Add PromQL query support for dashboard visualizations (ticket 013)
Hand-rolls a minimal PromQL parser (src/promql.rs) for metric-name + label-matcher selection, optional [range] selectors, and top-level sum()/avg()/rate() wrapping, rather than pulling in a full PromQL parser crate — the required subset is small and a hand-rolled parser stays fully engine-independent (mirrors filter_parser.rs) with no unused-AST overhead. Adds EngineQuery::Promql/EngineResponse::Promql (engine parses + evaluates in place against the index, no copying) and GET /api/query, returning Vec<PromqlSeriesDto> (labels + (timestamp_ms, f64) points) for charting, with malformed queries surfaced as 400 + ErrorDto. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XFUNZwCvz3kcod3352ZR2o
This commit is contained in:
co-authored by
Claude Sonnet 5
parent
e48c03218f
commit
ac67f9e120
+80
-1
@@ -4,7 +4,7 @@ use std::sync::{Arc, Mutex};
|
||||
|
||||
use crate::dto::{
|
||||
BucketValuesParams, CssEntryDto, ErrorDto, ImportCssRequest, LinkCssRequest,
|
||||
MetricDeclarationDto, ParamDeclarationDto, LogsParams, TimelineParams,
|
||||
MetricDeclarationDto, ParamDeclarationDto, LogsParams, PromqlParams, TimelineParams,
|
||||
};
|
||||
use crate::engine::{
|
||||
DeclareMetricRequest, DeclareParamRequest, EngineHandle, EngineMessage, EngineQuery,
|
||||
@@ -105,6 +105,7 @@ pub fn router(
|
||||
.route("/api/params", post(declare_param))
|
||||
.route("/api/metrics", get(list_metrics).post(declare_metric))
|
||||
.route("/api/metrics/{name}", get(get_metric_bucket_values))
|
||||
.route("/api/query", get(run_promql_query))
|
||||
.route("/api/settings/css", get(list_css).post(import_css))
|
||||
.route("/api/settings/css/link", post(link_css))
|
||||
.route("/api/settings/css/{id}", delete(remove_css))
|
||||
@@ -268,6 +269,31 @@ async fn get_metric_bucket_values(
|
||||
}
|
||||
}
|
||||
|
||||
/// `GET /api/query` — evaluates a PromQL query (ticket 013; see `crate::promql` for
|
||||
/// the supported grammar) against declared metrics. Query params: `promql` (the
|
||||
/// query string), `start_ms`, `end_ms` (bound which points are included, mirroring
|
||||
/// `/api/logs`/`/api/metrics/:name`). Returns `Vec<PromqlSeriesDto>` — chart-ready
|
||||
/// `labels` + `(timestamp_ms, value)` series — on success (`200 OK`), or
|
||||
/// `400 Bad Request` with `{ "error": "..." }` for a malformed query.
|
||||
async fn run_promql_query(
|
||||
State(state): State<ApiState>,
|
||||
Query(params): Query<PromqlParams>,
|
||||
) -> impl IntoResponse {
|
||||
let query = EngineQuery::Promql {
|
||||
query: params.promql,
|
||||
start_ms: params.start_ms,
|
||||
end_ms: params.end_ms,
|
||||
};
|
||||
match ask(&state.engine, query).await {
|
||||
Ok(EngineResponse::Promql(Ok(series))) => Json(series).into_response(),
|
||||
Ok(EngineResponse::Promql(Err(err))) => {
|
||||
(StatusCode::BAD_REQUEST, Json(ErrorDto { error: err })).into_response()
|
||||
}
|
||||
Ok(_) => StatusCode::INTERNAL_SERVER_ERROR.into_response(),
|
||||
Err(status) => status.into_response(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Maps a `CssError` from a settings mutation/lookup to a response status
|
||||
/// and message: `NotFound` -> 404, `NotImported` -> 400 (the id is valid but
|
||||
/// refers to a linked entry, which this operation doesn't apply to), `Io` ->
|
||||
@@ -580,6 +606,59 @@ mod tests {
|
||||
assert_eq!(values[0]["sequence"], 2);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn promql_query_returns_series_for_seeded_fixture() {
|
||||
let (app, engine, _settings, _dir) = test_app();
|
||||
|
||||
send_json(
|
||||
&app,
|
||||
"POST",
|
||||
"/api/metrics",
|
||||
json!({
|
||||
"name": "requests",
|
||||
"message_match_regex": r"request path=(?P<path>\S+)",
|
||||
"params": [
|
||||
{ "param_name": "path", "capture_group": "path", "kind": "string" }
|
||||
]
|
||||
}),
|
||||
)
|
||||
.await;
|
||||
|
||||
for (sequence, text) in [
|
||||
(0u64, "request path=/a"),
|
||||
(1u64, "request path=/b"),
|
||||
(2u64, "request path=/a"),
|
||||
] {
|
||||
engine
|
||||
.send(EngineMessage::Ingest(IngestedLine {
