使用 Java 中的位置索引进行流标记
Stream tokenizing with position indexes in Java
在 Java 中标记字节流时，我需要提取有关标记化单词索引的信息。例如，给定：
字符串 "Hello world! Java8 program." -> 流 -> ...
我需要这样的东西：
[(Hello, 0, 5), (world, 6, 11), (Java8, 13, 18), (program, 19, 25)]
问题类似Java NLP: Extracting Indicies When Tokenizing Text
区别在于程序输入是未知长度的流。我想将 SimpleTokenizer 应用于此任务，但不幸的是它只接受 String 作为输入。由于流可能很长，我不能直接将流转换为字符串（这会强制程序停止，直到流关闭）。我无法处理在 char 缓冲区上评估的块中的流，因为我可以打破该过程中的单词。你能帮我找到合适的解决方案吗？当前代码只能执行标记化而不包括索引：
public static void main(String[] args) throws IOException, ParseException {
final Reader input = initializeInput();
final Writer output = initializeOutput();
try {
final long count = process(input, output);
output.flush();
} finally {
input.close();
output.close();
}
}
protected static long process(Reader input, Writer output) throws IOException {
final StreamTokenizer st = new StreamTokenizer(input);
st.eolIsSignificant(false);
long count = 0;
int token;
while ((token = st.nextToken()) != StreamTokenizer.TT_EOF) {
if (token == StreamTokenizer.TT_WORD) {
final String word = st.sval;
count++;
output.write(word);
output.flush();
}
}
return count;
}
private static String asString(CharSequence stem) {
if (stem == null)
return "-";
return stem.toString();
}
private static Writer initializeOutput()
throws IOException, ParseException {
final Writer output;
output = new OutputStreamWriter(System.out, "UTF-8");
return output;
}
private static Reader initializeInput()
throws IOException {
final Reader input;
input = new InputStreamReader(System.in, "UTF-8");
return input;
}
我不会退回到使用 StreamTokenizer（OpenNLP 更强大一些！）。相反，关注如何在不破坏结构的情况下从输入中读取字符串。
我想您可能想看看 opennlp SimpleTokenizer 命令行工具如何在 CommandLineTokenizer 中处理这个问题。如果换行符不够好，那么您可以编写一个 ObjectStream<String> 将 "word wraps" 输入到字符串中。当然，所有 Span 位置都将是特定于行的，而不是来自 InputStream，但如果确实需要，您可以更正。
对于以后遇到类似问题的人：
我修改了 StreamTokenizer 的实现。不幸的是继承在这里是不可能的。 getLastTokenStart() 和 getLastTokenEnd() returns 每个解析步骤后解析的令牌索引。那是为字符串和数字准备的（没有在 CT_QUOTE、CT_COMMENT 上测试）
package wrapper;
import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;
import java.util.Arrays;
public class CustomStreamTokenizer {
private long lastTokenStart = 0;
private long lastTokenEnd = -1;
/* Only one of these will be non-null */
private Reader reader = null;
private InputStream input = null;
private char buf[] = new char[20];
private int peekc = NEED_CHAR;
private static final int NEED_CHAR = Integer.MAX_VALUE;
private static final int SKIP_LF = Integer.MAX_VALUE - 1;
private boolean pushedBack;
private boolean forceLower;
/** The line number of the last token read */
private int LINENO = 1;
private boolean eolIsSignificantP = false;
private boolean slashSlashCommentsP = false;
private boolean slashStarCommentsP = false;
private byte ctype[] = new byte[256];
private static final byte CT_WHITESPACE = 1;
private static final byte CT_DIGIT = 2;
private static final byte CT_ALPHA = 4;
private static final byte CT_QUOTE = 8;
private static final byte CT_COMMENT = 16;
/**
* After a call to the {@code 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:
* <ul>
* <li>{@code TT_WORD} indicates that the token is a word.
