int get_token()
{
int tok;
char *temp;
(token_type) = 0;
tok = 0;
temp = (token);
if (*(prog) == '\0')
{
*(token) = 0;
tok = FINISHED;
return ((token_type) = DELIMITER);
}
while (iswhite(*(prog))) ++(prog);
if (isdelim(*(prog)))
{
char t=*temp = *(prog);
(prog)++;
temp++;
if ((t == '>' || t == '<' || t == '!') && (*prog) && (*prog == '='))
{
*temp = *(prog);
(prog)++;
temp++;
}
*temp = 0;
return ((token_type) = DELIMITER);
}
if (isdigit(*(prog)))
{
while (!isdelim(*(prog)))
*temp++=*(prog)++;
*temp = '\0';
return ((token_type) = NUMBER);
}
if (isalpha2(*(prog)))
{
while (!isdelim(*(prog)))
*temp++=*(prog)++;
(token_type) = VARIABLE;
}
*temp = '\0';
if ((token_type) == VARIABLE)
{
tok = look_up((token));
if (tok)
(token_type) = FUNCTION;
}
return (token_type);
}
static void
outwinname(Biobuf *b, Hist *h, char *ds, char *p)
{
if(isdelim(p[0])) {
// full rooted name
zfile(b, ds, 3); // leading "c:/"
outzfile(b, p+1);
} else {
// relative name
if(h->offset == 0 && pathname && pathname[1] == ':') {
if(tolowerrune(ds[0]) == tolowerrune(pathname[0])) {
// using current drive
zfile(b, pathname, 3); // leading "c:/"
outzfile(b, pathname+3);
} else {
// using drive other then current,
// we don't have any simple way to
// determine current working directory
// there, therefore will output name as is
zfile(b, ds, 2); // leading "c:"
}
}
outzfile(b, p);
}
}
// ([0-9]|(~!@#$%^&*-+=\/)|[a-z])*[a-z]+([0-9]|(~!@#$%^&*-+=\/)|[a-z])
int read_symbol(FILE *in, struct value *val)
{
char c;
const char valid_chars[] = "~!@#$%^&*-+=/\\";
unsigned int i, non_numerical_seen = 0;
for (i = 0; i < MAX_SYMBOL_SIZE; i++) {
c = fgetc(in);
if (isdelim(c)) {
break;
} else if (!(isalnum(c) || strchr(valid_chars, c))) {
val->symbol[i+1] = 0;
ungets(val->symbol, in);
return READ_INVALID_CHAR;
} else if (!isdigit(c) && !non_numerical_seen) {
non_numerical_seen = 1;
}
val->symbol[i] = c;
}
val->symbol[i] = 0;
if (!val->symbol[0] || !non_numerical_seen) {
ungets(val->symbol, in);
return READ_FAIL;
} else {
val->type = SYMBOL;
return READ_SUCCESS;
}
}
static void tokeniser_advance(Tokeniser* t)
{
ASSERT(!tokeniser_eof(t), "next() on empty tokeniser");
SET(t->tokenIndex, nil_make());
skipSpace(t);
if (*t->cursor == 0) {
t->eof = 1;
return;
}
const char* punctChars = "()'";
for (int i = 0; punctChars[i] != 0; i++) {
if (*t->cursor == punctChars[i]) {
t->cursor++;
SET(t->tokenIndex, makeToken(&punctChars[i], 1));
return;
}
}
if (*t->cursor == '"') {
// Find out how long the escaped string is, and check it was terminated
// properly.
int length = 0;
t->cursor++; // advance past the initial "
const char* end = stringEscape(t->cursor, countChars, &length);
if (*end != '"') {
THROW("Expected \", got EOF");
}
// Now allocate a string and copy it in.
Pointer ptr = string_alloc(length);
char* dest = (char*) string_get(ptr);
stringEscape(t->cursor, copyChars, &dest);
*dest = 0;
// Advance the cursor past the string.
t->cursor = end + 1;
SET(t->tokenIndex, ptr);
}
else {
// Scan out a token
const char* start = t->cursor;
while (1) {
char c = *t->cursor;
if ((c == 0) || isspace(c) || isdelim(c)) {
int length = t->cursor - start;
SET(t->tokenIndex, makeToken(start, length));
break;
}
// Advance the cursor now, not earlier.
t->cursor++;
}
}
}
static void
outhist(Biobuf *b)
{
Hist *h;
char *p, ds[] = {'c', ':', '/', 0};
for(h = hist; h != H; h = h->link) {
p = h->name;
if(p) {
if(windows) {
// if windows variable is set, then, we know already,
// pathname is started with windows drive specifier
// and all '\' were replaced with '/' (see lex.c)
if(isdelim(p[0]) && isdelim(p[1])) {
// file name has network name in it,
// like \\server\share\dir\file.go
zfile(b, "//", 2); // leading "//"
outzfile(b, p+2);
} else if(p[1] == ':') {
// file name has drive letter in it
ds[0] = p[0];
outwinname(b, h, ds, p+2);
} else {
// no drive letter in file name
outwinname(b, h, pathname, p);
}
} else {
if(p[0] == '/') {
// full rooted name, like /home/rsc/dir/file.go
zfile(b, "/", 1); // leading "/"
outzfile(b, p+1);
} else {
// relative name, like dir/file.go
if(h->offset == 0 && pathname && pathname[0] == '/') {
zfile(b, "/", 1); // leading "/"
outzfile(b, pathname+1);
}
outzfile(b, p);
}
}
}
zhist(b, h->line, h->offset);
}
}
/*
* Find the next delimiter/non-delimiter within p
* Honor quotes and leading option characters
*/
static char *find(char *p, int delim)
{ int ch, quote;
int isopt;
assert(p);
#define isdelim(ch) (isopt? isoptdelim(ch): isargdelim(ch))
if((isopt = isoption(p)) != 0 && delim) {
/* Assume the following example:
p == "arg/opt"
first find("arg/opt", 1) == find next delimiter
returns pointer to "/opt"
Now the process would call skip delimiters to reach the
next argument --> find("/opt", 0) == find next non-delimiter
will return "/opt", because '/' is delimiter only when
searching for delimiters.
Now the process would call skip non-delimiters to reach the
end of the arg --> find("/opt", 1) == find next delimiter
This time the leading optch's are part of the argument.
===> This is performed in this branch.
If the string would be "/opt1/opt2", the call of
find("/opt1/opt2", 1) == find next delimiter must stop
at the second '/'.
