Extend Solr search: content coverage, 14.0.2, news recency, result images

- Index the text columns of the market/solution Content Blocks and the vitec_items/vitec_faq_items collection children; story documents now include their body (inline tt_content children via tx_vitec_usecase_content, same per-element extraction as pages) - stories were indexed with subtitle and teaser only until now - Upgrade EXT:solr 14.0.0-RC1 -> 14.0.2 final (the Solr image moved to a fresh volume because the configset changed; synonyms restored via REST) - News decay with age by publication date: crdate is the import date, so news map datetime to created; boost function gated to news only - Results carry `image`: processed 640px tile image per type, root-relative, null for pages and downloads - Spec v1.21: 7.16 states the /_json prefix and lists `solution` in the type vocabulary; footer had been stuck at v1.19 - suggest-demo.html fetches through /_json after the URL swap
2026-10-07 16:22:50 +02:00
1 parent 8e67f5db23
commit 9b1ad202a9
@@ -15,7 +15,7 @@
 		"sort-packages": true
 	},
 	"require": {
-		"apache-solr-for-typo3/solr": "^14.0@RC",
+		"apache-solr-for-typo3/solr": "^14.0.2",
 		"b13/container": "^3.1",
 		"b13/typo3-updater": "^1.1",
 		"evomedien/evo-megamenu-json": "^1.0.0",
@@ -4,20 +4,20 @@
        "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
        "This file is @generated automatically"
    ],
-    "content-hash": "0f38c50d2ecb8b6e4b0ec88fc7985249",
+    "content-hash": "f9a73e5875dc0072a5a3853989adda94",
    "packages": [
        {
            "name": "apache-solr-for-typo3/solr",
-            "version": "14.0.1",
+            "version": "14.0.2",
            "source": {
                "type": "git",
                "url": "https://github.com/TYPO3-Solr/ext-solr.git",
-                "reference": "25fad97ffe192b1c4afc9400b98f4b4c4d3a6ea3"
+                "reference": "d430194b11c0581bd70e96a0483ec813b8345529"
            },
            "dist": {
                "type": "zip",
-                "url": "https://api.github.com/repos/TYPO3-Solr/ext-solr/zipball/25fad97ffe192b1c4afc9400b98f4b4c4d3a6ea3",
-                "reference": "25fad97ffe192b1c4afc9400b98f4b4c4d3a6ea3",
+                "url": "https://api.github.com/repos/TYPO3-Solr/ext-solr/zipball/d430194b11c0581bd70e96a0483ec813b8345529",
+                "reference": "d430194b11c0581bd70e96a0483ec813b8345529",
                "shasum": ""
            },
            "require": {
@@ -129,7 +129,7 @@
                    "type": "custom"
                }
            ],
-            "time": "2026-09-03T14:19:19+00:00"
+            "time": "2026-09-16T13:50:16+00:00"
        },
        {
            "name": "b13/container",
@@ -10325,7 +10325,6 @@
    "aliases": [],
    "minimum-stability": "stable",
    "stability-flags": {
-        "apache-solr-for-typo3/solr": 5,
        "friendsoftypo3/headless": 5
    },
    "prefer-stable": false,
@@ -27,7 +27,7 @@ use TYPO3\CMS\Frontend\ContentObject\ContentObjectRenderer;
 *                       or the FlexForm override on the plugin),
 *     "numFound":       total hits,
 *     "totalPages":     ceil(numFound / resultsPerPage),
- *     "results":        [ { "title", "url", "type", "teaser" } ],
+ *     "results":        [ { "title", "url", "type", "teaser", "image" } ],
 *     "filter":         the active type filter or null,
 *     "facets":         { "type": [ { "value", "count", "active" } ] } -
 *                       counts stay complete while a filter is active,
@@ -217,11 +217,20 @@ class SearchJsonRenderer
                } else {
                    $teaser = mb_substr(trim((string)$document->getContent()), 0, self::TEASER_FALLBACK_LENGTH);
                }
+                $image = (string)($document['image'] ?? '');
+                // IMG_RESOURCE yields fileadmin/... without a leading slash -
+                // made root-relative like every other URL in the payload
+                if ($image !== '' && !str_starts_with($image, '/') && !preg_match('#^https?://#', $image)) {
+                    $image = '/' . $image;
+                }
                $results[] = [
                    'title' => (string)$document->getTitle(),
                    'url' => (string)$document->getUrl(),
                    'type' => self::TYPE_LABELS[$document->getType()] ?? (string)$document->getType(),
                    'teaser' => $teaser,
+                    // processed tile image (640px wide) from the index; null when the
+                    // document type has none (pages, downloads) or no image is set
+                    'image' => $image !== '' ? $image : null,
                ];
            }