* <li>{@code TT_NUMBER} indicates that the token is a number.
* <li>{@code TT_EOL} indicates that the end of line has been read.
* The field can only have this value if the
* {@code eolIsSignificant} method has been called with the
* argument {@code true}.
* <li>{@code TT_EOF} indicates that the end of the input stream
* has been reached.
* </ul>
* <p>
* The initial value of this field is -4.
*
* @see java.io.StreamTokenizer#eolIsSignificant(boolean)
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#quoteChar(int)
* @see java.io.StreamTokenizer#TT_EOF
* @see java.io.StreamTokenizer#TT_EOL
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#TT_WORD
*/
public int ttype = TT_NOTHING;
/**
* A constant indicating that the end of the stream has been read.
*/
public static final int TT_EOF = -1;
/**
* A constant indicating that the end of the line has been read.
*/
public static final int TT_EOL = '\n';
/**
* A constant indicating that a number token has been read.
*/
public static final int TT_NUMBER = -2;
/**
* A constant indicating that a word token has been read.
*/
public static final int TT_WORD = -3;
/* A constant indicating that no token has been read, used for
* initializing ttype. FIXME This could be made public and
* made available as the part of the API in a future release.
*/
private static final int TT_NOTHING = -4;
/**
* If the current token is a word token, this field contains a
* string giving the characters of the word token. When the current
* token is a quoted string token, this field contains the body of
* the string.
* <p>
* The current token is a word when the value of the
* {@code ttype} field is {@code TT_WORD}. The current token is
* a quoted string token when the value of the {@code ttype} field is
* a quote character.
* <p>
* The initial value of this field is null.
*
* @see java.io.StreamTokenizer#quoteChar(int)
* @see java.io.StreamTokenizer#TT_WORD
* @see java.io.StreamTokenizer#ttype
*/
public String sval;
/**
* If the current token is a number, this field contains the value
* of that number. The current token is a number when the value of
* the {@code ttype} field is {@code TT_NUMBER}.
* <p>
* The initial value of this field is 0.0.
*
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#ttype
*/
public double nval;
/** Private constructor that initializes everything except the streams. */
private CustomStreamTokenizer() {
wordChars('a', 'z');
wordChars('A', 'Z');
wordChars(128 + 32, 255);
whitespaceChars(0, ' ');
commentChar('/');
quoteChar('"');
quoteChar('\'');
parseNumbers();
}
/**
* Create a tokenizer that parses the given character stream.
*
* @param r a Reader object providing the input stream.
* @since JDK1.1
*/
public CustomStreamTokenizer(Reader r) {
this();
if (r == null) {
throw new NullPointerException();
}
reader = r;
}
/**
* Resets this tokenizer's syntax table so that all characters are
* "ordinary." See the {@code ordinaryChar} method
* for more information on a character being ordinary.
*
* @see java.io.StreamTokenizer#ordinaryChar(int)
*/
public void resetSyntax() {
for (int i = ctype.length; --i >= 0;)
ctype[i] = 0;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are word constituents. A word token consists of a word constituent
* followed by zero or more word constituents or number constituents.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
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 <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are white space characters. White space characters serve only to
* separate tokens in the input stream.
*
* <p>Any other attribute settings for the characters in the specified
* range are cleared.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
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;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are "ordinary" in this tokenizer. See the
* {@code ordinaryChar} method for more information on a
* character being ordinary.
*
* @param low the low end of the range.
* @param hi the high end of the range.
* @see java.io.StreamTokenizer#ordinaryChar(int)
*/
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 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 {@code ttype} field to the
* character value.
*
* <p>Making a line terminator character "ordinary" may interfere
* with the ability of a {@code CustomStreamTokenizer} to count
* lines. The {@code lineno} method may no longer reflect
* the presence of such terminator characters in its line count.
*
* @param ch the character.
