@promptbook/markdown-utils 0.101.0-0 → 0.101.0-10

package/README.md

@@ -48,7 +48,93 @@ npm i ptbk
 npm install @promptbook/markdown-utils
 ```
 
-Utility functions used for processing markdown. Its part of the larger [`@promptbook/utils`](https://www.npmjs.com/package/@promptbook/utils) ecosystem.
+Comprehensive markdown processing utilities for the Promptbook ecosystem, providing tools for parsing, manipulating, and extracting content from markdown documents.
+
+## 🎯 Purpose and Motivation
+
+This package provides specialized markdown processing capabilities that are essential for working with promptbooks and LLM-generated content. It handles markdown parsing, content extraction, text humanization, and various markdown transformations that are commonly needed when processing AI-generated text and promptbook documentation.
+
+## 🔧 High-Level Functionality
+
+The package offers comprehensive markdown processing capabilities:
+
+-   **Content Extraction**: Extract code blocks, lists, and sections from markdown
+-   **Text Processing**: Parse and manipulate markdown sections and content
+-   **AI Text Humanization**: Transform AI-generated text to be more human-readable
+-   **Markdown Manipulation**: Add, remove, and modify markdown formatting
+-   **Table and Chart Creation**: Generate markdown tables and charts
+-   **Scraping Integration**: Markdown-specific content scraping capabilities
+
+## ✨ Key Features
+
+-   📝 **Content Extraction** - Extract blocks, lists, and sections from markdown documents
+-   🎨 **Text Humanization** - Transform AI text with proper quotes, ellipsis, and formatting
+-   🔧 **Markdown Manipulation** - Add, remove, and modify markdown formatting
+-   📊 **Table Generation** - Create formatted markdown tables and charts
+-   🧹 **Content Cleaning** - Remove comments, links, and unwanted formatting
+-   📖 **Section Parsing** - Parse and split markdown into structured sections
+-   🔍 **Block Processing** - Extract and process code blocks and content blocks
+-   🤖 **AI Integration** - Specialized tools for processing LLM-generated markdown
+
+## 📦 Exported Entities
+
+### Version Information
+
+-   `BOOK_LANGUAGE_VERSION` - Current book language version
+-   `PROMPTBOOK_ENGINE_VERSION` - Current engine version
+
+### Content Extraction
+
+-   `extractBlock` - Extract specific blocks from content
+-   `extractJsonBlock` - Extract JSON blocks from content
+-   `extractAllBlocksFromMarkdown` - Extract all code blocks from markdown
+-   `extractAllListItemsFromMarkdown` - Extract all list items from markdown
+-   `extractOneBlockFromMarkdown` - Extract single code block from markdown
+
+### Markdown Scraping
+
+-   `createMarkdownScraper` - Create markdown content scraper
+-   `MarkdownScraper` - Markdown scraper class
+-   `_MarkdownScraperRegistration` - Markdown scraper registration
+
+### Type Definitions
+
+-   `string_markdown` - Markdown string type (type)
+-   `string_markdown_section` - Markdown section string type (type)
+-   `string_markdown_section_content` - Markdown section content type (type)
+-   `string_markdown_text` - Markdown text string type (type)
+-   `string_markdown_codeblock_language` - Markdown code block language type (type)
+-   `MarkdownSection` - Markdown section structure (type)
+
+### Content Generation
+
+-   `addAutoGeneratedSection` - Add auto-generated sections to markdown
+-   `createMarkdownChart` - Create markdown charts and diagrams
+-   `createMarkdownTable` - Create formatted markdown tables
+
+### Text Processing
+
+-   `escapeMarkdownBlock` - Escape markdown block content
+-   `flattenMarkdown` - Flatten markdown structure
+-   `parseMarkdownSection` - Parse markdown into sections
+-   `splitMarkdownIntoSections` - Split markdown into structured sections
+
+### AI Text Humanization
+
+-   `humanizeAiText` - Comprehensive AI text humanization
+-   `humanizeAiTextEllipsis` - Fix ellipsis formatting in AI text
+-   `humanizeAiTextEmdashed` - Fix em-dash formatting in AI text
+-   `humanizeAiTextQuotes` - Fix quote formatting in AI text
+-   `humanizeAiTextWhitespace` - Fix whitespace in AI text