@@ -394,6 +394,67 @@ plugin.tx_solr.index.queue.pages.fields {
                    40 = TEXT
                    40.field = vitec_quote
                    40.noTrimWrap = || |
+                    # Content Blocks with their own text columns (market/solution
+                    # templates, flip cards) - the workbook imports fill these
+                    50 = TEXT
+                    50.field = vitec_subline
+                    50.noTrimWrap = || |
+                    60 = TEXT
+                    60.field = vitec_intro_headline
+                    60.noTrimWrap = || |
+                    70 = TEXT
+                    70.field = vitec_intro_text
+                    70.noTrimWrap = || |
+                    80 = TEXT
+                    80.field = vitec_text1
+                    80.noTrimWrap = || |
+                    90 = TEXT
+                    90.field = vitec_text2
+                    90.noTrimWrap = || |
+                    100 = TEXT
+                    100.field = vitec_back_text
+                    100.noTrimWrap = || |
+                    110 = TEXT
+                    110.field = vitec_quote_position
+                    110.noTrimWrap = || |
+                    # Content Blocks collection children (cards, icon lists,
+                    # FAQ) live in their own tables, keyed on the parent uid
+                    120 = CONTENT
+                    120 {
+                        table = vitec_items
+                        select {
+                            pidInList.field = pid
+                            where.dataWrap = {#foreign_table_parent_uid} = {field:uid}
+                            orderBy = sorting
+                        }
+                        renderObj = COA
+                        renderObj {
+                            10 = TEXT
+                            10.field = headline
+                            10.noTrimWrap = || |
+                            20 = TEXT
+                            20.field = text
+                            20.noTrimWrap = || |
+                        }
+                    }
+                    130 = CONTENT
+                    130 {
+                        table = vitec_faq_items
+                        select {
+                            pidInList.field = pid
+                            where.dataWrap = {#foreign_table_parent_uid} = {field:uid}
+                            orderBy = sorting
+                        }
+                        renderObj = COA
+                        renderObj {
+                            10 = TEXT
+                            10.field = question
+                            10.noTrimWrap = || |
+                            20 = TEXT
+                            20.field = answer
+                            20.noTrimWrap = || |
+                        }
+                    }
                }
            }
        }
@@ -419,6 +480,37 @@ plugin.tx_solr.index.queue {

    products = 1
    products {
+        # result tile image: first reference, processed to 640px width
+        fields.image = FILES
+        fields.image {
+            references {
+                table = tx_vitec_domain_model_product
+                uid.data = field:uid
+                fieldName = image
+            }
+            maxItems = 1
+            renderObj = IMG_RESOURCE
+            renderObj {
+                file.import.data = file:current:uid
+                file.treatIdAsReference = 1
+                file.width = 640
+            }
+            stdWrap.ifEmpty.cObject = FILES
+            stdWrap.ifEmpty.cObject {
+                references {
+                    table = tx_vitec_domain_model_product
+                    uid.data = field:uid
+                    fieldName = productimage
+                }
+                maxItems = 1
+                renderObj = IMG_RESOURCE
+                renderObj {
+                    file.import.data = file:current:uid
+                    file.treatIdAsReference = 1
+                    file.width = 640
+                }
+            }
+        }
        # sys_category titles - feeds the category facet
        fields.category_stringM = SOLR_RELATION
        fields.category_stringM {
@@ -470,6 +562,22 @@ plugin.tx_solr.index.queue {

