mirror of
https://gitee.com/coder-xiaomo/leetcode-problemset
synced 2025-01-10 18:48:13 +08:00
179 lines
18 KiB
JSON
179 lines
18 KiB
JSON
{
|
|
"data": {
|
|
"question": {
|
|
"questionId": "393",
|
|
"questionFrontendId": "393",
|
|
"boundTopicId": null,
|
|
"title": "UTF-8 Validation",
|
|
"titleSlug": "utf-8-validation",
|
|
"content": "<p>Given an integer array <code>data</code> representing the data, return whether it is a valid <strong>UTF-8</strong> encoding.</p>\n\n<p>A character in <strong>UTF8</strong> can be from <b>1 to 4 bytes</b> long, subjected to the following rules:</p>\n\n<ol>\n\t<li>For a <strong>1-byte</strong> character, the first bit is a <code>0</code>, followed by its Unicode code.</li>\n\t<li>For an <strong>n-bytes</strong> character, the first <code>n</code> bits are all one's, the <code>n + 1</code> bit is <code>0</code>, followed by <code>n - 1</code> bytes with the most significant <code>2</code> bits being <code>10</code>.</li>\n</ol>\n\n<p>This is how the UTF-8 encoding would work:</p>\n\n<pre>\n<code> Char. number range | UTF-8 octet sequence\n (hexadecimal) | (binary)\n --------------------+---------------------------------------------\n 0000 0000-0000 007F | 0xxxxxxx\n 0000 0080-0000 07FF | 110xxxxx 10xxxxxx\n 0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx\n 0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx</code>\n</pre>\n\n<p><b>Note: </b>The input is an array of integers. Only the <b>least significant 8 bits</b> of each integer is used to store the data. This means each integer represents only 1 byte of data.</p>\n\n<p> </p>\n<p><strong>Example 1:</strong></p>\n\n<pre>\n<strong>Input:</strong> data = [197,130,1]\n<strong>Output:</strong> true\n<strong>Explanation:</strong> data represents the octet sequence: 11000101 10000010 00000001.\nIt is a valid utf-8 encoding for a 2-bytes character followed by a 1-byte character.\n</pre>\n\n<p><strong>Example 2:</strong></p>\n\n<pre>\n<strong>Input:</strong> data = [235,140,4]\n<strong>Output:</strong> false\n<strong>Explanation:</strong> data represented the octet sequence: 11101011 10001100 00000100.\nThe first 3 bits are all one's and the 4th bit is 0 means it is a 3-bytes character.\nThe next byte is a continuation byte which starts with 10 and that's correct.\nBut the second continuation byte does not start with 10, so it is invalid.\n</pre>\n\n<p> </p>\n<p><strong>Constraints:</strong></p>\n\n<ul>\n\t<li><code>1 <= data.length <= 2 * 10<sup>4</sup></code></li>\n\t<li><code>0 <= data[i] <= 255</code></li>\n</ul>\n",
|
|
"translatedTitle": null,
|
|
"translatedContent": null,
|
|
"isPaidOnly": false,
|
|
"difficulty": "Medium",
|
|
"likes": 364,
|
|
"dislikes": 1499,
|
|
"isLiked": null,
|
|
"similarQuestions": "[]",
|
|
"exampleTestcases": "[197,130,1]\n[235,140,4]",
|
|
"categoryTitle": "Algorithms",
|
|
"contributors": [],
|
|
"topicTags": [
|
|
{
|
|
"name": "Array",
|
|
"slug": "array",
|
|
"translatedName": null,
|
|
"__typename": "TopicTagNode"
|
|
},
|
|
{
|
|
"name": "Bit Manipulation",
|
|
"slug": "bit-manipulation",
|
|
"translatedName": null,
|
|
"__typename": "TopicTagNode"
|
|
}
|
|
],
|
|
"companyTagStats": null,
|
|
"codeSnippets": [
|
|
{
|
|
"lang": "C++",
|
|
"langSlug": "cpp",
|
|
"code": "class Solution {\npublic:\n bool validUtf8(vector<int>& data) {\n \n }\n};",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Java",
|
|
"langSlug": "java",
|
|
"code": "class Solution {\n public boolean validUtf8(int[] data) {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Python",
|
|
"langSlug": "python",
|
|
"code": "class Solution(object):\n def validUtf8(self, data):\n \"\"\"\n :type data: List[int]\n :rtype: bool\n \"\"\"\n ",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Python3",
|
|
"langSlug": "python3",
|
|
