Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(9)

Unified Diff: pkg/analyzer-experimental/lib/src/generated/html_scanner.dart

Issue 12502002: Update analyzer-experimental. (Closed) Base URL: https://dart.googlecode.com/svn/branches/bleeding_edge/dart
Patch Set: Created 7 years, 10 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
Index: pkg/analyzer-experimental/lib/src/generated/html_scanner.dart
diff --git a/pkg/analyzer-experimental/lib/src/generated/html_scanner.dart b/pkg/analyzer-experimental/lib/src/generated/html_scanner.dart
new file mode 100644
index 0000000000000000000000000000000000000000..fa9a3c176ac20716c638e3cda36b48739a123c6f
--- /dev/null
+++ b/pkg/analyzer-experimental/lib/src/generated/html_scanner.dart
@@ -0,0 +1,1261 @@
+// This code was auto-generated, is not intended to be edited, and is subject to
+// significant change. Please see the README file for more information.
+
+library engine.html.scanner;
+
+import 'dart:collection';
+import 'java_core.dart';
+import 'source.dart';
+import 'error.dart';
+import 'instrumentation.dart';
+
+/**
+ * Instances of the class {@code Token} represent a token that was scanned from the input. Each
+ * token knows which token follows it, acting as the head of a linked list of tokens.
+ */
+class Token {
+ /**
+ * The offset from the beginning of the file to the first character in the token.
+ */
+ int _offset = 0;
+ /**
+ * The previous token in the token stream.
+ */
+ Token _previous;
+ /**
+ * The next token in the token stream.
+ */
+ Token _next;
+ /**
+ * The type of the token.
+ */
+ TokenType _type;
+ /**
+ * The lexeme represented by this token.
+ */
+ String _value;
+ /**
+ * Initialize a newly created token.
+ * @param type the token type (not {@code null})
+ * @param offset the offset from the beginning of the file to the first character in the token
+ */
+ Token.con1(TokenType type, int offset) {
+ _jtd_constructor_143_impl(type, offset);
+ }
+ _jtd_constructor_143_impl(TokenType type, int offset) {
+ _jtd_constructor_144_impl(type, offset, type.lexeme);
+ }
+ /**
+ * Initialize a newly created token.
+ * @param type the token type (not {@code null})
+ * @param offset the offset from the beginning of the file to the first character in the token
+ * @param value the lexeme represented by this token (not {@code null})
+ */
+ Token.con2(TokenType type4, int offset3, String value7) {
+ _jtd_constructor_144_impl(type4, offset3, value7);
+ }
+ _jtd_constructor_144_impl(TokenType type4, int offset3, String value7) {
+ this._type = type4;
+ this._value = value7;
+ this._offset = offset3;
+ }
+ /**
+ * Return the offset from the beginning of the file to the character after last character of the
+ * token.
+ * @return the offset from the beginning of the file to the first character after last character
+ * of the token
+ */
+ int get end => _offset + length;
+ /**
+ * Return the number of characters in the node's source range.
+ * @return the number of characters in the node's source range
+ */
+ int get length => lexeme.length;
+ /**
+ * Return the lexeme that represents this token.
+ * @return the lexeme (not {@code null})
+ */
+ String get lexeme => _value;
+ /**
+ * Return the next token in the token stream.
+ * @return the next token in the token stream
+ */
+ Token get next => _next;
+ /**
+ * Return the offset from the beginning of the file to the first character in the token.
+ * @return the offset from the beginning of the file to the first character in the token
+ */
+ int get offset => _offset;
+ /**
+ * Return the previous token in the token stream.
+ * @return the previous token in the token stream
+ */
+ Token get previous => _previous;
+ /**
+ * Answer the token type for the receiver.
+ * @return the token type (not {@code null})
+ */
+ TokenType get type => _type;
+ /**
+ * Return {@code true} if this token is a synthetic token. A synthetic token is a token that was
+ * introduced by the parser in order to recover from an error in the code. Synthetic tokens always
+ * have a length of zero ({@code 0}).
+ * @return {@code true} if this token is a synthetic token
+ */
+ bool isSynthetic() => length == 0;
+ /**
+ * Set the next token in the token stream to the given token. This has the side-effect of setting
+ * this token to be the previous token for the given token.
+ * @param token the next token in the token stream
+ * @return the token that was passed in
+ */
+ Token setNext(Token token) {
+ _next = token;
+ token.previous = this;
+ return token;
+ }
+ String toString() => lexeme;
+ /**
+ * Set the previous token in the token stream to the given token.
+ * @param previous the previous token in the token stream
+ */
+ void set previous(Token previous2) {
+ this._previous = previous2;
+ }
+}
+/**
+ * Instances of {@code HtmlParseResult} hold the result of parsing an HTML file.
+ */
+class HtmlParseResult extends HtmlScanResult {
+ /**
+ * The unit containing the parsed information (not {@code null}).
+ */
+ HtmlUnit _unit;
+ HtmlParseResult(Token token, List<int> lineStarts, HtmlUnit unit) : super(token, lineStarts) {
+ this._unit = unit;
+ }
+ /**
+ * Answer the unit generated by parsing the source
+ * @return the unit (not {@code null})
+ */
+ HtmlUnit get htmlUnit => _unit;
+}
+/**
+ * Instances of the class {@code RecursiveXmlVisitor} implement an XML visitor that will recursively
+ * visit all of the nodes in an XML structure. For example, using an instance of this class to visit
+ * a {@link XmlTagNode} will also cause all of the contained {@link XmlAttributeNode}s and{@link XmlTagNode}s to be visited.
+ * <p>
+ * Subclasses that override a visit method must either invoke the overridden visit method or must
+ * explicitly ask the visited node to visit its children. Failure to do so will cause the children
+ * of the visited node to not be visited.
