PRBool nsCSSScanner::NextURL(nsresult& aErrorCode, nsCSSToken& aToken)
{
PRInt32 ch = Read(aErrorCode);
if (ch < 0) {
return PR_FALSE;
}
if (ch < 256) {
PRUint8* lexTable = gLexTable;
// STRING
if ((ch == '"') || (ch == '\'')) {
return ParseString(aErrorCode, ch, aToken);
}
// WS
if ((lexTable[ch] & IS_WHITESPACE) != 0) {
aToken.mType = eCSSToken_WhiteSpace;
aToken.mIdent.Assign(PRUnichar(ch));
(void) EatWhiteSpace(aErrorCode);
return PR_TRUE;
}
if (ch == '/') {
PRInt32 nextChar = Peek(aErrorCode);
if (nextChar == '*') {
(void) Read(aErrorCode);
#if 0
// If we change our storage data structures such that comments are
// stored (for Editor), we should reenable this code, condition it
// on being in editor mode, and apply glazou's patch from bug
// 60290.
aToken.mIdent.SetCapacity(2);
aToken.mIdent.Assign(PRUnichar(ch));
aToken.mIdent.Append(PRUnichar(nextChar));
return ParseCComment(aErrorCode, aToken);
#endif
return SkipCComment(aErrorCode) && Next(aErrorCode, aToken);
}
}
// Process a url lexical token. A CSS1 url token can contain
// characters beyond identifier characters (e.g. '/', ':', etc.)
// Because of this the normal rules for tokenizing the input don't
// apply very well. To simplify the parser and relax some of the
// requirements on the scanner we parse url's here. If we find a
// malformed URL then we emit a token of type "InvalidURL" so that
// the CSS1 parser can ignore the invalid input. We attempt to eat
// the right amount of input data when an invalid URL is presented.
aToken.mType = eCSSToken_InvalidURL;
nsString& ident = aToken.mIdent;
ident.SetLength(0);
if (ch == ')') {
Pushback(ch);
// empty url spec; just get out of here
aToken.mType = eCSSToken_URL;
} else {
// start of a non-quoted url
Pushback(ch);
PRBool ok = PR_TRUE;
for (;;) {
ch = Read(aErrorCode);
if (ch < 0) break;
if (ch == CSS_ESCAPE) {
ParseAndAppendEscape(aErrorCode, ident);
} else if ((ch == '"') || (ch == '\'') || (ch == '(')) {
// This is an invalid URL spec
ok = PR_FALSE;
} else if ((256 > ch) && ((gLexTable[ch] & IS_WHITESPACE) != 0)) {
// Whitespace is allowed at the end of the URL
(void) EatWhiteSpace(aErrorCode);
if (LookAhead(aErrorCode, ')')) {
Pushback(')'); // leave the closing symbol
// done!
break;
}
// Whitespace is followed by something other than a
// ")". This is an invalid url spec.
ok = PR_FALSE;
} else if (ch == ')') {
Unread();
// All done
break;
} else {
// A regular url character.
ident.Append(PRUnichar(ch));
}
}
// If the result of the above scanning is ok then change the token
// type to a useful one.
if (ok) {
aToken.mType = eCSSToken_URL;
}
}
}
return PR_TRUE;
}
PRBool
nsCSSScanner::Next(nsCSSToken& aToken)
{
for (;;) { // Infinite loop so we can restart after comments.
PRInt32 ch = Read();
if (ch < 0) {
return PR_FALSE;
}
// UNICODE-RANGE
if ((ch == 'u' || ch == 'U') && Peek() == '+')
return ParseURange(ch, aToken);
// IDENT
if (StartsIdent(ch, Peek()))
return ParseIdent(ch, aToken);
// AT_KEYWORD
if (ch == '@') {
PRInt32 nextChar = Read();
if (nextChar >= 0) {
PRInt32 followingChar = Peek();
Pushback(nextChar);
if (StartsIdent(nextChar, followingChar))
return ParseAtKeyword(ch, aToken);
}
}
// NUMBER or DIM
if ((ch == '.') || (ch == '+') || (ch == '-')) {
PRInt32 nextChar = Peek();
if (IsDigit(nextChar)) {
return ParseNumber(ch, aToken);
}
else if (('.' == nextChar) && ('.' != ch)) {
nextChar = Read();
PRInt32 followingChar = Peek();
Pushback(nextChar);
if (IsDigit(followingChar))
return ParseNumber(ch, aToken);
}
}
if (IsDigit(ch)) {
return ParseNumber(ch, aToken);
}
// ID
if (ch == '#') {
return ParseRef(ch, aToken);
}
// STRING
if ((ch == '"') || (ch == '\'')) {
return ParseString(ch, aToken);
}
// WS
if (IsWhitespace(ch)) {
aToken.mType = eCSSToken_WhiteSpace;
aToken.mIdent.Assign(PRUnichar(ch));
EatWhiteSpace();
return PR_TRUE;
}
if (ch == '/' && !IsSVGMode()) {
PRInt32 nextChar = Peek();
if (nextChar == '*') {
(void) Read();
#if 0
// If we change our storage data structures such that comments are
// stored (for Editor), we should reenable this code, condition it
// on being in editor mode, and apply glazou's patch from bug
// 60290.
