refactor: extract shared RankState, unify rod/goquery parse paths

bing/parse_html.go

@@ -21,9 +21,7 @@ func ParseHTML(r io.Reader) ([]core.SearchResult, error) {
 
 func parseBingDocument(doc *goquery.Document) []core.SearchResult {
 	var results []core.SearchResult
-	rank := 1
-	adRank := 1
-	absoluteRank := 1
+	rank := core.NewRankState(0)
 
 	doc.Find(Selectors.ResultItems).Each(func(_ int, item *goquery.Selection) {
 		isAd := item.Is(Selectors.Ads)
@@ -41,99 +39,89 @@ func parseBingDocument(doc *goquery.Document) []core.SearchResult {
 		if titleTag.Length() == 0 {
 			return
 		}
+		href, _ := titleTag.Attr("href")
+		title := bingDocumentTitle(item, titleTag)
+		desc := bingDocumentDescription(item, title)
 
-		link, exists := titleTag.Attr("href")
-		if !exists || link == "" || link == "#" {
-			return
+		if res, ok := assembleBingRow(href, title, desc, isAd, rank); ok {
+			results = append(results, res)
 		}
-
-		title := firstNonEmptyAttr(titleTag, "aria-label", "title")
-		if title == "" {
-			title = normalizeWhitespace(titleTag.Text())
-		}
-		if title == "" {
-			title = extractFirstText(item, Selectors.TitleFallbacks)
-		}
-		if title == "" {
-			return
-		}
-
-		desc := descriptionFromItem(item, title)
-
-		resultRank := rank
-		if isAd {
-			resultRank = adRank
-			adRank++
-		} else {
-			rank++
-		}
-
-		results = append(results, core.SearchResult{
-			Rank:         resultRank,
-			AbsoluteRank: absoluteRank,
-			URL:          link,
-			Title:        title,
-			Description:  desc,
-			Ad:           isAd,
-		})
-		absoluteRank++
 	})
 
 	return core.AttachFeaturesToFirstResult(core.DeduplicateResults(results), extractBingFeatures(doc))
 }
 
-func extractFirstText(item *goquery.Selection, selectors []string) string {
-	for _, selector := range selectors {
-		if tag := item.Find(selector).First(); tag.Length() > 0 {
-			if text := normalizeWhitespace(tag.Text()); text != "" {
-				return text
-			}
-			if label := firstNonEmptyAttr(tag, "aria-label", "title"); label != "" {
-				return label
-			}
+// assembleBingRow validates an already-extracted Bing row and assigns ranks.
+// Shared by the rod (browser) and goquery (raw / parse) parsers, which differ
+// only in how they pull title/href/desc out of the DOM.
+func assembleBingRow(href, title, desc string, isAd bool, rank *core.RankState) (core.SearchResult, bool) {
+	url := strings.TrimSpace(href)
+	if url == "" || url == "#" || strings.HasPrefix(url, "javascript:") {
+		return core.SearchResult{}, false
+	}
+	if title == "" {
+		return core.SearchResult{}, false
+	}
+
+	resultRank, absoluteRank := rank.Next(isAd)
+	return core.SearchResult{
+		Rank:         resultRank,
+		AbsoluteRank: absoluteRank,
+		URL:          url,
+		Title:        title,
+		Description:  desc,
+		Ad:           isAd,
+	}, true
+}
+
+// bingDocumentTitle reproduces the rod path's title fallback for goquery: the
+// title anchor's aria-label/title attribute, then its text, then any fallback
+// selector's text or aria-label.
+func bingDocumentTitle(item, titleTag *goquery.Selection) string {
+	if title := firstNonEmptyAttr(titleTag, "aria-label", "title"); title != "" {
+		return title
+	}
+	if title := core.NormalizeWhitespace(titleTag.Text()); title != "" {
+		return title
+	}
+	for _, selector := range Selectors.TitleFallbacks {
+		tag := item.Find(selector).First()
+		if tag.Length() == 0 {
+			continue
+		}
+		if text := core.NormalizeWhitespace(tag.Text()); text != "" {
+			return text
+		}
+		if label := firstNonEmptyAttr(tag, "aria-label", "title"); label != "" {
+			return label
 		}
 	}
 	return ""
 }
 
+// bingDocumentDescription reproduces the rod path's 3-selector description
+// fallback plus the strip-title structural fallback. Bing renders snippet text
+// with heavy source-indentation whitespace, so each candidate is collapsed.
+func bingDocumentDescription(item *goquery.Selection, title string) string {
+	for _, selector := range []string{Selectors.DescPrimary, Selectors.DescFallback, Selectors.DescAny} {
+		if tag := item.Find(selector).First(); tag.Length() > 0 {
+			if text := core.NormalizeWhitespace(tag.Text()); text != "" {
+				return text
+			}
+		}
+	}
+	return core.NormalizeWhitespace(strings.Replace(item.Text(), title, "", 1))
+}
+
 func firstNonEmptyAttr(item *goquery.Selection, attrs ...string) string {
 	for _, attr := range attrs {
 		value, exists := item.Attr(attr)
 		if !exists {
 			continue
 		}
-		if value = normalizeWhitespace(value); value != "" {
+		if value = core.NormalizeWhitespace(value); value != "" {
 			return value
 		}
 	}
 	return ""
 }
-
-// descriptionFromItem extracts a description using the same 4-step fallback
-// chain as the rod-based browser parser. Bing renders snippet text with heavy
-// source-indentation whitespace, so each candidate is whitespace-collapsed.
-func descriptionFromItem(item *goquery.Selection, title string) string {
-	if descTag := item.Find(Selectors.DescPrimary).First(); descTag.Length() > 0 {
-		if text := normalizeWhitespace(descTag.Text()); text != "" {
-			return text
-		}
-	}
-	if descTag := item.Find(Selectors.DescFallback).First(); descTag.Length() > 0 {
-		if text := normalizeWhitespace(descTag.Text()); text != "" {
-			return text
-		}
-	}
-	if descTag := item.Find(Selectors.DescAny).First(); descTag.Length() > 0 {
-		if text := normalizeWhitespace(descTag.Text()); text != "" {
-			return text
-		}
-	}
-	// Structural fallback: strip title from full text
-	return normalizeWhitespace(strings.Replace(item.Text(), title, "", 1))
-}
-
-// normalizeWhitespace collapses Bing's snippet-markup whitespace into single
-// spaces (see core.NormalizeWhitespace).
-func normalizeWhitespace(s string) string {
-	return core.NormalizeWhitespace(s)
-}