552 lines
15 KiB
C
552 lines
15 KiB
C
/*
|
||
** $Id: llex.c 11549 2011-04-01 10:35:32Z miros $
|
||
** Lexical Analyzer
|
||
** See Copyright Notice in lua.h
|
||
*/
|
||
|
||
|
||
#include <ctype.h>
|
||
#include <locale.h>
|
||
#include <string.h>
|
||
|
||
#define llex_c
|
||
#define LUA_CORE
|
||
|
||
#include "lua.h"
|
||
|
||
#include "ldo.h"
|
||
#include "llex.h"
|
||
#include "lobject.h"
|
||
#include "lparser.h"
|
||
#include "lstate.h"
|
||
#include "lstring.h"
|
||
#include "ltable.h"
|
||
#include "lzio.h"
|
||
|
||
|
||
|
||
#define next(ls) (ls->current = zgetc(ls->z))
|
||
|
||
|
||
|
||
|
||
#define currIsNewline(ls) (ls->current == '\n' || ls->current == '\r')
|
||
|
||
|
||
/* ORDER RESERVED */
|
||
const char *const luaX_tokens [] = {
|
||
"and", "break", "do", "else", "elseif",
|
||
"end", "false", "for", "function", "if",
|
||
"in", "local", "nil", "not", "or", "repeat",
|
||
"return", "then", "true", "until", "while",
|
||
"..", "...", "==", ">=", "<=", "~=",
|
||
"<number>", "<name>", "<string>", "<eof>",
|
||
NULL
|
||
};
|
||
|
||
|
||
#define save_and_next(ls) (save(ls, ls->current), next(ls))
|
||
|
||
|
||
static void save (LexState *ls, int c) {
|
||
Mbuffer *b = ls->buff;
|
||
if (b->n + 1 > b->buffsize) {
|
||
size_t newsize;
|
||
if (b->buffsize >= MAX_SIZET/2)
|
||
luaX_lexerror(ls, "lexical element too long", 0);
|
||
newsize = b->buffsize * 2;
|
||
luaZ_resizebuffer(ls->L, b, newsize);
|
||
}
|
||
b->buffer[b->n++] = cast(char, c);
|
||
}
|
||
|
||
|
||
void luaX_init (lua_State *L) {
|
||
int i;
|
||
for (i=0; i<NUM_RESERVED; i++) {
|
||
TString *ts = luaS_new(L, luaX_tokens[i]);
|
||
luaS_fix(ts); /* reserved words are never collected */
|
||
lua_assert(strlen(luaX_tokens[i])+1 <= TOKEN_LEN);
|
||
ts->tsv.reserved = cast_byte(i+1); /* reserved word */
|
||
}
|
||
}
|
||
|
||
|
||
#define MAXSRC 80
|
||
|
||
|
||
const char *luaX_token2str (LexState *ls, int token) {
|
||
if (token < FIRST_RESERVED) {
|
||
lua_assert(token == cast(unsigned char, token));
|
||
return (iscntrl(token)) ? luaO_pushfstring(ls->L, "char(%d)", token) :
|
||
luaO_pushfstring(ls->L, "%c", token);
|
||
}
|
||
else
|
||
return luaX_tokens[token-FIRST_RESERVED];
|
||
}
|
||
|
||
|
||
static const char *txtToken (LexState *ls, int token) {
|
||
switch (token) {
|
||
case TK_NAME:
|
||
case TK_STRING:
|
||
case TK_NUMBER:
|
||
save(ls, '\0');
|
||
return luaZ_buffer(ls->buff);
|
||
default:
|
||
return luaX_token2str(ls, token);
|
||
}
|
||
}
|
||
|
||
|
||
void luaX_lexerror (LexState *ls, const char *msg, int token) {
|
||
char buff[MAXSRC];
|
||
luaO_chunkid(buff, getstr(ls->source), MAXSRC);
|
||
msg = luaO_pushfstring(ls->L, "%s:%d: %s", buff, ls->linenumber, msg);
|
||
if (token)
|
||
luaO_pushfstring(ls->L, "%s near " LUA_QS, msg, txtToken(ls, token));
|
||
luaD_throw(ls->L, LUA_ERRSYNTAX);
|
||
}
|
||
|
||
|
||
void luaX_syntaxerror (LexState *ls, const char *msg) {
|
||
luaX_lexerror(ls, msg, ls->t.token);
|
||
}
|
||
|
||
|
||
TString *luaX_newstring (LexState *ls, const char *str, size_t l) {
|
||
lua_State *L = ls->L;
|
||
