peptide-repo-core v0.6.0: peptide schema backfill + Yoast-integrated Drug/MedicalWebPage/FAQ (#19)

Backfill psa_*->_pr_* meta (migration 0004 + PubChem fallback); enrich Drug node with {permalink}#drug @id + molecularFormula/Weight/alternateName; rewrite emitter into Yoast schema graph (MedicalWebPage retype + FAQPage, no duplicate nodes).

QA: APPROVE (independent) — qa-reviews/peptide-repo-core/2026-06-13-817690c1b6ec2118ddcf3b8cfe8bc5ea7f3933b3.md

Agent-Session: peptide-schema-backfill v0.6.0 merge
This commit is contained in:
peptiderepo
2026-06-13 13:09:56 +07:00
committed by GitHub
parent cc5d06b970
commit e9d97b51e2
18 changed files with 2004 additions and 119 deletions

View File

@@ -0,0 +1,158 @@
<?php
declare(strict_types=1);
/**
* Builds the schema.org Drug graph piece for a peptide page.
*
* What: Assembles a Drug (+ MolecularEntity) schema node from peptide DTO
* and the new _pr_* schema-input meta fields added in v0.6.0.
*
* Who calls it: PR_Core_Jsonld::build_drug_piece() during Yoast graph assembly
* or standalone @graph construction.
*
* Dependencies: PR_Core_Peptide_DTO, WordPress get_post_meta(), get_permalink().
*
* @see frontend/class-pr-core-jsonld.php — Orchestrator that calls this builder.
* @see ARCHITECTURE.md — §2.7 JSON-LD output.
*/
class PR_Core_Jsonld_Drug {
/** @var string Meta key: molecular formula sourced by migration 0004. */
private const META_FORMULA = '_pr_molecular_formula';
/** @var string Meta key: molecular weight (float string) sourced by migration 0004. */
private const META_WEIGHT = '_pr_molecular_weight';
/** @var string Meta key: aliases JSON array sourced by migration 0004. */
private const META_ALIASES = '_pr_aliases';
/** @var string Unit text for molecularWeight QuantitativeValue. */
private const UNIT_TEXT = 'g/mol';
/**
* Build a schema.org Drug piece array for a peptide.
*
* @param PR_Core_Peptide_DTO $peptide Peptide DTO.
* @return array<string, mixed> Schema.org Drug node.
*/
public function build( PR_Core_Peptide_DTO $peptide ): array {
$permalink = get_permalink( $peptide->id );
$node = [
'@type' => [ 'Drug', 'MolecularEntity' ],
'@id' => $permalink . '#drug',
'name' => $peptide->display_name ?: $peptide->title,
'url' => $permalink,
];
if ( '' !== $peptide->excerpt ) {
$node['description'] = $peptide->excerpt;
}
// alternateName: prefer _pr_aliases (v0.6.0), fall back to DTO aliases field.
$aliases = $this->get_aliases( $peptide );
if ( ! empty( $aliases ) ) {
$node['alternateName'] = $aliases;
}
// molecularFormula: prefer _pr_molecular_formula, fall back to DTO field.
$formula = $this->get_formula( $peptide );
if ( '' !== $formula ) {
$node['molecularFormula'] = $formula;
}
// molecularWeight: prefer _pr_molecular_weight, fall back to DTO field.
$weight = $this->get_weight( $peptide );
if ( $weight > 0.0 ) {
$node['molecularWeight'] = [
'@type' => 'QuantitativeValue',
'value' => $weight,
'unitText' => self::UNIT_TEXT,
];
}
// External identifiers: CAS and DrugBank omitted in v0.6.0 (no source).
// @see ARCHITECTURE.md §v0.6.0 schema sprint — future enrichment.
$legal_status = $this->build_legal_status();
if ( null !== $legal_status ) {
$node['legalStatus'] = $legal_status;
}
/**
* Filter the Drug schema node for a peptide.
*
* Known listeners: none.
* Registered at: PR_Core::register_public_filters() — carried forward from v0.5.0.
*
* @param array<string, mixed> $node Drug schema node.
* @param PR_Core_Peptide_DTO $peptide Peptide DTO.
*/
return apply_filters( 'pr_core_jsonld_peptide', $node, $peptide );
}
/**
* Get aliases array from _pr_aliases meta, falling back to DTO aliases.
*
* @param PR_Core_Peptide_DTO $peptide Peptide DTO.
* @return string[] Sanitized alias strings.
*/
private function get_aliases( PR_Core_Peptide_DTO $peptide ): array {
$raw = get_post_meta( $peptide->id, self::META_ALIASES, true );
if ( is_string( $raw ) && '' !== $raw ) {
$decoded = json_decode( $raw, true );
if ( is_array( $decoded ) && ! empty( $decoded ) ) {
return array_values( array_filter( array_map( 'sanitize_text_field', $decoded ) ) );
}
}
// Fall back to DTO aliases (legacy bare-key meta).
return $peptide->aliases;
}
/**
* Get molecular formula from _pr_molecular_formula meta, falling back to DTO.
*
* @param PR_Core_Peptide_DTO $peptide Peptide DTO.
* @return string Sanitized formula string, or '' if not available.
*/
private function get_formula( PR_Core_Peptide_DTO $peptide ): string {
$raw = (string) get_post_meta( $peptide->id, self::META_FORMULA, true );
if ( '' !== $raw ) {
return sanitize_text_field( $raw );
}
return $peptide->molecular_formula;
}
/**
* Get molecular weight float from _pr_molecular_weight meta, falling back to DTO.
*
* @param PR_Core_Peptide_DTO $peptide Peptide DTO.
* @return float Weight in g/mol, or 0.0 if not available.
*/
private function get_weight( PR_Core_Peptide_DTO $peptide ): float {
$raw = (string) get_post_meta( $peptide->id, self::META_WEIGHT, true );
if ( '' !== $raw ) {
$weight = (float) $raw;
if ( $weight > 0.0 ) {
return $weight;
}
}
return $peptide->molecular_weight;
}
/**
* Build a standard legalStatus node for research compounds.
*
* Returns null when legalStatus should be omitted (future: when per-peptide
* status is available from legal cells).
*
* @return array<string, string>|null
*/
private function build_legal_status(): ?array {
return [
'@type' => 'DrugLegalStatus',
'description' => esc_html__( 'Not approved for human therapeutic use; supplied for laboratory research purposes only.', 'peptide-repo-core' ),
];
}
}