"code": "class Solution:\n def validUtf8(self, data: List[int]) -> bool:\n ",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "C",
|
|
"langSlug": "c",
|
|
"code": "\n\nbool validUtf8(int* data, int dataSize){\n\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "C#",
|
|
"langSlug": "csharp",
|
|
"code": "public class Solution {\n public bool ValidUtf8(int[] data) {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "JavaScript",
|
|
"langSlug": "javascript",
|
|
"code": "/**\n * @param {number[]} data\n * @return {boolean}\n */\nvar validUtf8 = function(data) {\n \n};",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Ruby",
|
|
"langSlug": "ruby",
|
|
"code": "# @param {Integer[]} data\n# @return {Boolean}\ndef valid_utf8(data)\n \nend",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Swift",
|
|
"langSlug": "swift",
|
|
"code": "class Solution {\n func validUtf8(_ data: [Int]) -> Bool {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Go",
|
|
"langSlug": "golang",
|
|
"code": "func validUtf8(data []int) bool {\n \n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Scala",
|
|
"langSlug": "scala",
|
|
"code": "object Solution {\n def validUtf8(data: Array[Int]): Boolean = {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Kotlin",
|
|
"langSlug": "kotlin",
|
|
"code": "class Solution {\n fun validUtf8(data: IntArray): Boolean {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Rust",
|
|
"langSlug": "rust",
|
|
"code": "impl Solution {\n pub fn valid_utf8(data: Vec<i32>) -> bool {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "PHP",
|
|
"langSlug": "php",
|
|
"code": "class Solution {\n\n /**\n * @param Integer[] $data\n * @return Boolean\n */\n function validUtf8($data) {\n \n }\n}",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "TypeScript",
|
|
"langSlug": "typescript",
|
|
"code": "function validUtf8(data: number[]): boolean {\n\n};",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Racket",
|
|
"langSlug": "racket",
|
|
"code": "(define/contract (valid-utf8 data)\n (-> (listof exact-integer?) boolean?)\n\n )",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Erlang",
|
|
"langSlug": "erlang",
|
|
"code": "-spec valid_utf8(Data :: [integer()]) -> boolean().\nvalid_utf8(Data) ->\n .",
|
|
"__typename": "CodeSnippetNode"
|
|
},
|
|
{
|
|
"lang": "Elixir",
|
|
"langSlug": "elixir",
|
|
"code": "defmodule Solution do\n @spec valid_utf8(data :: [integer]) :: boolean\n def valid_utf8(data) do\n\n end\nend",
|
|
"__typename": "CodeSnippetNode"
|
|
}
|
|
],
|
|
"stats": "{\"totalAccepted\": \"66.7K\", \"totalSubmission\": \"170.4K\", \"totalAcceptedRaw\": 66676, \"totalSubmissionRaw\": 170447, \"acRate\": \"39.1%\"}",
|
|
"hints": [
|
|
"All you have to do is follow the rules. For a given integer, obtain its binary representation in the string form and work with the rules given in the problem.",
|
|
"An integer can either represent the start of a UTF-8 character, or a part of an existing UTF-8 character. There are two separate rules for these two scenarios in the problem.",
|
|
"If an integer is a part of an existing UTF-8 character, simply check the 2 most significant bits of in the binary representation string. They should be <b>10</b>. If the integer represents the start of a UTF-8 character, then the first few bits would be <b>1</b> followed by a <b>0</b>. The number of initial bits (most significant) bits determines the length of the UTF-8 character. \r\n\r\n<br><br>\r\n<b>Note:</b> The array can contain multiple valid UTF-8 characters.",
|
|
"String manipulation will work fine here. But, it is too slow. Can we instead use <b>bit manipulation</b> to do the validations instead of string manipulations?",
|
|
