rucc_session/

lib.rs

//! The `Session`: the options, the interner and the diagnostic sink that every stage of a
//! single compilation is handed.
//!
//! Design: `spec/03-architecture.md` and `spec/04-driver-and-cli.md`. Layer rank 4, see
//! `spec/18-package-layout.md`.
//!
//! Everything below the driver reaches the outside world through this type and not through
//! `std::fs`, `std::env` or `println!`. That is the whole reason the compiler can be used as
//! a library and tested without spawning a process, and it is enforced by the layer rule
//! rather than by discipline.
//!
//! # Status
//!
//! Options, optimisation levels, emit kinds, diagnostic counting, the source map every span
//! is resolved against, the file system the compiler reads through, the include search path
//! and the headers the compiler itself ships are real. The parallel job model is still a
//! placeholder.
//!
//! This crate is tier 3 in `spec/18-package-layout.md` section 18.5: its Rust API is
//! explicitly unstable and will change without a major version bump.

#![doc(html_root_url = "https://docs.rs/rucc-session/0.10.4")]

mod fs;
pub mod runtime;

pub use crate::fs::{Dir, FileSystem, Found, IncludeForm, MemoryFileSystem, SearchPath, path_key};

use std::fmt;
use std::str::FromStr;

use rucc_base::Interner;
use rucc_diag::{Diagnostic, Severity, SourceMap};
use rucc_target::{TargetInfo, Triple};

/// An optimisation level.
///
/// `spec/16-performance.md` section 16.4 gives each level a throughput budget and a code
/// quality budget, and the levels exist to make that tradeoff explicit rather than to be a
/// dial. There is no `-O4`, because a level nobody can state the contract for is a level
/// nobody can test.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub enum OptLevel {
    /// `-O0`. Compile as fast as possible and keep every variable inspectable.
    #[default]
    O0,
    /// `-O1`. The cheap wins, at roughly the cost of `-O0`.
    O1,
    /// `-O2`. The full pipeline. This is the level the code quality claim is about.
    O2,
    /// `-O3`. `-O2` plus the transformations that trade size for speed.
    O3,
    /// `-Os`. Optimise for size, at roughly `-O2` compile time.
    Os,
    /// `-Oz`. Optimise for size, aggressively.
    Oz,
}

impl OptLevel {
    /// The flag that selects this level.
    pub const fn as_flag(self) -> &'static str {
        match self {
            OptLevel::O0 => "-O0",
            OptLevel::O1 => "-O1",
            OptLevel::O2 => "-O2",
            OptLevel::O3 => "-O3",
            OptLevel::Os => "-Os",
            OptLevel::Oz => "-Oz",
        }
    }

    /// Whether this level optimises for size rather than speed.
    pub const fn is_size(self) -> bool {
        matches!(self, OptLevel::Os | OptLevel::Oz)
    }

    /// Whether the middle end runs at all.
    pub const fn runs_optimizer(self) -> bool {
        !matches!(self, OptLevel::O0)
    }
}

impl fmt::Display for OptLevel {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.write_str(self.as_flag())
    }
}

impl FromStr for OptLevel {
    type Err = ();

    /// Parses the part after `-O`, so `""` is `-O` which GCC treats as `-O1`.
    fn from_str(s: &str) -> Result<Self, ()> {
        Ok(match s {
            "0" => OptLevel::O0,
            "" | "1" => OptLevel::O1,
            "2" => OptLevel::O2,
            // GCC accepts `-O4` and above and treats them as `-O3`. Build systems in the
            // wild do pass them, so matching that is cheaper than being right.
            "3" | "4" | "5" | "6" | "7" | "8" | "9" => OptLevel::O3,
            "s" => OptLevel::Os,
            "z" => OptLevel::Oz,
            _ => return Err(()),
        })
    }
}

/// How much of the memory safety monitor is on, from `-fsafety=`.
///
/// Design: `spec/safe-memory/15-integration.md` section 15.4. One flag rather than a plane at a
/// time, because the tiers of `spec/safe-memory/02-threat-model.md` are the product and the
/// modifiers are how somebody who has read that document departs from one.
///
/// The tiers agree about which accesses are checked and disagree about what happens when a check
/// says no and about how much of the boundary is covered. That is why they are one value here and
/// not three booleans: a build asks for a tier, and everything else follows from it.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub enum Safety {
    /// `-fsafety=off`. No checks and no runtime. The default, and what every existing build gets.
    #[default]
    Off,
    /// `-fsafety=detect`. Tier D: report and carry on, for a test run or a fuzzer.
    Detect,
    /// `-fsafety=enforce`. Tier E: report and stop, for a program that faces the network.
    Enforce,
    /// `-fsafety=kernel`. Tier K: what a kernel can afford, with the allocator and the libc
    /// wrappers taken out because a kernel has neither.
    Kernel,
}

impl Safety {
    /// The spelling this tier is asked for by, without the flag in front of it.
    pub const fn as_str(self) -> &'static str {
        match self {
            Safety::Off => "off",
            Safety::Detect => "detect",
            Safety::Enforce => "enforce",
            Safety::Kernel => "kernel",
        }
    }

    /// Whether checks are inserted at all.
    ///
    /// The three tiers that are not `off` all insert the same checks at this milestone. What
    /// separates them is the reporter and the boundary, which are milestones S2 and S3 in
    /// `spec/safe-memory/16-milestones.md`.
    pub const fn instruments(self) -> bool {
        !matches!(self, Safety::Off)
    }
}

impl fmt::Display for Safety {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.write_str(self.as_str())
    }
}

impl FromStr for Safety {
    type Err = ();

