在线字数统计工具：快速统计中英文字数和字符数

function analyzeTextStats(text) {
  const normalized = text.replace(/\r\n/g, '\n').replace(/\r/g, '\n');
  const cjk = (normalized.match(
    /[\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\u3040-\u309f\u30a0-\u30ff\uac00-\ud7af]/gu
  ) || []).length;
  const latin = (normalized.match(/[A-Za-z0-9][A-Za-z0-9'’-]*/g) || []).length;
  let chars = 0;
  let noSpace = 0;
  for (const ch of normalized) {
    chars += 1;
    if (!/\s/u.test(ch)) noSpace += 1;
  }
  const lines = normalized ? normalized.split('\n').length : 0;
  const nonEmptyLines = normalized
    ? normalized.split('\n').filter((l) => l.trim()).length
    : 0;
  const trimmed = normalized.trim();
  const paragraphs = trimmed
    ? trimmed.split(/\n\s*\n/).filter((b) => b.trim()).length
    : 0;
  const readingMin = trimmed
    ? Math.max(1, Math.ceil(cjk / 400 + latin / 200))
    : 0;
  return {
    characters: chars,
    charactersNoSpaces: noSpace,
    whitespaceChars: chars - noSpace,
    words: cjk + latin,
    cjkChars: cjk,
    latinWords: latin,
    lines,
    nonEmptyLines,
    paragraphs,
    readingTimeMinutes: readingMin,
    utf8Bytes: new TextEncoder().encode(normalized).length,
  };
}

import math
import re

CJK_RE = re.compile(
    r'[\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff'
    r'\u3040-\u309f\u30a0-\u30ff\uac00-\ud7af]'
)
LATIN_RE = re.compile(r"[A-Za-z0-9][A-Za-z0-9'’-]*")

def analyze_text_stats(text: str) -> dict:
    normalized = text.replace('\r\n', '\n').replace('\r', '\n')
    cjk = len(CJK_RE.findall(normalized))
    latin = len(LATIN_RE.findall(normalized))
    chars = len(normalized)  # Python str is code points
    no_space = sum(1 for ch in normalized if not ch.isspace())
    lines = normalized.count('\n') + (1 if normalized else 0)
    non_empty = (
        sum(1 for line in normalized.split('\n') if line.strip())
        if normalized else 0
    )
    trimmed = normalized.strip()
    paragraphs = (
        len([b for b in re.split(r'\n\s*\n', trimmed) if b.strip()])
        if trimmed else 0
    )
    reading = max(1, math.ceil(cjk / 400 + latin / 200)) if trimmed else 0
    return {
        'characters': chars,
        'characters_no_spaces': no_space,
        'whitespace_chars': chars - no_space,
        'words': cjk + latin,
        'cjk_chars': cjk,
        'latin_words': latin,
        'lines': lines if normalized else 0,
        'non_empty_lines': non_empty,
        'paragraphs': paragraphs,
        'reading_time_minutes': reading,
        'utf8_bytes': len(normalized.encode('utf-8')),
    }