feat: add license_short from Wikipedia license identifiermain

- Extract license.identifier (e.g. CC-BY-SA-4.0) into new
  license_short column
- Warn if a license array has more than 1 entry (none seen yet)
- Include license_short IS NULL in getExistingWikiArticles query

2 files changed, 8 insertions, 3 deletions

diff --git a/src/wikiarticle.go b/src/wikiarticle.go
index 09c2da8..19f612c 100644
--- a/src/wikiarticle.go
+++ b/src/wikiarticle.go
@@ -26,6 +26,7 @@ type wikiArticleEntry struct {
 	PosterURL    string
 	Synopsis     string
 	License      string
+	LicenseShort string
 	LicenseURL   string
 	NumAccolades int
 	People       []wikiPerson
@@ -100,8 +101,12 @@ func (a *App) queryWikiArticle(name string) (wikiArticleEntry, int, error) {
 	// license
 	if licList, ok := article["license"]; ok {
 		if arr, ok := licList.([]interface{}); ok && len(arr) > 0 {
+			if len(arr) > 1 {
+				logWarn("license array has %d entries, using first (article %s)", len(arr), name)
+			}
 			if lic, ok := arr[0].(map[string]interface{}); ok {
 				entry.License = fmt.Sprintf("%v", lic["name"])
+				entry.LicenseShort = fmt.Sprintf("%v", lic["identifier"])
 				entry.LicenseURL = fmt.Sprintf("%v", lic["url"])
 			}
 		}
diff --git a/src/wikidata.go b/src/wikidata.go
index 3101673..5175d52 100644
--- a/src/wikidata.go
+++ b/src/wikidata.go
@@ -125,7 +125,7 @@ func (a *App) getExistingWikiArticles() ([]existingWikiArticle, error) {
 		WHERE wiki_article IS NOT NULL
 		AND wiki_status_code != 404
 		AND (synopsis IS NULL OR description IS NULL OR year IS NULL
-			OR poster_url IS NULL OR license IS NULL OR license_url IS NULL OR num_accolades IS NULL OR has_people = 0)
+			OR poster_url IS NULL OR license IS NULL OR license_short IS NULL OR license_url IS NULL OR num_accolades IS NULL OR has_people = 0)
 	`)
 	if err != nil {
 		return nil, fmt.Errorf("query existing wiki articles: %w", err)
@@ -254,10 +254,10 @@ func (a *App) wikiDataConsumer(artCh <-chan wikiArticleFetch, done chan<- struct
 		if statusCode == 200 {
 			a.DB.Exec(`
 				UPDATE imdb SET synopsis = ?, description = ?, year = ?, poster_url = ?,
-					license = ?, license_url = ?, num_accolades = ?
+					license = ?, license_short = ?, license_url = ?, num_accolades = ?
 				WHERE imdb_id = ?`,
 				entry.Synopsis, entry.Description, entry.Year, entry.PosterURL,
-				entry.License, entry.LicenseURL, entry.NumAccolades, art.imdbID)
+				entry.License, entry.LicenseShort, entry.LicenseURL, entry.NumAccolades, art.imdbID)
 			updated++
 		}