Last updated on October 9th, 2024 at 05:52 pm
Here, We see Tag Validator LeetCode Solution. This Leetcode problem is done in many programming languages like C++, Java, JavaScript, Python, etc. with different approaches.
List of all LeetCode Solution
Topics
Stack, String
Companies
Microsoft
Level of Question
Hard
Tag Validator LeetCode Solution
Table of Contents
Problem Statement
Given a string representing a code snippet, implement a tag validator to parse the code and return whether it is valid.
A code snippet is valid if all the following rules hold:
- The code must be wrapped in a valid closed tag. Otherwise, the code is invalid.
- A closed tag (not necessarily valid) has exactly the following format :
<TAG_NAME>TAG_CONTENT</TAG_NAME>
. Among them,<TAG_NAME>
is the start tag, and</TAG_NAME>
is the end tag. The TAG_NAME in start and end tags should be the same. A closed tag is valid if and only if the TAG_NAME and TAG_CONTENT are valid. - A valid
TAG_NAME
only contain upper-case letters, and has length in range [1,9]. Otherwise, theTAG_NAME
is invalid. - A valid
TAG_CONTENT
may contain other valid closed tags, cdata and any characters (see note1) EXCEPT unmatched<
, unmatched start and end tag, and unmatched or closed tags with invalid TAG_NAME. Otherwise, theTAG_CONTENT
is invalid. - A start tag is unmatched if no end tag exists with the same TAG_NAME, and vice versa. However, you also need to consider the issue of unbalanced when tags are nested.
- A
<
is unmatched if you cannot find a subsequent>
. And when you find a<
or</
, all the subsequent characters until the next>
should be parsed as TAG_NAME (not necessarily valid). - The cdata has the following format :
<![CDATA[CDATA_CONTENT]]>
. The range ofCDATA_CONTENT
is defined as the characters between<![CDATA[
and the first subsequent]]>
. CDATA_CONTENT
may contain any characters. The function of cdata is to forbid the validator to parseCDATA_CONTENT
, so even it has some characters that can be parsed as tag (no matter valid or invalid), you should treat it as regular characters.
Example 1:
Input: code = “<DIV>This is the first line <![CDATA[<div>]]></DIV>”
Output: true
Explanation: The code is wrapped in a closed tag : <DIV> and </DIV>. The TAG_NAME is valid, the TAG_CONTENT consists of some characters and cdata. Although CDATA_CONTENT has an unmatched start tag with invalid TAG_NAME, it should be considered as plain text, not parsed as a tag. So TAG_CONTENT is valid, and then the code is valid. Thus return true.
Example 2:
Input: code = “<DIV>>> ![cdata[]] <![CDATA[<div>]>]]>]]>>]</DIV>”
Output: true
Explanation: We first separate the code into : start_tag|tag_content|end_tag. start_tag -> “<DIV>” end_tag -> “</DIV>” tag_content could also be separated into : text1|cdata|text2. text1 -> “>> ![cdata[]] “ cdata -> “<![CDATA[<div>]>]]>”, where the CDATA_CONTENT is “<div>]>” text2 -> “]]>>]” The reason why start_tag is NOT “<DIV>>>” is because of the rule 6. The reason why cdata is NOT “<![CDATA[<div>]>]]>]]>” is because of the rule 7.
Example 3:
Input: code = “<A> <B> </A> </B>”
Output: false
Explanation: Unbalanced. If “<A>” is closed, then “<B>” must be unmatched, and vice versa.
1. Tag Validator LeetCode Solution C++
class Solution { public: bool isValid(string code) { int i = 0; return validTag(code, i) && i == code.size(); } private: bool validTag(string s, int& i) { int j = i; string tag = parseTagName(s, j); if (tag.empty()) return false; if (!validContent(s, j)) return false; int k = j + tag.size() + 2; // expecting j = pos of "</" , k = pos of '>' if (k >= s.size() || s.substr(j, k + 1 - j) != "</" + tag + ">") return false; i = k + 1; return true; } string parseTagName(string s, int& i) { if (s[i] != '<') return ""; int j = s.find('>', i); if (j == string::npos || j - 1 - i < 1 || 9 < j - 1 - i) return ""; string tag = s.substr(i + 1, j - 1 - i); for (char ch : tag) { if (ch < 'A' || 'Z' < ch) return ""; } i = j + 1; return tag; } bool validContent(string s, int& i) { int j = i; while (j < s.size()) { if (!validText(s, j) && !validCData(s, j) && !validTag(s, j)) break; } i = j; return true; } bool validText(string s, int& i) { int j = i; while (i < s.size() && s[i] != '<') { i++; } return i != j; } bool validCData(string s, int& i) { if (s.find("<![CDATA[", i) != i) return false; int j = s.find("]]>", i); if (j == string::npos) return false; i = j + 3; return true; } };
2. Tag Validator LeetCode Solution Java
class Solution { public boolean isValid(String code) { int length = code.length(); Stack S=new Stack(); for (int i = 0; i < length; i++) { if(i>0 && S.empty()) return false; if(code.startsWith("<![CDATA[",i)){ int pos=code.indexOf("]]>",i+9); if (pos==-1) return false; else i=pos+2; } else if(code.startsWith("</",i)){ int pos=code.indexOf('>',i+2); if (pos==-1) { return false; } String to_be_matched=code.substring(i+2,pos); if(S.empty()) return false; if(!to_be_matched.equals((String)S.pop())) return false; i=pos; } else if (code.charAt(i) == '<') { int pos=code.indexOf('>',i+1); if (pos==-1) return false; String to_be_pushed=code.substring(i+1, pos); if(!(to_be_pushed.length() >=1 && to_be_pushed.length() <=9)) return false; for(int k=0;k<to_be_pushed.length();k++) { char temp = to_be_pushed.charAt(k); if (!(temp >= 65 && temp <= 90)) return false; } S.push(to_be_pushed); i=pos; } else { int pos=code.indexOf('<',i); if (pos!=-1) { i=pos-1; } } } if(S.empty()) return true; else return false; } }
3. Tag Validator LeetCode Solution JavaScript
var isValid = function(code) { if (code === 't') return false; while (/<!\[CDATA\[.*?\]\]>/.test(code)) { code = code.replace(/<!\[CDATA\[.*?\]\]>/g, 'c'); } while (/<([A-Z]{1,9})>([^<]*)<\/(\1)>/.test(code)) { code = code.replace(/<([A-Z]{1,9})>([^<]*)<\/(\1)>/g, 't'); } return code === 't'; };
4. Tag Validator LeetCode Solution Python
class Solution(object): def isValid(self, code): code = code.replace("<![CDATA[", "?") if code[0] == "?": return False n = len(code) stack = [] i = 0 while i < n: if code[i] == "<": isClosingTag = False tagName = [] i += 1 if i < n and code[i] == "/": isClosingTag = True i += 1 while i < n and code[i] != ">": tagName.append(code[i]) i += 1 if len(tagName) < 1 or len(tagName) > 9: return False tagName = "".join(tagName) if tagName.isalpha() and tagName.isupper(): if isClosingTag: if stack and stack[-1] == tagName: stack.pop() if i != n - 1 and not stack: return False else: return False else: stack.append(tagName) else: return False elif code[i] == "?": i += 1 while (i + 2 < n) and not (code[i] == "]" and code[i + 1] == "]" and code[i + 2] == ">"): i += 1 if i + 2 < n and code[i] == "]" and code[i + 1] == "]" and code[i + 2] == ">": i += 3 else: if i != n - 1 and not stack: return False i += 1 return not stack