TString *ts = luaS_newlstr(L, str, l);
|
||
TValue *o = luaH_setstr(L, ls->fs->h, ts); /* entry for `str' */
|
||
if (ttisnil(o)) {
|
||
setbvalue(o, 1); /* make sure `str' will not be collected */
|
||
luaC_checkGC(L);
|
||
}
|
||
return ts;
|
||
}
|
||
|
||
|
||
static void inclinenumber (LexState *ls) {
|
||
int old = ls->current;
|
||
lua_assert(currIsNewline(ls));
|
||
next(ls); /* skip `\n' or `\r' */
|
||
if (currIsNewline(ls) && ls->current != old)
|
||
next(ls); /* skip `\n\r' or `\r\n' */
|
||
if (++ls->linenumber >= MAX_INT)
|
||
luaX_syntaxerror(ls, "chunk has too many lines");
|
||
}
|
||
|
||
|
||
void luaX_setinput (lua_State *L, LexState *ls, ZIO *z, TString *source) {
|
||
ls->decpoint = '.';
|
||
ls->L = L;
|
||
ls->lookahead.token = TK_EOS; /* no look-ahead token */
|
||
ls->z = z;
|
||
ls->fs = NULL;
|
||
ls->linenumber = 1;
|
||
ls->lastline = 1;
|
||
ls->source = source;
|
||
ls->prevtks[0].token = TK_EOS; /* no prev token */
|
||
ls->prevtks[1].token = TK_EOS; /* no prev token */
|
||
luaZ_resizebuffer(ls->L, ls->buff, LUA_MINBUFFER); /* initialize buffer */
|
||
next(ls); /* read first char */
|
||
}
|
||
|
||
|
||
|
||
/*
|
||
** =======================================================
|
||
** LEXICAL ANALYZER
|
||
** =======================================================
|
||
*/
|
||
|
||
|
||
|
||
static int check_next (LexState *ls, const char *set) {
|
||
if (!strchr(set, ls->current))
|
||
return 0;
|
||
save_and_next(ls);
|
||
return 1;
|
||
}
|
||
|
||
|
||
static void buffreplace (LexState *ls, char from, char to) {
|
||
size_t n = luaZ_bufflen(ls->buff);
|
||
char *p = luaZ_buffer(ls->buff);
|
||
while (n--)
|
||
if (p[n] == from) p[n] = to;
|
||
}
|
||
|
||
|
||
static void trydecpoint (LexState *ls, SemInfo *seminfo) {
|
||
/* format error: try to update decimal point separator */
|
||
struct lconv *cv = localeconv();
|
||
char old = ls->decpoint;
|
||
ls->decpoint = (cv ? cv->decimal_point[0] : '.');
|
||
buffreplace(ls, old, ls->decpoint); /* try updated decimal separator */
|
||
if (!luaO_str2d(luaZ_buffer(ls->buff), &seminfo->r)) {
|
||
/* format error with correct decimal point: no more options */
|
||
buffreplace(ls, ls->decpoint, '.'); /* undo change (for error message) */
|
||
luaX_lexerror(ls, "malformed number", TK_NUMBER);
|
||
}
|
||
}
|
||
|
||
|
||
/* LUA_NUMBER */
|
||
static void read_numeral (LexState *ls, SemInfo *seminfo) {
|
||
lua_assert(isdigit(ls->current));
|
||
do {
|
||
save_and_next(ls);
|
||
} while (isdigit(ls->current) || ls->current == '.');
|
||
if (check_next(ls, "Ee")) /* `E'? */
|
||
check_next(ls, "+-"); /* optional exponent sign */
|
||
while (isalnum(ls->current) || ls->current == '_')
|
||
save_and_next(ls);
|
||
save(ls, '\0');
|
||
buffreplace(ls, '.', ls->decpoint); /* follow locale for decimal point */
|
||
if (!luaO_str2d(luaZ_buffer(ls->buff), &seminfo->r)) /* format error? */
|
||
trydecpoint(ls, seminfo); /* try to update decimal point separator */
|
||
}
|
||
|
||
|
||
static int skip_sep (LexState *ls) {
|
||
int count = 0;
|
||
int s = ls->current;
|
||
lua_assert(s == '[' || s == ']');
|
