50줄의 정규식이 포함된 문서에서 복잡한 텍스트 구조를 효율적으로 청크하기

AI 실습 튜토리얼1년 전 업데이트 AI 공유 서클
7.5K 00

Jina의 CEO인 Xiao Han은 Jina 토큰화 도구에 사용된 핵심 청킹 구현의 인상적인 코드 스니펫을 GitHub에 공유했습니다. 이 정규식 코드 스니펫은 50줄이 조금 넘는 길이지만 모든 복잡한 텍스트 청킹 콘텐츠를 효율적으로 처리합니다. 성능은 놀라울 정도로 강력합니다.

 

50行正则表达式实现对文档内复杂文本结构高效分块

온라인 체험: https://jina.ai/tokenizer/

 

// Updated: Aug. 15, 2024
// Run: node testRegex.js testText.txt
// Used in https://jina.ai/tokenizer
const fs = require('fs');
const util = require('util');

// Define variables for magic numbers
const MAX_HEADING_LENGTH = 7;
const MAX_HEADING_CONTENT_LENGTH = 200;
const MAX_HEADING_UNDERLINE_LENGTH = 200;
const MAX_HTML_HEADING_ATTRIBUTES_LENGTH = 100;
const MAX_LIST_ITEM_LENGTH = 200;
const MAX_NESTED_LIST_ITEMS = 6;
const MAX_LIST_INDENT_SPACES = 7;
const MAX_BLOCKQUOTE_LINE_LENGTH = 200;
const MAX_BLOCKQUOTE_LINES = 15;
const MAX_CODE_BLOCK_LENGTH = 1500;
const MAX_CODE_LANGUAGE_LENGTH = 20;
const MAX_INDENTED_CODE_LINES = 20;
const MAX_TABLE_CELL_LENGTH = 200;
const MAX_TABLE_ROWS = 20;
const MAX_HTML_TABLE_LENGTH = 2000;
const MIN_HORIZONTAL_RULE_LENGTH = 3;
const MAX_SENTENCE_LENGTH = 400;
const MAX_QUOTED_TEXT_LENGTH = 300;
const MAX_PARENTHETICAL_CONTENT_LENGTH = 200;
const MAX_NESTED_PARENTHESES = 5;
const MAX_MATH_INLINE_LENGTH = 100;
const MAX_MATH_BLOCK_LENGTH = 500;
const MAX_PARAGRAPH_LENGTH = 1000;
const MAX_STANDALONE_LINE_LENGTH = 800;
const MAX_HTML_TAG_ATTRIBUTES_LENGTH = 100;
const MAX_HTML_TAG_CONTENT_LENGTH = 1000;
const LOOKAHEAD_RANGE = 100;  // Number of characters to look ahead for a sentence boundary

// Define the regex pattern
// Headings
// Citations
// List items
// Block quotes
// Code blocks
// Tables
// Horizontal rules
// Standalone lines or phrases
// Sentences or phrases
// Quoted text, parenthetical phrases, or bracketed content
// Paragraphs
// HTML-like tags and their content
// LaTeX-style math expressions
// Fallback for any remaining content
// Read the regex and test text from files

