package graph

import (
	"fmt"
	"net/url"
	"strings"

	"github.com/local/glpi-neural-brain/internal/model"
)

// NodeFilter limits knowledge-bearing nodes by the exact value stored in the
// KB document's source field. Values are compared case-sensitively after
// trimming surrounding whitespace. An empty Sources list means unrestricted.
// No category, origin, URI or taxonomy fallback participates in matching.
type NodeFilter struct {
	Sources []string
}

func (f NodeFilter) Matches(node model.Node) bool {
	if len(f.Sources) == 0 {
		return true
	}
	source := strings.TrimSpace(NodeSource(node))
	for _, wanted := range f.Sources {
		wanted = strings.TrimSpace(wanted)
		if wanted == "" {
			continue
		}
		if source == wanted {
			return true
		}
	}
	return false
}

// NodeSource returns only the explicit source metadata copied from the KB
// file's top-level source field (or assigned explicitly to generated research
// evidence). Technical origins such as glpi-kb are deliberately ignored.
func NodeSource(node model.Node) string {
	return metadataText(node.Metadata, "source")
}

// SourceFromURL derives the explicit source value used for learned web
// evidence. It is kept separate from NodeSource so ordinary nodes never fall
// back to their URI implicitly.
func SourceFromURL(raw string) string {
	parsed, err := url.Parse(strings.TrimSpace(raw))
	if err != nil {
		return ""
	}
	return strings.ToLower(strings.TrimSpace(parsed.Hostname()))
}

func metadataText(metadata map[string]any, key string) string {
	if metadata == nil {
		return ""
	}
	value, ok := metadata[key]
	if !ok || value == nil {
		return ""
	}
	text := strings.TrimSpace(fmt.Sprint(value))
	if text == "" || strings.EqualFold(text, "<nil>") || strings.EqualFold(text, "null") {
		return ""
	}
	return text
}