@lde/distribution-probe 0.1.3 → 0.1.5

package/dist/probe.d.ts

@@ -46,8 +46,14 @@ declare abstract class ProbeResult {
  * Result of probing a SPARQL endpoint.
  */
 export declare class SparqlProbeResult extends ProbeResult {
-    readonly acceptedContentType: string;
-    constructor(url: string, response: Response, responseTimeMs: number, acceptedContentType: string, failureReason?: string | null);
+    /**
+     * Content types the probe was prepared to accept as a valid answer. A SELECT or
+     * ASK query may be answered with SPARQL results in JSON or XML; the endpoint
+     * chooses, so success is not tied to a single serialization. A single string is
+     * accepted and normalized to a one-element list for backwards compatibility.
+     */
+    readonly acceptedContentTypes: readonly string[];
+    constructor(url: string, response: Response, responseTimeMs: number, acceptedContentTypes: string | readonly string[], failureReason?: string | null);
     isSuccess(): boolean;
 }
 /**

package/dist/probe.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"probe.d.ts","sourceRoot":"","sources":["../src/probe.ts"],"names":[],"mappings":"AAAA,OAAO,EAAyB,YAAY,EAAE,MAAM,cAAc,CAAC;AAGnE;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,0DAA0D;IAC1D,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB;;;;;OAKG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAKD;;GAEG;AACH,qBAAa,YAAY;aAEL,GAAG,EAAE,MAAM;aACX,OAAO,EAAE,MAAM;aACf,cAAc,EAAE,MAAM;gBAFtB,GAAG,EAAE,MAAM,EACX,OAAO,EAAE,MAAM,EACf,cAAc,EAAE,MAAM;CAEzC;AAED;;GAEG;AACH,uBAAe,WAAW;aAUN,GAAG,EAAE,MAAM;IAT7B,SAAgB,UAAU,EAAE,MAAM,CAAC;IACnC,SAAgB,UAAU,EAAE,MAAM,CAAC;IACnC,SAAgB,YAAY,EAAE,IAAI,GAAG,IAAI,CAAQ;IACjD,SAAgB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3C,SAAgB,aAAa,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7C,SAAgB,QAAQ,EAAE,MAAM,EAAE,CAAM;IACxC,SAAgB,cAAc,EAAE,MAAM,CAAC;gBAGrB,GAAG,EAAE,MAAM,EAC3B,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,aAAa,GAAE,MAAM,GAAG,IAAW;IAa9B,SAAS,IAAI,OAAO;CAO5B;AAKD;;GAEG;AACH,qBAAa,iBAAkB,SAAQ,WAAW;IAChD,SAAgB,mBAAmB,EAAE,MAAM,CAAC;gBAG1C,GAAG,EAAE,MAAM,EACX,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,mBAAmB,EAAE,MAAM,EAC3B,aAAa,GAAE,MAAM,GAAG,IAAW;IAM5B,SAAS,IAAI,OAAO;CAM9B;AAED;;GAEG;AACH,qBAAa,mBAAoB,SAAQ,WAAW;IAClD,SAAgB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;gBAGhD,GAAG,EAAE,MAAM,EACX,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,aAAa,GAAE,MAAM,GAAG,IAAW;CAQtC;AAED,MAAM,MAAM,eAAe,GACvB,iBAAiB,GACjB,mBAAmB,GACnB,YAAY,CAAC;AAIjB;;;;;;;;GAQG;AACH,wBAAsB,KAAK,CACzB,YAAY,EAAE,YAAY,EAC1B,OAAO,CAAC,EAAE,YAAY,GACrB,OAAO,CAAC,eAAe,CAAC,CAkC1B"}
+{"version":3,"file":"probe.d.ts","sourceRoot":"","sources":["../src/probe.ts"],"names":[],"mappings":"AAAA,OAAO,EAAyB,YAAY,EAAE,MAAM,cAAc,CAAC;AAGnE;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,0DAA0D;IAC1D,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB;;;OAGG;IACH,OAAO,CAAC,EAAE,OAAO,CAAC;IAClB;;;;;OAKG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;CACtB;AAKD;;GAEG;AACH,qBAAa,YAAY;aAEL,GAAG,EAAE,MAAM;aACX,OAAO,EAAE,MAAM;aACf,cAAc,EAAE,MAAM;gBAFtB,GAAG,EAAE,MAAM,EACX,OAAO,EAAE,MAAM,EACf,cAAc,EAAE,MAAM;CAEzC;AAED;;GAEG;AACH,uBAAe,WAAW;aAUN,GAAG,EAAE,MAAM;IAT7B,SAAgB,UAAU,EAAE,MAAM,CAAC;IACnC,SAAgB,UAAU,EAAE,MAAM,CAAC;IACnC,SAAgB,YAAY,EAAE,IAAI,GAAG,IAAI,CAAQ;IACjD,SAAgB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAC;IAC3C,SAAgB,aAAa,EAAE,MAAM,GAAG,IAAI,CAAC;IAC7C,SAAgB,QAAQ,EAAE,MAAM,EAAE,CAAM;IACxC,SAAgB,cAAc,EAAE,MAAM,CAAC;gBAGrB,GAAG,EAAE,MAAM,EAC3B,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,aAAa,GAAE,MAAM,GAAG,IAAW;IAa9B,SAAS,IAAI,OAAO;CAO5B;AAMD;;GAEG;AACH,qBAAa,iBAAkB,SAAQ,WAAW;IAChD;;;;;OAKG;IACH,SAAgB,oBAAoB,EAAE,SAAS,MAAM,EAAE,CAAC;gBAGtD,GAAG,EAAE,MAAM,EACX,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,oBAAoB,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,EAChD,aAAa,GAAE,MAAM,GAAG,IAAW;IAS5B,SAAS,IAAI,OAAO;CAQ9B;AAED;;GAEG;AACH,qBAAa,mBAAoB,SAAQ,WAAW;IAClD,SAAgB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;gBAGhD,GAAG,EAAE,MAAM,EACX,QAAQ,EAAE,QAAQ,EAClB,cAAc,EAAE,MAAM,EACtB,aAAa,GAAE,MAAM,GAAG,IAAW;CAQtC;AAED,MAAM,MAAM,eAAe,GACvB,iBAAiB,GACjB,mBAAmB,GACnB,YAAY,CAAC;AAIjB;;;;;;;;GAQG;AACH,wBAAsB,KAAK,CACzB,YAAY,EAAE,YAAY,EAC1B,OAAO,CAAC,EAAE,YAAY,GACrB,OAAO,CAAC,eAAe,CAAC,CAkC1B"}

