diff --git a/crates/hir_def/src/path.rs b/crates/hir_def/src/path.rs index 16440041dcb5..4cdb5913deb5 100644 --- a/crates/hir_def/src/path.rs +++ b/crates/hir_def/src/path.rs @@ -166,7 +166,7 @@ impl Path { } /// Converts a known mod path to `Path`. - pub(crate) fn from_known_path( + pub fn from_known_path( path: ModPath, generic_args: Vec>>, ) -> Path { diff --git a/crates/hir_ty/Cargo.toml b/crates/hir_ty/Cargo.toml index c3d02424d619..4b714c6d8e49 100644 --- a/crates/hir_ty/Cargo.toml +++ b/crates/hir_ty/Cargo.toml @@ -22,6 +22,7 @@ chalk-solve = { version = "0.68", default-features = false } chalk-ir = "0.68" chalk-recursive = "0.68" la-arena = { version = "0.2.0", path = "../../lib/arena" } +once_cell = { version = "1.5.0" } stdx = { path = "../stdx", version = "0.0.0" } hir_def = { path = "../hir_def", version = "0.0.0" } diff --git a/crates/hir_ty/src/diagnostics/expr.rs b/crates/hir_ty/src/diagnostics/expr.rs index 86f82e3fa450..3efbce77361e 100644 --- a/crates/hir_ty/src/diagnostics/expr.rs +++ b/crates/hir_ty/src/diagnostics/expr.rs @@ -2,9 +2,11 @@ //! through the body using inference results: mismatched arg counts, missing //! fields, etc. -use std::sync::Arc; +use std::{cell::RefCell, sync::Arc}; -use hir_def::{expr::Statement, path::path, resolver::HasResolver, AssocItemId, DefWithBodyId}; +use hir_def::{ + expr::Statement, path::path, resolver::HasResolver, AssocItemId, DefWithBodyId, HasModule, +}; use hir_expand::name; use rustc_hash::FxHashSet; use syntax::{ast, AstPtr}; @@ -12,7 +14,10 @@ use syntax::{ast, AstPtr}; use crate::{ db::HirDatabase, diagnostics::{ - match_check::{is_useful, MatchCheckCtx, Matrix, PatStack, Usefulness}, + match_check::{ + self, + usefulness::{compute_match_usefulness, expand_pattern, MatchCheckCtx, PatternArena}, + }, MismatchedArgCount, MissingFields, MissingMatchArms, MissingOkOrSomeInTailExpr, MissingPatFields, RemoveThisSemicolon, }, @@ -294,12 +299,12 @@ impl<'a, 'b> ExprValidator<'a, 'b> { &infer.type_of_expr[match_expr] }; - let cx = MatchCheckCtx { match_expr, body, infer: infer.clone(), db }; - let pats = arms.iter().map(|arm| arm.pat); + let pattern_arena = RefCell::new(PatternArena::new()); - let mut seen = Matrix::empty(); - for pat in pats { - if let Some(pat_ty) = infer.type_of_pat.get(pat) { + let mut m_arms = Vec::new(); + let mut has_lowering_errors = false; + for arm in arms { + if let Some(pat_ty) = infer.type_of_pat.get(arm.pat) { // We only include patterns whose type matches the type // of the match expression. If we had a InvalidMatchArmPattern // diagnostic or similar we could raise that in an else @@ -315,14 +320,25 @@ impl<'a, 'b> ExprValidator<'a, 'b> { .as_reference() .map(|(match_expr_ty, ..)| match_expr_ty == pat_ty) .unwrap_or(false)) - && types_of_subpatterns_do_match(pat, &cx.body, &infer) + && types_of_subpatterns_do_match(arm.pat, &body, &infer) { // If we had a NotUsefulMatchArm diagnostic, we could // check the usefulness of each pattern as we added it // to the matrix here. - let v = PatStack::from_pattern(pat); - seen.push(&cx, v); - continue; + let m_arm = match_check::MatchArm { + pat: self.lower_pattern( + arm.pat, + &mut pattern_arena.borrow_mut(), + db, + &body, + &mut has_lowering_errors, + ), + has_guard: arm.guard.is_some(), + }; + m_arms.push(m_arm); + if !has_lowering_errors { + continue; + } } } @@ -330,34 +346,73 @@ impl<'a, 'b> ExprValidator<'a, 'b> { // fit the match expression, we skip this diagnostic. Skipping the entire // diagnostic rather than just not including this match arm is preferred // to avoid the chance of false positives. + #[cfg(test)] + match_check::tests::report_bail_out(db, self.owner, arm.pat, self.sink); return; } - match is_useful(&cx, &seen, &PatStack::from_wild()) { - Ok(Usefulness::Useful) => (), - // if a wildcard pattern is not useful, then all patterns are covered - Ok(Usefulness::NotUseful) => return, - // this path is for unimplemented checks, so we err on the side of not - // reporting any errors - _ => return, - } + let cx = MatchCheckCtx { + module: self.owner.module(db.upcast()), + match_expr, + infer: &infer, + db, + pattern_arena: &pattern_arena, + eprint_panic_context: &|| { + use syntax::AstNode; + if let Ok(scrutinee_sptr) = source_map.expr_syntax(match_expr) { + let root = scrutinee_sptr.file_syntax(db.upcast()); + if let Some(match_ast) = scrutinee_sptr.value.to_node(&root).syntax().parent() { + eprintln!( + "Match checking is about to panic on this expression:\n{}", + match_ast.to_string(), + ); + } + } + }, + }; + let report = compute_match_usefulness(&cx, &m_arms); - if let Ok(source_ptr) = source_map.expr_syntax(id) { - let root = source_ptr.file_syntax(db.upcast()); - if let ast::Expr::MatchExpr(match_expr) = &source_ptr.value.to_node(&root) { - if let (Some(match_expr), Some(arms)) = - (match_expr.expr(), match_expr.match_arm_list()) - { - self.sink.push(MissingMatchArms { - file: source_ptr.file_id, - match_expr: AstPtr::new(&match_expr), - arms: AstPtr::new(&arms), - }) + // FIXME Report unreacheble arms + // https://github.com/rust-lang/rust/blob/25c15cdbe/compiler/rustc_mir_build/src/thir/pattern/check_match.rs#L200-L201 + + let witnesses = report.non_exhaustiveness_witnesses; + // FIXME Report witnesses + // eprintln!("compute_match_usefulness(..) -> {:?}", &witnesses); + if !witnesses.is_empty() { + if let Ok(source_ptr) = source_map.expr_syntax(id) { + let root = source_ptr.file_syntax(db.upcast()); + if let ast::Expr::MatchExpr(match_expr) = &source_ptr.value.to_node(&root) { + if let (Some(match_expr), Some(arms)) = + (match_expr.expr(), match_expr.match_arm_list()) + { + self.sink.push(MissingMatchArms { + file: source_ptr.file_id, + match_expr: AstPtr::new(&match_expr), + arms: AstPtr::new(&arms), + }) + } } } } } + fn lower_pattern( + &self, + pat: PatId, + pattern_arena: &mut PatternArena, + db: &dyn HirDatabase, + body: &Body, + have_errors: &mut bool, + ) -> match_check::PatId { + let mut patcx = match_check::PatCtxt::new(db, &self.infer, body); + let pattern = patcx.lower_pattern(pat); + let pattern = pattern_arena.alloc(expand_pattern(pattern)); + if !patcx.errors.is_empty() { + *have_errors = true; + } + pattern + } + fn validate_results_in_tail_expr(&mut self, body_id: ExprId, id: ExprId, db: &dyn HirDatabase) { // the mismatch will be on the whole block currently let mismatch = match self.infer.type_mismatch_for_expr(body_id) { diff --git a/crates/hir_ty/src/diagnostics/match_check.rs b/crates/hir_ty/src/diagnostics/match_check.rs index e8dd669bf6d9..a9a99f57a249 100644 --- a/crates/hir_ty/src/diagnostics/match_check.rs +++ b/crates/hir_ty/src/diagnostics/match_check.rs @@ -1,871 +1,416 @@ -//! This module implements match statement exhaustiveness checking and usefulness checking -//! for match arms. +//! Validation of matches. //! -//! It is modeled on the rustc module `librustc_mir_build::hair::pattern::_match`, which -//! contains very detailed documentation about the algorithms used here. I've duplicated -//! most of that documentation below. +//! This module provides lowering from [hir_def::expr::Pat] to [self::Pat] and match +//! checking algorithm. //! -//! This file includes the logic for exhaustiveness and usefulness checking for -//! pattern-matching. Specifically, given a list of patterns for a type, we can -//! tell whether: -//! - (a) the patterns cover every possible constructor for the type (exhaustiveness). -//! - (b) each pattern is necessary (usefulness). -//! -//! The algorithm implemented here is a modified version of the one described in -//! . -//! However, to save future implementors from reading the original paper, we -//! summarize the algorithm here to hopefully save time and be a little clearer -//! (without being so rigorous). -//! -//! The core of the algorithm revolves about a "usefulness" check. In particular, we -//! are trying to compute a predicate `U(P, p)` where `P` is a list of patterns (we refer to this as -//! a matrix). `U(P, p)` represents whether, given an existing list of patterns -//! `P_1 ..= P_m`, adding a new pattern `p` will be "useful" (that is, cover previously- -//! uncovered values of the type). -//! -//! If we have this predicate, then we can easily compute both exhaustiveness of an -//! entire set of patterns and the individual usefulness of each one. -//! (a) the set of patterns is exhaustive iff `U(P, _)` is false (i.e., adding a wildcard -//! match doesn't increase the number of values we're matching) -//! (b) a pattern `P_i` is not useful if `U(P[0..=(i-1), P_i)` is false (i.e., adding a -//! pattern to those that have come before it doesn't increase the number of values -//! we're matching). -//! -//! During the course of the algorithm, the rows of the matrix won't just be individual patterns, -//! but rather partially-deconstructed patterns in the form of a list of patterns. The paper -//! calls those pattern-vectors, and we will call them pattern-stacks. The same holds for the -//! new pattern `p`. -//! -//! For example, say we have the following: -//! -//! ```ignore -//! // x: (Option, Result<()>) -//! match x { -//! (Some(true), _) => (), -//! (None, Err(())) => (), -//! (None, Err(_)) => (), -//! } -//! ``` -//! -//! Here, the matrix `P` starts as: -//! -//! ```text -//! [ -//! [(Some(true), _)], -//! [(None, Err(()))], -//! [(None, Err(_))], -//! ] -//! ``` -//! -//! We can tell it's not exhaustive, because `U(P, _)` is true (we're not covering -//! `[(Some(false), _)]`, for instance). In addition, row 3 is not useful, because -//! all the values it covers are already covered by row 2. -//! -//! A list of patterns can be thought of as a stack, because we are mainly interested in the top of -//! the stack at any given point, and we can pop or apply constructors to get new pattern-stacks. -//! To match the paper, the top of the stack is at the beginning / on the left. -//! -//! There are two important operations on pattern-stacks necessary to understand the algorithm: -//! -//! 1. We can pop a given constructor off the top of a stack. This operation is called -//! `specialize`, and is denoted `S(c, p)` where `c` is a constructor (like `Some` or -//! `None`) and `p` a pattern-stack. -//! If the pattern on top of the stack can cover `c`, this removes the constructor and -//! pushes its arguments onto the stack. It also expands OR-patterns into distinct patterns. -//! Otherwise the pattern-stack is discarded. -//! This essentially filters those pattern-stacks whose top covers the constructor `c` and -//! discards the others. -//! -//! For example, the first pattern above initially gives a stack `[(Some(true), _)]`. If we -//! pop the tuple constructor, we are left with `[Some(true), _]`, and if we then pop the -//! `Some` constructor we get `[true, _]`. If we had popped `None` instead, we would get -//! nothing back. -//! -//! This returns zero or more new pattern-stacks, as follows. We look at the pattern `p_1` -//! on top of the stack, and we have four cases: -//! -//! * 1.1. `p_1 = c(r_1, .., r_a)`, i.e. the top of the stack has constructor `c`. We push onto -//! the stack the arguments of this constructor, and return the result: -//! -//! r_1, .., r_a, p_2, .., p_n -//! -//! * 1.2. `p_1 = c'(r_1, .., r_a')` where `c ≠ c'`. We discard the current stack and return -//! nothing. -//! * 1.3. `p_1 = _`. We push onto the stack as many wildcards as the constructor `c` has -//! arguments (its arity), and return the resulting stack: -//! -//! _, .., _, p_2, .., p_n -//! -//! * 1.4. `p_1 = r_1 | r_2`. We expand the OR-pattern and then recurse on each resulting stack: -//! -//! S(c, (r_1, p_2, .., p_n)) -//! S(c, (r_2, p_2, .., p_n)) -//! -//! 2. We can pop a wildcard off the top of the stack. This is called `D(p)`, where `p` is -//! a pattern-stack. -//! This is used when we know there are missing constructor cases, but there might be -//! existing wildcard patterns, so to check the usefulness of the matrix, we have to check -//! all its *other* components. -//! -//! It is computed as follows. We look at the pattern `p_1` on top of the stack, -//! and we have three cases: -//! * 1.1. `p_1 = c(r_1, .., r_a)`. We discard the current stack and return nothing. -//! * 1.2. `p_1 = _`. We return the rest of the stack: -//! -//! p_2, .., p_n -//! -//! * 1.3. `p_1 = r_1 | r_2`. We expand the OR-pattern and then recurse on each resulting stack: -//! -//! D((r_1, p_2, .., p_n)) -//! D((r_2, p_2, .., p_n)) -//! -//! Note that the OR-patterns are not always used directly in Rust, but are used to derive the -//! exhaustive integer matching rules, so they're written here for posterity. -//! -//! Both those operations extend straightforwardly to a list or pattern-stacks, i.e. a matrix, by -//! working row-by-row. Popping a constructor ends up keeping only the matrix rows that start with -//! the given constructor, and popping a wildcard keeps those rows that start with a wildcard. -//! -//! -//! The algorithm for computing `U` -//! ------------------------------- -//! The algorithm is inductive (on the number of columns: i.e., components of tuple patterns). -//! That means we're going to check the components from left-to-right, so the algorithm -//! operates principally on the first component of the matrix and new pattern-stack `p`. -//! This algorithm is realized in the `is_useful` function. -//! -//! Base case (`n = 0`, i.e., an empty tuple pattern): -//! - If `P` already contains an empty pattern (i.e., if the number of patterns `m > 0`), then -//! `U(P, p)` is false. -//! - Otherwise, `P` must be empty, so `U(P, p)` is true. -//! -//! Inductive step (`n > 0`, i.e., whether there's at least one column [which may then be expanded -//! into further columns later]). We're going to match on the top of the new pattern-stack, `p_1`: -//! -//! - If `p_1 == c(r_1, .., r_a)`, i.e. we have a constructor pattern. -//! Then, the usefulness of `p_1` can be reduced to whether it is useful when -//! we ignore all the patterns in the first column of `P` that involve other constructors. -//! This is where `S(c, P)` comes in: -//! -//! ```text -//! U(P, p) := U(S(c, P), S(c, p)) -//! ``` -//! -//! This special case is handled in `is_useful_specialized`. -//! -//! For example, if `P` is: -//! -//! ```text -//! [ -//! [Some(true), _], -//! [None, 0], -//! ] -//! ``` -//! -//! and `p` is `[Some(false), 0]`, then we don't care about row 2 since we know `p` only -//! matches values that row 2 doesn't. For row 1 however, we need to dig into the -//! arguments of `Some` to know whether some new value is covered. So we compute -//! `U([[true, _]], [false, 0])`. -//! -//! - If `p_1 == _`, then we look at the list of constructors that appear in the first component of -//! the rows of `P`: -//! - If there are some constructors that aren't present, then we might think that the -//! wildcard `_` is useful, since it covers those constructors that weren't covered -//! before. -//! That's almost correct, but only works if there were no wildcards in those first -//! components. So we need to check that `p` is useful with respect to the rows that -//! start with a wildcard, if there are any. This is where `D` comes in: -//! `U(P, p) := U(D(P), D(p))` -//! -//! For example, if `P` is: -//! ```text -//! [ -//! [_, true, _], -//! [None, false, 1], -//! ] -//! ``` -//! and `p` is `[_, false, _]`, the `Some` constructor doesn't appear in `P`. So if we -//! only had row 2, we'd know that `p` is useful. However row 1 starts with a -//! wildcard, so we need to check whether `U([[true, _]], [false, 1])`. -//! -//! - Otherwise, all possible constructors (for the relevant type) are present. In this -//! case we must check whether the wildcard pattern covers any unmatched value. For -//! that, we can think of the `_` pattern as a big OR-pattern that covers all -//! possible constructors. For `Option`, that would mean `_ = None | Some(_)` for -//! example. The wildcard pattern is useful in this case if it is useful when -//! specialized to one of the possible constructors. So we compute: -//! `U(P, p) := ∃(k ϵ constructors) U(S(k, P), S(k, p))` -//! -//! For example, if `P` is: -//! ```text -//! [ -//! [Some(true), _], -//! [None, false], -//! ] -//! ``` -//! and `p` is `[_, false]`, both `None` and `Some` constructors appear in the first -//! components of `P`. We will therefore try popping both constructors in turn: we -//! compute `U([[true, _]], [_, false])` for the `Some` constructor, and `U([[false]], -//! [false])` for the `None` constructor. The first case returns true, so we know that -//! `p` is useful for `P`. Indeed, it matches `[Some(false), _]` that wasn't matched -//! before. -//! -//! - If `p_1 == r_1 | r_2`, then the usefulness depends on each `r_i` separately: -//! -//! ```text -//! U(P, p) := U(P, (r_1, p_2, .., p_n)) -//! || U(P, (r_2, p_2, .., p_n)) -//! ``` -use std::{iter, sync::Arc}; +//! It is modeled on the rustc module `rustc_mir_build::thir::pattern`. -use hir_def::{ - adt::VariantData, - body::Body, - expr::{Expr, Literal, Pat, PatId}, - EnumVariantId, StructId, VariantId, -}; +mod deconstruct_pat; +mod pat_util; +pub(crate) mod usefulness; + +use hir_def::{body::Body, EnumVariantId, LocalFieldId, VariantId}; use la_arena::Idx; -use smallvec::{smallvec, SmallVec}; -use crate::{db::HirDatabase, AdtId, InferenceResult, Interner, TyExt, TyKind}; +use crate::{db::HirDatabase, InferenceResult, Interner, Substitution, Ty, TyKind}; -#[derive(Debug, Clone, Copy)] -/// Either a pattern from the source code being analyzed, represented as -/// as `PatId`, or a `Wild` pattern which is created as an intermediate -/// step in the match checking algorithm and thus is not backed by a -/// real `PatId`. -/// -/// Note that it is totally valid for the `PatId` variant to contain -/// a `PatId` which resolves to a `Wild` pattern, if that wild pattern -/// exists in the source code being analyzed. -enum PatIdOrWild { - PatId(PatId), - Wild, -} +use self::pat_util::EnumerateAndAdjustIterator; -impl PatIdOrWild { - fn as_pat(self, cx: &MatchCheckCtx) -> Pat { - match self { - PatIdOrWild::PatId(id) => cx.body.pats[id].clone(), - PatIdOrWild::Wild => Pat::Wild, - } - } +pub(crate) use self::usefulness::MatchArm; - fn as_id(self) -> Option { - match self { - PatIdOrWild::PatId(id) => Some(id), - PatIdOrWild::Wild => None, - } - } -} +pub(crate) type PatId = Idx; -impl From for PatIdOrWild { - fn from(pat_id: PatId) -> Self { - Self::PatId(pat_id) - } -} - -impl From<&PatId> for PatIdOrWild { - fn from(pat_id: &PatId) -> Self { - Self::PatId(*pat_id) - } -} - -#[derive(Debug, Clone, Copy, PartialEq)] -pub(super) enum MatchCheckErr { - NotImplemented, - MalformedMatchArm, - /// Used when type inference cannot resolve the type of - /// a pattern or expression. - Unknown, -} - -/// The return type of `is_useful` is either an indication of usefulness -/// of the match arm, or an error in the case the match statement -/// is made up of types for which exhaustiveness checking is currently -/// not completely implemented. -/// -/// The `std::result::Result` type is used here rather than a custom enum -/// to allow the use of `?`. -pub(super) type MatchCheckResult = Result; - -#[derive(Debug)] -/// A row in a Matrix. -/// -/// This type is modeled from the struct of the same name in `rustc`. -pub(super) struct PatStack(PatStackInner); -type PatStackInner = SmallVec<[PatIdOrWild; 2]>; - -impl PatStack { - pub(super) fn from_pattern(pat_id: PatId) -> PatStack { - Self(smallvec!(pat_id.into())) - } - - pub(super) fn from_wild() -> PatStack { - Self(smallvec!(PatIdOrWild::Wild)) - } - - fn from_slice(slice: &[PatIdOrWild]) -> PatStack { - Self(SmallVec::from_slice(slice)) - } - - fn from_vec(v: PatStackInner) -> PatStack { - Self(v) - } - - fn get_head(&self) -> Option { - self.0.first().copied() - } - - fn tail(&self) -> &[PatIdOrWild] { - self.0.get(1..).unwrap_or(&[]) - } - - fn to_tail(&self) -> PatStack { - Self::from_slice(self.tail()) - } - - fn replace_head_with(&self, pats: I) -> PatStack - where - I: Iterator, - T: Into, - { - let mut patterns: PatStackInner = smallvec![]; - for pat in pats { - patterns.push(pat.into()); - } - for pat in &self.0[1..] { - patterns.push(*pat); - } - PatStack::from_vec(patterns) - } - - /// Computes `D(self)`. - /// - /// See the module docs and the associated documentation in rustc for details. - fn specialize_wildcard(&self, cx: &MatchCheckCtx) -> Option { - if matches!(self.get_head()?.as_pat(cx), Pat::Wild) { - Some(self.to_tail()) - } else { - None - } - } - - /// Computes `S(constructor, self)`. - /// - /// See the module docs and the associated documentation in rustc for details. - fn specialize_constructor( - &self, - cx: &MatchCheckCtx, - constructor: &Constructor, - ) -> MatchCheckResult> { - let head = match self.get_head() { - Some(head) => head, - None => return Ok(None), - }; - - let head_pat = head.as_pat(cx); - let result = match (head_pat, constructor) { - (Pat::Tuple { args: pat_ids, ellipsis }, &Constructor::Tuple { arity }) => { - if let Some(ellipsis) = ellipsis { - let (pre, post) = pat_ids.split_at(ellipsis); - let n_wild_pats = arity.saturating_sub(pat_ids.len()); - let pre_iter = pre.iter().map(Into::into); - let wildcards = iter::repeat(PatIdOrWild::Wild).take(n_wild_pats); - let post_iter = post.iter().map(Into::into); - Some(self.replace_head_with(pre_iter.chain(wildcards).chain(post_iter))) - } else { - Some(self.replace_head_with(pat_ids.iter())) - } - } - (Pat::Lit(lit_expr), Constructor::Bool(constructor_val)) => { - match cx.body.exprs[lit_expr] { - Expr::Literal(Literal::Bool(pat_val)) if *constructor_val == pat_val => { - Some(self.to_tail()) - } - // it was a bool but the value doesn't match - Expr::Literal(Literal::Bool(_)) => None, - // perhaps this is actually unreachable given we have - // already checked that these match arms have the appropriate type? - _ => return Err(MatchCheckErr::NotImplemented), - } - } - (Pat::Wild, constructor) => Some(self.expand_wildcard(cx, constructor)?), - (Pat::Path(_), constructor) => { - // unit enum variants become `Pat::Path` - let pat_id = head.as_id().expect("we know this isn't a wild"); - let variant_id: VariantId = match constructor { - &Constructor::Enum(e) => e.into(), - &Constructor::Struct(s) => s.into(), - _ => return Err(MatchCheckErr::NotImplemented), - }; - if Some(variant_id) != cx.infer.variant_resolution_for_pat(pat_id) { - None - } else { - Some(self.to_tail()) - } - } - (Pat::TupleStruct { args: ref pat_ids, ellipsis, .. }, constructor) => { - let pat_id = head.as_id().expect("we know this isn't a wild"); - let variant_id: VariantId = match constructor { - &Constructor::Enum(e) => e.into(), - &Constructor::Struct(s) => s.into(), - _ => return Err(MatchCheckErr::MalformedMatchArm), - }; - if Some(variant_id) != cx.infer.variant_resolution_for_pat(pat_id) { - None - } else { - let constructor_arity = constructor.arity(cx)?; - if let Some(ellipsis_position) = ellipsis { - // If there are ellipsis in the pattern, the ellipsis must take the place - // of at least one sub-pattern, so `pat_ids` should be smaller than the - // constructor arity. - if pat_ids.len() < constructor_arity { - let mut new_patterns: Vec = vec![]; - - for pat_id in &pat_ids[0..ellipsis_position] { - new_patterns.push((*pat_id).into()); - } - - for _ in 0..(constructor_arity - pat_ids.len()) { - new_patterns.push(PatIdOrWild::Wild); - } - - for pat_id in &pat_ids[ellipsis_position..pat_ids.len()] { - new_patterns.push((*pat_id).into()); - } - - Some(self.replace_head_with(new_patterns.into_iter())) - } else { - return Err(MatchCheckErr::MalformedMatchArm); - } - } else { - // If there is no ellipsis in the tuple pattern, the number - // of patterns must equal the constructor arity. - if pat_ids.len() == constructor_arity { - Some(self.replace_head_with(pat_ids.into_iter())) - } else { - return Err(MatchCheckErr::MalformedMatchArm); - } - } - } - } - (Pat::Record { args: ref arg_patterns, .. }, constructor) => { - let pat_id = head.as_id().expect("we know this isn't a wild"); - let (variant_id, variant_data) = match constructor { - &Constructor::Enum(e) => ( - e.into(), - cx.db.enum_data(e.parent).variants[e.local_id].variant_data.clone(), - ), - &Constructor::Struct(s) => { - (s.into(), cx.db.struct_data(s).variant_data.clone()) - } - _ => return Err(MatchCheckErr::MalformedMatchArm), - }; - if Some(variant_id) != cx.infer.variant_resolution_for_pat(pat_id) { - None - } else { - match variant_data.as_ref() { - VariantData::Record(struct_field_arena) => { - // Here we treat any missing fields in the record as the wild pattern, as - // if the record has ellipsis. We want to do this here even if the - // record does not contain ellipsis, because it allows us to continue - // enforcing exhaustiveness for the rest of the match statement. - // - // Creating the diagnostic for the missing field in the pattern - // should be done in a different diagnostic. - let patterns = struct_field_arena.iter().map(|(_, struct_field)| { - arg_patterns - .iter() - .find(|pat| pat.name == struct_field.name) - .map(|pat| PatIdOrWild::from(pat.pat)) - .unwrap_or(PatIdOrWild::Wild) - }); - - Some(self.replace_head_with(patterns)) - } - _ => return Err(MatchCheckErr::Unknown), - } - } - } - (Pat::Or(_), _) => return Err(MatchCheckErr::NotImplemented), - (_, _) => return Err(MatchCheckErr::NotImplemented), - }; - - Ok(result) - } - - /// A special case of `specialize_constructor` where the head of the pattern stack - /// is a Wild pattern. - /// - /// Replaces the Wild pattern at the head of the pattern stack with N Wild patterns - /// (N >= 0), where N is the arity of the given constructor. - fn expand_wildcard( - &self, - cx: &MatchCheckCtx, - constructor: &Constructor, - ) -> MatchCheckResult { - assert_eq!( - Pat::Wild, - self.get_head().expect("expand_wildcard called on empty PatStack").as_pat(cx), - "expand_wildcard must only be called on PatStack with wild at head", - ); - - let mut patterns: PatStackInner = smallvec![]; - - for _ in 0..constructor.arity(cx)? { - patterns.push(PatIdOrWild::Wild); - } - - for pat in &self.0[1..] { - patterns.push(*pat); - } - - Ok(PatStack::from_vec(patterns)) - } -} - -/// A collection of PatStack. -/// -/// This type is modeled from the struct of the same name in `rustc`. -pub(super) struct Matrix(Vec); - -impl Matrix { - pub(super) fn empty() -> Self { - Self(vec![]) - } - - pub(super) fn push(&mut self, cx: &MatchCheckCtx, row: PatStack) { - if let Some(Pat::Or(pat_ids)) = row.get_head().map(|pat_id| pat_id.as_pat(cx)) { - // Or patterns are expanded here - for pat_id in pat_ids { - self.0.push(row.replace_head_with([pat_id].iter())); - } - } else { - self.0.push(row); - } - } - - fn is_empty(&self) -> bool { - self.0.is_empty() - } - - fn heads(&self) -> Vec { - self.0.iter().flat_map(|p| p.get_head()).collect() - } - - /// Computes `D(self)` for each contained PatStack. - /// - /// See the module docs and the associated documentation in rustc for details. - fn specialize_wildcard(&self, cx: &MatchCheckCtx) -> Self { - Self::collect(cx, self.0.iter().filter_map(|r| r.specialize_wildcard(cx))) - } - - /// Computes `S(constructor, self)` for each contained PatStack. - /// - /// See the module docs and the associated documentation in rustc for details. - fn specialize_constructor( - &self, - cx: &MatchCheckCtx, - constructor: &Constructor, - ) -> MatchCheckResult { - let mut new_matrix = Matrix::empty(); - for pat in &self.0 { - if let Some(pat) = pat.specialize_constructor(cx, constructor)? { - new_matrix.push(cx, pat); - } - } - - Ok(new_matrix) - } - - fn collect>(cx: &MatchCheckCtx, iter: T) -> Self { - let mut matrix = Matrix::empty(); - - for pat in iter { - // using push ensures we expand or-patterns - matrix.push(cx, pat); - } - - matrix - } +#[derive(Clone, Debug)] +pub(crate) enum PatternError { + Unimplemented, + UnresolvedVariant, + MissingField, + ExtraFields, } #[derive(Clone, Debug, PartialEq)] -/// An indication of the usefulness of a given match arm, where -/// usefulness is defined as matching some patterns which were -/// not matched by an prior match arms. -/// -/// We may eventually need an `Unknown` variant here. -pub(super) enum Usefulness { - Useful, - NotUseful, +pub(crate) struct FieldPat { + pub(crate) field: LocalFieldId, + pub(crate) pattern: Pat, } -pub(super) struct MatchCheckCtx<'a> { - pub(super) match_expr: Idx, - pub(super) body: Arc, - pub(super) infer: Arc, - pub(super) db: &'a dyn HirDatabase, +#[derive(Clone, Debug, PartialEq)] +pub(crate) struct Pat { + pub(crate) ty: Ty, + pub(crate) kind: Box, } -/// Given a set of patterns `matrix`, and pattern to consider `v`, determines -/// whether `v` is useful. A pattern is useful if it covers cases which were -/// not previously covered. -/// -/// When calling this function externally (that is, not the recursive calls) it -/// expected that you have already type checked the match arms. All patterns in -/// matrix should be the same type as v, as well as they should all be the same -/// type as the match expression. -pub(super) fn is_useful( - cx: &MatchCheckCtx, - matrix: &Matrix, - v: &PatStack, -) -> MatchCheckResult { - // Handle two special cases: - // - enum with no variants - // - `!