//! Workspace loader: loads an entry module and recursively follows its
//! `imports`.
//!
//! Convention: an `import { module: "foo" }` is resolved relative to
//! the entry file's directory as `<root_dir>/foo.ail.json`. Module
//! names must match the file stem (the loader rejects mismatches).
//!
//! The single entry point is [`load_workspace`]; it returns a fully
//! populated [`Workspace`] or a structured [`WorkspaceLoadError`].
//! [`module_hash`] is the module-granularity counterpart to
//! [`crate::def_hash`] and is used both internally (to detect a module
//! re-loaded from disk with different content) and by the CLI.
//!
//! This module is responsible only for **finding** and consistently
//! **loading** all reachable modules. Cross-module typechecking lives
//! in `ailang-check`; codegen in `ailang-codegen`. Neither is run from
//! here.
//!
//! # Examples
//!
//! ```ignore
//! use ailang_core::load_workspace;
//! use std::path::Path;
//!
//! let ws = load_workspace(Path::new("examples/ws_main.ail.json"))?;
//! assert_eq!(ws.entry, "ws_main");
//! // All transitively imported modules are now in `ws.modules`.
//! for (name, m) in &ws.modules {
//!     println!("{name}: {} defs", m.defs.len());
//! }
//! # Ok::<(), ailang_core::workspace::WorkspaceLoadError>(())
//! ```

use crate::ast::Module;
use crate::canonical;
use crate::{load_module, Error as CoreError};
use std::collections::{BTreeMap, HashSet};
use std::path::{Path, PathBuf};

/// Fully loaded workspace.
///
/// `entry` names the entry module (module name, **not** a path). All
/// transitively reachable modules are contained in `modules` and indexed
/// by `Module.name`. `root_dir` is the directory the entry file lives
/// in; all imports are resolved relative to it.
#[derive(Debug, Clone)]
pub struct Workspace {
    /// Name of the entry module (the one passed to [`load_workspace`]).
    pub entry: String,
    /// Every module reachable from `entry`, indexed by module name.
    /// `BTreeMap` is used so iteration order is deterministic, which
    /// matters for downstream codegen and reporting.
    pub modules: BTreeMap<String, Module>,
    /// Directory the entry file lives in; all imports are resolved
    /// relative to it.
    pub root_dir: PathBuf,
}

/// Structured errors of the workspace loader.
///
/// `Cycle.path` is the chain of module names in which the cycle was
/// closed — the last element is the name already present in `visiting`.
#[derive(Debug, thiserror::Error)]
pub enum WorkspaceLoadError {
    /// File I/O failed while reading a module file (typically: file
    /// missing, permission denied).
    #[error("io error for {path}: {source}")]
    Io {
        path: PathBuf,
        #[source]
        source: std::io::Error,
    },

    /// File contents failed to parse as a [`Module`] or had the wrong
    /// schema tag. Wraps a [`CoreError`] (the single-module loader's
    /// error type).
    #[error("schema/parse error in {path}: {source}")]
    Schema {
        path: PathBuf,
        #[source]
        source: CoreError,
    },

    /// An `import { module: "foo" }` did not resolve to an existing
    /// file at the expected path.
    #[error("module `{name}` not found (expected at {expected_path})")]
    ModuleNotFound { name: String, expected_path: PathBuf },

    /// The `name` field in a loaded module file disagrees with the
    /// file-stem-derived name the loader expected (i.e. the
    /// `<name>.ail.json` convention is broken).
    #[error(
        "module name in file ({name_in_file:?}) does not match expected name from path ({name_from_path:?})"
    )]
    ModuleNameMismatch {
        name_in_file: String,
        name_from_path: String,
    },

    /// An import cycle was detected. `path` is the chain of module
    /// names in which the cycle was closed — the last element is the
    /// name that was already on the visit stack.
    #[error("import cycle detected: {}", path.join(" -> "))]
    Cycle { path: Vec<String> },