||
save_and_next(ls);
|
||
while (ls->current == '=') {
|
||
save_and_next(ls);
|
||
count++;
|
||
}
|
||
return (ls->current == s) ? count : (-count) - 1;
|
||
}
|
||
|
||
|
||
static void read_long_string (LexState *ls, SemInfo *seminfo, int sep) {
|
||
int cont = 0;
|
||
(void)(cont); /* avoid warnings when `cont' is not used */
|
||
save_and_next(ls); /* skip 2nd `[' */
|
||
if (currIsNewline(ls)) /* string starts with a newline? */
|
||
inclinenumber(ls); /* skip it */
|
||
for (;;) {
|
||
switch (ls->current) {
|
||
case EOZ:
|
||
luaX_lexerror(ls, (seminfo) ? "unfinished long string" :
|
||
"unfinished long comment", TK_EOS);
|
||
break; /* to avoid warnings */
|
||
#if defined(LUA_COMPAT_LSTR)
|
||
case '[': {
|
||
if (skip_sep(ls) == sep) {
|
||
save_and_next(ls); /* skip 2nd `[' */
|
||
cont++;
|
||
#if LUA_COMPAT_LSTR == 1
|
||
if (sep == 0)
|
||
luaX_lexerror(ls, "nesting of [[...]] is deprecated", '[');
|
||
#endif
|
||
}
|
||
break;
|
||
}
|
||
#endif
|
||
case ']': {
|
||
if (skip_sep(ls) == sep) {
|
||
save_and_next(ls); /* skip 2nd `]' */
|
||
#if defined(LUA_COMPAT_LSTR) && LUA_COMPAT_LSTR == 2
|
||
cont--;
|
||
if (sep == 0 && cont >= 0) break;
|
||
#endif
|
||
goto endloop;
|
||
}
|
||
break;
|
||
}
|
||
case '\n':
|
||
case '\r': {
|
||
save(ls, '\n');
|
||
inclinenumber(ls);
|
||
if (!seminfo) luaZ_resetbuffer(ls->buff); /* avoid wasting space */
|
||
break;
|
||
}
|
||
default: {
|
||
if (seminfo) save_and_next(ls);
|
||
else next(ls);
|
||
}
|
||
}
|
||
} endloop:
|
||
if (seminfo)
|
||
seminfo->ts = luaX_newstring(ls, luaZ_buffer(ls->buff) + (2 + sep),
|
||
luaZ_bufflen(ls->buff) - 2*(2 + sep));
|
||
}
|
||
|
||
#define isgb2312cnschr(c) (((unsigned char)(c)) >= 0x7F)
|
||
|
||
static void read_string (LexState *ls, int del, SemInfo *seminfo) {
|
||
save_and_next(ls);
|
||
while (ls->current != del) {
|
||
switch (ls->current) {
|
||
case EOZ:
|
||
luaX_lexerror(ls, "unfinished string", TK_EOS);
|
||
continue; /* to avoid warnings */
|
||
case '\n':
|
||
case '\r':
|
||
luaX_lexerror(ls, "unfinished string", TK_STRING);
|
||
continue; /* to avoid warnings */
|
||
case '\\': {
|
||
int c;
|
||
next(ls); /* do not save the `\' */
|
||
switch (ls->current) {
|
||
case 'a': c = '\a'; break;
|
||
case 'b': c = '\b'; break;
|
||
case 'f': c = '\f'; break;
|
||
case 'n': c = '\n'; break;
|
||
case 'r': c = '\r'; break;
|
||
case 't': c = '\t'; break;
|
||
case 'v': c = '\v'; break;
|
||
case '\n': /* go through */
|
||
case '\r': save(ls, '\n'); inclinenumber(ls); continue;
|
||
case EOZ: continue; /* will raise an error next loop */
|
||
default: {
|
||
if (!isdigit(ls->current))
|
||
save_and_next(ls); /* handles \\, \", \', and \? */
|
||
else { /* \xxx */
|
||
int i = 0;
|
||
c = 0;
|
||
do {
|
||
c = 10*c + (ls->current-'0');
|
||
next(ls);
|
||
} while (++i<3 && isdigit(ls->current));
|
||
if (c > UCHAR_MAX)
|
||
luaX_lexerror(ls, "escape sequence too large", TK_STRING);
|
||
save(ls, c);
|
||
}
|
||
continue;
|
||
}
|
||
}
|
||
save(ls, c);
|
||
next(ls);
|
||
continue;
|
||
}
|
||
default:{
|
||
#ifdef _CP_FOR_GBK_
|
||