const chunkRegex = new RegExp(
    "(" +
    // 1. Headings (Setext-style, Markdown, and HTML-style, with length constraints)
    `(?:^(?:[#*=-]{1,${MAX_HEADING_LENGTH}}|\\w[^\\r\\n]{0,${MAX_HEADING_CONTENT_LENGTH}}\\r?\\n[-=]{2,${MAX_HEADING_UNDERLINE_LENGTH}}|<h[1-6][^>]{0,${MAX_HTML_HEADING_ATTRIBUTES_LENGTH}}>)[^\\r\\n]{1,${MAX_HEADING_CONTENT_LENGTH}}(?:</h[1-6]>)?(?:\\r?\\n|$))` +
    "|" +
    // New pattern for citations
    `(?:\\[[0-9]+\\][^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}})` +
    "|" +
    // 2. List items (bulleted, numbered, lettered, or task lists, including nested, up to three levels, with length constraints)
    `(?:(?:^|\\r?\\n)[ \\t]{0,3}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +
    `(?:(?:\\r?\\n[ \\t]{2,5}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?)))` +
    `{0,${MAX_NESTED_LIST_ITEMS}}(?:\\r?\\n[ \\t]{4,${MAX_LIST_INDENT_SPACES}}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?)))` +
    `{0,${MAX_NESTED_LIST_ITEMS}})?)` +
    "|" +
    // 3. Block quotes (including nested quotes and citations, up to three levels, with length constraints)
    `(?:(?:^>(?:>|\\s{2,}){0,2}(?:(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?=[\\r\\n]|$))|(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))\\r?\\n?){1,${MAX_BLOCKQUOTE_LINES}})` +
    "|" +
    // 4. Code blocks (fenced, indented, or HTML pre/code tags, with length constraints)
    `(?:(?:^|\\r?\\n)(?:\`\`\`|~~~)(?:\\w{0,${MAX_CODE_LANGUAGE_LENGTH}})?\\r?\\n[\\s\\S]{0,${MAX_CODE_BLOCK_LENGTH}}?(?:\`\`\`|~~~)\\r?\\n?` +
    `|(?:(?:^|\\r?\\n)(?: {4}|\\t)[^\\r\\n]{0,${MAX_LIST_ITEM_LENGTH}}(?:\\r?\\n(?: {4}|\\t)[^\\r\\n]{0,${MAX_LIST_ITEM_LENGTH}}){0,${MAX_INDENTED_CODE_LINES}}\\r?\\n?)` +
    `|(?:<pre>(?:<code>)?[\\s\\S]{0,${MAX_CODE_BLOCK_LENGTH}}?(?:</code>)?</pre>))` +
    "|" +
    // 5. Tables (Markdown, grid tables, and HTML tables, with length constraints)
    `(?:(?:^|\\r?\\n)(?:\\|[^\\r\\n]{0,${MAX_TABLE_CELL_LENGTH}}\\|(?:\\r?\\n\\|[-:]{1,${MAX_TABLE_CELL_LENGTH}}\\|){0,1}(?:\\r?\\n\\|[^\\r\\n]{0,${MAX_TABLE_CELL_LENGTH}}\\|){0,${MAX_TABLE_ROWS}}` +
    `|<table>[\\s\\S]{0,${MAX_HTML_TABLE_LENGTH}}?</table>))` +
    "|" +
    // 6. Horizontal rules (Markdown and HTML hr tag)
    `(?:^(?:[-*_]){${MIN_HORIZONTAL_RULE_LENGTH},}\\s*$|<hr\\s*/?>)` +
    "|" +
    // 10. Standalone lines or phrases (including single-line blocks and HTML elements, with length constraints)
    `(?:^(?:<[a-zA-Z][^>]{0,${MAX_HTML_TAG_ATTRIBUTES_LENGTH}}>)?(?:(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))(?:</[a-zA-Z]+>)?(?:\\r?\\n|$))` +
    "|" +
    // 7. Sentences or phrases ending with punctuation (including ellipsis and Unicode punctuation)
    `(?:(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?=[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +
    "|" +
    // 8. Quoted text, parenthetical phrases, or bracketed content (with length constraints)
    "(?:" +
    `(?<!\\w)\"\"\"[^\"]{0,${MAX_QUOTED_TEXT_LENGTH}}\"\"\"(?!\\w)` +
    `|(?<!\\w)(?:['\"\`'"])[^\\r\\n]{0,${MAX_QUOTED_TEXT_LENGTH}}\\1(?!\\w)` +
    `|\\([^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}(?:\\([^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}\\)[^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}){0,${MAX_NESTED_PARENTHESES}}\\)` +
    `|\\[[^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}(?:\\[[^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}\\][^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}){0,${MAX_NESTED_PARENTHESES}}\\]` +
    `|\\$[^\\r\\n$]{0,${MAX_MATH_INLINE_LENGTH}}\\$` +
    `|\`[^\`\\r\\n]{0,${MAX_MATH_INLINE_LENGTH}}\`` +
    ")" +
    "|" +
    // 9. Paragraphs (with length constraints)
    `(?:(?:^|\\r?\\n\\r?\\n)(?:<p>)?(?:(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))(?:</p>)?(?=\\r?\\n\\r?\\n|$))` +
    "|" +
    // 11. HTML-like tags and their content (including self-closing tags and attributes, with length constraints)
    `(?:<[a-zA-Z][^>]{0,${MAX_HTML_TAG_ATTRIBUTES_LENGTH}}(?:>[\\s\\S]{0,${MAX_HTML_TAG_CONTENT_LENGTH}}?</[a-zA-Z]+>|\\s*/>))` +
    "|" +
    // 12. LaTeX-style math expressions (inline and block, with length constraints)
    `(?:(?:\\$\\$[\\s\\S]{0,${MAX_MATH_BLOCK_LENGTH}}?\\$\\$)|(?:\\$[^\\$\\r\\n]{0,${MAX_MATH_INLINE_LENGTH}}\\$))` +
    "|" +
    // 14. Fallback for any remaining content (with length constraints)
    `(?:(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +
    ")",
    "gmu"
);