` type - // In those cases, no match arm is useful. - match cx.infer[cx.match_expr].strip_references().kind(&Interner) { - TyKind::Adt(AdtId(hir_def::AdtId::EnumId(enum_id)), ..) => { - if cx.db.enum_data(*enum_id).variants.is_empty() { - return Ok(Usefulness::NotUseful); - } - } - TyKind::Never => return Ok(Usefulness::NotUseful), - _ => (), - } - - let head = match v.get_head() { - Some(head) => head, - None => { - let result = if matrix.is_empty() { Usefulness::Useful } else { Usefulness::NotUseful }; - - return Ok(result); - } - }; - - if let Pat::Or(pat_ids) = head.as_pat(cx) { - let mut found_unimplemented = false; - let any_useful = pat_ids.iter().any(|&pat_id| { - let v = PatStack::from_pattern(pat_id); - - match is_useful(cx, matrix, &v) { - Ok(Usefulness::Useful) => true, - Ok(Usefulness::NotUseful) => false, - _ => { - found_unimplemented = true; - false - } - } - }); - - return if any_useful { - Ok(Usefulness::Useful) - } else if found_unimplemented { - Err(MatchCheckErr::NotImplemented) - } else { - Ok(Usefulness::NotUseful) - }; - } - - if let Some(constructor) = pat_constructor(cx, head)? { - let matrix = matrix.specialize_constructor(&cx, &constructor)?; - let v = v - .specialize_constructor(&cx, &constructor)? - .expect("we know this can't fail because we get the constructor from `v.head()` above"); - - is_useful(&cx, &matrix, &v) - } else { - // expanding wildcard - let mut used_constructors: Vec = vec![]; - for pat in matrix.heads() { - if let Some(constructor) = pat_constructor(cx, pat)? { - used_constructors.push(constructor); - } - } - - // We assume here that the first constructor is the "correct" type. Since we - // only care about the "type" of the constructor (i.e. if it is a bool we - // don't care about the value), this assumption should be valid as long as - // the match statement is well formed. We currently uphold this invariant by - // filtering match arms before calling `is_useful`, only passing in match arms - // whose type matches the type of the match expression. - match &used_constructors.first() { - Some(constructor) if all_constructors_covered(&cx, constructor, &used_constructors) => { - // If all constructors are covered, then we need to consider whether - // any values are covered by this wildcard. - // - // For example, with matrix '[[Some(true)], [None]]', all - // constructors are covered (`Some`/`None`), so we need - // to perform specialization to see that our wildcard will cover - // the `Some(false)` case. - // - // Here we create a constructor for each variant and then check - // usefulness after specializing for that constructor. - let mut found_unimplemented = false; - for constructor in constructor.all_constructors(cx) { - let matrix = matrix.specialize_constructor(&cx, &constructor)?; - let v = v.expand_wildcard(&cx, &constructor)?; - - match is_useful(&cx, &matrix, &v) { - Ok(Usefulness::Useful) => return Ok(Usefulness::Useful), - Ok(Usefulness::NotUseful) => continue, - _ => found_unimplemented = true, - }; - } - - if found_unimplemented { - Err(MatchCheckErr::NotImplemented) - } else { - Ok(Usefulness::NotUseful) - } - } - _ => { - // Either not all constructors are covered, or the only other arms - // are wildcards. Either way, this pattern is useful if it is useful - // when compared to those arms with wildcards. - let matrix = matrix.specialize_wildcard(&cx); - let v = v.to_tail(); - - is_useful(&cx, &matrix, &v) - } - } +impl Pat { + pub(crate) fn wildcard_from_ty(ty: Ty) -> Self { + Pat { ty, kind: Box::new(PatKind::Wild) } } } -#[derive(Debug, Clone, Copy)] -/// Similar to TypeCtor, but includes additional information about the specific -/// value being instantiated. For example, TypeCtor::Bool doesn't contain the -/// boolean value. -enum Constructor { - Bool(bool), - Tuple { arity: usize }, - Enum(EnumVariantId), - Struct(StructId), +/// Close relative to `rustc_mir_build::thir::pattern::PatKind` +#[derive(Clone, Debug, PartialEq)] +pub(crate) enum PatKind { + Wild, + + /// `x`, `ref x`, `x @ P`, etc. + Binding { + subpattern: Option, + }, + + /// `Foo(...)` or `Foo{...}` or `Foo`, where `Foo` is a variant name from an ADT with + /// multiple variants. + Variant { + substs: Substitution, + enum_variant: EnumVariantId, + subpatterns: Vec, + }, + + /// `(...)`, `Foo(...)`, `Foo{...}`, or `Foo`, where `Foo` is a variant name from an ADT with + /// a single variant. + Leaf { + subpatterns: Vec, + }, + + /// `box P`, `&P`, `&mut P`, etc. + Deref { + subpattern: Pat, + }, + + // FIXME: for now, only bool literals are implemented + LiteralBool { + value: bool, + }, + + /// An or-pattern, e.g. `p | q`. + /// Invariant: `pats.len() >= 2`. + Or { + pats: Vec, + }, } -impl Constructor { - fn arity(&self, cx: &MatchCheckCtx) -> MatchCheckResult { - let arity = match self { - Constructor::Bool(_) => 0, - Constructor::Tuple { arity } => *arity, - Constructor::Enum(e) => { - match cx.db.enum_data(e.parent).variants[e.local_id].variant_data.as_ref() { - VariantData::Tuple(struct_field_data) => struct_field_data.len(), - VariantData::Record(struct_field_data) => struct_field_data.len(), - VariantData::Unit => 0, - } - } - &Constructor::Struct(s) => match cx.db.struct_data(s).variant_data.as_ref() { - VariantData::Tuple(struct_field_data) => struct_field_data.len(), - VariantData::Record(struct_field_data) => struct_field_data.len(), - VariantData::Unit => 0, - }, - }; +pub(crate) struct PatCtxt<'a> { + db: &'a dyn HirDatabase, + infer: &'a InferenceResult, + body: &'a Body, + pub(crate) errors: Vec, +} - Ok(arity) +impl<'a> PatCtxt<'a> { + pub(crate) fn new(db: &'a dyn HirDatabase, infer: &'a InferenceResult, body: &'a Body) -> Self { + Self { db, infer, body, errors: Vec::new() } } - fn all_constructors(&self, cx: &MatchCheckCtx) -> Vec { - match self { - Constructor::Bool(_) => vec![Constructor::Bool(true), Constructor::Bool(false)], - Constructor::Tuple { .. } | Constructor::Struct(_) => vec![*self], - Constructor::Enum(e) => cx - .db - .enum_data(e.parent) - .variants - .iter() - .map(|(local_id, _)| { - Constructor::Enum(EnumVariantId { parent: e.parent, local_id }) - }) - .collect(), - } + pub(crate) fn lower_pattern(&mut self, pat: hir_def::expr::PatId) -> Pat { + // FIXME: implement pattern adjustments (implicit pattern dereference; "RFC 2005-match-ergonomics") + // More info https://github.com/rust-lang/rust/issues/42640#issuecomment-313535089 + let unadjusted_pat = self.lower_pattern_unadjusted(pat); + unadjusted_pat } -} -/// Returns the constructor for the given pattern. Should only return None -/// in the case of a Wild pattern. -fn pat_constructor(cx: &MatchCheckCtx, pat: PatIdOrWild) -> MatchCheckResult> { - let res = match pat.as_pat(cx) { - Pat::Wild => None, - Pat::Tuple { .. } => { - let pat_id = pat.as_id().expect("we already know this pattern is not a wild"); - Some(Constructor::Tuple { - arity: cx.infer.type_of_pat[pat_id] - .as_tuple() - .ok_or(MatchCheckErr::Unknown)? - .len(&Interner), - }) - } - Pat::Lit(lit_expr) => match cx.body.exprs[lit_expr] { - Expr::Literal(Literal::Bool(val)) => Some(Constructor::Bool(val)), - _ => return Err(MatchCheckErr::NotImplemented), - }, - Pat::TupleStruct { .. } | Pat::Path(_) | Pat::Record { .. } => { - let pat_id = pat.as_id().expect("we already know this pattern is not a wild"); - let variant_id = - cx.infer.variant_resolution_for_pat(pat_id).ok_or(MatchCheckErr::Unknown)?; - match variant_id { - VariantId::EnumVariantId(enum_variant_id) => { - Some(Constructor::Enum(enum_variant_id)) + fn lower_pattern_unadjusted(&mut self, pat: hir_def::expr::PatId) -> Pat { + let mut ty = &self.infer[pat]; + let variant = self.infer.variant_resolution_for_pat(pat); + + let kind = match self.body[pat] { + hir_def::expr::Pat::Wild => PatKind::Wild, + + hir_def::expr::Pat::Lit(expr) => self.lower_lit(expr), + + hir_def::expr::Pat::Path(ref path) => { + return self.lower_path(pat, path); + } + + hir_def::expr::Pat::Tuple { ref args, ellipsis } => { + let arity = match *ty.kind(&Interner) { + TyKind::Tuple(arity, _) => arity, + _ => panic!("unexpected type for tuple pattern: {:?}", ty), + }; + let subpatterns = self.lower_tuple_subpats(args, arity, ellipsis); + PatKind::Leaf { subpatterns } + } + + hir_def::expr::Pat::Bind { subpat, .. } => { + if let TyKind::Ref(.., rty) = ty.kind(&Interner) { + ty = rty; } - VariantId::StructId(struct_id) => Some(Constructor::Struct(struct_id)), - _ => return Err(MatchCheckErr::NotImplemented), - } - } - _ => return Err(MatchCheckErr::NotImplemented), - }; - - Ok(res) -} - -fn all_constructors_covered( - cx: &MatchCheckCtx, - constructor: &Constructor, - used_constructors: &[Constructor], -) -> bool { - match constructor { - Constructor::Tuple { arity } => { - used_constructors.iter().any(|constructor| match constructor { - Constructor::Tuple { arity: used_arity } => arity == used_arity, - _ => false, - }) - } - Constructor::Bool(_) => { - if used_constructors.is_empty() { - return false; + PatKind::Binding { subpattern: self.lower_opt_pattern(subpat) } } - let covers_true = - used_constructors.iter().any(|c| matches!(c, Constructor::Bool(true))); - let covers_false = - used_constructors.iter().any(|c| matches!(c, Constructor::Bool(false))); + hir_def::expr::Pat::TupleStruct { ref args, ellipsis, .. } if variant.is_some() => { + let expected_len = variant.unwrap().variant_data(self.db.upcast()).fields().len(); + let subpatterns = self.lower_tuple_subpats(args, expected_len, ellipsis); + self.lower_variant_or_leaf(pat, ty, subpatterns) + } - covers_true && covers_false - } - Constructor::Enum(e) => cx.db.enum_data(e.parent).variants.iter().all(|(id, _)| { - for constructor in used_constructors { - if let Constructor::Enum(e) = constructor { - if id == e.local_id { - return true; + hir_def::expr::Pat::Record { ref args, .. } if variant.is_some() => { + let variant_data = variant.unwrap().variant_data(self.db.upcast()); + let subpatterns = args + .iter() + .map(|field| { + // XXX(iDawer): field lookup is inefficient + variant_data.field(&field.name).map(|lfield_id| FieldPat { + field: lfield_id, + pattern: self.lower_pattern(field.pat), + }) + }) + .collect(); + match subpatterns { + Some(subpatterns) => self.lower_variant_or_leaf(pat, ty, subpatterns), + None => { + self.errors.push(PatternError::MissingField); + PatKind::Wild } } } + hir_def::expr::Pat::TupleStruct { .. } | hir_def::expr::Pat::Record { .. } => { + self.errors.push(PatternError::UnresolvedVariant); + PatKind::Wild + } - false - }), - &Constructor::Struct(s) => used_constructors.iter().any(|constructor| match constructor { - &Constructor::Struct(sid) => sid == s, - _ => false, - }), + hir_def::expr::Pat::Or(ref pats) => PatKind::Or { pats: self.lower_patterns(pats) }, + + _ => { + self.errors.push(PatternError::Unimplemented); + PatKind::Wild + } + }; + + Pat { ty: ty.clone(), kind: Box::new(kind) } + } + + fn lower_tuple_subpats( + &mut self, + pats: &[hir_def::expr::PatId], + expected_len: usize, + ellipsis: Option, + ) -> Vec { + if pats.len() > expected_len { + self.errors.push(PatternError::ExtraFields); + return Vec::new(); + } + + pats.iter() + .enumerate_and_adjust(expected_len, ellipsis) + .map(|(i, &subpattern)| FieldPat { + field: LocalFieldId::from_raw((i as u32).into()), + pattern: self.lower_pattern(subpattern), + }) + .collect() + } + + fn lower_patterns(&mut self, pats: &[hir_def::expr::PatId]) -> Vec { + pats.iter().map(|&p| self.lower_pattern(p)).collect() + } + + fn lower_opt_pattern(&mut self, pat: Option) -> Option { + pat.map(|p| self.lower_pattern(p)) + } + + fn lower_variant_or_leaf( + &mut self, + pat: hir_def::expr::PatId, + ty: &Ty, + subpatterns: Vec, + ) -> PatKind { + let kind = match self.infer.variant_resolution_for_pat(pat) { + Some(variant_id) => { + if let VariantId::EnumVariantId(enum_variant) = variant_id { + let substs = match ty.kind(&Interner) { + TyKind::Adt(_, substs) | TyKind::FnDef(_, substs) => substs.clone(), + TyKind::Error => { + return PatKind::Wild; + } + _ => panic!("inappropriate type for def: {:?