feat(runtime): implement single-article consolidation runtime and modularize codebase

2026-08-24 00:14:07 -03:00
parent e1e0be1353
commit 23de7d8fe7
176 changed files with 266754 additions and 10179 deletions
@@ -0,0 +1,97 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "https://schemas.aftech.internal/article-consolidation/v1/article-input.schema.json",
+  "x-contract-version": "1.0.0",
+  "title": "ArticleInputUnit",
+  "type": "object",
+  "required": [
+    "selected_extractor"
+  ],
+  "properties": {
+    "articles": false,
+    "selected_extractor": {
+      "type": "string",
+      "enum": ["trafilatura", "newspaper4k", "readability"]
+    },
+    "crawled_url": {
+      "type": ["string", "null"]
+    },
+    "error_message": {
+      "type": ["string", "null"]
+    },
+    "extraction_status": {
+      "type": ["string", "null"]
+    },
+    "http_status": {
+      "type": ["integer", "null"]
+    },
+    "input_meta": {
+      "type": ["object", "null"],
+      "properties": {
+        "url": { "type": ["string", "null"] },
+        "titulo": { "type": ["string", "null"] },
+        "subtitulo": { "type": ["string", "null"] },
+        "quando_publicado": { "type": ["string", "null"] }
+      },
+      "additionalProperties": true
+    },
+    "page_title": {
+      "type": ["string", "null"]
+    },
+    "trafilatura": {
+      "type": ["object", "null"],
+      "properties": {
+        "title": { "type": ["string", "null"] },
+        "author": { "type": ["string", "null"] },
+        "date": { "type": ["string", "null"] },
+        "description": { "type": ["string", "null"] },
+        "text": { "type": ["string", "null"] },
+        "markdown": { "type": ["string", "null"] },
+        "canonical_url": { "type": ["string", "null"] },
+        "image": { "type": ["string", "null"] },
+        "language": { "type": ["string", "null"] },
+        "sitename": { "type": ["string", "null"] },
+        "categories": { "type": "array", "items": { "type": "string" } },
+        "tags": { "type": "array", "items": { "type": "string" } },
+        "raw_json": { "type": ["object", "string", "null"] },
+        "pagetype": { "type": ["string", "null"] },
+        "error": { "type": ["string", "null"] }
+      },
+      "additionalProperties": true
+    },
+    "newspaper4k": {
+      "type": ["object", "null"],
+      "properties": {
+        "title": { "type": ["string", "null"] },
+        "authors": { "type": "array", "items": { "type": "string" } },
+        "publish_date": { "type": ["string", "null"] },
+        "meta_description": { "type": ["string", "null"] },
+        "text": { "type": ["string", "null"] },
+        "article_html": { "type": ["string", "null"] },
+        "canonical_link": { "type": ["string", "null"] },
+        "top_image": { "type": ["string", "null"] },
+        "images": { "type": "array", "items": { "type": "string" } },
+        "meta_data": { "type": "object" },
+        "meta_lang": { "type": ["string", "null"] },
+        "meta_site_name": { "type": ["string", "null"] },
+        "tags": { "type": "array", "items": { "type": "string" } },
+        "keywords": { "type": "array", "items": { "type": "string" } },
+        "error": { "type": ["string", "null"] }
+      },
+      "additionalProperties": true
+    },
+    "readability": {
+      "type": ["object", "null"],
+      "properties": {
+        "title": { "type": ["string", "null"] },
+        "short_title": { "type": ["string", "null"] },
+        "author": { "type": ["string", "null"] },
+        "cleaned_text": { "type": ["string", "null"] },
+        "cleaned_html": { "type": ["string", "null"] },
+        "error": { "type": ["string", "null"] }
+      },
+      "additionalProperties": true
+    }
+  },
+  "additionalProperties": true
+}