Files
Yevhen Odynets 346369ca11 srrdb: harvest the srrDB search API into a separate SQLite database
New scope reading the API instead of scraping HTML: one search path per run,
passed raw through --single-uri, and the answer stored as-is into its own
SQLite file created from the embedded schema.

Command line: --single-uri carries the path after /v1/search/
(category:flac/date:today/page:1) and must name a category; --sleep sets the
pause between pages, with the config value as fallback. A day named on the
command line is always fetched again and its dump rewritten, so cron can
refresh today hourly and yesterday daily.

Date placeholders: date:auto walks backwards to the newest day in
[srrdb.floor..yesterday] that has no dump yet, closing holes instead of
declaring the archive covered. date:today, date:yesterday and date:tomorrow
stand for the neighbouring days. Today is never taken by the walk, because a
day still being filled would be frozen by its own dump after the first run.

Dumps are the cursor as well as the record, so a missing dump directory is an
error instead of "nothing harvested yet": a renamed, unmounted or mistyped
directory must not send the run silently back to the beginning. An empty day is
a normal result and is remembered as harvested; API warnings never are, and
they reach the exit code.

Writes go through one transaction, so a day lands completely or not at all.
group and category come from the release line and the search path; status, nfo,
content and synced_at stay NULL. srrdb.log.jsonl records one line per finished
run, srrdb.error_log.jsonl keeps failures and API warnings apart by a kind
field.

Also: the console command contract returns (string, error), so a failing scope
reaches the process exit code and cron can tell a failed run from a successful
one. config/scope/srrdb.yaml is untracked because its paths differ per host.
modernc.org/sqlite replaces the archived libsql client, which only ever talked
to a server. pkg/repository/srrdb.go is split by responsibility and covered by
table-driven tests.
2026-09-30 09:27:33 +03:00

78 lines
2.0 KiB
Go

package repository
import (
"encoding/json"
"log/slog"
"os"
"strings"
"time"
"github.com/spf13/viper"
)
// srrdbAppendJSONL adds one object as a single line to a .jsonl log. A missing
// or failing log never changes the outcome of the run itself.
func srrdbAppendJSONL(key string, record map[string]any) {
path := viper.GetString(key)
if path == "" {
return
}
data, err := json.Marshal(record)
if err != nil {
slog.Error("encode srrdb log record", "key", key, "err", err)
return
}
file, err := os.OpenFile(path, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0o644)
if err != nil {
slog.Error("open srrdb log", "path", path, "err", err)
return
}
defer func() {
if cerr := file.Close(); cerr != nil {
slog.Error("close srrdb log", "path", path, "err", cerr)
}
}()
if _, err := file.Write(append(data, '\n')); err != nil {
slog.Error("write srrdb log", "path", path, "err", err)
}
}
// srrdbLogStatus appends the outcome of one finished run to srrdb.log.
func srrdbLogStatus(uri string, stored, reported int) {
srrdbAppendJSONL("srrdb.log", map[string]any{
"time": time.Now().Format(srrdbTimestamp),
"uri": uri,
"stored": stored,
"reported": reported,
})
}
// srrdbLogWarning records warnings reported by the API. They share the failure
// file but carry their own kind, because the endpoint answers an unrecognized
// keyword with HTTP 200 and an empty result set: the text is the only trace of a
// bad path, and it must stay distinguishable from a real breakdown.
func srrdbLogWarning(uri string, warnings []string) {
srrdbAppendJSONL("srrdb.error_log", map[string]any{
"kind": "warning",
"time": time.Now().Format(srrdbTimestamp),
"uri": uri,
"warnings": strings.Join(warnings, "; "),
})
}
// srrdbLogError appends one failure to srrdb.error_log.
func srrdbLogError(uri string, err error) {
srrdbAppendJSONL("srrdb.error_log", map[string]any{
"kind": "error",
"time": time.Now().Format(srrdbTimestamp),
"uri": uri,
"error": err.Error(),
})
}