}", ty), + }; + PatKind::Variant { substs, enum_variant, subpatterns } + } else { + PatKind::Leaf { subpatterns } + } + } + None => { + self.errors.push(PatternError::UnresolvedVariant); + PatKind::Wild + } + }; + kind + } + + fn lower_path(&mut self, pat: hir_def::expr::PatId, _path: &hir_def::path::Path) -> Pat { + let ty = &self.infer[pat]; + + let pat_from_kind = |kind| Pat { ty: ty.clone(), kind: Box::new(kind) }; + + match self.infer.variant_resolution_for_pat(pat) { + Some(_) => pat_from_kind(self.lower_variant_or_leaf(pat, ty, Vec::new())), + None => { + self.errors.push(PatternError::UnresolvedVariant); + pat_from_kind(PatKind::Wild) + } + } + } + + fn lower_lit(&mut self, expr: hir_def::expr::ExprId) -> PatKind { + use hir_def::expr::{Expr, Literal::Bool}; + + match self.body[expr] { + Expr::Literal(Bool(value)) => PatKind::LiteralBool { value }, + _ => { + self.errors.push(PatternError::Unimplemented); + PatKind::Wild + } + } + } +} + +pub(crate) trait PatternFoldable: Sized { + fn fold_with(&self, folder: &mut F) -> Self { + self.super_fold_with(folder) + } + + fn super_fold_with(&self, folder: &mut F) -> Self; +} + +pub(crate) trait PatternFolder: Sized { + fn fold_pattern(&mut self, pattern: &Pat) -> Pat { + pattern.super_fold_with(self) + } + + fn fold_pattern_kind(&mut self, kind: &PatKind) -> PatKind { + kind.super_fold_with(self) + } +} + +impl PatternFoldable for Box { + fn super_fold_with(&self, folder: &mut F) -> Self { + let content: T = (**self).fold_with(folder); + Box::new(content) + } +} + +impl PatternFoldable for Vec { + fn super_fold_with(&self, folder: &mut F) -> Self { + self.iter().map(|t| t.fold_with(folder)).collect() + } +} + +impl PatternFoldable for Option { + fn super_fold_with(&self, folder: &mut F) -> Self { + self.as_ref().map(|t| t.fold_with(folder)) + } +} + +macro_rules! clone_impls { + ($($ty:ty),+) => { + $( + impl PatternFoldable for $ty { + fn super_fold_with(&self, _: &mut F) -> Self { + Clone::clone(self) + } + } + )+ + } +} + +clone_impls! { LocalFieldId, Ty, Substitution, EnumVariantId } + +impl PatternFoldable for FieldPat { + fn super_fold_with(&self, folder: &mut F) -> Self { + FieldPat { field: self.field.fold_with(folder), pattern: self.pattern.fold_with(folder) } + } +} + +impl PatternFoldable for Pat { + fn fold_with(&self, folder: &mut F) -> Self { + folder.fold_pattern(self) + } + + fn super_fold_with(&self, folder: &mut F) -> Self { + Pat { ty: self.ty.fold_with(folder), kind: self.kind.fold_with(folder) } + } +} + +impl PatternFoldable for PatKind { + fn fold_with(&self, folder: &mut F) -> Self { + folder.fold_pattern_kind(self) + } + + fn super_fold_with(&self, folder: &mut F) -> Self { + match self { + PatKind::Wild => PatKind::Wild, + PatKind::Binding { subpattern } => { + PatKind::Binding { subpattern: subpattern.fold_with(folder) } + } + PatKind::Variant { substs, enum_variant, subpatterns } => PatKind::Variant { + substs: substs.fold_with(folder), + enum_variant: enum_variant.fold_with(folder), + subpatterns: subpatterns.fold_with(folder), + }, + PatKind::Leaf { subpatterns } => { + PatKind::Leaf { subpatterns: subpatterns.fold_with(folder) } + } + PatKind::Deref { subpattern } => { + PatKind::Deref { subpattern: subpattern.fold_with(folder) } + } + &PatKind::LiteralBool { value } => PatKind::LiteralBool { value }, + PatKind::Or { pats } => PatKind::Or { pats: pats.fold_with(folder) }, + } } } #[cfg(test)] -mod tests { +pub(super) mod tests { + mod report { + use std::any::Any; + + use hir_def::{expr::PatId, DefWithBodyId}; + use hir_expand::{HirFileId, InFile}; + use syntax::SyntaxNodePtr; + + use crate::{ + db::HirDatabase, + diagnostics_sink::{Diagnostic, DiagnosticCode, DiagnosticSink}, + }; + + /// In tests, match check bails out loudly. + /// This helps to catch incorrect tests that pass due to false negatives. + pub(crate) fn report_bail_out( + db: &dyn HirDatabase, + def: DefWithBodyId, + pat: PatId, + sink: &mut DiagnosticSink, + ) { + let (_, source_map) = db.body_with_source_map(def); + if let Ok(source_ptr) = source_map.pat_syntax(pat) { + let pat_syntax_ptr = source_ptr.value.either(Into::into, Into::into); + sink.push(BailedOut { file: source_ptr.file_id, pat_syntax_ptr }); + } + } + + #[derive(Debug)] + struct BailedOut { + file: HirFileId, + pat_syntax_ptr: SyntaxNodePtr, + } + + impl Diagnostic for BailedOut { + fn code(&self) -> DiagnosticCode { + DiagnosticCode("internal:match-check-bailed-out") + } + fn message(&self) -> String { + format!("Internal: match check bailed out") + } + fn display_source(&self) -> InFile { + InFile { file_id: self.file, value: self.pat_syntax_ptr.clone() } + } + fn as_any(&self) -> &(dyn Any + Send + 'static) { + self + } + } + } + use crate::diagnostics::tests::check_diagnostics; + pub(crate) use self::report::report_bail_out; + #[test] fn empty_tuple() { check_diagnostics( @@ -1113,14 +658,18 @@ enum Either2 { C, D } fn main() { match Either::A { Either2::C => (), + // ^^^^^^^^^^ Internal: match check bailed out Either2::D => (), } match (true, false) { (true, false, true) => (), + // ^^^^^^^^^^^^^^^^^^^ Internal: match check bailed out (true) => (), } match (true, false) { (true,) => {} } + // ^^^^^^^ Internal: match check bailed out match (0) { () => () } + // ^^ Internal: match check bailed out match Unresolved::Bar { Unresolved::Baz => () } } "#, @@ -1133,7 +682,9 @@ fn main() { r#" fn main() { match false { true | () => {} } + // ^^^^^^^^^ Internal: match check bailed out match (false,) { (true | (),) => {} } + // ^^^^^^^^^^^^ Internal: match check bailed out } "#, ); @@ -1157,6 +708,25 @@ fn main() { ); } + #[test] + fn malformed_match_arm_extra_fields() { + check_diagnostics( + r#" +enum A { B(isize, isize), C } +fn main() { + match A::B(1, 2) { + A::B(_, _, _) => (), + // ^^^^^^^^^^^^^ Internal: match check bailed out + } + match A::B(1, 2) { + A::C(_) => (), + // ^^^^^^^ Internal: match check bailed out + } +} +"#, + ); + } + #[test] fn expr_diverges() { check_diagnostics( @@ -1166,10 +736,12 @@ enum Either { A, B } fn main() { match loop {} { Either::A => (), + // ^^^^^^^^^ Internal: match check bailed out Either::B => (), } match loop {} { Either::A => (), + // ^^^^^^^^^ Internal: match check bailed out } match loop { break Foo::A } { //^^^^^^^^^^^^^^^^^^^^^ Missing match arm @@ -1357,6 +929,7 @@ fn enum_(never: Never) { } fn enum_ref(never: &Never) { match never {} + //^^^^^ Missing match arm } fn bang(never: !) { match never {} @@ -1376,6 +949,11 @@ fn main() { match Option::::None { None => (), Some(never) => match never {}, + // ^^^^^^^^^^^ Internal: match check bailed out + } + match Option::::None { + //^^^^^^^^^^^^^^^^^^^^^ Missing match arm + Option::Some(_never) => {}, } } "#, @@ -1513,6 +1091,151 @@ fn main() { "#, ); } + + #[test] + fn no_panic_at_unimplemented_subpattern_type() { + check_diagnostics( + r#" +struct S { a: char} +fn main(v: S) { + match v { S{ a } => {} } + match v { S{ a: _x } => {} } + match v { S{ a: 'a' } => {} } + //^^^^^^^^^^^ Internal: match check bailed out + match v { S{..} => {} } + match v { _ => {} } + match v { } + //^ Missing match arm +} +"#, + ); + } + + #[test] + fn binding() { + check_diagnostics( + r#" +fn main() { + match true { + _x @ true => {} + false => {} + } + match true { _x @ true => {} } + //^^^^ Missing match arm +} +"#, + ); + } + + #[test] + fn binding_ref_has_correct_type() { + // Asserts `PatKind::Binding(ref _x): bool`, not &bool. + // If that's not true match checking will panic with "incompatible constructors" + // FIXME: make facilities to test this directly like `tests::check_infer(..)` + check_diagnostics( + r#" +enum Foo { A } +fn main() { + // FIXME: this should not bail out but current behavior is such as the old algorithm. + // ExprValidator::validate_match(..) checks types of top level patterns incorrecly. + match Foo::A { + ref _x => {} + // ^^^^^^ Internal: match check bailed out + Foo::A => {} + } + match (true,) { + (ref _x,) => {} + (true,) => {} + } +} +"#, + ); + } + + #[test] + fn enum_non_exhaustive() { + check_diagnostics( + r#" +//- /lib.rs crate:lib +#[non_exhaustive] +pub enum E { A, B } +fn _local() { + match E::A { _ => {} } + match E::A { + E::A => {} + E::B => {} + } + match E::A { + E::A | E::B => {} + } +} + +//- /main.rs crate:main deps:lib +use lib::E; +fn main() { + match E::A { _ => {} } + match E::A { + //^^^^ Missing match arm + E::A => {} + E::B => {} + } + match E::A { + //^^^^ Missing match arm + E::A | E::B => {} + } +} +"#, + ); + } + + #[test] + fn match_guard() { + check_diagnostics( + r#" +fn main() { + match true { + true if false => {} + true => {} + false => {} + } + match true { + //^^^^ Missing match arm + true if false => {} + false => {} +} +"#, + ); + } + + #[test] + fn pattern_type_is_of_substitution() { + cov_mark::check!(match_check_wildcard_expanded_to_substitutions); + check_diagnostics( + r#" +struct Foo(T); +struct Bar; +fn main() { + match Foo(Bar) { + _ | Foo(Bar) => {} + } +} +"#, + ); + } + + #[test] + fn record_struct_no_such_field() { + check_diagnostics( + r#" +struct Foo { } +fn main(f: Foo) { + match f { Foo { bar } => () } + // ^^^^^^^^^^^ Internal: match check bailed out +} +"#, + ); + } + mod false_negatives { //! The implementation of match checking here is a work in progress. As we roll this out, we //! prefer false negatives to false positives (ideally there would be no false positives). This @@ -1533,11 +1256,44 @@ fn main() { fn main() { match 5 { 10 => (), + // ^^ Internal: match check bailed out 11..20 => (), } } "#, ); } + + #[test] + fn reference_patterns_at_top_level() { + check_diagnostics( + r#" +fn main() { + match &false { + &true => {} + // ^^^^^ Internal: match check bailed out + } +} + "#, + ); + } + + #[test] + fn reference_patterns_in_fields() { + check_diagnostics( + r#" +fn main() { + match (&false,) { + (true,) => {} + // ^^^^^^^ Internal: match check bailed out + } + match (&false,) { + (&true,) => {} + // ^^^^^^^^ Internal: match check bailed out + } +} + "#, + ); + } } } diff --git a/crates/hir_ty/src/diagnostics/match_check/deconstruct_pat.rs b/crates/hir_ty/src/diagnostics/match_check/deconstruct_pat.rs new file mode 100644 index 000000000000..1f4219b4226e --- /dev/null +++ b/crates/hir_ty/src/diagnostics/match_check/deconstruct_pat.rs @@ -0,0 +1,907 @@ +//! [`super::usefulness`] explains most of what is happening in this file. As explained there, +//! values and patterns are made from constructors applied to fields. This file defines a +//! `Constructor` enum, a `Fields` struct, and various operations to manipulate them and convert +//! them from/to patterns. +//! +//! There's one idea that is not detailed in [`super::usefulness`] because the details are not +//! needed there: _constructor splitting_. +//! +//! # Constructor splitting +//! +//! The idea is as follows: given a constructor `c` and a matrix, we want to specialize in turn +//! with all the value constructors that are covered by `c`, and compute usefulness for each. +//! Instead of listing all those constructors (which is intractable), we group those value +//! constructors together as much as possible. Example: +//! +//! ``` +//! match (0, false) { +//! (0 ..=100, true) => {} // `p_1` +//! (50..=150, false) => {} // `p_2` +//! (0 ..=200, _) => {} // `q` +//! } +//! ``` +//! +//! The naive approach would try all numbers in the range `0..=200`. But we can be a lot more +//! clever: `0` and `1` for example will match the exact same rows, and return equivalent +//! witnesses. In fact all of `0..50` would. We can thus restrict our exploration to 4 +//! constructors: `0..50`, `50..=100`, `101..=150` and `151..=200`. That is enough and infinitely +//! more tractable. +//! +//! We capture this idea in a function `split(p_1 ... p_n, c)` which returns a list of constructors +//! `c'` covered by `c`. Given such a `c'`, we require that all value ctors `c''` covered by `c'` +//! return an equivalent set of witnesses after specializing and computing usefulness. +//! In the example above, witnesses for specializing by `c''` covered by `0..50` will only differ +//! in their first element. +//! +//! We usually also ask that the `c'` together cover all of the original `c`. However we allow +//! skipping some constructors as long as it doesn't change whether the resulting list of witnesses +//! is empty of not. We use this in the wildcard `_` case. +//! +//! Splitting is implemented in the [`Constructor::split`] function. We don't do splitting for +//! or-patterns; instead we just try the alternatives one-by-one. For details on splitting +//! wildcards, see [`SplitWildcard`]; for integer ranges, see [`SplitIntRange`]; for slices, see +//! [`SplitVarLenSlice`]. + +use std::{ + cmp::{max, min}, + iter::once, + ops::RangeInclusive, +}; + +use hir_def::{EnumVariantId, HasModule, LocalFieldId, VariantId}; +use smallvec::{smallvec, SmallVec}; + +use crate::{AdtId, Interner, Scalar, Ty, TyExt, TyKind}; + +use super::{ + usefulness::{MatchCheckCtx, PatCtxt}, + FieldPat, Pat, PatId, PatKind, +}; + +use self::Constructor::*; + +/// [Constructor] uses this in umimplemented variants. +/// It allows porting match expressions from upstream algorithm without losing semantics. +#[derive(Copy, Clone, Debug, PartialEq, Eq)] +pub(super) enum Void {} + +/// An inclusive interval, used for precise integer exhaustiveness checking. +/// `IntRange`s always store a contiguous range. This means that values are +/// encoded such that `0` encodes the minimum value for the integer, +/// regardless of the signedness. +/// For example, the pattern `-128..=127i8` is encoded as `0..=255`. +/// This makes comparisons and arithmetic on interval endpoints much more +/// straightforward. See `signed_bias` for details. +/// +/// `IntRange` is never used to encode an empty range or a "range" that wraps +/// around the (offset) space: i.e., `range.lo <= range.hi`. +#[derive(Clone, Debug, PartialEq, Eq)] +pub(super) struct IntRange { + range: RangeInclusive, +} + +impl IntRange { + #[inline] + fn is_integral(ty: &Ty) -> bool { + match ty.kind(&Interner) { + TyKind::Scalar(Scalar::Char) + | TyKind::Scalar(Scalar::Int(_)) + | TyKind::Scalar(Scalar::Uint(_)) + | TyKind::Scalar(Scalar::Bool) => true, + _ => false, + } + } + + fn is_singleton(&self) -> bool { + self.range.start() == self.range.end() + } + + fn boundaries(&self) -> (u128, u128) { + (*self.range.start(), *self.range.end()) + } + + #[inline] + fn from_bool(value: bool) -> IntRange { + let val = value as u128; + IntRange { range: val..=val } + } + + #[inline] + fn from_range(lo: u128, hi: u128, scalar_ty: Scalar) -> IntRange { + if let Scalar::Bool = scalar_ty { + IntRange { range: lo..