vatrog-vm-introspection-engine/src/engine/text.c

#include <stdint.h>
#include <stddef.h>
#include "engine.h"
#include "vmie.h"

static void utf8_emit(uint32_t cp, char* dst, size_t size, size_t* need, size_t* wrote) {
    uint8_t b[4]; size_t k;
    if      (cp < 0x80)    { b[0]=(uint8_t)cp; k=1; }
    else if (cp < 0x800)   { b[0]=0xC0|(uint8_t)(cp>>6);  b[1]=0x80|(cp&0x3F); k=2; }
    else if (cp < 0x10000) { b[0]=0xE0|(uint8_t)(cp>>12); b[1]=0x80|((cp>>6)&0x3F); b[2]=0x80|(cp&0x3F); k=3; }
    else                   { b[0]=0xF0|(uint8_t)(cp>>18); b[1]=0x80|((cp>>12)&0x3F); b[2]=0x80|((cp>>6)&0x3F); b[3]=0x80|(cp&0x3F); k=4; }
    if (dst && *need + k < size) {
        for (size_t j = 0; j < k; j++) dst[*need + j] = (char)b[j];
        *wrote = *need + k;                        /* end of last full code point */
    }
    *need += k;
}

size_t gva_read_text(vmie* v, uintptr_t cr3, uintptr_t va, size_t nmemb, char* dst, size_t size) {
    vmie_mem* m = &v->mem;
    size_t   need = 0, wrote = 0;
    uint16_t stage[256];
    uint32_t hi = 0;
    nmemb &= ~(size_t)1;

    while (nmemb) {
        size_t chunk = nmemb < sizeof stage ? nmemb : sizeof stage;
        if (gva_read(m, cr3, va, stage, chunk)) {
            break;
        }
        const size_t units = chunk / 2;
        for (size_t i = 0; i < units; i++) {
            uint32_t u = stage[i];
            if (hi) {
                if (u >= 0xDC00 && u <= 0xDFFF) {
                    utf8_emit(0x10000u + ((hi - 0xD800u) << 10) + (u - 0xDC00u), dst, size, &need, &wrote);
                    hi = 0;
                    continue;
                }
                utf8_emit(0xFFFD, dst, size, &need, &wrote);
                hi = 0;
            }
            if      (u >= 0xD800 && u <= 0xDBFF) hi = u;
            else if (u >= 0xDC00 && u <= 0xDFFF) utf8_emit(0xFFFD, dst, size, &need, &wrote);
            else                                 utf8_emit(u, dst, size, &need, &wrote);
        }
        va    += chunk;
        nmemb -= chunk;
    }
    if (hi) utf8_emit(0xFFFD, dst, size, &need, &wrote);
    if (dst && size) dst[need < size ? need : wrote] = 0;
    return need;
}