|
||||
sequence,
|
||||
timestamp: Timestamp::from_millis(sequence as i64 * 1000),
|
||||
text: text.to_string(),
|
||||
}))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
let (status, body) =
|
||||
get_json(&app, "/api/query?promql=requests%7Bpath%3D%22%2Fa%22%7D").await;
|
||||
assert_eq!(status, StatusCode::OK);
|
||||
let series = body.as_array().unwrap();
|
||||
assert_eq!(series.len(), 1);
|
||||
assert_eq!(series[0]["labels"]["path"], "/a");
|
||||
let points = series[0]["points"].as_array().unwrap();
|
||||
assert_eq!(points.len(), 2);
|
||||
assert_eq!(points[0], json!([0, 1.0]));
|
||||
assert_eq!(points[1], json!([2000, 1.0]));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn promql_query_rejects_malformed_query_with_400() {
|
||||
let (app, _engine, _settings, _dir) = test_app();
|
||||
let (status, body) = get_json(&app, "/api/query?promql=not+valid(").await;
|
||||
assert_eq!(status, StatusCode::BAD_REQUEST);
|
||||
assert!(body["error"].as_str().is_some_and(|s| !s.is_empty()));
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn declaring_param_persists_into_active_profile() {
|
||||
let (app, _engine, settings_handle, dir) = test_app();
|
||||
|
||||
+25
@@ -83,6 +83,31 @@ pub struct BucketValuesParams {
|
||||
pub limit: Option<usize>,
|
||||
}
|
||||
|
||||
/// One chart-ready time series returned by `GET /api/query` (ticket 013's PromQL
|
||||
/// endpoint): a label combination plus its `(timestamp_ms, value)` points, sorted by
|
||||
/// timestamp. `labels` uses plain `String` values (not `MetricPrimitive`) since every
|
||||
/// value has already been through `MetricPrimitive`'s `Display` form — chart code
|
||||
/// doesn't need the typed value, just something to show in a legend/tooltip.
|
||||
///
|
||||
/// `value` is always `f64` (see `crate::engine::coerce_to_f64` for how a bucket's
|
||||
/// `MetricPrimitive` is coerced into one), since a chart needs a plottable number
|
||||
/// regardless of the underlying metric primitive's kind.
|
||||
#[derive(Debug, Clone, Serialize, PartialEq)]
|
||||
pub struct PromqlSeriesDto {
|
||||
pub labels: BTreeMap<String, String>,
|
||||
pub points: Vec<(i64, f64)>,
|
||||
}
|
||||
|
||||
/// Query params for `GET /api/query`. `promql` is the query string (see
|
||||
/// `crate::promql`); `start_ms`/`end_ms` bound which points are included, mirroring
|
||||
/// `/api/logs`/`/api/metrics/:name`.
|
||||
#[derive(Debug, Deserialize)]
|
||||
pub struct PromqlParams {
|
||||
pub promql: String,
|
||||
pub start_ms: Option<i64>,
|
||||
pub end_ms: Option<i64>,
|
||||
}
|
||||
|
||||
/// JSON error body returned by API handlers on a 4xx/5xx response, e.g.
|
||||
/// `{ "error": "invalid regex: ..." }`.
|
||||
#[derive(Debug, Serialize)]
|
||||
|
||||
+252
-2
@@ -1,10 +1,11 @@
|
||||
use crate::data_value::{DataValue, MetricPrimitiveKind, RegexToMetricPrimitiveMatcher};
|
||||
use crate::dto::{
|
||||
BucketValueDto, LogEntryDto, LogsParams, MetricDeclarationDto, ParamDeclarationDto, StatsDto,
|
||||
TimelineBucketDto, TimelineParams,
|
||||
BucketValueDto, LogEntryDto, LogsParams, MetricDeclarationDto, ParamDeclarationDto,
|
||||
PromqlSeriesDto, StatsDto, TimelineBucketDto, TimelineParams,
|
||||
};
|
||||
use crate::index_key::IndexKey;
|
||||
use crate::metric_primitive::{MetricPrimitive, Number};
|
||||
use crate::promql::{self, AggOp, LabelMatcher, PromqlQuery};
|
||||
use crate::timestamp::Timestamp;
|
||||
use regex::Regex;
|
||||
use serde::Deserialize;
|
||||
@@ -64,6 +65,13 @@ pub enum EngineQuery {
|
||||
since_sequence: Option<u64>,
|
||||
limit: Option<usize>,
|
||||
},
|
||||
/// PromQL query (ticket 013's `GET /api/query`). `query` is parsed here (rather
|
||||
/// than by the API handler) so parsing and evaluation both happen inside the
|
||||
/// single-owner engine loop, matching every other `EngineQuery` variant's
|
||||
/// pattern of evaluating in place against `index` with no copying. A malformed
|
||||
/// query is therefore only discovered once this reaches `handle_query`, hence
|
||||
/// `EngineResponse::Promql` carrying a `Result` rather than a bare `Vec`.