*/
while((ch = *++p) != 0 && isoptch(ch));
}
quote = 0;
while((ch = *p++) != '\0' && (quote
|| (delim && !(isdelim(ch) || isoptch(ch)))
|| (!delim && isdelim(ch))))
if(quote == ch)
quote = 0;
else if(strchr(QUOTE_STR, ch))
quote = ch;
return p - 1;
#undef isdelim
}
void get_token(void)
{
register char *temp;
tok_type=0;
temp=token;
*temp='\0';
if(!*p) return;
while(isspace(*p)) ++p;
if(isalpha(*p)) {
while(!isdelim(*p)) *temp++=*p++;
tok_type=STRING;
} else if(isdigit(*p) || *p=='-') {
while(!isdelim(*p)) *temp++=*p++;
tok_type= NUMBER;
}
*temp='\0';
}
static UINT32 suck_number(const UINT8 **psrc)
{
const UINT8 *src = *psrc;
UINT32 value = 0;
/* skip delimiters */
while (isdelim(*src))
src++;
/* loop over and accumulate digits */
while (isdigit(*src))
{
value = value * 10 + *src - '0';
src++;
}
/* return a pointer to the string afterwards */
*psrc = src;
return value;
}
static int Parse()
{
char* t;
type = 0;
t = token;
while( iswhite( *expression ) )
expression++;
if( isdelim( *expression ) )
{
type = DEL;
*t++ = *expression++;
}
else if( isnumer( *expression ) )
{
type = NUM;
while( isnumer( *expression ) )
*t++ = *expression++;
}
else if( isalpha( *expression ) )
{
type = VAR;
while( isalpha( *expression ) )
*t++ = *expression++;
token[VARLEN] = 0;
}
else if( *expression )
{
*t++ = *expression++;
*t = 0;
return E_SYNTAX ;
}
*t = 0;
while( iswhite( *expression ) )
expression++;
return E_OK;
}
/* (+|-|/0)[0-9]+ where /0 is a null token */
int read_fixnum(FILE *in, struct value *val)
{
char c;
char buf[BUF_LEN] = {0};
unsigned int i = 0, neg = 0;
c = fgetc(in);
if ('-' == c) {
neg = 1;
} else if (isdigit(c)) {
buf[i++] = c;
} else if ((EOF == c) || (c != '+')) {
ungetc(c, in);
return READ_FAIL;
}
while ((EOF != (c = fgetc(in))) && (i < BUF_LEN)) {
if (isdigit(c)) {
buf[i] = c;
} else if (isdelim(c)) {
ungetc(c, in);
break;
} else {
ungets(buf, in);
return READ_INVALID_CHAR;
}
i++;
}
if (buf[0] != 0) {
val->type = FIXNUM;
val->fixnum = atoi(buf) * (neg ? -1 : 1);
return READ_SUCCESS;
} else {
return READ_FAIL;
}
}
static void Parse(void)
{
char* t;
type = 0;
t = (char*)token;
while( iswhite( *expression ) )
expression++;
if( isdelim( *expression ) )
{
type = DEL;
*t++ = *expression++;
}
else if( isnumer( *expression ) )
{
type = NUM;
while( isnumer( *expression ) )
*t++ = *expression++;
}
else if( isalpha( *expression ) )
{
type = VAR;
while( isalpha( *expression ) )
*t++ = *expression++;
token[VARLEN] = 0;
}
else if( *expression )
{
*t++ = *expression++;
*t = 0;
ERR( E_SYNTAX );
}
*t = 0;
while( iswhite( *expression ) )
expression++;
}
int jed_parse(const void *data, size_t length, jed_data *result)
{
const UINT8 *cursrc = (const UINT8 *)data;
const UINT8 *srcend = cursrc + length;
const UINT8 *scan;
jed_parse_info pinfo;
UINT16 checksum;
int i;
/* initialize the output and the intermediate info struct */
memset(result, 0, sizeof(*result));
memset(&pinfo, 0, sizeof(pinfo));
/* first scan for the STX character; ignore anything prior */
while (cursrc < srcend && *cursrc != 0x02)
cursrc++;
if (cursrc >= srcend)
return JEDERR_INVALID_DATA;
/* then scan to see if we have an ETX */
scan = cursrc;
checksum = 0;
while (scan < srcend && *scan != 0x03)
checksum += *scan++ & 0x7f;
if (scan >= srcend)
return JEDERR_INVALID_DATA;
/* see if there is a transmission checksum at the end */
checksum += *scan;
if (scan + 4 < srcend && ishex(scan[1]) && ishex(scan[2]) && ishex(scan[3]) && ishex(scan[4]))
{
UINT16 dessum = (hexval(scan[1]) << 12) | (hexval(scan[2]) << 8) | (hexval(scan[3]) << 4) | hexval(scan[4] << 0);
if (dessum != 0 && dessum != checksum)
return JEDERR_BAD_XMIT_SUM;
}
/* the ETX becomes the real srcend */
srcend = scan;
/* blast through the comment field */
cursrc++;
while (cursrc < srcend && *cursrc != '*')
cursrc++;
/* now loop over fields and decide which ones go in the file output */
cursrc++;
while (cursrc < srcend)
{
/* skip over delimiters */
while (cursrc < srcend && isdelim(*cursrc))
cursrc++;
if (cursrc >= srcend)
break;
/* end of field is an asterisk -- find it */
scan = cursrc;
while (scan < srcend && *scan != '*')
scan++;
if (scan >= srcend)
return JEDERR_INVALID_DATA;
/* process the field */
process_field(result, cursrc, scan, &pinfo);
/* advance past it */
cursrc = scan + 1;
}
/* if we got an explicit fuse count, override our computed count */
if (pinfo.explicit_numfuses != 0)
result->numfuses = pinfo.explicit_numfuses;
/* clear out leftover bits */
if (result->numfuses % 8 != 0)
result->fusemap[result->numfuses / 8] &= (1 << (result->numfuses % 8)) - 1;
memset(&result->fusemap[(result->numfuses + 7) / 8], 0, sizeof(result->fusemap) - (result->numfuses + 7) / 8);
/* validate the checksum */
checksum = 0;
for (i = 0; i < (result->numfuses + 7) / 8; i++)
checksum += result->fusemap[i];
if (pinfo.checksum != 0 && checksum != pinfo.checksum)
return JEDERR_BAD_FUSE_SUM;
return JEDERR_NONE;
}
/* Get a bas_token. */
int get_token(){
char *temp;
bas_token_type=0; bas_tok=0;
temp=bas_token;
// printf( "gettoken: <%c>\n", *prog );
if(*prog=='\0') { /* end of file */
*bas_token=0;
bas_tok = FINISHED;
return(bas_token_type=DELIMITER);
}
while(iswhite(*prog)) ++prog; /* skip over white space */
/*
if(*prog=='\r') { /
++prog; ++prog;
bas_tok = EOL; *bas_token='\r';
bas_token[1]='\n'; bas_token[2]=0;
return (bas_token_type = DELIMITER);
}
*/
if(*prog=='\n') { // lf
++prog;
//currentline++; // just for debug
bas_tok = EOL; *bas_token='\n';
bas_token[1]=0;
// printf("...EOL found ...%s" , "");
return (bas_token_type = DELIMITER);
}
if(*prog=='#') { /* lf */
++prog;
bas_tok = COMMENT; *bas_token='#';
bas_token[1]=0;
return (bas_token_type = DELIMITER);
}
if(strchr("!+-*^/%=;(),><&|", *prog)){ /* delimiter */
*temp=*prog;
//if there is NOT double delimiter
if(strchr("+-*^/%;(),", *prog)){ /* delimiter */
// if (strchr("(", *prog)){ printf("delim found %c \n", *prog); }
// if (strchr(")", *prog)){ printf("delim found %c \n", *prog); }
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}// was single delimiter
/* DOUBLE DELIMITERS WILL BE SINGLFIED.......HERE
*
*/
// printf("case of dd may come <%c> <%c>\n", *prog, prog[1] );
if((strchr("=", *prog))&&(strchr("=",prog[1]) )){ /* double delimiter == is ~ */
bas_token[0]='~'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
if((strchr("!", *prog))&&(strchr("=",prog[1]) )){ /* double delimiter != is ! */
bas_token[0]='!'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
if((strchr("&", *prog))&&(strchr("&",prog[1]) )){ /* double delimiter && is @ */
bas_token[0]='@'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
if((strchr("|", *prog))&&(strchr("|",prog[1]) )){ /* double delimiter || is $*/
bas_token[0]='$'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
if((strchr(">", *prog))&&(strchr("=",prog[1]) )){ /* double delimiter >= is :*/
bas_token[0]=':'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
if((strchr("<", *prog))&&(strchr("=",prog[1]) )){ /* double delimiter <= is _ */
bas_token[0]='_'; bas_token[1]='\0';
prog++; /* advance to next position */
temp++;
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}// DELIMITERS - DOUBLE DELIMITERS-------------------END-----DOUBLE
/* 20100419 - now | and & are unabiguous
*
*/
//if there is NOT double delimiter
if(strchr("|&", *prog)){ /* delimiter */
// if (strchr("(", *prog)){ printf("delim found %c \n", *prog); }
// if (strchr(")", *prog)){ printf("delim found %c \n", *prog); }
prog++; /* advance to next position */
temp++;
*temp=0;
return (bas_token_type=DELIMITER);
}// was single delimiter
if(*prog=='"') { /* quoted string */
prog++;
while(*prog!='"'&& *prog!='\n') *temp++=*prog++;
if(*prog=='\n') serror(1);
prog++;*temp=0;
return(bas_token_type=QUOTE);
}
if(isdigit(*prog)) { /* number */
while(!isdelim(*prog)) *temp++=*prog++;
*temp = '\0';
// printf("temp=%s\n", bas_token);
return(bas_token_type = NUMBER);
}
if(isalpha(*prog)) { /* var or command */
while(!isdelim(*prog)) *temp++=*prog++;
bas_token_type=STRING;
}
*temp = '\0';
/* see if a string is a command or a variable */
if(bas_token_type==STRING) {
bas_tok=look_up(bas_token); /* convert to internal rep */
if(!bas_tok) bas_token_type = VARIABLE;
else bas_token_type = COMMAND; /* is a command */
}
return bas_token_type;
}//------------------------get_token
static void
outhist(Biobuf *b)
{
Hist *h;
char *p, ds[] = {'c', ':', '/', 0};
char *tofree;
int n;
static int first = 1;
static char *goroot, *goroot_final;
if(first) {
// Decide whether we need to rewrite paths from $GOROOT to $GOROOT_FINAL.