=hi } + } else { + unimplemented!() + } + } + + fn is_subrange(&self, other: &Self) -> bool { + other.range.start() <= self.range.start() && self.range.end() <= other.range.end() + } + + fn intersection(&self, other: &Self) -> Option { + let (lo, hi) = self.boundaries(); + let (other_lo, other_hi) = other.boundaries(); + if lo <= other_hi && other_lo <= hi { + Some(IntRange { range: max(lo, other_lo)..=min(hi, other_hi) }) + } else { + None + } + } + + /// See `Constructor::is_covered_by` + fn is_covered_by(&self, other: &Self) -> bool { + if self.intersection(other).is_some() { + // Constructor splitting should ensure that all intersections we encounter are actually + // inclusions. + assert!(self.is_subrange(other)); + true + } else { + false + } + } +} + +/// Represents a border between 2 integers. Because the intervals spanning borders must be able to +/// cover every integer, we need to be able to represent 2^128 + 1 such borders. +#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord)] +enum IntBorder { + JustBefore(u128), + AfterMax, +} + +/// A range of integers that is partitioned into disjoint subranges. This does constructor +/// splitting for integer ranges as explained at the top of the file. +/// +/// This is fed multiple ranges, and returns an output that covers the input, but is split so that +/// the only intersections between an output range and a seen range are inclusions. No output range +/// straddles the boundary of one of the inputs. +/// +/// The following input: +/// ``` +/// |-------------------------| // `self` +/// |------| |----------| |----| +/// |-------| |-------| +/// ``` +/// would be iterated over as follows: +/// ``` +/// ||---|--||-|---|---|---|--| +/// ``` +#[derive(Debug, Clone)] +struct SplitIntRange { + /// The range we are splitting + range: IntRange, + /// The borders of ranges we have seen. They are all contained within `range`. This is kept + /// sorted. + borders: Vec, +} + +impl SplitIntRange { + fn new(range: IntRange) -> Self { + SplitIntRange { range, borders: Vec::new() } + } + + /// Internal use + fn to_borders(r: IntRange) -> [IntBorder; 2] { + use IntBorder::*; + let (lo, hi) = r.boundaries(); + let lo = JustBefore(lo); + let hi = match hi.checked_add(1) { + Some(m) => JustBefore(m), + None => AfterMax, + }; + [lo, hi] + } + + /// Add ranges relative to which we split. + fn split(&mut self, ranges: impl Iterator) { + let this_range = &self.range; + let included_ranges = ranges.filter_map(|r| this_range.intersection(&r)); + let included_borders = included_ranges.flat_map(|r| { + let borders = Self::to_borders(r); + once(borders[0]).chain(once(borders[1])) + }); + self.borders.extend(included_borders); + self.borders.sort_unstable(); + } + + /// Iterate over the contained ranges. + fn iter(&self) -> impl Iterator + '_ { + use IntBorder::*; + + let self_range = Self::to_borders(self.range.clone()); + // Start with the start of the range. + let mut prev_border = self_range[0]; + self.borders + .iter() + .copied() + // End with the end of the range. + .chain(once(self_range[1])) + // List pairs of adjacent borders. + .map(move |border| { + let ret = (prev_border, border); + prev_border = border; + ret + }) + // Skip duplicates. + .filter(|(prev_border, border)| prev_border != border) + // Finally, convert to ranges. + .map(|(prev_border, border)| { + let range = match (prev_border, border) { + (JustBefore(n), JustBefore(m)) if n < m => n..=(m - 1), + (JustBefore(n), AfterMax) => n..=u128::MAX, + _ => unreachable!(), // Ruled out by the sorting and filtering we did + }; + IntRange { range } + }) + } +} + +/// A constructor for array and slice patterns. +#[derive(Copy, Clone, Debug, PartialEq, Eq)] +pub(super) struct Slice { + _unimplemented: Void, +} + +impl Slice { + /// See `Constructor::is_covered_by` + fn is_covered_by(self, _other: Self) -> bool { + unimplemented!() // never called as Slice contains Void + } +} + +/// A value can be decomposed into a constructor applied to some fields. This struct represents +/// the constructor. See also `Fields`. +/// +/// `pat_constructor` retrieves the constructor corresponding to a pattern. +/// `specialize_constructor` returns the list of fields corresponding to a pattern, given a +/// constructor. `Constructor::apply` reconstructs the pattern from a pair of `Constructor` and +/// `Fields`. +#[allow(dead_code)] +#[derive(Clone, Debug, PartialEq)] +pub(super) enum Constructor { + /// The constructor for patterns that have a single constructor, like tuples, struct patterns + /// and fixed-length arrays. + Single, + /// Enum variants. + Variant(EnumVariantId), + /// Ranges of integer literal values (`2`, `2..=5` or `2..5`). + IntRange(IntRange), + /// Ranges of floating-point literal values (`2.0..=5.2`). + FloatRange(Void), + /// String literals. Strings are not quite the same as `&[u8]` so we treat them separately. + Str(Void), + /// Array and slice patterns. + Slice(Slice), + /// Constants that must not be matched structurally. They are treated as black + /// boxes for the purposes of exhaustiveness: we must not inspect them, and they + /// don't count towards making a match exhaustive. + Opaque, + /// Fake extra constructor for enums that aren't allowed to be matched exhaustively. Also used + /// for those types for which we cannot list constructors explicitly, like `f64` and `str`. + NonExhaustive, + /// Stands for constructors that are not seen in the matrix, as explained in the documentation + /// for [`SplitWildcard`]. + Missing, + /// Wildcard pattern. + Wildcard, +} + +impl Constructor { + pub(super) fn is_wildcard(&self) -> bool { + matches!(self, Wildcard) + } + + fn as_int_range(&self) -> Option<&IntRange> { + match self { + IntRange(range) => Some(range), + _ => None, + } + } + + fn as_slice(&self) -> Option { + match self { + Slice(slice) => Some(*slice), + _ => None, + } + } + + fn variant_id_for_adt(&self, adt: hir_def::AdtId) -> VariantId { + match *self { + Variant(id) => id.into(), + Single => { + assert!(!matches!(adt, hir_def::AdtId::EnumId(_))); + match adt { + hir_def::AdtId::EnumId(_) => unreachable!(), + hir_def::AdtId::StructId(id) => id.into(), + hir_def::AdtId::UnionId(id) => id.into(), + } + } + _ => panic!("bad constructor {:?} for adt {:?}", self, adt), + } + } + + /// Determines the constructor that the given pattern can be specialized to. + pub(super) fn from_pat(cx: &MatchCheckCtx<'_>, pat: PatId) -> Self { + match cx.pattern_arena.borrow()[pat].kind.as_ref() { + PatKind::Binding { .. } | PatKind::Wild => Wildcard, + PatKind::Leaf { .. } | PatKind::Deref { .. } => Single, + &PatKind::Variant { enum_variant, .. } => Variant(enum_variant), + &PatKind::LiteralBool { value } => IntRange(IntRange::from_bool(value)), + PatKind::Or { .. } => cx.bug("Or-pattern should have been expanded earlier on."), + } + } + + /// Some constructors (namely `Wildcard`, `IntRange` and `Slice`) actually stand for a set of actual + /// constructors (like variants, integers or fixed-sized slices). When specializing for these + /// constructors, we want to be specialising for the actual underlying constructors. + /// Naively, we would simply return the list of constructors they correspond to. We instead are + /// more clever: if there are constructors that we know will behave the same wrt the current + /// matrix, we keep them grouped. For example, all slices of a sufficiently large length + /// will either be all useful or all non-useful with a given matrix. + /// + /// See the branches for details on how the splitting is done. + /// + /// This function may discard some irrelevant constructors if this preserves behavior and + /// diagnostics. Eg. for the `_` case, we ignore the constructors already present in the + /// matrix, unless all of them are. + pub(super) fn split<'a>( + &self, + pcx: PatCtxt<'_>, + ctors: impl Iterator + Clone, + ) -> SmallVec<[Self; 1]> { + match self { + Wildcard => { + let mut split_wildcard = SplitWildcard::new(pcx); + split_wildcard.split(pcx, ctors); + split_wildcard.into_ctors(pcx) + } + // Fast-track if the range is trivial. In particular, we don't do the overlapping + // ranges check. + IntRange(ctor_range) if !ctor_range.is_singleton() => { + let mut split_range = SplitIntRange::new(ctor_range.clone()); + let int_ranges = ctors.filter_map(|ctor| ctor.as_int_range()); + split_range.split(int_ranges.cloned()); + split_range.iter().map(IntRange).collect() + } + Slice(_) => unimplemented!(), + // Any other constructor can be used unchanged. + _ => smallvec![self.clone()], + } + } + + /// Returns whether `self` is covered by `other`, i.e. whether `self` is a subset of `other`. + /// For the simple cases, this is simply checking for equality. For the "grouped" constructors, + /// this checks for inclusion. + // We inline because this has a single call site in `Matrix::specialize_constructor`. + #[inline] + pub(super) fn is_covered_by(&self, pcx: PatCtxt<'_>, other: &Self) -> bool { + // This must be kept in sync with `is_covered_by_any`. + match (self, other) { + // Wildcards cover anything + (_, Wildcard) => true, + // The missing ctors are not covered by anything in the matrix except wildcards. + (Missing, _) | (Wildcard, _) => false, + + (Single, Single) => true, + (Variant(self_id), Variant(other_id)) => self_id == other_id, + + (IntRange(self_range), IntRange(other_range)) => self_range.is_covered_by(other_range), + (FloatRange(..), FloatRange(..)) => { + unimplemented!() + } + (Str(..), Str(..)) => { + unimplemented!() + } + (Slice(self_slice), Slice(other_slice)) => self_slice.is_covered_by(*other_slice), + + // We are trying to inspect an opaque constant. Thus we skip the row. + (Opaque, _) | (_, Opaque) => false, + // Only a wildcard pattern can match the special extra constructor. + (NonExhaustive, _) => false, + + _ => pcx.cx.bug(&format!( + "trying to compare incompatible constructors {:?} and {:?}", + self, other + )), + } + } + + /// Faster version of `is_covered_by` when applied to many constructors. `used_ctors` is + /// assumed to be built from `matrix.head_ctors()` with wildcards filtered out, and `self` is + /// assumed to have been split from a wildcard. + fn is_covered_by_any(&self, pcx: PatCtxt<'_>, used_ctors: &[Constructor]) -> bool { + if used_ctors.is_empty() { + return false; + } + + // This must be kept in sync with `is_covered_by`. + match self { + // If `self` is `Single`, `used_ctors` cannot contain anything else than `Single`s. + Single => !used_ctors.is_empty(), + Variant(_) => used_ctors.iter().any(|c| c == self), + IntRange(range) => used_ctors + .iter() + .filter_map(|c| c.as_int_range()) + .any(|other| range.is_covered_by(other)), + Slice(slice) => used_ctors + .iter() + .filter_map(|c| c.as_slice()) + .any(|other| slice.is_covered_by(other)), + // This constructor is never covered by anything else + NonExhaustive => false, + Str(..) | FloatRange(..) | Opaque | Missing | Wildcard => { + pcx.cx.bug(&format!("found unexpected ctor in all_ctors: {:?}", self)) + } + } + } +} + +/// A wildcard constructor that we split relative to the constructors in the matrix, as explained +/// at the top of the file. +/// +/// A constructor that is not present in the matrix rows will only be covered by the rows that have +/// wildcards. Thus we can group all of those constructors together; we call them "missing +/// constructors". Splitting a wildcard would therefore list all present constructors individually +/// (or grouped if they are integers or slices), and then all missing constructors together as a +/// group. +/// +/// However we can go further: since any constructor will match the wildcard rows, and having more +/// rows can only reduce the amount of usefulness witnesses, we can skip the present constructors +/// and only try the missing ones. +/// This will not preserve the whole list of witnesses, but will preserve whether the list is empty +/// or not. In fact this is quite natural from the point of view of diagnostics too. This is done +/// in `to_ctors`: in some cases we only return `Missing`. +#[derive(Debug)] +pub(super) struct SplitWildcard { + /// Constructors seen in the matrix. + matrix_ctors: Vec, + /// All the constructors for this type + all_ctors: SmallVec<[Constructor; 1]>, +} + +impl SplitWildcard { + pub(super) fn new(pcx: PatCtxt<'_>) -> Self { + let cx = pcx.cx; + let make_range = |start, end, scalar| IntRange(IntRange::from_range(start, end, scalar)); + + // Unhandled types are treated as non-exhaustive. Being explicit here instead of falling + // to catchall arm to ease further implementation. + let unhandled = || smallvec![NonExhaustive]; + + // This determines the set of all possible constructors for the type `pcx.ty`. For numbers, + // arrays and slices we use ranges and variable-length slices when appropriate. + // + // If the `exhaustive_patterns` feature is enabled, we make sure to omit constructors that + // are statically impossible. E.g., for `Option`, we do not include `Some(_)` in the + // returned list of constructors. + // Invariant: this is empty if and only if the type is uninhabited (as determined by + // `cx.is_uninhabited()`). + let all_ctors = match pcx.ty.kind(&Interner) { + TyKind::Scalar(Scalar::Bool) => smallvec![make_range(0, 1, Scalar::Bool)], + // TyKind::Array(..) if ... => unhandled(), + TyKind::Array(..) | TyKind::Slice(..) => unhandled(), + &TyKind::Adt(AdtId(hir_def::AdtId::EnumId(enum_id)), ref _substs) => { + let enum_data = cx.db.enum_data(enum_id); + + // If the enum is declared as `#[non_exhaustive]`, we treat it as if it had an + // additional "unknown" constructor. + // There is no point in enumerating all possible variants, because the user can't + // actually match against them all themselves. So we always return only the fictitious + // constructor. + // E.g., in an example like: + // + // ``` + // let err: io::ErrorKind = ...; + // match err { + // io::ErrorKind::NotFound => {}, + // } + // ``` + // + // we don't want to show every possible IO error, but instead have only `_` as the + // witness. + let is_declared_nonexhaustive = cx.is_foreign_non_exhaustive_enum(enum_id); + + // If `exhaustive_patterns` is disabled and our scrutinee is an empty enum, we treat it + // as though it had an "unknown" constructor to avoid exposing its emptiness. The + // exception is if the pattern is at the top level, because we want empty matches to be + // considered exhaustive. + let is_secretly_empty = enum_data.variants.is_empty() + && !cx.feature_exhaustive_patterns() + && !pcx.is_top_level; + + if is_secretly_empty || is_declared_nonexhaustive { + smallvec![NonExhaustive] + } else if cx.feature_exhaustive_patterns() { + unimplemented!