View File

@@ -0,0 +1,100 @@
<?php
declare(strict_types=1);
/**
* Builds the schema.org FAQPage graph piece for a peptide page.
*
* What: Reads _pr_faq_items post-meta (JSON array of {question, answer} objects)
* and produces a FAQPage node suitable for injection into Yoast's graph.
* Emits nothing when the meta is empty or absent.
*
* Who calls it: PR_Core_Jsonld::build_faq_piece() during graph assembly.
* Dependencies: WordPress get_post_meta(), get_permalink().
*
* @see frontend/class-pr-core-jsonld.php — Orchestrator that calls this builder.
* @see cpt/class-pr-core-schema-sanitizers.php — sanitize_faq_items() used on save.
* @see ARCHITECTURE.md — §2.7 JSON-LD output.
*/
class PR_Core_Jsonld_Faq {
/** @var string Meta key holding the FAQ items JSON array. */
public const META_FAQ_ITEMS = '_pr_faq_items';
/**
* Build a FAQPage node for a post, or return null if no items exist.
*
* @param int $post_id WordPress post ID.
* @param string $permalink Canonical permalink for @id construction.
* @return array<string, mixed>|null FAQPage schema node, or null when no items.
*/
public function build( int $post_id, string $permalink ): ?array {
$items = $this->get_validated_items( $post_id );
if ( empty( $items ) ) {
return null;
}
return [
'@type' => 'FAQPage',
'@id' => $permalink . '#faq',
'mainEntity' => array_map( [ $this, 'build_question' ], $items ),
];
}
/**
* Build a single Question node from a FAQ item array.
*
* @param array{question: string, answer: string} $item Sanitized FAQ item.
* @return array<string, mixed> Schema.org Question node.
*/
private function build_question( array $item ): array {
return [
'@type' => 'Question',
'name' => esc_html( $item['question'] ),
'acceptedAnswer' => [
'@type' => 'Answer',
'text' => esc_html( $item['answer'] ),
],
];
}
/**
* Read and validate _pr_faq_items meta, returning only well-formed items.
*
* Returns empty array when meta is absent, empty, or malformed.
* Does not trust stored values — re-validates each item at read time.
*
* @param int $post_id WordPress post ID.
* @return array<int, array{question: string, answer: string}> Validated items.
*/
private function get_validated_items( int $post_id ): array {
$raw = get_post_meta( $post_id, self::META_FAQ_ITEMS, true );
if ( ! is_string( $raw ) || '' === $raw ) {
return [];
}
$decoded = json_decode( $raw, true );
if ( ! is_array( $decoded ) || empty( $decoded ) ) {
return [];
}
$valid = [];
foreach ( $decoded as $item ) {
if ( ! is_array( $item ) ) {
continue;
}
$question = sanitize_text_field( (string) ( $item['question'] ?? '' ) );
$answer = sanitize_textarea_field( (string) ( $item['answer'] ?? '' ) );
if ( '' !== $question && '' !== $answer ) {
$valid[] = [
'question' => $question,
'answer' => $answer,
];
}
}
return $valid;
}
}