aToken.mIdent.SetCapacity(2);
aToken.mIdent.Assign(PRUnichar(ch));
aToken.mIdent.Append(PRUnichar(nextChar));
return ParseCComment(aToken);
#endif
if (!SkipCComment()) {
return PR_FALSE;
}
continue; // start again at the beginning
}
}
if (ch == '<') { // consume HTML comment tags
if (LookAhead('!')) {
if (LookAhead('-')) {
if (LookAhead('-')) {
aToken.mType = eCSSToken_HTMLComment;
aToken.mIdent.AssignLiteral("<!--");
return PR_TRUE;
}
Pushback('-');
}
Pushback('!');
}
}
if (ch == '-') { // check for HTML comment end
if (LookAhead('-')) {
if (LookAhead('>')) {
aToken.mType = eCSSToken_HTMLComment;
aToken.mIdent.AssignLiteral("-->");
return PR_TRUE;
}
Pushback('-');
}
}
// INCLUDES ("~=") and DASHMATCH ("|=")
if (( ch == '|' ) || ( ch == '~' ) || ( ch == '^' ) ||
( ch == '$' ) || ( ch == '*' )) {
PRInt32 nextChar = Read();
if ( nextChar == '=' ) {
if (ch == '~') {
aToken.mType = eCSSToken_Includes;
}
else if (ch == '|') {
aToken.mType = eCSSToken_Dashmatch;
}
else if (ch == '^') {
aToken.mType = eCSSToken_Beginsmatch;
}
else if (ch == '$') {
aToken.mType = eCSSToken_Endsmatch;
}
else if (ch == '*') {
aToken.mType = eCSSToken_Containsmatch;
}
return PR_TRUE;
} else if (nextChar >= 0) {
Pushback(nextChar);
}
}
aToken.mType = eCSSToken_Symbol;
aToken.mSymbol = ch;
return PR_TRUE;
}
}
PRBool nsCSSScanner::Next(nsresult& aErrorCode, nsCSSToken& aToken)
{
PRInt32 ch = Read(aErrorCode);
if (ch < 0) {
return PR_FALSE;
}
PRUint8* lexTable = gLexTable;
// IDENT
if (StartsIdent(ch, Peek(aErrorCode), lexTable))
return ParseIdent(aErrorCode, ch, aToken);
// From this point on, 0 <= ch < 256.
// AT_KEYWORD
if (ch == '@') {
PRInt32 nextChar = Read(aErrorCode);
PRInt32 followingChar = Peek(aErrorCode);
Pushback(nextChar);
if (StartsIdent(nextChar, followingChar, lexTable))
return ParseAtKeyword(aErrorCode, ch, aToken);
}
// NUMBER or DIM
if ((ch == '.') || (ch == '+') || (ch == '-')) {
PRInt32 nextChar = Peek(aErrorCode);
if (CheckLexTable(nextChar, IS_DIGIT, lexTable)) {
return ParseNumber(aErrorCode, ch, aToken);
}
else if (('.' == nextChar) && ('.' != ch)) {
nextChar = Read(aErrorCode);
PRInt32 followingChar = Peek(aErrorCode);
Pushback(nextChar);
if (CheckLexTable(followingChar, IS_DIGIT, lexTable))
return ParseNumber(aErrorCode, ch, aToken);
}
}
if ((lexTable[ch] & IS_DIGIT) != 0) {
return ParseNumber(aErrorCode, ch, aToken);
}
// ID
if (ch == '#') {
return ParseRef(aErrorCode, ch, aToken);
}
// STRING
if ((ch == '"') || (ch == '\'')) {
return ParseString(aErrorCode, ch, aToken);
}
// WS
if ((lexTable[ch] & IS_WHITESPACE) != 0) {
aToken.mType = eCSSToken_WhiteSpace;
aToken.mIdent.Assign(PRUnichar(ch));
(void) EatWhiteSpace(aErrorCode);
return PR_TRUE;
}
if (ch == '/') {
PRInt32 nextChar = Peek(aErrorCode);
if (nextChar == '*') {
(void) Read(aErrorCode);
#if 0
// If we change our storage data structures such that comments are
// stored (for Editor), we should reenable this code, condition it
// on being in editor mode, and apply glazou's patch from bug
// 60290.
aToken.mIdent.SetCapacity(2);
aToken.mIdent.Assign(PRUnichar(ch));
aToken.mIdent.Append(PRUnichar(nextChar));
return ParseCComment(aErrorCode, aToken);
#endif
return SkipCComment(aErrorCode) && Next(aErrorCode, aToken);
}
}
if (ch == '<') { // consume HTML comment tags
if (LookAhead(aErrorCode, '!')) {
if (LookAhead(aErrorCode, '-')) {
if (LookAhead(aErrorCode, '-')) {
aToken.mType = eCSSToken_HTMLComment;
aToken.mIdent.AssignLiteral("<!--");
return PR_TRUE;
}
Pushback('-');
}
Pushback('!');
}
}
if (ch == '-') { // check for HTML comment end
if (LookAhead(aErrorCode, '-')) {
if (LookAhead(aErrorCode, '>')) {
aToken.mType = eCSSToken_HTMLComment;
aToken.mIdent.AssignLiteral("-->");
return PR_TRUE;
}
Pushback('-');
}
}
// INCLUDES ("~=") and DASHMATCH ("|=")
if (( ch == '|' ) || ( ch == '~' ) || ( ch == '^' ) ||
( ch == '$' ) || ( ch == '*' )) {
PRInt32 nextChar = Read(aErrorCode);
if ( nextChar == '=' ) {
if (ch == '~') {
aToken.mType = eCSSToken_Includes;
}
else if (ch == '|') {
aToken.mType = eCSSToken_Dashmatch;
}
else if (ch == '^') {
aToken.mType = eCSSToken_Beginsmatch;
}
else if (ch == '$') {
aToken.mType = eCSSToken_Endsmatch;
}
else if (ch == '*') {
aToken.mType = eCSSToken_Containsmatch;
}
return PR_TRUE;
} else {
Pushback(nextChar);
}
}
aToken.mType = eCSSToken_Symbol;
aToken.mSymbol = ch;
return PR_TRUE;
}