() // see MatchCheckCtx.feature_exhaustive_patterns() + } else { + enum_data + .variants + .iter() + .map(|(local_id, ..)| Variant(EnumVariantId { parent: enum_id, local_id })) + .collect() + } + } + TyKind::Scalar(Scalar::Char) => unhandled(), + TyKind::Scalar(Scalar::Int(..)) | TyKind::Scalar(Scalar::Uint(..)) => unhandled(), + TyKind::Never if !cx.feature_exhaustive_patterns() && !pcx.is_top_level => { + smallvec![NonExhaustive] + } + TyKind::Never => SmallVec::new(), + _ if cx.is_uninhabited(&pcx.ty) => SmallVec::new(), + TyKind::Adt(..) | TyKind::Tuple(..) | TyKind::Ref(..) => smallvec![Single], + // This type is one for which we cannot list constructors, like `str` or `f64`. + _ => smallvec![NonExhaustive], + }; + SplitWildcard { matrix_ctors: Vec::new(), all_ctors } + } + + /// Pass a set of constructors relative to which to split this one. Don't call twice, it won't + /// do what you want. + pub(super) fn split<'a>( + &mut self, + pcx: PatCtxt<'_>, + ctors: impl Iterator + Clone, + ) { + // Since `all_ctors` never contains wildcards, this won't recurse further. + self.all_ctors = + self.all_ctors.iter().flat_map(|ctor| ctor.split(pcx, ctors.clone())).collect(); + self.matrix_ctors = ctors.filter(|c| !c.is_wildcard()).cloned().collect(); + } + + /// Whether there are any value constructors for this type that are not present in the matrix. + fn any_missing(&self, pcx: PatCtxt<'_>) -> bool { + self.iter_missing(pcx).next().is_some() + } + + /// Iterate over the constructors for this type that are not present in the matrix. + pub(super) fn iter_missing<'a>( + &'a self, + pcx: PatCtxt<'a>, + ) -> impl Iterator { + self.all_ctors.iter().filter(move |ctor| !ctor.is_covered_by_any(pcx, &self.matrix_ctors)) + } + + /// Return the set of constructors resulting from splitting the wildcard. As explained at the + /// top of the file, if any constructors are missing we can ignore the present ones. + fn into_ctors(self, pcx: PatCtxt<'_>) -> SmallVec<[Constructor; 1]> { + if self.any_missing(pcx) { + // Some constructors are missing, thus we can specialize with the special `Missing` + // constructor, which stands for those constructors that are not seen in the matrix, + // and matches the same rows as any of them (namely the wildcard rows). See the top of + // the file for details. + // However, when all constructors are missing we can also specialize with the full + // `Wildcard` constructor. The difference will depend on what we want in diagnostics. + + // If some constructors are missing, we typically want to report those constructors, + // e.g.: + // ``` + // enum Direction { N, S, E, W } + // let Direction::N = ...; + // ``` + // we can report 3 witnesses: `S`, `E`, and `W`. + // + // However, if the user didn't actually specify a constructor + // in this arm, e.g., in + // ``` + // let x: (Direction, Direction, bool) = ...; + // let (_, _, false) = x; + // ``` + // we don't want to show all 16 possible witnesses `(, , + // true)` - we are satisfied with `(_, _, true)`. So if all constructors are missing we + // prefer to report just a wildcard `_`. + // + // The exception is: if we are at the top-level, for example in an empty match, we + // sometimes prefer reporting the list of constructors instead of just `_`. + let report_when_all_missing = pcx.is_top_level && !IntRange::is_integral(pcx.ty); + let ctor = if !self.matrix_ctors.is_empty() || report_when_all_missing { + Missing + } else { + Wildcard + }; + return smallvec![ctor]; + } + + // All the constructors are present in the matrix, so we just go through them all. + self.all_ctors + } +} + +/// A value can be decomposed into a constructor applied to some fields. This struct represents +/// those fields, generalized to allow patterns in each field. See also `Constructor`. +/// This is constructed from a constructor using [`Fields::wildcards()`]. +/// +/// If a private or `non_exhaustive` field is uninhabited, the code mustn't observe that it is +/// uninhabited. For that, we filter these fields out of the matrix. This is handled automatically +/// in `Fields`. This filtering is uncommon in practice, because uninhabited fields are rarely used, +/// so we avoid it when possible to preserve performance. +#[derive(Debug, Clone)] +pub(super) enum Fields { + /// Lists of patterns that don't contain any filtered fields. + /// `Slice` and `Vec` behave the same; the difference is only to avoid allocating and + /// triple-dereferences when possible. Frankly this is premature optimization, I (Nadrieril) + /// have not measured if it really made a difference. + Vec(SmallVec<[PatId; 2]>), +} + +impl Fields { + /// Internal use. Use `Fields::wildcards()` instead. + /// Must not be used if the pattern is a field of a struct/tuple/variant. + fn from_single_pattern(pat: PatId) -> Self { + Fields::Vec(smallvec![pat]) + } + + /// Convenience; internal use. + fn wildcards_from_tys(cx: &MatchCheckCtx<'_>, tys: impl IntoIterator) -> Self { + let wilds = tys.into_iter().map(Pat::wildcard_from_ty); + let pats = wilds.map(|pat| cx.alloc_pat(pat)).collect(); + Fields::Vec(pats) + } + + /// Creates a new list of wildcard fields for a given constructor. + pub(crate) fn wildcards(pcx: PatCtxt<'_>, constructor: &Constructor) -> Self { + let ty = pcx.ty; + let cx = pcx.cx; + let wildcard_from_ty = |ty: &Ty| cx.alloc_pat(Pat::wildcard_from_ty(ty.clone())); + + let ret = match constructor { + Single | Variant(_) => match ty.kind(&Interner) { + TyKind::Tuple(_, substs) => { + let tys = substs.iter(&Interner).map(|ty| ty.assert_ty_ref(&Interner)); + Fields::wildcards_from_tys(cx, tys.cloned()) + } + TyKind::Ref(.., rty) => Fields::from_single_pattern(wildcard_from_ty(rty)), + &TyKind::Adt(AdtId(adt), ref substs) => { + if adt_is_box(adt, cx) { + // Use T as the sub pattern type of Box. + let subst_ty = substs.at(&Interner, 0).assert_ty_ref(&Interner); + Fields::from_single_pattern(wildcard_from_ty(subst_ty)) + } else { + let variant_id = constructor.variant_id_for_adt(adt); + let adt_is_local = + variant_id.module(cx.db.upcast()).krate() == cx.module.krate(); + // Whether we must not match the fields of this variant exhaustively. + let is_non_exhaustive = + is_field_list_non_exhaustive(variant_id, cx) && !adt_is_local; + + cov_mark::hit!(match_check_wildcard_expanded_to_substitutions); + let field_ty_data = cx.db.field_types(variant_id); + let field_tys = || { + field_ty_data + .iter() + .map(|(_, binders)| binders.clone().substitute(&Interner, substs)) + }; + + // In the following cases, we don't need to filter out any fields. This is + // the vast majority of real cases, since uninhabited fields are uncommon. + let has_no_hidden_fields = (matches!(adt, hir_def::AdtId::EnumId(_)) + && !is_non_exhaustive) + || !field_tys().any(|ty| cx.is_uninhabited(&ty)); + + if has_no_hidden_fields { + Fields::wildcards_from_tys(cx, field_tys()) + } else { + //FIXME(iDawer): see MatchCheckCtx::is_uninhabited, has_no_hidden_fields is always true + unimplemented!("exhaustive_patterns feature") + } + } + } + ty_kind => { + cx.bug(&format!("Unexpected type for `Single` constructor: {:?}", ty_kind)) + } + }, + Slice(..) => { + unimplemented!() + } + Str(..) | FloatRange(..) | IntRange(..) | NonExhaustive | Opaque | Missing + | Wildcard => Fields::Vec(Default::default()), + }; + ret + } + + /// Apply a constructor to a list of patterns, yielding a new pattern. `self` + /// must have as many elements as this constructor's arity. + /// + /// This is roughly the inverse of `specialize_constructor`. + /// + /// Examples: + /// `ctor`: `Constructor::Single` + /// `ty`: `Foo(u32, u32, u32)` + /// `self`: `[10, 20, _]` + /// returns `Foo(10, 20, _)` + /// + /// `ctor`: `Constructor::Variant(Option::Some)` + /// `ty`: `Option` + /// `self`: `[false]` + /// returns `Some(false)` + pub(super) fn apply(self, pcx: PatCtxt<'_>, ctor: &Constructor) -> Pat { + let subpatterns_and_indices = self.patterns_and_indices(); + let mut subpatterns = + subpatterns_and_indices.iter().map(|&(_, p)| pcx.cx.pattern_arena.borrow()[p].clone()); + // FIXME(iDawer) witnesses are not yet used + const UNHANDLED: PatKind = PatKind::Wild; + + let pat = match ctor { + Single | Variant(_) => match pcx.ty.kind(&Interner) { + TyKind::Adt(..) | TyKind::Tuple(..) => { + // We want the real indices here. + let subpatterns = subpatterns_and_indices + .iter() + .map(|&(field, pat)| FieldPat { + field, + pattern: pcx.cx.pattern_arena.borrow()[pat].clone(), + }) + .collect(); + + if let Some((adt, substs)) = pcx.ty.as_adt() { + if let hir_def::AdtId::EnumId(_) = adt { + let enum_variant = match ctor { + &Variant(id) => id, + _ => unreachable!(), + }; + PatKind::Variant { substs: substs.clone(), enum_variant, subpatterns } + } else { + PatKind::Leaf { subpatterns } + } + } else { + PatKind::Leaf { subpatterns } + } + } + // Note: given the expansion of `&str` patterns done in `expand_pattern`, we should + // be careful to reconstruct the correct constant pattern here. However a string + // literal pattern will never be reported as a non-exhaustiveness witness, so we + // can ignore this issue. + TyKind::Ref(..) => PatKind::Deref { subpattern: subpatterns.next().unwrap() }, + TyKind::Slice(..) | TyKind::Array(..) => { + pcx.cx.bug(&format!("bad slice pattern {:?} {:?}", ctor, pcx.ty)) + } + _ => PatKind::Wild, + }, + Constructor::Slice(_) => UNHANDLED, + Str(_) => UNHANDLED, + FloatRange(..) => UNHANDLED, + Constructor::IntRange(_) => UNHANDLED, + NonExhaustive => PatKind::Wild, + Wildcard => return Pat::wildcard_from_ty(pcx.ty.clone()), + Opaque => pcx.cx.bug("we should not try to apply an opaque constructor"), + Missing => pcx.cx.bug( + "trying to apply the `Missing` constructor;\ + this should have been done in `apply_constructors`", + ), + }; + + Pat { ty: pcx.ty.clone(), kind: Box::new(pat) } + } + + /// Returns the number of patterns. This is the same as the arity of the constructor used to + /// construct `self`. + pub(super) fn len(&self) -> usize { + match self { + Fields::Vec(pats) => pats.len(), + } + } + + /// Returns the list of patterns along with the corresponding field indices. + fn patterns_and_indices(&self) -> SmallVec<[(LocalFieldId, PatId); 2]> { + match self { + Fields::Vec(pats) => pats + .iter() + .copied() + .enumerate() + .map(|(i, p)| (LocalFieldId::from_raw((i as u32).into()), p)) + .collect(), + } + } + + pub(super) fn into_patterns(self) -> SmallVec<[PatId; 2]> { + match self { + Fields::Vec(pats) => pats, + } + } + + /// Overrides some of the fields with the provided patterns. Exactly like + /// `replace_fields_indexed`, except that it takes `FieldPat`s as input. + fn replace_with_fieldpats( + &self, + new_pats: impl IntoIterator, + ) -> Self { + self.replace_fields_indexed( + new_pats.into_iter().map(|(field, pat)| (u32::from(field.into_raw()) as usize, pat)), + ) + } + + /// Overrides some of the fields with the provided patterns. This is used when a pattern + /// defines some fields but not all, for example `Foo { field1: Some(_), .. }`: here we start + /// with a `Fields` that is just one wildcard per field of the `Foo` struct, and override the + /// entry corresponding to `field1` with the pattern `Some(_)`. This is also used for slice + /// patterns for the same reason. + fn replace_fields_indexed(&self, new_pats: impl IntoIterator) -> Self { + let mut fields = self.clone(); + + match &mut fields { + Fields::Vec(pats) => { + for (i, pat) in new_pats { + if let Some(p) = pats.get_mut(i) { + *p = pat; + } + } + } + } + fields + } + + /// Replaces contained fields with the given list of patterns. There must be `len()` patterns + /// in `pats`. + pub(super) fn replace_fields( + &self, + cx: &MatchCheckCtx<'_>, + pats: impl IntoIterator, + ) -> Self { + let pats = pats.into_iter().map(|pat| cx.alloc_pat(pat)).collect(); + + match self { + Fields::Vec(_) => Fields::Vec(pats), + } + } + + /// Replaces contained fields with the arguments of the given pattern. Only use on a pattern + /// that is compatible with the constructor used to build `self`. + /// This is meant to be used on the result of `Fields::wildcards()`. The idea is that + /// `wildcards` constructs a list of fields where all entries are wildcards, and the pattern + /// provided to this function fills some of the fields with non-wildcards. + /// In the following example `Fields::wildcards` would return `[_, _, _, _]`. If we call + /// `replace_with_pattern_arguments` on it with the pattern, the result will be `[Some(0), _, + /// _, _]`. + /// ```rust + /// let x: [Option; 4] = foo(); + /// match x { + /// [Some(0), ..] => {} + /// } + /// ``` + /// This is guaranteed to preserve the number of patterns in `self`. + pub(super) fn replace_with_pattern_arguments( + &self, + pat: PatId, + cx: &MatchCheckCtx<'_>, + ) -> Self { + // FIXME(iDawer): Factor out pattern deep cloning. See discussion: + // https://github.com/rust-analyzer/rust-analyzer/pull/8717#discussion_r633086640 + let mut arena = cx.pattern_arena.borrow_mut(); + match arena[pat].kind.as_ref() { + PatKind::Deref { subpattern } => { + assert_eq!