[WIP] Code Generation with Weaver - Example of Code Generation for SemConv Attribute Registry and SemConv Metrics

.github/codecov.yaml

@@ -13,4 +13,5 @@ coverage:
 
 ignore:
   - "crates/xtask"  # Part of the build system
-  - "src"           # CLI (not tested yet)
+  - "src"           # CLI (not tested yet)
+  - "crates/weaver_forge/codegen_examples/expected_codegen" # Generated code

.github/workflows/ci.yml

@@ -175,7 +175,7 @@ jobs:
       - name: Install cargo-tarpaulin
         run: cargo install cargo-tarpaulin
       - name: Gather coverage
-        run: cargo tarpaulin --workspace --output-dir coverage --out lcov -e xtask -e weaver
+        run: cargo tarpaulin --workspace --output-dir coverage --out lcov -e xtask -e weaver --exclude-files 'crates/weaver_forge/codegen_examples/expected_codegen/*'
       - name: Upload coverage reports to Codecov
         uses: codecov/codecov-action@v4.0.1
         with:

Cargo.toml

@@ -10,6 +10,7 @@ categories = ["command-line-utilities"]
 license = "Apache-2.0"
 readme = "README.md"
 publish = false
+resolver = "2"
 
 # Workspace definition ========================================================
 [workspace]

README.md

@@ -5,7 +5,7 @@
 [![build](https://github.com/open-telemetry/weaver/actions/workflows/audit.yml/badge.svg)](https://github.com/open-telemetry/weaver/actions/workflows/audit.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 ----
-(CONTRIBUTING.md) | [Links](#links) |
+
 [Getting started](#getting-started) | [Main commands](#main-commands) | [Generate Doc & Code](crates/weaver_forge/README.md) | [Architecture](docs/architecture.md) | [Change log](CHANGELOG.md) | [Contributing](CONTRIBUTING.md) | [Links](#links) |
 
 ## What is OpenTelemetry Weaver?

crates/weaver_forge/Cargo.toml

@@ -36,3 +36,8 @@ serde_json.workspace = true
 rayon.workspace = true
 walkdir.workspace = true
 
+[dev-dependencies]
+opentelemetry = { version = "0.22.0", features = ["trace", "metrics", "logs", "otel_unstable"] }
+opentelemetry_sdk = { version = "0.22.1", features = ["trace", "metrics", "logs"] }
+opentelemetry-stdout = { version = "0.3.0", features = ["trace", "metrics", "logs"] }
+

crates/weaver_forge/codegen_examples/expected_codegen/README.md

@@ -0,0 +1,20 @@
+# Semantic Conventions for Rust
+
+# Usage
+
+```rust
+fn main() {
+    // Display the KeyValue of the attribute CLIENT_ADDRESS initialized with the value "145.34.23.56"
+    println!("{:?}", semconv::client::CLIENT_ADDRESS.value("145.34.23.56".into()));
+    // Display the key of the attribute CLIENT_ADDRESS
+    println!("{:?}", semconv::client::CLIENT_ADDRESS.key());
+
+    // Display the KeyValue of the attribute CLIENT_PORT initialized with the value 8080
+    println!("{:?}", semconv::client::CLIENT_PORT.value(8080));
+    // Display the key of the attribute CLIENT_PORT
+    println!("{:?}", semconv::client::CLIENT_PORT.key());
+
+    // Display the string representation of the enum variant HttpRequestMethod::Connect
+    println!("{}", semconv::http::HttpRequestMethod::Connect);
+}
+```

crates/weaver_forge/codegen_examples/expected_codegen/attributes/client.rs

@@ -0,0 +1,27 @@
+/*
+ * Copyright The OpenTelemetry Authors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+//! These attributes may be used to describe the client in a connection-based network interaction where there is one side that initiates the connection (the client is the side that initiates the connection). This covers all TCP network interactions since TCP is connection-based and one side initiates the connection (an exception is made for peer-to-peer communication over TCP where the "user-facing" surface of the protocol / API doesn't expose a clear notion of client and server). This also covers UDP network interactions where one side initiates the interaction, e.g. QUIC (HTTP/3) and DNS.
+//! DO NOT EDIT, this is an Auto-generated file from templates/registry/rust/attributes/attributes.rs.j2
+
+/// Client address - domain name if available without reverse DNS lookup; otherwise, IP address or Unix domain socket name.
+///
+/// Notes:
+///   When observed from the server side, and when communicating through an intermediary, `client.address` SHOULD represent the client address behind any intermediaries,  for example proxies, if it's available.
+///
+/// Examples:
+/// - client.example.com
+/// - 10.1.2.80
+/// - /tmp/my.sock
+pub const CLIENT_ADDRESS: crate::attributes::AttributeKey<opentelemetry::StringValue> = crate::attributes::AttributeKey::new("client.address");
+
+/// Client port number.
+///
+/// Notes:
+///   When observed from the server side, and when communicating through an intermediary, `client.port` SHOULD represent the client port behind any intermediaries,  for example proxies, if it's available.
+///
+/// Examples:
+/// - 65123
+pub const CLIENT_PORT: crate::attributes::AttributeKey<i64> = crate::attributes::AttributeKey::new("client.port");

