@promptbook/pdf 0.92.0-23 → 0.92.0-25

package/esm/typings/src/types/typeAliases.d.ts

@@ -149,27 +149,29 @@ export type string_persona_description = string;
  */
 export type string_model_description = string;
 /**
- * Source of one knowledge
+ * Source of one knowledge piece.
  *
- * It can be a link, a relative path to file or direct text
+ * It can be a link, a relative path to file or direct text content.
  *
  * For example `"https://pavolhejny.com/"`
  * For example `"./pavol-hejny-cv.pdf"`
  * For example `"Pavol Hejný has web https://pavolhejny.com/"`
  * For example `"Pavol Hejný is web developer and creator of Promptbook and Collboard"`
  *
- * @@@ string_knowledge_source vs string_knowledge_source_link
+ * Note: Distinguishes between `string_knowledge_source_content` and `string_knowledge_source_link`:
+ * `string_knowledge_source_content` refers to the actual content or source of knowledge
+ * `string_knowledge_source_link` refers to a reference or link to the knowledge source
  */
 export type string_knowledge_source_content = string_knowledge_source_link | string_markdown;
 /**
- * One link to knowledge source
+ * One link to a knowledge source.
  *
- * It can be a link or relative path
+ * It can be a URL or relative path.
  *
  * For example `"https://pavolhejny.com/"`
  * For example `"./pavol-hejny-cv.pdf"`
  *
- * @@@ string_knowledge_source vs string_knowledge_source_link
+ * Note: string_knowledge_source_link refers to a reference or link to the knowledge source, while string_knowledge_source_content can be the link or the actual content.
  */
 export type string_knowledge_source_link = string_url | string_filename;
 /**

package/esm/typings/src/utils/editable/edit-pipeline-string/addPipelineCommand.d.ts

@@ -5,7 +5,7 @@ type AddPipelineCommandOptions = {
     pipelineString: PipelineString;
 };
 /**
- * @@@
+ * Adds a new command to a pipeline string in the correct format.
  *
  * @public exported from `@promptbook/editable`
  */
@@ -14,4 +14,4 @@ export {};
 /**
  * TODO: [🧠] What is the better solution - `- xxx`, - `-   xxx` or preserve (see also next TODO)
  * TODO: When existing commands 1) as 2) number 3) list, add 4) new command as next number
- */
+ */ 

package/esm/typings/src/utils/editable/edit-pipeline-string/deflatePipeline.d.ts

@@ -1,6 +1,9 @@
 import type { PipelineString } from '../../../pipeline/PipelineString';
 /**
- * @@@
+ * Converts a pipeline structure to its string representation.
+ *
+ * Transforms a flat, simple pipeline into a properly formatted pipeline string
+ * with sections for title, prompt, and return statement.
  *
  * @public exported from `@promptbook/editable`
  */

package/esm/typings/src/utils/editable/utils/isFlatPipeline.d.ts

@@ -1,6 +1,7 @@
 import type { PipelineString } from '../../../pipeline/PipelineString';
 /**
- * @@@
+ * Utility to determine if a pipeline string is in flat format.
+ * A flat pipeline is a simple text without proper structure (headers, blocks, etc).
  *
  * @public exported from `@promptbook/editable`
  */

package/esm/typings/src/utils/environment/$getGlobalScope.d.ts

@@ -1,6 +1,7 @@
 import type { really_any } from '../organization/really_any';
 /**
- * @@@
+ * Safely retrieves the global scope object (window in browser, global in Node.js)
+ * regardless of the JavaScript environment in which the code is running
  *
  * Note: `$` is used to indicate that this function is not a pure function - it access global scope
  *

package/esm/typings/src/utils/markdown/extractAllListItemsFromMarkdown.d.ts

@@ -9,7 +9,7 @@ import type { string_markdown_text } from '../../types/typeAliases';
  * Note: It can not work with html syntax and comments
  *
  * @param markdown any valid markdown
- * @returns @@@
+ * @returns An array of strings, each representing an individual list item found in the markdown
  * @public exported from `@promptbook/markdown-utils`
  */
 export declare function extractAllListItemsFromMarkdown(markdown: string_markdown): string_markdown_text[];

package/esm/typings/src/utils/normalization/nameToUriPart.d.ts

@@ -1,9 +1,9 @@
 /**
- * @@@
+ * Converts a name string into a URI-compatible format.
  *
- * @param name @@@
- * @returns @@@
- * @example @@@
+ * @param name The string to be converted to a URI-compatible format.
+ * @returns A URI-compatible string derived from the input name.
+ * @example 'Hello World' -> 'hello-world'
  * @public exported from `@promptbook/utils`
  */
 export declare function nameToUriPart(name: string): string;

