Merge pull request #123 from lquerel/prepare-public-api

refactor(semconv): Add more unit tests, fix inconsistencies

Cargo.toml

@@ -39,7 +39,7 @@ anyhow = "1.0.81"
 
 # Features definition =========================================================
 [features]
-experimental = ["tantivy", "weaver_schema", "weaver_template"]
+experimental = []
 
 # Crate definitions ===========================================================
 [[bin]]
@@ -51,20 +51,14 @@ name = "weaver"
 # local crates dependencies
 weaver_common = { path = "crates/weaver_common" }
 weaver_resolver = { path = "crates/weaver_resolver" }
-weaver_template = { path = "crates/weaver_template", optional = true }
 weaver_semconv = { path = "crates/weaver_semconv" }
 weaver_resolved_schema = { path = "crates/weaver_resolved_schema" }
 weaver_semconv_gen = { path = "crates/weaver_semconv_gen" }
-weaver_schema = { path = "crates/weaver_schema", optional = true }
 weaver_cache = { path = "crates/weaver_cache" }
 weaver_forge = { path = "crates/weaver_forge" }
 weaver_checker = { path = "crates/weaver_checker" }
 
 clap = { version = "4.5.4", features = ["derive"] }
-crossterm = "0.27.0"
-ratatui = "0.26.1"
-tui-textarea = "0.4.0"
-tantivy = { version = "0.22.0", optional = true }
 
 # workspace dependencies
 serde.workspace = true

crates/weaver_checker/src/lib.rs

@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 
-//! This crate integrates a general purpose policy engine with the Weaver
-//! project. The project `regorus` is the policy engine used in this crate to
-//! evaluate policies.
+#![doc = include_str!("../README.md")]
 
 use crate::violation::Violation;
 use crate::Error::CompoundError;
@@ -48,6 +46,15 @@ pub enum Error {
         error: String,
     },
 
+    /// A policy violation error.
+    #[error("Policy violation: {violation}, provenance: {provenance}")]
+    PolicyViolation {
+        /// The provenance of the violation (URL or path).
+        provenance: String,
+        /// The violation.
+        violation: Violation,
+    },
+
     /// A container for multiple errors.
     #[error("{:?}", Error::format_errors(.0))]
     CompoundError(Vec<Error>),
@@ -76,6 +83,16 @@ impl Error {
     }
 }
 
+/// Handles a list of errors and returns a compound error if the list is not
+/// empty or () if the list is empty.
+pub fn handle_errors(errors: Vec<Error>) -> Result<(), Error> {
+    if errors.is_empty() {
+        Ok(())
+    } else {
+        Err(CompoundError(errors))
+    }
+}
+
 /// The policy engine.
 #[derive(Clone, Default)]
 pub struct Engine {

crates/weaver_common/src/error.rs

@@ -22,6 +22,19 @@ pub trait WeaverError {
 /// A trait for types that can cleanly exit the application if an error
 /// is encountered.
 pub trait ExitIfError<T, E> {
+    /// Processes the `Result` and panics if it is an `Err`.
+    /// If `Ok`, the contained value is returned.
+    ///
+    /// # Arguments
+    /// * `self` - The `Result` to process.
+    /// * `logger` - An object implementing the `Logger` trait used to log any
+    /// errors.
+    ///
+    /// # Returns
+    /// The contained value if the result is `Ok`.
+    /// Panics if the result is `Err`.
+    fn panic_if_error(self, logger: impl Logger) -> T;
+
     /// Processes the `Result` and exits the application if it is an `Err`.
     /// If `Ok`, the contained value is returned.
     ///
@@ -55,6 +68,27 @@ pub trait ExitIfError<T, E> {
 /// Provides default implementations of the `ExitIfError` trait for any
 /// `Result<T, E>` where `E` implements `WeaverError`.
 impl<T, E: WeaverError> ExitIfError<T, E> for Result<T, E> {
+    /// Processes the `Result` and panics if it is an `Err`.
+    /// If `Ok`, the contained value is returned.
+    ///
+    /// # Arguments
+    /// * `self` - The `Result` to process.
+    /// * `logger` - An object implementing the `Logger` trait used to log any
+    /// errors.
+    ///
+    /// # Returns
+    /// The contained value if the result is `Ok`.
+    /// Panics if the result is `Err`.
+    fn panic_if_error(self, logger: impl Logger) -> T {
+        match self {
+            Ok(value) => value,
+            Err(e) => {
+                e.errors().iter().for_each(|msg| logger.error(msg));
+                panic!("One or several errors occurred (see above)");
+            }
+        }
+    }
+
     /// Processes the `Result` and exits the application if it is an `Err`.
     /// If `Ok`, the contained value is returned.
     ///