    /// A module was reachable through two import paths, and its
    /// on-disk content (compared via [`module_hash`]) differs between
    /// the two reads. This typically means the file changed mid-load.
    #[error(
        "module `{name}` was loaded twice with differing content (hashes differ)"
    )]
    ModuleHashMismatch { name: String },
}

/// Hash over the canonical bytes of a complete module.
///
/// Parallel to `def_hash`, but at module level. The workspace loader
/// uses this to verify double-loads; the CLI uses it to emit a stable
/// per-module identifier.
pub fn module_hash(m: &Module) -> String {
    let bytes = canonical::to_bytes(m);
    let h = blake3::hash(&bytes);
    h.to_hex().as_str()[..16].to_string()
}

/// Load entry module plus all transitively reachable modules.
///
/// Algorithm: DFS over `imports`, with two sets:
/// - `loaded` (= `modules` map): modules whose subtree is already fully
///   processed. On a re-hit only hash consistency is checked.
/// - `visiting`: stack of modules whose DFS descent is still running.
///   A hit here = cycle.
pub fn load_workspace(entry_path: &Path) -> Result<Workspace, WorkspaceLoadError> {
    let entry_path = entry_path.to_path_buf();
    let root_dir = entry_path
        .parent()
        .map(Path::to_path_buf)
        .unwrap_or_else(|| PathBuf::from("."));

    // Load entry module + check name<->filename convention.
    let entry_module = load_one(&entry_path)?;
    let expected_entry_name = module_name_from_path(&entry_path);
    if entry_module.name != expected_entry_name {
        return Err(WorkspaceLoadError::ModuleNameMismatch {
            name_in_file: entry_module.name.clone(),
            name_from_path: expected_entry_name,
        });
    }

    let entry_name = entry_module.name.clone();

    let mut modules: BTreeMap<String, Module> = BTreeMap::new();
    let mut visiting: Vec<String> = Vec::new();
    let mut visiting_set: HashSet<String> = HashSet::new();

    visit(
        entry_module,
        &root_dir,
        &mut modules,
        &mut visiting,
        &mut visiting_set,
    )?;

    Ok(Workspace {
        entry: entry_name,
        modules,
        root_dir,
    })
}

fn visit(
    module: Module,
    root_dir: &Path,
    modules: &mut BTreeMap<String, Module>,
    visiting: &mut Vec<String>,
    visiting_set: &mut HashSet<String>,
) -> Result<(), WorkspaceLoadError> {
    let name = module.name.clone();

    // Already fully loaded? Then do nothing. Hash consistency is checked
    // on re-encounter via imports (see below in the loop).
    if modules.contains_key(&name) {
        return Ok(());
    }

    // Cycle: same name currently on the DFS stack.
    if visiting_set.contains(&name) {
        let mut path = visiting.clone();
        path.push(name);
        return Err(WorkspaceLoadError::Cycle { path });
    }

    visiting.push(name.clone());
    visiting_set.insert(name.clone());

    // Process imports recursively.
    let imports = module.imports.clone();
    for imp in &imports {
        let imp_path = root_dir.join(format!("{}.ail.json", imp.module));

        if let Some(existing) = modules.get(&imp.module) {
            // Already fully loaded — check hash consistency, in case the
            // file on disk has changed.
            let on_disk = match load_one(&imp_path) {
                Ok(m) => m,
                Err(WorkspaceLoadError::Io { .. }) => continue,
                Err(e) => return Err(e),
            };
            if module_hash(existing) != module_hash(&on_disk) {
                return Err(WorkspaceLoadError::ModuleHashMismatch {
                    name: imp.module.clone(),
                });
            }
            continue;
        }

        if visiting_set.contains(&imp.module) {
            let mut path = visiting.clone();
            path.push(imp.module.clone());
            return Err(WorkspaceLoadError::Cycle { path });
        }

        if !imp_path.exists() {
            return Err(WorkspaceLoadError::ModuleNotFound {
                name: imp.module.clone(),
                expected_path: imp_path,
            });
        }

        let imported = load_one(&imp_path)?;
        if imported.name != imp.module {
            return Err(WorkspaceLoadError::ModuleNameMismatch {
                name_in_file: imported.name,
                name_from_path: imp.module.clone(),
            });
        }
        visit(imported, root_dir, modules, visiting, visiting_set)?;
    }

    visiting.pop();
    visiting_set.remove(&name);
    modules.insert(name, module);

