📝 std::string — Text Handling

std::string là container chuyên cho text — quản lý memory tự động và cung cấp nhiều string operations hữu ích.

---

Tạo String

#include <string>
#include <iostream>

int main() {
    // Empty string
    std::string s1;
    
    // From literal
    std::string s2 = "Hello";
    std::string s3("World");
    std::string s4{"Modern C++"};  // C++11
    
    // Repeated character
    std::string s5(5, 'x');  // "xxxxx"
    
    // Copy
    std::string s6(s2);
    
    // Substring
    std::string s7(s2, 1, 3);  // "ell" (start=1, len=3)
    
    return 0;
}

---

Basic Operations

Concatenation

std::string a = "Hello";
std::string b = "World";

// Operator +
std::string c = a + " " + b;  // "Hello World"

// Append
a += " C++";  // "Hello C++"
a.append("!");  // "Hello C++!"

// ⚠️ Không thể concat 2 literals trực tiếp
// std::string bad = "Hello" + "World";  // ❌ Error
std::string good = std::string("Hello") + "World";  // ✅

Length

std::string s = "Hello";

size_t len1 = s.size();    // 5 (preferred)
size_t len2 = s.length();  // 5 (same)

bool empty = s.empty();    // false

Access

std::string s = "Hello";

char c1 = s[0];      // 'H' — no bounds check
char c2 = s.at(0);   // 'H' — with bounds check

char first = s.front();  // 'H'
char last = s.back();    // 'o'

// Modify
s[0] = 'h';  // "hello"

---

Substring Operations

substr()

std::string s = "Hello World";

std::string sub1 = s.substr(0, 5);   // "Hello"
std::string sub2 = s.substr(6);      // "World" (từ index 6 đến hết)
std::string sub3 = s.substr(6, 3);   // "Wor"

find()

std::string s = "Hello World Wide Web";

// Find first occurrence
size_t pos = s.find("World");  // 6
if (pos != std::string::npos) {
    std::cout << "Found at " << pos << std::endl;
}

// Find từ vị trí cụ thể
size_t pos2 = s.find("W", 7);  // 12 ("Wide")

// Find last occurrence
size_t pos3 = s.rfind("W");    // 17 ("Web")

// Find character
size_t pos4 = s.find('o');     // 4

// Find any of characters
size_t pos5 = s.find_first_of("aeiou");  // 1 ('e')

replace()

std::string s = "Hello World";

s.replace(6, 5, "C++");  // "Hello C++"
// replace từ index 6, 5 characters, với "C++"

// Replace all occurrences (manual loop)
std::string text = "banana";
size_t pos = 0;
while ((pos = text.find("a", pos)) != std::string::npos) {
    text.replace(pos, 1, "o");
    ++pos;
}
// "bonono"

insert() and erase()

std::string s = "Hello World";

s.insert(5, " Beautiful");  // "Hello Beautiful World"
s.erase(6, 10);             // "Hello World"
s.erase(5);                 // "Hello" (từ index 5 đến hết)

---

Comparison

std::string a = "apple";
std::string b = "banana";

// Operators
if (a < b) {   // Lexicographic comparison
    std::cout << "apple comes before banana" << std::endl;
}

if (a == b) { }
if (a != b) { }

// compare() — returns int
int result = a.compare(b);
// < 0: a < b
// = 0: a == b
// > 0: a > b

// Case-insensitive (no built-in, manual)
#include <algorithm>
#include <cctype>

std::string lower_a = a;
std::transform(lower_a.begin(), lower_a.end(), lower_a.begin(), ::tolower);

---

Conversion

String ↔ Number

#include <string>

// String to number
std::string s1 = "42";
int num1 = std::stoi(s1);        // 42
long num2 = std::stol(s1);
double num3 = std::stod("3.14"); // 3.14

// Number to string
int n = 123;
std::string s2 = std::to_string(n);  // "123"

double d = 3.14159;
std::string s3 = std::to_string(d);  // "3.141590"

C-string Interop

std::string cpp_str = "Hello";

// std::string → C-string
const char* c_str = cpp_str.c_str();  // Null-terminated
const char* data = cpp_str.data();     // C++11: same as c_str()

// C-string → std::string
const char* c = "World";
std::string s(c);

---

String View (C++17)

#include <string_view>

void printView(std::string_view sv) {
    std::cout << sv << std::endl;
}

int main() {
    std::string s = "Hello World";
    
    // string_view không copy, chỉ "view" vào data
    std::string_view view1(s);
    std::string_view view2(s.data(), 5);  // "Hello"
    
    printView(s);         // ✅ No copy
    printView("literal"); // ✅ No copy
    
    return 0;
}

📌 Khi nào dùng string_view?

• Read-only access vào string
• Tránh unnecessary copies khi pass vào functions
• CẢNH BÁO: string_view không own data — đảm bảo source string còn sống!

---

Small String Optimization (SSO)

┌─────────────────────────────────────────────────────────────────┐
│               SMALL STRING OPTIMIZATION                         │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  Short strings (≤15-22 chars depending on implementation):     │
│  ┌────────────────────────────┐                                 │
│  │  string object itself      │ ← Data stored inline           │
│  │  contains the characters   │    No heap allocation!         │
│  └────────────────────────────┘                                 │
│                                                                 │
│  Long strings:                                                  │
│  ┌────────────────────────────┐     ┌─────────────────────┐    │
│  │ ptr | size | capacity     │────▶│ "Long string..."    │    │
│  └────────────────────────────┘     └─────────────────────┘    │
│       string object                    heap memory              │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

SSO giúp short strings rất nhanh vì không cần heap allocation.

---

Raw String Literals (C++11)

// Regular string — cần escape
std::string path1 = "C:\\Users\\HPN\\file.txt";
std::string regex1 = "\\d+\\.\\d+";

// Raw string — không cần escape
std::string path2 = R"(C:\Users\HPN\file.txt)";
std::string regex2 = R"(\d+\.\d+)";

// Multi-line
std::string html = R"(
<html>
    <body>
        <h1>Hello</h1>
    </body>
</html>
)";

---

Performance Tips

Operation	Time Complexity
size(), empty()	O(1)
operator[], at()	O(1)
append(), +=	O(m) amortized (m = added length)
find()	O(n)
substr()	O(k) (k = substring length)
Concatenation a + b	O(n+m) (creates new string)

📌 Best Practice

Với nhiều concatenations, dùng std::ostringstream hoặc pre-reserve() để tránh multiple allocations.

---

📚 Tổng kết

Feature	Key Takeaway
std::string	Thay thế char arrays
c_str()	Interop với C APIs
find(), substr()	Text processing
std::stoi/stod	String ↔ Number
std::string_view	Zero-copy read-only view (C++17)
SSO	Short strings = no heap
Raw literals	R"(...)" for special chars

---

➡️ Tiếp theo

Tiếp theo: std::map & unordered_map — Key-value storage.