View File

@@ -0,0 +1,134 @@
<?php
declare(strict_types=1);
/**
* Enriches Yoast's WebPage node to MedicalWebPage for peptide single pages.
*
* What: Hooks into Yoast's wpseo_schema_webpage_type filter to retype the page
* node to MedicalWebPage, and into wpseo_schema_graph to inject
* lastReviewed, reviewedBy, and audience enrichments.
*
* Who calls it: PR_Core_Jsonld::register_hooks() registers both filters.
* Dependencies: Yoast SEO (wordpress-seo) ≥ 27.6 when active; graceful no-op otherwise.
*
* @see frontend/class-pr-core-jsonld.php — Parent orchestrator.
* @see ARCHITECTURE.md — §2.7 JSON-LD output, Yoast integration contract.
*/
class PR_Core_Jsonld_Webpage {
/** @var string Meta key for last editorial review date (ISO date string). */
private const META_LAST_REVIEWED = '_pr_last_reviewed';
/** @var string Meta key for last source verification date (ISO date string). */
private const META_LAST_VERIFIED = '_pr_last_source_verified';
/**
* Return 'MedicalWebPage' as the schema type for peptide single pages.
*
* Hooked on: wpseo_schema_webpage_type (Yoast SEO ≥ 19.x).
* Passes through unchanged on non-peptide pages.
*
* @param string $type Existing Yoast page type (e.g., 'WebPage').
* @return string 'MedicalWebPage' on peptide singles, $type otherwise.
*/
public function retype_to_medical_webpage( string $type ): string {
if ( is_singular( PR_Core_Peptide_CPT::POST_TYPE ) ) {
return 'MedicalWebPage';
}
return $type;
}
/**
* Enrich Yoast's graph pieces array for peptide single pages.
*
* Injects lastReviewed, reviewedBy, and audience into the WebPage/MedicalWebPage
* node already in Yoast's graph. Does NOT add new WebPage or BreadcrumbList nodes.
*
* Hooked on: wpseo_schema_graph (Yoast SEO ≥ 19.x), priority 11.
*
* @param array<int, array<string, mixed>> $graph Yoast schema graph pieces array.
* @param \WPSEO_Schema_Context $context Yoast schema context object.
* @return array<int, array<string, mixed>> Modified graph.
*/
public function enrich_webpage_piece( array $graph, $context ): array {
if ( ! is_singular( PR_Core_Peptide_CPT::POST_TYPE ) ) {
return $graph;
}
$post_id = get_the_ID();
$enrichments = $this->build_webpage_enrichments( (int) $post_id );
if ( empty( $enrichments ) ) {
return $graph;
}
foreach ( $graph as &$piece ) {
if ( ! is_array( $piece ) ) {
continue;
}
$type = $piece['@type'] ?? '';
if ( 'WebPage' === $type || 'MedicalWebPage' === $type ) {
foreach ( $enrichments as $key => $value ) {
$piece[ $key ] = $value;
}
break;
}
}
return $graph;
}
/**
* Build MedicalWebPage enrichment fields for a peptide post.
*
* @param int $post_id WordPress post ID.
* @return array<string, mixed> Enrichment fields to merge into the WebPage node.
*/
private function build_webpage_enrichments( int $post_id ): array {
$enrichments = [];
// lastReviewed: prefer _pr_last_reviewed, fall back to _pr_last_source_verified,
// then post modified date.
$last_reviewed = (string) get_post_meta( $post_id, self::META_LAST_REVIEWED, true );
if ( '' === $last_reviewed ) {
$last_reviewed = (string) get_post_meta( $post_id, self::META_LAST_VERIFIED, true );
}
if ( '' === $last_reviewed ) {
$last_reviewed = get_post_modified_time( 'Y-m-d', false, $post_id ) ?: '';
}
if ( '' !== $last_reviewed ) {
$enrichments['lastReviewed'] = sanitize_text_field( $last_reviewed );
}
// reviewedBy: Person only when a medical editor is assigned; otherwise Organization.
$editor_id = (int) get_post_meta( $post_id, 'medical_editor_id', true );
if ( $editor_id > 0 ) {
$editor = get_userdata( $editor_id );
if ( $editor ) {
$enrichments['reviewedBy'] = [
'@type' => 'Person',
'name' => sanitize_text_field( $editor->display_name ),
'url' => get_author_posts_url( $editor_id ),
];
}
}
if ( ! isset( $enrichments['reviewedBy'] ) ) {
$enrichments['reviewedBy'] = [
'@type' => 'Organization',
'name' => 'Peptide Repo',
'url' => home_url(),
];
}
// audience: MedicalAudience for researchers.
$enrichments['audience'] = [
'@type' => 'MedicalAudience',
'audienceType' => 'Researcher',
];
return $enrichments;
}
}

