diff options
Diffstat (limited to 'src/utilfuns/utilstr.cpp')
-rw-r--r-- | src/utilfuns/utilstr.cpp | 217 |
1 files changed, 179 insertions, 38 deletions
diff --git a/src/utilfuns/utilstr.cpp b/src/utilfuns/utilstr.cpp index 67ffcd5..cabd455 100644 --- a/src/utilfuns/utilstr.cpp +++ b/src/utilfuns/utilstr.cpp @@ -1,5 +1,10 @@ -/* - * Copyright 2009 CrossWire Bible Society (http://www.crosswire.org) +/****************************************************************************** + * + * utilstr.cpp - String utility functions + * + * $Id: utilstr.cpp 2982 2013-09-15 13:33:03Z scribe $ + * + * Copyright 1997-2013 CrossWire Bible Society (http://www.crosswire.org) * CrossWire Bible Society * P. O. Box 2528 * Tempe, AZ 85280-2528 @@ -26,42 +31,40 @@ SWORD_NAMESPACE_START -const unsigned char SW_toupper_array[256] = - { - 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, - 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, - 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, 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, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, - 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, - 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, - 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, - 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, - 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, - 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, - 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, - 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, - 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff - }; - +const unsigned char SW_toupper_array[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, + 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, 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, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, + 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, + 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, + 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, + 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, + 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, + 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, + 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, + 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff +}; /****************************************************************************** @@ -243,6 +246,103 @@ __u32 getUniCharFromUTF8(const unsigned char **buf) { } +SWBuf getUTF8FromUniChar(__u32 uchar) { + SWBuf retVal("", 7); + unsigned int i; + + if (uchar < 0x80) { + retVal.append((unsigned char)uchar); + retVal.setSize(1); + } + else if (uchar < 0x800) { + retVal.setSize(2); + i = uchar & 0x3f; + retVal[1] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x1f; + retVal[0] = (unsigned char)(0xc0 | i); + } + else if (uchar < 0x10000) { + retVal.setSize(3); + i = uchar & 0x3f; + retVal[2] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[1] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x0f; + retVal[0] = (unsigned char)(0xe0 | i); + } + else if (uchar < 0x200000) { + retVal.setSize(4); + i = uchar & 0x3f; + retVal[3] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[2] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[1] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x07; + retVal[0] = (unsigned char)(0xf0 | i); + } + else if (uchar < 0x4000000) { + retVal.setSize(5); + i = uchar & 0x3f; + retVal[4] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[3] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[2] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[1] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x03; + retVal[0] = (unsigned char)(0xf8 | i); + } + else if (uchar < 0x80000000) { + retVal.setSize(6); + i = uchar & 0x3f; + retVal[5] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[4] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[3] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[2] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x3f; + retVal[1] = (unsigned char)(0x80 | i); + uchar >>= 6; + + i = uchar & 0x01; + retVal[0] = (unsigned char)(0xfc | i); + } + + return retVal; +} + SWBuf assureValidUTF8(const char *buf) { @@ -269,4 +369,45 @@ SWBuf assureValidUTF8(const char *buf) { return myCopy; } + +/**** + * This can be called to convert a UTF8 stream to an SWBuf which manages + * a wchar_t[] + * access buffer with (wchar_t *)SWBuf::getRawData(); + * + */ +SWBuf utf8ToWChar(const char *buf) { + + const char *q = 0; + SWBuf wcharBuf; + while (*buf) { + q = buf; + wchar_t wc = getUniCharFromUTF8((const unsigned char **)&buf); + if (!wc) { + // if my buffer was advanced but nothing was converted, I had invalid data + if (buf - q) { + // invalid bytes in UTF8 stream + wcharBuf.append((wchar_t)0x1a); // unicode replacement character + } + } + else wcharBuf.append(wc); + } + return wcharBuf; +} + + +/**** + * This can be called to convert a wchar_t[] to a UTF-8 SWBuf + * + */ +SWBuf wcharToUTF8(const wchar_t *buf) { + + SWBuf utf8Buf; + while (*buf) { + utf8Buf.append(getUTF8FromUniChar(*buf++)); + } + return utf8Buf; +} + + SWORD_NAMESPACE_END |