first = 0;
goroot = getenv("GOROOT");
goroot_final = getenv("GOROOT_FINAL");
if(goroot == nil)
goroot = "";
if(goroot_final == nil)
goroot_final = goroot;
if(strcmp(goroot, goroot_final) == 0) {
goroot = nil;
goroot_final = nil;
}
}
tofree = nil;
for(h = hist; h != H; h = h->link) {
p = h->name;
if(p) {
if(goroot != nil) {
n = strlen(goroot);
if(strncmp(p, goroot, strlen(goroot)) == 0 && p[n] == '/') {
tofree = smprint("%s%s", goroot_final, p+n);
p = tofree;
}
}
if(windows) {
// if windows variable is set, then, we know already,
// pathname is started with windows drive specifier
// and all '\' were replaced with '/' (see lex.c)
if(isdelim(p[0]) && isdelim(p[1])) {
// file name has network name in it,
// like \\server\share\dir\file.go
zfile(b, "//", 2); // leading "//"
outzfile(b, p+2);
} else if(p[1] == ':') {
// file name has drive letter in it
ds[0] = p[0];
outwinname(b, h, ds, p+2);
} else {
// no drive letter in file name
outwinname(b, h, pathname, p);
}
} else {
if(p[0] == '/') {
// full rooted name, like /home/rsc/dir/file.go
zfile(b, "/", 1); // leading "/"
outzfile(b, p+1);
} else {
// relative name, like dir/file.go
if(h->offset >= 0 && pathname && pathname[0] == '/') {
zfile(b, "/", 1); // leading "/"
outzfile(b, pathname+1);
}
outzfile(b, p);
}
}
}
zhist(b, h->line, h->offset);
if(tofree) {
free(tofree);
tofree = nil;
}
}
}
Token Tokenizer::getNextToken()
{
Token result;
if (position == LEN)
{
result.type = Token::TOKEN_TYPE::FINISHED;
result.stringRepresentation = "EOL";
return result;
}
do
{
//skip over whitespace characters
while (position < LEN && std::isspace(CUR))
position++;
//skip comments
if (CUR == '/')
{
if (NEXT == '*')
{
position+=2;
do
{
while (CUR != '*')
position++;
position++;
} while (CUR != '/');
position++;
}
else if (NEXT == '/')
{
position += 2;
while (CUR != '\n' && CUR != '\r')//new line
position++;
}
}
//skip over whitespace characters after comments
while (position < LEN && std::isspace(CUR))
position++;
} while (CUR == '/' && (NEXT == '/' || NEXT == '*'));
//end of file
if (position == LEN )
{
result.type = Token::TOKEN_TYPE::FINISHED;
result.stringRepresentation = "";
return result;
}
//operators
std::vector<string> operators{ "+", "-", "*", "/", "%", "++", "--", "==",
"!=", ">", "<", ">=", "<=", "&&", "||", "!",
"&", "|", "^", "~", "<<", ">>", "=", "+=",
"-=", "*=", "/=", "%=", ">>=", "<<=", "&=",
"^=", "|=", };//using initializer lists
int ind = 0;
string op = "";
//while there is a longer operator keep going
do
{
op += CUR;
position++;
} while ((std::find(operators.begin(), operators.end(), op) != operators.end()));
op.pop_back();//remove last character
position--;
if (op.length() > 0)
{
result.type = Token::TOKEN_TYPE::OPERATOR;
result.stringRepresentation = op;
return result;
}
//delimiters
if (std::strchr("(),;{}[].:", CUR))
{
result.type = Token::TOKEN_TYPE::DELIMITER;
result.stringRepresentation = "";
result.stringRepresentation += CUR;
position++;
return result;
}
string ligit_escape = "0abfnrtv\\\"?";
//string literal
if (CUR == '"')
{
string s = "";
position++;
bool escaped = false;
while (CUR != '"' || escaped)
{
if (CUR == '\n' || CUR == '\r')
{
result.type = Token::TOKEN_TYPE::ERROR;
result.stringRepresentation = generateErrorMessage("New line in string literal");
return result;
}
if (escaped && std::strchr(ligit_escape.c_str(), CUR)==nullptr)
{
result.type = Token::TOKEN_TYPE::ERROR;
result.stringRepresentation = generateErrorMessage("Illegal escape character");
return result;
}
s += CUR;
if (CUR == '\\')
escaped = true;
else
escaped = false;
position++;
}
position++;
result.type = Token::TOKEN_TYPE::STRING_LITERAL;
result.stringRepresentation = s;
return result;
}
//char literal
if (CUR == '\'')
{
position++;
if (CUR == '\\')
{
position++;
}
if (NEXT == '\'')
{
if (CUR == '\n' || CUR == '\r')
{
result.type = Token::TOKEN_TYPE::ERROR;
result.stringRepresentation = generateErrorMessage("New line in character literal");
return result;
}
else
{
result.type = Token::TOKEN_TYPE::CHAR_LITERAL;
result.stringRepresentation = "";
result.stringRepresentation += CUR;
return result;
position += 2;
}
}
else
{
result.type = Token::TOKEN_TYPE::ERROR;
result.stringRepresentation = generateErrorMessage("Character literal too long");
return result;
}
}
//number literal
if (std::isdigit(CUR))
{
string n;
n += CUR;
position++;
while (std::isdigit(CUR))
{
n += CUR;
position++;
}
result.type = Token::TOKEN_TYPE::NUMBER_LITERAL;
result.stringRepresentation = n;
return result;
}
//keywords and identifiers
string word = "";
if (std::isalpha(CUR) || CUR == '_')
{
while (!isdelim(CUR))
{
word += CUR;
position++;
}
}
std::vector<string> keywords{ "auto", "break", "case", "char", "const", "continue", "default",
"do", "double", "else", "enum", "extern", "float", "for", "goto",
"if", "int", "long", "register", "return", "short", "signed", "sizeof",
"static", "struct", "switch", "typedef", "union", "unsigned", "void",
"volatile", "while" };
if (word.length() > 0)
{
if ((std::find(keywords.begin(), keywords.end(), word) != keywords.end()))//its a keyword
{
result.type = Token::TOKEN_TYPE::KEYWORD;
result.stringRepresentation = word;
return result;
}
else
{
result.type = Token::TOKEN_TYPE::IDENTIFIER;
result.stringRepresentation = word;
return result;
}
}
result.type = Token::TOKEN_TYPE::ERROR;
result.stringRepresentation = generateErrorMessage("Unexpected character");
return result;
}
// Get a token.
tok_types get_token()
{
char *temp;
token_type = UNDEFTT; tok = UNDEFTOK;
temp = token;
*temp = '\0';
// Skip over white space.
while (isspace(*prog) && *prog) ++prog;
// Skip over newline.
while (*prog == '\r') {
++prog;
++prog;
// Again, skip over white space.
while (isspace(*prog) && *prog) ++prog;
}
// Check for end of program.
if (*prog == '\0') {
*token = '\0';
tok = END;
return (token_type = DELIMITER);
}
// Check for block delimiters.
if (strchr("{}", *prog)) {
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = BLOCK);
}
// Look for comments.
if (*prog == '/')
if (*(prog + 1) == '*') { // is a /* comment
prog += 2;
do { // find end of comment
while (*prog != '*') prog++;
prog++;
} while (*prog != '/');
prog++;
return (token_type = DELIMITER);
}
else if (*(prog + 1) == '/') { // is a // comment
prog += 2;
// Find end of comment.
while (*prog != '\r' && *prog != '\0') prog++;
if (*prog == '\r') prog += 2;
return (token_type = DELIMITER);
}
// Check for double-ops.