View File

@@ -4,33 +4,122 @@ declare(strict_types=1);
/**
* JSON-LD / schema.org structured data emission for peptide pages.
*
* What: Emits Drug schema on single peptide pages, Dataset schema on archives.
* Who calls it: PR_Core::init() registers wp_head hook.
* Dependencies: PR_Core_Peptide_Repository for data lookup.
* What: Integrates Drug, MedicalWebPage, and FAQPage schema into Yoast's graph
* on single peptide pages. When Yoast is inactive, emits a standalone
* @graph block via wp_head as a fallback.
*
* Consumer plugins can override via pr_core_jsonld_peptide filter.
* Who calls it: PR_Core::init() calls register_hooks(). Yoast hooks fire on
* every frontend page that Yoast processes.
*
* @see ARCHITECTURE.md — Section 2.7 JSON-LD output.
* Dependencies:
* - Yoast SEO (wordpress-seo) ≥ 27.6 for integrated emission path.
* - PR_Core_Jsonld_Drug, PR_Core_Jsonld_Webpage, PR_Core_Jsonld_Faq (builders).
* - PR_Core_Peptide_Repository, PR_Core_Peptide_CPT (data).
*
* Contract (ratified 2026-06-11, jsonld-contract-v1.md):
* - Integrated path: Yoast owns WebPage and BreadcrumbList — we never duplicate.
* - Standalone fallback: emits a complete @graph (Drug + FAQPage) only.
* - Drug @id: {permalink}#drug (stable for cross-plugin linking).
*
* @see frontend/class-pr-core-jsonld-drug.php — Drug piece builder.
* @see frontend/class-pr-core-jsonld-webpage.php — MedicalWebPage enrichment.
* @see frontend/class-pr-core-jsonld-faq.php — FAQPage piece builder.
* @see ARCHITECTURE.md — §2.7 JSON-LD output.
*/
class PR_Core_Jsonld {
/** @var PR_Core_Jsonld_Drug Drug piece builder. */
private PR_Core_Jsonld_Drug $drug_builder;
/** @var PR_Core_Jsonld_Webpage MedicalWebPage enricher. */
private PR_Core_Jsonld_Webpage $webpage_enricher;
/** @var PR_Core_Jsonld_Faq FAQ piece builder. */
private PR_Core_Jsonld_Faq $faq_builder;
/**
* Construct the orchestrator with its piece builders.
*/
public function __construct() {
$this->drug_builder = new PR_Core_Jsonld_Drug();
$this->webpage_enricher = new PR_Core_Jsonld_Webpage();
$this->faq_builder = new PR_Core_Jsonld_Faq();
}
/**
* Register hooks for JSON-LD output.
*
* Registers both the Yoast-integrated path (active when Yoast is loaded)
* and the standalone wp_head fallback (active only when Yoast is absent).
*
* Side effects: calls add_filter(), add_action().
*
* @return void
*/
public function register_hooks(): void {
add_action( 'wp_head', [ $this, 'emit_jsonld' ], 99 );
// Integrated path: hook into Yoast's schema graph.
// wpseo_schema_graph_pieces: filter on the array of schema piece objects.
// wpseo_schema_webpage_type: filter returning the WebPage @type string.
add_filter( 'wpseo_schema_graph_pieces', [ $this, 'inject_graph_pieces' ], 11, 2 );
add_filter( 'wpseo_schema_webpage_type', [ $this->webpage_enricher, 'retype_to_medical_webpage' ] );
add_filter( 'wpseo_schema_graph', [ $this->webpage_enricher, 'enrich_webpage_piece' ], 11, 2 );
// Standalone fallback: emits only when Yoast is not producing output.
add_action( 'wp_head', [ $this, 'emit_standalone_fallback' ], 99 );
}
/**
* Emit JSON-LD on peptide single pages.
* Inject Drug and FAQPage pieces into Yoast's schema graph.
*
* Side effects: outputs script tag in wp_head.
* Hooked on: wpseo_schema_graph_pieces (priority 11, after Yoast's own pieces).
* This filter receives Yoast's piece objects array. We append plain arrays;
* Yoast 27.6 accepts both objects and plain arrays in this filter.
*
* @param array<int, mixed> $pieces Existing graph pieces from Yoast.
* @param \WPSEO_Schema_Context $context Yoast schema context object.