* @see java.io.StreamTokenizer#ttype
*/
public void ordinaryChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = 0;
}
/**
* Specified that the character argument starts a single-line
* comment. All characters from the comment character to the end of
* the line are ignored by this stream tokenizer.
*
* <p>Any other attribute settings for the specified character are cleared.
*
* @param ch the character.
*/
public void commentChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_COMMENT;
}
/**
* Specifies that matching pairs of this character delimit string
* constants in this tokenizer.
* <p>
* When the {@code nextToken} method encounters a string
* constant, the {@code ttype} field is set to the string
* delimiter and the {@code sval} field is set to the body of
* the string.
* <p>
* 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
* {@code "\u005Cn"} and {@code "\u005Ct"} are recognized and
* converted to single characters as the string is parsed.
*
* <p>Any other attribute settings for the specified character are cleared.
*
* @param ch the character.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
public void quoteChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_QUOTE;
}
/**
* Specifies that numbers should be parsed by this tokenizer. The
* syntax table of this tokenizer is modified so that each of the twelve
* characters:
* <blockquote><pre>
* 0 1 2 3 4 5 6 7 8 9 . -
* </pre></blockquote>
* <p>
* has the "numeric" attribute.
* <p>
* 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 {@code ttype}
* field to the value {@code TT_NUMBER} and putting the numeric
* value of the token into the {@code nval} field.
*
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#ttype
*/
public void parseNumbers() {
for (int i = '0'; i <= '9'; i++)
ctype[i] |= CT_DIGIT;
ctype['.'] |= CT_DIGIT;
ctype['-'] |= CT_DIGIT;
}
/**
* 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 {@code nextToken} method returns
* {@code TT_EOL} and also sets the {@code ttype} field to
* this value when an end of line is read.
* <p>
* A line is a sequence of characters ending with either a
* carriage-return character ({@code '\u005Cr'}) or a newline
* character ({@code '\u005Cn'}). In addition, a carriage-return
* character followed immediately by a newline character is treated
* as a single end-of-line token.
* <p>
* If the {@code flag} is false, end-of-line characters are
* treated as white space and serve only to separate tokens.
*
* @param flag {@code true} indicates that end-of-line characters
* are separate tokens; {@code false} indicates that
* end-of-line characters are white space.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#ttype
* @see java.io.StreamTokenizer#TT_EOL
*/
public void eolIsSignificant(boolean flag) {
eolIsSignificantP = flag;
}
/**
* Determines whether or not the tokenizer recognizes C-style comments.
* If the flag argument is {@code true}, this stream tokenizer
* recognizes C-style comments. All text between successive
* occurrences of {@code /*} and <code>*/</code> are discarded.
* <p>
* If the flag argument is {@code false}, then C-style comments
* are not treated specially.
*
* @param flag {@code true} indicates to recognize and ignore
* C-style comments.
*/
public void slashStarComments(boolean flag) {
slashStarCommentsP = flag;
}
/**
* Determines whether or not the tokenizer recognizes C++-style comments.
* If the flag argument is {@code true}, this stream tokenizer
* recognizes C++-style comments. Any occurrence of two consecutive
* slash characters ({@code '/'}) is treated as the beginning of
* a comment that extends to the end of the line.
* <p>
* If the flag argument is {@code false}, then C++-style
* comments are not treated specially.
*
* @param flag {@code true} indicates to recognize and ignore
* C++-style comments.
*/
public void slashSlashComments(boolean flag) {
slashSlashCommentsP = flag;
}
/**
* Determines whether or not word token are automatically lowercased.
* If the flag argument is {@code true}, then the value in the
* {@code sval} field is lowercased whenever a word token is
* returned (the {@code ttype} field has the
* value {@code TT_WORD} by the {@code nextToken} method
* of this tokenizer.
* <p>
* If the flag argument is {@code false}, then the
* {@code sval} field is not modified.