// read from the arg[1] file
const testText = fs.readFileSync(process.argv[2], 'utf8');

// Function to format bytes to a human-readable string
function formatBytes(bytes) {
    if (bytes < 1024) return bytes + " bytes";
    else if (bytes < 1048576) return (bytes / 1024).toFixed(2) + " KB";
    else if (bytes < 1073741824) return (bytes / 1048576).toFixed(2) + " MB";
    else return (bytes / 1073741824).toFixed(2) + " GB";
}

// Start measuring time and memory
const startTime = process.hrtime();
const startMemory = process.memoryUsage().heapUsed;

// Apply the regex
const matches = testText.match(chunkRegex);

// End measuring time and memory
const endTime = process.hrtime(startTime);
const endMemory = process.memoryUsage().heapUsed;

// Calculate execution time and memory usage
const executionTime = endTime[0] + endTime[1] / 1e9;
const memoryUsed = endMemory - startMemory;

// Output results
console.log(`Number of chunks: ${matches ? matches.length : 0}`);
console.log(`Execution time: ${executionTime.toFixed(3)} seconds`);
console.log(`Memory used: ${formatBytes(memoryUsed)}`);

// Output the first 5 matches (or fewer if there are less than 5)
console.log('\nFirst 10 chunks:');
if (matches) {
    matches.slice(0, 100).forEach((match, index) => {
        console.log(util.inspect(match, {maxStringLength: 50}));
    });
} else {
    console.log('No chunks found.');
}

// Output regex flags
console.log(`\nRegex flags: ${chunkRegex.flags}`);

// Check for potential issues
if (executionTime > 5) {
    console.warn('\nWarning: Execution time exceeded 5 seconds. The regex might be too complex or the input too large.');
}
if (memoryUsed > 100 * 1024 * 1024) {
    console.warn('\nWarning: Memory usage exceeded 100 MB. Consider processing the input in smaller chunks.');
}

 

이 코드의 정규식은 제목, 목록 항목, 블록 참조, 코드 블록, 표, 가로줄 규칙, 별도의 줄 또는 구, 구두점이 있는 문장 또는 구, 따옴표로 묶은 텍스트, 괄호 내용, 코드 블록, 표, 가로줄 규칙, 별도의 줄 또는 구, HTML 태그 내용, LaTeX 수학 표현식 등 다양한 텍스트 구조를 고려합니다. 정규식 자체는 텍스트의 문맥이나 의미를 이해하지 못하지만 신중하게 설계된 패턴을 통해 텍스트 청킹을 근사화합니다.

코드 예제의 정규식은 "역추적"을 사용하는데, 이는 보다 의미 있는 의미 분할을 위해 필수적인 기능입니다. 예를 들어, 문장 중간에 끊어지지 않습니다. 그러나 깊게 중첩된 목록, 블록 참조 또는 괄호와 같은 구조의 경우 백트래킹이 어려울 수 있습니다. 이러한 경우를 최적화하기 위해 정규식을 더욱 개선하여 여러 수준의 중첩을 더 잘 처리하고 중첩을 최대 3개 수준과 같은 실용적인 수준으로 제한하여 성능을 보장하고 치명적인 백트래킹을 방지할 수 있습니다.