+ */
+class RecursiveXmlVisitor<R> implements XmlVisitor<R> {
+ R visitHtmlUnit(HtmlUnit node) {
+ node.visitChildren(this);
+ return null;
+ }
+ R visitXmlAttributeNode(XmlAttributeNode node) {
+ node.visitChildren(this);
+ return null;
+ }
+ R visitXmlTagNode(XmlTagNode node) {
+ node.visitChildren(this);
+ return null;
+ }
+}
+/**
+ * The abstract class {@code XmlNode} defines behavior common to all XML/HTML nodes.
+ */
+abstract class XmlNode {
+ /**
+ * The parent of the node, or {@code null} if the node is the root of an AST structure.
+ */
+ XmlNode _parent;
+ /**
+ * Use the given visitor to visit this node.
+ * @param visitor the visitor that will visit this node
+ * @return the value returned by the visitor as a result of visiting this node
+ */
+ accept(XmlVisitor visitor);
+ /**
+ * Return the first token included in this node's source range.
+ * @return the first token or {@code null} if none
+ */
+ Token get beginToken;
+ /**
+ * Return the offset of the character immediately following the last character of this node's
+ * source range. This is equivalent to {@code node.getOffset() + node.getLength()}. For an html
+ * unit this will be equal to the length of the unit's source.
+ * @return the offset of the character just past the node's source range
+ */
+ int get end => offset + length;
+ /**
+ * Return the last token included in this node's source range.
+ * @return the last token or {@code null} if none
+ */
+ Token get endToken;
+ /**
+ * Return the number of characters in the node's source range.
+ * @return the number of characters in the node's source range
+ */
+ int get length {
+ Token beginToken5 = beginToken;
+ Token endToken4 = endToken;
+ if (beginToken5 == null || endToken4 == null) {
+ return -1;
+ }
+ return endToken4.offset + endToken4.length - beginToken5.offset;
+ }
+ /**
+ * Return the offset from the beginning of the file to the first character in the node's source
+ * range.
+ * @return the offset from the beginning of the file to the first character in the node's source
+ * range
+ */
+ int get offset {
+ Token beginToken6 = beginToken;
+ if (beginToken6 == null) {
+ return -1;
+ }
+ return beginToken.offset;
+ }
+ /**
+ * Return this node's parent node, or {@code null} if this node is the root of an AST structure.
+ * <p>
+ * Note that the relationship between an AST node and its parent node may change over the lifetime
+ * of a node.
+ * @return the parent of this node, or {@code null} if none
+ */
+ XmlNode get parent => _parent;
+ /**
+ * Use the given visitor to visit all of the children of this node. The children will be visited
+ * in source order.
+ * @param visitor the visitor that will be used to visit the children of this node
+ */
+ void visitChildren(XmlVisitor<Object> visitor);
+ /**
+ * Make this node the parent of the given child nodes.
+ * @param children the nodes that will become the children of this node
+ * @return the nodes that were made children of this node
+ */
+ List<XmlNode> becomeParentOf(List<XmlNode> children) {
+ if (children != null) {
+ for (JavaIterator<XmlNode> iter = new JavaIterator(children); iter.hasNext;) {
+ XmlNode node = iter.next();
+ node.parent = this;
+ }
+ }
+ return children;
+ }
+ /**
+ * Make this node the parent of the given child node.
+ * @param child the node that will become a child of this node
+ * @return the node that was made a child of this node
+ */
+ XmlNode becomeParentOf2(XmlNode child) {
+ if (child != null) {
+ XmlNode node = child;
+ node.parent = this;
+ }
+ return child;
+ }
+ /**
+ * Set the parent of this node to the given node.
+ * @param newParent the node that is to be made the parent of this node
+ */
+ void set parent(XmlNode newParent) {
+ _parent = newParent;
+ }
+}
+/**
+ * The abstract class {@code AbstractScanner} implements a scanner for HTML code. Subclasses are
+ * required to implement the interface used to access the characters being scanned.
+ */
+abstract class AbstractScanner {
+ static List<String> _NO_PASS_THROUGH_ELEMENTS = <String> [];
+ /**
+ * The source being scanned.
+ */
+ Source _source;
+ /**
+ * The token pointing to the head of the linked list of tokens.
+ */
+ Token _tokens;
+ /**
+ * The last token that was scanned.
+ */
+ Token _tail;
+ /**
+ * A list containing the offsets of the first character of each line in the source code.
+ */
+ List<int> _lineStarts = new List<int>();
+ /**
+ * An array of element tags for which the content between tags should be consider a single token.
+ */
+ List<String> _passThroughElements = _NO_PASS_THROUGH_ELEMENTS;
+ /**
+ * Initialize a newly created scanner.
+ * @param source the source being scanned
+ */
+ AbstractScanner(Source source) {
+ this._source = source;
+ _tokens = new Token.con1(TokenType.EOF, -1);
+ _tokens.setNext(_tokens);
+ _tail = _tokens;
+ recordStartOfLine();
+ }
+ /**
+ * Return an array containing the offsets of the first character of each line in the source code.
+ * @return an array containing the offsets of the first character of each line in the source code
+ */
+ List<int> get lineStarts => _lineStarts;
+ /**
+ * Return the current offset relative to the beginning of the file. Return the initial offset if
+ * the scanner has not yet scanned the source code, and one (1) past the end of the source code if
+ * the source code has been scanned.
+ * @return the current offset of the scanner in the source
+ */
+ int get offset;
+ /**
+ * Answer the source being scanned.
+ * @return the source or {@code null} if undefined
+ */
+ Source get source => _source;
+ /**
+ * Set array of element tags for which the content between tags should be consider a single token.
+ */
+ void set passThroughElements(List<String> passThroughElements2) {
+ this._passThroughElements = passThroughElements2 != null ? passThroughElements2 : _NO_PASS_THROUGH_ELEMENTS;
+ }
+ /**
+ * Scan the source code to produce a list of tokens representing the source.