(self.len(), 1); + let subpattern = subpattern.clone(); + Fields::from_single_pattern(arena.alloc(subpattern)) + } + PatKind::Leaf { subpatterns } | PatKind::Variant { subpatterns, .. } => { + let subpatterns = subpatterns.clone(); + let subpatterns = subpatterns + .iter() + .map(|field_pat| (field_pat.field, arena.alloc(field_pat.pattern.clone()))); + self.replace_with_fieldpats(subpatterns) + } + + PatKind::Wild + | PatKind::Binding { .. } + | PatKind::LiteralBool { .. } + | PatKind::Or { .. } => self.clone(), + } + } +} + +fn is_field_list_non_exhaustive(variant_id: VariantId, cx: &MatchCheckCtx<'_>) -> bool { + let attr_def_id = match variant_id { + VariantId::EnumVariantId(id) => id.into(), + VariantId::StructId(id) => id.into(), + VariantId::UnionId(id) => id.into(), + }; + cx.db.attrs(attr_def_id).by_key("non_exhaustive").exists() +} + +fn adt_is_box(adt: hir_def::AdtId, cx: &MatchCheckCtx<'_>) -> bool { + use hir_def::lang_item::LangItemTarget; + match cx.db.lang_item(cx.module.krate(), "owned_box".into()) { + Some(LangItemTarget::StructId(box_id)) => adt == box_id.into(), + _ => false, + } +} diff --git a/crates/hir_ty/src/diagnostics/match_check/pat_util.rs b/crates/hir_ty/src/diagnostics/match_check/pat_util.rs new file mode 100644 index 000000000000..b89b4f2bfb7d --- /dev/null +++ b/crates/hir_ty/src/diagnostics/match_check/pat_util.rs @@ -0,0 +1,56 @@ +//! Pattern untilities. +//! +//! Originates from `rustc_hir::pat_util` + +use std::iter::{Enumerate, ExactSizeIterator}; + +pub(crate) struct EnumerateAndAdjust { + enumerate: Enumerate, + gap_pos: usize, + gap_len: usize, +} + +impl Iterator for EnumerateAndAdjust +where + I: Iterator, +{ + type Item = (usize, ::Item); + + fn next(&mut self) -> Option<(usize, ::Item)> { + self.enumerate + .next() + .map(|(i, elem)| (if i < self.gap_pos { i } else { i + self.gap_len }, elem)) + } + + fn size_hint(&self) -> (usize, Option) { + self.enumerate.size_hint() + } +} + +pub(crate) trait EnumerateAndAdjustIterator { + fn enumerate_and_adjust( + self, + expected_len: usize, + gap_pos: Option, + ) -> EnumerateAndAdjust + where + Self: Sized; +} + +impl EnumerateAndAdjustIterator for T { + fn enumerate_and_adjust( + self, + expected_len: usize, + gap_pos: Option, + ) -> EnumerateAndAdjust + where + Self: Sized, + { + let actual_len = self.len(); + EnumerateAndAdjust { + enumerate: self.enumerate(), + gap_pos: gap_pos.unwrap_or(expected_len), + gap_len: expected_len - actual_len, + } + } +} diff --git a/crates/hir_ty/src/diagnostics/match_check/usefulness.rs b/crates/hir_ty/src/diagnostics/match_check/usefulness.rs new file mode 100644 index 000000000000..83b094a89383 --- /dev/null +++ b/crates/hir_ty/src/diagnostics/match_check/usefulness.rs @@ -0,0 +1,1188 @@ +//! Based on rust-lang/rust 1.52.0-nightly (25c15cdbe 2021-04-22) +//! https://github.com/rust-lang/rust/blob/25c15cdbe/compiler/rustc_mir_build/src/thir/pattern/usefulness.rs +//! +//! ----- +//! +//! 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 +//! 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. +//! ```rust +//! 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 (matcheable) +//! 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 matcheable 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` 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: +//! ``` +//! 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: +//! +//! ``` +//! 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: +//! ``` +//! [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: +//! ``` +//! [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 std::{cell::RefCell, iter::FromIterator}; + +use hir_def::{expr::ExprId, HasModule, ModuleId}; +use la_arena::Arena; +use once_cell::unsync::OnceCell; +use rustc_hash::FxHashMap; +use smallvec::{smallvec, SmallVec}; + +use crate::{db::HirDatabase, InferenceResult, Interner, Ty}; + +use super::{ + deconstruct_pat::{Constructor, Fields, SplitWildcard}, + Pat, PatId, PatKind, PatternFoldable, PatternFolder, +}; + +use self::{helper::PatIdExt, Usefulness::*, WitnessPreference::*}; + +pub(crate) struct MatchCheckCtx<'a> { + pub(crate) module: ModuleId, + pub(crate) match_expr: ExprId, + pub(crate) infer: &'a InferenceResult, + pub(crate) db: &'a dyn HirDatabase, + /// Lowered patterns from arms plus generated by the check. + pub(crate) pattern_arena: &'a RefCell, + pub(crate) eprint_panic_context: &'a dyn Fn(), +} + +impl<'a> MatchCheckCtx<'a> { + pub(super) fn is_uninhabited(&self, _ty: &Ty) -> bool { + // FIXME(iDawer) implement exhaustive_patterns feature. More info in: + // Tracking issue for RFC 1872: exhaustive_patterns feature https://github.com/rust-lang/rust/issues/51085 + false + } + + /// Returns whether the given type is an enum from another crate declared `#[non_exhaustive]`. + pub(super) fn is_foreign_non_exhaustive_enum(&self, enum_id: hir_def::EnumId) -> bool { + let has_non_exhaustive_attr = + self.db.attrs(enum_id.into()).by_key("non_exhaustive").exists(); + let is_local = + hir_def::AdtId::from(enum_id).module(self.db.upcast()).krate() == self.module.krate(); + has_non_exhaustive_attr && !is_local + } + + // Rust feature described as "Allows exhaustive pattern matching on types that contain uninhabited types." + pub(super) fn feature_exhaustive_patterns(&self) -> bool { + // FIXME see MatchCheckCtx::is_uninhabited + false + } + + pub(super) fn alloc_pat(&self, pat: Pat) -> PatId { + self.pattern_arena.borrow_mut().alloc(pat) + } + + /// Get type of a pattern. Handles expanded patterns. + pub(super) fn type_of(&self, pat: PatId) -> Ty { + self.pattern_arena.borrow()[pat].ty.clone() + } + + #[track_caller] + pub(super) fn bug(&self, info: &str) -> ! { + (self.eprint_panic_context)(); + panic!("bug: {}", info); + } +} + +#[derive(Copy, Clone)] +pub(super) struct PatCtxt<'a> { + pub(super) cx: &'a MatchCheckCtx<'a>, + /// Type of the current column under investigation. + pub(super) ty: &'a Ty, + /// 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, +} + +pub(crate) fn expand_pattern(pat: Pat) -> Pat { + LiteralExpander.fold_pattern(&pat) +} + +struct LiteralExpander; + +impl PatternFolder for LiteralExpander { + fn fold_pattern(&mut self, pat: &Pat) -> Pat { + match (pat.ty.kind(&Interner), pat.kind.as_ref()) { + (_, PatKind::Binding { subpattern: Some(s), .. }) => s.fold_with(self), + _ => pat.super_fold_with(self), + } + } +} + +impl Pat { + fn _is_wildcard(&self) -> bool { + matches!(*self.kind, PatKind::Binding { subpattern: None, .. } | PatKind::Wild) + } +} + +impl PatIdExt for PatId { + fn is_or_pat(self, cx: &MatchCheckCtx<'_>) -> bool { + matches!(*cx.pattern_arena.borrow()[self].kind, PatKind::Or { .. }) + } + + /// Recursively expand this pattern into its subpatterns. Only useful for or-patterns. + fn expand_or_pat(self, cx: &MatchCheckCtx<'_>) -> Vec { + fn expand(pat: PatId, vec: &mut Vec, pat_arena: &mut PatternArena) { + if let PatKind::Or { pats } = pat_arena[pat].kind.as_ref() { + // FIXME(iDawer): Factor out pattern deep cloning. See discussion: + // https://github.com/rust-analyzer/rust-analyzer/pull/8717#discussion_r633086640 + let pats = pats.clone(); + for pat in pats { + let pat = pat_arena.alloc(pat.clone()); + expand(pat, vec, pat_arena); + } + } else { + vec.push(pat) + } + } + + let mut pat_arena = cx.pattern_arena.borrow_mut(); + let mut pats = Vec::new(); + expand(self, &mut pats, &mut pat_arena); + pats + } +} + +/// A row of a matrix. Rows of len 1 are very common, which is why `SmallVec[_; 2]` +/// works well. +#[derive(Clone)] +pub(super) struct PatStack { + pats: SmallVec<[PatId; 2]>, + /// Cache for the constructor of the head + head_ctor: OnceCell, +} + +impl PatStack { + fn from_pattern(pat: PatId) -> Self { + Self::from_vec(smallvec![pat]) + } + + fn from_vec(vec: SmallVec<[PatId; 2]>) -> Self { + PatStack { pats: vec, head_ctor: OnceCell::new() } + } + + fn is_empty(&self) -> bool { + self.pats.is_empty() + } + + fn len(&self) -> usize { + self.pats.len() + } + + fn head(&self) -> PatId { + self.pats[0] + } + + #[inline] + fn head_ctor(&self, cx: &MatchCheckCtx<'_>) -> &Constructor { + self.head_ctor.get_or_init(|| Constructor::from_pat(cx, self.head())) + } + + // 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(&self, cx: &MatchCheckCtx<'_>) -> impl Iterator + '_ { + self.head().expand_or_pat(cx).into_iter().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, + ctor_wild_subpatterns: &Fields, + cx: &MatchCheckCtx<'_>, + ) -> PatStack { + // We pop the head pattern and push the new fields extracted from the arguments of + // `self.head()`. + let mut new_fields = + ctor_wild_subpatterns.replace_with_pattern_arguments(self.head(), cx).into_patterns(); + new_fields.extend_from_slice(&self.pats[1..]); + PatStack::from_vec(new_fields) + } +} + +impl Default for PatStack { + fn default() -> Self { + Self::from_vec(smallvec![]) + } +} + +impl PartialEq for PatStack { + fn eq(&self, other: &Self) -> bool { + self.pats == other.pats + } +} + +impl FromIterator for PatStack { + fn from_iter(iter: T) -> Self + where + T: IntoIterator, + { + Self::from_vec(iter.into_iter().collect()) + } +} + +/// A 2D matrix. +#[derive(Clone)] +pub(super) struct Matrix { + patterns: Vec, +} + +impl Matrix { + 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 { + 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, cx: &MatchCheckCtx<'_>) { + if !row.is_empty() && row.head().is_or_pat(cx) { + for row in row.expand_or_pat(cx) { + self.patterns.push(row); + } + } else { + self.patterns.push(row); + } + } + + /// Iterate over the first component of each row + fn heads(&self) -> impl Iterator + '_ { + self.patterns.iter().map(|r| r.head()) + } + + /// Iterate over the first constructor of each row. + fn head_ctors<'a>( + &'a self, + cx: &'a MatchCheckCtx<'_>, + ) -> impl Iterator + Clone { + self.patterns.iter().map(move |r| r.head_ctor(cx)) + } + + /// This computes `S(constructor, self)`. See top of the file for explanations. + fn specialize_constructor( + &self, + pcx: PatCtxt<'_>, + ctor: &Constructor, + ctor_wild_subpatterns: &Fields, + ) -> Matrix { + let rows = self + .patterns + .iter() + .filter(|r| ctor.is_covered_by(pcx, r.head_ctor(pcx.cx))) + .map(|r| r.pop_head_constructor(ctor_wild_subpatterns, pcx.cx)); + Matrix::from_iter(rows, pcx.cx) + } + + fn from_iter(rows: impl IntoIterator, cx: &MatchCheckCtx<'_>) -> Matrix { + let mut matrix = Matrix::empty(); + for x in rows { + // Using `push` ensures we correctly expand or-patterns. + matrix.push(x, cx); + } + matrix + } +} + +/// Given a pattern or a pattern-stack, this struct captures a set of its subpatterns. We use that +/// to track reachable sub-patterns arising from or-patterns. In the absence of or-patterns this +/// will always be either `Empty` (the whole pattern is unreachable) or `Full` (the whole pattern +/// is reachable). When there are or-patterns, some subpatterns may be reachable while others +/// aren't. In this case the whole pattern still counts as reachable, but we will lint the +/// unreachable subpatterns. +/// +/// This supports a limited set of operations, so not all possible sets of subpatterns can be +/// represented. That's ok, we only want the ones that make sense for our usage. +/// +/// What we're doing is illustrated by this: +/// ``` +/// match (true, 0) { +/// (true, 0) => {} +/// (_, 1) => {} +/// (true | false, 0 | 1) => {} +/// } +/// ``` +/// When we try the alternatives of the `true | false` or-pattern, the last `0` is reachable in the +/// `false` alternative but not the `true`. So overall it is reachable. By contrast, the last `1` +/// is not reachable in either alternative, so we want to signal this to the user. +/// Therefore we take the union of sets of reachable patterns coming from different alternatives in +/// order to figure out which subpatterns are overall reachable. +/// +/// Invariant: we try to construct the smallest representation we can. In particular if +/// `self.is_empty()` we ensure that `self` is `Empty`, and same with `Full`. This is not important +/// for correctness currently. +#[derive(Debug, Clone)] +enum SubPatSet { + /// The empty set. This means the pattern is unreachable. + Empty, + /// The set containing the full pattern. + Full, + /// If the pattern is a pattern with a constructor or a pattern-stack, we store a set for each + /// of its subpatterns. Missing entries in the map are implicitly full, because that's the + /// common case. + Seq { subpats: FxHashMap }, + /// If the pattern is an or-pattern, we store a set for each of its alternatives. Missing + /// entries in the map are implicitly empty. Note: we always flatten nested or-patterns. + Alt { + subpats: FxHashMap, + /// Counts the total number of alternatives in the pattern + alt_count: usize, + /// We keep the pattern around to retrieve spans. + pat: PatId, + }, +} + +impl SubPatSet { + fn full() -> Self { + SubPatSet::Full + } + + fn empty() -> Self { + SubPatSet::Empty + } + + fn is_empty(&self) -> bool { + match self { + SubPatSet::Empty => true, + SubPatSet::Full => false, + // If any subpattern in a sequence is unreachable, the whole pattern is unreachable. + SubPatSet::Seq { subpats } => subpats.values().any(|set| set.is_empty()), + // An or-pattern is reachable if any of its alternatives is. + SubPatSet::Alt { subpats, .. } => subpats.values().all(|set| set.is_empty()), + } + } + + fn is_full(&self) -> bool { + match self { + SubPatSet::Empty => false, + SubPatSet::Full => true, + // The whole pattern is reachable only when all its alternatives are. + SubPatSet::Seq { subpats } => subpats.values().all(|sub_set| sub_set.is_full()), + // The whole or-pattern is reachable only when all its alternatives are. + SubPatSet::Alt { subpats, alt_count, .. } => { + subpats.len() == *alt_count && subpats.values().all(|set| set.is_full()) + } + } + } + + /// Union `self` with `other`, mutating `self`. + fn union(&mut self, other: Self) { + use SubPatSet::*; + // Union with full stays full; union with empty changes nothing. + if self.is_full() || other.is_empty() { + return; + } else if self.is_empty() { + *self = other; + return; + } else if other.is_full() { + *self = Full; + return; + } + + match (&mut *self, other) { + (Seq { subpats: s_set }, Seq { subpats: mut o_set }) => { + s_set.retain(|i, s_sub_set| { + // Missing entries count as full. + let o_sub_set = o_set.remove(&i).unwrap_or(Full); + s_sub_set.union(o_sub_set); + // We drop full entries. + !s_sub_set.is_full() + }); + // Everything left in `o_set` is missing from `s_set`, i.e. counts as full. Since + // unioning with full returns full, we can drop those entries. + } + (Alt { subpats: s_set, .. }, Alt { subpats: mut o_set, .. }) => { + s_set.retain(|i, s_sub_set| { + // Missing entries count as empty. + let o_sub_set = o_set.remove(&i).unwrap_or(Empty); + s_sub_set.union(o_sub_set); + // We drop empty entries. + !s_sub_set.is_empty() + }); + // Everything left in `o_set` is missing from `s_set`, i.e. counts as empty. Since + // unioning with empty changes nothing, we can take those entries as is. + s_set.extend(o_set); + } + _ => panic!