Support globs as cache keys

Author: charliermarsh

Cargo.lock

@@ -14,6 +14,7 @@ workspace = true
 
 [dependencies]
 fs-err = { workspace = true }
+glob = { workspace = true }
 schemars = { workspace = true, optional = true }
 serde = { workspace = true, features = ["derive"] }
 thiserror = { workspace = true }

crates/uv-cache-info/Cargo.toml

@@ -1,11 +1,12 @@
 use crate::commit_info::CacheCommit;
 use crate::timestamp::Timestamp;
 
+use glob::MatchOptions;
 use serde::Deserialize;
 use std::cmp::max;
 use std::io;
 use std::path::{Path, PathBuf};
-use tracing::debug;
+use tracing::{debug, warn};
 
 /// The information used to determine whether a built distribution is up-to-date, based on the
 /// timestamps of relevant files, the current commit of a repository, etc.
@@ -64,24 +65,81 @@ impl CacheInfo {
         // If no cache keys were defined, use the defaults.
         let cache_keys = cache_keys.unwrap_or_else(|| {
             vec![
-                CacheKey::Path(directory.join("pyproject.toml")),
-                CacheKey::Path(directory.join("setup.py")),
-                CacheKey::Path(directory.join("setup.cfg")),
+                CacheKey::Path("pyproject.toml".to_string()),
+                CacheKey::Path("setup.py".to_string()),
+                CacheKey::Path("setup.cfg".to_string()),
             ]
         });
 
         // Incorporate any additional timestamps or VCS information.
         for cache_key in &cache_keys {
             match cache_key {
                 CacheKey::Path(file) | CacheKey::File { file } => {
-                    timestamp = max(
-                        timestamp,
-                        file.metadata()
-                            .ok()
-                            .filter(std::fs::Metadata::is_file)
-                            .as_ref()
-                            .map(Timestamp::from_metadata),
-                    );
+                    if file.chars().any(|c| matches!(c, '*' | '?' | '[')) {
+                        // Treat the path as a glob.
+                        let path = directory.join(file);
+                        let Some(pattern) = path.to_str() else {
+                            warn!("Failed to convert pattern to string: {}", path.display());
+                            continue;
+                        };
+                        let paths = match glob::glob_with(
+                            pattern,
+                            MatchOptions {
+                                case_sensitive: false,
+                                require_literal_separator: true,
+                                require_literal_leading_dot: false,
+                            },
+                        ) {
+                            Ok(paths) => paths,
+                            Err(err) => {
+                                warn!("Failed to parse glob pattern: {err}");
+                                continue;
+                            }
+                        };
+                        for entry in paths {
+                            let entry = match entry {
+                                Ok(entry) => entry,
+                                Err(err) => {
+                                    warn!("Failed to read glob entry: {err}");
+                                    continue;
+                                }
+                            };
+                            let metadata = match entry.metadata() {
+                                Ok(metadata) => metadata,
+                                Err(err) => {
+                                    warn!("Failed to read metadata for glob entry: {err}");
+                                    continue;
+                                }
+                            };
+                            if metadata.is_file() {
+                                timestamp =
+                                    max(timestamp, Some(Timestamp::from_metadata(&metadata)));
+                            } else {
+                                warn!(
+                                    "Expected file for cache key, but found directory: `{}`",
+                                    entry.display()
+                                );
+                            }
+                        }
+                    } else {
+                        // Treat the path as a file.
+                        let path = directory.join(file);
+                        let metadata = match path.metadata() {
+                            Ok(metadata) => metadata,
+                            Err(err) => {
+                                warn!("Failed to read metadata for file: {err}");
+                                continue;
+                            }
+                        };
+                        if metadata.is_file() {
+                            timestamp = max(timestamp, Some(Timestamp::from_metadata(&metadata)));
+                        } else {
+                            warn!(
+                                "Expected file for cache key, but found directory: `{}`",
+                                path.display()
+                            );
+                        }
+                    }
                 }
                 CacheKey::Git { git: true } => match CacheCommit::from_repository(directory) {
                     Ok(commit_info) => commit = Some(commit_info),
@@ -165,10 +223,15 @@ struct ToolUv {
 #[cfg_attr(feature = "schemars", derive(schemars::JsonSchema))]
 #[serde(untagged, rename_all = "kebab-case", deny_unknown_fields)]
 pub enum CacheKey {
-    /// Ex) `"Cargo.lock"`
-    Path(PathBuf),
-    /// Ex) `{ file = "Cargo.lock" }`
-    File { file: PathBuf },
+    /// Ex) `"Cargo.lock"` or `"**/*.toml"`
+    Path(String),
+    /// Ex) `{ file = "Cargo.lock" }` or `{ file = "**/*.toml" }`
+    File { file: String },
     /// Ex) `{ git = true }`
     Git { git: bool },
 }
+
+pub enum FilePattern {
+    Glob(String),
+    Path(PathBuf),
+}