    /// Parses the part after `-fsafety=`.
    fn from_str(s: &str) -> Result<Self, ()> {
        Ok(match s {
            "off" => Safety::Off,
            "detect" => Safety::Detect,
            "enforce" => Safety::Enforce,
            "kernel" => Safety::Kernel,
            _ => return Err(()),
        })
    }
}

/// How far a name reaches outside a shared library when nothing in the source said.
///
/// `-fvisibility=`, which is written on every cmake project that cares about its exports and is
/// the way a library ships a small documented interface instead of every name it happens to
/// define. The attribute in the source wins wherever one was written, which is what makes the
/// flag a default rather than an override and what lets `-fvisibility=hidden` be put on a whole
/// tree and the dozen exported names marked one at a time.
///
/// Three answers to four spellings. `internal` is `hidden` plus a promise about never taking the
/// address across a component boundary, and nothing here derives anything from that promise, so
/// what it gets is the same symbol with a weaker claim on it.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub enum Visibility {
    /// `-fvisibility=default`. Exported and interposable, which is what a name gets when the flag
    /// is not written at all and what gcc does by default too.
    #[default]
    Default,
    /// `-fvisibility=hidden` and `-fvisibility=internal`. Not in the dynamic symbol table.
    Hidden,
    /// `-fvisibility=protected`. In the dynamic symbol table, and a reference from inside the
    /// library binds to the definition inside it.
    Protected,
}

impl Visibility {
    /// The spelling this is asked for by, without the flag in front of it.
    ///
    /// One spelling each, so `internal` is not here: it is a way of asking for `hidden` rather
    /// than an answer of its own.
    pub const fn as_str(self) -> &'static str {
        match self {
            Visibility::Default => "default",
            Visibility::Hidden => "hidden",
            Visibility::Protected => "protected",
        }
    }
}

impl fmt::Display for Visibility {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.write_str(self.as_str())
    }
}

impl FromStr for Visibility {
    type Err = ();

    /// Parses the part after `-fvisibility=`.
    fn from_str(s: &str) -> Result<Self, ()> {
        Ok(match s {
            "default" => Visibility::Default,
            "hidden" | "internal" => Visibility::Hidden,
            "protected" => Visibility::Protected,
            _ => return Err(()),
        })
    }
}

/// Which of the two position independent questions the output is answering.
///
/// Everything this compiler writes is position independent, so this is not about whether there are
/// absolute addresses in the text. It is about whether the link that reads the object is one that
/// puts every name in the same program. An executable is such a link and a shared library is not,
/// and the difference decides how a name is reached: from the instruction pointer where the
/// distance is a number the linker has, and out of the global offset table where it is not.
///
/// The expensive answer is the one that has to be asked for, which is gcc's arrangement and is why
/// `-fPIC` is on the compile line of every library and nowhere else. A name is only reached the
/// expensive way when it is one another object may define or replace, so `-fPIC -fvisibility=hidden`
/// costs no more than an executable does.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub enum Pic {
    /// `-fPIE`, `-fpie` and nothing at all. The link puts every name in one program, so a name this
    /// file defines is at a distance from the instruction asking, and a name it declares ends up at
    /// one too, because the linker answers a reference to a variable defined in a library by making
    /// room for it here and copying it. That is what a distribution's default build is.
    #[default]
    Executable,
    /// `-fPIC` and `-fpic`. The output may end up in a shared library, where a name the file
    /// exports is one something loaded earlier may define too, and where a name defined elsewhere
    /// is not copied in. Both are reached through the global offset table.
    Library,
}

impl Pic {
    /// The spelling this is asked for by, which is the one gcc's manual leads with.
    pub const fn as_str(self) -> &'static str {
        match self {
            Pic::Executable => "-fPIE",
            Pic::Library => "-fPIC",
        }
    }
}

impl fmt::Display for Pic {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
        f.write_str(self.as_str())
    }
}

/// What the compiler should produce.
///
/// The intermediate forms are not a debugging convenience bolted on later. Every one of them
/// is a documented textual form that round-trips, which is what makes the per-stage testing
/// in `spec/15-testing.md` section 15.2 possible.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Default)]
// Deliberately not `#[non_exhaustive]`. Adding a variant here has to break every
// match that needs to change, in this workspace and in anyone else's code. That is
// the property `spec/10-backend.md` section 10.8 is claiming when it says adding a
// target is a data change: the compiler tells you every place the data is read.
pub enum EmitKind {
    /// A linked executable. The default.
    #[default]
    Executable,
    /// An object file, `-c`.
    Object,
    /// Assembly text, `-S`.
    Asm,
    /// Preprocessed source, `-E`.
    Preprocessed,
    /// The typed AST, `--emit=tast`.
    Tast,
    /// The IR, `--emit=ir`.
    Ir,
    /// The machine IR after register allocation, `--emit=mir-final`.
    MirFinal,
    /// The safety summary, `--emit=safety-summary`.
    ///
    /// Not an intermediate form of the program the way the three above are. It is the answer to
    /// "what does this build's guarantee actually rest on", which
    /// `spec/safe-memory/07-check-elimination.md` section 7.8 asks for and
    /// `spec/safe-memory/10-boundaries.md` section 10.2 says why.
    SafetySummary,
    /// How the bytes of the translation unit's records fall into granules,
    /// `--emit=type-granules`.
    ///
    /// Not an intermediate form either. It is the measurement
    /// `spec/safe-memory/17-open-questions.md` question 6 asks for, which decides whether the
    /// type plane fits inside Tier D's memory budget, and it needs nothing past the type
    /// checker because it is a question about layouts rather than about code.
    TypeGranules,
}