*
* @param fl {@code true} indicates that all word tokens should
* be lowercased.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#ttype
* @see java.io.StreamTokenizer#TT_WORD
*/
public void lowerCaseMode(boolean fl) {
forceLower = fl;
}
/** Read the next character */
private int read() throws IOException {
lastTokenEnd++;
if (reader != null)
return reader.read();
else if (input != null)
return input.read();
else
throw new IllegalStateException();
}
/**
* Parses the next token from the input stream of this tokenizer.
* The type of the next token is returned in the {@code ttype}
* field. Additional information about the token may be in the
* {@code nval} field or the {@code sval} field of this
* tokenizer.
* <p>
* 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.
*
* @return the value of the {@code ttype} field.
* @exception IOException if an I/O error occurs.
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
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;
}
lastTokenStart = lastTokenEnd;
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 7, but not 7 */
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;
}
/**
* Causes the next call to the {@code nextToken} method of this
* tokenizer to return the current value in the {@code ttype}
* field, and not to modify the value in the {@code nval} or
* {@code sval} field.
*
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
public void pushBack() {
if (ttype != TT_NOTHING) /* No-op if nextToken() not called */
pushedBack = true;
}
/**
* Return the current line number.
*
* @return the current line number of this stream tokenizer.
*/
public int lineno() {
return LINENO;
}
/**
* Returns the string representation of the current stream token and
* the line number it occurs on.
*
* <p>The precise string returned is unspecified, although the following
* example can be considered typical:
*
* <blockquote><pre>Token['a'], line 10</pre></blockquote>
*
* @return a string representation of the token
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
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;
}
public long getLastTokenStart() {
return lastTokenStart;
}
public long getLastTokenEnd() {
return lastTokenEnd;
}
}
在 Java 中标记字节流时，我需要提取有关标记化单词索引的信息。例如，给定：
字符串 "Hello world! Java8 program." -> 流 -> ...
我需要这样的东西：
[(Hello, 0, 5), (world, 6, 11), (Java8, 13, 18), (program, 19, 25)]
问题类似Java NLP: Extracting Indicies When Tokenizing Text
区别在于程序输入是未知长度的流。我想将 SimpleTokenizer 应用于此任务，但不幸的是它只接受 String 作为输入。由于流可能很长，我不能直接将流转换为字符串（这会强制程序停止，直到流关闭）。我无法处理在 char 缓冲区上评估的块中的流，因为我可以打破该过程中的单词。你能帮我找到合适的解决方案吗？当前代码只能执行标记化而不包括索引：
public static void main(String[] args) throws IOException, ParseException {
final Reader input = initializeInput();
final Writer output = initializeOutput();
try {
final long count = process(input, output);
output.flush();
} finally {
input.close();
output.close();
}
}
protected static long process(Reader input, Writer output) throws IOException {
final StreamTokenizer st = new StreamTokenizer(input);
st.eolIsSignificant(false);
long count = 0;
int token;
while ((token = st.nextToken()) != StreamTokenizer.TT_EOF) {
if (token == StreamTokenizer.TT_WORD) {
final String word = st.sval;
count++;
output.write(word);
output.flush();
}
}
return count;
}
private static String asString(CharSequence stem) {
if (stem == null)
return "-";
return stem.toString();
}
private static Writer initializeOutput()
throws IOException, ParseException {
final Writer output;
output = new OutputStreamWriter(System.out, "UTF-8");
return output;
}
private static Reader initializeInput()
throws IOException {
final Reader input;
input = new InputStreamReader(System.in, "UTF-8");
return input;
}
我不会退回到使用 StreamTokenizer（OpenNLP 更强大一些！）。相反，关注如何在不破坏结构的情况下从输入中读取字符串。
我想您可能想看看 opennlp SimpleTokenizer 命令行工具如何在 CommandLineTokenizer 中处理这个问题。如果换行符不够好，那么您可以编写一个 ObjectStream<String> 将 "word wraps" 输入到字符串中。当然，所有 Span 位置都将是特定于行的，而不是来自 InputStream，但如果确实需要，您可以更正。
