Allow resolving from resolved schema using Manifest file.

crates/weaver_common/Cargo.toml

@@ -23,6 +23,7 @@ once_cell.workspace = true
 schemars.workspace = true
 ureq.workspace = true
 log.workspace = true
+url.workspace = true
 
 tempfile.workspace = true
 dirs = "6.0.0"

crates/weaver_common/src/lib.rs

@@ -17,6 +17,7 @@ use miette::Diagnostic;
 use paris::formatter::colorize_string;
 use serde::Serialize;
 use std::io::Write;
+use std::path::Path;
 use std::sync::atomic::{AtomicUsize, Ordering};
 use std::sync::{Arc, Mutex};
 
@@ -295,3 +296,36 @@ pub fn warn_flare<T: std::fmt::Display>(message: T) -> String {
 pub fn log_warn<T: std::fmt::Display>(message: T) {
     log::warn!("{}", warn_flare(message));
 }
+
+/// Types of path strings we can support.
+pub enum PathType {
+    /// A URL path, like http://server/
+    URL,
+    /// A relative path, like ../some-file
+    RelativePath,
+    /// An absolute path, like /my/file/location
+    AbsolutePath,
+    /// Weaver-special.  A reference to a file
+    /// in a git repo or other.
+    WeaverPath,
+}
+
+/// Returns the type of path we're dealing with.
+#[must_use]
+pub fn get_path_type(input: &str) -> PathType {
+    match url::Url::parse(input) {
+        Ok(_) => PathType::URL,
+        Err(url::ParseError::RelativeUrlWithoutBase) => {
+            let test_path = Path::new(input);
+            if test_path.is_absolute() {
+                PathType::AbsolutePath
+            } else {
+                PathType::RelativePath
+            }
+        }
+        // TODO - we can learn more from error, we may be able
+        // to determine if this is a git-relative path or
+        // in-archive file reference.
+        Err(_) => PathType::WeaverPath,
+    }
+}

crates/weaver_common/src/vdir.rs

@@ -130,6 +130,60 @@ pub enum VirtualDirectoryPath {
     },
 }
 
+impl VirtualDirectoryPath {
+    /// Converts a virtual directory path by manipulating the "sub folder".
+    ///
+    /// Returning an empty string means no sub_folder will be used in resulting path.
+    ///
+    /// Sub folder will be modified as follows:
+    ///
+    /// - LocalFolder: will see the entire path
+    /// - others: will see the path inside the archive or empty string if none.
+    pub fn map_sub_folder<F: FnOnce(String) -> String>(self, f: F) -> VirtualDirectoryPath {
+        match self {
+            LocalFolder { path } => LocalFolder { path: f(path) },
+            LocalArchive { path, sub_folder } => LocalArchive {
+                path,
+                sub_folder: {
+                    let result = f(sub_folder.unwrap_or("".to_owned()));
+                    if result.is_empty() {
+                        None
+                    } else {
+                        Some(result)
+                    }
+                },
+            },
+            RemoteArchive { url, sub_folder } => RemoteArchive {
+                url,
+                sub_folder: {
+                    let result = f(sub_folder.unwrap_or("".to_owned()));
+                    if result.is_empty() {
+                        None
+                    } else {
+                        Some(result)
+                    }
+                },
+            },
+            GitRepo {
+                url,
+                refspec,
+                sub_folder,
+            } => GitRepo {
+                url,
+                refspec,
+                sub_folder: {
+                    let result = f(sub_folder.unwrap_or("".to_owned()));
+                    if result.is_empty() {
+                        None
+                    } else {
+                        Some(result)
+                    }
+                },
+            },
+        }
+    }
+}
+
 /// Enables parsing a [`VirtualDirectoryPath`] from a string representation.
 ///
 /// This implementation allows easy deserialization from strings (e.g. configuration files, command-line arguments).
@@ -686,10 +740,18 @@ impl VirtualDirectory {
 
     /// Returns the original string representation that was used to create this `VirtualDirectory`.
     #[must_use]
-    pub fn vdir_path(&self) -> &str {
+    pub fn vdir_path_str(&self) -> &str {
         &self.vdir_path
     }
 
+    /// Returns the original `VirtualDirectoryRef` that was used to create this `VirtualDirectory`.
+    #[must_use]
+    pub fn vdir_path(&self) -> VirtualDirectoryPath {
+        self.vdir_path_str()
+            .try_into()
+            .expect("VirtualDirectory should not have invalid `vdir_path`.")
+    }
+
     /// Creates and returns a new temporary directory within `.weaver/vdir_cache`.
     ///
     /// The created directory and its contents are automatically deleted when dropped.

crates/weaver_resolved_schema/src/catalog.rs

@@ -15,12 +15,12 @@ use weaver_semconv::stability::Stability;
 /// Attribute references are used to refer to attributes in the catalog.
 ///
 /// Note : In the future, this catalog could be extended with other entities.
-#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default)]
+#[derive(Serialize, Deserialize, Debug, Clone, JsonSchema, Default, PartialEq, Eq)]
 #[serde(deny_unknown_fields)]
 #[must_use]
 pub struct Catalog {
     /// Catalog of attributes used in the schema.
-    #[serde(skip_serializing_if = "Vec::is_empty")]
+    #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub(crate) attributes: Vec<Attribute>,
 }
 

crates/weaver_resolved_schema/src/lib.rs

@@ -32,6 +32,8 @@ pub mod tags;
 pub mod v2;
 pub mod value;
 