impl EmitKind {
    /// The name used by `--emit=` and by `--print-config`.
    pub const fn as_str(self) -> &'static str {
        match self {
            EmitKind::Executable => "exe",
            EmitKind::Object => "obj",
            EmitKind::Asm => "asm",
            EmitKind::Preprocessed => "preprocessed",
            EmitKind::Tast => "tast",
            EmitKind::Ir => "ir",
            EmitKind::MirFinal => "mir-final",
            EmitKind::SafetySummary => "safety-summary",
            EmitKind::TypeGranules => "type-granules",
        }
    }
}

impl FromStr for EmitKind {
    type Err = ();

    fn from_str(s: &str) -> Result<Self, ()> {
        Ok(match s {
            "exe" => EmitKind::Executable,
            "obj" => EmitKind::Object,
            "asm" => EmitKind::Asm,
            "preprocessed" => EmitKind::Preprocessed,
            "tast" => EmitKind::Tast,
            "ir" => EmitKind::Ir,
            "mir-final" => EmitKind::MirFinal,
            "safety-summary" => EmitKind::SafetySummary,
            "type-granules" => EmitKind::TypeGranules,
            _ => return Err(()),
        })
    }
}

/// Which C the source is written in.
///
/// The GNU variants are the same language with `__STRICT_ANSI__` left undefined, so the
/// dialect and the extension question are two fields rather than ten variants.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash, Default)]
pub enum Std {
    /// `-std=c89`, and `-ansi`.
    C89,
    /// `-std=c99`.
    C99,
    /// `-std=c11`.
    C11,
    /// `-std=c17`, which is C11 with the defect reports applied.
    C17,
    /// `-std=c23`. The default, matching current GCC.
    #[default]
    C23,
}

impl Std {
    /// What `__STDC_VERSION__` says, which C89 does not define at all.
    pub const fn stdc_version(self) -> Option<&'static str> {
        match self {
            Std::C89 => None,
            Std::C99 => Some("199901L"),
            Std::C11 => Some("201112L"),
            Std::C17 => Some("201710L"),
            Std::C23 => Some("202311L"),
        }
    }

    /// The name in `-std=`.
    pub const fn as_str(self) -> &'static str {
        match self {
            Std::C89 => "c89",
            Std::C99 => "c99",
            Std::C11 => "c11",
            Std::C17 => "c17",
            Std::C23 => "c23",
        }
    }

    /// Whether this dialect has `_Atomic`, `_Thread_local` and the rest of C11.
    pub const fn has_c11(self) -> bool {
        matches!(self, Std::C11 | Std::C17 | Std::C23)
    }

    /// Reads a `-std=` argument, and says whether the GNU extensions came with it.
    ///
    /// Every alias GCC takes is here, including the `iso9899` spellings and the year based
    /// ones, because a build system that passes `-std=iso9899:1999` is passing what its
    /// author tested against and rejecting it helps nobody. An unknown dialect is `None`
    /// rather than a guess, since guessing means compiling a different language than the one
    /// asked for.
    #[must_use]
    pub fn from_flag(name: &str) -> Option<(Std, bool)> {
        let gnu = name.starts_with("gnu");
        let std = match name {
            "c89" | "c90" | "gnu89" | "gnu90" | "iso9899:1990" | "iso9899:199409" => Std::C89,
            "c99" | "c9x" | "gnu99" | "gnu9x" | "iso9899:1999" | "iso9899:199x" => Std::C99,
            "c11" | "c1x" | "gnu11" | "gnu1x" | "iso9899:2011" => Std::C11,
            "c17" | "c18" | "gnu17" | "gnu18" | "iso9899:2017" | "iso9899:2018" => Std::C17,
            "c23" | "c2x" | "gnu23" | "gnu2x" => Std::C23,
            _ => return None,
        };
        Some((std, gnu))
    }
}

/// The GCC release the compiler claims to be, as `__GNUC__`, `__GNUC_MINOR__` and
/// `__GNUC_PATCHLEVEL__`.
///
/// Design: `spec/04-driver-and-cli.md` section 4.5, which makes this a knob rather than a
/// constant and says to start conservative and raise it as the matrix in `rucc-gnu` fills in.
///
/// The default is seven, which is the lowest claim that gets a modern glibc. glibc gates most
/// of what it hands a caller on `__GNUC_PREREQ`, so the claim decides which half of
/// `sys/cdefs.h` we get, and below seven `bits/floatn-common.h` writes `typedef float _Float32;`
/// over a keyword this compiler already has. Every header that reaches it stops there, which
/// was most of them: on Ubuntu 24.04's glibc 2.39 the claim of 4.2.1 that stood here before got
/// 180 of 214 headers through and seven gets 202, and the amalgamated sqlite goes from four
/// errors to none.
///
/// It is still deliberately low. Claiming a version whose promises have not been kept means
/// being handed syntax the compiler cannot parse, so this moves when there is a measurement
/// saying it can. Thirteen and sixteen were measured alongside seven and came out identical on
/// glibc, on the macOS SDK and on sqlite, so the next move up is cheap; it is a separate one
/// because nothing yet needs it.
#[derive(Debug, Clone, Copy, PartialEq, Eq, PartialOrd, Ord, Hash)]
pub struct GnucVersion {
    /// `__GNUC__`.
    pub major: u32,
    /// `__GNUC_MINOR__`.
    pub minor: u32,
    /// `__GNUC_PATCHLEVEL__`.
    pub patch: u32,
}

impl Default for GnucVersion {
    fn default() -> GnucVersion {
        GnucVersion { major: 7, minor: 0, patch: 0 }
    }
}

impl FromStr for GnucVersion {
    type Err = String;

