Software /
code /
prosody
Diff
util-src/encodings.c @ 6607:64e6b88b6b21
Merge 0.9->0.10 (third time lucky)
author | Matthew Wild <mwild1@gmail.com> |
---|---|
date | Fri, 27 Mar 2015 22:11:58 +0000 |
parent | 6413:a552f4170aed |
parent | 6592:141afe8a167b |
child | 6608:b6e558febb7a |
line wrap: on
line diff
--- a/util-src/encodings.c Wed Jan 21 02:55:27 2015 +0100 +++ b/util-src/encodings.c Fri Mar 27 22:11:58 2015 +0000 @@ -1,6 +1,7 @@ /* Prosody IM -- Copyright (C) 2008-2010 Matthew Wild -- Copyright (C) 2008-2010 Waqas Hussain +-- Copyright (C) 1994-2015 Lua.org, PUC-Rio. -- -- This project is MIT/X11 licensed. Please see the -- COPYING file in the source package for more information. @@ -120,6 +121,88 @@ { NULL, NULL } }; +/******************* UTF-8 ********************/ + +/* + * Adapted from Lua 5.3 + * Needed because libidn does not validate that input is valid UTF-8 + */ + +#define MAXUNICODE 0x10FFFF + +/* + * Decode one UTF-8 sequence, returning NULL if byte sequence is invalid. + */ +static const char *utf8_decode (const char *o, int *val) { + static unsigned int limits[] = {0xFF, 0x7F, 0x7FF, 0xFFFF}; + const unsigned char *s = (const unsigned char *)o; + unsigned int c = s[0]; + unsigned int res = 0; /* final result */ + if (c < 0x80) /* ascii? */ + res = c; + else { + int count = 0; /* to count number of continuation bytes */ + while (c & 0x40) { /* still have continuation bytes? */ + int cc = s[++count]; /* read next byte */ + if ((cc & 0xC0) != 0x80) /* not a continuation byte? */ + return NULL; /* invalid byte sequence */ + res = (res << 6) | (cc & 0x3F); /* add lower 6 bits from cont. byte */ + c <<= 1; /* to test next bit */ + } + res |= ((c & 0x7F) << (count * 5)); /* add first byte */ + if (count > 3 || res > MAXUNICODE || res <= limits[count] || (0xd800 <= res && res <= 0xdfff) ) + return NULL; /* invalid byte sequence */ + s += count; /* skip continuation bytes read */ + } + if (val) *val = res; + return (const char *)s + 1; /* +1 to include first byte */ +} + +/* + * Check that a string is valid UTF-8 + * Returns NULL if not + */ +const char* check_utf8 (lua_State *L, int idx, size_t *l) { + size_t pos, len; + const char *s = luaL_checklstring(L, 1, &len); + pos = 0; + while (pos <= len) { + const char *s1 = utf8_decode(s + pos, NULL); + if (s1 == NULL) { /* conversion error? */ + return NULL; + } + pos = s1 - s; + } + if(l != NULL) { + *l = len; + } + return s; +} + +static int Lutf8_valid(lua_State *L) { + lua_pushboolean(L, check_utf8(L, 1, NULL) != NULL); + return 1; +} + +static int Lutf8_length(lua_State *L) { + size_t len; + if(!check_utf8(L, 1, &len)) { + lua_pushnil(L); + lua_pushliteral(L, "invalid utf8"); + return 2; + } + lua_pushinteger(L, len); + return 1; +} + +static const luaL_Reg Reg_utf8[] = +{ + { "valid", Lutf8_valid }, + { "length", Lutf8_length }, + { NULL, NULL } +}; + + /***************** STRINGPREP *****************/ #ifdef USE_STRINGPREP_ICU @@ -216,8 +299,8 @@ lua_pushnil(L); return 1; } - s = lua_tolstring(L, 1, &len); - if (len >= 1024) { + s = check_utf8(L, 1, &len); + if (s == NULL || len >= 1024 || len != strlen(s)) { lua_pushnil(L); return 1; /* TODO return error message */ } @@ -324,7 +407,11 @@ static int Lidna_to_ascii(lua_State *L) /** idna.to_ascii(s) */ { size_t len; - const char *s = luaL_checklstring(L, 1, &len); + const char *s = check_utf8(L, 1, &len); + if (s == NULL || len != strlen(s)) { + lua_pushnil(L); + return 1; /* TODO return error message */ + } char* output = NULL; int ret = idna_to_ascii_8z(s, &output, IDNA_USE_STD3_ASCII_RULES); if (ret == IDNA_SUCCESS) { @@ -384,6 +471,11 @@ luaL_register(L, NULL, Reg_idna); lua_setfield(L, -2, "idna"); + lua_newtable(L); + luaL_register(L, NULL, Reg_utf8); + lua_setfield(L, -2, "utf8"); + + lua_pushliteral(L, "version"); /** version */ lua_pushliteral(L, "-3.14"); lua_setfield(L, -2, "version"); return 1;