package sources

import (
	"fmt"
	"sort"

	"github.com/salvacybersec/keyhunter/pkg/providers"
)

// BuildQueries produces the search-string list a source should iterate for the
// given provider registry. Each keyword is formatted per source-specific syntax
// (e.g. GitHub's `"kw" in:file` qualifier). Keywords are deduped across
// providers and returned sorted for deterministic test output.
//
// A nil registry returns nil. An unknown source name falls back to the bare
// keyword form so new sources work safely until they register custom syntax.
func BuildQueries(reg *providers.Registry, source string) []string {
	if reg == nil {
		return nil
	}

	seen := make(map[string]struct{})
	for _, p := range reg.List() {
		for _, k := range p.Keywords {
			if k == "" {
				continue
			}
			seen[k] = struct{}{}
		}
	}

	keywords := make([]string, 0, len(seen))
	for k := range seen {
		keywords = append(keywords, k)
	}
	sort.Strings(keywords)

	out := make([]string, 0, len(keywords))
	for _, k := range keywords {
		out = append(out, formatQuery(source, k))
	}
	return out
}

// formatQuery applies source-specific search syntax to a raw keyword.
func formatQuery(source, keyword string) string {
	switch source {
	case "github", "gist":
		return fmt.Sprintf("%q in:file", keyword)
	default:
		// GitLab, Bitbucket, Codeberg, HuggingFace, Kaggle, Replit,
		// CodeSandbox, sandboxes, and unknown sources use bare keywords.
		return keyword
	}
}