|
||||
Promql { query: String, start_ms: Option<i64>, end_ms: Option<i64> },
|
||||
}
|
||||
|
||||
#[allow(dead_code)]
|
||||
@@ -99,6 +107,9 @@ pub enum EngineResponse {
|
||||
ParamDeclarations(Vec<ParamDeclarationDto>),
|
||||
MetricDeclarations(Vec<MetricDeclarationDto>),
|
||||
BucketValues(Vec<BucketValueDto>),
|
||||
/// `Err` holds a human-readable message for a malformed query (see
|
||||
/// `crate::promql::parse_query`), which the API layer maps to a 400 response.
|
||||
Promql(Result<Vec<PromqlSeriesDto>, String>),
|
||||
}
|
||||
|
||||
pub type EngineHandle = mpsc::Sender<EngineMessage>;
|
||||
@@ -486,6 +497,134 @@ fn handle_query(index: &BTreeMap<IndexKey, DataValue>, query: EngineQuery) -> En
|
||||
.collect();
|
||||
EngineResponse::BucketValues(values)
|
||||
}
|
||||
EngineQuery::Promql { query, start_ms, end_ms } => {
|
||||
let response = promql::parse_query(&query)
|
||||
.map(|parsed| evaluate_promql(index, &parsed, start_ms, end_ms));
|
||||
EngineResponse::Promql(response)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Coerces a bucket's stored `MetricPrimitive` into a plottable `f64` for
|
||||
/// `PromqlSeriesDto`:
|
||||
/// - `Number` uses its underlying numeric value.
|
||||
/// - `Timestamp` uses its millisecond value (arbitrary but at least meaningful/
|
||||
/// orderable, since there's no other sensible single number for a point in time).
|
||||
/// - `String` has no numeric reading at all, so it falls back to `1.0` — i.e. it is
|
||||
/// treated the same as the presence/occurrence marker `apply_metric_to_log` already
|
||||
/// stores for every bucket value today (ticket 003), meaning a PromQL series over a
|
||||
/// `String`-valued bucket becomes an occurrence-count series rather than being
|
||||
/// skipped. This keeps every declared metric queryable (matching the ticket's
|
||||
/// "documented fallback" requirement) rather than silently omitting non-numeric
|
||||
/// series.
|
||||
fn coerce_to_f64(value: &MetricPrimitive) -> f64 {
|
||||
match value {
|
||||
MetricPrimitive::Number(n) => match n {
|
||||
Number::Int(v) => *v as f64,
|
||||
Number::Float(v) => *v,
|
||||
},
|
||||
MetricPrimitive::Timestamp(ts) => ts.as_millis() as f64,
|
||||
MetricPrimitive::String(_) => 1.0,
|
||||
}
|
||||
}
|
||||
|
||||
/// True when every matcher in `matchers` is satisfied by `labels` (compared against
|
||||
/// each label value's `Display` form, same convention as `EngineQuery::BucketValues`'s
|
||||
/// `labels_filter`). Unmatched/extra labels on the bucket are ignored — a matcher list
|
||||
/// only needs to be a subset.
|
||||
fn matches_label_matchers(
|
||||
labels: &BTreeMap<String, MetricPrimitive>,
|
||||
matchers: &[LabelMatcher],
|
||||
) -> bool {
|
||||
matchers.iter().all(|matcher| {
|
||||
labels.get(&matcher.name).is_some_and(|value| value.to_string() == matcher.value)
|
||||
})
|
||||
}
|
||||
|
||||
/// Evaluates a parsed PromQL query against `index`, producing chart-ready series.
|
||||
///
|
||||
/// Baseline (no aggregation wrapper): one output series per distinct label
|
||||
/// combination that matches `parsed.metric_name` + `parsed.matchers`, with that
|
||||
/// combination's bucket values as `(timestamp_ms, value)` points (see
|
||||
/// `coerce_to_f64`), sorted by timestamp.
|
||||
///
|
||||
/// `sum()`/`avg()`: merges every matching series' points by exact millisecond
|
||||
/// timestamp (summing, or averaging, the values that land on the same timestamp
|
||||
/// across series) into a single output series with empty labels — the aggregation
|
||||
/// collapses the label dimension, same as PromQL's `sum by ()`/`avg by ()` default.
