@promptbook/website-crawler 0.75.1 → 0.75.3

package/esm/index.es.js

@@ -24,7 +24,7 @@ var BOOK_LANGUAGE_VERSION = '1.0.0';
  *
  * @see https://github.com/webgptorg/promptbook
  */
-var PROMPTBOOK_ENGINE_VERSION = '0.75.0';
+var PROMPTBOOK_ENGINE_VERSION = '0.75.2';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -1847,7 +1847,6 @@ function validatePipelineCore(pipeline) {
     while (unresovedTasks.length > 0) {
         _loop_3();
     }
-    // TODO: !!!!!! Test that pipeline interface implements declared formfactor interface
 }
 /**
  * TODO: !! [🧞‍♀️] Do not allow joker + foreach
@@ -2979,16 +2978,16 @@ function $registeredScrapersMessage() {
      * Mixes registered scrapers from $scrapersMetadataRegister and $scrapersRegister
      */
     var all = [];
-    var _loop_1 = function (packageName, className) {
+    var _loop_1 = function (packageName, className, mimeTypes, documentationUrl, isAvilableInBrowser) {
         if (all.some(function (item) { return item.packageName === packageName && item.className === className; })) {
             return "continue";
         }
-        all.push({ packageName: packageName, className: className });
+        all.push({ packageName: packageName, className: className, mimeTypes: mimeTypes, documentationUrl: documentationUrl, isAvilableInBrowser: isAvilableInBrowser });
     };
     try {
         for (var _c = __values($scrapersMetadataRegister.list()), _d = _c.next(); !_d.done; _d = _c.next()) {
-            var _e = _d.value, packageName = _e.packageName, className = _e.className;
-            _loop_1(packageName, className);
+            var _e = _d.value, packageName = _e.packageName, className = _e.className, mimeTypes = _e.mimeTypes, documentationUrl = _e.documentationUrl, isAvilableInBrowser = _e.isAvilableInBrowser;
+            _loop_1(packageName, className, mimeTypes, documentationUrl, isAvilableInBrowser);
         }
     }
     catch (e_1_1) { e_1 = { error: e_1_1 }; }
@@ -2998,16 +2997,16 @@ function $registeredScrapersMessage() {
         }
         finally { if (e_1) throw e_1.error; }
     }
-    var _loop_2 = function (packageName, className) {
+    var _loop_2 = function (packageName, className, mimeTypes, documentationUrl, isAvilableInBrowser) {
         if (all.some(function (item) { return item.packageName === packageName && item.className === className; })) {
             return "continue";
         }
-        all.push({ packageName: packageName, className: className });
+        all.push({ packageName: packageName, className: className, mimeTypes: mimeTypes, documentationUrl: documentationUrl, isAvilableInBrowser: isAvilableInBrowser });
     };
     try {
         for (var _f = __values($scrapersRegister.list()), _g = _f.next(); !_g.done; _g = _f.next()) {
-            var _h = _g.value, packageName = _h.packageName, className = _h.className;
-            _loop_2(packageName, className);
+            var _h = _g.value, packageName = _h.packageName, className = _h.className, mimeTypes = _h.mimeTypes, documentationUrl = _h.documentationUrl, isAvilableInBrowser = _h.isAvilableInBrowser;
+            _loop_2(packageName, className, mimeTypes, documentationUrl, isAvilableInBrowser);
         }
     }
     catch (e_2_1) { e_2 = { error: e_2_1 }; }
@@ -3037,29 +3036,33 @@ function $registeredScrapersMessage() {
     }
     return spaceTrim$1(function (block) { return "\n            Available scrapers are:\n            ".concat(block(metadata
         .map(function (_a, i) {
-        var packageName = _a.packageName, className = _a.className, isMetadataAviailable = _a.isMetadataAviailable, isInstalled = _a.isInstalled;
+        var packageName = _a.packageName, className = _a.className, isMetadataAviailable = _a.isMetadataAviailable, isInstalled = _a.isInstalled, mimeTypes = _a.mimeTypes, isAvilableInBrowser = _a.isAvilableInBrowser;
         var more;
+        // TODO: Use documentationUrl
         if (just(false)) {
             more = '';
         }
         else if (!isMetadataAviailable && !isInstalled) {
             // TODO: [�][�] Maybe do allow to do auto-install if package not registered and not found
-            more = "(not installed and no metadata, looks like a unexpected behavior)";
+            more = "*(not installed and no metadata, looks like a unexpected behavior)*";
         }
         else if (isMetadataAviailable && !isInstalled) {
             // TODO: [�][�]
-            more = "(not installed)";
+            more = "*(not installed)*";
         }
         else if (!isMetadataAviailable && isInstalled) {
-            more = "(no metadata, looks like a unexpected behavior)";
+            more = "*(no metadata, looks like a unexpected behavior)*";
         }
         else if (isMetadataAviailable && isInstalled) {
             more = "(installed)";
         }
         else {
-            more = "(unknown state, looks like a unexpected behavior)";
+            more = "*(unknown state, looks like a unexpected behavior)*";
         }
-        return "".concat(i + 1, ") `").concat(className, "` from `").concat(packageName, "` ").concat(more);
+        if (!isAvilableInBrowser) {
+            more += " *(not available in browser)*";
+        }
+        return "".concat(i + 1, ") `").concat(className, "` from `").concat(packageName, "` compatible to scrape ").concat(mimeTypes.join(', '), " ").concat(more);
     })
         .join('\n')), "\n        "); });
 }
@@ -3356,7 +3359,10 @@ function prepareKnowledgePieces(knowledgeSources, tools, options) {
                                         return [7 /*endfinally*/];
                                     case 9:
                                         if (partialPieces === null) {
-                                            throw new KnowledgeScrapeError(spaceTrim$1(function (block) { return "\n                        Cannot scrape knowledge from source: ".concat(knowledgeSource.sourceContent, "\n\n                        No scraper found for the mime type \"").concat(sourceHandler.mimeType, "\"\n\n                        ").concat(block($registeredScrapersMessage()), "\n\n\n                    "); }));
+                                            throw new KnowledgeScrapeError(spaceTrim$1(function (block) { return "\n                        Cannot scrape knowledge from source:\n                        \n                        > ".concat(block(knowledgeSource.sourceContent
+                                                .split('\n')
+                                                .map(function (line) { return "> ".concat(line); })
+                                                .join('\n')), "\n\n                        No scraper found for the mime type \"").concat(sourceHandler.mimeType, "\"\n\n                        ").concat(block($registeredScrapersMessage()), "\n\n\n                    "); }));
                                         }
                                         pieces = partialPieces.map(function (partialPiece) { return (__assign(__assign({}, partialPiece), { sources: [
                                                 {