对于以后遇到类似问题的人：
我修改了 StreamTokenizer 的实现。不幸的是继承在这里是不可能的。 getLastTokenStart() 和 getLastTokenEnd() returns 每个解析步骤后解析的令牌索引。那是为字符串和数字准备的（没有在 CT_QUOTE、CT_COMMENT 上测试）
package wrapper;
import java.io.IOException;
import java.io.InputStream;
import java.io.Reader;
import java.util.Arrays;
public class CustomStreamTokenizer {
private long lastTokenStart = 0;
private long lastTokenEnd = -1;
/* Only one of these will be non-null */
private Reader reader = null;
private InputStream input = null;
private char buf[] = new char[20];
private int peekc = NEED_CHAR;
private static final int NEED_CHAR = Integer.MAX_VALUE;
private static final int SKIP_LF = Integer.MAX_VALUE - 1;
private boolean pushedBack;
private boolean forceLower;
/** The line number of the last token read */
private int LINENO = 1;
private boolean eolIsSignificantP = false;
private boolean slashSlashCommentsP = false;
private boolean slashStarCommentsP = false;
private byte ctype[] = new byte[256];
private static final byte CT_WHITESPACE = 1;
private static final byte CT_DIGIT = 2;
private static final byte CT_ALPHA = 4;
private static final byte CT_QUOTE = 8;
private static final byte CT_COMMENT = 16;
/**
* After a call to the {@code 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:
* <ul>
* <li>{@code TT_WORD} indicates that the token is a word.
* <li>{@code TT_NUMBER} indicates that the token is a number.
* <li>{@code TT_EOL} indicates that the end of line has been read.
* The field can only have this value if the
* {@code eolIsSignificant} method has been called with the
* argument {@code true}.
* <li>{@code TT_EOF} indicates that the end of the input stream
* has been reached.
* </ul>
* <p>
* The initial value of this field is -4.
*
* @see java.io.StreamTokenizer#eolIsSignificant(boolean)
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#quoteChar(int)
* @see java.io.StreamTokenizer#TT_EOF
* @see java.io.StreamTokenizer#TT_EOL
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#TT_WORD
*/
public int ttype = TT_NOTHING;
/**
* A constant indicating that the end of the stream has been read.
*/
public static final int TT_EOF = -1;
/**
* A constant indicating that the end of the line has been read.
*/
public static final int TT_EOL = '\n';
/**
* A constant indicating that a number token has been read.
*/
public static final int TT_NUMBER = -2;
/**
* A constant indicating that a word token has been read.
*/
public static final int TT_WORD = -3;
/* A constant indicating that no token has been read, used for
* initializing ttype. FIXME This could be made public and
* made available as the part of the API in a future release.
*/
private static final int TT_NOTHING = -4;
/**
* If the current token is a word token, this field contains a
* string giving the characters of the word token. When the current
* token is a quoted string token, this field contains the body of
* the string.
* <p>
* The current token is a word when the value of the
* {@code ttype} field is {@code TT_WORD}. The current token is
* a quoted string token when the value of the {@code ttype} field is
* a quote character.
* <p>
* The initial value of this field is null.
*
* @see java.io.StreamTokenizer#quoteChar(int)
* @see java.io.StreamTokenizer#TT_WORD
* @see java.io.StreamTokenizer#ttype
*/
public String sval;
/**
* If the current token is a number, this field contains the value
* of that number. The current token is a number when the value of
* the {@code ttype} field is {@code TT_NUMBER}.
* <p>
* The initial value of this field is 0.0.
*
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#ttype
*/
public double nval;
/** Private constructor that initializes everything except the streams. */
private CustomStreamTokenizer() {
wordChars('a', 'z');
wordChars('A', 'Z');
wordChars(128 + 32, 255);
whitespaceChars(0, ' ');
commentChar('/');
quoteChar('"');
quoteChar('\'');
parseNumbers();
}
/**
* Create a tokenizer that parses the given character stream.