    /// Reads `-fgnuc-version=`, which is `15`, `15.1` or `15.1.0`.
    ///
    /// The short forms are not a convenience, they are what people write. A missing component
    /// is zero, the same way GCC treats a release with no patchlevel.
    fn from_str(text: &str) -> Result<GnucVersion, String> {
        let mut parts = text.split('.');
        let mut next = |what: &str| -> Result<u32, String> {
            match parts.next() {
                None => Ok(0),
                Some(field) => {
                    field.parse().map_err(|_| format!("`{text}` has a {what} that is not a number"))
                }
            }
        };
        let major = next("major")?;
        let minor = next("minor")?;
        let patch = next("patchlevel")?;
        if parts.next().is_some() {
            return Err(format!("`{text}` has more than three components"));
        }
        Ok(GnucVersion { major, minor, patch })
    }
}

/// What the `-d` family asks to be dumped alongside, or instead of, the preprocessed output.
///
/// Design: `spec/04-driver-and-cli.md` section 4.4.
///
/// GCC spells these as letters packed into one flag, so `-dDI` is two of them, and a letter it
/// does not know is ignored rather than rejected. That last part is deliberate on GCC's side
/// and worth copying: the family is a debugging aid and a build that passes `-dumpbase` should
/// not die on the `-d`.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
pub struct Dumps {
    /// `-dM`. Print the macros that are defined at the end, and nothing else.
    pub macros: bool,
}

impl Dumps {
    /// The letters GCC's preprocessor takes after `-d`.
    ///
    /// `M` is the macros, `D` is the macros in place, `N` is their names only, `I` is the
    /// `#include` lines and `U` is the macros as they are used. Only `M` does anything so far.
    const LETTERS: &'static str = "MDNIU";

    /// Whether `arg` is a flag from this family rather than something else beginning with
    /// `-d`.
    ///
    /// The check is here rather than in the driver so that the set of letters and the set of
    /// flags accepted cannot drift apart. It matters because `-dumpversion` also begins with
    /// `-d`, and a family that swallowed every such flag would turn a flag we have not written
    /// into a dump of nothing.
    #[must_use]
    pub fn is_family(arg: &str) -> bool {
        match arg.strip_prefix("-d") {
            Some("") | None => false,
            Some(letters) => letters.chars().all(|c| Dumps::LETTERS.contains(c)),
        }
    }

    /// Reads the letters after `-d`, ignoring the ones we do not implement yet.
    pub fn add(&mut self, letters: &str) {
        for letter in letters.chars() {
            if letter == 'M' {
                self.macros = true;
            }
        }
    }

    /// Whether anything at all was asked for.
    #[must_use]
    pub const fn any(self) -> bool {
        self.macros
    }
}

/// A file `-imacros` or `-include` named, read before the source file.
///
/// Design: `spec/04-driver-and-cli.md` section 4.4.
///
/// The flag a build reaches for when a whole tree has to see a definition that is not in any of
/// its files. The kernel builds every object with `-include` of its own configuration header, and
/// a configure script that has produced a `config.h` gets it into a third party source tree the
/// same way, without a patch.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Preinclude {
    /// The name as it was written, which is looked for the way a quoted include is looked for.
    pub name: String,
    /// Whether only the definitions it makes are wanted, which is what `-imacros` asks for.
    ///
    /// The text of an `-imacros` file is read and thrown away, so a header full of declarations
    /// contributes its macros and nothing else. That is what makes it usable on a file that has
    /// already been included by the source: the definitions arrive early and the declarations do
    /// not arrive twice.
    pub macros_only: bool,
}

/// What the `-M` family asks for, which is a make rule saying what a source file was built from.
///
/// Design: `spec/04-driver-and-cli.md` section 4.4.
///
/// This is a compiler flag rather than a separate tool because the answer is the set of files the
/// preprocessor opened, and nothing outside the preprocessor knows what that was. A build system
/// that generates its own makefiles asks for it on every compilation, which is why section 4.4
/// calls the family required rather than convenient.
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct Deps {
    /// Whether a rule is produced at all, which is any of `-M`, `-MM`, `-MD` and `-MMD`.
    pub emit: bool,
    /// Whether the rule is produced instead of compiling, which is `-M` and `-MM` and not the
    /// two that end in `D`.
    ///
    /// The split is GCC's and it is about who reads the answer. The two that stop after the rule
    /// write it to standard output for a person, and the two that do not write it to a file
    /// beside the object for `make` to include on the next run.
    pub instead_of_compiling: bool,
    /// Whether a header found in a system directory is listed, which `-MM` and `-MMD` turn off.
    ///
    /// A build that lists them is a build that rebuilds the world when the C library is updated,
    /// which is either what somebody wanted or the reason they reached for the other spelling.
    ///
    /// On unless a flag turned it off, and nothing turns it back on. That is GCC's behaviour and
    /// not an oversight: `-MM -M` leaves the system headers out, because the flag that asks for
    /// fewer of them is read as the answer to a question the other one never asked.
    pub system_headers: bool,
    /// Where the rule is written, from `-MF`, with `-` meaning standard output.
    ///
    /// `None` is the default, which is standard output when the rule replaces the compilation and
    /// the output file with a `.d` suffix when it does not.
    pub file: Option<String>,
    /// What the rule's targets are, from `-MT` and `-MQ`, in the order they were given.
    ///
    /// Already escaped, because that is the whole of the difference between the two flags: `-MQ`
    /// escapes what it is given and `-MT` writes it through untouched. Empty means the target is
    /// worked out from the output file, which is what a build that passes neither expects.
    pub targets: Vec<String>,
    /// Whether every prerequisite except the source gets a target of its own with no recipe,
    /// from `-MP`.
    ///
    /// This is what stops `make` failing outright when a header is deleted. Without it the old
    /// rule names a file that is gone and no rule makes it, and the build stops on a header that
    /// nothing needs any more.
    pub phony: bool,
}

impl Default for Deps {
    fn default() -> Deps {
        Deps {
            emit: false,
            instead_of_compiling: false,
            system_headers: true,
            file: None,
            targets: Vec::new(),
            phony: false,
        }
    }
}

