Skip to content

Fix parser.t tests 14 and 15: handle backslash-c without character and dollar at end of string #145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
fglock merged 3 commits into from
Jan 28, 2026
Merged

Fix parser.t tests 14 and 15: handle backslash-c without character and dollar at end of string #145

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4259854
Fix parser.t test 14: handle \c without character
fglock Jan 28, 2026
12764f6
Add targeted EOF check for $ at end of string
fglock Jan 28, 2026
3fbfdef
Fix parser.t test 15: handle $ at end of string
fglock Jan 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion src/main/java/org/perlonjava/parser/StringDoubleQuoted.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
import org.perlonjava.lexer.Lexer;
import org.perlonjava.lexer.LexerToken;
import org.perlonjava.lexer.LexerTokenType;
import org.perlonjava.runtime.PerlCompilerException;

import java.util.ArrayList;
import java.util.List;
Expand Down Expand Up @@ -457,7 +458,20 @@ private void parseDoubleQuotedEscapes() {
case "$" -> appendToCurrentSegment("$");

// Control character: \cX
case "c" -> handleControlCharacter();
case "c" -> {
var controlChar = TokenUtils.consumeChar(parser);
if (controlChar.isEmpty()) {
throw new PerlCompilerException(parser.tokenIndex, "Missing control char name in \\c", parser.ctx.errorUtil);
}
var c = controlChar.charAt(0);
var result = (c >= 'A' && c <= 'Z') ? String.valueOf((char) (c - 'A' + 1))
: (c >= 'a' && c <= 'z') ? String.valueOf((char) (c - 'a' + 1))
: c == '@' ? String.valueOf((char) 0)
: (c >= '[' && c <= '_') ? String.valueOf((char) (c - '[' + 27))
: c == '?' ? String.valueOf((char) 127)
: String.valueOf(c);
appendToCurrentSegment(result);
}

// Case modification end marker
case "E" -> {
Expand Down
73 changes: 64 additions & 9 deletions src/main/java/org/perlonjava/parser/StringSegmentParser.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,7 +390,49 @@ private Node parseSimpleVariableInterpolation(String sigil) {
}
}

// Special case: empty identifier for $ sigil (like $ at end of string)
if ("$".equals(sigil) && identifier.isEmpty()) {
// Check if we're at end of string
if (parser.tokenIndex >= parser.tokens.size() ||
parser.tokens.get(parser.tokenIndex).type == LexerTokenType.EOF) {
throw new PerlCompilerException(tokenIndex, "Final $ should be \\$ or $name", ctx.errorUtil);
}
}

return new OperatorNode(sigil, new IdentifierNode(identifier, tokenIndex), tokenIndex);
} else {
// No identifier found after sigil
// Check if we're at end of string for $ sigil
if ("$".equals(sigil) && (parser.tokenIndex >= parser.tokens.size() ||
parser.tokens.get(parser.tokenIndex).type == LexerTokenType.EOF)) {
throw new PerlCompilerException(tokenIndex, "Final $ should be \\$ or $name", ctx.errorUtil);
}

// For array sigils, check if next token starts with $ (e.g., @$b means array of $b)
if ("@".equals(sigil) && parser.tokenIndex < parser.tokens.size()) {
LexerToken nextToken = parser.tokens.get(parser.tokenIndex);
if (nextToken.text.startsWith("$")) {
// This is @$var - array of scalar variable
// Consume the $ token
TokenUtils.consume(parser);
// Now parse the rest of the identifier
identifier = IdentifierParser.parseComplexIdentifier(parser);
if (identifier == null || identifier.isEmpty()) {
throw new PerlCompilerException(tokenIndex, "Missing identifier after $", ctx.errorUtil);
}
// Return the array of scalar variable
return new OperatorNode(sigil, new OperatorNode("$", new IdentifierNode(identifier, tokenIndex), tokenIndex), tokenIndex);
}
}
if (!"$".equals(sigil)) {
throw new PerlCompilerException(tokenIndex, "Missing identifier after " + sigil, ctx.errorUtil);
}

// For $ sigil with no identifier, check if we're at end of string
if (parser.tokenIndex >= parser.tokens.size() ||
parser.tokens.get(parser.tokenIndex).type == LexerTokenType.EOF) {
throw new PerlCompilerException(tokenIndex, "Final $ should be \\$ or $name", ctx.errorUtil);
}
}

// Handle dereferenced variables: ${$var}, ${${$var}}, etc.
Expand Down Expand Up @@ -779,6 +821,13 @@ public void setOriginalStringContent(String content) {
this.originalStringContent = content;
}

/**
* Gets the original string content.
*/
protected String getOriginalStringContent() {
return originalStringContent;
}

/**
* Creates and throws an offset-aware error with correct context.
* Matches Perl's actual error format for string interpolation errors.
Expand Down Expand Up @@ -887,6 +936,11 @@ private boolean shouldInterpolateVariable(String sigil) {

var nextToken = tokens.get(parser.tokenIndex);
if (nextToken.type == LexerTokenType.EOF) {
// Special case: $ at EOF in double-quoted string should generate error
// But only for StringDoubleQuoted, not for other contexts like regex
if ("$".equals(sigil) && interpolateVariable && !isRegex && !isRegexReplacement) {
return true;
}
return false;
}

Expand Down Expand Up @@ -934,16 +988,17 @@ private boolean isNonInterpolatingCharacter(String text) {
*/
void handleControlCharacter() {
var controlChar = TokenUtils.consumeChar(parser);
if (!controlChar.isEmpty()) {
var c = controlChar.charAt(0);
var result = (c >= 'A' && c <= 'Z') ? String.valueOf((char) (c - 'A' + 1))
: (c >= 'a' && c <= 'z') ? String.valueOf((char) (c - 'a' + 1))
: c == '@' ? String.valueOf((char) 0)
: (c >= '[' && c <= '_') ? String.valueOf((char) (c - '[' + 27))
: c == '?' ? String.valueOf((char) 127)
: String.valueOf(c);
appendToCurrentSegment(result);
if (controlChar.isEmpty()) {
throw new PerlCompilerException(parser.tokenIndex, "Missing control char name in \\c", parser.ctx.errorUtil);
}
var c = controlChar.charAt(0);
var result = (c >= 'A' && c <= 'Z') ? String.valueOf((char) (c - 'A' + 1))
: (c >= 'a' && c <= 'z') ? String.valueOf((char) (c - 'a' + 1))
: c == '@' ? String.valueOf((char) 0)
: (c >= '[' && c <= '_') ? String.valueOf((char) (c - '[' + 27))
: c == '?' ? String.valueOf((char) 127)
: String.valueOf(c);
appendToCurrentSegment(result);
}

/**
Expand Down