|
||||
///
|
||||
/// `rate()`: requires (and, per `promql::parse_query`, is only ever given) a range
|
||||
/// selector. This is a simplified, single-point-per-series rate rather than PromQL's
|
||||
/// true sliding-window-per-evaluation-step semantics: for each matching series, it
|
||||
/// takes the window `(last_point_ts - range, last_point_ts]` and divides the number
|
||||
/// of points falling in that window by the range's duration in seconds, producing one
|
||||
/// `(last_point_ts, rate)` point per series. Since bucket values are occurrence
|
||||
/// markers rather than cumulative counters (ticket 003), an occurrence-count-per-
|
||||
/// second reading is the meaningful analogue of PromQL's counter-increase rate here.
|
||||
fn evaluate_promql(
|
||||
index: &BTreeMap<IndexKey, DataValue>,
|
||||
parsed: &PromqlQuery,
|
||||
start_ms: Option<i64>,
|
||||
end_ms: Option<i64>,
|
||||
) -> Vec<PromqlSeriesDto> {
|
||||
let mut series_points: BTreeMap<BTreeMap<String, String>, Vec<(i64, f64)>> = BTreeMap::new();
|
||||
for (labels, (_, timestamp, value)) in bucket_values(index, &parsed.metric_name, None)
|
||||
.filter(|(labels, _)| matches_label_matchers(labels, &parsed.matchers))
|
||||
.filter(|(_, (_, timestamp, _))| {
|
||||
start_ms.is_none_or(|start| timestamp.as_millis() >= start)
|
||||
&& end_ms.is_none_or(|end| timestamp.as_millis() <= end)
|
||||
})
|
||||
{
|
||||
let display_labels: BTreeMap<String, String> =
|
||||
labels.iter().map(|(name, value)| (name.clone(), value.to_string())).collect();
|
||||
series_points
|
||||
.entry(display_labels)
|
||||
.or_default()
|
||||
.push((timestamp.as_millis(), coerce_to_f64(value)));
|
||||
}
|
||||
for points in series_points.values_mut() {
|
||||
points.sort_by_key(|(timestamp_ms, _)| *timestamp_ms);
|
||||
}
|
||||
|
||||
match parsed.agg {
|
||||
None => series_points
|
||||
.into_iter()
|
||||
.map(|(labels, points)| PromqlSeriesDto { labels, points })
|
||||
.collect(),
|
||||
Some(AggOp::Sum) | Some(AggOp::Avg) => {
|
||||
let mut grouped: BTreeMap<i64, Vec<f64>> = BTreeMap::new();
|
||||
for points in series_points.values() {
|
||||
for (timestamp_ms, value) in points {
|
||||
grouped.entry(*timestamp_ms).or_default().push(*value);
|
||||
}
|
||||
}
|
||||
let is_avg = parsed.agg == Some(AggOp::Avg);
|
||||
let points = grouped
|
||||
.into_iter()
|
||||
.map(|(timestamp_ms, values)| {
|
||||
let sum: f64 = values.iter().sum();
|
||||
let value = if is_avg { sum / values.len() as f64 } else { sum };
|
||||
(timestamp_ms, value)
|
||||
})
|
||||
.collect();
|
||||
vec![PromqlSeriesDto { labels: BTreeMap::new(), points }]
|
||||
}
|
||||
Some(AggOp::Rate) => {
|
||||
// Validated by `promql::parse_query`: `rate()` never parses without one.
|
||||
let range_ms = parsed.range.expect("rate() always carries a range").as_millis() as i64;
|
||||
let range_seconds = range_ms as f64 / 1000.0;
|
||||
series_points
|
||||
.into_iter()
|
||||
.filter_map(|(labels, points)| {
|
||||
let last_ts = points.last()?.0;
|
||||
let window_start = last_ts - range_ms;
|
||||
let count_in_window =
|
||||
points.iter().filter(|(ts, _)| *ts > window_start && *ts <= last_ts).count();
|
||||
let rate = count_in_window as f64 / range_seconds;
|
||||
Some(PromqlSeriesDto { labels, points: vec![(last_ts, rate)] })
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -835,4 +974,115 @@ mod tests {
|
||||
assert_eq!(bucket_values(&index, "requests", None).count(), 1);
|
||||
assert_eq!(bucket_values(&index, "durations", None).count(), 1);
|
||||
}
|
||||
|
||||
fn declare_requests_metric(index: &mut BTreeMap<IndexKey, DataValue>) {
|
||||
declare_metric(
|
||||
index,
|
||||
metric_request(
|
||||
"requests",
|
||||
r"request path=(?P<path>\S+)",
|
||||
vec![("path", "path", MetricPrimitiveKind::String)],
|
||||
),
|
||||
)
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn promql_query_selects_matching_label_combination() {
|
||||
let mut index = BTreeMap::new();
|
||||
declare_requests_metric(&mut index);
|
||||
ingest_log(&mut index, 0, "request path=/a");
|
||||
ingest_log(&mut index, 1, "request path=/b");
|
||||
ingest_log(&mut index, 2, "request path=/a");
|
||||
|
||||
let parsed = promql::parse_query(r#"requests{path="/a"}"#).unwrap();
|
||||
let series = evaluate_promql(&index, &parsed, None, None);
|
||||
|
||||
assert_eq!(series.len(), 1);
|
||||
assert_eq!(series[0].labels.get("path").map(String::as_str), Some("/a"));
|
||||
// Occurrence markers coerce to 1.0 (see `coerce_to_f64`); timestamps come from
|
||||
// `ingest_log`'s `sequence as millis` helper.
