كيف أقسم النص إلى جمل؟

const text = "Hello world. How are you? I am fine.";
const sentences = text.split(". ");
console.log(sentences);
// ["Hello world", "How are you? I am fine."]

const text = "Dr. Smith works at Acme Inc. He starts at 9 a.m.";
const sentences = text.split(". ");
console.log(sentences);
// ["Dr", "Smith works at Acme Inc", "He starts at 9 a.m."]

const text = "Hello world. How are you? I am fine!";
const sentences = text.split(/[.?!]\s+/);
console.log(sentences);
// ["Hello world", "How are you", "I am fine", ""]

const text = "Dr. Smith works at Acme Inc. He starts at 9 a.m.";
const sentences = text.split(/[.?!]\s+/);
console.log(sentences);
// ["Dr", "Smith works at Acme Inc", "He starts at 9 a", "m", ""]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Hello world. How are you? I am fine!";
const segments = segmenter.segment(text);

for (const segment of segments) {
  console.log(segment.segment);
}
// "Hello world. "
// "How are you? "
// "I am fine!"

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Hello world. How are you? I am fine!";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// ["Hello world. ", "How are you? ", "I am fine!"]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Dr. Smith works at Acme Inc. He starts at 9 a.m.";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// ["Dr. Smith works at Acme Inc. ", "He starts at 9 a.m."]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Hello world. How are you? I am fine!";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment.trim());
console.log(sentences);
// ["Hello world.", "How are you?", "I am fine!"]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Hello world. How are you?";
const segments = segmenter.segment(text);

for (const segment of segments) {
  console.log({
    text: segment.segment,
    index: segment.index,
    input: segment.input
  });
}
// { text: "Hello world. ", index: 0, input: "Hello world. How are you?" }
// { text: "How are you?", index: 13, input: "Hello world. How are you?" }

const segmenter = new Intl.Segmenter("ja", { granularity: "sentence" });
const text = "私は猫です。名前はまだない。";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// ["私は猫です。", "名前はまだない。"]

const segmenter = new Intl.Segmenter("hi", { granularity: "sentence" });
const text = "यह एक वाक्य है। यह दूसरा वाक्य है।";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// ["यह एक वाक्य है। ", "यह दूसरा वाक्य है।"]

const englishText = "Hello world. How are you?";
const japaneseText = "私は猫です。名前はまだない。";

const englishSegmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const japaneseSegmenter = new Intl.Segmenter("ja", { granularity: "sentence" });

const englishSentences = Array.from(
  englishSegmenter.segment(englishText),
  s => s.segment
);

const japaneseSentences = Array.from(
  japaneseSegmenter.segment(japaneseText),
  s => s.segment
);

console.log(englishSentences);
// ["Hello world. ", "How are you?"]

console.log(japaneseSentences);
// ["私は猫です。", "名前はまだない。"]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "Hello world";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// ["Hello world"]

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
const text = "";
const segments = segmenter.segment(text);
const sentences = Array.from(segments, s => s.segment);
console.log(sentences);
// []

const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });

const texts = [
  "First text. With two sentences.",
  "Second text. With three sentences. And more.",
  "Third text."
];

texts.forEach(text => {
  const sentences = Array.from(segmenter.segment(text), s => s.segment);
  console.log(sentences);
});
// ["First text. ", "With two sentences."]
// ["Second text. ", "With three sentences. ", "And more."]
// ["Third text."]

function countSentences(text, locale = "en") {
  const segmenter = new Intl.Segmenter(locale, { granularity: "sentence" });
  const segments = segmenter.segment(text);
  return Array.from(segments).length;
}

console.log(countSentences("Hello world. How are you?"));
// 2

console.log(countSentences("Dr. Smith works at Acme Inc. He starts at 9 a.m."));
// 2

console.log(countSentences("Single sentence"));
// 1

console.log(countSentences("私は猫です。名前はまだない。", "ja"));
// 2

function getSentence(text, index, locale = "en") {
  const segmenter = new Intl.Segmenter(locale, { granularity: "sentence" });
  const segments = Array.from(segmenter.segment(text), s => s.segment);
  return segments[index] || null;
}

const text = "First sentence. Second sentence. Third sentence.";

console.log(getSentence(text, 0));
// "First sentence. "

console.log(getSentence(text, 1));
// "Second sentence. "

console.log(getSentence(text, 2));
// "Third sentence."

console.log(getSentence(text, 3));
// null

if (typeof Intl.Segmenter !== "undefined") {
  const segmenter = new Intl.Segmenter("en", { granularity: "sentence" });
  const text = "Hello world. How are you?";
  const sentences = Array.from(segmenter.segment(text), s => s.segment);
  console.log(sentences);
} else {
  console.log("Intl.Segmenter is not supported");
}

function splitSentences(text, locale = "en") {
  if (typeof Intl.Segmenter !== "undefined") {
    const segmenter = new Intl.Segmenter(locale, { granularity: "sentence" });
    return Array.from(segmenter.segment(text), s => s.segment);
  }

  // Fallback for older environments
  return text.split(/[.!?]\s+/).filter(s => s.length > 0);
}

console.log(splitSentences("Hello world. How are you?"));
// ["Hello world. ", "How are you?"]