规范格式

leetcode/0393.UTF-8-Validation/393. UTF-8 Validation.go

@@ -0,0 +1,26 @@
+package leetcode
+
+func validUtf8(data []int) bool {
+	count := 0
+	for _, d := range data {
+		if count == 0 {
+			if d >= 248 { // 11111000 = 248
+				return false
+			} else if d >= 240 { // 11110000 = 240
+				count = 3
+			} else if d >= 224 { // 11100000 = 224
+				count = 2
+			} else if d >= 192 { // 11000000 = 192
+				count = 1
+			} else if d > 127 { // 01111111 = 127
+				return false
+			}
+		} else {
+			if d <= 127 || d >= 192 {
+				return false
+			}
+			count--
+		}
+	}
+	return count == 0
+}

leetcode/0393.UTF-8-Validation/393. UTF-8 Validation_test.go

@@ -0,0 +1,47 @@
+package leetcode
+
+import (
+	"fmt"
+	"testing"
+)
+
+type question393 struct {
+	para393
+	ans393
+}
+
+// para 是参数
+// one 代表第一个参数
+type para393 struct {
+	one []int
+}
+
+// ans 是答案
+// one 代表第一个答案
+type ans393 struct {
+	one bool
+}
+
+func Test_Problem393(t *testing.T) {
+
+	qs := []question393{
+
+		question393{
+			para393{[]int{197, 130, 1}},
+			ans393{true},
+		},
+
+		question393{
+			para393{[]int{235, 140, 4}},
+			ans393{false},
+		},
+	}
+
+	fmt.Printf("------------------------Leetcode Problem 393------------------------\n")
+
+	for _, q := range qs {
+		_, p := q.ans393, q.para393
+		fmt.Printf("【input】:%v       【output】:%v\n", p, validUtf8(p.one))
+	}
+	fmt.Printf("\n\n\n")
+}

leetcode/0393.UTF-8-Validation/README.md

@@ -0,0 +1,71 @@
+# [393. UTF-8 Validation](https://leetcode.com/problems/utf-8-validation/)
+
+
+
+## 题目:
+
+A character in UTF8 can be from **1 to 4 bytes** long, subjected to the following rules:
+
+1. For 1-byte character, the first bit is a 0, followed by its unicode code.
+2. For n-bytes character, the first n-bits are all one's, the n+1 bit is 0, followed by n-1 bytes with most significant 2 bits being 10.
+
+This is how the UTF-8 encoding would work:
+
+       Char. number range  |        UTF-8 octet sequence
+          (hexadecimal)    |              (binary)
+       --------------------+---------------------------------------------
+       0000 0000-0000 007F | 0xxxxxxx
+       0000 0080-0000 07FF | 110xxxxx 10xxxxxx
+       0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx
+       0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+
+Given an array of integers representing the data, return whether it is a valid utf-8 encoding.
+
+**Note:**The input is an array of integers. Only the **least significant 8 bits** of each integer is used to store the data. This means each integer represents only 1 byte of data.
+
+**Example 1:**
+
+    data = [197, 130, 1], which represents the octet sequence: 11000101 10000010 00000001.
+    
+    Return true.
+    It is a valid utf-8 encoding for a 2-bytes character followed by a 1-byte character.
+
+**Example 2:**
+
+    data = [235, 140, 4], which represented the octet sequence: 11101011 10001100 00000100.
+    
+    Return false.
+    The first 3 bits are all one's and the 4th bit is 0 means it is a 3-bytes character.
+    The next byte is a continuation byte which starts with 10 and that's correct.
+    But the second continuation byte does not start with 10, so it is invalid.
+
+## 题目大意
+
+UTF-8 中的一个字符可能的长度为 1 到 4 字节，遵循以下的规则：
+
+对于 1 字节的字符，字节的第一位设为 0，后面 7 位为这个符号的 unicode 码。
+对于 n 字节的字符 (n > 1)，第一个字节的前 n 位都设为 1，第 n+1 位设为 0，后面字节的前两位一律设为 10。剩下的没有提及的二进制位，全部为这个符号的 unicode 码。
+这是 UTF-8 编码的工作方式：
+
+```c
+   Char. number range  |        UTF-8 octet sequence
+      (hexadecimal)    |              (binary)
+   --------------------+---------------------------------------------
+   0000 0000-0000 007F | 0xxxxxxx
+   0000 0080-0000 07FF | 110xxxxx 10xxxxxx
+   0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx
+   0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
+
+```
+
+给定一个表示数据的整数数组，返回它是否为有效的 utf-8 编码。
+
+注意:
+
+输入是整数数组。只有每个整数的最低 8 个有效位用来存储数据。这意味着每个整数只表示 1 字节的数据。
+
+
+## 解题思路
+
+- 这一题看似很复杂，其实严格按照 UTF8 定义来模拟就可以了。
+