|
||||
assert_eq!(series[0].points, vec![(0, 1.0), (2, 1.0)]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn promql_query_with_no_matching_labels_returns_no_series() {
|
||||
let mut index = BTreeMap::new();
|
||||
declare_requests_metric(&mut index);
|
||||
ingest_log(&mut index, 0, "request path=/a");
|
||||
|
||||
let parsed = promql::parse_query(r#"requests{path="/nope"}"#).unwrap();
|
||||
let series = evaluate_promql(&index, &parsed, None, None);
|
||||
assert!(series.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn promql_sum_aggregates_across_label_combinations() {
|
||||
let mut index = BTreeMap::new();
|
||||
declare_requests_metric(&mut index);
|
||||
ingest_log(&mut index, 0, "request path=/a");
|
||||
ingest_log(&mut index, 0, "request path=/b");
|
||||
|
||||
let parsed = promql::parse_query("sum(requests)").unwrap();
|
||||
let series = evaluate_promql(&index, &parsed, None, None);
|
||||
|
||||
assert_eq!(series.len(), 1);
|
||||
assert!(series[0].labels.is_empty());
|
||||
assert_eq!(series[0].points, vec![(0, 2.0)]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn promql_range_bounds_filter_points_via_start_end_ms() {
|
||||
let mut index = BTreeMap::new();
|
||||
declare_requests_metric(&mut index);
|
||||
ingest_log(&mut index, 0, "request path=/a");
|
||||
ingest_log(&mut index, 5, "request path=/a");
|
||||
ingest_log(&mut index, 10, "request path=/a");
|
||||
|
||||
let parsed = promql::parse_query("requests").unwrap();
|
||||
let series = evaluate_promql(&index, &parsed, Some(1), Some(9));
|
||||
|
||||
assert_eq!(series.len(), 1);
|
||||
assert_eq!(series[0].points, vec![(5, 1.0)]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn handle_query_promql_rejects_malformed_query() {
|
||||
let index = BTreeMap::new();
|
||||
let response = handle_query(
|
||||
&index,
|
||||
EngineQuery::Promql {
|
||||
query: "not a valid promql query(".to_string(),
|
||||
start_ms: None,
|
||||
end_ms: None,
|
||||
},
|
||||
);
|
||||
match response {
|
||||
EngineResponse::Promql(Err(message)) => assert!(!message.is_empty()),
|
||||
_ => panic!("expected EngineResponse::Promql(Err(_))"),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn handle_query_promql_returns_series_for_valid_query() {
|
||||
let mut index = BTreeMap::new();
|
||||
declare_requests_metric(&mut index);
|
||||
ingest_log(&mut index, 0, "request path=/a");
|
||||
|
||||
let response = handle_query(
|
||||
&index,
|
||||
EngineQuery::Promql {
|
||||
query: r#"requests{path="/a"}"#.to_string(),
|
||||
start_ms: None,
|
||||
end_ms: None,
|
||||
},
|
||||
);
|
||||
match response {
|
||||
EngineResponse::Promql(Ok(series)) => {
|
||||
assert_eq!(series.len(), 1);
|
||||
assert_eq!(series[0].points, vec![(0, 1.0)]);
|
||||
}
|
||||
_ => panic!("expected EngineResponse::Promql(Ok(_))"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,6 +8,7 @@ mod index_key;
|
||||
mod ingest;
|
||||
mod metric_primitive;
|
||||
mod profile;
|
||||
mod promql;
|
||||
mod settings;
|
||||
mod timestamp;
|
||||
|
||||
|
||||
+369
@@ -0,0 +1,369 @@
|
||||
//! Hand-rolled parser for a small PromQL subset (ticket 013).
|
||||
//!