*
* @param r a Reader object providing the input stream.
* @since JDK1.1
*/
public CustomStreamTokenizer(Reader r) {
this();
if (r == null) {
throw new NullPointerException();
}
reader = r;
}
/**
* Resets this tokenizer's syntax table so that all characters are
* "ordinary." See the {@code ordinaryChar} method
* for more information on a character being ordinary.
*
* @see java.io.StreamTokenizer#ordinaryChar(int)
*/
public void resetSyntax() {
for (int i = ctype.length; --i >= 0;)
ctype[i] = 0;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are word constituents. A word token consists of a word constituent
* followed by zero or more word constituents or number constituents.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
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 <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are white space characters. White space characters serve only to
* separate tokens in the input stream.
*
* <p>Any other attribute settings for the characters in the specified
* range are cleared.
*
* @param low the low end of the range.
* @param hi the high end of the range.
*/
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;
}
/**
* Specifies that all characters <i>c</i> in the range
* <code>low <= <i>c</i> <= high</code>
* are "ordinary" in this tokenizer. See the
* {@code ordinaryChar} method for more information on a
* character being ordinary.
*
* @param low the low end of the range.
* @param hi the high end of the range.
* @see java.io.StreamTokenizer#ordinaryChar(int)
*/
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 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 {@code ttype} field to the
* character value.
*
* <p>Making a line terminator character "ordinary" may interfere
* with the ability of a {@code CustomStreamTokenizer} to count
* lines. The {@code lineno} method may no longer reflect
* the presence of such terminator characters in its line count.
*
* @param ch the character.
* @see java.io.StreamTokenizer#ttype
*/
public void ordinaryChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = 0;
}
/**
* Specified that the character argument starts a single-line
* comment. All characters from the comment character to the end of
* the line are ignored by this stream tokenizer.
*
* <p>Any other attribute settings for the specified character are cleared.
*
* @param ch the character.
*/
public void commentChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_COMMENT;
}
/**
* Specifies that matching pairs of this character delimit string
* constants in this tokenizer.
* <p>
* When the {@code nextToken} method encounters a string
* constant, the {@code ttype} field is set to the string
* delimiter and the {@code sval} field is set to the body of
* the string.
* <p>
* 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
* {@code "\u005Cn"} and {@code "\u005Ct"} are recognized and
* converted to single characters as the string is parsed.
*
* <p>Any other attribute settings for the specified character are cleared.
*
* @param ch the character.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
public void quoteChar(int ch) {
if (ch >= 0 && ch < ctype.length)
ctype[ch] = CT_QUOTE;
}
/**
* Specifies that numbers should be parsed by this tokenizer. The
* syntax table of this tokenizer is modified so that each of the twelve
* characters:
* <blockquote><pre>
* 0 1 2 3 4 5 6 7 8 9 . -
* </pre></blockquote>
* <p>
* has the "numeric" attribute.
* <p>
* 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 {@code ttype}
* field to the value {@code TT_NUMBER} and putting the numeric
* value of the token into the {@code nval} field.
*
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#TT_NUMBER
* @see java.io.StreamTokenizer#ttype
*/
public void parseNumbers() {
for (int i = '0'; i <= '9'; i++)
ctype[i] |= CT_DIGIT;
ctype['.'] |= CT_DIGIT;
ctype['-'] |= CT_DIGIT;
}
/**
* 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 {@code nextToken} method returns
* {@code TT_EOL} and also sets the {@code ttype} field to
* this value when an end of line is read.
* <p>
* A line is a sequence of characters ending with either a
* carriage-return character ({@code '\u005Cr'}) or a newline
* character ({@code '\u005Cn'}). In addition, a carriage-return
* character followed immediately by a newline character is treated
* as a single end-of-line token.
