[WIP] Registry manifest and Schema diff

.clippy.toml

@@ -1,4 +1,4 @@
-msrv = "1.76.0"  # MSRV
+msrv = "1.80.0"  # MSRV
 warn-on-all-wildcard-imports = true
 allow-expect-in-tests = true
 allow-unwrap-in-tests = true

Cargo.toml

@@ -33,7 +33,7 @@ edition = "2021"
 repository = "https://github.com/open-telemetry/weaver"
 license = "Apache-2.0"
 publish = false
-rust-version = "1.76"
+rust-version = "1.80"
 
 [workspace.dependencies]
 serde = { version = "1.0.210", features = ["derive"] }
@@ -78,6 +78,7 @@ weaver_semconv_gen = { path = "crates/weaver_semconv_gen" }
 weaver_cache = { path = "crates/weaver_cache" }
 weaver_forge = { path = "crates/weaver_forge" }
 weaver_checker = { path = "crates/weaver_checker" }
+weaver_otel_schema = { path = "crates/weaver_otel_schema" }
 
 clap = { version = "4.5.20", features = ["derive"] }
 rayon = "1.10.0"

crates/weaver_cache/src/lib.rs

@@ -99,7 +99,7 @@ impl From<Error> for DiagnosticMessages {
 /// - A simple wrapper around a local directory
 /// - Initialized from a Git repository
 /// - Initialized from a Git archive
-#[derive(Default)]
+#[derive(Default, Debug)]
 pub struct RegistryRepo {
     // A unique identifier for the registry (e.g. main, baseline, etc.)
     id: String,
@@ -509,6 +509,17 @@ impl RegistryRepo {
         &self.registry_path
     }
 
+    /// Returns the path to the `registry_manifest.yaml` file (if any).
+    #[must_use]
+    pub fn manifest_path(&self) -> Option<PathBuf> {
+        let manifest_path = self.path.join("registry_manifest.yaml");
+        if manifest_path.exists() {
+            Some(manifest_path)
+        } else {
+            None
+        }
+    }
+
     /// Creates a temporary directory for the registry repository and returns the path.
     /// The temporary directory is created in the `.weaver/semconv_registry_cache`.
     fn create_tmp_repo() -> Result<TempDir, Error> {

crates/weaver_codegen_test/build.rs

@@ -24,7 +24,6 @@ use weaver_semconv::registry::SemConvRegistry;
 
 const SEMCONV_REGISTRY_PATH: &str = "./semconv_registry/";
 const TEMPLATES_PATH: &str = "./templates/registry/";
-const REGISTRY_ID: &str = "test";
 const TARGET: &str = "rust";
 
 fn main() {
@@ -49,7 +48,8 @@ fn main() {
         .ignore(|e| matches!(e.severity(), Some(miette::Severity::Warning)))
         .into_result_failing_non_fatal()
         .unwrap_or_else(|e| process_error(&logger, e));
-    let mut registry = SemConvRegistry::from_semconv_specs(REGISTRY_ID, semconv_specs);
+    let mut registry = SemConvRegistry::from_semconv_specs(&registry_repo, semconv_specs)
+        .unwrap_or_else(|e| process_error(&logger, e));
     let schema = SchemaResolver::resolve_semantic_convention_registry(&mut registry)
         .unwrap_or_else(|e| process_error(&logger, e));
 
@@ -61,13 +61,9 @@ fn main() {
     engine
         .import_jq_package(SEMCONV_JQ)
         .unwrap_or_else(|e| process_error(&logger, e));
-    let template_registry = ResolvedRegistry::try_from_resolved_registry(
-        schema
-            .registry(REGISTRY_ID)
-            .expect("Failed to get the registry from the resolved schema"),
-        schema.catalog(),
-    )
-    .unwrap_or_else(|e| process_error(&logger, e));
+    let template_registry =
+        ResolvedRegistry::try_from_resolved_registry(&schema.registry, schema.catalog())
+            .unwrap_or_else(|e| process_error(&logger, e));
     let target_dir: PathBuf = target_dir.into();
     engine
         .generate(

crates/weaver_common/src/diagnostic.rs

@@ -180,8 +180,7 @@ impl DiagnosticMessages {
         Self(vec![DiagnosticMessage::new(error)])
     }
 
