants. Also remove any unstable feature gated variants. + // Because of how we computed `nonexhaustive_enum_missing_real_variants`, + // this will not return an empty `Vec`. + .filter(|c| !(c.is_non_exhaustive() || c.is_unstable_variant(pcx))) + .cloned() + .map(|missing_ctor| DeconstructedPat::wild_from_ctor(pcx, missing_ctor)) + .collect::<Vec<_>>() + }; + + lint_non_exhaustive_omitted_patterns(pcx.cx, pcx.ty, pcx.span, hir_id, patterns); + } + + ret.extend(usefulness); + } + } + + if ret.is_useful() { + v.head().set_reachable(); + } + + debug!(?ret); + ret +} + +/// The arm of a match expression. +#[derive(Clone, Copy, Debug)] +pub(crate) struct MatchArm<'p, 'tcx> { + /// The pattern must have been lowered through `check_match::MatchVisitor::lower_pattern`. + pub(crate) pat: &'p DeconstructedPat<'p, 'tcx>, + pub(crate) hir_id: HirId, + pub(crate) has_guard: bool, +} + +/// Indicates whether or not a given arm is reachable. +#[derive(Clone, Debug)] +pub(crate) enum Reachability { + /// The arm is reachable. This additionally carries a set of or-pattern branches that have been + /// found to be unreachable despite the overall arm being reachable. Used only in the presence + /// of or-patterns, otherwise it stays empty. + Reachable(Vec<Span>), + /// The arm is unreachable. + Unreachable, +} + +/// The output of checking a match for exhaustiveness and arm reachability. +pub(crate) struct UsefulnessReport<'p, 'tcx> { + /// For each arm of the input, whether that arm is reachable after the arms above it. + pub(crate) arm_usefulness: Vec<(MatchArm<'p, 'tcx>, Reachability)>, + /// If the match is exhaustive, this is empty. If not, this contains witnesses for the lack of + /// exhaustiveness. + pub(crate) non_exhaustiveness_witnesses: Vec<DeconstructedPat<'p, 'tcx>>, +} + +/// The entrypoint for the usefulness algorithm. Computes whether a match is exhaustive and which +/// of its arms are reachable. +/// +/// Note: the input patterns must have been lowered through +/// `check_match::MatchVisitor::lower_pattern`. +#[instrument(skip(cx, arms), level = "debug")] +pub(crate) fn compute_match_usefulness<'p, 'tcx>( + cx: &MatchCheckCtxt<'p, 'tcx>, + arms: &[MatchArm<'p, 'tcx>], + scrut_hir_id: HirId, + scrut_ty: Ty<'tcx>, +) -> UsefulnessReport<'p, 'tcx> { + let mut matrix = Matrix::empty(); + let arm_usefulness: Vec<_> = arms + .iter() + .copied() + .map(|arm| { + debug!(?arm); + let v = PatStack::from_pattern(arm.pat); + is_useful(cx, &matrix, &v, RealArm, arm.hir_id, arm.has_guard, true); + if !arm.has_guard { + matrix.push(v); + } + let reachability = if arm.pat.is_reachable() { + Reachability::Reachable(arm.pat.unreachable_spans()) + } else { + Reachability::Unreachable + }; + (arm, reachability) + }) + .collect(); + + let wild_pattern = cx.pattern_arena.alloc(DeconstructedPat::wildcard(scrut_ty)); + let v = PatStack::from_pattern(wild_pattern); + let usefulness = is_useful(cx, &matrix, &v, FakeExtraWildcard, scrut_hir_id, false, true); + let non_exhaustiveness_witnesses = match usefulness { + WithWitnesses(pats) => pats.into_iter().map(|w| w.single_pattern()).collect(), + NoWitnesses { .. } => bug!(), + }; + UsefulnessReport { arm_usefulness, non_exhaustiveness_witnesses } +} |