@promptbook/markitdown 0.100.4-0 → 0.101.0-1

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

@@ -0,0 +1,13 @@
+import { string_markdown } from '../../types/typeAliases';
+/**
+ * Change ellipsis character to three dots `…` -> `...`
+ *
+ * Note: [🔂] This function is idempotent.
+ * Tip: If you want to do the full cleanup, look for `humanizeAiText` exported `@promptbook/markdown-utils`
+ *
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function humanizeAiTextEllipsis(aiText: string_markdown): string_markdown;
+/**
+ * Note: [🏂] This function is not tested by itself but together with other cleanup functions with `humanizeAiText`
+ */

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

@@ -0,0 +1,13 @@
+import { string_markdown } from '../../types/typeAliases';
+/**
+ * Change em-dashes to regular dashes `—` -> `-`
+ *
+ * Note: [🔂] This function is idempotent.
+ * Tip: If you want to do the full cleanup, look for `humanizeAiText` exported `@promptbook/markdown-utils`
+ *
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function humanizeAiTextEmdashed(aiText: string_markdown): string_markdown;
+/**
+ * Note: [🏂] This function is not tested by itself but together with other cleanup functions with `humanizeAiText`
+ */

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

@@ -0,0 +1,13 @@
+import { string_markdown } from '../../types/typeAliases';
+/**
+ * Change smart quotes to regular quotes
+ *
+ * Note: [🔂] This function is idempotent.
+ * Tip: If you want to do the full cleanup, look for `humanizeAiText` exported `@promptbook/markdown-utils`
+ *
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function humanizeAiTextQuotes(aiText: string_markdown): string_markdown;
+/**
+ * Note: [🏂] This function is not tested by itself but together with other cleanup functions with `humanizeAiText`
+ */

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

@@ -0,0 +1,13 @@
+import { string_markdown } from '../../types/typeAliases';
+/**
+ * Change unprintable hard spaces to regular spaces
+ *
+ * Note: [🔂] This function is idempotent.
+ * Tip: If you want to do the full cleanup, look for `humanizeAiText` exported `@promptbook/markdown-utils`
+ *
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function humanizeAiTextWhitespace(aiText: string_markdown): string_markdown;
+/**
+ * Note: [🏂] This function is not tested by itself but together with other cleanup functions with `humanizeAiText`
+ */

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

@@ -7,3 +7,11 @@ import type { string_html } from '../../types/typeAliases';
  * @private withing the package because of HUGE size of prettier dependency
  */
 export declare function prettifyMarkdown<TContent extends string_html>(content: TContent): TContent;
+/**
+ * Async version of prettifyMarkdown using dynamic imports
+ *
+ * @param content raw html code
+ * @returns formatted html code
+ * @private withing the package because of HUGE size of prettier dependency
+ */
+export declare function prettifyMarkdownAsync<TContent extends string_html>(content: TContent): Promise<TContent>;

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

@@ -0,0 +1,12 @@
+import { string_markdown } from '../../types/typeAliases';
+/**
+ * Function `promptbookifyAiText` will slightly modify the text so we know it was processed by Promptbook
+ *
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function promptbookifyAiText(text: string_markdown): string_markdown;
+/**
+ * TODO: !!!!! Make the function idempotent and add "Note: [🔂] This function is idempotent."
+ * TODO: [🅾️]!!! Use this across the project where AI text is involved
+ * TODO: [🧠][✌️] Make some Promptbook-native token system
+ */

package/esm/typings/src/utils/markdown/promptbookifyAiText.test.d.ts

@@ -0,0 +1 @@
+export {};

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

@@ -0,0 +1,11 @@
+/**
+ * Removes Markdown link tags from a string.
+ *
+ * @param {string} str - The string to remove Markdown tags from.
+ * @returns {string} The input string with all Markdown tags removed.
+ * @public exported from `@promptbook/markdown-utils`
+ */
+export declare function removeMarkdownLinks(str: string): string;
+/**
+ * @see https://chat.openai.com/chat/bb7c3a5b-fe9c-4ccc-9057-f47e0fd66489
+ */

package/esm/typings/src/utils/markdown/removeMarkdownLinks.test.d.ts

@@ -0,0 +1,4 @@
+export {};
+/**
+ * @see https://chat.openai.com/chat/bb7c3a5b-fe9c-4ccc-9057-f47e0fd66489
+ */

