feat: add -wiki-only flag to rerun only wiki data extraction

- fetchWikiArticlesData is standalone again (re-extracted from consumer)
- -wiki-only flag skips SPARQL pipeline, runs only wiki data fetch
- Default behavior: full pipeline (SPARQL + wiki data in parallel)

2 files changed, 46 insertions, 11 deletions

diff --git a/src/main.go b/src/main.go
index 272e4b6..cf1c74b 100644
--- a/src/main.go
+++ b/src/main.go
@@ -1,6 +1,7 @@
 package main
 
 import (
+	"flag"
 	"fmt"
 	"log"
 	"regexp"
@@ -164,6 +165,9 @@ func (a *App) extractImdbIDs() error {
 }
 
 func main() {
+	wikiOnly := flag.Bool("wiki-only", false, "only fetch wiki article data, skip SPARQL")
+	flag.Parse()
+
 	cfg, err := LoadConfig("config.json")
 	if err != nil {
 		log.Fatalf("failed to load config: %v", err)
@@ -183,19 +187,25 @@ func main() {
 	}
 	defer app.DB.Close()
 
-	if err = app.extractImdbIDs(); err != nil {
-		log.Fatalf("extractImdbIDs: %v", err)
-	}
+	if !*wikiOnly {
+		if err = app.extractImdbIDs(); err != nil {
+			log.Fatalf("extractImdbIDs: %v", err)
+		}
 
-	if err = app.populateImdbTable(); err != nil {
-		log.Fatalf("populateImdbTable: %v", err)
-	}
+		if err = app.populateImdbTable(); err != nil {
+			log.Fatalf("populateImdbTable: %v", err)
+		}
 
-	if err = app.fetchAndUpdateImdbData(); err != nil {
-		log.Fatalf("fetchAndUpdateImdbData: %v", err)
-	}
+		if err = app.fetchAndUpdateImdbData(); err != nil {
+			log.Fatalf("fetchAndUpdateImdbData: %v", err)
+		}
 
-	if err = app.fetchWikiArticles(); err != nil {
-		log.Fatalf("fetchWikiArticles: %v", err)
+		if err = app.fetchWikiArticles(); err != nil {
+			log.Fatalf("fetchWikiArticles: %v", err)
+		}
+	} else {
+		if err = app.fetchWikiArticlesData(); err != nil {
+			log.Fatalf("fetchWikiArticlesData: %v", err)
+		}
 	}
 }
diff --git a/src/wikidata.go b/src/wikidata.go
index 9dacb7b..5d1b594 100644
--- a/src/wikidata.go
+++ b/src/wikidata.go
@@ -274,6 +274,31 @@ func (a *App) wikiDataConsumer(artCh <-chan wikiArticleFetch, done chan<- struct
 
 	log.Printf("fetchWikiArticlesData: %d updated, %d skipped (non-200)", updated, skipped)
 }
+// fetchWikiArticlesData fetches wiki article data from the custom server for all
+// entries that have a wiki_article but need data extraction. Callable independently.
+func (a *App) fetchWikiArticlesData() error {
+	existing, err := a.getExistingWikiArticles()
+	if err != nil {
+		return err
+	}
+	if len(existing) == 0 {
+		log.Println("fetchWikiArticlesData: all entries complete, skipping")
+		return nil
+	}
+	log.Printf("fetchWikiArticlesData: %d entries need wiki data", len(existing))
+
+	artCh := make(chan wikiArticleFetch, len(existing))
+	consumerDone := make(chan struct{})
+	go a.wikiDataConsumer(artCh, consumerDone)
+
+	for _, e := range existing {
+		artCh <- wikiArticleFetch{imdbID: e.imdbID, name: e.wikiArticle}
+	}
+	close(artCh)
+	<-consumerDone
+
+	return nil
+}
 
 // queryWikidataBatch sends a SPARQL query for the given IDs and returns a map of id -> wikiAcc.
 func (a *App) queryWikidataBatch(ids []string) (map[string]wikiAcc, error) {