Luke/snow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: 支持数字字面量中的下划线分隔符

Browse Source 
- 增加了对数字中下划线的处理逻辑
- 添加了防止下划线连续出现、以下划线开头或结尾的校验
- 优化了小数部分的下划线检查
- 修复了数字后紧跟下划线的错误处理
- 最后返回的数字字面量中将移除所有的下划线
This commit is contained in:
Luke 2025-07-17 11:47:19 +08:00
parent ac5b73e320
commit d0e8cee6bd
1 changed files with 38 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
src/main/java/org/jcnc/snow/compiler/lexer/scanners/NumberTokenScanner.java
View File

@ -80,6 +80,9 @@ public class NumberTokenScanner extends AbstractTokenScanner {
StringBuilder literal = new StringBuilder();
State state = State.INT_PART;
boolean lastWasUnderscore = false; // 记录前一个是否是下划线
boolean sawDigit = false; // 当前段落是否有数字（防止以下划线开头）
/* ───── 1. 主体扫描 —— 整数 / 小数 ───── */
mainLoop:
while (!ctx.isAtEnd() && state != State.END) {
@ -89,10 +92,25 @@ public class NumberTokenScanner extends AbstractTokenScanner {
case INT_PART:
if (Character.isDigit(ch)) {
literal.append(ctx.advance());
lastWasUnderscore = false;
sawDigit = true;
} else if (ch == '_') {
if (!sawDigit)
throw new LexicalException("数字不能以下划线开头", line, col);
if (lastWasUnderscore)
throw new LexicalException("数字中下划线不能连续出现", line, col);
literal.append(ctx.advance());
lastWasUnderscore = true;
} else if (ch == '.') {
if (lastWasUnderscore)
throw new LexicalException("下划线不能出现在小数点前", line, col);
state = State.DEC_POINT;
literal.append(ctx.advance());
// 不要重置sawDigit！
// sawDigit = false; // 移除此句
} else {
if (lastWasUnderscore)
throw new LexicalException("数字不能以下划线结尾", line, col);
state = State.END;
}
break;
@ -100,18 +118,30 @@ public class NumberTokenScanner extends AbstractTokenScanner {
/* 已读到小数点，下一字符必须是数字 */
case DEC_POINT:
if (Character.isDigit(ch)) {
state = State.FRAC_PART;
literal.append(ctx.advance());
state = State.FRAC_PART;
sawDigit = true;
} else if (ch == '_') { // 防止小数点后直接跟下划线
throw new LexicalException("小数点后不能直接跟下划线", line, col);
} else {
throw new LexicalException("小数点后必须跟数字", line, col);
}
break;
/* 小数部分 */
case FRAC_PART:
if (Character.isDigit(ch)) {
literal.append(ctx.advance());
lastWasUnderscore = false;
} else if (ch == '_') { // 小数部分下划线检查
if (lastWasUnderscore)
throw new LexicalException("数字中下划线不能连续出现", line, col);
literal.append(ctx.advance());
lastWasUnderscore = true;
} else {
if (lastWasUnderscore)
throw new LexicalException("数字不能以下划线结尾", line, col);
state = State.END;
}
break;
@ -121,6 +151,10 @@ public class NumberTokenScanner extends AbstractTokenScanner {
}
}
// 主体结束后，下划线不能在末尾
if (lastWasUnderscore)
throw new LexicalException("数字不能以下划线结尾", line, col);
/* ───── 2. 后缀及非法尾随字符检查 ───── */
if (!ctx.isAtEnd()) {
char next = ctx.peek();
@ -154,7 +188,7 @@ public class NumberTokenScanner extends AbstractTokenScanner {
}
/* ───── 3. 生成并返回 Token ───── */
return new Token(TokenType.NUMBER_LITERAL, literal.toString(), line, col);
return new Token(TokenType.NUMBER_LITERAL, literal.toString().replace("_", ""), line, col);
}
/**