/// Whether `-save-temps` was given and where it puts the files it keeps.
///
/// Design: `spec/04-driver-and-cli.md` section 4.10.
///
/// The flag is how a build gets at the preprocessed source of the file that failed without running
/// the compiler a second time under different flags, which is the one way to be sure the text being
/// read is the text that was compiled. A bug report against a compiler is usually a preprocessed
/// file and nothing else, and this is where that file comes from.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
pub enum SaveTemps {
    /// Not asked for, and nothing is kept.
    #[default]
    No,
    /// Beside the file the compilation produced, which is `-save-temps=obj`.
    ///
    /// This is what the bare `-save-temps` does as well. GCC's manual says the bare spelling is
    /// `-save-temps=cwd`, and gcc 16 does not do that: `-save-temps -c a.c -o out/a.o` leaves
    /// `out/a.i` and `out/a.s` rather than `a.i` and `a.s`. The measurement is what is followed
    /// here, because a build that reads the manual and a build that reads the compiler both end up
    /// looking for the files where the compiler put them.
    Object,
    /// In the working directory, which is `-save-temps=cwd`.
    Cwd,
}

impl SaveTemps {
    /// Whether anything is kept at all.
    #[must_use]
    pub const fn wanted(self) -> bool {
        !matches!(self, SaveTemps::No)
    }
}

impl FromStr for SaveTemps {
    type Err = String;

    /// Reads what came after the `=`, which is the only part that varies.
    ///
    /// # Errors
    ///
    /// Returns the offending word. GCC treats an unknown one as fatal rather than ignoring it,
    /// which is right: a misspelled keyword here means the files a person went looking for are not
    /// written and nothing said so.
    fn from_str(s: &str) -> Result<SaveTemps, String> {
        match s {
            "obj" => Ok(SaveTemps::Object),
            "cwd" => Ok(SaveTemps::Cwd),
            _ => Err(format!("`{s}` is not a -save-temps option; accepted: cwd, obj")),
        }
    }
}