+ * @return the first token in the list of tokens that were produced
+ */
+ Token tokenize() {
+ scan();
+ appendEofToken();
+ return firstToken();
+ }
+ /**
+ * Advance the current position and return the character at the new current position.
+ * @return the character at the new current position
+ */
+ int advance();
+ /**
+ * Return the substring of the source code between the start offset and the modified current
+ * position. The current position is modified by adding the end delta.
+ * @param start the offset to the beginning of the string, relative to the start of the file
+ * @param endDelta the number of character after the current location to be included in the
+ * string, or the number of characters before the current location to be excluded if the
+ * offset is negative
+ * @return the specified substring of the source code
+ */
+ String getString(int start, int endDelta);
+ /**
+ * Return the character at the current position without changing the current position.
+ * @return the character at the current position
+ */
+ int peek();
+ /**
+ * Record the fact that we are at the beginning of a new line in the source.
+ */
+ void recordStartOfLine() {
+ _lineStarts.add(offset);
+ }
+ void appendEofToken() {
+ Token eofToken = new Token.con1(TokenType.EOF, offset);
+ eofToken.setNext(eofToken);
+ _tail = _tail.setNext(eofToken);
+ }
+ Token emit(Token token) {
+ _tail.setNext(token);
+ _tail = token;
+ return token;
+ }
+ Token emit2(TokenType type, int start) => emit(new Token.con1(type, start));
+ Token emit3(TokenType type, int start, int count) => emit(new Token.con2(type, start, getString(start, count)));
+ Token firstToken() => _tokens.next;
+ int recordStartOfLineAndAdvance(int c) {
+ if (c == 0xD) {
+ c = advance();
+ if (c == 0xA) {
+ c = advance();
+ }
+ recordStartOfLine();
+ } else if (c == 0xA) {
+ c = advance();
+ recordStartOfLine();
+ } else {
+ c = advance();
+ }
+ return c;
+ }
+ void scan() {
+ bool inBrackets = false;
+ bool passThrough = false;
+ int c = advance();
+ while (c >= 0) {
+ int start = offset;
+ if (c == 0x3C) {
+ c = advance();
+ if (c == 0x21) {
+ c = advance();
+ if (c == 0x2D && peek() == 0x2D) {
+ c = advance();
+ int dashCount = 1;
+ while (c >= 0) {
+ if (c == 0x2D) {
+ dashCount++;
+ } else if (c == 0x3E && dashCount >= 2) {
+ c = advance();
+ break;
+ } else {
+ dashCount = 0;
+ }
+ c = recordStartOfLineAndAdvance(c);
+ }
+ emit3(TokenType.COMMENT, start, -1);
+ if (_tail.length < 7) {
+ }
+ } else {
+ while (c >= 0) {
+ if (c == 0x3E) {
+ c = advance();
+ break;
+ }
+ c = recordStartOfLineAndAdvance(c);
+ }
+ emit3(TokenType.DECLARATION, start, -1);
+ if (!_tail.lexeme.endsWith(">")) {
+ }
+ }
+ } else if (c == 0x3F) {
+ while (c >= 0) {
+ if (c == 0x3F) {
+ c = advance();
+ if (c == 0x3E) {
+ c = advance();
+ break;
+ }
+ } else {
+ c = recordStartOfLineAndAdvance(c);
+ }
+ }
+ emit3(TokenType.DIRECTIVE, start, -1);
+ if (_tail.length < 4) {
+ }
+ } else if (c == 0x2F) {
+ emit2(TokenType.LT_SLASH, start);
+ inBrackets = true;
+ c = advance();
+ } else {
+ inBrackets = true;
+ emit2(TokenType.LT, start);
+ while (Character.isWhitespace(c)) {
+ c = recordStartOfLineAndAdvance(c);
+ }
+ if (Character.isLetterOrDigit(c)) {
+ int tagStart = offset;
+ c = advance();
+ while (Character.isLetterOrDigit(c) || c == 0x2D || c == 0x5F) {
+ c = advance();
+ }
+ emit3(TokenType.TAG, tagStart, -1);
+ String tag = _tail.lexeme;
+ for (String str in _passThroughElements) {
+ if (str == tag) {
+ passThrough = true;
+ break;
+ }
+ }
+ }
+ }
+ } else if (c == 0x3E) {
+ emit2(TokenType.GT, start);
+ inBrackets = false;
+ c = advance();
+ if (passThrough) {
+ while (c >= 0 && (c != 0x3C || peek() != 0x2F)) {
+ c = recordStartOfLineAndAdvance(c);
+ }
+ if (start + 1 < offset) {
+ emit3(TokenType.TEXT, start + 1, -1);
+ }
+ passThrough = false;
+ }
+ } else if (c == 0x2F && peek() == 0x3E) {
+ advance();
+ emit2(TokenType.SLASH_GT, start);
+ inBrackets = false;
+ c = advance();
+ } else if (!inBrackets) {
+ c = recordStartOfLineAndAdvance(c);
+ while (c != 0x3C && c >= 0) {
+ c = recordStartOfLineAndAdvance(c);
+ }
+ emit3(TokenType.TEXT, start, -1);
+ } else if (c == 0x22 || c == 0x27) {
+ int endQuote = c;
+ c = advance();
+ while (c >= 0) {
+ if (c == endQuote) {
+ c = advance();
+ break;
+ }
+ c = recordStartOfLineAndAdvance(c);
+ }
+ emit3(TokenType.STRING, start, -1);
+ } else if (c == 0x3D) {
+ emit2(TokenType.EQ, start);
+ c = advance();
+ } else if (Character.isWhitespace(c)) {
+ do {
+ c = recordStartOfLineAndAdvance(c);
+ } while (Character.isWhitespace(c));
+ } else if (Character.isLetterOrDigit(c)) {
+ c = advance();
+ while (Character.isLetterOrDigit(c) || c == 0x2D || c == 0x5F) {
+ c = advance();
+ }
+ emit3(TokenType.TAG, start, -1);
+ } else {
+ emit3(TokenType.TEXT, start, 0);
+ c = advance();
+ }
+ }
+ }
+}
+/**
+ * Instances of {@code HtmlScanResult} hold the result of scanning an HTML file.
+ */
+class HtmlScanResult {
+ /**
+ * The first token in the token stream (not {@code null}).
+ */
+ Token _token;
+ /**
+ * The line start information that was produced.
+ */
+ List<int> _lineStarts;
+ HtmlScanResult(Token token, List<int> lineStarts) {
+ this._token = token;
+ this._lineStarts = lineStarts;
+ }
+ /**
+ * Answer the line start information that was produced.
+ * @return an array of line starts (not {@code null})
+ */
+ List<int> get lineStarts => _lineStarts;
+ /**
+ * Answer the first token in the token stream.
+ * @return the token (not {@code null})
+ */
+ Token get token => _token;
+}
+/**
+ * Instances of the class {@code StringScanner} implement a scanner that reads from a string. The
+ * scanning logic is in the superclass.
+ */
+class StringScanner extends AbstractScanner {
+ /**
+ * The string from which characters will be read.
+ */
+ String _string;
+ /**
+ * The number of characters in the string.
+ */
+ int _stringLength = 0;
+ /**
+ * The index, relative to the string, of the last character that was read.
+ */
+ int _charOffset = 0;
+ /**
+ * Initialize a newly created scanner to scan the characters in the given string.
+ * @param source the source being scanned
+ * @param string the string from which characters will be read
+ */
+ StringScanner(Source source, String string) : super(source) {
+ this._string = string;
+ this._stringLength = string.length;
+ this._charOffset = -1;
+ }
+ int get offset => _charOffset;
+ void set offset(int offset12) {
+ _charOffset = offset12;
+ }
+ int advance() {
+ if (++_charOffset < _stringLength) {
+ return _string.codeUnitAt(_charOffset);
+ }
+ _charOffset = _stringLength;
+ return -1;
+ }
+ String getString(int start, int endDelta) => _string.substring(start, _charOffset + 1 + endDelta);
+ int peek() {
+ if (_charOffset + 1 < _stringLength) {
+ return _string.codeUnitAt(_charOffset + 1);
+ }
+ return -1;
+ }
+}
+/**
+ * Instances of the class {@code CharBufferScanner} implement a scanner that reads from a character
+ * buffer. The scanning logic is in the superclass.
+ */
+class CharBufferScanner extends AbstractScanner {
+ /**
+ * The buffer from which characters will be read.
+ */
+ CharBuffer _buffer;
+ /**
+ * The number of characters in the buffer.
+ */
+ int _bufferLength = 0;
+ /**
+ * The index of the last character that was read.
+ */
+ int _charOffset = 0;
+ /**
+ * Initialize a newly created scanner to scan the characters in the given character buffer.
+ * @param source the source being scanned
+ * @param buffer the buffer from which characters will be read
+ */
+ CharBufferScanner(Source source, CharBuffer buffer) : super(source) {
+ this._buffer = buffer;
+ this._bufferLength = buffer.length();
+ this._charOffset = -1;
+ }
+ int get offset => _charOffset;
+ int advance() {
+ if (++_charOffset < _bufferLength) {
+ return _buffer.charAt(_charOffset);
+ }
+ _charOffset = _bufferLength;
+ return -1;
+ }
+ String getString(int start, int endDelta) => _buffer.subSequence(start, _charOffset + 1 + endDelta).toString();
+ int peek() {
+ if (_charOffset + 1 < _bufferLength) {
+ return _buffer.charAt(_charOffset + 1);
+ }
+ return -1;
+ }
+}
+/**
+ * The enumeration {@code TokenType} defines the types of tokens that can be returned by the
+ * scanner.
+ */
+class TokenType {
+ /**
+ * The type of the token that marks the end of the input.
+ */
+ static final TokenType EOF = new TokenType_EOF('EOF', 0, "");
+ static final TokenType EQ = new TokenType('EQ', 1, "=");
+ static final TokenType GT = new TokenType('GT', 2, ">");
+ static final TokenType LT_SLASH = new TokenType('LT_SLASH', 3, "</");
+ static final TokenType LT = new TokenType('LT', 4, "<");
+ static final TokenType SLASH_GT = new TokenType('SLASH_GT', 5, "/>");
+ static final TokenType COMMENT = new TokenType('COMMENT', 6, null);
+ static final TokenType DECLARATION = new TokenType('DECLARATION', 7, null);
+ static final TokenType DIRECTIVE = new TokenType('DIRECTIVE', 8, null);
+ static final TokenType STRING = new TokenType('STRING', 9, null);
+ static final TokenType TAG = new TokenType('TAG', 10, null);
+ static final TokenType TEXT = new TokenType('TEXT', 11, null);
+ static final List<TokenType> values = [EOF, EQ, GT, LT_SLASH, LT, SLASH_GT, COMMENT, DECLARATION, DIRECTIVE, STRING, TAG, TEXT];
+ final String __name;
+ final int __ordinal;
+ /**
+ * The lexeme that defines this type of token, or {@code null} if there is more than one possible
+ * lexeme for this type of token.
+ */
+ String _lexeme;
+ TokenType(this.__name, this.__ordinal, String lexeme) {
+ this._lexeme = lexeme;
+ }
+ /**
+ * Return the lexeme that defines this type of token, or {@code null} if there is more than one
+ * possible lexeme for this type of token.
+ * @return the lexeme that defines this type of token
+ */
+ String get lexeme => _lexeme;
+ String toString() => __name;
+}
+class TokenType_EOF extends TokenType {
+ TokenType_EOF(String ___name, int ___ordinal, String arg0) : super(___name, ___ordinal, arg0);
+ String toString() => "-eof-";
+}
+/**
+ * Instances of {@code XmlAttributeNode} represent name/value pairs owned by an {@link XmlTagNode}.
+ */
+class XmlAttributeNode extends XmlNode {
+ Token _name;
+ Token _equals;
+ Token _value;
+ /**
+ * Construct a new instance representing an XML attribute.
+ * @param name the name token (not {@code null}). This may be a zero length token if the attribute
+ * is badly formed.
+ * @param equals the equals sign or {@code null} if none
+ * @param value the value token (not {@code null})
+ */
+ XmlAttributeNode(Token name, Token equals, Token value) {
+ this._name = name;
+ this._equals = equals;
+ this._value = value;
+ }
+ accept(XmlVisitor visitor) => visitor.visitXmlAttributeNode(this);
+ Token get beginToken => _name;
+ Token get endToken => _value;
+ /**
+ * Answer the equals sign token that appears between the name and value tokens. This may be{@code null} if the attribute is badly formed.
+ * @return the token or {@code null} if there is no equals sign between the name and value
+ */
+ Token get equals => _equals;
+ /**
+ * Answer the attribute name. This may be a zero length token if the attribute is badly formed.
+ * @return the name (not {@code null})
+ */
+ Token get name => _name;
+ /**
+ * Answer the attribute value. A properly formed value will start and end with matching quote
+ * characters, but the value returned may not be properly formed.
+ * @return the value or {@code null} if this represents a badly formed attribute
+ */
+ Token get value => _value;
+ void visitChildren(XmlVisitor<Object> visitor) {
+ }
+}
+/**
+ * The interface {@code XmlVisitor} defines the behavior of objects that can be used to visit an{@link XmlNode} structure.
+ */
+abstract class XmlVisitor<R> {
+ R visitHtmlUnit(HtmlUnit htmlUnit);
+ R visitXmlAttributeNode(XmlAttributeNode xmlAttributeNode);
+ R visitXmlTagNode(XmlTagNode xmlTagNode);
+}
+/**
+ * Instances of {@code HtmlScanner} receive and scan HTML content from a {@link Source}.<br/>
+ * For example, the following code scans HTML source and returns the result:
+ * <pre>
+ * HtmlScanner scanner = new HtmlScanner(source);
+ * source.getContents(scanner);
+ * return scanner.getResult();
+ * </pre>
+ */
+class HtmlScanner implements Source_ContentReceiver {
+ List<String> _SCRIPT_TAG = <String> ["script"];
+ /**
+ * The source being scanned (not {@code null})
+ */
+ Source _source;
+ /**
+ * The scanner used to scan the source
+ */
+ AbstractScanner _scanner;
+ /**
+ * The first token in the token stream.
+ */
+ Token _token;
+ /**
+ * Construct a new instance to scan the specified source.
+ * @param source the source to be scanned (not {@code null})
+ */
+ HtmlScanner(Source source) {
+ this._source = source;
+ }
+ accept(CharBuffer contents) {
+ _scanner = new CharBufferScanner(_source, contents);
+ _scanner.passThroughElements = _SCRIPT_TAG;
+ _token = _scanner.tokenize();
+ }
+ void accept2(String contents) {
+ _scanner = new StringScanner(_source, contents);
+ _scanner.passThroughElements = _SCRIPT_TAG;
+ _token = _scanner.tokenize();
+ }
+ /**
+ * Answer the result of scanning the source
+ * @return the result (not {@code null})
+ */
+ HtmlScanResult get result => new HtmlScanResult(_token, _scanner.lineStarts);
+}
+/**
+ * Instances of the class {@code XmlParser} are used to parse tokens into a AST structure comprised
+ * of {@link XmlNode}s.
+ */
+class XmlParser {
+ /**
+ * The source being parsed.
+ */
+ Source _source;
+ /**
+ * The next token to be parsed.
+ */
+ Token _currentToken;
+ /**
+ * Construct a parser for the specified source.
+ * @param source the source being parsed
+ */
+ XmlParser(Source source) {
+ this._source = source;
+ }
+ /**
+ * Answer the source being parsed.
+ * @return the source
+ */
+ Source get source => _source;
+ /**
+ * Answer {@code true} if the specified tag is self closing and thus should never have content or
+ * child tag nodes.
+ * @param tag the tag (not {@code null})
+ * @return {@code true} if self closing
+ */
+ bool isSelfClosing(Token tag) => false;
+ /**
+ * Parse the entire token stream and in the process, advance the current token to the end of the
+ * token stream.
+ * @return the list of tag nodes found (not {@code null}, contains no {@code null})
+ */
+ List<XmlTagNode> parseTopTagNodes(Token firstToken) {
+ _currentToken = firstToken;
+ List<XmlTagNode> tagNodes = new List<XmlTagNode>();
+ while (true) {
+ while (true) {
+ if (_currentToken.type == TokenType.LT) {
+ tagNodes.add(parseTagNode());
+ } else if (_currentToken.type == TokenType.DECLARATION || _currentToken.type == TokenType.DIRECTIVE || _currentToken.type == TokenType.COMMENT) {
+ _currentToken = _currentToken.next;
+ } else if (_currentToken.type == TokenType.EOF) {
+ return tagNodes;
+ } else {
+ reportUnexpectedToken();
+ _currentToken = _currentToken.next;
+ }
+ break;
+ }
+ }
+ }
+ /**
+ * Answer the current token.
+ * @return the current token
+ */
+ Token get currentToken => _currentToken;
+ /**
+ * Insert a synthetic token of the specified type before the current token
+ * @param type the type of token to be inserted (not {@code null})
+ * @return the synthetic token that was inserted (not {@code null})
+ */
+ Token insertSyntheticToken(TokenType type) {
+ Token token = new Token.con2(type, _currentToken.offset, "");
+ _currentToken.previous.setNext(token);
+ token.setNext(_currentToken);
+ return token;
+ }
+ /**
+ * Parse the token stream for an attribute. This method advances the current token over the
+ * attribute, but should not be called if the {@link #currentToken} is not {@link TokenType#TAG}.
+ * @return the attribute (not {@code null})
+ */
+ XmlAttributeNode parseAttribute() {
+ Token name = _currentToken;
+ _currentToken = _currentToken.next;
+ Token equals;
+ if (identical(_currentToken.type, TokenType.EQ)) {
+ equals = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ equals = insertSyntheticToken(TokenType.EQ);
+ }
+ Token value;
+ if (identical(_currentToken.type, TokenType.STRING)) {
+ value = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ value = insertSyntheticToken(TokenType.STRING);
+ }
+ return new XmlAttributeNode(name, equals, value);
+ }
+ /**
+ * Parse the stream for a sequence of attributes. This method advances the current token to the
+ * next {@link TokenType#GT}, {@link TokenType#SLASH_GT}, or {@link TokenType#EOF}.
+ * @return a collection of zero or more attributes (not {@code null}, contains no {@code null}s)
+ */
+ List<XmlAttributeNode> parseAttributes() {
+ TokenType type11 = _currentToken.type;
+ if (identical(type11, TokenType.GT) || identical(type11, TokenType.SLASH_GT) || identical(type11, TokenType.EOF)) {
+ return XmlTagNode.NO_ATTRIBUTES;
+ }
+ List<XmlAttributeNode> attributes = new List<XmlAttributeNode>();
+ while (true) {
+ while (true) {
+ if (_currentToken.type == TokenType.GT || _currentToken.type == TokenType.SLASH_GT || _currentToken.type == TokenType.EOF) {
+ return attributes;
+ } else if (_currentToken.type == TokenType.TAG) {
+ attributes.add(parseAttribute());
+ } else {
+ reportUnexpectedToken();
+ _currentToken = _currentToken.next;
+ }
+ break;
+ }
+ }
+ }
+ /**
+ * Parse the stream for a sequence of tag nodes existing within a parent tag node. This method
+ * advances the current token to the next {@link TokenType#LT_SLASH} or {@link TokenType#EOF}.
+ * @return a list of nodes (not {@code null}, contains no {@code null}s)
+ */
+ List<XmlTagNode> parseChildTagNodes() {
+ TokenType type12 = _currentToken.type;
+ if (identical(type12, TokenType.LT_SLASH) || identical(type12, TokenType.EOF)) {
+ return XmlTagNode.NO_TAG_NODES;
+ }
+ List<XmlTagNode> nodes = new List<XmlTagNode>();
+ while (true) {
+ while (true) {
+ if (_currentToken.type == TokenType.LT) {
+ nodes.add(parseTagNode());
+ } else if (_currentToken.type == TokenType.LT_SLASH || _currentToken.type == TokenType.EOF) {
+ return nodes;
+ } else if (_currentToken.type == TokenType.COMMENT) {
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ _currentToken = _currentToken.next;
+ }
+ break;
+ }
+ }
+ }
+ /**
+ * Parse the token stream for the next tag node. This method advances current token over the
+ * parsed tag node, but should only be called if the current token is {@link TokenType#LT}
+ * @return the tag node or {@code null} if none found
+ */
+ XmlTagNode parseTagNode() {
+ Token nodeStart = _currentToken;
+ _currentToken = _currentToken.next;
+ Token tag;
+ if (identical(_currentToken.type, TokenType.TAG)) {
+ tag = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ tag = insertSyntheticToken(TokenType.TAG);
+ }
+ List<XmlAttributeNode> attributes = parseAttributes();
+ Token attributeEnd;
+ if (identical(_currentToken.type, TokenType.GT) || identical(_currentToken.type, TokenType.SLASH_GT)) {
+ attributeEnd = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ attributeEnd = insertSyntheticToken(TokenType.SLASH_GT);
+ }
+ if (identical(attributeEnd.type, TokenType.SLASH_GT) || isSelfClosing(tag)) {
+ return new XmlTagNode(nodeStart, tag, attributes, attributeEnd, XmlTagNode.NO_TAG_NODES, _currentToken, null, attributeEnd);
+ }
+ List<XmlTagNode> tagNodes = parseChildTagNodes();
+ Token contentEnd;
+ if (identical(_currentToken.type, TokenType.LT_SLASH)) {
+ contentEnd = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ contentEnd = insertSyntheticToken(TokenType.LT_SLASH);
+ }
+ Token closingTag;
+ if (identical(_currentToken.type, TokenType.TAG)) {
+ closingTag = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ closingTag = insertSyntheticToken(TokenType.TAG);
+ }
+ Token nodeEnd;
+ if (identical(_currentToken.type, TokenType.GT)) {
+ nodeEnd = _currentToken;
+ _currentToken = _currentToken.next;
+ } else {
+ reportUnexpectedToken();
+ nodeEnd = insertSyntheticToken(TokenType.GT);
+ }
+ return new XmlTagNode(nodeStart, tag, attributes, attributeEnd, tagNodes, contentEnd, closingTag, nodeEnd);
+ }
+ /**
+ * Report the current token as unexpected
+ */
+ void reportUnexpectedToken() {
+ }
+}
+/**
+ * Instances of {@code XmlTagNode} represent XML or HTML elements such as {@code <p>} and{@code <body foo="bar"> ... </body>}.
+ */
+class XmlTagNode extends XmlNode {
+ /**
+ * Constant representing empty list of attributes.
+ */
+ static List<XmlAttributeNode> NO_ATTRIBUTES = new UnmodifiableListView(new List<XmlAttributeNode>());
+ /**
+ * Constant representing empty list of tag nodes.
+ */
+ static List<XmlTagNode> NO_TAG_NODES = new UnmodifiableListView(new List<XmlTagNode>());
+ /**
+ * The starting {@link TokenType#LT} token (not {@code null}).
+ */
+ Token _nodeStart;
+ /**
+ * The {@link TokenType#TAG} token after the starting '&lt;' (not {@code null}).
+ */
+ Token _tag;
+ /**
+ * The attributes contained by the receiver (not {@code null}, contains no {@code null}s).
+ */
+ List<XmlAttributeNode> _attributes;
+ /**
+ * The {@link TokenType#GT} or {@link TokenType#SLASH_GT} token after the attributes (not{@code null}). The token may be the same token as {@link #nodeEnd} if there are no child{@link #tagNodes}.
+ */
+ Token _attributeEnd;
+ /**
+ * The tag nodes contained in the receiver (not {@code null}, contains no {@code null}s).
+ */
+ List<XmlTagNode> _tagNodes;
+ /**
+ * The token (not {@code null}) after the content, which may be
+ * <ul>
+ * <li>(1) {@link TokenType#LT_SLASH} for nodes with open and close tags, or</li>
+ * <li>(2) the {@link TokenType#LT} nodeStart of the next sibling node if this node is self
+ * closing or the attributeEnd is {@link TokenType#SLASH_GT}, or</li>
+ * <li>(3) {@link TokenType#EOF} if the node does not have a closing tag and is the last node in
+ * the stream {@link TokenType#LT_SLASH} token after the content, or {@code null} if there is no
+ * content and the attributes ended with {@link TokenType#SLASH_GT}.</li>
+ * </ul>
+ */
+ Token _contentEnd;
+ /**
+ * The closing {@link TokenType#TAG} after the child elements or {@code null} if there is no
+ * content and the attributes ended with {@link TokenType#SLASH_GT}
+ */
+ Token _closingTag;
+ /**
+ * The ending {@link TokenType#GT} or {@link TokenType#SLASH_GT} token (not {@code null}).
+ */
+ Token _nodeEnd;
+ /**
+ * Construct a new instance representing an XML or HTML element
+ * @param nodeStart the starting {@link TokenType#LT} token (not {@code null})
+ * @param tag the {@link TokenType#TAG} token after the starting '&lt;' (not {@code null}).
+ * @param attributes the attributes associated with this element or {@link #NO_ATTRIBUTES} (not{@code null}, contains no {@code null}s)
+ * @param attributeEnd The {@link TokenType#GT} or {@link TokenType#SLASH_GT} token after the
+ * attributes (not {@code null}). The token may be the same token as {@link #nodeEnd} if
+ * there are no child {@link #tagNodes}.
+ * @param tagNodes child tag nodes of the receiver or {@link #NO_TAG_NODES} (not {@code null},
+ * contains no {@code null}s)
+ * @param contentEnd the token (not {@code null}) after the content, which may be
+ * <ul>
+ * <li>(1) {@link TokenType#LT_SLASH} for nodes with open and close tags, or</li>
+ * <li>(2) the {@link TokenType#LT} nodeStart of the next sibling node if this node is
+ * self closing or the attributeEnd is {@link TokenType#SLASH_GT}, or</li>
+ * <li>(3) {@link TokenType#EOF} if the node does not have a closing tag and is the last
+ * node in the stream {@link TokenType#LT_SLASH} token after the content, or {@code null}if there is no content and the attributes ended with {@link TokenType#SLASH_GT}.</li>
+ * </ul>
+ * @param closingTag the closing {@link TokenType#TAG} after the child elements or {@code null} if
+ * there is no content and the attributes ended with {@link TokenType#SLASH_GT}
+ * @param nodeEnd the ending {@link TokenType#GT} or {@link TokenType#SLASH_GT} token (not{@code null})
+ */
+ XmlTagNode(Token nodeStart, Token tag, List<XmlAttributeNode> attributes, Token attributeEnd, List<XmlTagNode> tagNodes, Token contentEnd, Token closingTag, Token nodeEnd) {
+ this._nodeStart = nodeStart;
+ this._tag = tag;
+ this._attributes = becomeParentOf(attributes);
+ this._attributeEnd = attributeEnd;
+ this._tagNodes = becomeParentOf(tagNodes);
+ this._contentEnd = contentEnd;
+ this._closingTag = closingTag;
+ this._nodeEnd = nodeEnd;
+ }
+ accept(XmlVisitor visitor) => visitor.visitXmlTagNode(this);
+ /**
+ * The {@link TokenType#GT} or {@link TokenType#SLASH_GT} token after the attributes (not{@code null}). The token may be the same token as {@link #nodeEnd} if there are no child{@link #tagNodes}.
+ * @return the token (not {@code null})
+ */
+ Token get attributeEnd => _attributeEnd;
+ /**
+ * Answer the receiver's attributes. Callers should not manipulate the returned list to edit the
+ * AST structure.
+ * @return the attributes (not {@code null}, contains no {@code null}s)
+ */
+ List<XmlAttributeNode> get attributes => _attributes;
+ Token get beginToken => _nodeStart;
+ /**
+ * The the closing {@link TokenType#TAG} after the child elements or {@code null} if there is no
+ * content and the attributes ended with {@link TokenType#SLASH_GT}
+ * @return the closing tag or {@code null}
+ */
+ Token get closingTag => _closingTag;
+ /**
+ * Answer a string representing the content contained in the receiver. This includes the textual
+ * representation of any child tag nodes ({@link #getTagNodes()}). Whitespace between '&lt;',
+ * '&lt;/', and '>', '/>' is discarded, but all other whitespace is preserved.
+ * @return the content (not {@code null})
+ */
+ String get content {
+ Token token = _attributeEnd.next;
+ if (identical(token, _contentEnd)) {
+ return "";
+ }
+ String content = token.lexeme;
+ token = token.next;
+ if (identical(token, _contentEnd)) {
+ return content;
+ }
+ StringBuffer buffer = new StringBuffer();
+ while (token != _contentEnd) {
+ buffer.write(token.lexeme);
+ token = token.next;
+ }
+ return buffer.toString();
+ }
+ /**
+ * Answer the token (not {@code null}) after the content, which may be
+ * <ul>
+ * <li>(1) {@link TokenType#LT_SLASH} for nodes with open and close tags, or</li>
+ * <li>(2) the {@link TokenType#LT} nodeStart of the next sibling node if this node is self
+ * closing or the attributeEnd is {@link TokenType#SLASH_GT}, or</li>
+ * <li>(3) {@link TokenType#EOF} if the node does not have a closing tag and is the last node in
+ * the stream {@link TokenType#LT_SLASH} token after the content, or {@code null} if there is no
+ * content and the attributes ended with {@link TokenType#SLASH_GT}.</li>
+ * </ul>
+ * @return the token (not {@code null})
+ */
+ Token get contentEnd => _contentEnd;
+ Token get endToken {
+ if (_nodeEnd != null) {
+ return _nodeEnd;
+ }
+ if (_closingTag != null) {
+ return _closingTag;
+ }
+ if (_contentEnd != null) {
+ return _contentEnd;
+ }
+ if (!_tagNodes.isEmpty) {
+ return _tagNodes[_tagNodes.length - 1].endToken;
+ }
+ if (_attributeEnd != null) {
+ return _attributeEnd;
+ }
+ if (!_attributes.isEmpty) {
+ return _attributes[_attributes.length - 1].endToken;
+ }
+ return _tag;
+ }
+ /**
+ * Answer the ending {@link TokenType#GT} or {@link TokenType#SLASH_GT} token.
+ * @return the token (not {@code null})
+ */
+ Token get nodeEnd => _nodeEnd;
+ /**
+ * Answer the starting {@link TokenType#LT} token.
+ * @return the token (not {@code null})
+ */
+ Token get nodeStart => _nodeStart;
+ /**
+ * Answer the {@link TokenType#TAG} token after the starting '&lt;'.
+ * @return the token (not {@code null})
+ */
+ Token get tag => _tag;
+ /**
+ * Answer the tag nodes contained in the receiver. Callers should not manipulate the returned list
+ * to edit the AST structure.
+ * @return the children (not {@code null}, contains no {@code null}s)
+ */
+ List<XmlTagNode> get tagNodes => _tagNodes;
+ void visitChildren(XmlVisitor<Object> visitor) {
+ for (XmlAttributeNode node in _attributes) {
+ node.accept(visitor);
+ }
+ for (XmlTagNode node in _tagNodes) {
+ node.accept(visitor);
+ }
+ }
+}
+/**
+ * Instances of the class {@code HtmlParser} are used to parse tokens into a AST structure comprised
+ * of {@link XmlNode}s.
+ */
+class HtmlParser extends XmlParser {
+ static Set<String> SELF_CLOSING = new Set<String>();
+ /**
+ * Construct a parser for the specified source.
+ * @param source the source being parsed
+ */
+ HtmlParser(Source source) : super(source) {
+ }
+ /**
+ * Parse the tokens specified by the given scan result.
+ * @param scanResult the result of scanning an HTML source (not {@code null})
+ * @return the parse result (not {@code null})
+ */
+ HtmlParseResult parse(HtmlScanResult scanResult) {
+ Token firstToken = scanResult.token;
+ List<XmlTagNode> tagNodes = parseTopTagNodes(firstToken);
+ HtmlUnit unit = new HtmlUnit(firstToken, tagNodes, currentToken);
+ return new HtmlParseResult(firstToken, scanResult.lineStarts, unit);
+ }
+ /**
+ * Scan then parse the specified source.
+ * @param source the source to be scanned and parsed (not {@code null})
+ * @return the parse result (not {@code null})
+ */
+ HtmlParseResult parse2(Source source) {
+ HtmlScanner scanner = new HtmlScanner(source);
+ source.getContents(scanner);
+ return parse(scanner.result);
+ }
+ bool isSelfClosing(Token tag) => SELF_CLOSING.contains(tag.lexeme);
+}
+/**
+ * Instances of the class {@code HtmlUnit} represent the contents of an HTML file.
+ */
+class HtmlUnit extends XmlNode {
+ /**
+ * The first token in the token stream that was parsed to form this HTML unit.
+ */
+ Token _beginToken;
+ /**
+ * The last token in the token stream that was parsed to form this compilation unit. This token
+ * should always have a type of {@link TokenType.EOF}.
+ */
+ Token _endToken;
+ /**
+ * The tag nodes contained in the receiver (not {@code null}, contains no {@code null}s).
+ */
+ List<XmlTagNode> _tagNodes;
+ /**
+ * Construct a new instance representing the content of an HTML file.
+ * @param beginToken the first token in the file (not {@code null})
+ * @param tagNodes child tag nodes of the receiver (not {@code null}, contains no {@code null}s)
+ * @param endToken the last token in the token stream which should be of type{@link TokenType.EOF}
+ */
+ HtmlUnit(Token beginToken, List<XmlTagNode> tagNodes, Token endToken) {
+ this._beginToken = beginToken;
+ this._tagNodes = becomeParentOf(tagNodes);
+ this._endToken = endToken;
+ }
+ accept(XmlVisitor visitor) => visitor.visitHtmlUnit(this);
+ Token get beginToken => _beginToken;
+ Token get endToken => _endToken;
+ /**
+ * Answer the tag nodes contained in the receiver. Callers should not manipulate the returned list
+ * to edit the AST structure.
+ * @return the children (not {@code null}, contains no {@code null}s)
+ */
+ List<XmlTagNode> get tagNodes => _tagNodes;
+ void visitChildren(XmlVisitor<Object> visitor) {
+ for (XmlTagNode node in _tagNodes) {
+ node.accept(visitor);
+ }
+ }
+}

Powered by Google App Engine
This is Rietveld 408576698