i have a string i need to convert it into a array of object
const str = "addias (brand|type) sneakers(product) for men(o)"
expected output
let output = [
{
key:"addias",
value:["brand","type"]
},
{
key:"sneakers",
value:["product"]
},
{
key:"for men",
value:[]
}
]
code i tried
function gerateSchema(val) {
let split = val.split(" ")
let maps = split.map((i) => {
let obj = i.split("(")
let key = obj[0].replaceAll(/\s/g, "")
let cleanValue = obj[1].replace(/[{()}]/g, "")
let stripedValues = cleanValue.split("|")
return {
key: key,
value: stripedValues,
}
})
return maps
}
let out = gerateSchema(str)
but this breaking when there is some word with space for example for men
how to do split with a regex
One approach would be first do a regex find all to find all key/value combinations in the original string. Then, iterate that result and build out a hashmap using the word keys and the array values.
var str = "addias (brand|type) sneakers(product) for men(o)";
var matches = str.match(/\w+(?: \w+)*\s*\(.*?\)/g, str);
var array = [];
for (var i=0; i < matches.length; ++i) {
var parts = matches[i].split(/\s*(?=\()/);
var map = {};
map["key"] = parts[0];
map["value"] = parts[1].replace(/^\(|\)$/g, "").split(/\|/);
array.push(map);
}
console.log(array);The first regex matches each key/value string:
\w+ match a word
(?: \w+)* followed by a space, and another word, the quantity zero or more times
\s* optional whitespace
\( (
.*? pipe separated value string
\) )
Then, we split each term on \s*(?=\(), which is the space(s) immediately preceding the (...|...) term. Finally, we split the value string on pipe | to generate the set of values.
An alternative way could be this.
const str = "addias (brand|type) sneakers(product) for men(o)"
const array = str.split(')').filter(i => i.length).map(i => {
const item = i.split('(');
return {
key: item[0].trim(),
value: item[1].split('|')
}
})
console.log(array)With a little help from regex101.com, derived the following regex expressions and the following code.
([^\(]+)\(([^\)]*)\) which breaks down into
([^\(]+) - capture 1 or more chars up to the first ( as group 1
\( - swallow the left parens
([^\)]*) - capture everything up to the next occurrence of ) as group 2
\) - swallow the right parens
and I was starting to [^|]+ - to parse the text of group 2, but it's actually simpler with a simple split statement.
function generateSchema(str) {
const regex = /([^\(]+)\(([^\)]*)\)/mg; // captures the 'word (word)' pattern
let m;
let output = [];
let obj = {};
while ((m = regex.exec(str)) !== null) {
// This is necessary to avoid infinite loops with zero-width matches
if (m.index === regex.lastIndex) {
regex.lastIndex++;
}
m.forEach((match, groupIndex) => {
if (groupIndex === 1) {
obj = {};
obj.key = match.trim();
} else if (groupIndex === 2) {
obj.value = match.split('|').map(i=>i.trim());
output.push(obj);
}
});
}
return output;
}
const str = "addidas (brand | type ) sneakers(product) for men(o)";
console.log(generateSchema(str));