package/esm/typings/src/utils/normalization/nameToUriParts.d.ts

@@ -1,9 +1,9 @@
 /**
- * @@@
+ * Converts a given name into URI-compatible parts.
  *
- * @param name @@@
- * @returns @@@
- * @example @@@
+ * @param name The name to be converted into URI parts.
+ * @returns An array of URI-compatible parts derived from the name.
+ * @example 'Example Name' -> ['example', 'name']
  * @public exported from `@promptbook/utils`
  */
 export declare function nameToUriParts(name: string): string[];

package/esm/typings/src/utils/normalization/normalize-to-kebab-case.d.ts

@@ -7,10 +7,10 @@
  */
 export type string_kebab_case = string;
 /**
- * @@@
+ * Converts a given text to kebab-case format.
  *
- * @param text @@@
- * @returns @@@
+ * @param text The text to be converted.
+ * @returns The kebab-case formatted string.
  * @example 'hello-world'
  * @example 'i-love-promptbook'
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/normalization/normalizeTo_SCREAMING_CASE.d.ts

@@ -7,10 +7,10 @@
  */
 export type string_SCREAMING_CASE = string;
 /**
- * @@@
+ * Normalizes a text string to SCREAMING_CASE (all uppercase with underscores).
  *
- * @param text @@@
- * @returns @@@
+ * @param text The text string to be converted to SCREAMING_CASE format.
+ * @returns The normalized text in SCREAMING_CASE format.
  * @example 'HELLO_WORLD'
  * @example 'I_LOVE_PROMPTBOOK'
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/normalization/normalizeTo_camelCase.d.ts

@@ -7,11 +7,11 @@
  */
 export type string_camelCase = string;
 /**
- * @@@
+ * Normalizes a given text to camelCase format.
  *
- * @param text @@@
- * @param _isFirstLetterCapital @@@
- * @returns @@@
+ * @param text The text to be normalized.
+ * @param _isFirstLetterCapital Whether the first letter should be capitalized.
+ * @returns The camelCase formatted string.
  * @example 'helloWorld'
  * @example 'iLovePromptbook'
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/normalization/normalizeTo_snake_case.d.ts

@@ -6,10 +6,10 @@
  */
 export type string_snake_case = string;
 /**
- * @@@
+ * Normalizes a text string to snake_case format.
  *
- * @param text @@@
- * @returns @@@
+ * @param text The text string to be converted to snake_case format.
+ * @returns The normalized text in snake_case format.
  * @example 'hello_world'
  * @example 'i_love_promptbook'
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/normalization/removeDiacritics.d.ts

@@ -1,8 +1,8 @@
 /**
- * @@@
+ * Removes diacritic marks (accents) from characters in a string.
  *
- * @param input @@@
- * @returns @@@
+ * @param input The string containing diacritics to be normalized.
+ * @returns The string with diacritics removed or normalized.
  * @public exported from `@promptbook/utils`
  */
 export declare function removeDiacritics(input: string): string;

package/esm/typings/src/utils/normalization/searchKeywords.d.ts

@@ -1,6 +1,6 @@
 import type { Keywords } from './IKeywords';
 /**
- * @@@
+ * Searches set of keywords for a specific keyword
  *
  * @param haystack
  * @param needle
@@ -8,3 +8,6 @@ import type { Keywords } from './IKeywords';
  * @public exported from `@promptbook/utils`
  */
 export declare function searchKeywords(haystack: Keywords, needle: Keywords): boolean;
+/**
+ * TODO: Rename to `isKeywordInKeywords`
+ */

package/esm/typings/src/utils/normalization/titleToName.d.ts

@@ -1,9 +1,9 @@
 /**
- * @@@
+ * Converts a title string into a normalized name.
  *
- * @param value @@@
- * @returns @@@
- * @example @@@
+ * @param value The title string to be converted to a name.
+ * @returns A normalized name derived from the input title.
+ * @example 'Hello World!' -> 'hello-world'
  * @public exported from `@promptbook/utils`
  */
 export declare function titleToName(value: string): string;

package/esm/typings/src/utils/organization/empty_object.d.ts

@@ -2,8 +2,8 @@
  * Organizational helper to better mark the place where to really use empty object `{}`
  *
  * Note: There are 2 similar types>
- * - `empty_object` @@@
- * - `just_empty_object` @@@
+ * - `empty_object` Type used for empty data objects allowing for potential future extensions
+ * - `just_empty_object` Type used when an object must remain permanently empty
  *
  * @private within the repository
  */

