canada-api 5.1.6 → 5.1.7

package/README.md

@@ -9,7 +9,7 @@ Cross platform API for fetching public data from [canada.ca](https://www.canada.
 ## Browser
 
 ```html
-<script src="https://cdn.jsdelivr.net/npm/canada-api@5.1.6"></script>
+<script src="https://cdn.jsdelivr.net/npm/canada-api@5.1.7"></script>
 ```
 
 ## Node 18+
@@ -72,9 +72,9 @@ Fetches and parses the sitemap for the given page, returning its child pages. En
 ### `ca.content(url)`
 
 - `url` {string|URL} - Absolute or relative URL
-- Returns: {Promise} Fulfills with a response whose `data` is the raw HTML string
+- Returns: {Promise} Fulfills with a response whose `data` is the raw HTML string, or parsed JSON for DAM asset URLs
 
-Retrieves the HTML content of the page.
+Retrieves the HTML content of the page. DAM asset URLs under `/content/dam/` are passed through without forcing a `.html` suffix.
 
 ```json
 {
@@ -90,9 +90,9 @@ Retrieves the HTML content of the page.
 ### `ca.meta(url)`
 
 - `url` {string|URL} - Absolute or relative URL
-- Returns: {Promise} Fulfills with a response whose `data` is a formatted metadata object
+- Returns: {Promise} Fulfills with a response whose `data` is a formatted metadata object, or parsed JSON for DAM asset URLs
 
-Fetches JCR metadata for the given page. The following transformations are applied:
+Fetches JCR metadata for the given page. For DAM asset URLs under `/content/dam/`, the asset JSON response is returned. The following transformations are applied to page metadata:
 
 - String `"true"` / `"false"` values are converted to booleans
 - `@TypeHint` properties are removed
@@ -152,7 +152,7 @@ API multiplateforme pour récupérer des données publiques de [canada.ca](https
 ## Navigateur
 
 ```html
-<script src="https://cdn.jsdelivr.net/npm/canada-api@5.1.6"></script>
+<script src="https://cdn.jsdelivr.net/npm/canada-api@5.1.7"></script>
 ```
 
 ## Node 18+
@@ -207,9 +207,9 @@ Récupère et analyse le plan de site de la page donnée, retournant ses pages e
 ### `ca.content(url)`
 
 - `url` {string|URL} - URL absolue ou relative
-- Retourne: {Promise} Résout avec une réponse dont `data` est la chaîne HTML brute
+- Retourne: {Promise} Résout avec une réponse dont `data` est la chaîne HTML brute, ou le JSON analysé pour les URL d'actifs DAM
 
-Récupère le contenu HTML de la page.
+Récupère le contenu HTML de la page. Les URL d'actifs DAM sous `/content/dam/` sont transmises sans forcer le suffixe `.html`.
 
 ```json
 {
@@ -225,9 +225,9 @@ Récupère le contenu HTML de la page.
 ### `ca.meta(url)`
 
 - `url` {string|URL} - URL absolue ou relative
-- Retourne: {Promise} Résout avec une réponse dont `data` est un objet de métadonnées formaté
+- Retourne: {Promise} Résout avec une réponse dont `data` est un objet de métadonnées formaté, ou le JSON analysé pour les URL d'actifs DAM
 
-Récupère les métadonnées JCR de la page donnée. Les transformations suivantes sont appliquées :
+Récupère les métadonnées JCR de la page donnée. Pour les URL d'actifs DAM sous `/content/dam/`, la réponse JSON de l'actif est retournée. Les transformations suivantes sont appliquées aux métadonnées de page :
 
 - Les valeurs `"true"` / `"false"` sont converties en booléens
 - Les propriétés `@TypeHint` sont supprimées