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

@@ -1,6 +1,8 @@
 /**
  * Makes first letter of a string uppercase
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @public exported from `@promptbook/utils`
  */
 export declare function capitalize(word: string): string;

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

@@ -1,5 +1,7 @@
 /**
- * Makes first letter of a string uppercase
+ * Makes first letter of a string lowercase
+ *
+ * Note: [🔂] This function is idempotent.
  *
  * @public exported from `@promptbook/utils`
  */

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

@@ -9,6 +9,8 @@ export type string_SCREAMING_CASE = string;
 /**
  * Normalizes a text string to SCREAMING_CASE (all uppercase with underscores).
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @param text The text string to be converted to SCREAMING_CASE format.
  * @returns The normalized text in SCREAMING_CASE format.
  * @example 'HELLO_WORLD'

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

@@ -8,6 +8,8 @@ export type string_snake_case = string;
 /**
  * Normalizes a text string to snake_case format.
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @param text The text string to be converted to snake_case format.
  * @returns The normalized text in snake_case format.
  * @example 'hello_world'

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

@@ -1,6 +1,8 @@
 /**
  * Take every whitespace (space, new line, tab) and replace it with a single space
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @public exported from `@promptbook/utils`
  */
 export declare function normalizeWhitespaces(sentence: string): string;

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

@@ -1,6 +1,8 @@
 /**
  * Removes diacritic marks (accents) from characters in a string.
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @param input The string containing diacritics to be normalized.
  * @returns The string with diacritics removed or normalized.
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/parseNumber.d.ts

@@ -1,6 +1,7 @@
 /**
  * Function parseNumber will parse number from string
  *
+ * Note: [🔂] This function is idempotent.
  * Unlike Number.parseInt, Number.parseFloat it will never ever result in NaN
  * Note: it also works only with decimal numbers
  *

package/esm/typings/src/utils/removeEmojis.d.ts

@@ -1,6 +1,8 @@
 /**
  * Removes emojis from a string and fix whitespaces
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @param text with emojis
  * @returns text without emojis
  * @public exported from `@promptbook/utils`

package/esm/typings/src/utils/removeQuotes.d.ts

@@ -1,6 +1,7 @@
 /**
  * Removes quotes from a string
  *
+ * Note: [🔂] This function is idempotent.
  * Tip: This is very useful for post-processing of the result of the LLM model
  * Note: This function removes only the same quotes from the beginning and the end of the string
  * Note: There are two similar functions:

package/esm/typings/src/utils/serialization/deepClone.d.ts

@@ -2,6 +2,7 @@ import type { WritableDeep } from 'type-fest';
 /**
  * Creates a deep clone of the given object
  *
+ * Note: [🔂] This function is idempotent.
  * Note: This method only works for objects that are fully serializable to JSON and do not contain functions, Dates, or special types.
  *
  * @param objectValue The object to clone.

package/esm/typings/src/utils/trimCodeBlock.d.ts

@@ -1,6 +1,7 @@
 /**
  * Function trimCodeBlock will trim starting and ending code block from the string if it is present.
  *
+ * Note: [🔂] This function is idempotent.
  * Note: This is useful for post-processing of the result of the chat LLM model
  *       when the model wraps the result in the (markdown) code block.
  *

package/esm/typings/src/utils/validators/url/isValidUrl.d.ts

@@ -3,6 +3,7 @@ import type { really_unknown } from '../../organization/really_unknown';
 /**
  * Tests if given string is valid URL.
  *
+ * Note: [🔂] This function is idempotent.
  * Note: Dataurl are considered perfectly valid.
  * Note: There are two similar functions:
  * - `isValidUrl` which tests any URL

package/esm/typings/src/utils/validators/uuid/isValidUuid.d.ts

@@ -3,6 +3,8 @@ import type { really_unknown } from '../../organization/really_unknown';
 /**
  * Checks if value is valid uuid
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @public exported from `@promptbook/utils`
  */
 export declare function isValidUuid(value: really_unknown): value is string_uuid;

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

@@ -15,7 +15,7 @@ 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., `0.100.3-0`).
+ * It follows semantic versioning (e.g., `0.101.0-0`).
  *
  * @generated
  */