package/esm/typings/src/utils/organization/just_empty_object.d.ts

@@ -1,9 +1,9 @@
 /**
- * Organizational helper to better @@@@
+ * Organizational helper to better distinguish different empty object use cases.
  *
- * Note: There are 2 similar types>
- * - `empty_object` @@@
- * - `just_empty_object` @@@
+ * Note: There are 2 similar types:
+ * - `empty_object` Type used for empty data objects with potential extensions
+ * - `just_empty_object` Type used specifically for objects that must remain empty
  *
  * Note: In most cases, you should use `empty_object`
  *

package/esm/typings/src/version.d.ts

@@ -14,7 +14,8 @@ export declare const BOOK_LANGUAGE_VERSION: string_semantic_version;
  */
 export declare const PROMPTBOOK_ENGINE_VERSION: string_promptbook_version;
 /**
- * @@@
+ * Represents the version string of the Promptbook engine.
+ * It follows semantic versioning (e.g., `0.92.0-24`).
  *
  * @generated
  */

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@promptbook/pdf",
-    "version": "0.92.0-23",
+    "version": "0.92.0-25",
     "description": "It's time for a paradigm shift. The future of software in plain English, French or Latin",
     "private": false,
     "sideEffects": false,
@@ -51,7 +51,7 @@
     "module": "./esm/index.es.js",
     "typings": "./esm/typings/src/_packages/pdf.index.d.ts",
     "peerDependencies": {
-        "@promptbook/core": "0.92.0-23"
+        "@promptbook/core": "0.92.0-25"
     },
     "dependencies": {
         "crypto": "1.0.1",

package/umd/index.umd.js

@@ -25,7 +25,7 @@
      * @generated
      * @see https://github.com/webgptorg/promptbook
      */
-    const PROMPTBOOK_ENGINE_VERSION = '0.92.0-23';
+    const PROMPTBOOK_ENGINE_VERSION = '0.92.0-25';
     /**
      * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
      * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -102,11 +102,20 @@
      */
     const DEFAULT_MAX_FILE_SIZE = 100 * 1024 * 1024; // 100MB
     /**
-     * @@@
+     * Threshold value that determines when a dataset is considered "big"
+     * and may require special handling or optimizations
+     *
+     * For example, when error occurs in one item of the big dataset, it will not fail the whole pipeline
      *
      * @public exported from `@promptbook/core`
      */
     const BIG_DATASET_TRESHOLD = 50;
+    /**
+     * Placeholder text used to represent a placeholder value of failed operation
+     *
+     * @public exported from `@promptbook/core`
+     */
+    const FAILED_VALUE_PLACEHOLDER = '!?';
     // <- TODO: [🧠] Better system for generator warnings - not always "code" and "by `@promptbook/cli`"
     /**
      * The maximum number of iterations for a loops
@@ -360,7 +369,8 @@
      */
 
     /**
-     * @@@
+     * Converts a name to a properly formatted subfolder path for cache storage.
+     * Handles normalization and path formatting to create consistent cache directory structures.
      *
      * @private for `FileCacheStorage`
      */
@@ -613,10 +623,10 @@
     */
 
     /**
-     * @@@
+     * Removes diacritic marks (accents) from characters in a string.
      *
-     * @param input @@@
-     * @returns @@@
+     * @param input The string containing diacritics to be normalized.
+     * @returns The string with diacritics removed or normalized.
      * @public exported from `@promptbook/utils`
      */
     function removeDiacritics(input) {
@@ -630,10 +640,10 @@
      */
 
     /**
-     * @@@
+     * Converts a given text to kebab-case format.
      *
-     * @param text @@@
-     * @returns @@@
+     * @param text The text to be converted.
+     * @returns The kebab-case formatted string.
      * @example 'hello-world'
      * @example 'i-love-promptbook'
      * @public exported from `@promptbook/utils`
@@ -775,11 +785,11 @@
     }
 
     /**
-     * @@@
+     * Converts a title string into a normalized name.
      *
-     * @param value @@@
-     * @returns @@@
-     * @example @@@
+     * @param value The title string to be converted to a name.
+     * @returns A normalized name derived from the input title.
+     * @example 'Hello World!' -> 'hello-world'
      * @public exported from `@promptbook/utils`
      */
     function titleToName(value) {
@@ -812,9 +822,8 @@
     }
 