crates/weaver_common/src/lib.rs

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 
-//! A generic logger that can be used to log messages to the console.
+#![doc = include_str!("../README.md")]
 
 pub mod error;
 pub mod quiet;

crates/weaver_forge/README.md

@@ -214,7 +214,7 @@ The following filters are available:
 in the `acronyms` section of the `weaver.yaml` configuration file.
 - `split_ids`: Splits a string by '.' creating a list of nested ids.
 - `flatten`: Converts a List of Lists into a single list with all elements.
-e.g. [[a,b],[c]] => [a,b,c]
+e.g. \[\[a,b\],\[c\]\] => \[a,b,c\]
 
 
 > Note 1: This project uses the [convert_case](https://crates.io/crates/convert_case)

crates/weaver_forge/src/lib.rs

@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 
-//! This crate extends the MiniJinja template engine to add helper functions
-//! and filters for working with semantic convention registries and telemetry
-//! schemas.
+#![doc = include_str!("../README.md")]
 
 use std::fmt::{Debug, Display, Formatter};
 use std::fs;
@@ -470,7 +468,7 @@ mod tests {
     use weaver_common::TestLogger;
     use weaver_diff::diff_output;
     use weaver_resolver::SchemaResolver;
-    use weaver_semconv::SemConvRegistry;
+    use weaver_semconv::registry::SemConvRegistry;
 
     use crate::debug::print_dedup_errors;
     use crate::filter::Filter;
@@ -614,7 +612,7 @@ mod tests {
         });
 
         let registry_id = "default";
-        let mut registry = SemConvRegistry::try_from_path(registry_id, "data/*.yaml")
+        let mut registry = SemConvRegistry::try_from_path_pattern(registry_id, "data/*.yaml")
             .expect("Failed to load registry");
         let schema = SchemaResolver::resolve_semantic_convention_registry(&mut registry)
             .expect("Failed to resolve registry");

crates/weaver_resolver/Cargo.toml

@@ -15,20 +15,14 @@ workspace = true
 weaver_common = {  path = "../weaver_common" }
 weaver_diff = { path = "../weaver_diff" }
 weaver_semconv = { path = "../weaver_semconv" }
-weaver_schema = { path = "../weaver_schema" }
-weaver_version = { path = "../weaver_version" }
 weaver_cache = { path = "../weaver_cache" }
 weaver_resolved_schema = { path = "../weaver_resolved_schema" }
-weaver_checker = { path = "../weaver_checker" }
 
-regex.workspace = true
 thiserror.workspace = true
 rayon.workspace = true
 serde.workspace = true
 serde_json.workspace = true
 walkdir.workspace = true
 
-url = "2.5.0"
-
 [dev-dependencies]
 glob = "0.3.1"

crates/weaver_resolver/allowed-external-types.toml

@@ -9,7 +9,5 @@ allowed_external_types = [
     "weaver_semconv::*",
     "weaver_common::*",
     "weaver_cache::Cache",
-    "weaver_schema::*",
     "weaver_version::*",
-    "weaver_checker::*"
 ]

crates/weaver_resolver/data/registry-test-lineage-0/expected-attribute-catalog.json