이 코드가 매우 완벽하지는 않지만 세부 사항을 최적화하려는 이러한 아이디어에 따라 그 효과는 더 개선 될 여지가 있음을 예측할 수 있습니다.Jina 공식 클라우드 서비스는 개발자가 사용을 경험할 수 있도록 분사 인터페이스로 제공되며 무료입니다.

 

파이썬 버전

"""
// 1. Headings (Setext-style, Markdown, and HTML-style, with length constraints)
`(?:^(?:[#*=-]{1,${MAX_HEADING_LENGTH}}|\\w[^\\r\\n]{0,${MAX_HEADING_CONTENT_LENGTH}}\\r?\\n[-=]{2,${MAX_HEADING_UNDERLINE_LENGTH}}|<h[1-6][^>]{0,${MAX_HTML_HEADING_ATTRIBUTES_LENGTH}}>)[^\\r\\n]{1,${MAX_HEADING_CONTENT_LENGTH}}(?:</h[1-6]>)?(?:\\r?\\n|$))` +
"|" +
// New pattern for citations
`(?:\\[[0-9]+\\][^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}})` +
"""
heading_regex = regex.compile(
# 1. Headings (Setext-style, Markdown, and HTML-style, with length constraints)
rf"(?:^" # 开始匹配行的开头
rf"(?:^(?:[#*=-]{{1,{MAX_HEADING_LENGTH}}}" # Markdown 风格的标题
rf"|\w[^\r\n]{{0,{MAX_HEADING_CONTENT_LENGTH}}}\r?\n[-=]{{2,{MAX_HEADING_UNDERLINE_LENGTH}}}" # Setext 风格的标题
rf"|<h[1-6][^>]{{0,{MAX_HTML_HEADING_ATTRIBUTES_LENGTH}}}>[^\r\n]{{1,{MAX_HEADING_CONTENT_LENGTH}}}" # HTML 风格的标题
rf")"
rf"[^\r\n]{{1,{MAX_HEADING_CONTENT_LENGTH}}})" # 匹配标题内容
rf"(?:</h[1-6]>)?" # 可选的闭合标签
rf"(?:\r?\n|$)" # 行尾匹配
rf")"
rf"|"
rf"(?:\[[0-9]+\][^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}})"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 2. List items (bulleted, numbered, lettered, or task lists, including nested, up to three levels, with length constraints)
`(?:(?:^|\\r?\\n)[ \\t]{0,3}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+
(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|
[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|
(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))|
(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])
(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +


`(?:(?:\\r?\\n[ \\t]{2,5}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+
(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b
(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))
|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))
|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])
(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?)))` +


`{0,${MAX_NESTED_LIST_ITEMS}}(?:\\r?\\n[ \\t]{4,${MAX_LIST_INDENT_SPACES}}(?:[-*+•]|\\d{1,3}\\.\\w\\.|\\[[ xX]\\])[ \\t]+
(?:(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b
(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))
|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[\\r\\n]|$))
|(?:\\b[^\\r\\n]{1,${MAX_LIST_ITEM_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])
(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?)))` +
`{0,${MAX_NESTED_LIST_ITEMS}})?)` +
"""
list_item_full_regex = regex.compile(
# 2. List items (bulleted, numbered, lettered, or task lists, including nested, up to three levels, with length constraints)
rf"(?:(?:^|\r?\n)[ \t]{{0,3}}(?:[-*+•]|\d{{1,3}}\.\w\.|\[[ xX]\])[ \t]+"
rf"(?:(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[\r\n]|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])"
rf"(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?))"


rf"(?:(?:\r?\n[ \t]{{2,5}}(?:[-*+•]|\d{{1,3}}\.\w\.|\[[ xX]\])[ \t]+"
rf"(?:(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b"
rf"(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[\r\n]|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])"
rf"(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?)))"
rf"{{0,{MAX_NESTED_LIST_ITEMS}}}"


