// Copyright (c) 2012- PPSSPP Project. // This program is free software: you can redistribute it and/or modify // it under the terms of the GNU General Public License as published by // the Free Software Foundation, version 2.0 or later versions. // This program is distributed in the hope that it will be useful, // but WITHOUT ANY WARRANTY; without even the implied warranty of // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the // GNU General Public License 2.0 for more details. // A copy of the GPL 2.0 should have been included with the program. // If not, see http://www.gnu.org/licenses/ // Official git repository and contact information can be found at // https://github.com/hrydgard/ppsspp and http://www.ppsspp.org/. #include "util/text/utf8.h" #include "util/text/utf16.h" #include "util/text/shiftjis.h" #include "Common/ChunkFile.h" #include "Core/HLE/HLE.h" #include "Core/Reporting.h" typedef PSPPointer PSPCharPointer; typedef PSPPointer PSPWCharPointer; static u16 errorUTF8; static u16 errorUTF16; static u16 errorSJIS; // These tables point directly to PSP memory and map all 64k possible u16 values. static PSPWCharPointer ucs2jisTable; static PSPWCharPointer jis2ucsTable; void __CccInit() { errorUTF8 = 0; errorUTF16 = 0; errorSJIS = 0; ucs2jisTable = 0; jis2ucsTable = 0; } void __CccDoState(PointerWrap &p) { auto s = p.Section("sceCcc", 1); if (!s) return; p.Do(errorUTF8); p.Do(errorUTF16); p.Do(errorSJIS); p.Do(ucs2jisTable); p.Do(jis2ucsTable); } u32 __CccUCStoJIS(u32 c, u32 alt) { // JIS can only be 16-bit at most, UCS can be 32 (even if the table only supports UCS-2.) alt &= 0xFFFF; // If it's outside the table or blank in the table, return alt. if (c > 0xFFFF || ucs2jisTable[c] == 0) return alt; return ucs2jisTable[c]; } u32 __CccJIStoUCS(u32 c, u32 alt) { // JIS can only be 16-bit at most, UCS can be 32 (even if the table only supports UCS-2.) c &= 0xFFFF; if (jis2ucsTable[c] == 0) return alt; return jis2ucsTable[c]; } void sceCccSetTable(u32 jis2ucs, u32 ucs2jis) { // Both tables jis2ucs and ucs2jis have a size of 0x20000 bytes. DEBUG_LOG(HLE, "sceCccSetTable(%08x, %08x)", jis2ucs, ucs2jis); ucs2jisTable = ucs2jis; jis2ucsTable = jis2ucs; } int sceCccUTF8toUTF16(u32 dstAddr, int dstSize, u32 srcAddr) { PSPCharPointer src; PSPWCharPointer dst; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccUTF8toUTF16(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccUTF8toUTF16(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); UTF8 utf(src); int n = 0; while (u32 c = utf.next()) { dst += UTF16LE::encode(dst, c); n++; } return n; } int sceCccUTF8toSJIS(u32 dstAddr, int dstSize, u32 srcAddr) { PSPCharPointer dst, src; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccUTF8toSJIS(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } if (!ucs2jisTable.IsValid()) { ERROR_LOG(HLE, "sceCccUTF8toSJIS(%08x, %d, %08x): table not loaded", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccUTF8toSJIS(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); UTF8 utf(src); int n = 0; while (u32 c = utf.next()) { dst += ShiftJIS::encode(dst, __CccUCStoJIS(c, errorSJIS)); n++; } return n; } int sceCccUTF16toUTF8(u32 dstAddr, int dstSize, u32 srcAddr) { PSPWCharPointer src; PSPCharPointer dst; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccUTF16toUTF8(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccUTF16toUTF8(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); UTF16LE utf(src); int n = 0; while (u32 c = utf.next()) { dst += UTF8::encode(dst, c); n++; } return n; } int sceCccUTF16toSJIS(u32 dstAddr, int dstSize, u32 srcAddr) { PSPWCharPointer src; PSPCharPointer dst; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccUTF16toSJIS(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } if (!ucs2jisTable.IsValid()) { ERROR_LOG(HLE, "sceCccUTF16toSJIS(%08x, %d, %08x): table not loaded", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccUTF16toSJIS(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); UTF16LE utf(src); int n = 0; while (u32 c = utf.next()) { dst += ShiftJIS::encode(dst, __CccUCStoJIS(c, errorSJIS)); n++; } return n; } int sceCccSJIStoUTF8(u32 dstAddr, int dstSize, u32 srcAddr) { PSPCharPointer dst, src; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccSJIStoUTF8(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } if (!jis2ucsTable.IsValid()) { ERROR_LOG(HLE, "sceCccSJIStoUTF8(%08x, %d, %08x): table not loaded", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccSJIStoUTF8(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); ShiftJIS sjis(src); int n = 0; while (u32 c = sjis.next()) { dst += UTF8::encode(dst, __CccJIStoUCS(c, errorUTF8)); n++; } return n; } int sceCccSJIStoUTF16(u32 dstAddr, int dstSize, u32 srcAddr) { PSPCharPointer src; PSPWCharPointer dst; dst = dstAddr; src = srcAddr; if (!dst.IsValid() || !src.IsValid()) { ERROR_LOG(HLE, "sceCccSJIStoUTF16(%08x, %d, %08x): invalid pointers", dstAddr, dstSize, srcAddr); return 0; } if (!jis2ucsTable.IsValid()) { ERROR_LOG(HLE, "sceCccSJIStoUTF16(%08x, %d, %08x): table not loaded", dstAddr, dstSize, srcAddr); return 0; } DEBUG_LOG(HLE, "sceCccSJIStoUTF16(%08x, %d, %08x)", dstAddr, dstSize, srcAddr); ShiftJIS sjis(src); int n = 0; while (u32 c = sjis.next()) { dst += UTF16LE::encode(dst, __CccJIStoUCS(c, errorUTF16)); n++; } return n; } int sceCccStrlenUTF8(u32 strAddr) { PSPCharPointer str; str = strAddr; if (!str.IsValid()) { ERROR_LOG(HLE, "sceCccStrlenUTF8(%08x): invalid pointer", strAddr); return 0; } DEBUG_LOG(HLE, "sceCccStrlenUTF8(%08x): invalid pointer", strAddr); return UTF8(str).length(); } int sceCccStrlenUTF16(u32 strAddr) { PSPWCharPointer str; str = strAddr; if (!str.IsValid()) { ERROR_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr); return 0; } DEBUG_LOG(HLE, "sceCccStrlenUTF16(%08x): invalid pointer", strAddr); return UTF16LE(str).length(); } int sceCccStrlenSJIS(u32 strAddr) { PSPCharPointer str; str = strAddr; if (!str.IsValid()) { ERROR_LOG(HLE, "sceCccStrlenSJIS(%08x): invalid pointer", strAddr); return 0; } DEBUG_LOG(HLE, "sceCccStrlenSJIS(%08x): invalid pointer", strAddr); return ShiftJIS(str).length(); } u32 sceCccEncodeUTF8(u32 dstAddrAddr, u32 ucs) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccEncodeUTF8(%08x, U+%04x): invalid pointer", dstAddrAddr, ucs); return 0; } DEBUG_LOG(HLE, "sceCccEncodeUTF8(%08x, U+%04x)", dstAddrAddr, ucs); *dstp += UTF8::encode(*dstp, ucs); return dstp->ptr; } void sceCccEncodeUTF16(u32 dstAddrAddr, u32 ucs) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccEncodeUTF16(%08x, U+%04x): invalid pointer", dstAddrAddr, ucs); return; } DEBUG_LOG(HLE, "sceCccEncodeUTF16(%08x, U+%04x)", dstAddrAddr, ucs); // Anything above 0x10FFFF is unencodable, and 0xD800 - 0xDFFF are reserved for surrogate pairs. if (ucs > 0x10FFFF || (ucs & 0xD800) == 0xD800) ucs = errorUTF16; *dstp += UTF16LE::encode(*dstp, ucs); } u32 sceCccEncodeSJIS(u32 dstAddrAddr, u32 jis) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccEncodeSJIS(%08x, U+%04x): invalid pointer", dstAddrAddr, jis); return 0; } DEBUG_LOG(HLE, "sceCccEncodeSJIS(%08x, U+%04x)", dstAddrAddr, jis); *dstp += ShiftJIS::encode(*dstp, jis); return dstp->ptr; } u32 sceCccDecodeUTF8(u32 dstAddrAddr) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccDecodeUTF8(%08x): invalid pointer", dstAddrAddr); // Should crash? return 0; } DEBUG_LOG(HLE, "sceCccDecodeUTF8(%08x)", dstAddrAddr); UTF8 utf(*dstp); u32 result = utf.next(); *dstp += utf.byteIndex(); if (result == UTF8::INVALID) return errorUTF8; return result; } u32 sceCccDecodeUTF16(u32 dstAddrAddr) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccDecodeUTF16(%08x): invalid