("bug"), + } + + if self.is_full() { + *self = Full; + } + } + + /// Returns a list of the unreachable subpatterns. If `self` is empty (i.e. the + /// whole pattern is unreachable) we return `None`. + fn list_unreachable_subpatterns(&self, cx: &MatchCheckCtx<'_>) -> Option> { + /// Panics if `set.is_empty()`. + fn fill_subpats( + set: &SubPatSet, + unreachable_pats: &mut Vec, + cx: &MatchCheckCtx<'_>, + ) { + match set { + SubPatSet::Empty => panic!("bug"), + SubPatSet::Full => {} + SubPatSet::Seq { subpats } => { + for (_, sub_set) in subpats { + fill_subpats(sub_set, unreachable_pats, cx); + } + } + SubPatSet::Alt { subpats, pat, alt_count, .. } => { + let expanded = pat.expand_or_pat(cx); + for i in 0..*alt_count { + let sub_set = subpats.get(&i).unwrap_or(&SubPatSet::Empty); + if sub_set.is_empty() { + // Found a unreachable subpattern. + unreachable_pats.push(expanded[i]); + } else { + fill_subpats(sub_set, unreachable_pats, cx); + } + } + } + } + } + + if self.is_empty() { + return None; + } + if self.is_full() { + // No subpatterns are unreachable. + return Some(Vec::new()); + } + let mut unreachable_pats = Vec::new(); + fill_subpats(self, &mut unreachable_pats, cx); + Some(unreachable_pats) + } + + /// When `self` refers to a patstack that was obtained from specialization, after running + /// `unspecialize` it will refer to the original patstack before specialization. + fn unspecialize(self, arity: usize) -> Self { + use SubPatSet::*; + match self { + Full => Full, + Empty => Empty, + Seq { subpats } => { + // We gather the first `arity` subpatterns together and shift the remaining ones. + let mut new_subpats = FxHashMap::default(); + let mut new_subpats_first_col = FxHashMap::default(); + for (i, sub_set) in subpats { + if i < arity { + // The first `arity` indices are now part of the pattern in the first + // column. + new_subpats_first_col.insert(i, sub_set); + } else { + // Indices after `arity` are simply shifted + new_subpats.insert(i - arity + 1, sub_set); + } + } + // If `new_subpats_first_col` has no entries it counts as full, so we can omit it. + if !new_subpats_first_col.is_empty() { + new_subpats.insert(0, Seq { subpats: new_subpats_first_col }); + } + Seq { subpats: new_subpats } + } + Alt { .. } => panic!("bug"), // `self` is a patstack + } + } + + /// When `self` refers to a patstack that was obtained from splitting an or-pattern, after + /// running `unspecialize` it will refer to the original patstack before splitting. + /// + /// For example: + /// ``` + /// match Some(true) { + /// Some(true) => {} + /// None | Some(true | false) => {} + /// } + /// ``` + /// Here `None` would return the full set and `Some(true | false)` would return the set + /// containing `false`. After `unsplit_or_pat`, we want the set to contain `None` and `false`. + /// This is what this function does. + fn unsplit_or_pat(mut self, alt_id: usize, alt_count: usize, pat: PatId) -> Self { + use SubPatSet::*; + if self.is_empty() { + return Empty; + } + + // Subpatterns coming from inside the or-pattern alternative itself, e.g. in `None | Some(0 + // | 1)`. + let set_first_col = match &mut self { + Full => Full, + Seq { subpats } => subpats.remove(&0).unwrap_or(Full), + Empty => unreachable!(), + Alt { .. } => panic!("bug"), // `self` is a patstack + }; + let mut subpats_first_col = FxHashMap::default(); + subpats_first_col.insert(alt_id, set_first_col); + let set_first_col = Alt { subpats: subpats_first_col, pat, alt_count }; + + let mut subpats = match self { + Full => FxHashMap::default(), + Seq { subpats } => subpats, + Empty => unreachable!(), + Alt { .. } => panic!("bug"), // `self` is a patstack + }; + subpats.insert(0, set_first_col); + Seq { subpats } + } +} + +/// 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 `WitnessPreference`. +#[derive(Clone, Debug)] +enum Usefulness { + /// Carries a set of subpatterns that have been found to be reachable. If empty, this indicates + /// the whole pattern is unreachable. If not, this indicates that the pattern is reachable but + /// that some sub-patterns may be unreachable (due to or-patterns). In the absence of + /// or-patterns this will always be either `Empty` (the whole pattern is unreachable) or `Full` + /// (the whole pattern is reachable). + NoWitnesses(SubPatSet), + /// Carries a list of witnesses of non-exhaustiveness. If empty, indicates that the whole + /// pattern is unreachable. + WithWitnesses(Vec), +} + +impl Usefulness { + fn new_useful(preference: WitnessPreference) -> Self { + match preference { + ConstructWitness => WithWitnesses(vec![Witness(vec![])]), + LeaveOutWitness => NoWitnesses(SubPatSet::full()), + } + } + fn new_not_useful(preference: WitnessPreference) -> Self { + match preference { + ConstructWitness => WithWitnesses(vec![]), + LeaveOutWitness => NoWitnesses(SubPatSet::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(s), NoWitnesses(o)) => s.union(o), + _ => unreachable!(), + } + } + + /// When trying several branches and each returns a `Usefulness`, we need to combine the + /// results together. + fn merge(pref: WitnessPreference, usefulnesses: impl Iterator) -> Self { + let mut ret = Self::new_not_useful(pref); + for u in usefulnesses { + ret.extend(u); + if let NoWitnesses(subpats) = &ret { + if subpats.is_full() { + // Once we reach the full set, more unions won't change the result. + return ret; + } + } + } + ret + } + + /// After calculating the usefulness for a branch of an or-pattern, call this to make this + /// usefulness mergeable with those from the other branches. + fn unsplit_or_pat(self, alt_id: usize, alt_count: usize, pat: PatId) -> Self { + match self { + NoWitnesses(subpats) => NoWitnesses(subpats.unsplit_or_pat(alt_id, alt_count, pat)), + WithWitnesses(_) => panic!("bug"), + } + } + + /// After calculating usefulness after a specialization, call this to recontruct 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<'_>, + matrix: &Matrix, + ctor: &Constructor, + ctor_wild_subpatterns: &Fields, + ) -> Self { + match self { + WithWitnesses(witnesses) if witnesses.is_empty() => WithWitnesses(witnesses), + WithWitnesses(witnesses) => { + let new_witnesses = if matches!(ctor, Constructor::Missing) { + let mut split_wildcard = SplitWildcard::new(pcx); + split_wildcard.split(pcx, matrix.head_ctors(pcx.cx)); + // 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 new_patterns: Vec<_> = split_wildcard + .iter_missing(pcx) + .map(|missing_ctor| { + Fields::wildcards(pcx, missing_ctor).apply(pcx, missing_ctor) + }) + .collect(); + witnesses + .into_iter() + .flat_map(|witness| { + new_patterns.iter().map(move |pat| { + let mut witness = witness.clone(); + witness.0.push(pat.clone()); + witness + }) + }) + .collect() + } else { + witnesses + .into_iter() + .map(|witness| witness.apply_constructor(pcx, &ctor, ctor_wild_subpatterns)) + .collect() + }; + WithWitnesses(new_witnesses) + } + NoWitnesses(subpats) => NoWitnesses(subpats.unspecialize(ctor_wild_subpatterns.len())), + } + } +} + +#[derive(Copy, Clone, Debug)] +enum WitnessPreference { + ConstructWitness, + LeaveOutWitness, +} + +/// 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 +/// +/// ``` +/// struct Pair(Option<(u32, u32)>, bool); +/// +/// 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(Clone, Debug)] +pub(crate) struct Witness(Vec); + +impl Witness { + /// Asserts that the witness contains a single pattern, and returns it. + fn single_pattern(self) -> Pat { + 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<'_>, + ctor: &Constructor, + ctor_wild_subpatterns: &Fields, + ) -> Self { + let pat = { + let len = self.0.len(); + let arity = ctor_wild_subpatterns.len(); + let pats = self.0.drain((len - arity)..).rev(); + ctor_wild_subpatterns.replace_fields(pcx.cx, pats).apply(pcx, ctor) + }; + + self.0.push(pat); + + self + } +} + +/// Algorithm from . +/// 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`. +/// +/// 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. +fn is_useful( + cx: &MatchCheckCtx<'_>, + matrix: &Matrix, + v: &PatStack, + witness_preference: WitnessPreference, + is_under_guard: bool, + is_top_level: bool, +) -> Usefulness { + 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) + }; + return ret; + } + + assert!(rows.iter().all(|r| r.len() == v.len())); + + // FIXME(Nadrieril): Hack to work around type normalization issues (see rust-lang/rust#72476). + let ty = matrix.heads().next().map_or(cx.type_of(v.head()), |r| cx.type_of(r)); + let pcx = PatCtxt { cx, ty: &ty, is_top_level }; + + // If the first pattern is an or-pattern, expand it. + let ret = if v.head().is_or_pat(cx) { + //expanding or-pattern + let v_head = v.head(); + let vs: Vec<_> = v.expand_or_pat(cx).collect(); + let alt_count = vs.len(); + // We try each or-pattern branch in turn. + let mut matrix = matrix.clone(); + let usefulnesses = vs.into_iter().enumerate().map(|(i, v)| { + let usefulness = is_useful(cx, &matrix, &v, witness_preference, is_under_guard, false); + // 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, cx); + } + usefulness.unsplit_or_pat(i, alt_count, v_head) + }); + Usefulness::merge(witness_preference, usefulnesses) + } else { + let v_ctor = v.head_ctor(cx); + // if let Constructor::IntRange(ctor_range) = v_ctor { + // // Lint on likely incorrect range patterns (#63987) + // ctor_range.lint_overlapping_range_endpoints( + // pcx, + // matrix.head_ctors_and_spans(cx), + // matrix.column_count().unwrap_or(0), + // hir_id, + // ) + // } + + // We split the head constructor of `v`. + let split_ctors = v_ctor.split(pcx, matrix.head_ctors(cx)); + // 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; + let usefulnesses = split_ctors.into_iter().map(|ctor| { + // debug!("specialize({:?})", ctor); + // We cache the result of `Fields::wildcards` because it is used a lot. + let ctor_wild_subpatterns = Fields::wildcards(pcx, &ctor); + let spec_matrix = + start_matrix.specialize_constructor(pcx, &ctor, &ctor_wild_subpatterns); + let v = v.pop_head_constructor(&ctor_wild_subpatterns, cx); + let usefulness = + is_useful(cx, &spec_matrix, &v, witness_preference, is_under_guard, false); + usefulness.apply_constructor(pcx, start_matrix, &ctor, &ctor_wild_subpatterns) + }); + Usefulness::merge(witness_preference, usefulnesses) + }; + + ret +} + +/// The arm of a match expression. +#[derive(Clone, Copy)] +pub(crate) struct MatchArm { + pub(crate) pat: PatId, + 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), + /// The arm is unreachable. + Unreachable, +} + +/// The output of checking a match for exhaustiveness and arm reachability. +pub(crate) struct UsefulnessReport { + /// For each arm of the input, whether that arm is reachable after the arms above it. + pub(crate) _arm_usefulness: Vec<(MatchArm, 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, +} + +/// 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`. +pub(crate) fn compute_match_usefulness( + cx: &MatchCheckCtx<'_>, + arms: &[MatchArm], +) -> UsefulnessReport { + let mut matrix = Matrix::empty(); + let arm_usefulness: Vec<_> = arms + .iter() + .copied() + .map(|arm| { + let v = PatStack::from_pattern(arm.pat); + let usefulness = is_useful(cx, &matrix, &v, LeaveOutWitness, arm.has_guard, true); + if !arm.has_guard { + matrix.push(v, cx); + } + let reachability = match usefulness { + NoWitnesses(subpats) if subpats.is_empty() => Reachability::Unreachable, + NoWitnesses(subpats) => { + Reachability::Reachable(subpats.list_unreachable_subpatterns(cx).unwrap()) + } + WithWitnesses(..) => panic!("bug"), + }; + (arm, reachability) + }) + .collect(); + + let wild_pattern = + cx.pattern_arena.borrow_mut().alloc(Pat::wildcard_from_ty(cx.infer[cx.match_expr].clone())); + let v = PatStack::from_pattern(wild_pattern); + let usefulness = is_useful(cx, &matrix, &v, ConstructWitness, false, true); + let non_exhaustiveness_witnesses = match usefulness { + WithWitnesses(pats) => pats.into_iter().map(Witness::single_pattern).collect(), + NoWitnesses(_) => panic!("bug"), + }; + UsefulnessReport { _arm_usefulness: arm_usefulness, non_exhaustiveness_witnesses } +} + +pub(crate) type PatternArena = Arena; + +mod helper { + use super::MatchCheckCtx; + + pub(super) trait PatIdExt: Sized { + // fn is_wildcard(self, cx: &MatchCheckCtx<'_>) -> bool; + fn is_or_pat(self, cx: &MatchCheckCtx<'_>) -> bool; + fn expand_or_pat(self, cx: &MatchCheckCtx<'_>) -> Vec; + } + + // Copy-pasted from rust/compiler/rustc_data_structures/src/captures.rs + /// "Signaling" trait used in impl trait to tag lifetimes that you may + /// need to capture but don't really need for other reasons. + /// Basically a workaround; see [this comment] for details. + /// + /// [this comment]: https://github.com/rust-lang/rust/issues/34511#issuecomment-373423999 + // FIXME(eddyb) false positive, the lifetime parameter is "phantom" but needed. + #[allow(unused_lifetimes)] + pub(crate) trait Captures<'a> {} + + impl<'a, T: ?Sized> Captures<'a> for T {} +}