    Ok(())
}

fn load_one(path: &Path) -> Result<Module, WorkspaceLoadError> {
    match load_module(path) {
        Ok(m) => Ok(m),
        Err(CoreError::Io(e)) => Err(WorkspaceLoadError::Io {
            path: path.to_path_buf(),
            source: e,
        }),
        Err(e) => Err(WorkspaceLoadError::Schema {
            path: path.to_path_buf(),
            source: e,
        }),
    }
}

fn module_name_from_path(p: &Path) -> String {
    let file = p.file_name().and_then(|s| s.to_str()).unwrap_or("");
    // Convention: `<name>.ail.json`.
    if let Some(stripped) = file.strip_suffix(".ail.json") {
        return stripped.to_string();
    }
    // Fallback: strip only the last extension.
    Path::new(file)
        .file_stem()
        .and_then(|s| s.to_str())
        .unwrap_or(file)
        .to_string()
}

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

    fn write_module(dir: &Path, name: &str, imports: &[&str]) -> PathBuf {
        let imports_json: Vec<serde_json::Value> = imports
            .iter()
            .map(|m| serde_json::json!({ "module": m }))
            .collect();
        let module = serde_json::json!({
            "schema": crate::SCHEMA,
            "name": name,
            "imports": imports_json,
            "defs": [],
        });
        let path = dir.join(format!("{name}.ail.json"));
        fs::write(&path, serde_json::to_vec_pretty(&module).unwrap()).unwrap();
        path
    }

    fn tmp_dir(tag: &str) -> PathBuf {
        let d = std::env::temp_dir().join(format!(
            "ailang_workspace_test_{tag}_{}",
            std::process::id()
        ));
        let _ = fs::remove_dir_all(&d);
        fs::create_dir_all(&d).unwrap();
        d
    }

    #[test]
    fn loads_example_workspace_happy_path() {
        // Uses the canonical example files under `examples/`. This
        // test documents that the loader relies on the committed
        // workspace example.
        let manifest_dir = env!("CARGO_MANIFEST_DIR");
        let workspace_root =
            Path::new(manifest_dir).parent().unwrap().parent().unwrap();
        let entry = workspace_root.join("examples").join("ws_main.ail.json");

        let ws = load_workspace(&entry).expect("load workspace");
        assert_eq!(ws.entry, "ws_main");
        assert!(ws.modules.contains_key("ws_main"));
        assert!(ws.modules.contains_key("ws_lib"));
        assert_eq!(ws.modules.len(), 2);
    }

    #[test]
    fn detects_import_cycle() {
        let dir = tmp_dir("cycle");
        write_module(&dir, "a", &["b"]);
        write_module(&dir, "b", &["a"]);
        let entry = dir.join("a.ail.json");

        let err = load_workspace(&entry).expect_err("must error on cycle");
        match err {
            WorkspaceLoadError::Cycle { path } => {
                assert!(path.contains(&"a".to_string()));
                assert!(path.contains(&"b".to_string()));
            }
            other => panic!("expected Cycle, got {other:?}"),
        }
    }

    #[test]
    fn module_not_found_yields_structured_error() {
        let dir = tmp_dir("notfound");
        write_module(&dir, "main", &["does_not_exist"]);
        let entry = dir.join("main.ail.json");

        let err = load_workspace(&entry).expect_err("must error on missing module");
        match err {
            WorkspaceLoadError::ModuleNotFound { name, expected_path } => {
                assert_eq!(name, "does_not_exist");
                assert!(expected_path.ends_with("does_not_exist.ail.json"));
            }
            other => panic!("expected ModuleNotFound, got {other:?}"),
        }
    }
}