Add script to validate a single article + docs

libraries/from-bodyxml/readme.md

@@ -0,0 +1,31 @@
+a library (and cli) for creating a (transit) content-tree from a bodyXML
+
+## Testing
+
+### Generate a bodyTree from a content api URL
+
+```
+curl "$CONTENT_API_HOST/internalcontent/9e9192ba-02f1-4034-aaf0-200270d0f6d7?apiKey=$CONTENT_API_READ_KEY" | jq '.bodyXML' -r | node libraries/from-bodyxml/cli.js
+```
+
+### Validate from-bodyxml's output against the schema
+
+Ensure you have the environment variables:
+
+- CONTENT_API_HOST
+- CONTENT_API_READ_KEY
+
+```
+ node libraries/from-bodyxml/validate.js  9e9192ba-02f1-4034-aaf0-200270d0f6d7
+```
+
+### Validate articles published in the last 5 minutes
+
+Ensure you have the environment variables:
+
+- CONTENT_API_HOST
+- CONTENT_API_READ_KEY
+
+```
+node --test libraries/from-bodyxml/smoke-test.js
+```

libraries/from-bodyxml/validate.js

@@ -0,0 +1,90 @@
+import assert from "node:assert";
+import fromBodyXML from "./index.js";
+import Ajv from "ajv";
+import fs from "node:fs";
+import path from "node:path";
+import test from "node:test";
+import { fileURLToPath } from "url";
+import { dirname } from "path";
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const apiHost = process.env.CONTENT_API_HOST || "https://api-t.ft.com";
+const apiKey = process.env.CONTENT_API_READ_KEY;
+const uuid = process.argv[2];
+
+const transitTreeSchemaFile = fs.readFileSync(
+  path.resolve(__dirname, "../../schemas/transit-tree.schema.json")
+);
+
+const transitTreeSchema = JSON.parse(transitTreeSchemaFile);
+
+const ajv = new Ajv();
+
+const validate = ajv.compile(transitTreeSchema);
+
+/**
+ * Gets the value from an object based on an AJV instancePath.
+ *
+ * @param {Object} obj - The JSON object to navigate.
+ * @param {string} instancePath - The AJV instancePath (e.g., "/body/children/14/type").
+ * @returns {*} - The value at the given instancePath, or undefined if the path does not exist.
+ */
+function getValueAtInstancePath(obj, instancePath) {
+  // Split the path into parts, ignoring the leading "/"
+  const parts = instancePath.split("/").filter(Boolean);
+
+  // Navigate through the object
+  return parts.reduce((acc, key) => {
+    // Convert array indices from string to number
+    const index = Number(key);
+    return acc && !isNaN(index) ? acc[index] : acc?.[key];
+  }, obj);
+}
+
+async function fetchArticleFromCAPI(uuid) {
+  try {
+    const response = await fetch(`${apiHost}/internalcontent/${uuid}`, {
+      headers: {
+        "Content-Type": "application/json",
+        "x-api-key": apiKey ?? "",
+      },
+    });
+
+    if (!response.ok) {
+      throw new Error(`Error fetching ${apiUrl}: ${response.status}`);
+    }
+
+    const data = await response.json();
+    return data;
+  } catch (error) {
+    console.error("Error fetching ${apiUrl}:", error);
+  }
+}
+
+test("Validating " + uuid, async (t) => {
+  const article = await fetchArticleFromCAPI(uuid);
+  if (!article.bodyXML) {
+    console.log("No bodyXML");
+    t.skip("Skipping - no bodyXML");
+    return;
+  }
+
+  const bodyTree = fromBodyXML(article.bodyXML);
+  const isValid = validate(bodyTree);
+  // Add the erroneous value to the error message, for debugging
+  if (!isValid) {
+    validate.errors.forEach(
+      (error) =>
+        (error.instanceValue = getValueAtInstancePath(
+          bodyTree,
+          error.instancePath
+        ))
+    );
+  }
+  assert.ok(
+    isValid,
+    `Transit tree is invalid: ${JSON.stringify(validate.errors, null, 2)}`
+  );
+});