/// Everything a compilation was asked to do.
///
/// Options are a plain value with no interior mutability, so a caller can build one, clone
/// it, tweak one field and run a second compilation, which is exactly what the differential
/// testing in `spec/15-testing.md` needs.
#[derive(Debug, Clone, PartialEq, Eq)]
#[non_exhaustive]
pub struct Options {
    /// The target to generate code for.
    pub target: Triple,
    /// The optimisation level.
    pub opt_level: OptLevel,
    /// How much of the memory safety monitor is on, from `-fsafety=`.
    ///
    /// Off unless it was asked for. A program built without the flag is compiled by exactly the
    /// pipeline it was compiled by before the monitor existed, which is the only way the feature
    /// can be developed in the open without every build paying for it.
    pub safety: Safety,
    /// What to produce.
    pub emit: EmitKind,
    /// Whether to emit debug information.
    pub debug_info: bool,
    /// Whether every function keeps a frame pointer, from `-fno-omit-frame-pointer`.
    ///
    /// Off by default, which is what gcc does at every level above `-O0` and what leaves the
    /// register free for the allocator. A profiler that walks the stack by following saved frame
    /// pointers needs it on, and so does any code a debugger has to unwind without unwind tables.
    pub frame_pointer: bool,
    /// Whether the red zone may be used, from `-mno-red-zone` turned around.
    ///
    /// The 128 bytes below the stack pointer that the System V psABI promises no signal handler
    /// will touch, which lets a small leaf function keep its locals without moving the stack
    /// pointer at all. A kernel turns this off, because an interrupt taken on the kernel stack
    /// makes the promise false, and every kernel build in the wild passes `-mno-red-zone` for
    /// exactly that reason. A convention without a red zone ignores this.
    pub red_zone: bool,
    /// Whether warnings are errors.
    pub warnings_are_errors: bool,
    /// Whether a warning is raised at all, which is `-w` turned around.
    ///
    /// A build that passes this has decided it does not want to hear about anything that is not
    /// fatal, and the flag is dropped at the one place every diagnostic goes through rather than
    /// tested at each site that raises one. `-w` beats `-Werror` where both are given, because a
    /// warning that was never raised cannot be promoted.
    pub warnings: bool,
    /// How many diagnostics to print before giving up. Past a certain point the output is
    /// noise from a single earlier mistake, and GCC's default of no limit is not a kindness.
    pub error_limit: u32,
    /// The dialect, from `-std=`.
    pub std: Std,
    /// Whether the GNU extensions are on, which is `-std=gnu23` rather than `-std=c23`.
    pub gnu_extensions: bool,
    /// Whether `-pedantic` was given, which is what turns a use of an extension from silence
    /// into a diagnostic. It is not the same knob as the dialect: `-std=c17 -pedantic` warns
    /// about a construct that `-std=c17` alone accepts without a word.
    pub pedantic: bool,
    /// Whether `-fpermissive` was given, which turns the rules gcc 14 promoted from errors back
    /// into warnings.
    ///
    /// Six of them, all about code written before the language settled: a declaration with no
    /// type in it, a call to a function nothing declared, a parameter in an old style definition
    /// with no type, a pointer made from an integer, a pointer assigned from a pointer to
    /// something else, and a `return` whose value disagrees with what was promised. The flag says
    /// nothing about any other diagnostic, and it does not say to compile something different: a
    /// program it accepts is compiled the way the rule it broke says it means.
    pub permissive: bool,
    /// Whether the whole unit is under GNU's reading of `inline` rather than C's, which is
    /// `-fgnu89-inline`.
    ///
    /// Under C's reading a definition every file-scope declaration wrote `inline` for and none
    /// wrote `extern` for emits nothing, and under GNU's it is the definition alone that decides
    /// and `extern inline` is the one that emits nothing. The C89 dialects are under GNU's
    /// whatever this says, since that is where the older reading came from, so this is the flag a
    /// program written against it reaches for when it is being compiled under a later dialect.
    pub gnu89_inline: bool,
    /// What a name that nothing in the source said anything about reaches, from `-fvisibility=`.
    pub visibility: Visibility,
    /// Whether the object may end up in a shared library, from `-fPIC` and `-fPIE`.
    pub pic: Pic,
    /// Whether a definition in this unit may be replaced at load time by one in another object,
    /// from `-fsemantic-interposition` and `-fno-semantic-interposition`.
    ///
    /// True is the honest answer and is gcc's default, because that is what an exported name in a
    /// shared library means: the dynamic linker takes the first definition it finds in load order,
    /// so a function this unit defines and calls may not be the one that runs. Everything the
    /// optimizer reads off a body has to stop at a name like that.
    ///
    /// False is a promise the build makes, and every distribution makes it, because otherwise a
    /// library cannot inline its own functions into each other. It is a promise rather than a
    /// deduction: nothing checks it, and a program that then interposes one of those names gets a
    /// mixture of the two definitions. It says nothing about `-fPIE`, where no name is replaceable
    /// to begin with, and it says nothing about how an address is reached, which is the separate
    /// question `-fPIC` decides.
    pub interposition: bool,
    /// The GCC release claimed, from `-fgnuc-version=`.
    pub gnuc: GnucVersion,
    /// Whether there is a standard library, which is `-ffreestanding` turned around.
    pub hosted: bool,
    /// Whether a call to a C library function written under its own plain name may be taken to
    /// mean that function, which is `-fno-builtin` turned around.
    ///
    /// The names are reserved, so `llabs` is the library's `llabs` and the compiler is allowed to
    /// know what it does. A program that means something else by one of them is the reason the
    /// flag exists, and `-ffreestanding` turns it off as well, because a freestanding program has
    /// no C library for the name to be the name of. The `__builtin_` spellings are not affected by
    /// either, since the prefix is the program saying which function it means.
    pub builtins: bool,
    /// The names `-fno-builtin-<name>` took away one at a time, without the prefix.
    ///
    /// A build that means its own `memcpy` and the library's everything else writes this rather
    /// than the whole flag, which is what the kernel does for a handful of names.
    pub no_builtin: Vec<String>,
    /// `-D` in command line order. `FOO` means `FOO=1`, as GCC has it.
    pub defines: Vec<String>,
    /// `-U` in command line order, applied after the defines because `-U` wins.
    pub undefines: Vec<String>,
    /// Where a header is looked for.
    pub search: SearchPath,
    /// What `-imacros` and `-include` named, in command line order.
    pub preincludes: Vec<Preinclude>,
    /// Whether `-E` writes line markers, which `-P` turns off.
    pub line_markers: bool,
    /// What the `-d` family asks for.
    pub dumps: Dumps,
    /// What the `-M` family asks for.
    pub deps: Deps,
    /// Whether the intermediate files are kept, from `-save-temps`.
    pub save_temps: SaveTemps,
    /// Whether each step says how long it took, from `-time`.
    pub time: bool,
    /// What `-f<pass>` and `-fno-<pass>` said about an optimizer pass, in the order the command
    /// line said it, so that the last mention of a pass is the one that decides.
    ///
    /// The pipeline the level chose is the starting point and this is what is added to and taken
    /// away from it. The names are checked against the pass list while the arguments are parsed,
    /// so anything in here is a pass the compiler has.
    pub passes: Vec<(String, bool)>,
    /// What `-fpass-fuel=<pass>=<n>` limited a pass to, by pass name.
    ///
    /// A pass with an entry here performs exactly that many transformations and then stops
    /// transforming, which is what bisects a miscompilation to one rewrite. See section 9.10 of
    /// `spec/09-optimizer.md`.
    pub pass_fuel: Vec<(String, u32)>,
    /// What `-fpass-fuel-global=<n>` limited the whole pipeline to, across every pass.
    ///
    /// The outer of the two searches in section 4.5 of `spec/optimizer/04-pass-manager.md`.
    /// Halving this says which pass holds the bad rewrite, and halving `-fpass-fuel` for that
    /// pass says which rewrite it is. Where both are given, a pass is stopped by whichever of
    /// the two is tighter.
    pub pass_fuel_global: Option<u32>,
    /// What `-fdisable-<pass>[=<range>]` and `-fenable-<pass>[=<range>]` said, in the order the
    /// command line said it, with `true` for the enabling half.
    ///
    /// A rule covers the functions it names and nothing else, and the last rule that covers a
    /// function is the one that decides for it, so the order has to survive. This is the second
    /// half of the bisection interface in section 41.6 of `spec/optimizer/41-correctness.md`:
    /// `-fpass-fuel` finds the rewrite and this finds the function. The pass names are checked
    /// against the pass list while the arguments are parsed.
    pub pass_gates: Vec<(bool, String)>,
    /// What `-fdump-ir=` asked to see, as it was written, which is `all`, `before-<pass>` or
    /// `after-<pass>`.
    pub dump_ir: Vec<String>,
    /// What `-fopt-info` asked to hear about, as the keywords were written, with the leading
    /// hyphen taken off, so a bare `-fopt-info` is the empty string in here.
    ///
    /// The keywords are `optimized`, `missed`, `note` and `all`, and two flags add up rather than
    /// the second replacing the first. Checked while the arguments are parsed, so anything in
    /// here is a spelling the optimizer understands. See section 42.2 of
    /// `spec/optimizer/42-measurement.md` for why `missed` is the one that earns the feature.
    pub opt_info: Vec<String>,
    /// Where `-fopt-info=<file>` sends the remarks, or `None` for standard error.
    ///
    /// One file for the whole run rather than one per input, the way GCC does it, and the last
    /// one on the command line is the one that decides. A harness that wants the remarks kept
    /// away from the diagnostics gives a file, which is what the corpus in `tamnd/rucc-corpus`
    /// does with GCC so that a rejection can still be matched against the diagnostic stream.
    pub opt_info_file: Option<String>,
    /// Whether the IR verifier runs after every pass that changed anything.
    ///
    /// On in a debug build without being asked, since that is where a broken pass should be
    /// caught. `-Zverify-each` turns it on in a release build, which is what CI wants.
    pub verify_each: bool,
    /// Where `-Zrule-coverage=FILE` writes which lowering rules fired, if it was given.
    ///
    /// A measurement rather than a thing a build asks for, which is why it is spelled with a `-Z`
    /// the way an unstable option is everywhere else: it is here for the harness in
    /// `tamnd/rucc-compat` to union over a corpus and report, and nothing about the code that comes
    /// out changes when it is on. One file per run of the compiler, holding the whole rule set with
    /// the rules this run reached marked, whatever the run compiled and however many files it was.
    pub rule_coverage: Option<String>,
}