if (strchr("!<>=+-", *prog)) {
switch (*prog) {
case '=':
if (*(prog + 1) == '=') {
prog++; prog++;
*temp = EQ;
temp++; *temp = EQ; temp++;
*temp = '\0';
}
break;
case '!':
if (*(prog + 1) == '=') {
prog++; prog++;
*temp = NE;
temp++; *temp = NE; temp++;
*temp = '\0';
}
break;
case '<':
if (*(prog + 1) == '=') {
prog++; prog++;
*temp = LE; temp++; *temp = LE;
}
else if (*(prog + 1) == '<') {
prog++; prog++;
*temp = LS; temp++; *temp = LS;
}
else {
prog++;
*temp = LT;
}
temp++;
*temp = '\0';
break;
case '>':
if (*(prog + 1) == '=') {
prog++; prog++;
*temp = GE; temp++; *temp = GE;
}
else if (*(prog + 1) == '>') {
prog++; prog++;
*temp = RS; temp++; *temp = RS;
}
else {
prog++;
*temp = GT;
}
temp++;
*temp = '\0';
break;
case '+':
if (*(prog + 1) == '+') {
prog++; prog++;
*temp = INC; temp++; *temp = INC;
temp++;
*temp = '\0';
}
break;
case '-':
if (*(prog + 1) == '-') {
prog++; prog++;
*temp = DEC; temp++; *temp = DEC;
temp++;
*temp = '\0';
}
break;
}
if (*token) return(token_type = DELIMITER);
}
// Check for other delimiters.
if (strchr("+-*^/%=;:(),'", *prog)) {
*temp = *prog;
prog++;
temp++;
*temp = '\0';
return (token_type = DELIMITER);
}
// Read a quoted string.
if (*prog == '"') {
prog++;
while (*prog != '"' && *prog != '\r' && *prog) {
// Check for \n escape sequence.
if (*prog == '\\') {
if (*(prog + 1) == 'n') {
prog++;
*temp++ = '\n';
}
}
else if ((temp - token) < MAX_T_LEN)
*temp++ = *prog;
prog++;
}
if (*prog == '\r' || *prog == 0)
throw InterpExc(SYNTAX);
prog++; *temp = '\0';
return (token_type = STRING);
}
// Read an integer number.
if (isdigit(*prog)) {
while (!isdelim(*prog)) {
if ((temp - token) < MAX_ID_LEN)
*temp++ = *prog;
prog++;
}
*temp = '\0';
return (token_type = NUMBER);
}
// Read identifier or keyword.
if (isalpha(*prog)) {
while (!isdelim(*prog)) {
if ((temp - token) < MAX_ID_LEN)
*temp++ = *prog;
prog++;
}
token_type = TEMP;
}
*temp = '\0';
// Determine if token is a keyword or identifier.
if (token_type == TEMP) {
tok = look_up(token); // convert to internal form
if (tok) token_type = KEYWORD; // is a keyword
else token_type = IDENTIFIER;
}
// Check for unidentified character in file.
if (token_type == UNDEFTT)
throw InterpExc(SYNTAX);
return token_type;
}
static int
argcv_scan (struct argcv_info *ap)
{
int i = 0;
int len = ap->len;
const char *command = ap->command;
const char *delim = ap->delim;
const char *comment = ap->comment;
for (;;)
{
i = ap->save;
if (i >= len)
return i + 1;
/* Skip initial whitespace */
while (i < len && isws (command[i]))
i++;
ap->start = i;
if (!isdelim (command[i], delim))
{
while (i < len)
{
if (command[i] == '\\')
{
if (++i == len)
break;
i++;
continue;
}
if (command[i] == '\'' || command[i] == '"')
{
int j;
for (j = i + 1; j < len && command[j] != command[i]; j++)
if (command[j] == '\\')
j++;
if (j < len)
i = j + 1;
else
i++;
}
else if (isws (command[i]) || isdelim (command[i], delim))
break;
else
i++; /* skip the escaped character */
}
i--;
}
else if (!(ap->flags & DICO_ARGCV_RETURN_DELIMS))
{
while (i < len && isdelim (command[i], delim))
i++;
ap->save = i;
continue;
}
ap->end = i;
ap->save = ap->finish_pos = i + 1;
/* If we have a token, and it starts with a comment character, skip
to the newline and restart the token search. */
if (ap->save <= len)
{
if (strchr (comment, command[ap->start]) != NULL)
{
ap->finish_pos = ap->start;
i = ap->save;
while (i < len && command[i] != '\n')
i++;
ap->save = i;
continue;
}
}
break;
}
return ap->save;
}
int
parse(int *argc, char ***argv, char *str)
{
int ac;
char *val, *p, *q, *copy = NULL;
size_t i = 0;
char token, tmp, quote, *buf;
enum { STR, VAR, WHITE } state;
ac = *argc = 0;
quote = 0;
if (!str || (p = copy = backslash(str)) == NULL)
return 1;
/* Initialize vector and state */
clean();
state = STR;
buf = (char *)alloc(PARSE_BUFSIZE);
token = 0;
/* And awaaaaaaaaay we go! */
while (*p) {
switch (state) {
case STR:
if ((*p == '\\') && p[1]) {
p++;
PARSE_FAIL(i == (PARSE_BUFSIZE - 1));
buf[i++] = *p++;
} else if (isquote(*p)) {
quote = quote ? 0 : *p;
++p;
}
else if (isspace(*p) && !quote) {
state = WHITE;
if (i) {
buf[i] = '\0';
PARSE_FAIL(insert(&ac, buf));
i = 0;
}
++p;
} else if (*p == '$') {
token = isdelim(*(p + 1));
if (token)
p += 2;
else
++p;
state = VAR;
} else {
PARSE_FAIL(i == (PARSE_BUFSIZE - 1));
buf[i++] = *p++;
}
break;
case WHITE:
if (isspace(*p))
++p;
else
state = STR;
break;
case VAR:
if (token) {
PARSE_FAIL((q = strchr(p, token)) == NULL);
} else {
q = p;
while (*q && !isspace(*q))
++q;
}
tmp = *q;
*q = '\0';
if ((val = variable_lookup(p)) != NULL) {
size_t len = strlen(val);
strncpy(buf + i, val, PARSE_BUFSIZE - (i + 1));
i += min(len, PARSE_BUFSIZE - 1);
}
*q = tmp; /* restore value */
p = q + (token ? 1 : 0);
state = STR;
break;
}
}
/* If at end of token, add it */
if (i && state == STR) {
buf[i] = '\0';
PARSE_FAIL(insert(&ac, buf));
}
args[ac] = NULL;
*argc = ac;
*argv = (char **)alloc((sizeof(char *) * ac + 1));
bcopy(args, *argv, sizeof(char *) * ac + 1);
free(buf);
free(copy);
return 0;
}
int ps_parse_get_token (FILE *stream, int *type, char *buffer, int bufflen)
{
int i = 0;
char ch;
int unbalanced = 0, escape = 0; /* for STRING type */
int have_digit = 0, have_exp = 0; /* for INTEGER/REAL type */
if (type == NULL || buffer == NULL || bufflen < 1) {
fprintf(stderr, "no space allocated for input buffer");
return PS_PARSE_BUFF_ERROR;
}
/* skip whitespaces, comments */
while ((ch = fgetc(stream)) != EOF) {
if (ch == '%') {
skip_line (stream);
} else if (!isspace(ch)) {
break;
}
}
if (ch == EOF) {
*type = PS_UNKNOWN;
return PS_PARSE_END;
}
switch (ch) {
case '/':
*type = PS_NAME;
break;
case '(':
*type = PS_STRING;
break;
case '<': /* hex or a85 or dict */
ch = fgetc(stream);
if (ch == '<') {
*type = PS_BEGIN_DICT;
return PS_PARSE_OK;
} else if (ch == '~') {
*type = PS_STRING_A85;
} else if (isxdigit(ch)) {
*type = PS_STRING_AHX;
buffer[i++] = ch;
} else {
return PS_PARSE_INVALID;
}
break;
case '[':
*type = PS_BEGIN_ARRAY;
return PS_PARSE_OK;
break;
case ']':
*type = PS_END_ARRAY;
return PS_PARSE_OK;
break;
case '{':
*type = PS_BEGIN_PROC;