-    /// Returns true if all the diagnostic messages are explicitly marked as
-    /// warnings or advices.
+    /// Returns true if at least one diagnostic message has an error severity.
     #[must_use]
     pub fn has_error(&self) -> bool {
         let non_error_count = self

crates/weaver_forge/expected_output/test/resource/library.md

@@ -22,7 +22,7 @@ Brief: Span attributes used by non-OTLP exporters to represent OpenTelemetry Sco
 - Examples: [
     "io.opentelemetry.contrib.mongodb",
 ]
-- Deprecated: use the `otel.scope.name` attribute.
+- Deprecated: {"action": "renamed", "new_name": "otel.scope.name", "note": "use the `otel.scope.name` attribute."}
 
 
 #### Attribute `otel.library.version`
@@ -36,7 +36,7 @@ Brief: Span attributes used by non-OTLP exporters to represent OpenTelemetry Sco
 - Examples: [
     "1.0.0",
 ]
-- Deprecated: use the `otel.scope.version` attribute.
+- Deprecated: {"action": "renamed", "new_name": "otel.scope.version", "note": "use the `otel.scope.version` attribute."}
 
 
 

crates/weaver_forge/expected_output/test/resources.md

@@ -25,7 +25,7 @@ Brief: Span attributes used by non-OTLP exporters to represent OpenTelemetry Sco
 - Examples: [
     "io.opentelemetry.contrib.mongodb",
 ]
-- Deprecated: use the `otel.scope.name` attribute.
+- Deprecated: {"action": "renamed", "new_name": "otel.scope.name", "note": "use the `otel.scope.name` attribute."}
 
 
 #### Attribute `otel.library.version`
@@ -39,7 +39,7 @@ Brief: Span attributes used by non-OTLP exporters to represent OpenTelemetry Sco
 - Examples: [
     "1.0.0",
 ]
-- Deprecated: use the `otel.scope.version` attribute.
+- Deprecated: {"action": "renamed", "new_name": "otel.scope.version", "note": "use the `otel.scope.version` attribute."}
 
 
 

crates/weaver_forge/src/extensions/util.rs

@@ -19,6 +19,7 @@ pub(crate) fn add_filters(env: &mut Environment<'_>, target_config: &WeaverConfi
     env.add_filter("flatten", flatten);
     env.add_filter("split_id", split_id);
     env.add_filter("regex_replace", regex_replace);
+    env.add_filter("toyaml", to_yaml);
 }
 
 /// Add utility functions to the environment.
@@ -86,6 +87,32 @@ fn regex_replace(
         .to_string())
 }
 
+/// Convert a value to a YAML string.
+fn to_yaml(value: Value) -> Result<Value, minijinja::Error> {
+    serde_yaml::to_string(&value)
+        .map_err(|e| {
+            minijinja::Error::new(
+                ErrorKind::InvalidOperation,
+                format!("Failed to convert to YAML: {}", e),
+            )
+        })
+        .map(|s| {
+            // When this filter is used the return value is safe for both HTML and YAML
+            // Note: this code is a copy of the `tojson` filter with the JSON-specific parts removed
+            let mut rv = String::with_capacity(s.len());
+            for c in s.chars() {
+                match c {
+                    '<' => rv.push_str("\\u003c"),
+                    '>' => rv.push_str("\\u003e"),
+                    '&' => rv.push_str("\\u0026"),
+                    '\'' => rv.push_str("\\u0027"),
+                    _ => rv.push(c),
+                }
+            }
+            Value::from_safe_string(rv)
+        })
+}
+
 /// Create a filter that replaces acronyms in the input string with the full
 /// name defined in the `acronyms` list.
 ///
@@ -159,4 +186,18 @@ mod tests {
             "This A test with multiple A's"
         );
     }
+
+    #[test]
+    fn test_to_yaml() {
+        let mut env = Environment::new();
+        let ctx = serde_json::json!({"ctx": {"key": "value", "nested": {"key": "value"}}});
+        let config = crate::config::WeaverConfig::default();
+
+        add_filters(&mut env, &config);
+
+        assert_eq!(
+            env.render_str("{{ ctx | toyaml }}", &ctx).unwrap(),
+            "key: value\nnested:\n  key: value\n"
+        );
+    }
 }

crates/weaver_forge/src/lib.rs

@@ -755,13 +755,12 @@ mod tests {
         let registry = SemConvRegistry::try_from_path_pattern(registry_id, "data/*.yaml")
             .into_result_failing_non_fatal()
             .expect("Failed to load registry");
-        prepare_test_with_registry(target, cli_params, registry_id, registry)
+        prepare_test_with_registry(target, cli_params, registry)
     }
 
     fn prepare_test_with_registry(
         target: &str,
         cli_params: Params,
-        registry_id: &str,
         mut registry: SemConvRegistry,
     ) -> (
         TestLogger,
@@ -779,16 +778,14 @@ mod tests {
         let schema = SchemaResolver::resolve_semantic_convention_registry(&mut registry)
             .expect("Failed to resolve registry");
 