package/dist/probe.js

@@ -46,19 +46,29 @@ class ProbeResult {
     }
 }
 const SPARQL_RESULTS_JSON = 'application/sparql-results+json';
+const SPARQL_RESULTS_XML = 'application/sparql-results+xml';
 const SPARQL_RDF_RESULTS = 'application/n-triples';
 /**
  * Result of probing a SPARQL endpoint.
  */
 export class SparqlProbeResult extends ProbeResult {
-    acceptedContentType;
-    constructor(url, response, responseTimeMs, acceptedContentType, failureReason = null) {
+    /**
+     * Content types the probe was prepared to accept as a valid answer. A SELECT or
+     * ASK query may be answered with SPARQL results in JSON or XML; the endpoint
+     * chooses, so success is not tied to a single serialization. A single string is
+     * accepted and normalized to a one-element list for backwards compatibility.
+     */
+    acceptedContentTypes;
+    constructor(url, response, responseTimeMs, acceptedContentTypes, failureReason = null) {
         super(url, response, responseTimeMs, failureReason);
-        this.acceptedContentType = acceptedContentType;
+        this.acceptedContentTypes =
+            typeof acceptedContentTypes === 'string'
+                ? [acceptedContentTypes]
+                : acceptedContentTypes;
     }
     isSuccess() {
         return (super.isSuccess() &&
-            (this.contentType?.startsWith(this.acceptedContentType) ?? false));
+            this.acceptedContentTypes.some((type) => this.contentType?.startsWith(type) ?? false));
     }
 }
 /**
@@ -137,18 +147,33 @@ function detectSparqlQueryType(query) {
     const match = /\b(ASK|SELECT|CONSTRUCT|DESCRIBE)\b/i.exec(withoutComments);
     return (match?.[1].toUpperCase() ?? 'SELECT');
 }
-function acceptHeaderForQueryType(queryType) {
+/**
+ * Content types a SPARQL endpoint may legitimately answer with, in preference
+ * order, for the given query type. SELECT and ASK return a results document
+ * (JSON or XML – the endpoint chooses); CONSTRUCT and DESCRIBE return RDF.
+ */
+function acceptableContentTypes(queryType) {
     if (queryType === 'ASK' || queryType === 'SELECT') {
-        return SPARQL_RESULTS_JSON;
+        return [SPARQL_RESULTS_JSON, SPARQL_RESULTS_XML];
     }
-    return SPARQL_RDF_RESULTS;
+    return [SPARQL_RDF_RESULTS];
+}
+/**
+ * Build an `Accept` header that prefers the first content type but still accepts
+ * the rest at a lower q-value, so an endpoint that only serves a later type is
+ * not rejected with a 406.
+ */
+function acceptHeader(contentTypes) {
+    return contentTypes
+        .map((type, index) => (index === 0 ? type : `${type};q=0.9`))
+        .join(', ');
 }
 async function probeSparqlEndpoint(url, _distribution, options, authHeaders, start) {
     const queryType = detectSparqlQueryType(options.sparqlQuery);
-    const accept = acceptHeaderForQueryType(queryType);
+    const acceptedContentTypes = acceptableContentTypes(queryType);
     const headers = new Headers({
         'Content-Type': 'application/x-www-form-urlencoded;charset=UTF-8',
-        Accept: accept,
+        Accept: acceptHeader(acceptedContentTypes),
     });
     for (const [key, value] of authHeaders) {
         headers.set(key, value);
@@ -160,19 +185,19 @@ async function probeSparqlEndpoint(url, _distribution, options, authHeaders, sta
         body: `query=${encodeURIComponent(options.sparqlQuery)}`,
     });
     const actualContentType = response.headers.get('Content-Type');
-    const contentTypeMatches = actualContentType?.startsWith(accept) ?? false;