return PS_PARSE_OK;
break;
case '}':
*type = PS_END_PROC;
return PS_PARSE_OK;
break;
case '>':
if (fgetc(stream) == '>') {
*type = PS_END_DICT;
return PS_PARSE_OK;
} else {
if (verbose)
fprintf(stderr, "unexpected character `>'\n");
*type = PS_UNKNOWN;
return PS_PARSE_INVALID;
}
break;
case ')':
if (verbose)
fprintf(stderr, "unexpected character `%c'\n", ch);
*type = PS_UNKNOWN;
return PS_PARSE_INVALID;
break;
default:
if (isdigit(ch)) {
have_digit = 1;
*type = PS_INTEGER; /* actually undecided (maybe TOKEN/REAL/RADIX) */
} else if (ch == '-' || ch == '+') {
*type = PS_INTEGER;
} else if (ch == '.') {
*type = PS_REAL;
} else {
*type = PS_TOKEN;
}
buffer[i++] = ch;
break;
}
#define isdelim(ch) \
ch == '(' || ch == '<' || ch == '[' || ch == ']' \
|| ch == '{' || ch == '}' || ch == '/' || ch == '%'
while ((ch = fgetc(stream)) != EOF) {
if (*type == PS_TOKEN || *type == PS_NAME) {
if (isspace(ch)) {
break; /* not strict */
} else if (isdelim(ch)) {
ungetc(ch, stream);
break;
}
} else if (*type == PS_INTEGER) {
if (isspace(ch)) {
break;
} else if (isdelim(ch)) {
ungetc(ch, stream);
break;
} else if (ch == '#') {
/* check base (2-36) here */
*type = PS_RADIX;
} else if (ch == '.' && !have_exp) {
*type = PS_REAL;
} else if (ch == '+' || ch == '-') {
if (i < 1 || (buffer[i-1] != 'e' && buffer[i-1] != 'E')) {
*type = PS_TOKEN;
}
} else if ((ch == 'e' || ch == 'E') && have_digit ) {
have_exp = 1;
} else if (isdigit(ch)) {
have_digit = 1;
} else {
*type = PS_TOKEN; /* not a number */
}
} else if (*type == PS_REAL) {
if (isspace(ch)) {
break;
} else if (isdelim(ch)) {
ungetc(ch, stream);
break;
} else if (ch == '+' || ch == '-') {
if (i < 1 || (buffer[i-1] != 'e' && buffer[i-1] != 'E')) {
*type = PS_TOKEN;
}
} else if ((ch == 'e' || ch == 'E') && have_digit ) {
have_exp = 1;
} else if (isdigit(ch)) {
have_digit = 1;
} else {
*type = PS_TOKEN; /* not a number */
}
} else if (*type == PS_RADIX) {
if (isspace(ch)) {
break;
} else if (isdelim(ch)) {
ungetc(ch, stream);
break;
} else if (!(isalpha(ch) || isdigit(ch))) {
*type = PS_TOKEN;
}
/* string is somewhat special */
} else if (*type == PS_STRING) {
if (escape) {
escape = 0;
} else {
if (ch == '(') {
unbalanced++;
} else if (ch == ')') {
if (!unbalanced)
break;
unbalanced--;
} else if (ch == '\\') {
escape = 1;
}
}
} else if (*type == PS_STRING_AHX) {
if (ch == '>') {
break;
} else if (isspace(ch)) {
continue; /* next */
} else if (!isxdigit(ch)) {
if (verbose)
fprintf(stderr, "non hex digit appears in <...>\n");
*type = PS_UNKNOWN;
return PS_PARSE_INVALID;
}
/* not strictly checking string */
} else if (*type == PS_STRING_A85) {
if (ch == '~' && fgetc(stream) == '>') {
break;
} else if (ch < '!' || (ch > 'u' && ch != 'z')) {
*type = PS_UNKNOWN;
return PS_PARSE_INVALID;
}
}
if (i >= bufflen) { /* error */
*type = PS_UNKNOWN;
return PS_PARSE_BUFF_ERROR;
}
buffer[i++] = ch;
}
buffer[i] = 0;
if (ch == EOF) {
if (i == 0) {
return PS_PARSE_END;
} else {
*type = PS_UNKNOWN;
return PS_PARSE_INVALID;
}
}
/*
if (*type == PS_RADIX && check_radix(buffer) < 0)
*type = TOKEN;
*/
if ((*type == PS_REAL || *type == PS_INTEGER) && !have_digit)
*type = PS_TOKEN;
return PS_PARSE_OK;
}
static bool uri_parse(const char *str, size_t len, struct uri_info *uri)
{
const char *b, *p = str, *e = str+len, *x;
#define NEXT(I) ({ \
b = p += (I); \
STRSEARCH(p, e-p, isdelim(*p)); \
})
NEXT(0);
if (p < e && p[0] == ':' && !(
(x = strndigit(p+1, MIN(e-p-1,PORT_LEN))) > p+1 &&
(x == e || isdelim(*x))))
{
uri->scheme = b;
uri->scheme_len = p-b;
NEXT(1);
}
else
{
uri->scheme = NULL;
uri->scheme_len = 0;
}
if (p < e-1 && p == b && p[0] == '/' && p[1] == '/')
NEXT(2);
if (p < e-1 && *p == '@')
NEXT(1);
uri->host = b;
uri->host_len = p-b;
uri->port = -1;
while (p < e-1 && p[0] == ':')
{
char portbuf[8];
unsigned portlen = sizeof(portbuf)-1;
NEXT(1);
if (p-b < portlen)
portlen = p-b;
memcpy(portbuf, b, portlen);
portbuf[portlen] = 0;
uri->port = strtoul(portbuf, (char **)&x, 10);
if (!*x)
break;
uri->host_len = p-uri->host;
uri->port = -1;
}
if (p < e)
{
uri->path = p;
uri->path_len = e-p;
}
else
{
uri->path = NULL;
uri->path_len = 0;
}
#undef NEXT
return true;
}
int mailesmtp_parse_ehlo(mailsmtp * session)
{
char * response;
/* restore data */
session->esmtp = MAILSMTP_ESMTP;
session->auth = MAILSMTP_AUTH_CHECKED;
response = session->response;
/* ESMTP supported extensions :
DSN
EXPN
8BITMIME
SIZE [<n>]
ETRN
STARTTLS
AUTH <mechanisms...>
*/
while (response != NULL) {
if (!strncasecmp(response, "EXPN", 4) && isdelim(response[4])) {
session->esmtp |= MAILSMTP_ESMTP_EXPN;
}
else if (!strncasecmp(response, "ETRN", 4) && isdelim(response[4])) {
session->esmtp |= MAILSMTP_ESMTP_ETRN;
}
else if (!strncasecmp(response, "DSN", 3) && isdelim(response[3])) {
session->esmtp |= MAILSMTP_ESMTP_DSN;
}
else if (!strncasecmp(response, "8BITMIME", 8) && isdelim(response[8])) {
session->esmtp |= MAILSMTP_ESMTP_8BITMIME;
}
else if (!strncasecmp(response, "STARTTLS", 8) && isdelim(response[8])) {
session->esmtp |= MAILSMTP_ESMTP_STARTTLS;
}
else if (!strncasecmp(response, "SIZE", 4) && isdelim(response[4])) {
session->esmtp |= MAILSMTP_ESMTP_SIZE;
if ((response[4] == ' ') || (response[4] == '\t')) {
session->smtp_max_msg_size = strtoul(response + 4, NULL, 10);
}
/* TODO: grab optionnal max size */
}
else if (!strncasecmp(response, "PIPELINING", 10) && isdelim(response[10])) {
session->esmtp |= MAILSMTP_ESMTP_PIPELINING;
}
else if (!strncasecmp(response, "AUTH ", 5)) {
response += 5; /* remove "AUTH " */
while (response[0] != '\n' && response[0] != '\0') {
while (response[0] == ' ') response++;
if (strncasecmp(response, "LOGIN", 5) == 0) {
session->auth |= MAILSMTP_AUTH_LOGIN;
response += 5;
} else if (strncasecmp(response, "CRAM-MD5", 8) == 0) {
session->auth |= MAILSMTP_AUTH_CRAM_MD5;
response += 8;
} else if (strncasecmp(response, "PLAIN", 5) == 0) {
session->auth |= MAILSMTP_AUTH_PLAIN;
response += 5;
} else if (strncasecmp(response, "DIGEST-MD5", 10) == 0) {
session->auth |= MAILSMTP_AUTH_DIGEST_MD5;
response += 10;
} else if (strncasecmp(response, "GSSAPI", 6) == 0) {
