| public int | ttype | After a call to the nextToken method, this field
contains the type of the token just read. For a single character
token, its value is the single character, converted to an integer.
For a quoted string token, its value is the quote character.
Otherwise, its value is one of the following:
TT_WORD indicates that the token is a word.
TT_NUMBER indicates that the token is a number.
TT_EOL indicates that the end of line has been read.
The field can only have this value if the
eolIsSignificant method has been called with the
argument true.
TT_EOF indicates that the end of the input stream
has been reached.
The initial value of this field is -4. Also see:
- java.io.StreamTokenizer#eolIsSignificant(boolean)
- java.io.StreamTokenizer#nextToken()
- java.io.StreamTokenizer#quoteChar(int)
- java.io.StreamTokenizer#TT_EOF
- java.io.StreamTokenizer#TT_EOL
- java.io.StreamTokenizer#TT_NUMBER
- java.io.StreamTokenizer#TT_WORD
|
| Method from java.io.StreamTokenizer Detail: |
|---|
 public void commentChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_COMMENT;
}
|
public void eolIsSignificant(boolean flag) {
eolIsSignificantP = flag;
} Determines whether or not ends of line are treated as tokens.
If the flag argument is true, this tokenizer treats end of lines
as tokens; the nextToken method returns
TT_EOL and also sets the ttype field to
this value when an end of line is read.
A line is a sequence of characters ending with either a
carriage-return character ('\r') or a newline
character ('\n'). In addition, a carriage-return
character followed immediately by a newline character is treated
as a single end-of-line token.
If the flag is false, end-of-line characters are
treated as white space and serve only to separate tokens. |
public int lineno() {
return LINENO;
} Return the current line number. |
public void lowerCaseMode(boolean fl) {
forceLower = fl;
} Determines whether or not word token are automatically lowercased.
If the flag argument is true, then the value in the
sval field is lowercased whenever a word token is
returned (the ttype field has the
value TT_WORD by the nextToken method
of this tokenizer.
If the flag argument is false, then the
sval field is not modified. |
public int nextToken() throws IOException {
if (pushedBack) {
pushedBack = false;
return ttype;
}
byte ct[] = ctype;
sval = null;
int c = peekc;
if (c < 0)
c = NEED_CHAR;
if (c == SKIP_LF) {
c = read();
if (c < 0)
return ttype = TT_EOF;
if (c == '\n')
c = NEED_CHAR;
}
if (c == NEED_CHAR) {
c = read();
if (c < 0)
return ttype = TT_EOF;
}
ttype = c; /* Just to be safe */
/* Set peekc so that the next invocation of nextToken will read
* another character unless peekc is reset in this invocation
*/
peekc = NEED_CHAR;
int ctype = c < 256 ? ct[c] : CT_ALPHA;
while ((ctype & CT_WHITESPACE) != 0) {
if (c == '\r') {
LINENO++;
if (eolIsSignificantP) {
peekc = SKIP_LF;
return ttype = TT_EOL;
}
c = read();
if (c == '\n')
c = read();
} else {
if (c == '\n') {
LINENO++;
if (eolIsSignificantP) {
return ttype = TT_EOL;
}
}
c = read();
}
if (c < 0)
return ttype = TT_EOF;
ctype = c < 256 ? ct[c] : CT_ALPHA;
}
if ((ctype & CT_DIGIT) != 0) {
boolean neg = false;
if (c == '-') {
c = read();
if (c != '.' && (c < '0' || c > '9')) {
peekc = c;
return ttype = '-';
}
neg = true;
}
double v = 0;
int decexp = 0;
int seendot = 0;
while (true) {
if (c == '.' && seendot == 0)
seendot = 1;
else if ('0' < = c && c < = '9') {
v = v * 10 + (c - '0');
decexp += seendot;
