sm-journal-plugin/models/post_search.go

package models

import (
	"context"
	"html"
	"strconv"
	"strings"
	"time"

	"git.golem15.com/golem15/summercms/modules/beachcomber"
	"gorm.io/gorm"
)

var (
	_ beachcomber.Searchable          = (*Post)(nil)
	_ beachcomber.IndexSchemaProvider = (*Post)(nil)
)

// SearchableAs is the Typesense collection name (D-12).
func (Post) SearchableAs() string { return "golem15_journal_posts" }

// ShouldBeSearchable is false when the post is unpublished or the
// beachcomber Gate (search_use_typesense) is off.
func (p *Post) ShouldBeSearchable() bool {
	if p == nil || !p.Published || p.PublishedAt == nil || !p.PublishedAt.Before(time.Now()) {
		return false
	}
	return SearchGateEnabled()
}

// ToSearchableArray builds the Typesense document after commit.
func (p *Post) ToSearchableArray(ctx context.Context, db *gorm.DB) (map[string]any, error) {
	if p == nil {
		return nil, nil
	}
	published := 0
	if p.Published && p.PublishedAt != nil && p.PublishedAt.Before(time.Now()) {
		published = 1
	}
	pinned := 0
	if p.IsPinned {
		pinned = 1
	}
	var publishedAt int64
	if p.PublishedAt != nil {
		publishedAt = p.PublishedAt.Unix()
	}
	var createdAt int64
	if p.CreatedAt != nil {
		createdAt = p.CreatedAt.Unix()
	}
	userID := 0
	if p.UserID != nil {
		userID = int(*p.UserID)
	}
	catIDs := make([]int, 0, len(p.Categories))
	tagIDs := make([]int, 0, len(p.Tags))
	if db != nil {
		var cats []PostCategory
		if err := db.WithContext(ctx).Where("post_id = ?", p.ID).Find(&cats).Error; err == nil {
			for _, c := range cats {
				catIDs = append(catIDs, int(c.CategoryID))
			}
		}
		var tags []PostTag
		if err := db.WithContext(ctx).Where("post_id = ?", p.ID).Find(&tags).Error; err == nil {
			for _, t := range tags {
				tagIDs = append(tagIDs, int(t.TagID))
			}
		}
	}
	return map[string]any{
		"id":           strconv.FormatUint(uint64(p.ID), 10),
		"published":    published,
		"published_at": publishedAt,
		"is_pinned":    pinned,
		"user_id":      userID,
		"created_at":   createdAt,
		"category_ids": catIDs,
		"tag_ids":      tagIDs,
		"title":        p.Title,
		"excerpt":      p.Excerpt,
		"content":      PlainText(p.searchContent()),
	}, nil
}

// searchContent is the post body to index: the rendered content_html, or
// content when nothing has been rendered.
func (p *Post) searchContent() string {
	if strings.TrimSpace(p.ContentHTML) != "" {
		return p.ContentHTML
	}
	return p.Content
}

// SearchIndexSchema is the Typesense collection schema. It applies only when
// the collection is created; journal:reindex --fresh recreates it.
func (Post) SearchIndexSchema() map[string]any {
	return map[string]any{
		"fields": []map[string]any{
			{"name": "id", "type": "string"},
			{"name": "title", "type": "string"},
			{"name": "excerpt", "type": "string"},
			{"name": "content", "type": "string"},
			{"name": "published", "type": "int64"},
			{"name": "published_at", "type": "int64"},
			{"name": "is_pinned", "type": "int64"},
			{"name": "user_id", "type": "int64"},
			{"name": "created_at", "type": "int64"},
			{"name": "category_ids", "type": "int64[]", "facet": false},
			{"name": "tag_ids", "type": "int64[]", "facet": false},
		},
	}
}

// PlainText drops HTML tags and unescapes entities, with whitespace runs
// collapsed to one space. A tag counts as a word break.
func PlainText(s string) string {
	var b strings.Builder
	inTag := false
	for _, r := range s {
		switch {
		case r == '<':
			inTag = true
			b.WriteRune(' ')
		case r == '>':
			inTag = false
		case !inTag:
			b.WriteRune(r)
		}
	}
	return strings.Join(strings.Fields(html.UnescapeString(b.String())), " ")
}