crates/uv-cache-info/src/cache_info.rs

@@ -58,13 +58,20 @@ pub struct Options {
     /// to ensure that the project is rebuilt whenever the `requirements.txt` file is modified (in
     /// addition to watching the `pyproject.toml`).
     ///
+    /// Globs are supported, following the syntax of the [`glob`](https://docs.rs/glob/0.3.1/glob/struct.Pattern.html)
+    /// crate. For example, to invalidate the cache whenever a `.toml` file in the project directory
+    /// or any of its subdirectories is modified, you can specify `cache-keys = [{ file = "**/*.toml" }]`.
+    /// Note that the use of globs can be expensive, as uv may need to walk the filesystem to
+    /// determine whether any files have changed.
+    ///
     /// Cache keys can also include version control information. For example, if a project uses
     /// `setuptools_scm` to read its version from a Git tag, you can specify `cache-keys = [{ git = true }, { file = "pyproject.toml" }]`
     /// to include the current Git commit hash in the cache key (in addition to the
     /// `pyproject.toml`).
     ///
     /// Cache keys only affect the project defined by the `pyproject.toml` in which they're
-    /// specified (as opposed to, e.g., affecting all members in a workspace).
+    /// specified (as opposed to, e.g., affecting all members in a workspace), and all paths and
+    /// globs are interpreted as relative to the project directory.
     #[option(
         default = r#"[{ file = "pyproject.toml" }, { file = "setup.py" }, { file = "setup.cfg" }]"#,
         value_type = "list[dict]",

crates/uv-settings/src/settings.rs

@@ -3265,6 +3265,62 @@ fn invalidate_path_on_cache_key() -> Result<()> {
     "###
     );
 
+    // Modify the `pyproject.toml` to use a glob.
+    pyproject_toml.write_str(
+        r#"[project]
+        name = "example"
+        version = "0.0.0"
+        dependencies = ["anyio==4.0.0"]
+        requires-python = ">=3.8"
+
+        [tool.uv]
+        cache-keys = [{ file = "**/*.txt" }]
+"#,
+    )?;
+
+    // Write a new file.
+    editable_dir
+        .child("resources")
+        .child("data.txt")
+        .write_str("data")?;
+
+    // Installing again should update the package.
+    uv_snapshot!(context.filters(), context.pip_install()
+        .arg("example @ .")
+        .current_dir(editable_dir.path()), @r###"
+    success: true
+    exit_code: 0
+    ----- stdout -----
+
+    ----- stderr -----
+    Resolved 4 packages in [TIME]
+    Prepared 1 package in [TIME]
+    Uninstalled 1 package in [TIME]
+    Installed 1 package in [TIME]
+     ~ example==0.0.0 (from file://[TEMP_DIR]/editable)
+    "###
+    );
+
+    // Write a new file in the current directory.
+    editable_dir.child("data.txt").write_str("data")?;
+
+    // Installing again should update the package.
+    uv_snapshot!(context.filters(), context.pip_install()
+        .arg("example @ .")
+        .current_dir(editable_dir.path()), @r###"
+    success: true
+    exit_code: 0
+    ----- stdout -----
+
+    ----- stderr -----
+    Resolved 4 packages in [TIME]
+    Prepared 1 package in [TIME]
+    Uninstalled 1 package in [TIME]
+    Installed 1 package in [TIME]
+     ~ example==0.0.0 (from file://[TEMP_DIR]/editable)
+    "###
+    );
+
     Ok(())
 }
 

crates/uv/tests/pip_install.rs

@@ -52,6 +52,21 @@ the following to the project's `pyproject.toml`:
 cache-keys = [{ file = "requirements.txt" }]
 ```
 
+Globs are supported, following the syntax of the
+[`glob`](https://docs.rs/glob/0.3.1/glob/struct.Pattern.html) crate. For example, to invalidate the
+cache whenever a `.toml` file in the project directory or any of its subdirectories is modified, use
+the following:
+
+```toml title="pyproject.toml"
+[tool.uv]
+cache-keys = [{ file = "**/*.toml" }]
+```
+
+!!! note
+
+    The use of globs can be expensive, as uv may need to walk the filesystem to determine whether any files have changed.
+    This may, in turn, requiring traversal of large or deeply nested directories.
+
 As an escape hatch, if a project uses `dynamic` metadata that isn't covered by `tool.uv.cache-keys`,
 you can instruct uv to _always_ rebuild and reinstall it by adding the project to the
 `tool.uv.reinstall-package` list:

docs/concepts/cache.md

@@ -76,13 +76,20 @@ As an example: if a project uses dynamic metadata to read its dependencies from
 to ensure that the project is rebuilt whenever the `requirements.txt` file is modified (in
 addition to watching the `pyproject.toml`).
 
+Globs are supported, following the syntax of the [`glob`](https://docs.rs/glob/0.3.1/glob/struct.Pattern.html)
+crate. For example, to invalidate the cache whenever a `.toml` file in the project directory
+or any of its subdirectories is modified, you can specify `cache-keys = [{ file = "**/*.toml" }]`.
+Note that the use of globs can be expensive, as uv will need to walk the filesystem to
+determine whether any files have changed.
+
 Cache keys can also include version control information. For example, if a project uses
 `setuptools_scm` to read its version from a Git tag, you can specify `cache-keys = [{ git = true }, { file = "pyproject.toml" }]`
 to include the current Git commit hash in the cache key (in addition to the
 `pyproject.toml`).
 
 Cache keys only affect the project defined by the `pyproject.toml` in which they're
-specified (as opposed to, e.g., affecting all members in a workspace).
+specified (as opposed to, e.g., affecting all members in a workspace), and all paths and
+globs are interpreted as relative to the project directory.
 
 **Default value**: `[{ file = "pyproject.toml" }, { file = "setup.py" }, { file = "setup.cfg" }]`