|
||||
//! Design decision: a crates.io PromQL parser (e.g. `promql-parser`) was considered
|
||||
//! but rejected — the required subset here is tiny (metric name + label matchers,
|
||||
//! plus an optional `[5m]` range and a single top-level `sum()`/`avg()`/`rate()`
|
||||
//! wrapper), while a full PromQL parser brings a large, largely-unused AST plus an
|
||||
//! extra maintenance dependency. Mirroring `filter_parser.rs`'s approach (a small,
|
||||
//! engine-independent parser module) is simpler and easier to control/extend, and
|
||||
//! keeps parsing fully decoupled from the engine's index — this module knows nothing
|
||||
//! about `IndexKey`/`DataValue`, only `PromqlQuery`'s own types below.
|
||||
//!
|
||||
//! ## Supported grammar
|
||||
//!
|
||||
//! ```text
|
||||
//! query := aggregation | vector_selector
|
||||
//! aggregation := agg_op "(" vector_selector ")"
|
||||
//! agg_op := "sum" | "avg" | "rate"
|
||||
//! vector_selector := metric_name label_matchers? range_selector?
|
||||
//! metric_name := [a-zA-Z_][a-zA-Z0-9_]*
|
||||
//! label_matchers := "{" label_matcher ("," label_matcher)* "}"
|
||||
//! label_matcher := label_name "=" quoted_string
|
||||
//! label_name := [a-zA-Z_][a-zA-Z0-9_]*
|
||||
//! quoted_string := '"' (any char except '"' or '\')* '"'
|
||||
//! range_selector := "[" digits duration_unit "]"
|
||||
//! duration_unit := "s" | "m" | "h" | "d"
|
||||
//! ```
|
||||
//!
|
||||
//! Only exact-match label matchers (`=`) are supported — PromQL's `!=`, `=~`, `!~`
|
||||
//! are out of scope for this ticket's required subset. `rate()` requires its inner
|
||||
//! vector selector to carry a range selector (matching real PromQL), and is rejected
|
||||
//! at parse time otherwise.
|
||||
|
||||
use std::time::Duration;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum AggOp {
|
||||
Sum,
|
||||
Avg,
|
||||
Rate,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct LabelMatcher {
|
||||
pub name: String,
|
||||
pub value: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct PromqlQuery {
|
||||
pub agg: Option<AggOp>,
|
||||
pub metric_name: String,
|
||||
pub matchers: Vec<LabelMatcher>,
|
||||
pub range: Option<Duration>,
|
||||
}
|
||||
|
||||
/// Parses a PromQL query string per the grammar documented above. Returns a
|
||||
/// human-readable error message (suitable for surfacing directly to an API caller)
|
||||
/// on any malformed input.
|
||||
pub fn parse_query(input: &str) -> Result<PromqlQuery, String> {
|
||||
let mut parser = Parser::new(input);
|
||||
let query = parser.parse_query()?;
|
||||
parser.skip_whitespace();
|
||||
if !parser.is_at_end() {
|
||||
return Err(format!("unexpected trailing input: '{}'", parser.remaining()));
|
||||
}
|
||||
if query.agg == Some(AggOp::Rate) && query.range.is_none() {
|
||||
return Err("rate() requires a range selector, e.g. rate(my_metric[5m])".to_string());
|
||||
}
|
||||
Ok(query)
|
||||
}
|
||||
|
||||
struct Parser<'a> {
|
||||
input: &'a str,
|
||||
pos: usize,
|
||||
}
|
||||
|
||||
impl<'a> Parser<'a> {
|
||||
fn new(input: &'a str) -> Self {
|
||||
Parser { input, pos: 0 }
|
||||
}
|
||||
|
||||
fn remaining(&self) -> &'a str {
|
||||
&self.input[self.pos..]
|
||||
}
|
||||
|
||||
fn is_at_end(&self) -> bool {
|
||||
self.pos >= self.input.len()
|
||||
}
|
||||
|
||||
fn skip_whitespace(&mut self) {
|
||||
while self.remaining().starts_with(|c: char| c.is_whitespace()) {
|
||||
self.pos += 1;
|
||||
}
|
||||
}
|
||||
|
||||
fn peek(&self) -> Option<char> {
|
||||
self.remaining().chars().next()
|
||||
}
|
||||
|
||||
fn expect_char(&mut self, expected: char) -> Result<(), String> {
|
||||
self.skip_whitespace();
|
||||
match self.peek() {
|
||||
Some(c) if c == expected => {
|
||||
self.pos += c.len_utf8();
|
||||
Ok(())
|
||||
}
|
||||
Some(c) => Err(format!("expected '{expected}', found '{c}'")),
|
||||
None => Err(format!("expected '{expected}', found end of input")),
|
||||
}
|
||||
}
|
||||
|
||||
/// `[a-zA-Z_][a-zA-Z0-9_]*`, used for both metric names and label names.
