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.
This commit is contained in:
Yevhen Odynets
2026-09-30 09:27:33 +03:00
parent 332d143f1f
commit 346369ca11
35 changed files with 1653 additions and 53 deletions
+3 -3
View File
@@ -8,7 +8,7 @@ import (
"github.com/spf13/viper"
)
func (h *Handler) Console() string {
func (h *Handler) Console() (string, error) {
viper.SetDefault("env", "devel")
cmd := viper.GetString("create")
cmdList := viper.Sub("console.cmd")
@@ -16,11 +16,11 @@ func (h *Handler) Console() string {
if !slices.Contains(allowCreate, cmd) {
fmt.Printf("%s Not allowed command %s used\n", aurora.BgMagenta("[WARN]"), aurora.Magenta(cmd))
return ""
return "", fmt.Errorf("command %q is not allowed", cmd)
}
fmt.Printf("%v\n", slices.Contains(allowCreate, cmd))
return viper.GetString("env")
return viper.GetString("env"), nil
}
+18 -10
View File
@@ -1,7 +1,7 @@
package handler
import (
"log" // Додано імпорт log
"fmt"
"github.com/spf13/viper"
@@ -10,7 +10,9 @@ import (
)
// consoleCommandHandler визначає тип для функцій-обробників консольних команд.
type consoleCommandHandler func() string
// The error it returns decides the process exit code, so cron can tell a failed
// run from a successful one.
type consoleCommandHandler func() (string, error)
type Handler struct {
services *service.Service
@@ -29,24 +31,30 @@ func New(services *service.Service) *Handler {
"prescene": h.Prescene,
"rutracker": h.Rutracker,
"stb": h.STB,
"srrdb": h.Srrdb,
//"web": h.Web,
}
return h
}
func (h *Handler) InitConsole() string {
// InitConsole runs the command selected by --scope-enable. The text is returned
// even together with an error, so the caller can print what happened before it
// reports the failure.
func (h *Handler) InitConsole() (string, error) {
commandName := viper.GetString(constant.FlagScopeEnable)
if cmdFunc, ok := h.consoleCommands[commandName]; ok {
return commandName + " launched, " + cmdFunc() + "\n"
} else {
log.Printf("Error: unknown console command '%s'", commandName)
return "Error: unknown console command"
cmdFunc, ok := h.consoleCommands[commandName]
if !ok {
return "", fmt.Errorf("unknown console command %q", commandName)
}
result, err := cmdFunc()
return commandName + " launched, " + result + "\n", err
}
func (h *Handler) InitRoutes() string {
func (h *Handler) InitRoutes() (string, error) {
//TODO:
return "i am the web initiator"
return "i am the web initiator", nil
}
+3 -2
View File
@@ -12,13 +12,14 @@ import (
"git.kplus.net.ua/yevhen/resource-scraper/types/constant"
)
func (h *Handler) Info() string {
func (h *Handler) Info() (string, error) {
md5()
fmt.Printf("%s: %s; %s: %s\n",
aurora.Cyan("ENV"),
viper.GetString(constant.FlagEnv), aurora.Cyan("SCOPE"), viper.GetString(constant.FlagScopeEnable))
return "info"
return "info", nil
}
func md5() {
+2 -2
View File
@@ -1,5 +1,5 @@
package handler
func (h *Handler) MetalArchives() string {
return "MetalArchives................."
func (h *Handler) MetalArchives() (string, error) {
return "MetalArchives.................", nil
}
+6 -9
View File
@@ -2,7 +2,6 @@ package handler
import (
"fmt"
"log/slog"
"math"
"strconv"
"time"
@@ -12,7 +11,7 @@ import (
"git.kplus.net.ua/yevhen/resource-scraper/types/constant"
)
func (h *Handler) Prescene() string {
func (h *Handler) Prescene() (string, error) {
currMinute := time.Now().Minute()
levels := viper.GetInt(constant.CfgKeyLevelsToScrape)
initPage := strconv.Itoa(currMinute/(60/levels) + 1)
@@ -30,17 +29,15 @@ func (h *Handler) Prescene() string {
pagesToScrape = append(pagesToScrape, strconv.Itoa(page))
}
_, err := h.services.Prescene.GetSrrDb()
if err != nil {
slog.Error("error occurred while getting page: ", "err", err.Error())
if _, err := h.services.Prescene.GetSrrDb(); err != nil {
return "ps", fmt.Errorf("getting srr db: %w", err)
}
_, err = h.services.Prescene.GetPage(pagesToScrape)
if err != nil {
slog.Error("error occurred while getting page: ", "err", err.Error())
if _, err := h.services.Prescene.GetPage(pagesToScrape); err != nil {
return "ps", fmt.Errorf("getting page: %w", err)
}
fmt.Printf("%+v\n", pagesToScrape)
return "ps"
return "ps", nil
}
+4 -6
View File
@@ -2,20 +2,18 @@ package handler
import (
"fmt"
"log/slog"
"time"
"github.com/spf13/viper"
)
func (h *Handler) Rutracker() string {
func (h *Handler) Rutracker() (string, error) {
key := fmt.Sprintf("topic.%v", time.Now().Hour())
topics := viper.GetStringSlice(key)
_, err := h.services.Rutracker.GetTopic(topics)
if err != nil {
slog.Error("error occurred while getting topic: ", "err", err.Error())
if _, err := h.services.Rutracker.GetTopic(topics); err != nil {
return "rt", fmt.Errorf("getting topic: %w", err)
}
return "rt"
return "rt", nil
}
+22
View File
@@ -0,0 +1,22 @@
package handler
import (
"errors"
"fmt"
"github.com/spf13/viper"
"git.kplus.net.ua/yevhen/resource-scraper/types/constant"
)
// Srrdb runs one srrDB search pass over the raw path given by --single-uri.
func (h *Handler) Srrdb() (string, error) {
uri := viper.GetString(constant.FlagSingleUri)
if uri == "" {
return "srrdb", errors.New("no search path, pass --single-uri")
}
stored, err := h.services.Srrdb.Search(uri)
return fmt.Sprintf("%d records\n", stored), err
}
+3 -5
View File
@@ -3,20 +3,18 @@ package handler
import (
"errors"
"fmt"
"log/slog"
"github.com/spf13/viper"
"git.kplus.net.ua/yevhen/resource-scraper/types/constant"
)
func (h *Handler) STB() string {
func (h *Handler) STB() (string, error) {
endpoint := fmt.Sprintf("%s.%s", constant.ScopeShareTheBrutality, constant.CfgKeyEndpoint)
endpoint = viper.GetString(endpoint)
if endpoint == "" {
slog.Error("getting endpoint from config", "err", errors.New("no endpoint provided"))
return "stb"
return "stb", errors.New("no endpoint provided")
}
es, ms := h.services.ShareTheBrutality.GetMail(endpoint)
@@ -32,5 +30,5 @@ func (h *Handler) STB() string {
slog.Error("error occurred while getting topic: ", "err", err)
}*/
return fmt.Sprintf("Added %d records\n", len(es))
return fmt.Sprintf("Added %d records\n", len(es)), nil
}