@@ -3,46 +3,60 @@
     "name": "server.port",
     "type": "string",
     "brief": "Server port",
+    "examples": [
+      "80",
+      "443"
+    ],
     "requirement_level": "recommended"
   },
   {
     "name": "network.protocol.name",
     "type": "string",
     "brief": "Network protocol name",
+    "examples": [
+      "http",
+      "spdy"
+    ],
     "requirement_level": "recommended"
   },
   {
     "name": "network.protocol.version",
     "type": "string",
     "brief": "Network protocol version",
+    "examples": [
+      "1.0",
+      "2.0"
+    ],
     "requirement_level": "recommended"
   },
   {
     "name": "network.type",
     "type": "string",
     "brief": "Network type",
+    "examples": [
+      "ipv4",
+      "ipv6"
+    ],
     "requirement_level": "recommended"
   },
   {
     "name": "server.port",
     "type": "string",
     "brief": "Server port",
-    "requirement_level": "opt_in"
-  },
-  {
-    "name": "network.protocol.name",
-    "type": "string",
-    "brief": "Network protocol name",
     "examples": [
-      "http",
-      "spdy"
+      "80",
+      "443"
     ],
-    "requirement_level": "recommended"
+    "requirement_level": "opt_in"
   },
   {
     "name": "network.protocol.version",
     "type": "string",
     "brief": "Network protocol version",
+    "examples": [
+      "1.0",
+      "2.0"
+    ],
     "requirement_level": "opt_in"
   }
 ]

crates/weaver_resolver/data/registry-test-lineage-0/expected-registry.json

@@ -30,10 +30,10 @@
       "type": "attribute_group",
       "brief": "Top level group",
       "attributes": [
+        1,
         3,
         4,
-        5,
-        6
+        5
       ],
       "lineage": {
         "source_file": "data/registry-test-lineage-0/registry/groups.yaml",
@@ -42,6 +42,7 @@
             "source_group": "registry.network",
             "inherited_fields": [
               "brief",
+              "examples",
               "note"
             ],
             "locally_overridden_fields": [
@@ -52,6 +53,7 @@
             "source_group": "registry.network",
             "inherited_fields": [
               "brief",
+              "examples",
               "note",
               "requirement_level"
             ]
@@ -60,6 +62,7 @@
             "source_group": "registry.server",
             "inherited_fields": [
               "brief",
+              "examples",
               "note"
             ],
             "locally_overridden_fields": [

crates/weaver_resolver/data/registry-test-lineage-0/registry/groups.yaml

@@ -6,6 +6,7 @@ groups:
       - id: server.port
         type: string
         brief: Server port
+        examples: [ '80', '443' ]
 
   - id: registry.network
     type: attribute_group
@@ -14,12 +15,15 @@ groups:
       - id: network.protocol.name
         type: string
         brief: Network protocol name
+        examples: [ 'http', 'spdy' ]
       - id: network.protocol.version
         type: string
         brief: Network protocol version
+        examples: [ '1.0', '2.0' ]
       - id: network.type
         type: string
         brief: Network type
+        examples: [ 'ipv4', 'ipv6' ]
 
   - id: top.level.group
     type: attribute_group

crates/weaver_resolver/data/registry-test-lineage-1/expected-attribute-catalog.json

@@ -3,6 +3,9 @@
     "name": "server.port",
     "type": "string",
     "brief": "Server port",
+    "examples": [
+      "8080"
+    ],
     "requirement_level": "recommended"
   }
 ]

crates/weaver_resolver/data/registry-test-lineage-1/expected-registry.json

@@ -15,6 +15,7 @@
             "source_group": "intermediate.level",
             "inherited_fields": [
               "brief",
+              "examples",
               "note",
               "requirement_level"
             ]
@@ -36,6 +37,7 @@
             "source_group": "base.level",
             "inherited_fields": [
               "brief",
+              "examples",
               "note",
               "requirement_level"
             ]

crates/weaver_resolver/data/registry-test-lineage-1/registry/groups.yaml

@@ -13,4 +13,5 @@ groups:
     attributes:
       - id: server.port
         type: string
-        brief: Server port
+        brief: Server port
+        examples: ['8080']