rf"(?:\r?\n[ \t]{{4,{MAX_LIST_INDENT_SPACES}}}(?:[-*+•]|\d{{1,3}}\.\w\.|\[[ xX]\])[ \t]+"
rf"(?:(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b"
rf"(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[\r\n]|$))"
rf"|(?:\b[^\r\n]{{1,{MAX_LIST_ITEM_LENGTH}}}\b(?=[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])"
rf"(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?)))"
rf"{{0,{MAX_NESTED_LIST_ITEMS}}})?)"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 3. Block quotes (including nested quotes and citations, up to three levels, with length constraints)
`(?:(?:^>(?:>|\\s{2,}){0,2}(?:
(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))
|(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?=[\\r\\n]|$))
|(?:\\b[^\\r\\n]{0,${MAX_BLOCKQUOTE_LINE_LENGTH}}\\b(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])
(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])
(?=\\s|$))?))\\r?\\n?){1,${MAX_BLOCKQUOTE_LINES}})` +
"""


block_quotes_regex = regex.compile(
# 3. Block quotes (including nested quotes and citations, up to three levels, with length constraints)
rf"(?:(?:^>(?:>|\s{{2,}}){{0,2}}(?:"
rf"(?:\b[^\r\n]{{0,{MAX_BLOCKQUOTE_LINE_LENGTH}}}\b(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))"
rf"|(?:\b[^\r\n]{{0,{MAX_BLOCKQUOTE_LINE_LENGTH}}}\b(?=[\r\n]|$))"
rf"|(?:\b[^\r\n]{{0,{MAX_BLOCKQUOTE_LINE_LENGTH}}}\b(?=[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])"
rf"(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])"
rf"(?=\s|$))?))\r?\n?){{1,{MAX_BLOCKQUOTE_LINES}}})"
,
regex.MULTILINE | regex.UNICODE
)


# """
# // 4. Code blocks (fenced, indented, or HTML pre/code tags, with length constraints)
# `(?:(?:^|\\r?\\n)(?:\`\`\`|~~~)(?:\\w{0,${MAX_CODE_LANGUAGE_LENGTH}})?\\r?\\n[\\s\\S]{0,${MAX_CODE_BLOCK_LENGTH}}?(?:\`\`\`|~~~)\\r?\\n?` +
# `|(?:(?:^|\\r?\\n)(?: {4}|\\t)[^\\r\\n]{0,${MAX_LIST_ITEM_LENGTH}}(?:\\r?\\n(?: {4}|\\t)[^\\r\\n]{0,${MAX_LIST_ITEM_LENGTH}}){0,${MAX_INDENTED_CODE_LINES}}\\r?\\n?)` +
# `|(?:<pre>(?:<code>)?[\\s\\S]{0,${MAX_CODE_BLOCK_LENGTH}}?(?:</code>)?</pre>))` +
# """


code_blocks_regex = regex.compile(
# 4. Code blocks (fenced, indented, or HTML pre/code tags, with length constraints)
rf"(?:(?:^|\r?\n)(?:\`\`\`|~~~)(?:\w{{0,{MAX_CODE_LANGUAGE_LENGTH}}})?\r?\n[\s\S]{{0,{MAX_CODE_BLOCK_LENGTH}}}?(?:\`\`\`|~~~)\r?\n?"
rf"|(?:(?:^|\r?\n)(?: {4}|\t)[^\r\n]{{0,{MAX_LIST_ITEM_LENGTH}}}(?:\r?\n(?: {4}|\t)[^\r\n]{{0,{MAX_LIST_ITEM_LENGTH}}}){{0,{MAX_INDENTED_CODE_LINES}}}\r?\n?)"
rf"|(?:<pre>(?:<code>)?[\s\S]{{0,{MAX_CODE_BLOCK_LENGTH}}}?(?:</code>)?</pre>))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 5. Tables (Markdown, grid tables, and HTML tables, with length constraints)
`(?:(?:^|\\r?\\n)(?:\\|[^\\r\\n]{0,${MAX_TABLE_CELL_LENGTH}}\\|(?:\\r?\\n\\|[-:]{1,${MAX_TABLE_CELL_LENGTH}}\\|){0,1}
(?:\\r?\\n\\|[^\\r\\n]{0,${MAX_TABLE_CELL_LENGTH}}\\|){0,${MAX_TABLE_ROWS}}` +
`|<table>[\\s\\S]{0,${MAX_HTML_TABLE_LENGTH}}?</table>))` +
"""