+-   `promptbookifyAiText` - Transform AI text for promptbook format
+
+### Content Cleaning
+
+-   `removeMarkdownComments` - Remove comments from markdown
+-   `removeMarkdownFormatting` - Remove markdown formatting
+-   `removeMarkdownLinks` - Remove links from markdown
+
+> 💡 This package provides markdown processing utilities for promptbook applications. For the core functionality, see [@promptbook/core](#-packages) or install all packages with `npm i ptbk`
 
 
 ---

package/esm/index.es.js

@@ -1,7 +1,4 @@
 import spaceTrim, { spaceTrim as spaceTrim$1 } from 'spacetrim';
-import parserHtml from 'prettier/parser-html';
-import parserMarkdown from 'prettier/parser-markdown';
-import { format } from 'prettier/standalone';
 import { randomBytes } from 'crypto';
 import { Subject } from 'rxjs';
 import { forTime } from 'waitasecond';
@@ -26,7 +23,7 @@ const BOOK_LANGUAGE_VERSION = '1.0.0';
  * @generated
  * @see https://github.com/webgptorg/promptbook
  */
-const PROMPTBOOK_ENGINE_VERSION = '0.101.0-0';
+const PROMPTBOOK_ENGINE_VERSION = '0.101.0-10';
 /**
  * TODO: string_promptbook_version should be constrained to the all versions of Promptbook engine
  * Note: [💞] Ignore a discrepancy between file name and entity name
@@ -51,6 +48,8 @@ class ParseError extends Error {
 /**
  * Makes first letter of a string uppercase
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @public exported from `@promptbook/utils`
  */
 function capitalize(word) {
@@ -642,6 +641,7 @@ function isValidFilePath(filename) {
 /**
  * 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
@@ -705,8 +705,18 @@ function validatePipelineString(pipelineString) {
  * @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 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, parserHtml],
             // TODO: DRY - make some import or auto-copy of .prettierrc
@@ -1054,6 +1064,7 @@ function checkSerializableAsJson(options) {
 /**
  * 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.
@@ -2989,6 +3000,8 @@ function $getGlobalScope() {
 /**
  * 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'
@@ -3044,6 +3057,8 @@ function normalizeTo_SCREAMING_CASE(text) {
 /**
  * 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'
@@ -3461,6 +3476,8 @@ for (let i = 0; i < defaultDiacriticsRemovalMap.length; i++) {
 /**
  * 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`
@@ -3615,6 +3632,8 @@ function mimeTypeToExtension(value) {
 /**
  * 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`
@@ -6616,6 +6635,8 @@ function createMarkdownChart(options) {
  * Function escapeMarkdownBlock will escape markdown block if needed
  * It is useful when you want have block in block
  *
+ * Note: [🔂] This function is idempotent.
+ *
  * @public exported from `@promptbook/markdown-utils`
  */
 function escapeMarkdownBlock(value) {
@@ -6783,6 +6804,7 @@ function flattenMarkdown(markdown) {
 /**
  * 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`
@@ -6797,6 +6819,7 @@ function humanizeAiTextEllipsis(aiText) {
 /**
  * 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`
@@ -6811,6 +6834,7 @@ function humanizeAiTextEmdashed(aiText) {
 /**
  * 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`
@@ -6832,6 +6856,7 @@ function humanizeAiTextQuotes(aiText) {
 /**
  * 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`
@@ -6846,6 +6871,7 @@ function humanizeAiTextWhitespace(aiText) {
 /**
  * Function `humanizeAiText` will remove traces of AI text generation artifacts
  *
+ * Note: [🔂] This function is idempotent.
  * Tip: If you want more control, look for other functions for example `humanizeAiTextEmdashed` exported `@promptbook/markdown-utils`
  *
  * @public exported from `@promptbook/markdown-utils`
@@ -6859,6 +6885,7 @@ function humanizeAiText(aiText) {
     return cleanedText;
 }
 /**
+ * TODO: [🧠] Maybe this should be exported from `@promptbook/utils` not `@promptbook/markdown-utils`
  * TODO: [🅾️] !!! Use this across the project where AI text is involved
  */
 
@@ -6878,6 +6905,7 @@ function promptbookifyAiText(text) {
     return promptbookifiedText;
 }
 /**
+ * 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
  */