本文整理汇总了Java中org.jsoup.nodes.Entities.getCharacterByName方法的典型用法代码示例。如果您正苦于以下问题：Java Entities.getCharacterByName方法的具体用法？Java Entities.getCharacterByName怎么用？Java Entities.getCharacterByName使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类org.jsoup.nodes.Entities的用法示例。
在下文中一共展示了Entities.getCharacterByName方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: consumeCharacterReference
import org.jsoup.nodes.Entities; //导入方法依赖的package包/类
char[] consumeCharacterReference(Character additionalAllowedCharacter, boolean inAttribute) {
if (reader.isEmpty())
return null;
if (additionalAllowedCharacter != null && additionalAllowedCharacter == reader.current())
return null;
if (reader.matchesAnySorted(notCharRefCharsSorted))
return null;
final char[] charRef = charRefHolder;
reader.mark();
if (reader.matchConsume("#")) { // numbered
boolean isHexMode = reader.matchConsumeIgnoreCase("X");
String numRef = isHexMode ? reader.consumeHexSequence() : reader.consumeDigitSequence();
if (numRef.length() == 0) { // didn't match anything
characterReferenceError("numeric reference with no numerals");
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
int charval = -1;
try {
int base = isHexMode ? 16 : 10;
charval = Integer.valueOf(numRef, base);
} catch (NumberFormatException e) {
} // skip
if (charval == -1 || (charval >= 0xD800 && charval <= 0xDFFF) || charval > 0x10FFFF) {
characterReferenceError("character outside of valid range");
charRef[0] = replacementChar;
return charRef;
} else {
// todo: implement number replacement table
// todo: check for extra illegal unicode points as parse errors
if (charval < Character.MIN_SUPPLEMENTARY_CODE_POINT) {
charRef[0] = (char) charval;
return charRef;
} else
return Character.toChars(charval);
}
} else { // named
// get as many letters as possible, and look for matching entities.
String nameRef = reader.consumeLetterThenDigitSequence();
boolean looksLegit = reader.matches(';');
// found if a base named entity without a ;, or an extended entity with the ;.
boolean found = (Entities.isBaseNamedEntity(nameRef) || (Entities.isNamedEntity(nameRef) && looksLegit));
if (!found) {
reader.rewindToMark();
if (looksLegit) // named with semicolon
characterReferenceError(String.format("invalid named referenece '%s'", nameRef));
return null;
}
if (inAttribute && (reader.matchesLetter() || reader.matchesDigit() || reader.matchesAny('=', '-', '_'))) {
// don't want that to match
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
charRef[0] = Entities.getCharacterByName(nameRef);
return charRef;
}
}
示例2: consumeCharacterReference
import org.jsoup.nodes.Entities; //导入方法依赖的package包/类
char[] consumeCharacterReference(Character additionalAllowedCharacter, boolean inAttribute) {
if (reader.isEmpty())
return null;
if (additionalAllowedCharacter != null && additionalAllowedCharacter == reader.current())
return null;
if (reader.matchesAny('\t', '\n', '\r', '\f', ' ', '<', '&'))
return null;
reader.mark();
if (reader.matchConsume("#")) { // numbered
boolean isHexMode = reader.matchConsumeIgnoreCase("X");
String numRef = isHexMode ? reader.consumeHexSequence() : reader.consumeDigitSequence();
if (numRef.length() == 0) { // didn't match anything
characterReferenceError("numeric reference with no numerals");
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
int charval = -1;
try {
int base = isHexMode ? 16 : 10;
charval = Integer.valueOf(numRef, base);
} catch (NumberFormatException e) {
} // skip
if (charval == -1 || (charval >= 0xD800 && charval <= 0xDFFF) || charval > 0x10FFFF) {
characterReferenceError("character outside of valid range");
return new char[]{replacementChar};
} else {
// todo: implement number replacement table
// todo: check for extra illegal unicode points as parse errors
return Character.toChars(charval);
}
} else { // named
// get as many letters as possible, and look for matching entities.
String nameRef = reader.consumeLetterThenDigitSequence();
boolean looksLegit = reader.matches(';');
// found if a base named entity without a ;, or an extended entity with the ;.
boolean found = (Entities.isBaseNamedEntity(nameRef) || (Entities.isNamedEntity(nameRef) && looksLegit));
if (!found) {
reader.rewindToMark();
if (looksLegit) // named with semicolon
characterReferenceError(String.format("invalid named referenece '%s'", nameRef));
return null;
}
if (inAttribute && (reader.matchesLetter() || reader.matchesDigit() || reader.matchesAny('=', '-', '_'))) {
// don't want that to match
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError("missing semicolon"); // missing semi
return new char[]{Entities.getCharacterByName(nameRef)};
}
}
示例3: consumeCharacterReference
import org.jsoup.nodes.Entities; //导入方法依赖的package包/类
Character consumeCharacterReference(Character additionalAllowedCharacter, boolean inAttribute) {
if (reader.isEmpty())
return null;
if (additionalAllowedCharacter != null && additionalAllowedCharacter == reader.current())
return null;
if (reader.matchesAny('\t', '\n', '\f', '<', '&'))
return null;
reader.mark();
if (reader.matchConsume("#")) { // numbered
boolean isHexMode = reader.matchConsumeIgnoreCase("X");
String numRef = isHexMode ? reader.consumeHexSequence() : reader.consumeDigitSequence();
if (numRef.length() == 0) { // didn't match anything
characterReferenceError();
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError(); // missing semi
int charval = -1;
try {
int base = isHexMode ? 16 : 10;
charval = Integer.valueOf(numRef, base);
} catch (NumberFormatException e) {
} // skip
if (charval == -1 || (charval >= 0xD800 && charval <= 0xDFFF) || charval > 0x10FFFF) {
characterReferenceError();
return replacementChar;
} else {
// todo: implement number replacement table
// todo: check for extra illegal unicode points as parse errors
return (char) charval;
}
} else { // named
// get as many letters as possible, and look for matching entities. unconsume backwards till a match is found
String nameRef = reader.consumeLetterSequence();
boolean looksLegit = reader.matches(';');
boolean found = false;
while (nameRef.length() > 0 && !found) {
if (Entities.isNamedEntity(nameRef))
found = true;
else {
nameRef = nameRef.substring(0, nameRef.length()-1);
reader.unconsume();
}
}
if (!found) {
if (looksLegit) // named with semicolon
characterReferenceError();
reader.rewindToMark();
return null;
}
if (inAttribute && (reader.matchesLetter() || reader.matchesDigit() || reader.matches('='))) {
// don't want that to match
reader.rewindToMark();
return null;
}
if (!reader.matchConsume(";"))
characterReferenceError(); // missing semi
return Entities.getCharacterByName(nameRef);
}
}