diff options
Diffstat (limited to 'lib/unistr')
| -rw-r--r-- | lib/unistr/u-cpy.h | 33 | ||||
| -rw-r--r-- | lib/unistr/u8-cpy.c | 33 | ||||
| -rw-r--r-- | lib/unistr/u8-mbtouc-unsafe-aux.c | 139 | ||||
| -rw-r--r-- | lib/unistr/u8-mbtouc-unsafe.c | 150 | ||||
| -rw-r--r-- | lib/unistr/u8-strlen.c | 29 | ||||
| -rw-r--r-- | lib/unistr/u8-uctomb-aux.c | 60 | ||||
| -rw-r--r-- | lib/unistr/u8-uctomb.c | 79 |
7 files changed, 523 insertions, 0 deletions
diff --git a/lib/unistr/u-cpy.h b/lib/unistr/u-cpy.h new file mode 100644 index 0000000..8ee3c83 --- /dev/null +++ b/lib/unistr/u-cpy.h @@ -0,0 +1,33 @@ +/* Copy piece of UTF-8/UTF-16/UTF-32 string. + Copyright (C) 1999, 2002, 2006, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2002. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <string.h> + +UNIT * +FUNC (UNIT *dest, const UNIT *src, size_t n) +{ +#if 0 + UNIT *destptr = dest; + + for (; n > 0; n--) + *destptr++ = *src++; +#else + if (n > 0) + memcpy ((char *) dest, (const char *) src, n * sizeof (UNIT)); +#endif + return dest; +} diff --git a/lib/unistr/u8-cpy.c b/lib/unistr/u8-cpy.c new file mode 100644 index 0000000..e884b32 --- /dev/null +++ b/lib/unistr/u8-cpy.c @@ -0,0 +1,33 @@ +/* Copy piece of UTF-8 string. + Copyright (C) 2002, 2006, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2002. + + This file is free software. + It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+". + You can redistribute it and/or modify it under either + - the terms of the GNU Lesser General Public License as published + by the Free Software Foundation, either version 3, or (at your + option) any later version, or + - the terms of the GNU General Public License as published by the + Free Software Foundation; either version 2, or (at your option) + any later version, or + - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". + + This file 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 + Lesser General Public License and the GNU General Public License + for more details. + + You should have received a copy of the GNU Lesser General Public + License and of the GNU General Public License along with this + program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +/* Specification. */ +#include "unistr.h" + +#define FUNC u8_cpy +#define UNIT uint8_t +#include "u-cpy.h" diff --git a/lib/unistr/u8-mbtouc-unsafe-aux.c b/lib/unistr/u8-mbtouc-unsafe-aux.c new file mode 100644 index 0000000..9e2e34b --- /dev/null +++ b/lib/unistr/u8-mbtouc-unsafe-aux.c @@ -0,0 +1,139 @@ +/* Conversion UTF-8 to UCS-4. + Copyright (C) 2001-2002, 2006-2007, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2001. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +/* Specification. */ +#include "unistr.h" + +#if defined IN_LIBUNISTRING || HAVE_INLINE + +int +u8_mbtouc_unsafe_aux (ucs4_t *puc, const uint8_t *s, size_t n) +{ + uint8_t c = *s; + + if (c >= 0xc2) + { + if (c < 0xe0) + { + if (n >= 2) + { + if ((s[1] ^ 0x80) < 0x40) + { + *puc = ((unsigned int) (c & 0x1f) << 6) + | (unsigned int) (s[1] ^ 0x80); + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + return 1; + } + } + else if (c < 0xf0) + { + if (n >= 3) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((c >= 0xe1 || s[1] >= 0xa0) + && (c != 0xed || s[1] < 0xa0)) + { + *puc = ((unsigned int) (c & 0x0f) << 12) + | ((unsigned int) (s[1] ^ 0x80) << 6) + | (unsigned int) (s[2] ^ 0x80); + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else + return 2; + } + } + else if (c < 0xf8) + { + if (n >= 4) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((c >= 0xf1 || s[1] >= 0x90) + && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) + ) + { + *puc = ((unsigned int) (c & 0x07) << 18) + | ((unsigned int) (s[1] ^ 0x80) << 12) + | ((unsigned int) (s[2] ^ 0x80) << 6) + | (unsigned int) (s[3] ^ 0x80); + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else if (n == 2 || (s[2] ^ 0x80) >= 0x40) + return 2; + else + return 3; + } + } + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 1; +} + +#endif diff --git a/lib/unistr/u8-mbtouc-unsafe.c b/lib/unistr/u8-mbtouc-unsafe.c new file mode 100644 index 0000000..71d0db8 --- /dev/null +++ b/lib/unistr/u8-mbtouc-unsafe.c @@ -0,0 +1,150 @@ +/* Look at first character in UTF-8 string. + Copyright (C) 1999-2002, 2006-2007, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2001. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +#if defined IN_LIBUNISTRING +/* Tell unistr.h to declare u8_mbtouc_unsafe as 'extern', not + 'static inline'. */ +# include "unistring-notinline.h" +#endif + +/* Specification. */ +#include "unistr.h" + +#if !HAVE_INLINE + +int +u8_mbtouc_unsafe (ucs4_t *puc, const uint8_t *s, size_t n) +{ + uint8_t c = *s; + + if (c < 0x80) + { + *puc = c; + return 1; + } + else if (c >= 0xc2) + { + if (c < 0xe0) + { + if (n >= 2) + { + if ((s[1] ^ 0x80) < 0x40) + { + *puc = ((unsigned int) (c & 0x1f) << 6) + | (unsigned int) (s[1] ^ 0x80); + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + return 1; + } + } + else if (c < 0xf0) + { + if (n >= 3) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((c >= 0xe1 || s[1] >= 0xa0) + && (c != 0xed || s[1] < 0xa0)) + { + *puc = ((unsigned int) (c & 0x0f) << 12) + | ((unsigned int) (s[1] ^ 0x80) << 6) + | (unsigned int) (s[2] ^ 0x80); + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else + return 2; + } + } + else if (c < 0xf8) + { + if (n >= 4) + { + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((c >= 0xf1 || s[1] >= 0x90) + && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) + ) + { + *puc = ((unsigned int) (c & 0x07) << 18) + | ((unsigned int) (s[1] ^ 0x80) << 12) + | ((unsigned int) (s[2] ^ 0x80) << 6) + | (unsigned int) (s[3] ^ 0x80); + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; + } + /* invalid multibyte character */ + } + else + { + /* incomplete multibyte character */ + *puc = 0xfffd; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else if (n == 2 || (s[2] ^ 0x80) >= 0x40) + return 2; + else + return 3; + } + } + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 1; +} + +#endif diff --git a/lib/unistr/u8-strlen.c b/lib/unistr/u8-strlen.c new file mode 100644 index 0000000..40b35a3 --- /dev/null +++ b/lib/unistr/u8-strlen.c @@ -0,0 +1,29 @@ +/* Determine length of UTF-8 string. + Copyright (C) 2002, 2006, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2002. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +/* Specification. */ +#include "unistr.h" + +#include <string.h> + +size_t +u8_strlen (const uint8_t *s) +{ + return strlen ((const char *) s); +} diff --git a/lib/unistr/u8-uctomb-aux.c b/lib/unistr/u8-uctomb-aux.c new file mode 100644 index 0000000..6deeeb7 --- /dev/null +++ b/lib/unistr/u8-uctomb-aux.c @@ -0,0 +1,60 @@ +/* Conversion UCS-4 to UTF-8. + Copyright (C) 2002, 2006-2007, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2002. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +/* Specification. */ +#include "unistr.h" + +#include "attribute.h" + +int +u8_uctomb_aux (uint8_t *s, ucs4_t uc, ptrdiff_t n) +{ + int count; + + if (uc < 0x80) + /* The case n >= 1 is already handled by the caller. */ + return -2; + else if (uc < 0x800) + count = 2; + else if (uc < 0x10000) + { + if (uc < 0xd800 || uc >= 0xe000) + count = 3; + else + return -1; + } + else if (uc < 0x110000) + count = 4; + else + return -1; + + if (n < count) + return -2; + + switch (count) /* note: code falls through cases! */ + { + case 4: s[3] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x10000; + FALLTHROUGH; + case 3: s[2] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x800; + FALLTHROUGH; + case 2: s[1] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0xc0; + /*case 1:*/ s[0] = uc; + } + return count; +} diff --git a/lib/unistr/u8-uctomb.c b/lib/unistr/u8-uctomb.c new file mode 100644 index 0000000..58de19b --- /dev/null +++ b/lib/unistr/u8-uctomb.c @@ -0,0 +1,79 @@ +/* Store a character in UTF-8 string. + Copyright (C) 2002, 2005-2006, 2009-2023 Free Software Foundation, Inc. + Written by Bruno Haible <bruno@clisp.org>, 2002. + + This file is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License as + published by the Free Software Foundation; either version 2.1 of the + License, or (at your option) any later version. + + This file 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 Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. */ + +#include <config.h> + +#if defined IN_LIBUNISTRING +/* Tell unistr.h to declare u8_uctomb as 'extern', not 'static inline'. */ +# include "unistring-notinline.h" +#endif + +/* Specification. */ +#include "unistr.h" + +#include "attribute.h" + +#if !HAVE_INLINE + +int +u8_uctomb (uint8_t *s, ucs4_t uc, ptrdiff_t n) +{ + if (uc < 0x80) + { + if (n > 0) + { + s[0] = uc; + return 1; + } + /* else return -2, below. */ + } + else + { + int count; + + if (uc < 0x800) + count = 2; + else if (uc < 0x10000) + { + if (uc < 0xd800 || uc >= 0xe000) + count = 3; + else + return -1; + } + else if (uc < 0x110000) + count = 4; + else + return -1; + + if (n >= count) + { + switch (count) /* note: code falls through cases! */ + { + case 4: s[3] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x10000; + FALLTHROUGH; + case 3: s[2] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0x800; + FALLTHROUGH; + case 2: s[1] = 0x80 | (uc & 0x3f); uc = uc >> 6; uc |= 0xc0; + /*case 1:*/ s[0] = uc; + } + return count; + } + } + return -2; +} + +#endif |