"We can use bit masking to check how many initial bits are set for a given number. <b>We only need to work with the 8 least significant bits as mentioned in the problem.</b>\r\n\r\n<pre>\r\nmask = 1 << 7\r\nwhile mask & num:\r\n n_bytes += 1\r\n mask = mask >> 1\r\n</pre>\r\n\r\nCan you use bit-masking to perform the second validation as well i.e. checking if the most significant bit is 1 and the second most significant bit a 0?",
|
|
"To check if the most significant bit is a 1 and the second most significant bit is a 0, we can make use of the following two masks.\r\n\r\n<pre>\r\nmask1 = 1 << 7\r\nmask2 = 1 << 6\r\n\r\nif not (num & mask1 and not (num & mask2)):\r\n return False\r\n</pre>"
|
|
],
|
|
"solution": {
|
|
"id": "596",
|
|
"canSeeDetail": true,
|
|
"paidOnly": false,
|
|
"hasVideoSolution": false,
|
|
"paidOnlyVideo": true,
|
|
"__typename": "ArticleNode"
|
|
},
|
|
"status": null,
|
|
"sampleTestCase": "[197,130,1]",
|
|
"metaData": "{\r\n \"name\": \"validUtf8\",\r\n \"params\": [\r\n {\r\n \"name\": \"data\",\r\n \"type\": \"integer[]\"\r\n }\r\n ],\r\n \"return\": {\r\n \"type\": \"boolean\"\r\n }\r\n}",
|
|
"judgerAvailable": true,
|
|
"judgeType": "large",
|
|
"mysqlSchemas": [],
|
|
"enableRunCode": true,
|
|
"enableTestMode": false,
|
|
"enableDebugger": true,
|
|
"envInfo": "{\"cpp\": [\"C++\", \"<p>Compiled with <code> clang 11 </code> using the latest C++ 17 standard.</p>\\r\\n\\r\\n<p>Your code is compiled with level two optimization (<code>-O2</code>). <a href=\\\"https://github.com/google/sanitizers/wiki/AddressSanitizer\\\" target=\\\"_blank\\\">AddressSanitizer</a> is also enabled to help detect out-of-bounds and use-after-free bugs.</p>\\r\\n\\r\\n<p>Most standard library headers are already included automatically for your convenience.</p>\"], \"java\": [\"Java\", \"<p><code> OpenJDK 17 </code>. Java 8 features such as lambda expressions and stream API can be used. </p>\\r\\n\\r\\n<p>Most standard library headers are already included automatically for your convenience.</p>\\r\\n<p>Includes <code>Pair</code> class from https://docs.oracle.com/javase/8/javafx/api/javafx/util/Pair.html.</p>\"], \"python\": [\"Python\", \"<p><code>Python 2.7.12</code>.</p>\\r\\n\\r\\n<p>Most libraries are already imported automatically for your convenience, such as <a href=\\\"https://docs.python.org/2/library/array.html\\\" target=\\\"_blank\\\">array</a>, <a href=\\\"https://docs.python.org/2/library/bisect.html\\\" target=\\\"_blank\\\">bisect</a>, <a href=\\\"https://docs.python.org/2/library/collections.html\\\" target=\\\"_blank\\\">collections</a>. If you need more libraries, you can import it yourself.</p>\\r\\n\\r\\n<p>For Map/TreeMap data structure, you may use <a href=\\\"http://www.grantjenks.com/docs/sortedcontainers/\\\" target=\\\"_blank\\\">sortedcontainers</a> library.</p>\\r\\n\\r\\n<p>Note that Python 2.7 <a href=\\\"https://www.python.org/dev/peps/pep-0373/\\\" target=\\\"_blank\\\">will not be maintained past 2020</a>. For the latest Python, please choose Python3 instead.</p>\"], \"c\": [\"C\", \"<p>Compiled with <code>gcc 8.2</code> using the gnu99 standard.</p>\\r\\n\\r\\n<p>Your code is compiled with level one optimization (<code>-O1</code>). <a href=\\\"https://github.com/google/sanitizers/wiki/AddressSanitizer\\\" target=\\\"_blank\\\">AddressSanitizer</a> is also enabled to help detect out-of-bounds and use-after-free bugs.</p>\\r\\n\\r\\n<p>Most standard library headers are already included automatically for your convenience.</p>\\r\\n\\r\\n<p>For hash table operations, you may use <a href=\\\"https://troydhanson.github.io/uthash/\\\" target=\\\"_blank\\\">uthash</a>. \\\"uthash.h\\\" is included by default. Below are some examples:</p>\\r\\n\\r\\n<p><b>1. Adding an item to a hash.