package/dist/ca.js

@@ -1 +1 @@
-!function(t,e){"object"==typeof exports&&"object"==typeof module?module.exports=e():"function"==typeof define&&define.amd?define("ca",[],e):"object"==typeof exports?exports.ca=e():t.ca=e()}(Object("undefined"!=typeof self?self:this),()=>(()=>{"use strict";var t={d:(e,r)=>{for(var a in r)t.o(r,a)&&!t.o(e,a)&&Object.defineProperty(e,a,{enumerable:!0,get:r[a]})},o:(t,e)=>Object.prototype.hasOwnProperty.call(t,e)},e={};t.d(e,{default:()=>c});const r="https://www.canada.ca",a=t=>{if("string"==typeof t)t=new URL(t,r);else{if(!(t instanceof URL))throw new TypeError("string or URL object expected");t=new URL(t.href)}if(t.origin!==r)throw new Error("URL must start with "+r);if(t.pathname=t.pathname.replace(/^\/content\/canadasite/,""),t.pathname=t.pathname.replace(/\.[^/]*$/,"").replace(/\/+$/,""),!t.pathname.startsWith("/en/")&&!t.pathname.startsWith("/fr/"))throw new Error(`Invalid path: "${t.pathname}" must start with /en/ or /fr/`);return t},n=async(t,e={})=>{(t=new URL(t,r)).searchParams.set("_",Date.now());const{headers:a={},...n}=e;let o;try{o=await fetch(t,{signal:AbortSignal.timeout(3e4),...n,headers:{"User-Agent":"canada-api/5.1.6",Accept:"*/*",...a}})}catch(e){throw e.url=t.toString(),e}if(!o.ok){const e=new Error(`Request to ${t} failed: ${o.status} ${o.statusText}`);throw e.url=t.toString(),e}let s=await o.text();const c=o.headers.get("content-type")?.includes("application/json");if(c)try{s=JSON.parse(s)}catch(e){const r=new Error(`Failed to parse JSON response from ${t}: ${e.message}`);throw r.url=t.toString(),r}return{data:s,status:o.status,statusText:o.statusText,headers:Object.fromEntries(o.headers)}},o={Jan:"01",Feb:"02",Mar:"03",Apr:"04",May:"05",Jun:"06",Jul:"07",Aug:"08",Sep:"09",Oct:"10",Nov:"11",Dec:"12"};function s(t){if(/^\d{4}-\d{2}-\d{2}$/.test(t))return new Date(t).toISOString();let e=/^\w{3} (\w{3}) (\d{2}) (\d{4}) ([\d:]{8}) GMT([\-+]\d{4})$/.exec(t);return e?new Date(`${e[3]}-${o[e[1]]}-${e[2]}T${e[4]}${e[5]}`).toISOString():t}const c={normalize:a,request:n,children:async t=>{const e=a(t);e.pathname+=".sitemap.xml";const r=await n(e,{redirect:"error"});return r.data=[...r.data.matchAll(/<url>([\s\S]*?)<\/url>/g)].map(([,t])=>{const e=t.match(/<loc>([\s\S]*?)<\/loc>/)?.[1],r=t.match(/<lastmod>([\s\S]*?)<\/lastmod>/)?.[1];return{loc:e,lastmod:r}}).filter(t=>t.loc).map(t=>({path:a(t.loc).pathname,lastmod:t.lastmod?new Date(t.lastmod).toISOString():null})),r},content:async t=>{const e=a(t);return e.pathname+=".html",n(e,{redirect:"error"})},meta:async t=>{const e=a(t);e.pathname+="/_jcr_content.json";const r=await n(e,{redirect:"error"});return r.data=(t=>{const e={};for(const[r,n]of Object.entries(t))r.endsWith("@TypeHint")||Array.isArray(n)&&0===n.length||("true"===n?e[r]=!0:"false"===n?e[r]=!1:"gcAltLanguagePeer"===r?(e[r]=n,e.peer=a(n).pathname):e[r]="string"==typeof n?s(n.trim()):n);return Object.keys(e).sort().reduce((t,r)=>(t[r]=e[r],t),{})})(r.data),r}};return e.default})());