    markets = 1
    markets {
+        # result tile image: first reference, processed to 640px width
+        fields.image = FILES
+        fields.image {
+            references {
+                table = tx_vitec_domain_model_market
+                uid.data = field:uid
+                fieldName = image
+            }
+            maxItems = 1
+            renderObj = IMG_RESOURCE
+            renderObj {
+                file.import.data = file:current:uid
+                file.treatIdAsReference = 1
+                file.width = 640
+            }
+        }
        type = tx_vitec_domain_model_market
        # only markets with an editorially assigned detail page are linkable;
        # grows automatically as editors fill the field (4 of 34 right now)
@@ -503,6 +611,37 @@ plugin.tx_solr.index.queue {

    usecases = 1
    usecases {
+        # result tile image: first reference, processed to 640px width
+        fields.image = FILES
+        fields.image {
+            references {
+                table = tx_vitec_domain_model_usecase
+                uid.data = field:uid
+                fieldName = card_image
+            }
+            maxItems = 1
+            renderObj = IMG_RESOURCE
+            renderObj {
+                file.import.data = file:current:uid
+                file.treatIdAsReference = 1
+                file.width = 640
+            }
+            stdWrap.ifEmpty.cObject = FILES
+            stdWrap.ifEmpty.cObject {
+                references {
+                    table = tx_vitec_domain_model_usecase
+                    uid.data = field:uid
+                    fieldName = hero_bgimage
+                }
+                maxItems = 1
+                renderObj = IMG_RESOURCE
+                renderObj {
+                    file.import.data = file:current:uid
+                    file.treatIdAsReference = 1
+                    file.width = 640
+                }
+            }
+        }
        # market titles from the MM relation - feeds the market facet
        fields.market_stringM = SOLR_RELATION
        fields.market_stringM {
@@ -524,6 +663,18 @@ plugin.tx_solr.index.queue {
                    20 = TEXT
                    20.field = teaser
                    20.noTrimWrap = || |
+                    # the story body: inline tt_content children (text, columns,
+                    # quotations) - same per-element extraction as page content
+                    30 = CONTENT
+                    30 {
+                        table = tt_content
+                        select {
+                            pidInList.field = pid
+                            where.dataWrap = {#tx_vitec_usecase_content} = {field:uid}
+                            orderBy = sorting
+                        }
+                        renderObj < plugin.tx_solr.index.queue.pages.fields.content.cObject.10.renderObj
+                    }
                }
            }
            url = TEXT
@@ -544,6 +695,22 @@ plugin.tx_solr.index.queue {
    # 39 records a detail_page (and slug). Same pattern as markets.
    solutions = 1
    solutions {
+        # result tile image: first reference, processed to 640px width
+        fields.image = FILES
+        fields.image {
+            references {
+                table = tx_vitec_domain_model_solution
+                uid.data = field:uid
+                fieldName = image
+            }
+            maxItems = 1
+            renderObj = IMG_RESOURCE
+            renderObj {
+                file.import.data = file:current:uid
+                file.treatIdAsReference = 1
+                file.width = 640
+            }
+        }
        type = tx_vitec_domain_model_solution
        additionalWhereClause = detail_page > 0
        fields {
@@ -575,6 +742,25 @@ plugin.tx_solr.index.queue {