impl Options {
    /// Default options for `target`.
    pub fn new(target: Triple) -> Self {
        Self {
            target,
            opt_level: OptLevel::default(),
            safety: Safety::default(),
            emit: EmitKind::default(),
            debug_info: false,
            frame_pointer: false,
            red_zone: true,
            warnings_are_errors: false,
            warnings: true,
            error_limit: 20,
            std: Std::default(),
            gnu_extensions: true,
            pedantic: false,
            permissive: false,
            gnu89_inline: false,
            visibility: Visibility::default(),
            pic: Pic::default(),
            interposition: true,
            gnuc: GnucVersion::default(),
            hosted: true,
            builtins: true,
            no_builtin: Vec::new(),
            defines: Vec::new(),
            undefines: Vec::new(),
            search: SearchPath::new(),
            preincludes: Vec::new(),
            line_markers: true,
            dumps: Dumps::default(),
            deps: Deps::default(),
            save_temps: SaveTemps::default(),
            time: false,
            passes: Vec::new(),
            pass_fuel: Vec::new(),
            pass_fuel_global: None,
            pass_gates: Vec::new(),
            dump_ir: Vec::new(),
            opt_info: Vec::new(),
            opt_info_file: None,
            verify_each: cfg!(debug_assertions),
            rule_coverage: None,
        }
    }
}

/// One compilation.
///
/// Holds the options, the string interner and the diagnostics raised so far. Passing a
/// `&mut Session` is how a stage reports a problem, and the return value of a stage says
/// what it produced, never whether it succeeded: that question is answered by
/// [`Session::has_errors`].
#[derive(Debug)]
pub struct Session {
    /// What this compilation was asked to do.
    pub opts: Options,
    /// Everything known about the target.
    pub target: TargetInfo,
    /// The one interner for the compilation.
    pub interner: Interner,
    /// Every file read during the compilation, and the flat coordinate space their spans
    /// live in.
    ///
    /// This is on the session rather than passed around separately because a span is only
    /// meaningful against the map that issued it, and one map per compilation is the rule
    /// that makes that true by construction.
    pub sources: SourceMap,
    diagnostics: Vec<Diagnostic>,
    error_count: u32,
    warning_count: u32,
}

impl Session {
    /// A session for `opts`.
    pub fn new(opts: Options) -> Self {
        let target = TargetInfo::new(opts.target);
        Self {
            opts,
            target,
            interner: Interner::with_capacity(1024),
            sources: SourceMap::new(),
            diagnostics: Vec::new(),
            error_count: 0,
            warning_count: 0,
        }
    }

    /// Records a diagnostic.
    ///
    /// Under `-Werror` a warning is promoted here, once, rather than at every site that
    /// raises one, and under `-w` it is dropped here for the same reason. A warning that `-w`
    /// dropped is not counted, so `-w -Werror` compiles rather than failing on a warning
    /// nobody was going to see.
    pub fn emit(&mut self, mut diag: Diagnostic) {
        if !self.opts.warnings && diag.severity == Severity::Warning {
            return;
        }
        if self.opts.warnings_are_errors && diag.severity == Severity::Warning {
            diag.severity = Severity::Error;
        }
        match diag.severity {
            Severity::Error | Severity::Ice => self.error_count += 1,
            Severity::Warning => self.warning_count += 1,
            Severity::Note | Severity::Help => {}
        }
        self.diagnostics.push(diag);
    }

    /// Everything raised so far, in the order it was raised.
    pub fn diagnostics(&self) -> &[Diagnostic] {
        &self.diagnostics
    }

    /// Whether anything fatal has been raised.
    pub fn has_errors(&self) -> bool {
        self.error_count > 0
    }

    /// How many errors have been raised.
    pub fn error_count(&self) -> u32 {
        self.error_count
    }

    /// How many warnings have been raised.
    pub fn warning_count(&self) -> u32 {
        self.warning_count
    }

    /// Whether the error limit has been reached and the caller should stop.
    pub fn error_limit_reached(&self) -> bool {
        self.opts.error_limit != 0 && self.error_count >= self.opts.error_limit
    }
}

#[cfg(test)]
mod tests {
    use super::*;

    fn session() -> Session {
        Session::new(Options::new("x86_64-unknown-linux-gnu".parse().unwrap()))
    }

