df740d3e1a
- jobs: a table-backed queue in the same SQLite file. No Redis, no second process, included in the same backup. claim() is a single UPDATE...RETURNING so a job cannot run twice even with several workers. Failures back off exponentially; a missing handler fails permanently rather than retrying a bug. - metadata: Provider interface plus Open Library and Google Books (both keyless). The enricher tries providers in registration order, falls back on empty, and continues past a provider error. - migration 0004: metadata_fetch records the attempt, not just the match, so a rescan does not re-hammer a rate-limited API for an item that will never match. Errors are always retried; ok/notfound are cached for 30 days. - enrichment writes provider_ids, updates title/year, links authors through people/item_people, and downloads the cover as an asset. The cover download runs outside the transaction: a slow image host must not hold a write lock. - endpoints: queue enrichment per library, and inspect an item's matches. - web: Enrich button per library. Verified live against Open Library: "The Hobbit" matched /works/OL27482W, title and year 1937 written, a 301x500 JPEG cover downloaded and served.
114 lines
2.9 KiB
Go
114 lines
2.9 KiB
Go
package metadata
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"net/url"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// OpenLibrary matches books by title and author. No API key, no registration.
|
|
type OpenLibrary struct {
|
|
Client *http.Client
|
|
}
|
|
|
|
// NewOpenLibrary builds the provider with a bounded HTTP client.
|
|
func NewOpenLibrary() *OpenLibrary {
|
|
return &OpenLibrary{Client: &http.Client{Timeout: 10 * time.Second}}
|
|
}
|
|
|
|
func (p *OpenLibrary) Name() string { return "openlibrary" }
|
|
|
|
func (p *OpenLibrary) Kinds() []string { return []string{"ebooks", "audiobooks"} }
|
|
|
|
// olSearchResponse is the subset of the search API this provider reads.
|
|
type olSearchResponse struct {
|
|
Docs []struct {
|
|
Key string `json:"key"`
|
|
Title string `json:"title"`
|
|
AuthorName []string `json:"author_name"`
|
|
FirstPublish int `json:"first_publish_year"`
|
|
Publisher []string `json:"publisher"`
|
|
Language []string `json:"language"`
|
|
CoverID int `json:"cover_i"`
|
|
ISBN []string `json:"isbn"`
|
|
} `json:"docs"`
|
|
}
|
|
|
|
func (p *OpenLibrary) Search(ctx context.Context, q Query) ([]Candidate, error) {
|
|
params := url.Values{}
|
|
params.Set("limit", "5")
|
|
params.Set("fields", "key,title,author_name,first_publish_year,publisher,language,cover_i,isbn")
|
|
if q.ISBN != "" {
|
|
params.Set("isbn", q.ISBN)
|
|
} else {
|
|
if q.Title != "" {
|
|
params.Set("title", q.Title)
|
|
}
|
|
if q.Author != "" {
|
|
params.Set("author", q.Author)
|
|
}
|
|
}
|
|
if params.Get("isbn") == "" && params.Get("title") == "" {
|
|
return nil, nil
|
|
}
|
|
|
|
endpoint := "https://openlibrary.org/search.json?" + params.Encode()
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
// Open Library asks callers to identify themselves.
|
|
req.Header.Set("User-Agent", "Vellum/0.1 (self-hosted media server)")
|
|
|
|
resp, err := p.Client.Do(req)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("openlibrary: %w", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
return nil, fmt.Errorf("openlibrary: status %d", resp.StatusCode)
|
|
}
|
|
|
|
var parsed olSearchResponse
|
|
if err := json.NewDecoder(resp.Body).Decode(&parsed); err != nil {
|
|
return nil, fmt.Errorf("openlibrary: decode: %w", err)
|
|
}
|
|
|
|
out := make([]Candidate, 0, len(parsed.Docs))
|
|
for _, d := range parsed.Docs {
|
|
if d.Title == "" {
|
|
continue
|
|
}
|
|
c := Candidate{
|
|
Provider: p.Name(),
|
|
ExternalID: d.Key,
|
|
Title: d.Title,
|
|
Authors: d.AuthorName,
|
|
Year: d.FirstPublish,
|
|
Language: first(d.Language),
|
|
}
|
|
if len(d.Publisher) > 0 {
|
|
c.Publisher = d.Publisher[0]
|
|
}
|
|
if len(d.ISBN) > 0 {
|
|
c.ISBN = d.ISBN[0]
|
|
}
|
|
if d.CoverID > 0 {
|
|
c.CoverURL = "https://covers.openlibrary.org/b/id/" + strconv.Itoa(d.CoverID) + "-L.jpg"
|
|
}
|
|
out = append(out, c)
|
|
}
|
|
return out, nil
|
|
}
|
|
|
|
func first(s []string) string {
|
|
if len(s) == 0 {
|
|
return ""
|
|
}
|
|
return strings.TrimSpace(s[0])
|
|
}
|