+!function(t,e){"object"==typeof exports&&"object"==typeof module?module.exports=e():"function"==typeof define&&define.amd?define("ca",[],e):"object"==typeof exports?exports.ca=e():t.ca=e()}(Object("undefined"!=typeof self?self:this),()=>(()=>{"use strict";var t={d:(e,a)=>{for(var r in a)t.o(a,r)&&!t.o(e,r)&&Object.defineProperty(e,r,{enumerable:!0,get:a[r]})},o:(t,e)=>Object.prototype.hasOwnProperty.call(t,e)},e={};t.d(e,{default:()=>c});const a="https://www.canada.ca",r=t=>{if("string"==typeof t)t=new URL(t,a);else{if(!(t instanceof URL))throw new TypeError("string or URL object expected");t=new URL(t.href)}if(t.origin!==a)throw new Error("URL must start with "+a);if(t.pathname.startsWith("/content/dam/"))return t;if(t.pathname=t.pathname.replace(/^\/content\/canadasite/,""),t.pathname=t.pathname.replace(/\/+$/,""),t.pathname=t.pathname.replace(/\.[^/]*$/,""),!t.pathname.startsWith("/en/")&&!t.pathname.startsWith("/fr/"))throw new Error(`Invalid path: "${t.pathname}" must start with /en/ or /fr/`);return t},n=async(t,e={})=>{(t=new URL(t,a)).searchParams.set("_",Date.now());const{headers:r={},...n}=e;let o;try{o=await fetch(t,{signal:AbortSignal.timeout(3e4),...n,headers:{"User-Agent":"canada-api/5.1.7",Accept:"*/*",...r}})}catch(e){throw e.url=t.toString(),e}if(!o.ok){const e=new Error(`Request to ${t} failed: ${o.status} ${o.statusText}`);throw e.url=t.toString(),e}let s=await o.text();const c=o.headers.get("content-type")?.includes("application/json");if(c)try{s=JSON.parse(s)}catch(e){const a=new Error(`Failed to parse JSON response from ${t}: ${e.message}`);throw a.url=t.toString(),a}return{data:s,status:o.status,statusText:o.statusText,headers:Object.fromEntries(o.headers)}},o={Jan:"01",Feb:"02",Mar:"03",Apr:"04",May:"05",Jun:"06",Jul:"07",Aug:"08",Sep:"09",Oct:"10",Nov:"11",Dec:"12"};function s(t){if(/^\d{4}-\d{2}-\d{2}$/.test(t))return new Date(t).toISOString();let e=/^\w{3} (\w{3}) (\d{2}) (\d{4}) ([\d:]{8}) GMT([\-+]\d{4})$/.exec(t);return e?new Date(`${e[3]}-${o[e[1]]}-${e[2]}T${e[4]}${e[5]}`).toISOString():t}const c={normalize:r,request:n,children:async t=>{const e=r(t);if(e.pathname.startsWith("/content/dam/"))throw new Error(`children not available for DAM assets: "${e.pathname}"`);e.pathname+=".sitemap.xml";const a=await n(e,{redirect:"error"});return a.data=[...a.data.matchAll(/<url>([\s\S]*?)<\/url>/g)].map(([,t])=>{const e=t.match(/<loc>([\s\S]*?)<\/loc>/)?.[1],a=t.match(/<lastmod>([\s\S]*?)<\/lastmod>/)?.[1];return{loc:e,lastmod:a}}).filter(t=>t.loc).map(t=>({path:r(t.loc).pathname,lastmod:t.lastmod?new Date(t.lastmod).toISOString():null})),a},content:async t=>{const e=r(t);return e.pathname.startsWith("/content/dam/")||(e.pathname+=".html"),n(e,{redirect:"error"})},meta:async t=>{const e=r(t);e.pathname.startsWith("/content/dam/")?e.pathname+="/.json":e.pathname+="/_jcr_content.json";const a=await n(e,{redirect:"error"});return a.data=(t=>{const e={};for(const[a,n]of Object.entries(t))a.endsWith("@TypeHint")||Array.isArray(n)&&0===n.length||("true"===n?e[a]=!0:"false"===n?e[a]=!1:"gcAltLanguagePeer"===a?(e[a]=n,e.peer=r(n).pathname):e[a]="string"==typeof n?s(n.trim()):n);return Object.keys(e).sort().reduce((t,a)=>(t[a]=e[a],t),{})})(a.data),a}};return e.default})());