     /**
-     * Create a filename for intermediate cache for scrapers
-     *
-     * Note: It also checks if directory exists and creates it if not
+     * Retrieves an intermediate source for a scraper based on the knowledge source.
+     * Manages the caching and retrieval of intermediate scraper results for optimized performance.
      *
      * @private as internal utility for scrapers
      */
@@ -1448,13 +1457,13 @@
      */
     const REPLACING_NONCE = 'ptbkauk42kV2dzao34faw7FudQUHYPtW';
     /**
-     * @@@
+     * Placeholder value indicating a parameter is missing its value.
      *
      * @private within the repository
      */
     const RESERVED_PARAMETER_MISSING_VALUE = 'MISSING-' + REPLACING_NONCE;
     /**
-     * @@@
+     * Placeholder value indicating a parameter is restricted and cannot be used directly.
      *
      * @private within the repository
      */
@@ -1953,7 +1962,7 @@
         /**
          * Constructs a pipeline collection from pipelines
          *
-         * @param pipelines @@@
+         * @param pipelines Array of pipeline JSON objects to include in the collection
          *
          * Note: During the construction logic of all pipelines are validated
          * Note: It is not recommended to use this constructor directly, use `createCollectionFromJson` *(or other variant)* instead
@@ -2117,8 +2126,8 @@
      * @public exported from `@promptbook/core`
      */
     function isPipelinePrepared(pipeline) {
-        // Note: Ignoring `pipeline.preparations` @@@
-        // Note: Ignoring `pipeline.knowledgePieces` @@@
+        // Note: Ignoring `pipeline.preparations`
+        // Note: Ignoring `pipeline.knowledgePieces`
         if (pipeline.title === undefined || pipeline.title === '' || pipeline.title === DEFAULT_BOOK_TITLE) {
             // TODO: !!! Comment this out
             console.log('Pipeline is not prepared because title is undefined or empty', pipeline);
@@ -3090,7 +3099,8 @@
      */
 
     /**
-     * @@@
+     * Safely retrieves the global scope object (window in browser, global in Node.js)
+     * regardless of the JavaScript environment in which the code is running
      *
      * Note: `$` is used to indicate that this function is not a pure function - it access global scope
      *
@@ -3101,10 +3111,10 @@
     }
 
     /**
-     * @@@
+     * Normalizes a text string to SCREAMING_CASE (all uppercase with underscores).
      *
-     * @param text @@@
-     * @returns @@@
+     * @param text The text string to be converted to SCREAMING_CASE format.
+     * @returns The normalized text in SCREAMING_CASE format.
      * @example 'HELLO_WORLD'
      * @example 'I_LOVE_PROMPTBOOK'
      * @public exported from `@promptbook/utils`
@@ -3156,10 +3166,10 @@
      */
 
     /**
-     * @@@
+     * Normalizes a text string to snake_case format.
      *
-     * @param text @@@
-     * @returns @@@
+     * @param text The text string to be converted to snake_case format.
+     * @returns The normalized text in snake_case format.
      * @example 'hello_world'
      * @example 'i_love_promptbook'
      * @public exported from `@promptbook/utils`
@@ -3229,10 +3239,11 @@
      */
 
     /**
-     * @@@
+     * Registry for all available scrapers in the system.
+     * Central point for registering and accessing different types of content scrapers.
      *
      * Note: `$` is used to indicate that this interacts with the global scope
-     * @singleton Only one instance of each register is created per build, but thare can be more @@@
+     * @singleton Only one instance of each register is created per build, but there can be more than one in different build modules
      * @public exported from `@promptbook/core`
      */
     const $scrapersRegister = new $Register('scraper_constructors');
@@ -3410,7 +3421,9 @@
      */
 
     /**
-     * @@@
+     * Factory function that creates a handler for processing knowledge sources.
+     * Provides standardized processing of different types of knowledge sources
+     * across various scraper implementations.
      *
      * @public exported from `@promptbook/core`
      */
@@ -3651,9 +3664,12 @@
      */
 
