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.
130 lines
3.2 KiB
Go
130 lines
3.2 KiB
Go
package metadata
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"net/http"
|
|
"net/url"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
)
|
|
|
|
// GoogleBooks is a fallback catalogue for books. No API key for low volume.
|
|
type GoogleBooks struct {
|
|
Client *http.Client
|
|
}
|
|
|
|
// NewGoogleBooks builds the provider with a bounded HTTP client.
|
|
func NewGoogleBooks() *GoogleBooks {
|
|
return &GoogleBooks{Client: &http.Client{Timeout: 10 * time.Second}}
|
|
}
|
|
|
|
func (p *GoogleBooks) Name() string { return "googlebooks" }
|
|
|
|
func (p *GoogleBooks) Kinds() []string { return []string{"ebooks"} }
|
|
|
|
type gbResponse struct {
|
|
Items []struct {
|
|
ID string `json:"id"`
|
|
VolumeInfo struct {
|
|
Title string `json:"title"`
|
|
Authors []string `json:"authors"`
|
|
Publisher string `json:"publisher"`
|
|
Language string `json:"language"`
|
|
Description string `json:"description"`
|
|
PublishedDate string `json:"publishedDate"`
|
|
ImageLinks struct {
|
|
Thumbnail string `json:"thumbnail"`
|
|
} `json:"imageLinks"`
|
|
IndustryIdentifiers []struct {
|
|
Type string `json:"type"`
|
|
Identifier string `json:"identifier"`
|
|
} `json:"industryIdentifiers"`
|
|
} `json:"volumeInfo"`
|
|
} `json:"items"`
|
|
}
|
|
|
|
func (p *GoogleBooks) Search(ctx context.Context, q Query) ([]Candidate, error) {
|
|
var terms []string
|
|
if q.ISBN != "" {
|
|
terms = append(terms, "isbn:"+q.ISBN)
|
|
} else {
|
|
if q.Title != "" {
|
|
terms = append(terms, "intitle:"+q.Title)
|
|
}
|
|
if q.Author != "" {
|
|
terms = append(terms, "inauthor:"+q.Author)
|
|
}
|
|
}
|
|
if len(terms) == 0 {
|
|
return nil, nil
|
|
}
|
|
|
|
params := url.Values{}
|
|
params.Set("q", strings.Join(terms, "+"))
|
|
params.Set("maxResults", "5")
|
|
params.Set("printType", "books")
|
|
|
|
endpoint := "https://www.googleapis.com/books/v1/volumes?" + params.Encode()
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
resp, err := p.Client.Do(req)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("googlebooks: %w", err)
|
|
}
|
|
defer resp.Body.Close()
|
|
if resp.StatusCode != http.StatusOK {
|
|
return nil, fmt.Errorf("googlebooks: status %d", resp.StatusCode)
|
|
}
|
|
|
|
var parsed gbResponse
|
|
if err := json.NewDecoder(resp.Body).Decode(&parsed); err != nil {
|
|
return nil, fmt.Errorf("googlebooks: decode: %w", err)
|
|
}
|
|
|
|
out := make([]Candidate, 0, len(parsed.Items))
|
|
for _, item := range parsed.Items {
|
|
v := item.VolumeInfo
|
|
if v.Title == "" {
|
|
continue
|
|
}
|
|
c := Candidate{
|
|
Provider: p.Name(),
|
|
ExternalID: item.ID,
|
|
Title: v.Title,
|
|
Authors: v.Authors,
|
|
Publisher: v.Publisher,
|
|
Language: v.Language,
|
|
Description: v.Description,
|
|
Year: parseYear(v.PublishedDate),
|
|
}
|
|
// Google returns http:// thumbnail URLs; https avoids mixed content.
|
|
if v.ImageLinks.Thumbnail != "" {
|
|
c.CoverURL = strings.Replace(v.ImageLinks.Thumbnail, "http://", "https://", 1)
|
|
}
|
|
for _, id := range v.IndustryIdentifiers {
|
|
if id.Type == "ISBN_13" || c.ISBN == "" {
|
|
c.ISBN = id.Identifier
|
|
}
|
|
}
|
|
out = append(out, c)
|
|
}
|
|
return out, nil
|
|
}
|
|
|
|
// parseYear extracts a leading 4-digit year from dates like "2021-05-04".
|
|
func parseYear(date string) int {
|
|
if len(date) < 4 {
|
|
return 0
|
|
}
|
|
n, err := strconv.Atoi(date[:4])
|
|
if err != nil {
|
|
return 0
|
|
}
|
|
return n
|
|
}
|