Port upstream 0.66.0: MiniMax browser storage discovery (stacked on #646)

rust/src/browser/mod.rs

@@ -4,6 +4,7 @@ pub mod cookie_cache;
 pub mod cookies;
 pub mod detection;
 pub mod leveldb;
+pub mod storage_discovery;
 pub mod watchdog;
 pub mod wsl_paths;
 

rust/src/browser/storage_discovery.rs

@@ -0,0 +1,139 @@
+//! Locates raw Chromium profile stores (Local Storage, Session Storage, IndexedDB) across the
+//! installed Chromium-family browsers.
+//!
+//! Each consumer supplies its own decoder; this module only answers "which directories could hold
+//! the data". It never opens, locks, or decrypts anything, so it is safe to run while the browser
+//! is open and needs no credential-store access.
+//!
+//! The browser catalog is [`super::detection::BrowserType`] (via [`BrowserDetector`]); a
+//! Chromium-family browser that is not in that catalog is not visited.
+
+use std::path::{Path, PathBuf};
+
+use super::detection::BrowserDetector;
+use super::leveldb::local_storage::local_storage_dir;
+
+const INDEXED_DB_DIR: &str = "IndexedDB";
+const SESSION_STORAGE_DIR: &str = "Session Storage";
+const INDEXED_DB_SUFFIX: &str = ".indexeddb.leveldb";
+
+/// Which per-profile store to locate.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+pub enum StorageKind {
+    /// `<profile>/Local Storage/leveldb`
+    LocalStorage,
+    /// `<profile>/Session Storage`
+    SessionStorage,
+    /// `<profile>/IndexedDB/<origin>.indexeddb.leveldb` for every database whose directory name
+    /// starts with one of `origin_prefixes` (for example `https_platform.minimax.io_`).
+    IndexedDb {
+        origin_prefixes: &'static [&'static str],
+    },
+}
+
+impl StorageKind {
+    fn label_suffix(self) -> &'static str {
+        match self {
+            Self::LocalStorage => "",
+            Self::SessionStorage => " (Session Storage)",
+            Self::IndexedDb { .. } => " (IndexedDB)",
+        }
+    }
+}
+
+/// One directory that may hold data of the requested [`StorageKind`].
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct StorageCandidate {
+    /// Human-readable source, such as `Google Chrome Default (Session Storage)`.
+    pub label: String,
+    pub path: PathBuf,
+}
+
+/// Candidates for `kind` in every installed Chromium-family browser, in catalog order.
+pub fn discover(kind: StorageKind) -> Vec<StorageCandidate> {
+    BrowserDetector::detect_all()
+        .iter()
+        .filter(|browser| browser.browser_type.is_chromium_based())
+        .flat_map(|browser| {
+            candidates_in_user_data_dir(
+                &browser.user_data_dir,
+                browser.browser_type.display_name(),
+                kind,
+            )
+        })
+        .collect()
+}
+
+/// Candidates for `kind` in one browser `User Data` directory, profiles sorted by name.
+///
+/// Only `Default`, `Profile *`, and `user-*` directories count as profiles; guest and system
+/// profiles are ignored.
+pub fn candidates_in_user_data_dir(
+    user_data_dir: &Path,
+    label_prefix: &str,
+    kind: StorageKind,
+) -> Vec<StorageCandidate> {
+    sorted_child_dirs(user_data_dir, is_profile_dir_name)
+        .into_iter()
+        .flat_map(|(name, profile_dir)| {
+            let label = format!("{label_prefix} {name}{}", kind.label_suffix());
+            profile_store_paths(&profile_dir, kind)
+                .into_iter()
+                .map(move |path| StorageCandidate {
+                    label: label.clone(),
+                    path,
+                })
+        })
+        .collect()
+}
+
+fn profile_store_paths(profile_dir: &Path, kind: StorageKind) -> Vec<PathBuf> {
+    match kind {
+        StorageKind::LocalStorage => existing(local_storage_dir(profile_dir)),
+        StorageKind::SessionStorage => existing(profile_dir.join(SESSION_STORAGE_DIR)),
+        StorageKind::IndexedDb { origin_prefixes } => {
+            sorted_child_dirs(&profile_dir.join(INDEXED_DB_DIR), |name| {
+                name.ends_with(INDEXED_DB_SUFFIX)
+                    && origin_prefixes
+                        .iter()
+                        .any(|prefix| name.starts_with(prefix))
+            })
+            .into_iter()
+            .map(|(_, path)| path)
+            .collect()
+        }
+    }
+}
+
+fn existing(path: PathBuf) -> Vec<PathBuf> {
+    if path.exists() {
+        vec![path]
+    } else {
+        Vec::new()
+    }
+}
+
+fn is_profile_dir_name(name: &str) -> bool {
+    name == "Default" || name.starts_with("Profile ") || name.starts_with("user-")
+}
+
+/// Child directories of `dir` whose (non-hidden, valid UTF-8) name passes `keep`, sorted by name.
+/// A missing or unreadable `dir` yields nothing.
+fn sorted_child_dirs(dir: &Path, keep: impl Fn(&str) -> bool) -> Vec<(String, PathBuf)> {
+    let Ok(entries) = std::fs::read_dir(dir) else {
+        return Vec::new();
+    };
+    let mut children: Vec<(String, PathBuf)> = entries
+        .flatten()
+        .filter_map(|entry| {
+            let name = entry.file_name().into_string().ok()?;
+            let is_dir = entry.file_type().is_ok_and(|kind| kind.is_dir());
+            (is_dir && !name.starts_with('.') && keep(&name)).then(|| (name, entry.path()))
+        })
+        .collect();
+    children.sort_by(|left, right| left.0.cmp(&right.0));
+    children
+}
+
+#[cfg(test)]
+mod tests;