} else
break;
c = read();
}
peekc = c;
if (decexp != 0) {
double denom = 10;
decexp--;
while (decexp > 0) {
denom *= 10;
decexp--;
}
/* Do one division of a likely-to-be-more-accurate number */
v = v / denom;
}
nval = neg ? -v : v;
return ttype = TT_NUMBER;
}
if ((ctype & CT_ALPHA) != 0) {
int i = 0;
do {
if (i >= buf.length) {
buf = Arrays.copyOf(buf, buf.length * 2);
}
buf[i++] = (char) c;
c = read();
ctype = c < 0 ? CT_WHITESPACE : c < 256 ? ct[c] : CT_ALPHA;
} while ((ctype & (CT_ALPHA | CT_DIGIT)) != 0);
peekc = c;
sval = String.copyValueOf(buf, 0, i);
if (forceLower)
sval = sval.toLowerCase();
return ttype = TT_WORD;
}
if ((ctype & CT_QUOTE) != 0) {
ttype = c;
int i = 0;
/* Invariants (because \Octal needs a lookahead):
* (i) c contains char value
* (ii) d contains the lookahead
*/
int d = read();
while (d >= 0 && d != ttype && d != '\n' && d != '\r') {
if (d == '\\') {
c = read();
int first = c; /* To allow \377, but not \477 */
if (c >= '0' && c < = '7') {
c = c - '0';
int c2 = read();
if ('0' < = c2 && c2 < = '7') {
c = (c < < 3) + (c2 - '0');
c2 = read();
if ('0' < = c2 && c2 < = '7' && first < = '3') {
c = (c < < 3) + (c2 - '0');
d = read();
} else
d = c2;
} else
d = c2;
} else {
switch (c) {
case 'a':
c = 0x7;
break;
case 'b':
c = '\b';
break;
case 'f':
c = 0xC;
break;
case 'n':
c = '\n';
break;
case 'r':
c = '\r';
break;
case 't':
c = '\t';
break;
case 'v':
c = 0xB;
break;
}
d = read();
}
} else {
c = d;
d = read();
}
if (i >= buf.length) {
buf = Arrays.copyOf(buf, buf.length * 2);
}
buf[i++] = (char)c;
}
/* If we broke out of the loop because we found a matching quote
* character then arrange to read a new character next time
* around; otherwise, save the character.
*/
peekc = (d == ttype) ? NEED_CHAR : d;
sval = String.copyValueOf(buf, 0, i);
return ttype;
}
if (c == '/' && (slashSlashCommentsP || slashStarCommentsP)) {
c = read();
if (c == '*' && slashStarCommentsP) {
int prevc = 0;
while ((c = read()) != '/' || prevc != '*') {
if (c == '\r') {
LINENO++;
c = read();
if (c == '\n') {
c = read();
}
} else {
if (c == '\n') {
LINENO++;
c = read();
}
}
if (c < 0)
return ttype = TT_EOF;
prevc = c;
}
return nextToken();
} else if (c == '/' && slashSlashCommentsP) {
while ((c = read()) != '\n' && c != '\r' && c >= 0);
peekc = c;
return nextToken();
} else {
/* Now see if it is still a single line comment */
if ((ct['/'] & CT_COMMENT) != 0) {
while ((c = read()) != '\n' && c != '\r' && c >= 0);
peekc = c;
return nextToken();
} else {
peekc = c;
return ttype = '/';
}
}
}
if ((ctype & CT_COMMENT) != 0) {
while ((c = read()) != '\n' && c != '\r' && c >= 0);
peekc = c;
return nextToken();
}
return ttype = c;
} Parses the next token from the input stream of this tokenizer.
The type of the next token is returned in the ttype
field. Additional information about the token may be in the
nval field or the sval field of this
tokenizer.
Typical clients of this
class first set up the syntax tables and then sit in a loop
calling nextToken to parse successive tokens until TT_EOF
is returned. |
public void ordinaryChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = 0;
} Specifies that the character argument is "ordinary"
in this tokenizer. It removes any special significance the
character has as a comment character, word component, string
delimiter, white space, or number character. When such a character
is encountered by the parser, the parser treats it as a
single-character token and sets ttype field to the
character value.
