Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Embed and expose examples in Rust #198

Merged
merged 2 commits into from
Jan 5, 2024
Merged

Embed and expose examples in Rust #198

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e120ff2
Embed and expose examples in Rust
Swatinem Jan 5, 2024
f73b56b
explain single examples limitation
Swatinem Jan 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,15 @@ version = "0.1.39"
edition = "2021"

build = "rust/build.rs"
include = ["/rust/*.rs", "/Cargo.toml", "/schemas/**", "/topics/**", "/README.md", "/LICENSE.md"]
include = [
"/examples/**",
"/rust/*.rs",
"/schemas/**",
"/topics/**",
"/Cargo.toml",
"/LICENSE.md",
"/README.md",
]

# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

Expand All @@ -27,10 +35,10 @@ default = ["type_generation"]
type_generation = ["prettyplease", "schemars", "syn", "typify", "regress"]

[dependencies]
serde = { version = "1.0", features = ["derive"]}
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"
serde_yaml = "0.9"
regress = { version = "0.5.0", optional = true } # required by generated code
regress = { version = "0.5.0", optional = true } # required by generated code
jsonschema = "0.17.1"
thiserror = "1.0.49"

Expand Down
53 changes: 47 additions & 6 deletions rust/build.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,34 +48,75 @@ fn generate_embedded_data() -> String {
let manifest_root = std::env::var("CARGO_MANIFEST_DIR").unwrap_or_default();
let topics = enumerate_dir("topics");
let schemas = enumerate_dir("schemas");
let examples = enumerate_dir("examples");

let mut code = String::new();
use std::fmt::Write;
let w = &mut code;

writeln!(w, "const TOPICS: &[(&'static str, &'static str)] = &[").unwrap();
writeln!(w, "const TOPICS: &[(&str, &str)] = &[").unwrap();
for topic in topics {
let name = topic.strip_suffix(".yaml").unwrap();
let path = format!("{manifest_root}/topics/{topic}");
writeln!(w, " ({name:?}, include_str!({path:?})),").unwrap();
}
writeln!(w, "];\n").unwrap();

writeln!(w, "const SCHEMAS: &[(&'static str, &'static str)] = &[").unwrap();
writeln!(w, "const SCHEMAS: &[(&str, &str)] = &[").unwrap();
for schema in schemas {
let path = format!("{manifest_root}/schemas/{schema}");
writeln!(w, " ({schema:?}, include_str!({path:?})),").unwrap();
}
writeln!(w, "];").unwrap();

let mut last_prefix = None;
writeln!(w, "const EXAMPLES: &[(&str, &[&[u8]])] = &[").unwrap();
for example in &examples {
let last_slash = example.rfind('/').unwrap();
let (prefix, _name) = example.split_at(last_slash + 1);
match last_prefix {
None => {
writeln!(w, " ({prefix:?}, &[").unwrap();
}
Some(last_prefix) if last_prefix != prefix => {
writeln!(w, " ]),").unwrap();
writeln!(w, " ({prefix:?}, &[").unwrap();
}
_ => {}
}
last_prefix = Some(prefix);
let path = format!("{manifest_root}/examples/{example}");
writeln!(w, " include_bytes!({path:?}),").unwrap();
}
writeln!(w, " ]),").unwrap();
writeln!(w, "];").unwrap();

code
}

fn enumerate_dir(dir: &str) -> Vec<String> {
let mut files: Vec<_> = std::fs::read_dir(dir)
.unwrap()
.map(|entry| entry.unwrap().file_name().into_string().unwrap())
.collect();
let mut files = vec![];

fn collect_files(files: &mut Vec<String>, dir: &Path, prefix: &str) {
for entry in std::fs::read_dir(dir).unwrap() {
let entry = entry.unwrap();
let name = entry.file_name().into_string().unwrap();
let name = if prefix.is_empty() {
name
} else {
format!("{prefix}/{name}")
};
let ty = entry.file_type().unwrap();
if ty.is_dir() {
collect_files(files, &entry.path(), &name)
} else if ty.is_file() {
files.push(name);
}
}
}

collect_files(&mut files, dir.as_ref(), "");

files.sort();
files
}
Expand Down
42 changes: 26 additions & 16 deletions rust/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,9 +58,9 @@ struct TopicData {
schemas: Vec<TopicSchema>,
}

fn find_entry<'s>(slice: &[(&str, &'s str)], key: &str) -> Option<&'s str> {
fn find_entry<'s, T>(slice: &'s [(&str, T)], key: &str) -> Option<&'s T> {
let idx = slice.binary_search_by_key(&key, |&(name, _)| name).ok()?;
Some(slice.get(idx)?.1)
Some(&slice.get(idx)?.1)
}

impl TopicData {
Expand All @@ -77,6 +77,7 @@ pub struct Schema {
pub compatibility_mode: CompatibilityMode,
schema: &'static str,
compiled_json_schema: JSONSchema,
examples: &'static [&'static [u8]],
}

impl PartialEq for Schema {
Expand All @@ -103,6 +104,11 @@ impl Schema {
pub fn raw_schema(&self) -> &str {
self.schema
}

/// Returns a list of examples for this schema.
pub fn examples(&self) -> &[&[u8]] {
self.examples
}
}

fn get_topic_schema(topic: &str, version: Option<u16>) -> Result<TopicSchema, SchemaError> {
Expand Down Expand Up @@ -146,22 +152,28 @@ pub fn get_schema(topic: &str, version: Option<u16>) -> Result<Schema, SchemaErr
let s = serde_json::from_str(schema).map_err(|_| SchemaError::InvalidSchema)?;
let compiled_json_schema = JSONSchema::compile(&s).map_err(|_| SchemaError::InvalidSchema)?;

// FIXME(swatinem): This assumes that there is only a single examples directory
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

there is, or am i misunderstanding what this means?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I expanded the FIXME comment:

    // FIXME(swatinem): This assumes that there is only a single `examples` entry in the definition.
    // If we would want to support multiple, we would have to either merge those in code generation,
    // or rather use a `fn examples() -> impl Iterator`.

let examples = schema_metadata
.examples
.first()
.and_then(|example| find_entry(EXAMPLES, example))
.copied()
.unwrap_or_default();

Ok(Schema {
version: schema_metadata.version,
schema_type: schema_metadata.schema_type,
compatibility_mode: schema_metadata.compatibility_mode,
schema,
compiled_json_schema,
examples,
})
}

#[cfg(test)]
mod tests {
use super::*;

use std::fs::read_to_string;
use std::path::Path;

#[test]
fn test_get_schema() {
assert!(matches!(
Expand All @@ -178,18 +190,16 @@ mod tests {

#[test]
fn test_validate() {
let topic = "snuba-queries";
let topic_schema = get_topic_schema(topic, None).unwrap();
let schema = get_schema(topic, None).unwrap();
let example_dir = topic_schema.examples.first().unwrap();
let example_path = Path::new(env!("CARGO_MANIFEST_DIR"))
.join(format!("examples/{}{}", example_dir, "snuba-queries1.json"));
let example = read_to_string(example_path).unwrap();
schema.validate_json(example.as_bytes()).unwrap();

let invalid = "{}";
let schema = get_schema("snuba-queries", None).unwrap();

let examples = schema.examples();
assert!(!examples.is_empty());
for example in examples {
schema.validate_json(example).unwrap();
}

assert!(matches!(
schema.validate_json(invalid.as_bytes()),
schema.validate_json(b"{}"),
Err(SchemaError::InvalidMessage)
));
}
Expand Down
Loading