/* if first char is multibyte lead char, read two char */
|
||
if (isgb2312cnschr(ls->current))
|
||
save_and_next(ls);
|
||
#endif
|
||
save_and_next(ls);
|
||
}
|
||
}
|
||
}
|
||
save_and_next(ls); /* skip delimiter */
|
||
seminfo->ts = luaX_newstring(ls, luaZ_buffer(ls->buff) + 1,
|
||
luaZ_bufflen(ls->buff) - 2);
|
||
}
|
||
|
||
static int llex (LexState *ls, SemInfo *seminfo) {
|
||
luaZ_resetbuffer(ls->buff);
|
||
for (;;) {
|
||
switch (ls->current) {
|
||
case '\n':
|
||
case '\r': {
|
||
inclinenumber(ls);
|
||
continue;
|
||
}
|
||
case '-': {
|
||
next(ls);
|
||
if (ls->current != '-') return '-';
|
||
/* else is a comment */
|
||
next(ls);
|
||
if (ls->current == '[') {
|
||
int sep = skip_sep(ls);
|
||
luaZ_resetbuffer(ls->buff); /* `skip_sep' may dirty the buffer */
|
||
if (sep >= 0) {
|
||
read_long_string(ls, NULL, sep); /* long comment */
|
||
luaZ_resetbuffer(ls->buff);
|
||
continue;
|
||
}
|
||
}
|
||
/* else short comment */
|
||
while (!currIsNewline(ls) && ls->current != EOZ)
|
||
next(ls);
|
||
continue;
|
||
}
|
||
case '[': {
|
||
int sep = skip_sep(ls);
|
||
if (sep >= 0) {
|
||
read_long_string(ls, seminfo, sep);
|
||
return TK_STRING;
|
||
}
|
||
else if (sep == -1) return '[';
|
||
else luaX_lexerror(ls, "invalid long string delimiter", TK_STRING);
|
||
}
|
||
case '=': {
|
||
next(ls);
|
||
if (ls->current != '=') return '=';
|
||
else { next(ls); return TK_EQ; }
|
||
}
|
||
case '<': {
|
||
next(ls);
|
||
if (ls->current != '=') return '<';
|
||
else { next(ls); return TK_LE; }
|
||
}
|
||
case '>': {
|
||
next(ls);
|
||
if (ls->current != '=') return '>';
|
||
else { next(ls); return TK_GE; }
|
||
}
|
||
case '~': {
|
||
next(ls);
|
||
if (ls->current != '=') return '~';
|
||
else { next(ls); return TK_NE; }
|
||
}
|
||
case '"':
|
||
case '\'': {
|
||
read_string(ls, ls->current, seminfo);
|
||
return TK_STRING;
|
||
}
|
||
case '.': {
|
||
save_and_next(ls);
|
||
if (check_next(ls, ".")) {
|
||
if (check_next(ls, "."))
|
||
return TK_DOTS; /* ... */
|
||
else return TK_CONCAT; /* .. */
|
||
}
|
||
else if (!isdigit(ls->current)) return '.';
|
||
else {
|
||
read_numeral(ls, seminfo);
|
||
return TK_NUMBER;
|
||
}
|
||
}
|
||
case EOZ: {
|
||
return TK_EOS;
|
||
}
|
||
default: {
|
||
if (isspace(ls->current)) {
|
||
lua_assert(!currIsNewline(ls));
|
||
next(ls);
|
||
continue;
|
||
}
|
||
else if (isdigit(ls->current)) {
|
||
read_numeral(ls, seminfo);
|
||
return TK_NUMBER;
|
||
}
|
||
/*
|
||
isgb2312cnschr mecro use for:
|
||
chinese identifier support
|
||
<09><><EFBFBD>ı<EFBFBD>ʶ<EFBFBD><CAB6>֧<EFBFBD><D6A7>, miros 2009-05-26
|
||
*/
|
||
else if (isalpha(ls->current) || ls->current == '_' || isgb2312cnschr(ls->current)) {
|
||
/* identifier or reserved word */
|
||
TString *ts;
|
||
do {
|
||
#ifdef _CP_FOR_GBK_
|
||
/* if first char is multibyte lead char, read two char */
|
||
if (isgb2312cnschr(ls->current))
|
||
save_and_next(ls);
|
||
#endif
|
||
save_and_next(ls);
|
||
} while (isalnum(ls->current) || ls->current == '_' || isgb2312cnschr(ls->current));
|
||
ts = luaX_newstring(ls, luaZ_buffer(ls->buff),
|
||
luaZ_bufflen(ls->buff));
