📄 xmlencodingdetector.java
字号:
// scan character
int c = fCurrentEntity.ch[fCurrentEntity.position++];
boolean external = false;
if (c == '\n' ||
(c == '\r' && (external = fCurrentEntity.isExternal()))) {
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = (char)c;
load(1, false);
}
if (c == '\r' && external) {
if (fCurrentEntity.ch[fCurrentEntity.position++] != '\n') {
fCurrentEntity.position--;
}
c = '\n';
}
}
// return character that was scanned
fCurrentEntity.columnNumber++;
return c;
}
// Adapted from:
// org.apache.xerces.impl.XMLEntityManager.EntityScanner.scanName
/**
* Returns a string matching the Name production appearing immediately
* on the input as a symbol, or null if no Name string is present.
* <p>
* <strong>Note:</strong> The Name characters are consumed.
* <p>
* <strong>Note:</strong> The string returned must be a symbol. The
* SymbolTable can be used for this purpose.
*
* @throws IOException Thrown if i/o error occurs.
* @throws EOFException Thrown on end of file.
*
* @see SymbolTable
* @see XMLChar#isName
* @see XMLChar#isNameStart
*/
public String scanName() throws IOException {
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
// scan name
int offset = fCurrentEntity.position;
if (XMLChar.isNameStart(fCurrentEntity.ch[offset])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[offset];
offset = 0;
if (load(1, false)) {
fCurrentEntity.columnNumber++;
String symbol = fSymbolTable.addSymbol(fCurrentEntity.ch,
0, 1);
return symbol;
}
}
while (XMLChar.isName(fCurrentEntity.ch[fCurrentEntity.position])) {
if (++fCurrentEntity.position == fCurrentEntity.count) {
int length = fCurrentEntity.position - offset;
if (length == fBufferSize) {
// bad luck we have to resize our buffer
char[] tmp = new char[fBufferSize * 2];
System.arraycopy(fCurrentEntity.ch, offset,
tmp, 0, length);
fCurrentEntity.ch = tmp;
fBufferSize *= 2;
} else {
System.arraycopy(fCurrentEntity.ch, offset,
fCurrentEntity.ch, 0, length);
}
offset = 0;
if (load(length, false)) {
break;
}
}
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length;
// return name
String symbol = null;
if (length > 0) {
symbol = fSymbolTable.addSymbol(fCurrentEntity.ch, offset, length);
}
return symbol;
}
// Adapted from:
// org.apache.xerces.impl.XMLEntityManager.EntityScanner.scanLiteral
/**
* Scans a range of attribute value data, setting the fields of the
* XMLString structure, appropriately.
* <p>
* <strong>Note:</strong> The characters are consumed.
* <p>
* <strong>Note:</strong> This method does not guarantee to return
* the longest run of attribute value data. This method may return
* before the quote character due to reaching the end of the input
* buffer or any other reason.
* <p>
* <strong>Note:</strong> The fields contained in the XMLString
* structure are not guaranteed to remain valid upon subsequent calls
* to the entity scanner. Therefore, the caller is responsible for
* immediately using the returned character data or making a copy of
* the character data.
*
* @param quote The quote character that signifies the end of the
* attribute value data.
* @param content The content structure to fill.
*
* @return Returns the next character on the input, if known. This
* value may be -1 but this does <em>note</em> designate
* end of file.
*
* @throws IOException Thrown if i/o error occurs.
* @throws EOFException Thrown on end of file.
*/
public int scanLiteral(int quote, XMLString content)
throws IOException {
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
} else if (fCurrentEntity.position == fCurrentEntity.count - 1) {
fCurrentEntity.ch[0] = fCurrentEntity.ch[fCurrentEntity.count - 1];
load(1, false);
fCurrentEntity.position = 0;
}
// normalize newlines
int offset = fCurrentEntity.position;
int c = fCurrentEntity.ch[offset];
int newlines = 0;
boolean external = fCurrentEntity.isExternal();
if (c == '\n' || (c == '\r' && external)) {
do {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == '\r' && external) {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.position = newlines;
if (load(newlines, false)) {
break;
}
}
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n') {
fCurrentEntity.position++;
offset++;
}
/*** NEWLINE NORMALIZATION ***/
else {
newlines++;
}
/***/
}
else if (c == '\n') {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.position = newlines;
if (load(newlines, false)) {
break;
}
}
/*** NEWLINE NORMALIZATION ***
if (fCurrentEntity.ch[fCurrentEntity.position] == '\r'
&& external) {
fCurrentEntity.position++;
offset++;
}
/***/
}
else {
fCurrentEntity.position--;
break;
}
} while (fCurrentEntity.position < fCurrentEntity.count - 1);
for (int i = offset; i < fCurrentEntity.position; i++) {
fCurrentEntity.ch[i] = '\n';
}
int length = fCurrentEntity.position - offset;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
content.setValues(fCurrentEntity.ch, offset, length);
return -1;
}
}
// scan literal value
while (fCurrentEntity.position < fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if ((c == quote &&
(!fCurrentEntity.literal || external))
|| c == '%' || !XMLChar.isContent(c)) {
fCurrentEntity.position--;
break;
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
content.setValues(fCurrentEntity.ch, offset, length);
// return next character
if (fCurrentEntity.position != fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position];
// NOTE: We don't want to accidentally signal the
// end of the literal if we're expanding an
// entity appearing in the literal. -Ac
if (c == quote && fCurrentEntity.literal) {
c = -1;
}
}
else {
c = -1;
}
return c;
}
/**
* Scans a range of character data up to the specified delimiter,
* setting the fields of the XMLString structure, appropriately.