* <p>
* If the {@code flag} is false, end-of-line characters are
* treated as white space and serve only to separate tokens.
*
* @param flag {@code true} indicates that end-of-line characters
* are separate tokens; {@code false} indicates that
* end-of-line characters are white space.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#ttype
* @see java.io.StreamTokenizer#TT_EOL
*/
public void eolIsSignificant(boolean flag) {
eolIsSignificantP = flag;
}
/**
* Determines whether or not the tokenizer recognizes C-style comments.
* If the flag argument is {@code true}, this stream tokenizer
* recognizes C-style comments. All text between successive
* occurrences of {@code /*} and <code>*/</code> are discarded.
* <p>
* If the flag argument is {@code false}, then C-style comments
* are not treated specially.
*
* @param flag {@code true} indicates to recognize and ignore
* C-style comments.
*/
public void slashStarComments(boolean flag) {
slashStarCommentsP = flag;
}
/**
* Determines whether or not the tokenizer recognizes C++-style comments.
* If the flag argument is {@code true}, this stream tokenizer
* recognizes C++-style comments. Any occurrence of two consecutive
* slash characters ({@code '/'}) is treated as the beginning of
* a comment that extends to the end of the line.
* <p>
* If the flag argument is {@code false}, then C++-style
* comments are not treated specially.
*
* @param flag {@code true} indicates to recognize and ignore
* C++-style comments.
*/
public void slashSlashComments(boolean flag) {
slashSlashCommentsP = flag;
}
/**
* Determines whether or not word token are automatically lowercased.
* If the flag argument is {@code true}, then the value in the
* {@code sval} field is lowercased whenever a word token is
* returned (the {@code ttype} field has the
* value {@code TT_WORD} by the {@code nextToken} method
* of this tokenizer.
* <p>
* If the flag argument is {@code false}, then the
* {@code sval} field is not modified.
*
* @param fl {@code true} indicates that all word tokens should
* be lowercased.
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#ttype
* @see java.io.StreamTokenizer#TT_WORD
*/
public void lowerCaseMode(boolean fl) {
forceLower = fl;
}
/** Read the next character */
private int read() throws IOException {
lastTokenEnd++;
if (reader != null)
return reader.read();
else if (input != null)
return input.read();
else
throw new IllegalStateException();
}
/**
* Parses the next token from the input stream of this tokenizer.
* The type of the next token is returned in the {@code ttype}
* field. Additional information about the token may be in the
* {@code nval} field or the {@code sval} field of this
* tokenizer.
* <p>
* 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.
*
* @return the value of the {@code ttype} field.
* @exception IOException if an I/O error occurs.
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
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;
}
lastTokenStart = lastTokenEnd;
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 7, but not 7 */
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;
}
/**
* Causes the next call to the {@code nextToken} method of this
* tokenizer to return the current value in the {@code ttype}
* field, and not to modify the value in the {@code nval} or
* {@code sval} field.
*
* @see java.io.StreamTokenizer#nextToken()
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
public void pushBack() {
if (ttype != TT_NOTHING) /* No-op if nextToken() not called */
pushedBack = true;
}
/**
* Return the current line number.
*
* @return the current line number of this stream tokenizer.
*/
public int lineno() {
return LINENO;
}
/**
* Returns the string representation of the current stream token and
* the line number it occurs on.
*
* <p>The precise string returned is unspecified, although the following
* example can be considered typical:
*
* <blockquote><pre>Token['a'], line 10</pre></blockquote>
*
* @return a string representation of the token
* @see java.io.StreamTokenizer#nval
* @see java.io.StreamTokenizer#sval
* @see java.io.StreamTokenizer#ttype
*/
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;
}
public long getLastTokenStart() {
return lastTokenStart;
}
public long getLastTokenEnd() {
return lastTokenEnd;
}
}