|
||
if (ts->tsv.reserved > 0) /* reserved word? */
|
||
return ts->tsv.reserved - 1 + FIRST_RESERVED;
|
||
else {
|
||
seminfo->ts = ts;
|
||
return TK_NAME;
|
||
}
|
||
}
|
||
else {
|
||
int c = ls->current;
|
||
next(ls);
|
||
return c; /* single-char tokens (+ - / ...) */
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
|
||
TString* luaX_mergestring(LexState *ls, TString* a, TString* b)
|
||
{
|
||
stringtable *tb;
|
||
char *newstr;
|
||
size_t size1, size2;
|
||
TString *ts;
|
||
|
||
tb = &G(ls->L)->strt;
|
||
|
||
size1 = a->tsv.len;
|
||
size2 = b->tsv.len;
|
||
|
||
//alloc temp buffer
|
||
newstr = luaM_malloc( ls->L, size1 + size2 + 1 );
|
||
|
||
/* concat the strings */
|
||
strncpy( newstr, getstr(a), size1 );
|
||
strncpy( &newstr[size1], getstr(b), size2 );
|
||
newstr[size1 + size2] = 0; /* set string terminate char */
|
||
|
||
/* alloc new string */
|
||
ts = luaX_newstring( ls, newstr, size1 + size2 );
|
||
|
||
//free temp buffer
|
||
luaM_free( ls->L, newstr );
|
||
|
||
return ts;
|
||
}
|
||
|
||
void luaX_next (LexState *ls) {
|
||
//miros 2009-05-26
|
||
//<2F><><EFBFBD>ӳ<EFBFBD><D3B3><EFBFBD><EFBFBD>ַ<EFBFBD><D6B7><EFBFBD><EFBFBD>ϲ<EFBFBD><CFB2><EFBFBD><EFBFBD><EFBFBD>
|
||
// merge conatant string concat operation
|
||
// "abc" .. "def" --> "abcdef"
|
||
|
||
//ls->lastline = ls->linenumber;
|
||
//if (ls->lookahead.token != TK_EOS) { /* is there a look-ahead token? */
|
||
// ls->t = ls->lookahead; /* use this one */
|
||
// ls->lookahead.token = TK_EOS; /* and discharge it */
|
||
//}
|
||
//else
|
||
// ls->t.token = llex(ls, &ls->t.seminfo); /* read next token */
|
||
|
||
ls->lastline = ls->linenumber;
|
||
if (ls->lookahead.token != TK_EOS) /* is there a look-ahead token? */
|
||
{
|
||
ls->t = ls->lookahead; /* use this one */
|
||
ls->lookahead.token = TK_EOS; /* and discharge it */
|
||
}
|
||
else if ( ls->prevtks[0].token != TK_EOS )
|
||
{
|
||
ls->t = ls->prevtks[0]; /* use prev one */
|
||
ls->prevtks[0] = ls->prevtks[1];
|
||
ls->prevtks[1].token = TK_EOS;
|
||
}
|
||
else
|
||
{
|
||
ls->t.token = llex(ls, &ls->t.seminfo); /* read next token */
|
||
while ( ls->t.token == TK_STRING )
|
||
{
|
||
/* read token after string */
|
||
ls->prevtks[0].token = llex(ls, &ls->prevtks[0].seminfo);
|
||
/* check the token after string is concat operator */
|
||
if ( ls->prevtks[0].token != TK_CONCAT )
|
||
break;
|
||
|
||
/* read token after concat operator */
|
||
ls->prevtks[1].token = llex(ls, &ls->prevtks[1].seminfo);
|
||
/* if the token after concat operator is string */
|
||
if ( ls->prevtks[1].token != TK_STRING )
|
||
break;
|
||
|
||
/* merge to a new string and free old strings */
|
||
ls->t.seminfo.ts = luaX_mergestring( ls, ls->t.seminfo.ts, ls->prevtks[1].seminfo.ts );
|
||
|
||
ls->prevtks[0].token = TK_EOS; /* set prev tokens to EOS */
|
||
ls->prevtks[1].token = TK_EOS; /* set prev tokens to EOS */
|
||
}
|
||
}
|
||
}
|
||
|
||
|
||
void luaX_lookahead (LexState *ls) {
|
||
lua_assert(ls->lookahead.token == TK_EOS);
|
||
ls->lookahead.token = llex(ls, &ls->lookahead.seminfo);
|
||
}
|
||
|