    news = 1
    news {
+        # crdate is the IMPORT date (Jul/Aug 2026) - the publication date
+        # lives in datetime. `created` feeds the news recency boost.
+        fields.created = datetime
+        # result tile image: first reference, processed to 640px width
+        fields.image = FILES
+        fields.image {
+            references {
+                table = tx_news_domain_model_news
+                uid.data = field:uid
+                fieldName = fal_media
+            }
+            maxItems = 1
+            renderObj = IMG_RESOURCE
+            renderObj {
+                file.import.data = file:current:uid
+                file.treatIdAsReference = 1
+                file.width = 640
+            }
+        }
        type = tx_news_domain_model_news
        # type 1 ("page as news") points at pages that are already indexed as
        # pages - indexing them again would duplicate every one of them
@@ -707,3 +893,9 @@ plugin.tx_solr.suggest {
    # type and the full indexed content - too fat and off-contract for type-ahead
    showTopResults = 0
 }
+
+# News recency: old news decays against everything else. Additive edismax
+# boost (bf): non-news documents get the constant 10, news get
+# recip(age) = 10 when new, ~5 after one year, ~0.7 after 13 years.
+# The gate keeps products/pages/stories out of the decay entirely.
+plugin.tx_solr.search.query.boostFunction = if(termfreq(type,'tx_news_domain_model_news'),recip(ms(NOW,created),3.16e-11,10,1),10)
@@ -3,9 +3,9 @@
 | | |
 |---|---|
 | **Document identifier** | EVO‑VITEC‑HL‑001 |
-| **Version** | 1.20 |
+| **Version** | 1.21 |
 | **Status** | Released |
-| **Date** | 2026‑10‑01 |
+| **Date** | 2026‑10‑07 |
 | **Applies to** | `evomedien/vitec` on TYPO3 v14.3 (headless) |
 | **Owner** | evomedien — VITEC relaunch |

@@ -33,6 +33,7 @@
 | 1.18 | 2026‑09‑24 | **Interface change (additive).** Products gained `solutions` — an MM relation to solutions, emitted as solution cards in both product payloads — and a **Resources tab**: child table `tx_vitec_product_resource` with documentation / support cards (editable title, text and icon around one link, resolved per 9.12; cards without a resolvable link are not emitted) plus a `datasheets` MM selection of download records rendered into the same envelope as `type: datasheet` cards, delivered detail‑only as the `resources` list envelope whose `layout` switches to `carousel` above three cards in total (7.15). The `solutions` relation accepts group‑level records: the eight groups exist as `is_group = 1` solutions (created by `vitec:create-solution-groups`, excluded from lists and from `vitec:align-solutions`) because the agency workbooks reference the group level. Editorial: the footer had been stuck at v1.15 since 1.16/1.17 (2026‑09‑11). |
 | 1.19 | 2026‑09‑25 | **Interface change (additive).** The `vitec_card` Content Block gained the `layout_variant` value `flipcard` and a *Card Back* palette: `back_headline` (string, max 100) and `back_text` (richtext → HTML). The two fields are `displayCond`‑gated on the flipcard layout in the backend but serialised unconditionally (7.7) — the front end **shall** key the back face on `layout_variant`, never on field presence, because stored back values persist when an editor switches the layout away. Backend repair: `vitec_layout_variant` / `vitec_background_variant` are shared with `vitec_ctabanner`, and the index‑wise Content‑Blocks merge had dropped four card‑only select values (“Missing label”) — per‑type item lists now come from `columnsOverrides` (7.7); the Card‑Back palette lives in the Layout tab below the variant select. Editorial: the head‑matter version had been stuck at v1.17 since 1.18. |
 | 1.20 | 2026‑10‑01 | **Interface change (additive).** Sub-market page template: frontend layout 21 with one colPos group per design section (`colPos110`..`colPos160`, clause 7.17); new Content Blocks `vitec_markethero`, `vitec_marketintro`, `vitec_marketinsights`; new plugin `vitec_productfeature` (key `productfeature`, one product in the 7.15.2 item shape); story cards gained `quote`/`quotePerson`/`quoteRole`; `vitec_usecaselist` gained the layout value `testimonials`; `vitec_productlist` gained hand-picked product selection (editor order, category filter ignored). Field semantics: Template_Sub-Market_Spezifikation_2026-10-01.md. |
+| 1.21 | 2026‑10‑07 | **Interface change (additive) and corpus change.** Search results carry `image` (processed 640 px tile image, root-relative, `null` for types without one). Corpus: story documents now include their body (the inline `tt_content` children), page and story content include the text columns of the market/solution Content Blocks and the `vitec_items`/`vitec_faq_items` collection children; solutions are indexed. News rank by publication date (`datetime`; `crdate` is the import date) with an age-decay boost. EXT:solr upgraded from 14.0.0-RC1 to 14.0.2 final (TYPO3 and the Solr image). Editorial: 7.16 now states the `/_json` prefix the URL swap introduced, the `type` vocabulary lists `solution` (delivered since 1.14), and the footer had been stuck at v1.19. |