+pub use error::Error;
+
 /// The registry ID for the OpenTelemetry semantic conventions.
 /// This ID is reserved and should not be used by any other registry.
 pub const OTEL_REGISTRY_ID: &str = "OTEL";

crates/weaver_resolver/Cargo.toml

@@ -21,6 +21,7 @@ thiserror.workspace = true
 rayon.workspace = true
 serde.workspace = true
 serde_json.workspace = true
+serde_yaml.workspace = true
 walkdir.workspace = true
 miette.workspace = true
 itertools.workspace = true

crates/weaver_resolver/data/registry-test-1-single-attr-ref/expected-attribute-catalog.json

@@ -1,28 +1,30 @@
-[
-  {
-    "name": "messaging.destination.name",
-    "type": "string",
-    "brief": "The message destination name",
-    "examples": [
-      "MyQueue",
-      "MyTopic"
-    ],
-    "requirement_level": "recommended",
-    "note": "Destination name SHOULD uniquely identify a specific queue, topic or other entity within the broker. If\nthe broker doesn't have such notion, the destination name SHOULD uniquely identify the broker.\n",
-    "stability": "stable"
-  },
-  {
-    "name": "messaging.destination.name",
-    "type": "string",
-    "brief": "The message destination name",
-    "examples": [
-      "MyQueue",
-      "MyTopic"
-    ],
-    "requirement_level": {
-      "conditionally_required": "if and only if `messaging.destination.name` is known to have low cardinality. Otherwise, `messaging.destination.template` MAY be populated."
+{
+  "attributes": [
+    {
+      "name": "messaging.destination.name",
+      "type": "string",
+      "brief": "The message destination name",
+      "examples": [
+        "MyQueue",
+        "MyTopic"
+      ],
+      "requirement_level": "recommended",
+      "note": "Destination name SHOULD uniquely identify a specific queue, topic or other entity within the broker. If\nthe broker doesn't have such notion, the destination name SHOULD uniquely identify the broker.\n",
+      "stability": "stable"
     },
-    "note": "Destination name SHOULD uniquely identify a specific queue, topic or other entity within the broker. If\nthe broker doesn't have such notion, the destination name SHOULD uniquely identify the broker.\n",
-    "stability": "stable"
-  }
-]
+    {
+      "name": "messaging.destination.name",
+      "type": "string",
+      "brief": "The message destination name",
+      "examples": [
+        "MyQueue",
+        "MyTopic"
+      ],
+      "requirement_level": {
+        "conditionally_required": "if and only if `messaging.destination.name` is known to have low cardinality. Otherwise, `messaging.destination.template` MAY be populated."
+      },
+      "note": "Destination name SHOULD uniquely identify a specific queue, topic or other entity within the broker. If\nthe broker doesn't have such notion, the destination name SHOULD uniquely identify the broker.\n",
+      "stability": "stable"
+    }
+  ]
+}

crates/weaver_resolver/data/registry-test-10-prefix-refs/expected-attribute-catalog.json

@@ -1,63 +1,65 @@
-[
-  {
-    "name": "client.geo.lat",
-    "type": "string",
-    "brief": "My own latitude",
-    "examples": [
-      "123.456"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development",
-    "prefix": true
-  },
-  {
-    "name": "client.geo.lat",
-    "type": "string",
-    "brief": "this is embedded attribute",
-    "examples": [
-      "123.456"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development"
-  },
-  {
-    "name": "client.id",
-    "type": "string",
-    "brief": "some client id\n",
-    "examples": [
-      "a.einstein"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development"
-  },
-  {
-    "name": "geo.lat",
-    "type": "string",
-    "brief": "latitude of the geo coordinates.\n",
-    "examples": [
-      "123.456"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development"
-  },
-  {
-    "name": "geo.lat",
-    "type": "string",
-    "brief": "this is ref attribute",
-    "examples": [
-      "123.456"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development"
-  },
-  {
-    "name": "geo.lon",
-    "type": "string",
-    "brief": "longitude of the geo coordinates.\n",
-    "examples": [
-      "234.456"
-    ],
-    "requirement_level": "recommended",
-    "stability": "development"
-  }
-]
+{
+  "attributes": [
+    {
+      "name": "client.geo.lat",
+      "type": "string",
+      "brief": "My own latitude",
+      "examples": [
+        "123.456"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development",
+      "prefix": true
+    },
+    {
+      "name": "client.geo.lat",
+      "type": "string",
+      "brief": "this is embedded attribute",
+      "examples": [
+        "123.456"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development"
+    },
+    {
+      "name": "client.id",
+      "type": "string",
+      "brief": "some client id\n",
+      "examples": [
+        "a.einstein"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development"
+    },
+    {
+      "name": "geo.lat",
+      "type": "string",
+      "brief": "latitude of the geo coordinates.\n",
+      "examples": [
+        "123.456"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development"
+    },
+    {
+      "name": "geo.lat",
+      "type": "string",
+      "brief": "this is ref attribute",
+      "examples": [
+        "123.456"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development"
+    },
+    {
+      "name": "geo.lon",
+      "type": "string",
+      "brief": "longitude of the geo coordinates.\n",
+      "examples": [
+        "234.456"
+      ],
+      "requirement_level": "recommended",
+      "stability": "development"
+    }
+  ]
+}