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "@promptbook/markitdown",
-    "version": "0.100.4-0",
+    "version": "0.101.0-1",
     "description": "Promptbook: Run AI apps in plain human language across multiple models and platforms",
     "private": false,
     "sideEffects": false,
@@ -91,7 +91,7 @@
     "module": "./esm/index.es.js",
     "typings": "./esm/typings/src/_packages/markitdown.index.d.ts",
     "peerDependencies": {
-        "@promptbook/core": "0.100.4-0"
+        "@promptbook/core": "0.101.0-1"
     },
     "dependencies": {
         "crypto": "1.0.1",

package/umd/index.umd.js

@@ -1,15 +1,13 @@
 (function (global, factory) {
-    typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('fs/promises'), require('spacetrim'), require('crypto-js'), require('crypto-js/enc-hex'), require('path'), require('prettier/parser-html'), require('prettier/parser-markdown'), require('prettier/standalone'), require('crypto'), require('rxjs'), require('waitasecond'), require('crypto-js/sha256'), require('mime-types'), require('papaparse')) :
-    typeof define === 'function' && define.amd ? define(['exports', 'fs/promises', 'spacetrim', 'crypto-js', 'crypto-js/enc-hex', 'path', 'prettier/parser-html', 'prettier/parser-markdown', 'prettier/standalone', 'crypto', 'rxjs', 'waitasecond', 'crypto-js/sha256', 'mime-types', 'papaparse'], factory) :
-    (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-markitdown"] = {}, global.promises, global.spaceTrim, global.cryptoJs, global.hexEncoder, global.path, global.parserHtml, global.parserMarkdown, global.standalone, global.crypto, global.rxjs, global.waitasecond, global.sha256, global.mimeTypes, global.papaparse));
-})(this, (function (exports, promises, spaceTrim, cryptoJs, hexEncoder, path, parserHtml, parserMarkdown, standalone, crypto, rxjs, waitasecond, sha256, mimeTypes, papaparse) { 'use strict';
+    typeof exports === 'object' && typeof module !== 'undefined' ? factory(exports, require('fs/promises'), require('spacetrim'), require('crypto-js'), require('crypto-js/enc-hex'), require('path'), require('crypto'), require('rxjs'), require('waitasecond'), require('crypto-js/sha256'), require('mime-types'), require('papaparse')) :
+    typeof define === 'function' && define.amd ? define(['exports', 'fs/promises', 'spacetrim', 'crypto-js', 'crypto-js/enc-hex', 'path', 'crypto', 'rxjs', 'waitasecond', 'crypto-js/sha256', 'mime-types', 'papaparse'], factory) :
+    (global = typeof globalThis !== 'undefined' ? globalThis : global || self, factory(global["promptbook-markitdown"] = {}, global.promises, global.spaceTrim, global.cryptoJs, global.hexEncoder, global.path, global.crypto, global.rxjs, global.waitasecond, global.sha256, global.mimeTypes, global.papaparse));
+})(this, (function (exports, promises, spaceTrim, cryptoJs, hexEncoder, path, crypto, rxjs, waitasecond, sha256, mimeTypes, papaparse) { 'use strict';
 
     function _interopDefaultLegacy (e) { return e && typeof e === 'object' && 'default' in e ? e : { 'default': e }; }
 
     var spaceTrim__default = /*#__PURE__*/_interopDefaultLegacy(spaceTrim);
     var hexEncoder__default = /*#__PURE__*/_interopDefaultLegacy(hexEncoder);
-    var parserHtml__default = /*#__PURE__*/_interopDefaultLegacy(parserHtml);
-    var parserMarkdown__default = /*#__PURE__*/_interopDefaultLegacy(parserMarkdown);
     var sha256__default = /*#__PURE__*/_interopDefaultLegacy(sha256);
 