    #[test]
    fn a_version_claim_reads_the_way_gcc_prints_one() {
        // `gcc -dumpfullversion` gives all three, `gcc -dumpversion` gives one, and both are
        // things a script pastes straight into a flag.
        let all = |v: &str| v.parse::<GnucVersion>().unwrap();
        assert_eq!(all("15.1.0"), GnucVersion { major: 15, minor: 1, patch: 0 });
        assert_eq!(all("15"), GnucVersion { major: 15, minor: 0, patch: 0 });
        assert_eq!(all("4.2"), GnucVersion { major: 4, minor: 2, patch: 0 });
        assert!("".parse::<GnucVersion>().is_err());
        assert!("15.".parse::<GnucVersion>().is_err(), "a trailing dot is a typo, not a zero");
        assert!("1.2.3.4".parse::<GnucVersion>().is_err());
    }

    #[test]
    fn optimisation_levels_parse_the_way_gcc_spells_them() {
        assert_eq!("".parse::<OptLevel>().unwrap(), OptLevel::O1);
        assert_eq!("0".parse::<OptLevel>().unwrap(), OptLevel::O0);
        assert_eq!("2".parse::<OptLevel>().unwrap(), OptLevel::O2);
        assert_eq!("9".parse::<OptLevel>().unwrap(), OptLevel::O3);
        assert_eq!("s".parse::<OptLevel>().unwrap(), OptLevel::Os);
        assert!("q".parse::<OptLevel>().is_err());
    }

    #[test]
    fn only_o0_skips_the_optimizer() {
        assert!(!OptLevel::O0.runs_optimizer());
        assert!(OptLevel::O1.runs_optimizer());
        assert!(OptLevel::Oz.runs_optimizer());
    }

    #[test]
    fn the_safety_tiers_round_trip_and_nothing_else_is_one() {
        for tier in [Safety::Off, Safety::Detect, Safety::Enforce, Safety::Kernel] {
            assert_eq!(tier.as_str().parse::<Safety>().unwrap(), tier);
        }
        // `on` is the obvious thing to try and it is not a tier, because which tier somebody
        // means by it is the whole question document 02 answers.
        assert!("on".parse::<Safety>().is_err());
        assert!("".parse::<Safety>().is_err());
    }

    #[test]
    fn the_two_places_the_intermediate_files_can_go_are_the_two_words_that_are_taken() {
        assert_eq!("obj".parse::<SaveTemps>().unwrap(), SaveTemps::Object);
        assert_eq!("cwd".parse::<SaveTemps>().unwrap(), SaveTemps::Cwd);
        // The names of the two flags that mean the same thing as `=obj` are not themselves
        // arguments of it, and neither is silence.
        assert!("obj,cwd".parse::<SaveTemps>().is_err());
        assert!("".parse::<SaveTemps>().is_err());
        // Nothing is kept unless something asked, and both of the words that ask do ask.
        assert_eq!(SaveTemps::default(), SaveTemps::No);
        assert!(!SaveTemps::No.wanted());
        assert!(SaveTemps::Object.wanted());
        assert!(SaveTemps::Cwd.wanted());
    }

    #[test]
    fn a_build_that_did_not_ask_for_the_monitor_does_not_get_it() {
        assert_eq!(Safety::default(), Safety::Off);
        assert!(!Safety::Off.instruments());
        assert!(Safety::Detect.instruments());
        assert!(Safety::Enforce.instruments());
        assert!(Safety::Kernel.instruments());
    }

    #[test]
    fn emit_kinds_round_trip_through_their_names() {
        for k in [
            EmitKind::Executable,
            EmitKind::Object,
            EmitKind::Asm,
            EmitKind::Preprocessed,
            EmitKind::Tast,
            EmitKind::Ir,
            EmitKind::MirFinal,
        ] {
            assert_eq!(k.as_str().parse::<EmitKind>().unwrap(), k);
        }
    }

    #[test]
    fn errors_are_counted_and_warnings_are_not() {
        let mut s = session();
        s.emit(Diagnostic::error("no", rucc_diag::Span::DUMMY));
        s.emit(Diagnostic::warning("hmm", rucc_diag::Span::DUMMY));
        assert_eq!(s.error_count(), 1);
        assert_eq!(s.warning_count(), 1);
        assert!(s.has_errors());
        assert_eq!(s.diagnostics().len(), 2);
    }

    #[test]
    fn werror_promotes_once_at_the_sink() {
        let mut opts = Options::new("x86_64-unknown-linux-gnu".parse().unwrap());
        opts.warnings_are_errors = true;
        let mut s = Session::new(opts);
        s.emit(Diagnostic::warning("hmm", rucc_diag::Span::DUMMY));
        assert_eq!(s.error_count(), 1);
        assert_eq!(s.warning_count(), 0);
        assert_eq!(s.diagnostics()[0].severity, Severity::Error);
    }

    #[test]
    fn the_error_limit_can_be_switched_off() {
        let mut opts = Options::new("x86_64-unknown-linux-gnu".parse().unwrap());
        opts.error_limit = 0;
        let mut s = Session::new(opts);
        for _ in 0..100 {
            s.emit(Diagnostic::error("no", rucc_diag::Span::DUMMY));
        }
        assert!(!s.error_limit_reached());
    }

    #[test]
    fn the_session_carries_the_source_map_spans_are_resolved_against() {
        let mut s = session();
        let file = s.sources.add("a.c", b"int x;\n".to_vec()).unwrap();
        let start = s.sources.file(file).start;
        assert_eq!(s.sources.render_position(start + 4), "a.c:1:5");
    }

    #[test]
    fn the_session_carries_the_resolved_target() {
        let s = session();
        assert_eq!(s.target.pointer_width, 64);
        assert!(s.target.char_is_signed);
    }
}