|
||||
fn parse_identifier(&mut self) -> Result<String, String> {
|
||||
self.skip_whitespace();
|
||||
let rest = self.remaining();
|
||||
let mut chars = rest.char_indices();
|
||||
match chars.next() {
|
||||
Some((_, c)) if c.is_ascii_alphabetic() || c == '_' => {}
|
||||
Some((_, c)) => return Err(format!("expected an identifier, found '{c}'")),
|
||||
None => return Err("expected an identifier, found end of input".to_string()),
|
||||
}
|
||||
let end = chars
|
||||
.find(|(_, c)| !(c.is_ascii_alphanumeric() || *c == '_'))
|
||||
.map(|(idx, _)| idx)
|
||||
.unwrap_or(rest.len());
|
||||
let ident = &rest[..end];
|
||||
self.pos += end;
|
||||
Ok(ident.to_string())
|
||||
}
|
||||
|
||||
fn parse_quoted_string(&mut self) -> Result<String, String> {
|
||||
self.expect_char('"')?;
|
||||
let rest = self.remaining();
|
||||
let end = rest.find('"').ok_or("unterminated string literal (missing closing '\"')")?;
|
||||
let value = &rest[..end];
|
||||
if value.contains('\\') {
|
||||
return Err("escape sequences in label values are not supported".to_string());
|
||||
}
|
||||
self.pos += end;
|
||||
self.expect_char('"')?;
|
||||
Ok(value.to_string())
|
||||
}
|
||||
|
||||
fn parse_label_matcher(&mut self) -> Result<LabelMatcher, String> {
|
||||
let name = self.parse_identifier()?;
|
||||
self.expect_char('=')?;
|
||||
self.skip_whitespace();
|
||||
if self.peek() == Some('~') {
|
||||
return Err("regex label matchers ('=~') are not supported, only '='".to_string());
|
||||
}
|
||||
let value = self.parse_quoted_string()?;
|
||||
Ok(LabelMatcher { name, value })
|
||||
}
|
||||
|
||||
fn parse_label_matchers(&mut self) -> Result<Vec<LabelMatcher>, String> {
|
||||
self.skip_whitespace();
|
||||
if self.peek() != Some('{') {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
self.expect_char('{')?;
|
||||
let mut matchers = Vec::new();
|
||||
self.skip_whitespace();
|
||||
if self.peek() == Some('}') {
|
||||
self.expect_char('}')?;
|
||||
return Ok(matchers);
|
||||
}
|
||||
loop {
|
||||
matchers.push(self.parse_label_matcher()?);
|
||||
self.skip_whitespace();
|
||||
match self.peek() {
|
||||
Some(',') => {
|
||||
self.pos += 1;
|
||||
}
|
||||
Some('}') => break,
|
||||
Some(c) => return Err(format!("expected ',' or '}}', found '{c}'")),
|
||||
None => return Err("unterminated label matcher list (missing '}')".to_string()),
|
||||
}
|
||||
}
|
||||
self.expect_char('}')?;
|
||||
Ok(matchers)
|
||||
}
|
||||
|
||||
/// `[<digits><unit>]`, e.g. `[5m]`.
|
||||
fn parse_range_selector(&mut self) -> Result<Option<Duration>, String> {
|
||||
self.skip_whitespace();
|
||||
if self.peek() != Some('[') {
|
||||
return Ok(None);
|
||||
}
|
||||
self.expect_char('[')?;
|
||||
let rest = self.remaining();
|
||||
let digits_end = rest
|
||||
.find(|c: char| !c.is_ascii_digit())
|
||||
.ok_or("unterminated range selector (missing unit and ']')")?;
|
||||
if digits_end == 0 {
|
||||
return Err("range selector must start with a number, e.g. [5m]".to_string());
|
||||
}
|
||||
let digits: i64 = rest[..digits_end]
|
||||
.parse()
|
||||
.map_err(|_| "range selector duration is not a valid number".to_string())?;
|
||||
self.pos += digits_end;
|
||||
|
||||
let unit = self.peek().ok_or("range selector is missing a duration unit")?;
|
||||
let seconds_per_unit: i64 = match unit {
|
||||
's' => 1,
|
||||
'm' => 60,
|
||||
'h' => 60 * 60,
|
||||
'd' => 24 * 60 * 60,
|
||||
other => {
|
||||
return Err(format!(
|
||||
"unknown duration unit '{other}' (expected one of s, m, h, d)"
|
||||
));
|
||||
}
|
||||
};
|
||||
self.pos += unit.len_utf8();
|
||||
self.expect_char(']')?;
|
||||
Ok(Some(Duration::from_secs((digits * seconds_per_unit).max(0) as u64)))
|
||||
}
|
||||
|
||||
fn parse_vector_selector(&mut self) -> Result<PromqlQuery, String> {
|
||||
let metric_name = self.parse_identifier()?;
|
||||
let matchers = self.parse_label_matchers()?;
|
||||
let range = self.parse_range_selector()?;
|
||||
Ok(PromqlQuery { agg: None, metric_name, matchers, range })
|
||||
}
|
||||
|
||||
fn parse_query(&mut self) -> Result<PromqlQuery, String> {
|
||||
self.skip_whitespace();
|
||||
let checkpoint = self.pos;
|
||||
let ident = self.parse_identifier()?;
|
||||
let agg = match ident.as_str() {
|
||||
"sum" => Some(AggOp::Sum),
|
||||
"avg" => Some(AggOp::Avg),
|
||||
"rate" => Some(AggOp::Rate),
|
||||
_ => None,
|
||||
};
|
||||
self.skip_whitespace();
|
||||
if agg.is_some() && self.peek() == Some('(') {
|
||||
self.expect_char('(')?;
|
||||
let mut inner = self.parse_vector_selector()?;
|
||||
self.expect_char(')')?;
|
||||
inner.agg = agg;
|
||||
Ok(inner)
|
||||
} else {
|
||||
// Not (or not followed by) an aggregation call — rewind and parse the
|
||||
// whole thing as a plain vector selector (covers metric names that
|
||||
// happen to collide with an agg_op keyword, e.g. a metric named `rate`
|
||||
// used without a call).