session->auth |= MAILSMTP_AUTH_GSSAPI;
response += 6;
} else if (strncasecmp(response, "SRP", 3) == 0) {
session->auth |= MAILSMTP_AUTH_SRP;
response += 3;
} else if (strncasecmp(response, "NTLM", 4) == 0) {
session->auth |= MAILSMTP_AUTH_NTLM;
response += 4;
} else if (strncasecmp(response, "KERBEROS_V4", 11) == 0) {
session->auth |= MAILSMTP_AUTH_KERBEROS_V4;
response += 11;
} else {
/* unknown auth method - jump to next word or eol */
while (!isdelim(response[0]) || response[0] == '\r')
response++;
}
}
}
// for broken servers
else if (!strncasecmp(response, "AUTH=", 5)) {
response += 5; /* remove "AUTH=" */
while (response[0] != '\n' && response[0] != '\0') {
while (response[0] == ' ') response++;
if (strncasecmp(response, "LOGIN", 5) == 0) {
session->auth |= MAILSMTP_AUTH_LOGIN;
response += 5;
} else if (strncasecmp(response, "CRAM-MD5", 8) == 0) {
session->auth |= MAILSMTP_AUTH_CRAM_MD5;
response += 8;
} else if (strncasecmp(response, "PLAIN", 5) == 0) {
session->auth |= MAILSMTP_AUTH_PLAIN;
response += 5;
} else if (strncasecmp(response, "DIGEST-MD5", 10) == 0) {
session->auth |= MAILSMTP_AUTH_DIGEST_MD5;
response += 10;
} else if (strncasecmp(response, "GSSAPI", 6) == 0) {
session->auth |= MAILSMTP_AUTH_GSSAPI;
response += 6;
} else if (strncasecmp(response, "SRP", 3) == 0) {
session->auth |= MAILSMTP_AUTH_SRP;
response += 3;
} else if (strncasecmp(response, "NTLM", 4) == 0) {
session->auth |= MAILSMTP_AUTH_NTLM;
response += 4;
} else if (strncasecmp(response, "KERBEROS_V4", 11) == 0) {
session->auth |= MAILSMTP_AUTH_KERBEROS_V4;
response += 11;
} else {
/* unknown auth method - jump to next word or eol */
while (!isdelim(response[0]) || response[0] == '\r')
response++;
}
}
}
response = strpbrk(response, "\n");
if (response != NULL)
response++;
}
return MAILSMTP_NO_ERROR;
}
static char *
next_token(char *p, char *end, char **new_p, int *delim)
{
char *tok_start = NULL, *tok_end = NULL, *tok = NULL, *sa_start = NULL;
int in_tok = 0;
int in_quote = 0;
int in_parens = 0;
int in_comment_ss = 0;
int in_comment_cpp = 0;
int in_comment_sa = 0;
int had_quote = 0;
int is_escaped = 0;
char *cpp_token_line = NULL;
char *cpp_token_file = NULL;
*delim = 0;
if (p >= end) return NULL;
while (p < end)
{
if (*p == '\n')
{
in_comment_ss = 0;
in_comment_cpp = 0;
cpp_token_line = NULL;
cpp_token_file = NULL;
line++;
}
if ((!in_comment_ss) && (!in_comment_sa))
{
if ((!in_quote) && (*p == '/') && (p < (end - 1)) && (*(p + 1) == '/'))
in_comment_ss = 1;
if ((!in_quote) && (*p == '#'))
in_comment_cpp = 1;
if ((!in_quote) && (*p == '/') && (p < (end - 1)) && (*(p + 1) == '*'))
{
in_comment_sa = 1;
sa_start = p;
}
}
if ((in_comment_cpp) && (*p == '#'))
{
char *pp, fl[4096];
char *tmpstr = NULL;
int l, nm;
/* handle cpp comments */
/* their line format is
* # <line no. of next line> <filename from next line on> [??]
*/
cpp_token_line = NULL;
cpp_token_file = NULL;
pp = p;
while ((pp < end) && (*pp != '\n'))
{
pp++;
}
l = pp - p;
tmpstr = alloca(l + 1);
if (!tmpstr)
{
ERR("%s: Error. %s:%i malloc %i bytes failed",
progname, file_in, line - 1, l + 1);
exit(-1);
}
strncpy(tmpstr, p, l);
tmpstr[l] = 0;
l = sscanf(tmpstr, "%*s %i \"%[^\"]\"", &nm, fl);
if (l == 2)
{
strcpy(file_buf, fl);
line = nm;
file_in = file_buf;
}
}
else if ((!in_comment_ss) && (!in_comment_sa) && (!in_comment_cpp))
{
if (!in_tok)
{
if (!in_quote)
{
if (!isspace(*p))
{
if (*p == '"')
{
in_quote = 1;
had_quote = 1;
}
else if (*p == '(')
in_parens++;
in_tok = 1;
tok_start = p;
if (isdelim(*p)) *delim = 1;
}
}
}
else
{
if (in_quote)
{
if ((*p) == '\\')
is_escaped = !is_escaped;
else if (((*p) == '"') && (!is_escaped))
{
in_quote = 0;
had_quote = 1;
}
else if (is_escaped)
is_escaped = 0;
}
else if (in_parens)
{
if (((*p) == ')') && (!is_escaped))
in_parens--;
}
else
{
if (*p == '"')
{
in_quote = 1;
had_quote = 1;
}
else if (*p == '(')
in_parens++;
/* check for end-of-token */
if (
(isspace(*p)) ||
((*delim) && (!isdelim(*p))) ||
(isdelim(*p))
)
{
in_tok = 0;
tok_end = p - 1;
if (*p == '\n') line--;
goto done;
}
}
}
}
if (in_comment_sa)
{
if ((*p == '/') && (*(p - 1) == '*') && ((p - sa_start) > 2))
in_comment_sa = 0;
}
p++;
}
if (!in_tok) return NULL;
tok_end = p - 1;
done:
*new_p = p;
tok = mem_alloc(tok_end - tok_start + 2);
strncpy(tok, tok_start, tok_end - tok_start + 1);
tok[tok_end - tok_start + 1] = 0;
if (had_quote)
{
is_escaped = 0;
p = tok;
while (*p)
{
if ((*p == '\"') && (!is_escaped))
{
memmove(p, p + 1, strlen(p));
}
else if ((*p == '\\') && (*(p + 1) == 'n'))
{
memmove(p, p + 1, strlen(p));
*p = '\n';
}
else if ((*p == '\\') && (*(p + 1) == 't'))
{
memmove(p, p + 1, strlen(p));
*p = '\t';
}
else if (*p == '\\')
{
memmove(p, p + 1, strlen(p));
if (*p == '\\') p++;
else is_escaped = 1;
}
else
{
if (is_escaped) is_escaped = 0;
p++;
}
}
}
else if ((tok) && (*tok == '('))
{
char *tmp;
tmp = tok;
tok = perform_math(tok);
free(tmp);
}
return tok;
}
/* Get a token. */
char get_token(void)
{
register char *temp;
token_type = 0; tok = 0;
temp = token;
*temp = '\0';
/* skip over white space */
while (iswhite(*prog) && *prog) ++prog;
/* Handle Windows and Mac newlines */
if (*prog == '\r') {
++prog;
/* Only skip \n if it exists (if it doesn't, we are running on mac) */
if (*prog == '\n') {
++prog;
}
/* skip over white space */
while (iswhite(*prog) && *prog) ++prog;
}
/* Handle Unix newlines */
if (*prog == '\n') {
++prog;
/* skip over white space */
while (iswhite(*prog) && *prog) ++prog;
}
if (*prog == '\0') { /* end of file */
*token = '\0';
tok = FINISHED;
return (token_type = DELIMITER);
}
if (strchr("{}", *prog)) { /* block delimiters */
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = BLOCK);
}
/* look for comments */
if (*prog == '/')
if (*(prog + 1) == '*') { /* is a comment */
prog += 2;
do { /* find end of comment */
while (*prog != '*' && *prog != '\0') prog++;
if (*prog == '\0') {
prog--;
break;
}
prog++;
} while (*prog != '/');
prog++;
}
/* look for C++ style comments */
if (*prog == '/')
if (*(prog + 1) == '/') { /* is a comment */
prog += 2;
/* find end of line */
while (*prog != '\r' && *prog != '\n' && *prog != '\0') prog++;
