Algorithm to search words before and after the search string within phrases-CodePudding

Suppose I have below array of phrases

 const senetences = [
    { "text": "And a moment I Yes." },
    { "text": "Wait a moment I Yes." },
    { "text": "And a moment I Hello, Guenta, trenteuno." },
    { "text": "Okay a moment. Hello. Perfect." },
    { "text": "And a moment." },
    { "text": "And a moment I Hello, Guenta, trenteuno." },
    { "text": "Just a moment in Quinta trenteuno." },
    { "text": "And a moment in Quinta trenteuno." },
    { "text": "Wait a moment I Hello, Guenta, trenteuno." },
    { "text": "Just a moment in Quinta trenteuno." }
  ]

Now I search for... suppose moment. So I need to get the some words before and after the exact word moment and their matching score in the whole array.

Example output

[
  "text": "And a moment", "score": 5, "percent": 50,
  "text": "moment I Hello", "score": 3, "percent": 30,
  "text": "moment in Quinta", "score": 3, "percent": 30,
  "text": "Wait a moment", "score": 2, "percent": 20,
  "text": "moment I Yes", "score": 2, "percent": 20,
  "text": "Just a moment", "score": 2, "percent": 20,
  "text": "Okay a moment", "score": 1, "percent": 10
]

score is the number of time it is occurred and the percent is the number of time occurred divided by the total number of sentences.

I am able to get the words after looping on senetences but get stuck after it.

const string = "moment";
const words = [];
senetences.map((a) => {
  const arrayString = a.text.toLowerCase().split(' ');
  const index = arrayString.indexOf(string.toLowerCase());
  words.push(`${arrayString[index - 2]} ${arrayString[index - 1]} ${arrayString[index]}`);
  words.push(`${arrayString[index]} ${arrayString[index   1]} ${arrayString[index   2]}`);
})

After that I got stuck how to find in the senetences array now.

const output = []
senetences.map((a) => {
    phrases.map((p) => {
    const index = a.text.toLowerCase().indexOf(p)
    if (index !== -1) {
        output.push(a.text)
    }
  })
})

CodePudding user response：

You can store the strings and counts in an object:

const sentences = [
  {"text": "And a moment I Yes."},
  {"text": "Wait a moment I Yes."},
  {"text": "And a moment I Hello, Guenta, trenteuno."},
  {"text": "Okay a moment. Hello. Perfect."},
  {"text": "And a moment."},
  {"text": "And a moment I Hello, Guenta, trenteuno."},
  {"text": "Just a moment in Quinta trenteuno."},
  {"text": "And a moment in Quinta trenteuno."},
  {"text": "Wait a moment I Hello, Guenta, trenteuno."},
  {"text": "Just a moment in Quinta trenteuno."}
];

const string = "moment";
const words = sentences.reduce((acc, { text }) => {
  const arrayString = text.replaceAll(/\.|,/g, '').split(' ');
  const index = arrayString.findIndex(el => el.toLowerCase() === string.toLowerCase());
  if (index >= 2) {
    const key = `${arrayString[index - 2]} ${arrayString[index - 1]} ${arrayString[index]}`;
    acc[key] = (acc[key] ?? 0)   1;
  }
  if (index < arrayString.length - 2) {
    const key = `${arrayString[index]} ${arrayString[index   1]} ${arrayString[index   2]}`;
    acc[key] = (acc[key] ?? 0)   1;
  }
  return acc;
}, {})

const result = Object.entries(words)
                     .map(el => ({ text: el[0], score: el[1], percent: 100 * el[1] / sentences.length }))
                     .sort((l, r) => r.score - l.score)
console.log(result);

CodePudding user response：

This function should work, i added a precision parameter, to set how many words you want to use in your search, and added some code to replace all non text characters in the sentences.

function searchAndScoreWords(sentences,searchPhrase,precision){
    //construct wordsArray
    const wordsArray = [];
    sentences.map((sentence) => {
      const arrayString = sentence.text.toLowerCase().replace(/(\.)|(\,)|(')|(\!)|(\?)/g,'').split(' ');
      const index = arrayString.indexOf(searchPhrase.toLowerCase());
      if(index!==-1){
        //if enough words before the search pharse push the words before phrase to array
        if(index>=precision-1){
            let words = [];
            for(let i=index-precision 1;i<=index;i  ){
                words.push(arrayString[i]);
            }
            wordsArray.push(words.join(' '));
        }

        //if enough words after the search pharse push the words before phrase to array
        if(index<=arrayString.length-precision){
            let words = [];
            for(let i=index;i<=index precision-1;i  ){
                words.push(arrayString[i]);
            }
            wordsArray.push(words.join(' '));
        }
      }
    })

    //generate scores 
    let output = [];
    for(let i=0;i<wordsArray.length;i  ){
        let occurrences = 0;
        for(let j=0;j<wordsArray.length;j  ){
            if(wordsArray[i]===wordsArray[j]){
                occurrences  ;
            }
        }
        if(!output.find(e=>e.text===wordsArray[i])){
            output.push({
                text:wordsArray[i],
                score:occurrences,
                percent:occurrences/sentences.length*100
            });
        }
        
    }

    return output;
}
const sentences = [
    { "text": "And a moment, I Yes." },
    { "text": "Wait a moment' I Yes." },
    { "text": "And a moment? I Hello, Guenta, trenteuno." },
    { "text": "Okay a moment. Hello. Perfect." },
    { "text": "And a moment." },
    { "text": "And a moment! I Hello, Guenta, trenteuno." },
    { "text": "Just a moment in Quinta trenteuno." },
    { "text": "And a moment in Quinta trenteuno." },
    { "text": "Wait a moment I Hello, Guenta, trenteuno." },
    { "text": "Just a moment in Quinta trenteuno." }
  ]

console.log(searchAndScoreWords(sentences,"moment",3));