crates/weaver_forge/codegen_examples/expected_codegen/attributes/error.rs

@@ -0,0 +1,75 @@
+/*
+ * Copyright The OpenTelemetry Authors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+//! This document defines the shared attributes used to report an error.
+//! DO NOT EDIT, this is an Auto-generated file from templates/registry/rust/attributes/attributes.rs.j2
+
+/// Describes a class of error the operation ended with.
+///
+/// Notes:
+///   The `error.type` SHOULD be predictable, and SHOULD have low cardinality.
+///   
+///   When `error.type` is set to a type (e.g., an exception type), its
+///   canonical class name identifying the type within the artifact SHOULD be used.
+///   
+///   Instrumentations SHOULD document the list of errors they report.
+///   
+///   The cardinality of `error.type` within one instrumentation library SHOULD be low.
+///   Telemetry consumers that aggregate data from multiple instrumentation libraries and applications
+///   should be prepared for `error.type` to have high cardinality at query time when no
+///   additional filters are applied.
+///   
+///   If the operation has completed successfully, instrumentations SHOULD NOT set `error.type`.
+///   
+///   If a specific domain defines its own set of error identifiers (such as HTTP or gRPC status codes),
+///   it's RECOMMENDED to:
+///   
+///   * Use a domain-specific attribute
+///   * Set `error.type` to capture all errors, regardless of whether they are defined within the domain-specific set or not.
+///
+/// Examples:
+/// - timeout
+/// - java.net.UnknownHostException
+/// - server_certificate_invalid
+/// - 500
+pub const ERROR_TYPE: crate::attributes::AttributeKey<ErrorType> = crate::attributes::AttributeKey::new("error.type");
+
+/// Describes a class of error the operation ended with.
+#[derive(Debug, Clone)]
+#[non_exhaustive]
+pub enum ErrorType {    /// A fallback error value to be used when the instrumentation doesn't define a custom value.
+    Other,
+    /// This variant allows defining a custom entry in the enum.
+    _Custom(String),
+}
+
+impl ErrorType {
+    /// Returns the string representation of the [`ErrorType`].
+    pub fn as_str(&self) -> &str {
+        match self {
+            ErrorType::Other => "_OTHER",
+            ErrorType::_Custom(v) => v.as_str(),
+            // Without this default case, the match expression would not
+            // contain any variants if all variants are annotated with the
+            // 'semconv_experimental' feature and the feature is not enabled.
+            #[allow(unreachable_patterns)]
+            _ => unreachable!(),
+        }
+    }
+}
+
+impl core::fmt::Display for ErrorType {
+    /// Formats the value using the given formatter.
+    fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
+        write!(f, "{}", self.as_str())
+    }
+}
+
+impl crate::attributes::AttributeKey<ErrorType> {
+    /// Returns a [`KeyValue`] pair for the given value.
+    pub fn value(&self, v: &ErrorType) -> opentelemetry::KeyValue {
+        opentelemetry::KeyValue::new(self.key.clone(), v.to_string())
+    }
+}

crates/weaver_forge/codegen_examples/expected_codegen/attributes/exception.rs

@@ -0,0 +1,47 @@
+/*
+ * Copyright The OpenTelemetry Authors
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+//! This document defines the shared attributes used to report a single exception associated with a span or log.
+//! DO NOT EDIT, this is an Auto-generated file from templates/registry/rust/attributes/attributes.rs.j2
+
+/// SHOULD be set to true if the exception event is recorded at a point where it is known that the exception is escaping the scope of the span.
+///
+/// Notes:
+///   An exception is considered to have escaped (or left) the scope of a span,
+///   if that span is ended while the exception is still logically "in flight".
+///   This may be actually "in flight" in some languages (e.g. if the exception
+///   is passed to a Context manager's `__exit__` method in Python) but will
+///   usually be caught at the point of recording the exception in most languages.
+///   
+///   It is usually not possible to determine at the point where an exception is thrown
+///   whether it will escape the scope of a span.
+///   However, it is trivial to know that an exception
+///   will escape, if one checks for an active exception just before ending the span,
+///   as done in the [example for recording span exceptions](#recording-an-exception).
+///   
+///   It follows that an exception may still escape the scope of the span
+///   even if the `exception.escaped` attribute was not set or set to false,
+///   since the event might have been recorded at a time where it was not
+///   clear whether the exception will escape.
+pub const EXCEPTION_ESCAPED: crate::attributes::AttributeKey<bool> = crate::attributes::AttributeKey::new("exception.escaped");
+
+/// The exception message.
+///
+/// Examples:
+/// - Division by zero
+/// - Can't convert 'int' object to str implicitly
+pub const EXCEPTION_MESSAGE: crate::attributes::AttributeKey<opentelemetry::StringValue> = crate::attributes::AttributeKey::new("exception.message");
+
+/// A stacktrace as a string in the natural representation for the language runtime. The representation is to be determined and documented by each language SIG.
+///
+/// Example: Exception in thread "main" java.lang.RuntimeException: Test exception\n at com.example.GenerateTrace.methodB(GenerateTrace.java:13)\n at com.example.GenerateTrace.methodA(GenerateTrace.java:9)\n at com.example.GenerateTrace.main(GenerateTrace.java:5)
+pub const EXCEPTION_STACKTRACE: crate::attributes::AttributeKey<opentelemetry::StringValue> = crate::attributes::AttributeKey::new("exception.stacktrace");
+
+/// The type of the exception (its fully-qualified class name, if applicable). The dynamic type of the exception should be preferred over the static type in languages that support it.
+///
+/// Examples:
+/// - java.net.ConnectException
+/// - OSError
+pub const EXCEPTION_TYPE: crate::attributes::AttributeKey<opentelemetry::StringValue> = crate::attributes::AttributeKey::new("exception.type");