tables_regex = regex.compile(
# 5. Tables (Markdown, grid tables, and HTML tables, with length constraints)
rf"(?:(?:^|\r?\n)(?:\|[^\r\n]{{0,{MAX_TABLE_CELL_LENGTH}}}\|(?:\r?\n\|[-:]{{1,{MAX_TABLE_CELL_LENGTH}}}\|)?"
rf"(?:\r?\n\|[^\r\n]{{0,{MAX_TABLE_CELL_LENGTH}}}\|){{0,{MAX_TABLE_ROWS}}}"
rf"|<table>[\s\S]{{0,{MAX_HTML_TABLE_LENGTH}}}?</table>))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 6. Horizontal rules (Markdown and HTML hr tag)
`(?:^(?:[-*_]){${MIN_HORIZONTAL_RULE_LENGTH},}\\s*$|<hr\\s*/?>)` +
"""


horizontal_rules_regex = regex.compile(
# 6. Horizontal rules (Markdown and HTML hr tag)
rf"(?:^(?:[-*_]){{{MIN_HORIZONTAL_RULE_LENGTH},}}\s*$|<hr\s*/?>)"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 10. Standalone lines or phrases (including single-line blocks and HTML elements, with length constraints)
`(?:^(?:<[a-zA-Z][^>]{0,${MAX_HTML_TAG_ATTRIBUTES_LENGTH}}>)?(?:(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))(?:</[a-zA-Z]+>)?(?:\\r?\\n|$))` +
"""


standalone_lines_regex = regex.compile(
# 10. Standalone lines or phrases (including single-line blocks and HTML elements, with length constraints)
rf"(?:^(?:<[a-zA-Z][^>]{{0,{MAX_HTML_TAG_ATTRIBUTES_LENGTH}}}>)?(?:(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))|(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?=[\r\n]|$))|(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?=[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?))(?:</[a-zA-Z]+>)?(?:\r?\n|$))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 7. Sentences or phrases ending with punctuation (including ellipsis and Unicode punctuation)
`(?:(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_SENTENCE_LENGTH}}(?=[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.\\.\\.|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +
"""


sentences_regex = regex.compile(
# 7. Sentences or phrases ending with punctuation (including ellipsis and Unicode punctuation)
rf"(?:(?:[^\r\n]{{1,{MAX_SENTENCE_LENGTH}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))|(?:[^\r\n]{{1,{MAX_SENTENCE_LENGTH}}}(?=[\r\n]|$))|(?:[^\r\n]{{1,{MAX_SENTENCE_LENGTH}}}(?=[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.\.\.|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?))"
,
regex.MULTILINE | regex.UNICODE
)


# // 8. Quoted text, parenthetical phrases, or bracketed content (with length constraints)
# "(?:" +
# `(?<!\\w)\"\"\"[^\"]{0,${MAX_QUOTED_TEXT_LENGTH}}\"\"\"(?!\\w)` +
# `|(?<!\\w)(?:['\"\`'"])[^\\r\\n]{0,${MAX_QUOTED_TEXT_LENGTH}}\\1(?!\\w)` +
# `|\\([^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}(?:\\([^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}\\)[^\\r\\n()]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}){0,${MAX_NESTED_PARENTHESES}}\\)` +
# `|\\[[^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}(?:\\[[^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}\\][^\\r\\n\\[\\]]{0,${MAX_PARENTHETICAL_CONTENT_LENGTH}}){0,${MAX_NESTED_PARENTHESES}}\\]` +
# `|\\$[^\\r\\n$]{0,${MAX_MATH_INLINE_LENGTH}}\\$` +
# `|\`[^\`\\r\\n]{0,${MAX_MATH_INLINE_LENGTH}}\`` +
# ")" +