-        let template_registry = ResolvedRegistry::try_from_resolved_registry(
-            schema.registry(registry_id).expect("registry not found"),
-            schema.catalog(),
-        )
-        .unwrap_or_else(|e| {
-            panic!(
-                "Failed to create the context for the template evaluation: {:?}",
-                e
-            )
-        });
+        let template_registry =
+            ResolvedRegistry::try_from_resolved_registry(&schema.registry, schema.catalog())
+                .unwrap_or_else(|e| {
+                    panic!(
+                        "Failed to create the context for the template evaluation: {:?}",
+                        e
+                    )
+                });
 
         // Delete all the files in the observed_output/target directory
         // before generating the new files.
@@ -959,16 +956,14 @@ mod tests {
         let schema = SchemaResolver::resolve_semantic_convention_registry(&mut registry)
             .expect("Failed to resolve registry");
 
-        let template_registry = ResolvedRegistry::try_from_resolved_registry(
-            schema.registry(registry_id).expect("registry not found"),
-            schema.catalog(),
-        )
-        .unwrap_or_else(|e| {
-            panic!(
-                "Failed to create the context for the template evaluation: {:?}",
-                e
-            )
-        });
+        let template_registry =
+            ResolvedRegistry::try_from_resolved_registry(&schema.registry, schema.catalog())
+                .unwrap_or_else(|e| {
+                    panic!(
+                        "Failed to create the context for the template evaluation: {:?}",
+                        e
+                    )
+                });
 
         engine
             .generate(
@@ -1093,7 +1088,7 @@ mod tests {
         .into_result_failing_non_fatal()
         .expect("Failed to load registry");
         let (logger, engine, template_registry, observed_output, expected_output) =
-            prepare_test_with_registry("comment_format", Params::default(), registry_id, registry);
+            prepare_test_with_registry("comment_format", Params::default(), registry);
 
         engine
             .generate(

crates/weaver_forge/src/registry.rs

@@ -12,6 +12,7 @@ use weaver_resolved_schema::catalog::Catalog;
 use weaver_resolved_schema::lineage::GroupLineage;
 use weaver_resolved_schema::registry::{Constraint, Group, Registry};
 use weaver_semconv::any_value::AnyValueSpec;
+use weaver_semconv::deprecated::Deprecated;
 use weaver_semconv::group::{GroupType, InstrumentSpec, SpanKindSpec};
 use weaver_semconv::stability::Stability;
 
@@ -63,7 +64,7 @@ pub struct ResolvedGroup {
     /// provided as `description` MUST specify why it's deprecated and/or what
     /// to use instead. See also stability.
     #[serde(skip_serializing_if = "Option::is_none")]
-    pub deprecated: Option<String>,
+    pub deprecated: Option<Deprecated>,
     /// Additional constraints.
     /// Allow to define additional requirements on the semantic convention.
     /// It defaults to an empty list.

crates/weaver_otel_schema/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "weaver_otel_schema"
+version = "0.10.0"
+authors.workspace = true
+repository.workspace = true
+license.workspace = true
+publish.workspace = true
+edition.workspace = true
+rust-version.workspace = true
+
+[lints]
+workspace = true
+
+[dependencies]
+weaver_version = { path = "../weaver_version" }
+weaver_common = { path = "../weaver_common" }
+
+thiserror.workspace = true
+serde.workspace = true
+serde_yaml.workspace = true
+miette.workspace = true

crates/weaver_otel_schema/README.md

@@ -0,0 +1,3 @@
+# OpenTelemetry Schema Data Model
+
+This crate describes the data model for the OpenTelemetry telemetry schema.

crates/weaver_otel_schema/allowed-external-types.toml

@@ -0,0 +1,6 @@
+# Copyright The OpenTelemetry Authors
+# SPDX-License-Identifier: Apache-2.0
+# This is used with cargo-check-external-types to reduce the surface area of downstream crates from
+# the public API. Ideally this can have a few exceptions as possible.
+allowed_external_types = [
+]