if (*prog == '\r' && *(prog + 1) == '\n') {
prog++;
}
}
/* look for the end of file after a comment */
if (*prog == '\0') { /* end of file */
*token = '\0';
tok = FINISHED;
return (token_type = DELIMITER);
}
if (strchr("!<>=", *prog)) { /* is or might be
a relational operator */
switch (*prog) {
case '=': if (*(prog + 1) == '=') {
prog++; prog++;
*temp = EQ;
temp++; *temp = EQ; temp++;
*temp = '\0';
}
break;
case '!': if (*(prog + 1) == '=') {
prog++; prog++;
*temp = NE;
temp++; *temp = NE; temp++;
*temp = '\0';
}
break;
case '<': if (*(prog + 1) == '=') {
prog++; prog++;
*temp = LE; temp++; *temp = LE;
}
else {
prog++;
*temp = LT;
}
temp++;
*temp = '\0';
break;
case '>': if (*(prog + 1) == '=') {
prog++; prog++;
*temp = GE; temp++; *temp = GE;
}
else {
prog++;
*temp = GT;
}
temp++;
*temp = '\0';
break;
}
if (*token) return(token_type = DELIMITER);
}
if (strchr("+-*^/%=;(),'", *prog)) { /* delimiter */
*temp = *prog;
prog++; /* advance to next position */
temp++;
*temp = '\0';
return (token_type = DELIMITER);
}
if (*prog == '"') { /* quoted string */
prog++;
while ((*prog != '"' && *prog != '\r' && *prog != '\n' && *prog != '\0') || (*prog == '"' && *(prog - 1) == '\\')) *temp++ = *prog++;
if (*prog == '\r' || *prog == '\n' || *prog == '\0') sntx_err(SYNTAX);
prog++; *temp = '\0';
str_replace(token, "\\a", "\a");
str_replace(token, "\\b", "\b");
str_replace(token, "\\f", "\f");
str_replace(token, "\\n", "\n");
str_replace(token, "\\r", "\r");
str_replace(token, "\\t", "\t");
str_replace(token, "\\v", "\v");
str_replace(token, "\\\\", "\\");
str_replace(token, "\\\'", "\'");
str_replace(token, "\\\"", "\"");
return (token_type = STRING);
}
if (isdigit((int)*prog)) { /* number */
while (!isdelim(*prog)) *temp++ = *prog++;
*temp = '\0';
return (token_type = NUMBER);
}
if (isalpha((int)*prog)) { /* var or command */
while (!isdelim(*prog)) *temp++ = *prog++;
token_type = TEMP;
}
*temp = '\0';
/* see if a string is a command or a variable */
if (token_type == TEMP) {
tok = look_up(token); /* convert to internal rep */
if (tok) token_type = KEYWORD; /* is a keyword */
else token_type = IDENTIFIER;
}
return token_type;
}
static int
argcv_scan (int len, const char *command, const char *delim, const char *cmnt,
int *start, int *end, int *save)
{
int i = 0;
for (;;)
{
i = *save;
if (i >= len)
return i + 1;
/* Skip initial whitespace */
while (i < len && isws (command[i]))
i++;
*start = i;
if (!isdelim (command[i], delim))
{
while (i < len)
{
if (command[i] == '\\')
{
if (++i == len)
break;
i++;
continue;
}
if (command[i] == '\'' || command[i] == '"')
{
int j;
for (j = i+1; j < len && command[j] != command[i]; j++)
if (command[j] == '\\')
j++;
if (j < len)
i = j+1;
else
i++;
}
else if (isws (command[i]) || isdelim (command[i], delim))
break;
else
i++; /* skip the escaped character */
}
i--;
}
*end = i;
*save = i + 1;
/* If we have a token, and it starts with a comment character, skip
to the newline and restart the token search. */
if (*save <= len)
{
if (strchr (cmnt, command[*start]) != NULL)
{
i = *save;
while (i < len && command[i] != '\n')
i++;
*save = i;
continue;
}
}
break;
}
return *save;
}
int get_token()
{
char *temp;
token_type = 0;
tok = 0;
temp = token;
*temp = '\0';
while(iswhite(*prog) && *prog)
++prog;
if(*prog=='\n') {
++prog;
while(iswhite(*prog) && *prog)
++prog;
}
if(*prog=='\0') {
*token = '\0';
tok = FINISHED;
return(token_type=DELIMITER);
}
if(strchr1("{}", *prog)) {
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = BLOCK);
}
if(*prog=='/') {
if(*(prog+1)=='*') {
prog += 2;
do {
while(*prog!='*')
prog++;
prog++;
} while (*prog!='/');
prog++;
}
}
if(strchr1("!<>=", *prog)) {
switch(*prog) {
case '=':
if(*(prog+1)=='=') {
prog++; prog++;
*temp = EQ;
temp++; *temp = EQ; temp++;
*temp = '\0';
}
break;
case '!':
if(*(prog+1)=='=') {
prog++; prog++;
*temp = NE;
temp++; *temp = NE; temp++;
*temp = '\0';
}
break;
case '<':
if(*(prog+1)=='=') {
prog++; prog++;
*temp = LE; temp++; *temp = LE;
} else {
prog++;
*temp = LT;
}
temp++;
*temp = '\0';
break;
case '>':
if(*(prog+1)=='=') {
prog++; prog++;
*temp = GE; temp++; *temp = GE;
} else {
prog++;
*temp = GT;
}
temp++;
*temp = '\0';
break;
}
if(*token)
return(token_type = DELIMITER);
}
if(strchr1("+-*^&|/%=;(),'", *prog)){
*temp = *prog;
prog++;
temp++;
*temp = '\0';
return (token_type=DELIMITER);
}
if(*prog=='"') {
prog++;
while(*prog!='"'&& *prog!='\n')
*temp++ = *prog++;
if(*prog=='\n')
sntx_err(SYNTAX);
prog++; *temp = '\0';
return(token_type=STRING);
}
if(isdigit(*prog)) {
while(!isdelim(*prog))
*temp++ = *prog++;
*temp = '\0';
return(token_type = NUMBER);
}
if(isalph(*prog)) {
while(!isdelim(*prog))
*temp++ = *prog++;
token_type=TEMP;
}
*temp = '\0';
if(token_type==TEMP) {
tok = look_up(token);
if(tok)
token_type = KEYWORD;
else
token_type = IDENTIFIER;
}
return token_type;
}
BOOL parse_cmd(char *cmd)
{
unsigned int i, rc;
int Argc; // argument count
#define MAXARGS 32
char *Argv[MAXARGS]; // argument pointers
char *pszTemp;
if (strlen(cmd)==0)
{
return FALSE;
}
if (strlen(cmd)==2)
if (cmd[1]==':')
{
if (QueryDriveReady(cmd[0]-'a'+1))
DosSetDefaultDisk(cmd[0]-'a'+1);
return FALSE;
}
while (( *cmd == ' ' ) || ( *cmd == '\t' ))
cmd++;
// loop through arguments
for ( Argc = 0; (( Argc < MAXARGS ) && ( *cmd )); Argc++ ) {
pszTemp = cmd; // save start of argument
while ( isdelim( *cmd ) == 0 ) {
if ( *cmd )
cmd++;
}
// check flag for terminators
if (Argc == 0) { // '\0' after program name only
if (( *cmd != '\0' ))
*cmd++ = '\0';
}
// update the Argv pointer
Argv[ Argc ] = pszTemp;
log("Argv[%d]=%s\n", Argc, pszTemp);
// skip delimiters for Argv[2] onwards
while (( *cmd ) && ( isdelim( *cmd )))
cmd++;
}
while (*cmd && isdelim(*cmd))
cmd--;
// change the first trailing delimiter to '\0'
cmd++;
*cmd = '\0'; /* second NULL terminator */
Argv[Argc] = NULL;
log("Argv[%d]=%s\n", Argc, 0);
if (!strcmp(Argv[0], "exit"))
{
return TRUE;
}
for (i = 0; commands[i]; i ++)
{
if (!strcmp(Argv[0], commands[i]->cmdname))
{
(*(commands[i]->func))(Argc, Argv);
return FALSE;
}
}
//log("argc=%d\n", Argc);