* @return array<int, mixed> Pieces array with Drug and FAQPage appended.
*/
public function inject_graph_pieces( array $pieces, $context ): array {
if ( ! is_singular( PR_Core_Peptide_CPT::POST_TYPE ) ) {
return $pieces;
}
$post_id = get_the_ID();
if ( ! $post_id ) {
return $pieces;
}
$peptide = ( new PR_Core_Peptide_Repository() )->find_by_id( (int) $post_id );
if ( ! $peptide ) {
return $pieces;
}
$pieces[] = $this->drug_builder->build( $peptide );
$faq_piece = $this->faq_builder->build( (int) $post_id, get_permalink( (int) $post_id ) );
if ( null !== $faq_piece ) {
$pieces[] = $faq_piece;
}
return $pieces;
}
/**
* Emit a standalone @graph block via wp_head when Yoast is not active.
*
* Guard: suppressed if Yoast is loaded (function_exists check). This is the
* no-Yoast fallback required by the jsonld-contract. When Yoast is present,
* the integrated path (inject_graph_pieces) handles emission.
*
* Side effects: outputs a script tag in wp_head.
*
* @return void
*/
public function emit_jsonld(): void {
public function emit_standalone_fallback(): void {
if ( function_exists( 'YoastSEO' ) ) {
return;
}
if ( ! is_singular( PR_Core_Peptide_CPT::POST_TYPE ) ) {
return;
}
@@ -40,86 +129,25 @@ class PR_Core_Jsonld {
return;
}
$repo = new PR_Core_Peptide_Repository();
$peptide = $repo->find_by_id( $post_id );
$peptide = ( new PR_Core_Peptide_Repository() )->find_by_id( (int) $post_id );
if ( ! $peptide ) {
return;
}
$schema = $this->build_drug_schema( $peptide );
$permalink = get_permalink( (int) $post_id );
$graph = [ $this->drug_builder->build( $peptide ) ];
/**
* Filter the JSON-LD schema for a peptide page.
*
* @param array<string, mixed> $schema Schema.org data array.
* @param PR_Core_Peptide_DTO $peptide The peptide DTO.
*/
$schema = apply_filters( 'pr_core_jsonld_peptide', $schema, $peptide );
if ( empty( $schema ) ) {
return;
$faq_piece = $this->faq_builder->build( (int) $post_id, $permalink );
if ( null !== $faq_piece ) {
$graph[] = $faq_piece;
}
printf(
'<script type="application/ld+json">%s</script>' . "\n",
wp_json_encode( $schema, JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE | JSON_PRETTY_PRINT )
wp_json_encode(
[ '@context' => 'https://schema.org', '@graph' => $graph ],
JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE | JSON_PRETTY_PRINT
)
);
}
/**
* Build a schema.org Drug object for a peptide.
*
* @param PR_Core_Peptide_DTO $peptide Peptide data.
* @return array<string, mixed> Schema.org JSON-LD structure.
*/
private function build_drug_schema( PR_Core_Peptide_DTO $peptide ): array {
$schema = [
'@context' => 'https://schema.org',
'@type' => 'Drug',
'name' => $peptide->display_name ?: $peptide->title,
'url' => get_permalink( $peptide->id ),
'description' => $peptide->excerpt,
];
if ( ! empty( $peptide->aliases ) ) {
$schema['alternateName'] = $peptide->aliases;
}
if ( '' !== $peptide->molecular_formula ) {
$schema['molecularFormula'] = $peptide->molecular_formula;
}
if ( $peptide->molecular_weight > 0 ) {
$schema['molecularWeight'] = [
'@type' => 'QuantitativeValue',
'value' => $peptide->molecular_weight,
'unitText' => 'Da',
];
}
// External identifiers as codes.
$codes = [];
if ( '' !== $peptide->cas_number ) {
$codes[] = [
'@type' => 'MedicalCode',
'codeValue' => $peptide->cas_number,
'codingSystem' => 'CAS',
];
}
if ( '' !== $peptide->drugbank_id ) {
$codes[] = [
'@type' => 'MedicalCode',
'codeValue' => $peptide->drugbank_id,
'codingSystem' => 'DrugBank',
];
}
if ( ! empty( $codes ) ) {
$schema['code'] = $codes;
}
return $schema;
}
}