quoted_regex = regex.compile(
# 8. Quoted text, parenthetical phrases, or bracketed content (with length constraints)
rf"(?:"
rf"(?<!\w)\"\"\"[^\"]{{0,{MAX_QUOTED_TEXT_LENGTH}}}\"\"\"(?!\w)"
rf"|(?<!\w)(?:['\"\`\'])[^\r\n]{{0,{MAX_QUOTED_TEXT_LENGTH}}}\\1(?!\w)"
rf"|\([^\r\n()]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}(?:\([^\r\n()]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}\)[^\r\n()]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}){{0,{MAX_NESTED_PARENTHESES}}}\)"
rf"|\[[^\r\n\[\]]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}(?:\[[^\r\n\[\]]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}\][^\r\n\[\]]{{0,{MAX_PARENTHETICAL_CONTENT_LENGTH}}}){{0,{MAX_NESTED_PARENTHESES}}}\]"
rf"|\$[^\r\n$]{{0,{MAX_MATH_INLINE_LENGTH}}}\$"
rf"|\"[^\"\r\n]{{0,{MAX_MATH_INLINE_LENGTH}}}\""
rf")"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 9. Paragraphs (with length constraints)
`(?:(?:^|\\r?\\n\\r?\\n)(?:<p>)?(?:(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_PARAGRAPH_LENGTH}}(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))(?:</p>)?(?=\\r?\\n\\r?\\n|$))` +
"""


paragraphs_regex = regex.compile(
# 9. Paragraphs (with length constraints)
rf"(?:(?:^|\r?\n\r?\n)(?:<p>)?(?:(?:[^\r\n]{{1,{MAX_PARAGRAPH_LENGTH}}}(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))|(?:[^\r\n]{{1,{MAX_PARAGRAPH_LENGTH}}}(?=[\r\n]|$))|(?:[^\r\n]{{1,{MAX_PARAGRAPH_LENGTH}}}(?=[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?))(?:</p>)?(?=\r?\n\r?\n|$))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 11. HTML-like tags and their content (including self-closing tags and attributes, with length constraints)
`(?:<[a-zA-Z][^>]{0,${MAX_HTML_TAG_ATTRIBUTES_LENGTH}}(?:>[\\s\\S]{0,${MAX_HTML_TAG_CONTENT_LENGTH}}?</[a-zA-Z]+>|\\s*/>))` +
"""


HTML_like_tags_regex = regex.compile(
# 11. HTML-like tags and their content (including self-closing tags and attributes, with length constraints)
rf"(?:<[a-zA-Z][^>]{{0,{MAX_HTML_TAG_ATTRIBUTES_LENGTH}}}(?:>[\s\S]{{0,{MAX_HTML_TAG_CONTENT_LENGTH}}}?</[a-zA-Z]+>|\s*/>))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 12. LaTeX-style math expressions (inline and block, with length constraints)
`(?:(?:\\$\\$[\\s\\S]{0,${MAX_MATH_BLOCK_LENGTH}}?\\$\\$)|(?:\\$[^\\$\\r\\n]{0,${MAX_MATH_INLINE_LENGTH}}\\$))` +
"""


LaTeX_style_math_regex = regex.compile(
# 12. LaTeX-style math expressions (inline and block, with length constraints)
rf"(?:(?:\$\$[\s\S]{{0,{MAX_MATH_BLOCK_LENGTH}}}?\$\$)|(?:\$[^\$\r\n]{{0,{MAX_MATH_INLINE_LENGTH}}}\$))"
,
regex.MULTILINE | regex.UNICODE
)


"""
// 14. Fallback for any remaining content (with length constraints)
`(?:(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[\\r\\n]|$))|(?:[^\\r\\n]{1,${MAX_STANDALONE_LINE_LENGTH}}(?=[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?:.{1,${LOOKAHEAD_RANGE}}(?:[.!?…]|\\.{3}|[\\u2026\\u2047-\\u2049]|[\\p{Emoji_Presentation}\\p{Extended_Pictographic}])(?=\\s|$))?))` +
"""


fallback_regex = regex.compile(
# 14. Fallback for any remaining content (with length constraints)
rf"(?:(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))|(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?=[\r\n]|$))|(?:[^\r\n]{{1,{MAX_STANDALONE_LINE_LENGTH}}}(?=[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?:.{{1,{LOOKAHEAD_RANGE}}}(?:[.!?…]|\.{3}|[\u2026\u2047-\u2049]|[\p{{Emoji_Presentation}}\p{{Extended_Pictographic}}])(?=\s|$))?))"
,
regex.MULTILINE | regex.UNICODE
)

© 저작권 정책
기사 저작권 AI 공유 서클 모두 무단 복제하지 마세요.

관련 문서

댓글 없음

댓글에 참여하려면 로그인해야 합니다!
지금 로그인
없음
댓글 없음...

선택한 AI 도구

최신 컬렉션

최신 기사