squall/storm/Unicode.cpp

#include "storm/Unicode.hpp"
#include "storm/Error.hpp"
#include "storm/String.hpp"

// Windows
// https://en.wikipedia.org/wiki/Windows-1252
const char16_t CP1252[256] = {
    0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
    0x8, 0x9, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF,
    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
    0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
    0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
    0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
    0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
    0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
    0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
    0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
    0x20AC, 0xFFFF, 0x201A, 0x192, 0x201E, 0x2026, 0x2020, 0x2021,
    0x2C6, 0x2030, 0x160, 0x2039, 0x152, 0xFFFF, 0x17D, 0xFFFF,
    0xFFFF, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
    0x2DC, 0x2122, 0x161, 0x203A, 0x153, 0xFFFF, 0x17E, 0x178,
    0xA0, 0xA1, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7,
    0xA8, 0xA9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
    0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0xB6, 0xB7,
    0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
    0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
    0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
    0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
    0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
    0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
    0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
    0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
    0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF,
};

// Mac
// https://en.wikipedia.org/wiki/Mac_OS_Roman
const char16_t CP10000[256] = {
    0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
    0x8, 0x9, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF,
    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
    0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
    0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
    0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
    0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
    0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
    0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
    0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
    0xC4, 0xC5, 0xC7, 0xC9, 0xD1, 0xD6, 0xDC, 0xE1,
    0xE0, 0xE2, 0xE4, 0xE3, 0xE5, 0xE7, 0xE9, 0xE8,
    0xEA, 0xEB, 0xED, 0xEC, 0xEE, 0xEF, 0xF1, 0xF3,
    0xF2, 0xF4, 0xF6, 0xF5, 0xFA, 0xF9, 0xFB, 0xFC,
    0x2020, 0xB0, 0xA2, 0xA3, 0xA7, 0x2022, 0xB6, 0xDF,
    0xAE, 0xA9, 0x2122, 0xB4, 0xA8, 0x2260, 0xC6, 0xD8,
    0x221E, 0xB1, 0x2264, 0x2265, 0xA5, 0xB5, 0x2202, 0x2211,
    0x220F, 0x3C0, 0x222B, 0xAA, 0xBA, 0x2126, 0xE6, 0xF8,
    0xBF, 0xA1, 0xAC, 0x221A, 0x192, 0x2248, 0x2206, 0xAB,
    0xBB, 0x2026, 0xA0, 0xC0, 0xC3, 0xD5, 0x152, 0x153,
    0x2013, 0x2014, 0x201C, 0x201D, 0x2018, 0x2019, 0xF7, 0x25CA,
    0xFF, 0x178, 0x2044, 0xA4, 0x2039, 0x203A, 0xFB01, 0xFB02,
    0x2021, 0xB7, 0x201A, 0x201E, 0x2030, 0xC2, 0xCA, 0xC1,
    0xCB, 0xC8, 0xCD, 0xCE, 0xCF, 0xCC, 0xD3, 0xD4,
    0xFFFF, 0xD2, 0xDA, 0xDB, 0xD9, 0x131, 0x2C6, 0x2DC,
    0xAF, 0x2D8, 0x2D9, 0x2DA, 0xB8, 0x2DD, 0x2DB, 0x2C7,
};

// DOS
// https://en.wikipedia.org/wiki/Code_page_437
const char16_t CP437[256] = {
    0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7,
    0x8, 0x9, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF,
    0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
    0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
    0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
    0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
    0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
    0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
    0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
    0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
    0xC7, 0xFC, 0xE9, 0xE2, 0xE4, 0xE0, 0xE5, 0xE7,
    0xEA, 0xEB, 0xE8, 0xEF, 0xEE, 0xEC, 0xC4, 0xC5,
    0xC9, 0xE6, 0xC6, 0xF4, 0xF6, 0xF2, 0xFB, 0xF9,
    0xFF, 0xD6, 0xDC, 0xA2, 0xA3, 0xA5, 0x20A7, 0x192,
    0xE1, 0xED, 0xF3, 0xFA, 0xF1, 0xD1, 0xAA, 0xBA,
    0xBF, 0x2310, 0xAC, 0xBD, 0xBC, 0xA1, 0xAB, 0xBB,
    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
    0x2555, 0x2563, 0x2551, 0x2557, 0x255D, 0x255C, 0x255B, 0x2510,
    0x2514, 0x2534, 0x252C, 0x251C, 0x2500, 0x253C, 0x255E, 0x255F,
    0x255A, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0x2567,
    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256B,
    0x256A, 0x2518, 0x250C, 0x2588, 0x2584, 0x258C, 0x2590, 0x2580,
    0x3B1, 0xDF, 0x393, 0x3C0, 0x3A3, 0x3C3, 0xB5, 0x3C4,
    0x3A6, 0x398, 0x3A9, 0x3B4, 0x221E, 0x3C6, 0x3B5, 0x2229,
    0x2261, 0xB1, 0x2265, 0x2264, 0x2320, 0x2321, 0xF7, 0x2248,
    0xB0, 0x2219, 0xB7, 0x221A, 0x207F, 0xB2, 0x25A0, 0xA0,
};

ptrdiff_t SUniConvertCPToUTF16(const char16_t* codepage, char16_t* dest, const char* source, uint32_t destsize) {
    if (destsize == 0) return 0;

    char16_t* curr = dest;
    while (*source && destsize != 0) {
        *curr++ = codepage[static_cast<uint8_t>(*source)];
        source++;
        destsize--;
    }

    if (destsize != 0) *curr++ = '\0';
    STORM_ASSERT(curr >= dest);
    STORM_ASSERT(curr - dest <= STORM_MAX_STR);
    return curr - dest;
}