* <p>
* <strong>Note:</strong> The characters are consumed.
* <p>
* <strong>Note:</strong> This assumes that the internal buffer is
* at least the same size, or bigger, than the length of the delimiter
* and that the delimiter contains at least one character.
* <p>
* <strong>Note:</strong> This method does not guarantee to return
* the longest run of character data. This method may return before
* the delimiter due to reaching the end of the input buffer or any
* other reason.
* <p>
* <strong>Note:</strong> The fields contained in the XMLString
* structure are not guaranteed to remain valid upon subsequent calls
* to the entity scanner. Therefore, the caller is responsible for
* immediately using the returned character data or making a copy of
* the character data.
*
* @param delimiter The string that signifies the end of the character
* data to be scanned.
* @param buffer The data structure to fill.
*
* @return Returns true if there is more data to scan, false otherwise.
*
* @throws IOException Thrown if i/o error occurs.
* @throws EOFException Thrown on end of file.
*/
public boolean scanData(String delimiter, XMLStringBuffer buffer)
throws IOException {
boolean done = false;
int delimLen = delimiter.length();
char charAt0 = delimiter.charAt(0);
boolean external = fCurrentEntity.isExternal();
do {
// load more characters, if needed
if (fCurrentEntity.position == fCurrentEntity.count) {
load(0, true);
}
else if (fCurrentEntity.position >= fCurrentEntity.count - delimLen) {
System.arraycopy(fCurrentEntity.ch, fCurrentEntity.position,
fCurrentEntity.ch, 0, fCurrentEntity.count - fCurrentEntity.position);
load(fCurrentEntity.count - fCurrentEntity.position, false);
fCurrentEntity.position = 0;
}
if (fCurrentEntity.position >= fCurrentEntity.count - delimLen) {
// something must be wrong with the input: e.g., file ends an
// unterminated comment
int length = fCurrentEntity.count - fCurrentEntity.position;
buffer.append (fCurrentEntity.ch, fCurrentEntity.position,
length);
fCurrentEntity.columnNumber += fCurrentEntity.count;
fCurrentEntity.position = fCurrentEntity.count;
load(0,true);
return false;
}
// normalize newlines
int offset = fCurrentEntity.position;
int c = fCurrentEntity.ch[offset];
int newlines = 0;
if (c == '\n' || (c == '\r' && external)) {
do {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == '\r' && external) {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.position = newlines;
if (load(newlines, false)) {
break;
}
}
if (fCurrentEntity.ch[fCurrentEntity.position] == '\n') {
fCurrentEntity.position++;
offset++;
}
/*** NEWLINE NORMALIZATION ***/
else {
newlines++;
}
}
else if (c == '\n') {
newlines++;
fCurrentEntity.lineNumber++;
fCurrentEntity.columnNumber = 1;
if (fCurrentEntity.position == fCurrentEntity.count) {
offset = 0;
fCurrentEntity.position = newlines;
fCurrentEntity.count = newlines;
if (load(newlines, false)) {
break;
}
}
}
else {
fCurrentEntity.position--;
break;
}
} while (fCurrentEntity.position < fCurrentEntity.count - 1);
for (int i = offset; i < fCurrentEntity.position; i++) {
fCurrentEntity.ch[i] = '\n';
}
int length = fCurrentEntity.position - offset;
if (fCurrentEntity.position == fCurrentEntity.count - 1) {
buffer.append(fCurrentEntity.ch, offset, length);
return true;
}
}
// iterate over buffer looking for delimiter
OUTER: while (fCurrentEntity.position < fCurrentEntity.count) {
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (c == charAt0) {
// looks like we just hit the delimiter
int delimOffset = fCurrentEntity.position - 1;
for (int i = 1; i < delimLen; i++) {
if (fCurrentEntity.position == fCurrentEntity.count) {
fCurrentEntity.position -= i;
break OUTER;
}
c = fCurrentEntity.ch[fCurrentEntity.position++];
if (delimiter.charAt(i) != c) {
fCurrentEntity.position--;
break;
}
}
if (fCurrentEntity.position == delimOffset + delimLen) {
done = true;
break;
}
}
else if (c == '\n' || (external && c == '\r')) {
fCurrentEntity.position--;
break;
}
else if (XMLChar.isInvalid(c)) {
fCurrentEntity.position--;
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
buffer.append(fCurrentEntity.ch, offset, length);
return true;
}
}
int length = fCurrentEntity.position - offset;
fCurrentEntity.columnNumber += length - newlines;
if (done) {
length -= delimLen;
}
buffer.append (fCurrentEntity.ch, offset, length);
// return true if string was skipped
} while (!done);
return !done;
}
// Adapted from:
// org.apache.xerces.impl.XMLEntityManager.EntityScanner.skipChar
/**
* Skips a character appearing immediately on the input.
* <p>
* <strong>Note:</strong> The character is consumed only if it matches
* the specified character.
*
* @param c The character to skip.
*
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -