Home » openjdk-7 » com.sun.tools » javac » parser » [javadoc | source]

com.sun.tools.javac.parser
public class: Scanner [javadoc | source]

java.lang.Object
   com.sun.tools.javac.parser.Scanner

All Implemented Interfaces:
    Lexer

Direct Known Subclasses:
    DocCommentScanner

The lexical analyzer maps an input stream consisting of ASCII characters and Unicode escapes into a token sequence.

This is NOT part of any supported API. If you write code that depends on this, you do so at your own risk. This code and its internal interfaces are subject to change or deletion without notice.

Nested Class Summary:
public enum class	Scanner.CommentStyle

Field Summary
protected  boolean	deprecatedFlag	Has a @deprecated been encountered in last doc comment? this needs to be reset by client.
static final  boolean	surrogatesSupported	Are surrogates supported?

Constructor:
protected Scanner(ScannerFactory fac, CharBuffer buffer) { this(fac, JavacFileManager.toArray(buffer), buffer.limit()); } Create a scanner from the input buffer. buffer must implement array() and compact(), and remaining() must be less than limit().
protected Scanner(ScannerFactory fac, char[] input, int inputLength) { this(fac); eofPos = inputLength; if (inputLength == input.length) { if (input.length > 0 && Character.isWhitespace(input[input.length - 1])) { inputLength--; } else { char[] newInput = new char[inputLength + 1]; System.arraycopy(input, 0, newInput, 0, input.length); input = newInput; } } buf = input; buflen = inputLength; buf[buflen] = EOI; bp = -1; scanChar(); } Create a scanner from the input array. This method might modify the array. To avoid copying the input array, ensure that {@code inputLength < input.length} or {@code input[input.length -1]} is a white space character. Parameters: fac - the factory which created this Scanner input - the input, might be modified inputLength - the size of the input. Must be positive and less than or equal to input.length.

Method from com.sun.tools.javac.parser.Scanner Summary:
deprecatedFlag,   docComment,   endPos,   errPos,   errPos,   getLineMap,   getRawCharacters,   getRawCharacters,   name,   nextToken,   pos,   prevEndPos,   processComment,   processLineTerminator,   processWhiteSpace,   radix,   resetDeprecatedFlag,   stringVal,   token,   token

Methods from java.lang.Object:
clone,   equals,   finalize,   getClass,   hashCode,   notify,   notifyAll,   toString,   wait,   wait,   wait

Method from com.sun.tools.javac.parser.Scanner Detail:
public boolean deprecatedFlag() { return deprecatedFlag; } Has a @deprecated been encountered in last doc comment? This needs to be reset by client with resetDeprecatedFlag.
public String docComment() { return null; } Returns the documentation string of the current token.
public int endPos() { return endPos; } Return the last character position of the current token.
public int errPos() { return errPos; } Return the position where a lexical error occurred;
public void errPos(int pos) { errPos = pos; } Set the position where a lexical error occurred;
public LineMap getLineMap() { return Position.makeLineMap(buf, buflen, false); } Build a map for translating between line numbers and positions in the input.
public char[] getRawCharacters() { char[] chars = new char[buflen]; System.arraycopy(buf, 0, chars, 0, buflen); return chars; } Returns a copy of the input buffer, up to its inputLength. Unicode escape sequences are not translated.
public char[] getRawCharacters(int beginIndex, int endIndex) { int length = endIndex - beginIndex; char[] chars = new char[length]; System.arraycopy(buf, beginIndex, chars, 0, length); return chars; } Returns a copy of a character array subset of the input buffer. The returned array begins at the beginIndex and extends to the character at index endIndex - 1. Thus the length of the substring is endIndex-beginIndex. This behavior is like String.substring(beginIndex, endIndex). Unicode escape sequences are not translated.
public Name name() { return name; } Return the name of an identifier or token for the current token.
public void nextToken() { try { prevEndPos = endPos; sp = 0; while (true) { pos = bp; switch (ch) { case ' ': // (Spec 3.6) case '\t': // (Spec 3.6) case FF: // (Spec 3.6) do { scanChar(); } while (ch == ' ' || ch == '\t' || ch == FF); endPos = bp; processWhiteSpace(); break; case LF: // (Spec 3.4) scanChar(); endPos = bp; processLineTerminator(); break; case CR: // (Spec 3.4) scanChar(); if (ch == LF) { scanChar(); } endPos = bp; processLineTerminator(); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': case 'G': case 'H': case 'I': case 'J': case 'K': case 'L': case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': case 'S': case 'T': case 'U': case 'V': case 'W': case 'X': case 'Y': case 'Z': case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': case 'i': case 'j': case 'k': case 'l': case 'm': case 'n': case 'o': case 'p': case 'q': case 'r': case 's': case 't': case 'u': case 'v': case 'w': case 'x': case 'y': case 'z': case '$': case '_': scanIdent(); return; case '0': scanChar(); if (ch == 'x' || ch == 'X') { scanChar(); skipIllegalUnderscores(); if (ch == '.') { scanHexFractionAndSuffix(false); } else if (digit(16) < 0) { lexError("invalid.hex.number"); } else { scanNumber(16); } } else if (ch == 'b' || ch == 'B') { if (!allowBinaryLiterals) { lexError("unsupported.binary.lit", source.name); allowBinaryLiterals = true; } scanChar(); skipIllegalUnderscores(); if (digit(2) < 0) { lexError("invalid.binary.number"); } else { scanNumber(2); } } else { putChar('0'); if (ch == '_') { int savePos = bp; do { scanChar(); } while (ch == '_'); if (digit(10) < 0) { lexError(savePos, "illegal.underscore"); } } scanNumber(8); } return; case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': scanNumber(10); return; case '.': scanChar(); if ('0' < = ch && ch < = '9') { putChar('.'); scanFractionAndSuffix(); } else if (ch == '.') { putChar('.'); putChar('.'); scanChar(); if (ch == '.') { scanChar(); putChar('.'); token = ELLIPSIS; } else { lexError("malformed.fp.lit"); } } else { token = DOT; } return; case ',': scanChar(); token = COMMA; return; case ';': scanChar(); token = SEMI; return; case '(': scanChar(); token = LPAREN; return; case ')': scanChar(); token = RPAREN; return; case '[': scanChar(); token = LBRACKET; return; case ']': scanChar(); token = RBRACKET; return; case '{': scanChar(); token = LBRACE; return; case '}': scanChar(); token = RBRACE; return; case '/': scanChar(); if (ch == '/') { do { scanCommentChar(); } while (ch != CR && ch != LF && bp < buflen); if (bp < buflen) { endPos = bp; processComment(CommentStyle.LINE); } break; } else if (ch == '*') { scanChar(); CommentStyle style; if (ch == '*') { style = CommentStyle.JAVADOC; scanDocComment(); } else { style = CommentStyle.BLOCK; while (bp < buflen) { if (ch == '*') { scanChar(); if (ch == '/') break; } else { scanCommentChar(); } } } if (ch == '/') { scanChar(); endPos = bp; processComment(style); break; } else { lexError("unclosed.comment"); return; } } else if (ch == '=') { name = names.slashequals; token = SLASHEQ; scanChar(); } else { name = names.slash; token = SLASH; } return; case '\'': scanChar(); if (ch == '\'') { lexError("empty.char.lit"); } else { if (ch == CR || ch == LF) lexError(pos, "illegal.line.end.in.char.lit"); scanLitChar(); if (ch == '\'') { scanChar(); token = CHARLITERAL; } else { lexError(pos, "unclosed.char.lit"); } } return; case '\"': scanChar(); while (ch != '\"' && ch != CR && ch != LF && bp < buflen) scanLitChar(); if (ch == '\"') { token = STRINGLITERAL; scanChar(); } else { lexError(pos, "unclosed.str.lit"); } return; default: if (isSpecial(ch)) { scanOperator(); } else { boolean isJavaIdentifierStart; if (ch < '\u0080') { // all ASCII range chars already handled, above isJavaIdentifierStart = false; } else { char high = scanSurrogates(); if (high != 0) { if (sp == sbuf.length) { putChar(high); } else { sbuf[sp++] = high; } isJavaIdentifierStart = Character.isJavaIdentifierStart( Character.toCodePoint(high, ch)); } else { isJavaIdentifierStart = Character.isJavaIdentifierStart(ch); } } if (isJavaIdentifierStart) { scanIdent(); } else if (bp == buflen || ch == EOI && bp+1 == buflen) { // JLS 3.5 token = EOF; pos = bp = eofPos; } else { lexError("illegal.char", String.valueOf((int)ch)); scanChar(); } } return; } } } finally { endPos = bp; if (scannerDebug) System.out.println("nextToken(" + pos + "," + endPos + ")=|" + new String(getRawCharacters(pos, endPos)) + "|"); } } Read token.
public int pos() { return pos; } Return the current token's position: a 0-based offset from beginning of the raw input stream (before unicode translation)
public int prevEndPos() { return prevEndPos; } Return the last character position of the previous token.
protected void processComment(CommentStyle style) { if (scannerDebug) System.out.println("processComment(" + pos + "," + endPos + "," + style + ")=|" + new String(getRawCharacters(pos, endPos)) + "|"); } Called when a complete comment has been scanned. pos and endPos will mark the comment boundary.
protected void processLineTerminator() { if (scannerDebug) System.out.println("processTerminator(" + pos + "," + endPos + ")=|" + new String(getRawCharacters(pos, endPos)) + "|"); } Called when a line terminator has been processed.
protected void processWhiteSpace() { if (scannerDebug) System.out.println("processWhitespace(" + pos + "," + endPos + ")=|" + new String(getRawCharacters(pos, endPos)) + "|"); } Called when a complete whitespace run has been scanned. pos and endPos will mark the whitespace boundary.
public int radix() { return radix; } Return the radix of a numeric literal token.
public void resetDeprecatedFlag() { deprecatedFlag = false; }
public String stringVal() { return new String(sbuf, 0, sp); } The value of a literal token, recorded as a string. For integers, leading 0x and 'l' suffixes are suppressed.
public Token token() { return token; } Return the current token, set by nextToken().
public void token(Token token) { this.token = token; } Sets the current token.