feat: language stream graph on dashboard

Full-stack feature showing programming languages by commit activity
as a stream graph on the dashboard.

Backend:
- migration: repo_languages table (source, repo, language, bytes, color)
- worker: fetch language breakdowns via GitHub GraphQL (batched,
  20 repos/request) and Gitea REST API during poll cycles
- API: GET /v1/languages/daily (daily commit counts per language),
  GET /v1/languages/repos (all stored repo language data)
- fix timezone bug in daily_counts and language_daily_counts: the
  PostgreSQL server timezone (Europe/Sofia, UTC+3) shifted day
  boundaries, miscounting events near midnight. Now uses explicit
  UTC boundaries in generate_series JOINs.
- use per-source CASE for repo name extraction in language query
  to match gitea payload structure (repo.full_name vs repo.name)
- Gitea languages use GitHub colors via COALESCE fallback

Frontend:
- LanguageStreamGraph component: pure SVG stream graph, weekly
  buckets, centered baseline, top 8 languages + Other, GitHub
  canonical language colors, legend with color dots
- DashPage/ProjectPage: fetch repo languages once via new endpoint
  instead of per-repo forge proxy calls (eliminates 200+ GitHub
  API calls and 403 rate limit errors)
- removed fetchLanguages forge proxy wrapper (dead code)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-06 06:27:59 +03:00
parent c66aaeb268
commit ee93429317
12 changed files with 604 additions and 63 deletions

View File

@@ -9,12 +9,13 @@
//! Each item carries a self-contained payload — including the event-emitting
//! host — so the reshape layer can construct URLs without needing config.
use std::collections::HashSet;
use std::sync::Arc;
use async_trait::async_trait;
use chrono::{DateTime, Utc};
use moments_core::{EventSource, EventWriter, PollerStateStore, SourceError};
use moments_entities::{Event, Source};
use moments_entities::{Event, RepoLanguage, Source};
use reqwest::{Client, header};
use serde_json::Value;
use tracing::debug;
@@ -126,17 +127,19 @@ impl GiteaSource {
/// for org feeds which contain all members' activity).
///
/// `base_url` should contain everything except the `&page=N` suffix.
/// Returns (ingested_count, set_of_repo_full_names).
async fn poll_feed(
&self,
state_key: &str,
base_url: &str,
filter_user: bool,
) -> Result<usize, SourceError> {
) -> Result<(usize, HashSet<String>), SourceError> {
let prior = self.state.load(state_key).await?;
let first_run = prior.is_none();
let max_pages = if first_run { MAX_BACKFILL_PAGES } else { 1 };
let mut total = 0usize;
let mut repos = HashSet::new();
for page in 1..=max_pages {
let url = format!("{base_url}&page={page}");
let req = self.apply_headers(self.client.get(&url));
@@ -155,6 +158,17 @@ impl GiteaSource {
break;
}
// Collect repo names from feed items
for item in &items {
if let Some(name) = item
.get("repo")
.and_then(|r| r.get("full_name"))
.and_then(Value::as_str)
{
repos.insert(name.to_string());
}
}
let events: Vec<Event> = items
.iter()
.filter(|it| {
@@ -177,6 +191,44 @@ impl GiteaSource {
}
self.state.touch(state_key).await?;
Ok((total, repos))
}
/// Fetch language breakdowns for the given repos via the Gitea REST API.
async fn fetch_languages(&self, repos: &HashSet<String>) -> Result<usize, SourceError> {
let mut total = 0usize;
for repo in repos {
let url = format!(
"https://{}/api/v1/repos/{}/languages",
self.config.host, repo
);
let req = self.apply_headers(self.client.get(&url));
let resp = req
.send()
.await
.map_err(|e| SourceError::Http(e.to_string()))?;
if !resp.status().is_success() {
tracing::warn!(repo = %repo, status = %resp.status(), "gitea language fetch failed; skipping");
continue;
}
let lang_map: std::collections::HashMap<String, i64> = resp
.json()
.await
.map_err(|e| SourceError::Parse(e.to_string()))?;
let languages: Vec<RepoLanguage> = lang_map
.into_iter()
.map(|(language, bytes)| RepoLanguage {
source: Source::Gitea,
repo: repo.clone(),
language,
bytes,
color: None, // Gitea doesn't return colors
})
.collect();
total += self.writer.upsert_repo_languages(&languages).await?;
}
debug!(total, repos = repos.len(), "gitea repo languages updated");
Ok(total)
}
}
@@ -188,9 +240,12 @@ impl EventSource for GiteaSource {
}
async fn poll(&self) -> Result<usize, SourceError> {
let mut all_repos = HashSet::new();
// Poll user's own activity feed (existing behavior).
let user_url = self.user_feed_base_url();
let mut total = self.poll_feed(SOURCE_NAME, &user_url, false).await?;
let (mut total, repos) = self.poll_feed(SOURCE_NAME, &user_url, false).await?;
all_repos.extend(repos);
// Discover orgs and poll each org's activity feed, filtering for
// events performed by this user.
@@ -199,13 +254,20 @@ impl EventSource for GiteaSource {
let state_key = format!("gitea:org:{org}");
let org_url = self.org_feed_base_url(org);
match self.poll_feed(&state_key, &org_url, true).await {
Ok(n) => total += n,
Ok((n, repos)) => {
total += n;
all_repos.extend(repos);
}
Err(e) => {
tracing::warn!(org = %org, error = %e, "failed to poll org feed");
}
}
}
if let Err(e) = self.fetch_languages(&all_repos).await {
tracing::warn!(error = %e, "gitea language fetch failed; continuing");
}
debug!(ingested = total, orgs = orgs.len(), "gitea poll complete");
Ok(total)
}