+    const matchedContentType = acceptedContentTypes.find((type) => actualContentType?.startsWith(type) ?? false);
     let failureReason = null;
-    if (response.ok && contentTypeMatches) {
-        failureReason = await validateSparqlResponse(response, queryType);
+    if (response.ok && matchedContentType !== undefined) {
+        failureReason = await validateSparqlResponse(response, queryType, matchedContentType);
     }
     else {
         // Drain unconsumed body to release the underlying connection.
         await response.body?.cancel();
     }
     const responseTimeMs = Math.round(performance.now() - start);
-    return new SparqlProbeResult(url, response, responseTimeMs, accept, failureReason);
+    return new SparqlProbeResult(url, response, responseTimeMs, acceptedContentTypes, failureReason);
 }
-async function validateSparqlResponse(response, queryType) {
+async function validateSparqlResponse(response, queryType, contentType) {
     const body = await response.text();
     if (body.length === 0) {
         return 'SPARQL endpoint returned an empty response';
@@ -182,6 +207,11 @@ async function validateSparqlResponse(response, queryType) {
         // endpoint answered. Deep parse validation is the data-dump path’s job.
         return null;
     }
+    return contentType.startsWith(SPARQL_RESULTS_XML)
+        ? validateSparqlXmlResults(body, queryType)
+        : validateSparqlJsonResults(body, queryType);
+}
+function validateSparqlJsonResults(body, queryType) {
     let json;
     try {
         json = JSON.parse(body);
@@ -201,9 +231,38 @@ async function validateSparqlResponse(response, queryType) {
     }
     return null;
 }
+/**
+ * Lightweight structural check on a SPARQL Query Results XML document. Mirrors
+ * the JSON path’s intent – confirm the endpoint answered with the expected shape
+ * – without pulling in a full XML parser.
+ */
+function validateSparqlXmlResults(body, queryType) {
+    if (!/<sparql[\s>]/i.test(body)) {
+        return 'SPARQL endpoint returned invalid XML';
+    }
+    if (queryType === 'ASK') {
+        if (!/<boolean>\s*(true|false)\s*<\/boolean>/i.test(body)) {
+            return 'SPARQL endpoint did not return a valid ASK result';
+        }
+        return null;
+    }
+    // SELECT
+    if (!/<results[\s/>]/i.test(body)) {
+        return 'SPARQL endpoint did not return a valid results object';
+    }
+    return null;
+}
 async function probeDataDump(url, distribution, options, authHeaders, start) {
+    // Express a preference for the declared media type, but accept anything as a
+    // fallback. Servers that implement RFC 9110 §12.5.1 content negotiation will
+    // pick the declared type (preserving our ability to detect real Content-Type
+    // mismatches). Servers that reject any non-*/* Accept with 406 — notably
+    // Dataverse's /api/access/datafile/ endpoint (IQSS/dataverse#12410) — fall
+    // back to */* and return the file unchanged.
     const headers = new Headers({
-        Accept: distribution.mimeType ?? '*/*',
+        Accept: distribution.mimeType
+            ? `${distribution.mimeType}, */*;q=0.5`
+            : '*/*',
         'Accept-Encoding': 'identity',
     });
     for (const [key, value] of authHeaders) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lde/distribution-probe",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "repository": {
     "url": "git+https://github.com/ldelements/lde.git",
     "directory": "packages/distribution-probe"