 This document is drafted in the style of, and adopts the terminology conventions of,
 ISO/IEC/IEEE 42010 (architecture description), ISO/IEC/IEEE 26514 (information for
@@ -1033,6 +1034,10 @@ headless by `SearchJsonRenderer` under the payload key `search`. The renderer ru
 EXT:solr’s own query pipeline (`SearchRequestBuilder` → `SearchResultSetService`) -
 only the rendering differs from the stock Fluid plugin.

+Since the URL swap of 2026‑09‑28 every JSON URL carries the prefix `/_json`:
+the search answers at `/_json/search?q=…`, while the bare `/search` serves the
+single-page app. Paths in this clause are given without the prefix.
+
 **Request.** GET parameters on the search page:

 | Parameter | Meaning |
@@ -1071,13 +1076,15 @@ identifier).
  },
  "results": [
    { "title": "MGW Diamond-H", "url": "/product/mgw-diamond-h-hdmi-encoder",
-      "type": "product", "teaser": "… 4K HDMI <mark>Encoder</mark> …" }
+      "type": "product", "teaser": "… 4K HDMI <mark>Encoder</mark> …",
+      "image": "/fileadmin/_processed_/…/csm_mgw-diamond-h_….jpg" }
  ],
  "suggestions": []
 }
 ```

- `type` **shall** be one of `page | product | market | story | news | download`
+- `type` **shall** be one of `page | product | market | solution | story | news |
+  download`
  (mapping table in the renderer; unknown index types pass through verbatim).
 - `teaser` carries the highlighted fragment (`<mark>…</mark>`, fragments joined
  with " ... ") when highlighting applies, otherwise a plain 250-character excerpt
@@ -1085,6 +1092,10 @@ identifier).
 - `url` follows the shared link contract: root-relative, resolved server-side.
  `download` results point at the forced-download endpoint `/download/<slug>`
  (5.3) - front ends should present them as file downloads.
+- `image` is a processed tile image (640 px wide, root-relative) or `null`.
+  Sources: products `image` (fallback `productimage`), stories `card_image`
+  (fallback `hero_bgimage`), markets/solutions `image`, news `fal_media`;
+  pages and downloads carry none.
 - `facets.type` carries the per-type counts for filter tabs, ordered by count.
  While a `filter` is active the counts remain those of the unfiltered query, so
  tabs do not collapse - except when the filtered result is empty, where only
@@ -1102,11 +1113,16 @@ resolvable public URL - products, markets (only those with `detail_page`),
 use cases, news (`type = 0`; "page as news" records are excluded because their
 target pages are already indexed) and downloads (`private_download = 0 AND
 hideonwebsite = 0`; their `content` additionally carries the file text extracted
-through Apache Tika, so datasheet specifications are searchable). Solutions are not indexed until they carry slugs or detail
-pages. Ranking boosts products (^10) and stories (^2). Every executed search is
+through Apache Tika, so datasheet specifications are searchable). Solutions are indexed like markets (`detail_page > 0`). Stories include their
+body - the inline `tt_content` children - and both page and story content
+include the text columns of the market/solution Content Blocks and the
+collection children (`vitec_items`, `vitec_faq_items`). Ranking boosts products
+(^10) and stories (^2); news decay with age by their publication date
+(`datetime` mapped to `created` - `crdate` is the import date), all other
+types are exempt. Every executed search is
 logged to `tx_solr_statistics` with the last two IP octets masked.

-**Autocomplete.** `GET /search?type=7384&tx_solr[queryString]=<input>` answers as
+**Autocomplete.** `GET /_json/search?type=7384&tx_solr[queryString]=<input>` answers as
 a lean JSON page type without the page envelope:

 ```json
@@ -1120,14 +1136,17 @@ wired as **USER_INT** - the example shipped with EXT:solr predates TYPO3 v14
 (`config.no_cache` no longer exists), and a cached USER would pin the first
 query’s suggestions for every later request. Front ends should debounce
 (~200 ms), start at 2-3 characters, and turn a picked suggestion into a
-regular `/search?q=` request. Top-result documents are deliberately disabled
+regular `/_json/search?q=` request. Top-result documents are deliberately disabled
 (`showTopResults = 0`): their shape is hardcoded upstream and carries the raw
 document type and the full indexed content.

 **Operations.** Indexing runs automatically: record and page saves enter the
 index queue, a scheduler task (Index Queue Worker, every 5 minutes) pushes them
 to Solr; the CLI command `vitec:solr-index` (with `--initialize` and `--debug`)
-covers manual runs - EXT:solr 14 ships no console commands of its own. Page
+covers manual runs - EXT:solr 14 ships no console commands of its own. Versions:
+EXT:solr 14.0.2 and the matching image `typo3solr/ext-solr:14.0.2` (Solr 10);
+an image upgrade needs a fresh volume, because an existing volume keeps its
+old configset - managed synonyms are restored through the REST API. Page
 content is extracted from the page’s `tt_content` rows via
 `index.queue.pages.fields.content` because the headless JSON output carries no
 `TYPO3SEARCH` markers.
@@ -1538,4 +1557,4 @@ remediation.
 - Header convention — the uniform header section across CEs, plugins and containers.
 - `Configuration/Sets/Vitecset/setup.typoscript` — the single TypoScript entry point.

-*End of document EVO‑VITEC‑HL‑001 v1.19.*
+*End of document EVO‑VITEC‑HL‑001 v1.21.*
@@ -23,8 +23,8 @@
    <meta name="twitter:description" content="Enterprise IPTV, video streaming, and digital signage solutions." />
    <link rel="icon" type="image/svg+xml" href="/fileadmin/icons/favicon.ico" />
    <title>VITEC</title>
-    <script type="module" crossorigin src="/_frontend/assets/index-BpTqLcih.js"></script>
-    <link rel="stylesheet" crossorigin href="/_frontend/assets/index-CAiVTATb.css">
+    <script type="module" crossorigin src="/_frontend/assets/index-CEaqwHyi.js"></script>
+    <link rel="stylesheet" crossorigin href="/_frontend/assets/index-CgBOr71d.css">
  </head>
  <body>
    <div id="page"></div>␍
@@ -81,7 +81,7 @@
    const val = input.value.trim();
    if (val.length < 2) { dd.classList.remove('open'); return; }
    debounceTimer = setTimeout(async () => {
-      const url = '/search?type=7384&tx_solr[queryString]=' + encodeURIComponent(val);
+      const url = '/_json/search?type=7384&tx_solr[queryString]=' + encodeURIComponent(val);
      const j = await (await fetch(url)).json();
      const terms = Object.entries(j.suggestions || {});
      dd.innerHTML = terms.map(([t, c]) =>
@@ -106,7 +106,7 @@
  // ---- Suche: GET /search?q=...&filter=...&page=... ----
  async function runSearch(q, filter, page) {
    if (!q) return;
-    const url = '/search?q=' + encodeURIComponent(q)
+    const url = '/_json/search?q=' + encodeURIComponent(q)
      + (filter ? '&filter=' + filter : '') + (page > 1 ? '&page=' + page : '');
    const json = await (await fetch(url)).json();
    const s = json.content.colPos0[0].content.search;