pointer", dstAddrAddr); // Should crash? return 0; } DEBUG_LOG(HLE, "sceCccDecodeUTF16(%08x)", dstAddrAddr); // TODO: Does it do any detection of BOM? UTF16LE utf(*dstp); u32 result = utf.next(); *dstp += utf.byteIndex(); if (result == UTF16LE::INVALID) return errorUTF16; return result; } u32 sceCccDecodeSJIS(u32 dstAddrAddr) { auto dstp = PSPPointer::Create(dstAddrAddr); if (!dstp.IsValid() || !dstp->IsValid()) { ERROR_LOG(HLE, "sceCccDecodeSJIS(%08x): invalid pointer", dstAddrAddr); // Should crash? return 0; } DEBUG_LOG(HLE, "sceCccDecodeSJIS(%08x)", dstAddrAddr); ShiftJIS sjis(*dstp); u32 result = sjis.next(); *dstp += sjis.byteIndex(); if (result == ShiftJIS::INVALID) return errorSJIS; return result; } int sceCccIsValidUTF8(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidUTF8(%08x)", c); return c != 0; } int sceCccIsValidUTF16(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidUTF16(%08x)", c); return c != 0; } int sceCccIsValidSJIS(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidSJIS(%08x)", c); return c != 0; } int sceCccIsValidUCS2(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidUCS2(%08x)", c); return c != 0; } int sceCccIsValidUCS4(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidUCS4(%08x)", c); return c != 0; } int sceCccIsValidJIS(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidJIS(%08x)", c); return c != 0; } int sceCccIsValidUnicode(u32 c) { WARN_LOG(HLE, "UNIMPL sceCccIsValidUnicode(%08x)", c); return c != 0; } u32 sceCccSetErrorCharUTF8(u32 c) { DEBUG_LOG(HLE, "sceCccSetErrorCharUTF8(%08x)", c); int result = errorUTF8; errorUTF8 = c; return result; } u32 sceCccSetErrorCharUTF16(u32 c) { DEBUG_LOG(HLE, "sceCccSetErrorCharUTF16(%08x)", c); int result = errorUTF16; errorUTF16 = c; return result; } u32 sceCccSetErrorCharSJIS(u32 c) { DEBUG_LOG(HLE, "sceCccSetErrorCharSJIS(%04x)", c); int result = errorSJIS; errorSJIS = c; return result; } u32 sceCccUCStoJIS(u32 c, u32 alt) { if (ucs2jisTable.IsValid()) { DEBUG_LOG(HLE, "sceCccUCStoJIS(%08x, %08x)", c, alt); return __CccUCStoJIS(c, alt); } else { ERROR_LOG(HLE, "sceCccUCStoJIS(%08x, %08x): table not loaded", c, alt); return alt; } } u32 sceCccJIStoUCS(u32 c, u32 alt) { if (jis2ucsTable.IsValid()) { DEBUG_LOG(HLE, "sceCccUCStoJIS(%08x, %08x)", c, alt); return __CccJIStoUCS(c, alt); } else { ERROR_LOG(HLE, "sceCccUCStoJIS(%08x, %08x): table not loaded", c, alt); return alt; } } const HLEFunction sceCcc[] = { {0xB4D1CBBF, WrapV_UU, "sceCccSetTable"}, {0x00D1378F, WrapI_UIU, "sceCccUTF8toUTF16"}, {0x6F82EE03, WrapI_UIU, "sceCccUTF8toSJIS"}, {0x41B724A5, WrapI_UIU, "sceCccUTF16toUTF8"}, {0xF1B73D12, WrapI_UIU, "sceCccUTF16toSJIS"}, {0xA62E6E80, WrapI_UIU, "sceCccSJIStoUTF8"}, {0xBEB47224, WrapI_UIU, "sceCccSJIStoUTF16"}, {0xb7d3c112, WrapI_U, "sceCccStrlenUTF8"}, {0x4BDEB2A8, WrapI_U, "sceCccStrlenUTF16"}, {0xd9392ccb, WrapI_U, "sceCccStrlenSJIS"}, {0x92C05851, WrapU_UU, "sceCccEncodeUTF8"}, {0x8406F469, WrapV_UU, "sceCccEncodeUTF16"}, {0x068c4320, WrapU_UU, "sceCccEncodeSJIS"}, {0xc6a8bee2, WrapU_U, "sceCccDecodeUTF8"}, {0xe0cf8091, WrapU_U, "sceCccDecodeUTF16"}, {0x953e6c10, WrapU_U, "sceCccDecodeSJIS"}, {0x90521ac5, WrapI_U, "sceCccIsValidUTF8"}, {0xcc0a8bda, WrapI_U, "sceCccIsValidUTF16"}, {0x67bf0d19, WrapI_U, "sceCccIsValidSJIS"}, {0x76e33e9c, WrapI_U, "sceCccIsValidUCS2"}, {0xd2b18485, WrapI_U, "sceCccIsValidUCS4"}, {0xa2d5d209, WrapI_U, "sceCccIsValidJIS"}, {0xbd11eef3, WrapI_U, "sceCccIsValidUnicode"}, {0x17e1d813, WrapU_U, "sceCccSetErrorCharUTF8"}, {0xb8476cf4, WrapU_U, "sceCccSetErrorCharUTF16"}, {0xc56949ad, WrapU_U, "sceCccSetErrorCharSJIS"}, {0x70ecaa10, WrapU_UU, "sceCccUCStoJIS"}, {0xfb7846e2, WrapU_UU, "sceCccJIStoUCS"}, }; void Register_sceCcc() { RegisterModule("sceCcc", ARRAY_SIZE(sceCcc), sceCcc); }