     // ⚠️ WARNING: This code has been generated so that any manual changes will be overwritten
@@ -26,7 +24,7 @@
      * @generated
      * @see https://github.com/webgptorg/promptbook
      */
-    const PROMPTBOOK_ENGINE_VERSION = '0.100.4-0';
+    const PROMPTBOOK_ENGINE_VERSION = '0.101.0-1';
     /**
      * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
      * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -639,6 +637,8 @@
     /**
      * Removes diacritic marks (accents) from characters in a string.
      *
+     * Note: [🔂] This function is idempotent.
+     *
      * @param input The string containing diacritics to be normalized.
      * @returns The string with diacritics removed or normalized.
      * @public exported from `@promptbook/utils`
@@ -707,6 +707,8 @@
     /**
      * Removes emojis from a string and fix whitespaces
      *
+     * Note: [🔂] This function is idempotent.
+     *
      * @param text with emojis
      * @returns text without emojis
      * @public exported from `@promptbook/utils`
@@ -779,6 +781,7 @@
     /**
      * Tests if given string is valid URL.
      *
+     * Note: [🔂] This function is idempotent.
      * Note: Dataurl are considered perfectly valid.
      * Note: There are two similar functions:
      * - `isValidUrl` which tests any URL
@@ -1038,10 +1041,20 @@
      * @private withing the package because of HUGE size of prettier dependency
      */
     function prettifyMarkdown(content) {
+        // In browser/Next.js environments, just return the original content
+        // since prettier parsers are not available and would cause bundling issues
+        if (typeof window !== 'undefined') {
+            return content;
+        }
         try {
-            return standalone.format(content, {
+            // Use dynamic require to avoid static imports that cause bundling issues
+            // This will only work in Node.js environments
+            const prettierStandalone = eval('require')('prettier/standalone');
+            const parserMarkdown = eval('require')('prettier/parser-markdown');
+            const parserHtml = eval('require')('prettier/parser-html');
+            return prettierStandalone.format(content, {
                 parser: 'markdown',
-                plugins: [parserMarkdown__default["default"], parserHtml__default["default"]],
+                plugins: [parserMarkdown, parserHtml],
                 // TODO: DRY - make some import or auto-copy of .prettierrc
                 endOfLine: 'lf',
                 tabWidth: 4,
@@ -1067,6 +1080,8 @@
     /**
      * Makes first letter of a string uppercase
      *
+     * Note: [🔂] This function is idempotent.
+     *
      * @public exported from `@promptbook/utils`
      */
     function capitalize(word) {
@@ -1396,6 +1411,7 @@
     /**
      * Creates a deep clone of the given object
      *
+     * Note: [🔂] This function is idempotent.
      * Note: This method only works for objects that are fully serializable to JSON and do not contain functions, Dates, or special types.
      *
      * @param objectValue The object to clone.
@@ -2996,7 +3012,7 @@
     };
     /**
      * TODO: Refactor this - each profile must be alongside the provider definition
-     * TODO: [🕛] Unite `AvatarProfileProps`, `ChatParticipant`, `LlmExecutionTools` +  `LlmToolsMetadata`
+     * TODO: [🕛] Unite `AgentBasicInformation`, `ChatParticipant`, `LlmExecutionTools` +  `LlmToolsMetadata`
      * Note: [💞] Ignore a discrepancy between file name and entity name
      */
 
@@ -3305,6 +3321,8 @@
     /**
      * Normalizes a text string to SCREAMING_CASE (all uppercase with underscores).
      *
+     * Note: [🔂] This function is idempotent.
+     *
      * @param text The text string to be converted to SCREAMING_CASE format.
      * @returns The normalized text in SCREAMING_CASE format.
      * @example 'HELLO_WORLD'
@@ -3360,6 +3378,8 @@
     /**
      * Normalizes a text string to snake_case format.
      *
+     * Note: [🔂] This function is idempotent.
+     *
      * @param text The text string to be converted to snake_case format.
      * @returns The normalized text in snake_case format.
      * @example 'hello_world'
@@ -4920,6 +4940,7 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
      */
 
     /**
@@ -4954,6 +4975,7 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
      */
 
     /**
@@ -4968,6 +4990,7 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
      */
 
     /**
@@ -4980,6 +5003,7 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
      */
 
     /**
@@ -5000,6 +5024,7 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
      */
 
     /**
@@ -5016,6 +5041,8 @@
     }
     /**
      * TODO: [🥴] Implement counting in formats - like JSON, CSV, XML,...
+     * TODO: [🧠][✌️] Make some Promptbook-native token system
+     * TODO: [✌️] `countWords` should be just `splitWords(...).length`, and all other counters should use this pattern as well
      */
 
     /**