ptrdiff_t SUniConvertUTF16ToCP(const char16_t* codepage, char* dest, const char16_t* source, uint32_t destsize) {
    if (destsize == 0) return 0;

    char* curr = dest;
    while (*source && destsize != 0) {
        if (*source < 256 && *source == codepage[*source]) {
            *curr++ = static_cast<uint8_t>(*source++);
        }
        else {
            int i = 255;
            while (i > 0 && *source != codepage[i]) {
                i--;
            }
            *curr++ = i ? i : '?';
            source++;
        }
        destsize--;
    }

    if (destsize != 0) *curr++ = '\0';
    STORM_ASSERT(curr >= dest);
    STORM_ASSERT(curr - dest <= STORM_MAX_STR);
    return curr - dest;
}

int32_t FindUTF8Character(const char* utf8String, int32_t index, int32_t direction) {
    for (; index > 0; index += direction) {
        char c = utf8String[index];
        if (c == '\0') break;
        if ((c & 0xC0) != 0x80) break;
    }
    return index;
}

ptrdiff_t STORMAPI SUniConvertUTF16ToDos(char* dest, const char16_t* source, uint32_t destsize) {
    return SUniConvertUTF16ToCP(CP437, dest, source, destsize);
}

ptrdiff_t STORMAPI SUniConvertUTF16ToMac(char* dest, const char16_t* source, uint32_t destsize) {
    return SUniConvertUTF16ToCP(CP10000, dest, source, destsize);
}

ptrdiff_t STORMAPI SUniConvertUTF16ToWin(char* dest, const char16_t* source, uint32_t destsize) {
    // TODO: Starcraft flavour branches with `GetACP() == 949` (IBM Korean lang)
    return SUniConvertUTF16ToCP(CP1252, dest, source, destsize);
}

ptrdiff_t STORMAPI SUniConvertDosToUTF16(char16_t* dest, const char* source, uint32_t destsize) {
    return SUniConvertCPToUTF16(CP437, dest, source, destsize);
}

ptrdiff_t STORMAPI SUniConvertMacToUTF16(char16_t* dest, const char* source, uint32_t destsize) {
    return SUniConvertCPToUTF16(CP10000, dest, source, destsize);
}

ptrdiff_t STORMAPI SUniConvertWinToUTF16(char16_t* dest, const char* source, uint32_t destsize) {
    // TODO: Starcraft flavour branches with `GetACP() == 949` (IBM Korean lang)
    return SUniConvertCPToUTF16(CP1252, dest, source, destsize);
}

int32_t STORMAPI SUniFindAfterUTF8Chr(const char* utf8String, int32_t index) {
    return FindUTF8Character(utf8String, index + 1, 1);
}

int32_t STORMAPI SUniFindUTF8ChrStart(const char* utf8String, int32_t index) {
    return FindUTF8Character(utf8String, index, -1);
}

uint32_t STORMAPI SUniSGetUTF8(const uint8_t* strptr, int32_t* chars) {
    if (chars) {
        *chars = 0;
    }

    if (!strptr || !*strptr) {
        return -1;
    }

    if (chars) {
        *chars = *chars + 1;
    }

    uint32_t value = *strptr;
    int32_t extra;

    if ((value & 0xFE) == 0xFC) {
        value &= 0x01;
        extra = 5;
    } else if ((value & 0xFC) == 0xF8) {
        value &= 0x03;
        extra = 4;
    } else if ((value & 0xF8) == 0xF0) {
        value &= 0x07;
        extra = 3;
    } else if ((value & 0xF0) == 0xE0) {
        value &= 0x0F;
        extra = 2;
    } else if ((value & 0xE0) == 0xC0) {
        value &= 0x1F;
        extra = 1;
    } else if ((value & 0x80) == 0x00) {
        return value;
    } else {
        return 0x80000000;
    }

    const uint8_t* next = strptr + 1;

    for (int32_t i = 0; i < extra; i++, next++) {
        if (!*next) {
            return -1;
        }

        if (chars) {
            *chars = *chars + 1;
        }

        if ((*next & 0xC0) != 0x80) {
            return 0x80000000;
        }

        value = (value << 6) | (*next & 0x3F);
    }

    return value;
}

void STORMAPI SUniSPutUTF8(uint32_t c, char* strptr) {
    if (!strptr) {
        return;
    }

    auto curstr = strptr;
    auto v3 = c;
    char v4, v5, v6, v7;

    if (c >= 0x80) {
        if (c >= 0x800) {
            if (c >= 0x10000) {
                if (c >= 0x200000) {
                    if (c >= 0x400000) {
                        if (c >= 0x80000000) {
                            *curstr = 0;
                            return;
                        }

                        *strptr = (c >> 30) | 0xFC;
                        curstr = strptr + 1;
                        // TODO this seems likely to be bitwise right shift 24, not 8
                        v7 = ((c >> 8) & 0x3F) | 0x80;
                    } else {
                        // TODO this seems likely to be bitwise right shift 24, not 8
                        v7 = (c >> 8) | 0xF8;
                    }

                    *curstr++ = v7;
                    v6 = ((c >> 18) & 0x3F) | 0x80;
                } else {
                    v6 = (c >> 18) | 0xF0;
                }

                *curstr++ = v6;
                v5 = ((c >> 12) & 0x3F) | 0x80;
            } else {
                v5 = (c >> 12) | 0xE0;
            }

            *curstr++ = v5;
            v4 = ((c >> 6) & 0x3F) | 0x80;
        } else {
            v4 = (c >> 6) | 0xC0;
        }

        *curstr++ = v4;
        v3 = (c & 0x3F) | 0x80;
    }

    *curstr++ = v3;
    *curstr = '\0';
}