     /**
-     * @@@
+     * Prepares tasks by adding knowledge to the prompt and ensuring all necessary parameters are included.
      *
-     * @public exported from `@promptbook/core`
+     * @param tasks Sequence of tasks that are chained together to form a pipeline
+     * @returns A promise that resolves to the prepared tasks.
+     *
+     * @private internal utility of `preparePipeline`
      */
     async function prepareTasks(pipeline, tools, options) {
         const { maxParallelCount = DEFAULT_MAX_PARALLEL_COUNT } = options;
@@ -4191,6 +4207,15 @@
                         mappedData.push(mappedRow);
                         if (onProgress) {
                             // Note: Report the CSV with all rows mapped so far
+                            /*
+                            !!!!
+                             // Report progress with updated value
+                                const progressData = mappedData.map((row, i) =>
+                                  i > index ? { ...row, [outputParameterName]: PENDING_VALUE_PLACEHOLDER } : row,
+                              );
+
+
+                            */
                             await onProgress(papaparse.unparse(mappedData, { ...settings, ...MANDATORY_CSV_SETTINGS }));
                         }
                     }
@@ -4407,7 +4432,7 @@
             else if (!availableParametersNames.has(parameterName) && expectedParameterNames.has(parameterName)) ;
         }
         if (expectedParameterNames.size === 0) {
-            // Note: [👨‍👨‍👧] Now we can freeze `mappedParameters` to prevent @@@
+            // Note: [👨‍👨‍👧] Now we can freeze `mappedParameters` to prevent accidental modifications after mapping
             Object.freeze(mappedParameters);
             return mappedParameters;
         }
@@ -4438,7 +4463,7 @@
         for (let i = 0; i < expectedParameterNames.size; i++) {
             mappedParameters[expectedParameterNamesArray[i]] = availableParameters[availableParametersNamesArray[i]];
         }
-        // Note: [👨‍👨‍👧] Now we can freeze `mappedParameters` to prevent @@@
+        // Note: [👨‍👨‍👧] Now we can freeze `mappedParameters` to prevent accidental modifications after mapping
         Object.freeze(mappedParameters);
         return mappedParameters;
     }
@@ -5191,15 +5216,14 @@
                     const highLevelError = new PipelineExecutionError(spaceTrim__default["default"]((block) => `
                             ${error.message}
 
-                            This is error in FOREACH command when mapping data
+                            This is error in FOREACH command when mapping ${formatDefinition.formatName} ${subvalueParser.subvalueName} data (${index + 1}/${length})
                             You have probbably passed wrong data to pipeline or wrong data was generated which are processed by FOREACH command
 
                             ${block(pipelineIdentification)}
-                            Subparameter index: ${index}
                         `));
                     if (length > BIG_DATASET_TRESHOLD) {
                         console.error(highLevelError);
-                        return '~';
+                        return FAILED_VALUE_PLACEHOLDER;
                     }
                     throw highLevelError;
                 }
@@ -5223,14 +5247,13 @@
                 catch (error) {
                     if (length > BIG_DATASET_TRESHOLD) {
                         console.error(spaceTrim__default["default"]((block) => `
-                              Error in FOREACH command:
+                              ${error.message}
 
-                              ${block(pipelineIdentification)}
+                              This is error in FOREACH command when processing ${formatDefinition.formatName} ${subvalueParser.subvalueName} data (${index + 1}/${length})
 
                               ${block(pipelineIdentification)}
-                              Subparameter index: ${index}
                           `));
-                        return '~';
+                        return FAILED_VALUE_PLACEHOLDER;
                     }
                     throw error;
                 }
@@ -6146,8 +6169,8 @@
                 extension: 'md',
                 isVerbose,
             });
-            // TODO: @@@ Preserve, delete or modify
-            // Note: Running Pandoc ONLY if the file in the cache does not exist
+            // TODO: Determine if Markitdown conversion should run only if the cache file doesn't exist, or always.
+            // Note: Running Markitdown conversion ONLY if the file in the cache does not exist
             if (!(await isFileExisting(cacheFilehandler.filename, this.tools.fs))) {
                 const src = source.filename || source.url || null;
                 // console.log('!!', { src, source, cacheFilehandler });
@@ -6169,11 +6192,11 @@
             return cacheFilehandler;
         }
         /**
-         * Scrapes the docx file and returns the knowledge pieces or `null` if it can't scrape it
+         * Scrapes the source document (PDF, DOCX, etc.) and returns the knowledge pieces or `null` if it can't scrape it.
          */
         async scrape(source) {
             const cacheFilehandler = await this.$convert(source);
-            // TODO: @@@ Preserve, delete or modify
+            // TODO: Ensure this correctly creates the source object for the internal MarkdownScraper using the converted file.
             const markdownSource = {
                 source: source.source,
                 filename: cacheFilehandler.filename,
@@ -6317,7 +6340,8 @@
      */
 
     /**
-     * @@@
+     * Factory function to create an instance of PdfScraper.
+     * It bundles the scraper class with its metadata.
      *
      * @public exported from `@promptbook/pdf`
      */