|
||||
self.pos = checkpoint;
|
||||
self.parse_vector_selector()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn parses_bare_metric_name() {
|
||||
let query = parse_query("requests").unwrap();
|
||||
assert_eq!(query.agg, None);
|
||||
assert_eq!(query.metric_name, "requests");
|
||||
assert!(query.matchers.is_empty());
|
||||
assert_eq!(query.range, None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_metric_with_single_label_matcher() {
|
||||
let query = parse_query(r#"requests{path="/a"}"#).unwrap();
|
||||
assert_eq!(query.metric_name, "requests");
|
||||
assert_eq!(
|
||||
query.matchers,
|
||||
vec![LabelMatcher { name: "path".to_string(), value: "/a".to_string() }]
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_metric_with_multiple_label_matchers() {
|
||||
let query = parse_query(r#"requests{path="/a", method="GET"}"#).unwrap();
|
||||
assert_eq!(query.matchers.len(), 2);
|
||||
assert_eq!(query.matchers[0].name, "path");
|
||||
assert_eq!(query.matchers[1].name, "method");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_range_selector() {
|
||||
let query = parse_query("requests[5m]").unwrap();
|
||||
assert_eq!(query.range, Some(Duration::from_secs(300)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_label_matchers_and_range_together() {
|
||||
let query = parse_query(r#"requests{path="/a"}[1h]"#).unwrap();
|
||||
assert_eq!(query.matchers.len(), 1);
|
||||
assert_eq!(query.range, Some(Duration::from_secs(3600)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_sum_aggregation() {
|
||||
let query = parse_query(r#"sum(requests{path="/a"})"#).unwrap();
|
||||
assert_eq!(query.agg, Some(AggOp::Sum));
|
||||
assert_eq!(query.metric_name, "requests");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_avg_aggregation() {
|
||||
let query = parse_query("avg(requests)").unwrap();
|
||||
assert_eq!(query.agg, Some(AggOp::Avg));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn parses_rate_with_range() {
|
||||
let query = parse_query("rate(requests[5m])").unwrap();
|
||||
assert_eq!(query.agg, Some(AggOp::Rate));
|
||||
assert_eq!(query.range, Some(Duration::from_secs(300)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_rate_without_range() {
|
||||
let err = parse_query("rate(requests)").unwrap_err();
|
||||
assert!(err.contains("range selector"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_empty_input() {
|
||||
assert!(parse_query("").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unclosed_brace() {
|
||||
assert!(parse_query(r#"requests{path="/a""#).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unclosed_bracket() {
|
||||
assert!(parse_query("requests[5m").is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unknown_aggregation() {
|
||||
// `count` isn't a supported agg_op, so this parses as a bare metric named
|
||||
// `count`, then trips on the unexpected trailing `(...)`.
|
||||
let err = parse_query("count(requests)").unwrap_err();
|
||||
assert!(err.contains("unexpected trailing input"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_regex_label_matcher() {
|
||||
let err = parse_query(r#"requests{path=~"/a"}"#).unwrap_err();
|
||||
assert!(err.contains("regex label matchers"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_missing_metric_name() {
|
||||
assert!(parse_query(r#"{path="/a"}"#).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_unknown_duration_unit() {
|
||||
let err = parse_query("requests[5x]").unwrap_err();
|
||||
assert!(err.contains("duration unit"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_trailing_garbage() {
|
||||
let err = parse_query("requests extra").unwrap_err();
|
||||
assert!(err.contains("unexpected trailing input"));
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user