//for (i = 0; i < Argc; i++)
// log("argv[%d]=%s\n", i, Argv[i]);
execute_external(Argc, Argv);
return FALSE;
}
/* Чтение лексемы */
char get_token()
{
register char *temp;
token_type = 0; tok = 0;
temp = token;
if( *prog == '\0' )
{
/* Конец файла */
*token = 0;
tok = FINISHED;
return( token_type = DELIMITER );
}
while( iswhite(*prog) ) ++prog; /* Пропуск пробелов */
if( *prog == '\r' )
{
/* конец строки программы */
++prog; ++prog;
tok = EOL; *token = '\r';
token[1] = '\n'; token[2] = 0;
return (token_type = DELIMITER );
}
if( strchr("+-*^/%=;(),<>", *prog ) )
{
/* Разделитель */
*temp = *prog;
prog++; /* Переход на следующу позицию */
temp++;
*temp = 0;
return ( token_type = DELIMITER );
}
if ( *prog == '"' )
{
/* строка кавычек */
prog ++;
while( *prog != '"' && *prog != '\r' ) *temp++ = *prog++;
if( *prog == '\r' ) serror(1);
prog++; *temp = 0;
return( token_type = QUOTE );
}
if( isdigit(*prog) )
{
/* число */
while( !isdelim( *prog ) ) *temp++ = *prog++;
*temp = '\0';
return( token_type = NUMBER );
}
if( isalpha( *prog ) )
{
/* переменная или команда */
while( !isdelim( *prog ) ) *temp++ = *prog++;
token_type = STRING;
}
*temp = '\0';
/* просматривается, если строка - переменная или команда */
if ( token_type == STRING )
{
tok = look_up( token ); /* Преобразование во внутренний формат */ //Пока что таблица table не заполнена, посему look_up === 0
if ( !tok ) token_type = VARIABLE;
else token_type = COMMAND; /* это команда */
}
return token_type;
}
static inline int isregular(int ch)
{
return !isdelim(ch) && !iswhite(ch) && ch != EOF;
}
/* Get a token. */
get_token(void)
{
register char *temp;
token_type = 0; tok = 0;
temp = token;
*temp = '\0';
/* skip over white space */
while(iswhite(*prog) && *prog) ++prog;
if(*prog==0x0a) {
++prog;
// ++prog;
/* skip over white space */
while(iswhite(*prog) && *prog) ++prog;
}
if(*prog=='\0') { /* end of file */
*token = '\0';
tok = FINISHED;
return(token_type=DELIMITER);
}
if(strchr("{}", *prog)) { /* block delimiters */
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = BLOCK);
}
/* look for comments */
if(*prog=='/')
if(*(prog+1)=='*') { /* is a comment */
prog += 2;
do { /* find end of comment */
while(*prog!='*') prog++;
prog++;
} while (*prog!='/');
prog++;
}
if(strchr("!<>=", *prog)) { /* is or might be
a relation operator */
switch(*prog) {
case '=': if(*(prog+1)=='=') {
prog++; prog++;
*temp = EQ;
temp++; *temp = EQ; temp++;
*temp = '\0';
}
break;
case '!': if(*(prog+1)=='=') {
prog++; prog++;
*temp = NE;
temp++; *temp = NE; temp++;
*temp = '\0';
}
break;
case '<': if(*(prog+1)=='=') {
prog++; prog++;
*temp = LE; temp++; *temp = LE;
}
else {
prog++;
*temp = LT;
}
temp++;
*temp = '\0';
break;
case '>': if(*(prog+1)=='=') {
prog++; prog++;
*temp = GE; temp++; *temp = GE;
}
else {
prog++;
*temp = GT;
}
temp++;
*temp = '\0';
break;
}
if(*token) return(token_type = DELIMITER);
}
if(strchr("+-*^/%=;(),'", *prog)){ /* delimiter */
*temp = *prog;
prog++; /* advance to next position */
temp++;
*temp = '\0';
return (token_type=DELIMITER);
}
if(*prog=='"') { /* quoted string */
prog++;
while(*prog!='"'&& *prog!=0x0a) *temp++ = *prog++;
if(*prog==0x0a) sntx_err(SYNTAX);
prog++; *temp = '\0';
return(token_type=STRING);
}
if(isdigit(*prog)) { /* number */
while(!isdelim(*prog)) *temp++ = *prog++;
*temp = '\0';
return(token_type = NUMBER);
}
if(isalpha(*prog)) { /* var or command */
while(!isdelim(*prog)) *temp++ = *prog++;
token_type=TEMP;
}
*temp = '\0';
/* see if a string is a command or a variable */
if(token_type==TEMP) {
tok = look_up(token); /* convert to internal rep */
if(tok) token_type = KEYWORD; /* is a keyword */
else token_type = IDENTIFIER;
}
return token_type;
}
/* Считывание лексемы из входного потока. */
int get_token(void) {
register char *temp;
token_type = 0;
tok = 0;
temp = token;
*temp = '\0';
/* пропуск пробелов, символов табуляции и пустой строки */
while(iswhite(*prog) && *prog) {
++prog;
}
while(*prog == '\r' || *prog == '\n') {
++prog;
// COMPILER_SPECIFIC
while(iswhite(*prog) && *prog) {
++prog;
}
}
/* конец файла */
if(*prog == '\0') {
*token = '\0';
tok = FINISHED;
return (token_type = DELIMITER);
}
/* блок кода */
if(strchr("{}", *prog)) { /* ограничение блока */
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = BLOCK);
}
/* массив */
if(strchr("[]", *prog)) {
*temp = *prog;
temp++;
*temp = '\0';
prog++;
return (token_type = ARRAY);
}
/* комментарий */
if(*prog == '/') {
if(*(prog+1) == '*') {
prog += 2;
do {
while(*prog != '*') {
prog++;
}
prog++;
} while(*prog != '/');
prog++;
}
}
/* оператор сравнения */
if(strchr("!<>=", *prog)) {
switch(*prog) {
case '=':
if(*(prog+1) == '=') { // ==
prog++;
prog++;
*temp = EQ;
temp++;
*temp = EQ;
temp++;
*temp = '\0';
}
break;
case '!':
if(*(prog+1) == '=') { // !=
prog++;
prog++;
*temp = NE;
temp++;
*temp = NE;
temp++;
*temp = '\0';
}
break;
case '<':
if(*(prog+1) == '=') { // <=
prog++;
prog++;
*temp = LE;
temp++;
*temp = LE;
} else { // <
prog++;
*temp = LT;
}
temp++;
*temp = '\0';
break;
case '>':
if(*(prog+1) == '=') { // >=
prog++;
prog++;
*temp = GE;
temp++;
*temp = GE;
} else { // >
prog++;
*temp = GT;
}
temp++;
*temp = '\0';
break;
}
if(*token) {
return(token_type = DELIMITER);
}
}
/* разделитель */
if(strchr("+-*^/%=;(),'", *prog)) {
*temp = *prog;
prog++; /* продвижение на следующую позицию */
temp++;
*temp = '\0';
return (token_type = DELIMITER);
}
/* строка в кавычках */
if(*prog=='"') {
prog++;
while(*prog != '"' && *prog != '\r') {
*temp++ = *prog++;
}
if(*prog == '\r') {
sntx_err(SYNTAX);
}
prog++;
*temp = '\0';
return (token_type = STRING);
}
/* число */
if(isdigit(*prog)) {
while(!isdelim(*prog)) {
*temp++ = *prog++;
}
*temp = '\0';
return (token_type = NUMBER);
}
/* переменная или оператор */
if(isalpha(*prog)) {
while(!isdelim(*prog)) {
*temp++ = *prog++;
}
token_type = TEMP;
}
*temp = '\0';
/* ключевое слово или имя */
if(token_type==TEMP) {
tok = look_up(token); /* преобразовать во внутренее представление */
if(tok) {
token_type = KEYWORD; /* это зарезервированное слово */
} else {
token_type = IDENTIFIER;
}
}
return token_type;
}