Making a line terminator character "ordinary" may interfere
with the ability of a StreamTokenizer to count
lines. The lineno method may no longer reflect
the presence of such terminator characters in its line count. |
public void ordinaryChars(int low,
int hi) {
if (low < 0)
low = 0;
if (hi >= ctype.length)
hi = ctype.length - 1;
while (low < = hi)
ctype[low++] = 0;
} Specifies that all characters c in the range
low <= c <= high
are "ordinary" in this tokenizer. See the
ordinaryChar method for more information on a
character being ordinary. |
public void parseNumbers() {
for (int i = '0'; i < = '9'; i++)
ctype[i] |= CT_DIGIT;
ctype['.'] |= CT_DIGIT;
ctype['-'] |= CT_DIGIT;
} Specifies that numbers should be parsed by this tokenizer. The
syntax table of this tokenizer is modified so that each of the twelve
characters:
0 1 2 3 4 5 6 7 8 9 . -
has the "numeric" attribute.
When the parser encounters a word token that has the format of a
double precision floating-point number, it treats the token as a
number rather than a word, by setting the ttype
field to the value TT_NUMBER and putting the numeric
value of the token into the nval field. |
public void pushBack() {
if (ttype != TT_NOTHING) /* No-op if nextToken() not called */
pushedBack = true;
} Causes the next call to the nextToken method of this
tokenizer to return the current value in the ttype
field, and not to modify the value in the nval or
sval field. |
public void quoteChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_QUOTE;
} Specifies that matching pairs of this character delimit string
constants in this tokenizer.
When the nextToken method encounters a string
constant, the ttype field is set to the string
delimiter and the sval field is set to the body of
the string.
If a string quote character is encountered, then a string is
recognized, consisting of all characters after (but not including)
the string quote character, up to (but not including) the next
occurrence of that same string quote character, or a line
terminator, or end of file. The usual escape sequences such as
"\n" and "\t" are recognized and
converted to single characters as the string is parsed.
Any other attribute settings for the specified character are cleared. |
public void resetSyntax() {
for (int i = ctype.length; --i >= 0;)
ctype[i] = 0;
} Resets this tokenizer's syntax table so that all characters are
"ordinary." See the ordinaryChar method
for more information on a character being ordinary. |
public void slashSlashComments(boolean flag) {
slashSlashCommentsP = flag;
} Determines whether or not the tokenizer recognizes C++-style comments.
If the flag argument is true, this stream tokenizer
recognizes C++-style comments. Any occurrence of two consecutive
slash characters ('/') is treated as the beginning of
a comment that extends to the end of the line.
If the flag argument is false, then C++-style
comments are not treated specially. |
public void slashStarComments(boolean flag) {
slashStarCommentsP = flag;
} Determines whether or not the tokenizer recognizes C-style comments.
If the flag argument is true, this stream tokenizer
recognizes C-style comments. All text between successive
occurrences of /* and */ are discarded.
If the flag argument is false, then C-style comments
are not treated specially. |
public String toString() {
String ret;
switch (ttype) {
case TT_EOF:
ret = "EOF";
break;
case TT_EOL:
ret = "EOL";
break;
case TT_WORD:
ret = sval;
break;
case TT_NUMBER:
ret = "n=" + nval;
break;
case TT_NOTHING:
ret = "NOTHING";
break;
default: {
/*
* ttype is the first character of either a quoted string or
* is an ordinary character. ttype can definitely not be less
* than 0, since those are reserved values used in the previous
* case statements
*/
if (ttype < 256 &&
((ctype[ttype] & CT_QUOTE) != 0)) {
ret = sval;
break;
}
char s[] = new char[3];
s[0] = s[2] = '\'';
s[1] = (char) ttype;
ret = new String(s);
break;
}
}
return "Token[" + ret + "], line " + LINENO;
} Returns the string representation of the current stream token and
the line number it occurs on.
The precise string returned is unspecified, although the following
example can be considered typical:
Token['a'], line 10
|
public void whitespaceChars(int low,
int hi) {
if (low < 0)
low = 0;
if (hi >= ctype.length)
hi = ctype.length - 1;
while (low < = hi)
ctype[low++] = CT_WHITESPACE;
} |
public void wordChars(int low,
int hi) {
if (low < 0)
low = 0;
if (hi >= ctype.length)
hi = ctype.length - 1;
while (low < = hi)
ctype[low++] |= CT_ALPHA;
} Specifies that all characters c in the range
low <= c <= high
are word constituents. A word token consists of a word constituent
followed by zero or more word constituents or number constituents. |
java.io.StreamTokenizer