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "canada-api",
-	"version": "5.1.6",
+	"version": "5.1.7",
 	"description": "Cross platform API to fetch data from canada.ca",
 	"type": "module",
 	"main": "src/index.js",

package/src/children.js

@@ -10,7 +10,7 @@ import request from "./request.js";
 
 /**
  * Parse XML sitemap data into structured URL entries
- * @param {string} data - Raw XML sitemap content
+ * @param {string} xml - Raw XML sitemap content
  * @returns {SitemapEntry[]} Array of sitemap entries with path and lastmod. Entries missing a `<loc>` element are skipped.
  */
 export const parseSitemap = (xml) => {
@@ -29,12 +29,17 @@ export const parseSitemap = (xml) => {
 
 /**
  * Fetch and parse sitemap children for a canada.ca page
- * @param {string|URL} url - Absolute or relative URL
+ * @param {string|URL} url - Absolute or relative URL for a canada.ca page
  * @returns {Promise<{data: SitemapEntry[], status: number, statusText: string, headers: object}>}
- * @throws {Error} If the request fails or returns a non-2xx status
+ * @throws {Error} If the URL points to a DAM asset path or if the request fails/returns a non-2xx status
  */
 const children = async (url) => {
     const target = normalize(url);
+
+    if (target.pathname.startsWith('/content/dam/')) {
+        throw new Error(`children not available for DAM assets: "${target.pathname}"`);
+    }
+
     target.pathname += '.sitemap.xml';
 
     const response = await request(target, {

package/src/content.js

@@ -2,14 +2,17 @@ import normalize from "./normalize.js";
 import request from "./request.js";
 
 /**
- * Fetch HTML content for a canada.ca page
+ * Fetch content for a canada.ca page or DAM asset
  * @param {string|URL} url - Absolute or relative URL
- * @returns {Promise<{data: string, status: number, statusText: string, headers: object}>}
+ * @returns {Promise<{data: string|object, status: number, statusText: string, headers: object}>}
  * @throws {Error} If the request fails or returns a non-2xx status
  */
 const content = async (url) => {
     const target = normalize(url);
-    target.pathname += '.html';
+
+    if (!target.pathname.startsWith('/content/dam/')) {
+        target.pathname += '.html';
+    }
 
     return request(target, {
         redirect: 'error'

package/src/meta.js

@@ -81,14 +81,19 @@ export const formatMeta = (data) => {
 }
 
 /**
- * Fetch and format JCR metadata for a canada.ca page
+ * Fetch and format metadata
  * @param {string|URL} url - Absolute or relative URL
- * @returns {Promise<{data: Record<string, any>, status: number, statusText: string, headers: object}>}
+ * @returns {Promise<{data: Record<string, any>|any, status: number, statusText: string, headers: object}>}
  * @throws {Error} If the request fails or returns a non-2xx status
  */
 const meta = async (url) => {
     const target = normalize(url);
-    target.pathname += '/_jcr_content.json';
+
+    if (target.pathname.startsWith('/content/dam/')) {
+        target.pathname += '/.json'
+    } else {
+        target.pathname += '/_jcr_content.json';
+    }
 
     const response = await request(target, {
         redirect: 'error'

package/src/normalize.js

@@ -2,10 +2,10 @@ import { BASE_URL } from './config.js';
 
 /**
  * Normalize a canada.ca URL to a clean pathname
- * @param {string|URL} url - A full URL or relative path (e.g., 'https://www.canada.ca/en/page' or '/en/page')
- * @returns {URL} Normalized URL object with cleaned pathname
+ * @param {string|URL} url - A full URL or relative path (e.g., 'https://www.canada.ca/en/page', '/en/page', or '/content/dam/...')
+ * @returns {URL} Normalized URL object with a cleaned pathname
  * @throws {TypeError} If url is not a string or URL object
- * @throws {Error} If URL is not from canada.ca or path doesn't start with /en/ or /fr/
+ * @throws {Error} If URL is not from canada.ca or the path doesn't start with /en/, /fr/, or /content/dam/
  */
 const normalize = (url) => {
 
@@ -22,10 +22,16 @@ const normalize = (url) => {
         throw new Error('URL must start with ' + BASE_URL)
     }
 
+    // No normalization for DAM asset paths
+    if (url.pathname.startsWith('/content/dam/')) {
+        return url
+    }
+
     url.pathname = url.pathname.replace(/^\/content\/canadasite/, '');
+    url.pathname = url.pathname.replace(/\/+$/, '');
 
-    // Remove file extensions (like .html, .xml) and trailing slashes
-    url.pathname = url.pathname.replace(/\.[^/]*$/, '').replace(/\/+$/, '');
+    // Remove file extensions (like .html, .xml)
+    url.pathname = url.pathname.replace(/\.[^/]*$/, '');
 
     // Verify root language
     if (!url.pathname.startsWith('/en/') && !url.pathname.startsWith('/fr/')) {

package/src/request.js

@@ -22,7 +22,7 @@ const request = async (url, options = {}) => {
             signal: AbortSignal.timeout(DEFAULT_TIMEOUT),
             ...requestOptions,
             headers: {
-                'User-Agent': 'canada-api/5.1.6',
+                'User-Agent': 'canada-api/5.1.7',
                 'Accept': '*/*',
                 ...customHeaders
             }