</b>\\r\\n<pre>\\r\\nstruct hash_entry {\\r\\n int id; /* we'll use this field as the key */\\r\\n char name[10];\\r\\n UT_hash_handle hh; /* makes this structure hashable */\\r\\n};\\r\\n\\r\\nstruct hash_entry *users = NULL;\\r\\n\\r\\nvoid add_user(struct hash_entry *s) {\\r\\n HASH_ADD_INT(users, id, s);\\r\\n}\\r\\n</pre>\\r\\n</p>\\r\\n\\r\\n<p><b>2. Looking up an item in a hash:</b>\\r\\n<pre>\\r\\nstruct hash_entry *find_user(int user_id) {\\r\\n struct hash_entry *s;\\r\\n HASH_FIND_INT(users, &user_id, s);\\r\\n return s;\\r\\n}\\r\\n</pre>\\r\\n</p>\\r\\n\\r\\n<p><b>3. Deleting an item in a hash:</b>\\r\\n<pre>\\r\\nvoid delete_user(struct hash_entry *user) {\\r\\n HASH_DEL(users, user); \\r\\n}\\r\\n</pre>\\r\\n</p>\"], \"csharp\": [\"C#\", \"<p><a href=\\\"https://docs.microsoft.com/en-us/dotnet/csharp/whats-new/csharp-9\\\" target=\\\"_blank\\\">C# 10 with .NET 6 runtime</a></p>\\r\\n\\r\\n<p>Your code is compiled with debug flag enabled (<code>/debug</code>).</p>\"], \"javascript\": [\"JavaScript\", \"<p><code>Node.js 16.13.2</code>.</p>\\r\\n\\r\\n<p>Your code is run with <code>--harmony</code> flag, enabling <a href=\\\"http://node.green/\\\" target=\\\"_blank\\\">new ES6 features</a>.</p>\\r\\n\\r\\n<p><a href=\\\"https://lodash.com\\\" target=\\\"_blank\\\">lodash.js</a> library is included by default.</p>\\r\\n\\r\\n<p>For Priority Queue / Queue data structures, you may use <a href=\\\"https://github.com/datastructures-js/priority-queue\\\" target=\\\"_blank\\\">datastructures-js/priority-queue</a> and <a href=\\\"https://github.com/datastructures-js/queue\\\" target=\\\"_blank\\\">datastructures-js/queue</a>.</p>\"], \"ruby\": [\"Ruby\", \"<p><code>Ruby 3.1</code></p>\\r\\n\\r\\n<p>Some common data structure implementations are provided in the Algorithms module: https://www.rubydoc.info/github/kanwei/algorithms/Algorithms</p>\"], \"swift\": [\"Swift\", \"<p><code>Swift 5.5.2</code>.</p>\"], \"golang\": [\"Go\", \"<p><code>Go 1.17.6</code>.</p>\\r\\n\\r\\n<p>Support <a href=\\\"https://godoc.org/github.com/emirpasic/gods\\\" target=\\\"_blank\\\">https://godoc.org/github.com/emirpasic/gods</a> library.</p>\"], \"python3\": [\"Python3\", \"<p><code>Python 3.10</code>.</p>\\r\\n\\r\\n<p>Most libraries are already imported automatically for your convenience, such as <a href=\\\"https://docs.python.org/3/library/array.html\\\" target=\\\"_blank\\\">array</a>, <a href=\\\"https://docs.python.org/3/library/bisect.html\\\" target=\\\"_blank\\\">bisect</a>, <a href=\\\"https://docs.python.org/3/library/collections.html\\\" target=\\\"_blank\\\">collections</a>. If you need more libraries, you can import it yourself.</p>\\r\\n\\r\\n<p>For Map/TreeMap data structure, you may use <a href=\\\"http://www.grantjenks.com/docs/sortedcontainers/\\\" target=\\\"_blank\\\">sortedcontainers</a> library.</p>\"], \"scala\": [\"Scala\", \"<p><code>Scala 2.13.7</code>.</p>\"], \"kotlin\": [\"Kotlin\", \"<p><code>Kotlin 1.3.10</code>.</p>\"], \"rust\": [\"Rust\", \"<p><code>Rust 1.58.1</code></p>\\r\\n\\r\\n<p>Supports <a href=\\\"https://crates.io/crates/rand\\\" target=\\\"_blank\\\">rand </a> v0.6\\u00a0from crates.io</p>\"], \"php\": [\"PHP\", \"<p><code>PHP 8.1</code>.</p>\\r\\n<p>With bcmath module</p>\"], \"typescript\": [\"Typescript\", \"<p><code>TypeScript 4.5.4, Node.js 16.13.2</code>.</p>\\r\\n\\r\\n<p>Your code is run with <code>--harmony</code> flag, enabling <a href=\\\"http://node.green/\\\" target=\\\"_blank\\\">new ES2020 features</a>.</p>\\r\\n\\r\\n<p><a href=\\\"https://lodash.com\\\" target=\\\"_blank\\\">lodash.js</a> library is included by default.</p>\"], \"racket\": [\"Racket\", \"<p>Run with <code>Racket 8.3</code>.</p>\"], \"erlang\": [\"Erlang\", \"Erlang/OTP 24.2\"], \"elixir\": [\"Elixir\", \"Elixir 1.13.0 with Erlang/OTP 24.2\"]}",
|
|
"libraryUrl": null,
|
|
"adminUrl": null,
|
|
"challengeQuestion": null,
|
|
"__typename": "QuestionNode"
|
|
}
|
|
}
|
|
} |