<?php
class AIT_AIRCE_Content_Extractor {

    /**
     * Build normalized text for embedding.
     */
    public function extract_for_embedding( $post_id ) {

        $post = get_post( $post_id );
        if ( ! $post ) {
            return '';
        }

        $title   = wp_strip_all_tags( get_the_title( $post ) );
        $excerpt = wp_strip_all_tags( get_the_excerpt( $post ) );

        $content = $post->post_content;
        $content = strip_shortcodes( $content );
        $content = wp_strip_all_tags( $content );

        $text = trim( $title . "\n\n" . $excerpt . "\n\n" . $content );

        // Soft limit to avoid huge requests.
        if ( strlen( $text ) > 12000 ) {
            $text = substr( $text, 0, 12000 );
        }

        return $text;
    }
}