rust/src/browser/storage_discovery/tests.rs

@@ -0,0 +1,158 @@
+use super::*;
+use std::fs;
+
+const PREFIXES: &[&str] = &[
+    "https_platform.minimax.io_",
+    "https_www.minimax.io_",
+    "https_minimax.io_",
+    "https_platform.minimaxi.com_",
+    "https_minimaxi.com_",
+    "https_www.minimaxi.com_",
+];
+
+fn indexed_db() -> StorageKind {
+    StorageKind::IndexedDb {
+        origin_prefixes: PREFIXES,
+    }
+}
+
+fn mkdir(root: &Path, relative: &str) {
+    fs::create_dir_all(root.join(relative)).unwrap();
+}
+
+fn paths(root: &Path, candidates: &[StorageCandidate]) -> Vec<String> {
+    candidates
+        .iter()
+        .map(|candidate| {
+            candidate
+                .path
+                .strip_prefix(root)
+                .unwrap()
+                .to_string_lossy()
+                .replace('\\', "/")
+        })
+        .collect()
+}
+
+#[test]
+fn each_storage_kind_resolves_to_its_profile_directory() {
+    let root = tempfile::tempdir().unwrap();
+    let database = "IndexedDB/https_platform.minimax.io_0.indexeddb.leveldb";
+    for path in ["Local Storage/leveldb", "Session Storage", database] {
+        mkdir(root.path(), &format!("Default/{path}"));
+    }
+
+    let cases = [
+        (
+            StorageKind::LocalStorage,
+            "Default/Local Storage/leveldb",
+            "",
+        ),
+        (
+            StorageKind::SessionStorage,
+            "Default/Session Storage",
+            " (Session Storage)",
+        ),
+        (indexed_db(), &format!("Default/{database}"), " (IndexedDB)"),
+    ];
+    for (kind, expected_path, suffix) in cases {
+        let found = candidates_in_user_data_dir(root.path(), "Google Chrome", kind);
+        assert_eq!(paths(root.path(), &found), [expected_path]);
+        assert_eq!(found[0].label, format!("Google Chrome Default{suffix}"));
+    }
+}
+
+#[test]
+fn missing_stores_and_missing_user_data_dir_yield_nothing() {
+    let root = tempfile::tempdir().unwrap();
+    mkdir(root.path(), "Default");
+    for kind in [
+        StorageKind::LocalStorage,
+        StorageKind::SessionStorage,
+        indexed_db(),
+    ] {
+        assert!(candidates_in_user_data_dir(root.path(), "Chrome", kind).is_empty());
+        assert!(
+            candidates_in_user_data_dir(&root.path().join("absent"), "Chrome", kind).is_empty()
+        );
+    }
+}
+
+#[test]
+fn only_default_profile_and_user_profiles_are_visited_in_name_order() {
+    let root = tempfile::tempdir().unwrap();
+    for profile in [
+        "user-work",
+        "Profile 2",
+        "Default",
+        "Guest Profile",
+        "System Profile",
+        ".hidden",
+        "Profile1",
+    ] {
+        mkdir(root.path(), &format!("{profile}/Local Storage/leveldb"));
+    }
+    // A file named like a profile is not a profile.
+    fs::write(root.path().join("Profile 9"), b"x").unwrap();
+
+    let found = candidates_in_user_data_dir(root.path(), "Edge", StorageKind::LocalStorage);
+    assert_eq!(
+        found
+            .iter()
+            .map(|candidate| candidate.label.as_str())
+            .collect::<Vec<_>>(),
+        ["Edge Default", "Edge Profile 2", "Edge user-work"]
+    );
+}
+
+#[test]
+fn indexed_db_keeps_only_allowed_origin_databases_that_are_directories() {
+    let root = tempfile::tempdir().unwrap();
+    let allowed = [
+        "https_platform.minimax.io_0",
+        "https_www.minimax.io_0",
+        "https_minimax.io_0",
+        "https_platform.minimaxi.com_0",
+        "https_www.minimaxi.com_0",
+        "https_minimaxi.com_0",
+    ]
+    .map(|origin| format!("{origin}.indexeddb.leveldb"));
+    let excluded = [
+        "https_other.example_0.indexeddb.leveldb",
+        "https_minimax.io.evil_0.indexeddb.leveldb",
+        "https_minimax.io_0.indexeddb.blob",
+        ".https_minimax.io_0.indexeddb.leveldb",
+    ];
+    for profile in ["Default", "Profile 2", "user-work", "Guest Profile"] {
+        for database in allowed.iter().map(String::as_str).chain(excluded) {
+            mkdir(root.path(), &format!("{profile}/IndexedDB/{database}"));
+        }
+    }
+    fs::write(
+        root.path()
+            .join("Default/IndexedDB/https_minimax.io_1.indexeddb.leveldb"),
+        b"x",
+    )
+    .unwrap();
+
+    let found = candidates_in_user_data_dir(root.path(), "Fixture", indexed_db());
+
+    assert_eq!(found.len(), 3 * allowed.len());
+    let mut expected_names: Vec<&str> = allowed.iter().map(String::as_str).collect();
+    expected_names.sort_unstable();
+    for (profile, group) in ["Default", "Profile 2", "user-work"]
+        .iter()
+        .zip(found.chunks(allowed.len()))
+    {
+        let names: Vec<_> = group
+            .iter()
+            .map(|candidate| candidate.path.file_name().unwrap().to_str().unwrap())
+            .collect();
+        assert_eq!(names, expected_names);
+        assert!(
+            group
+                .iter()
+                .all(|candidate| candidate.label == format!("Fixture {profile} (IndexedDB)"))
+        );
+    }
+}