[sparkie]

> The biggest downside to this approach is we can't prevent the library user from using a struct initializer and creating an invalid structure (eg, length and actual string length not matching). It would be nice if there were some similar to trick to prevent using compound initializers with the type, then we could have full encapsulation without resorting to opaque pointers.

Hmm, I found a solution and it was easier than expected. GCC has `__attribute__((designated_init))` we can stick on the struct which prevents positional initializers and requires the field names to be used (assuming -Werror). Since those names are poisoned, we won't be able to initialize except through functions defined in our library. We can similarly use a macro and #undef it.

Full encapsulation of a struct defined in a header:

    #ifndef FOO_STRING_H
    #define FOO_STRING_H

    #include <stddef.h>
    #include <stdlib.h>
    #include <string.h>
    #if defined __has_include
    # if __has_include("config.h")
    #  include "config.h"
    # endif
    #endif

    typedef size_t string_length_t;
    #ifdef CONFIG_STRING_LENGTH_MAX
    #define STRING_LENGTH_MAX CONFIG_STRING_LENGTH_MAX
    #else
    #define STRING_LENGTH_MAX (1 << 24)
    #endif

    typedef struct __attribute__((designated_init)) {
        const string_length_t _internal_string_length;
        const char *const _internal_string_chars;
    } string_t;

    #define STRING_CREATE(len, ptr) (string_t){ ._internal_string_length = (len), ._internal_string_chars = (ptr) }
    #define STRING_LENGTH(s) (s._internal_string_length)
    #define STRING_CHARS(s) (s._internal_string_chars)
    #pragma GCC poison _internal_string_length _internal_string_chars


    constexpr string_t error_string = STRING_CREATE(0, nullptr);
    constexpr string_t empty_string = STRING_CREATE(0, "");

    inline static string_t string_alloc_from_chars(const char *chars) {
        if (__builtin_expect(chars == nullptr, false)) return error_string;
        size_t len = strnlen(chars, STRING_LENGTH_MAX);
        if (__builtin_expect(len == 0, false)) return empty_string;
        if (__builtin_expect(len < STRING_LENGTH_MAX, true)) {
            char *mem = malloc(len + 1);
            strncpy(mem, chars, len);
            mem[len] = '\0';
            return STRING_CREATE(len, mem);
        } else return error_string;
    }

    inline static const char *string_to_chars(string_t string) {
        return STRING_CHARS(string);
    }

    inline static string_length_t string_length(string_t string) {
        return STRING_LENGTH(string);
    }

    inline static void string_free(string_t s) {
        free((char*)STRING_CHARS(s));
    }

    inline static bool string_is_valid(string_t string) {
        return STRING_CHARS(string) != nullptr;
    }

    // ... other string function

    #undef STRING_LENGTH
    #undef STRING_CHARS
    #undef STRING_CREATE

    #endif /* FOO_STRING_H */

Aside from horrible pointer aliasing tricks, the only way to create a `string_t` is via `string_alloc_from_chars` or other functions defined in the library which return `string_t`.

    #include <stdio.h>
    int main() {
        string_t s = string_alloc_from_chars("Hello World!");
        if (string_is_valid(s)) 
            puts(string_to_chars(s));
        string_free(s);
        return 0;
    }