Skip to content

lexer: read / after a built-in variable as division #143

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
sylvestre merged 2 commits into from
Oct 25, 2026
Merged

lexer: read / after a built-in variable as division #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a2dd734
lexer: read / after a built-in variable as division
jayhemnani9910 Oct 23, 2026
f15885c
tests: cover NR /= after a built-in variable
jayhemnani9910 Oct 24, 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
42 changes: 21 additions & 21 deletions lexer/src/lib.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,47 +183,47 @@ pub enum Token<'a> {
Lshift,
#[token("rshift", |lex| parse_non_posix_keyword(lex, Token::Rshift))]
Rshift,
#[regex("(awk::)?NR", accept_expression)]
#[regex("(awk::)?NR", accept_operator)]
NrVariable,
#[regex("(awk::)?NF", accept_expression)]
#[regex("(awk::)?NF", accept_operator)]
NfVariable,
#[regex("(awk::)?FS", accept_expression)]
#[regex("(awk::)?FS", accept_operator)]
FsVariable,
#[regex("(awk::)?FPAT", accept_expression)]
#[regex("(awk::)?FPAT", accept_operator)]
FpatVariable,
#[regex("(awk::)?FIELDWIDTHS", accept_expression)]
#[regex("(awk::)?FIELDWIDTHS", accept_operator)]
FieldwidthsVariable,
#[regex("(awk::)?RS", accept_expression)]
#[regex("(awk::)?RS", accept_operator)]
RsVariable,
#[regex("(awk::)?OFS", accept_expression)]
#[regex("(awk::)?OFS", accept_operator)]
OfsVariable,
#[regex("(awk::)?ORS", accept_expression)]
#[regex("(awk::)?ORS", accept_operator)]
OrsVariable,
#[regex("(awk::)?FILENAME", accept_expression)]
#[regex("(awk::)?FILENAME", accept_operator)]
FilenameVariable,
#[regex("(awk::)?ARGC", accept_expression)]
#[regex("(awk::)?ARGC", accept_operator)]
ArgcVariable,
#[regex("(awk::)?ARGV", accept_expression)]
#[regex("(awk::)?ARGV", accept_operator)]
ArgvVariable,
#[regex("(awk::)?SUBSEP", accept_expression)]
#[regex("(awk::)?SUBSEP", accept_operator)]
SubsepVariable,
#[regex("(awk::)?FNR", accept_expression)]
#[regex("(awk::)?FNR", accept_operator)]
FnrVariable,
#[regex("(awk::)?ARGIND")]
#[regex("(awk::)?ARGIND", accept_operator)]
ArgindVariable,
#[regex("(awk::)?OFMT", accept_expression)]
#[regex("(awk::)?OFMT", accept_operator)]
OfmtVariable,
#[regex("(awk::)?RSTART", accept_expression)]
#[regex("(awk::)?RSTART", accept_operator)]
RstartVariable,
#[regex("(awk::)?RLENGTH", accept_expression)]
#[regex("(awk::)?RLENGTH", accept_operator)]
RlengthVariable,
#[regex("(awk::)?ENVIRON", accept_expression)]
#[regex("(awk::)?ENVIRON", accept_operator)]
EnvironVariable,
#[regex("(awk::)?PROCINFO", accept_expression)]
#[regex("(awk::)?PROCINFO", accept_operator)]
ProcinfoVariable,
#[regex("(awk::)?SYMTAB", accept_expression)]
#[regex("(awk::)?SYMTAB", accept_operator)]
SymtabVariable,
#[regex("(awk::)?FUNCTAB", accept_expression)]
#[regex("(awk::)?FUNCTAB", accept_operator)]
FunctabVariable,
#[regex("(?&identifier)", Identifier::parse::<0>)]
Identifier(Identifier<'a>),
Expand Down
5 changes: 4 additions & 1 deletion lexer/src/tests.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,13 +241,16 @@ fn lexer_test_general_tokens() {
fn lexer_test_regex_ambiguity() {
let arena = Bump::new();
assert_eq!(
&lex(b"1/=1. a/=1", &arena, false, false),
&lex(b"1/=1. a/=1 NR/=1", &arena, false, false),
&[
Token::Integer(1),
Token::SlashAssign,
Token::Number(1.),
Token::Identifier(Identifier { literal: "a" }),
Token::SlashAssign,
Token::Integer(1),
Token::NrVariable,
Token::SlashAssign,
Token::Integer(1)
]
);
Expand Down
9 changes: 9 additions & 0 deletions tests/by-util/test_awk.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -899,3 +899,12 @@ fn bare_regex_in_expression_matches_record() {
.succeeds()
.stdout_is("y 2\n2\n");
}

#[test]
fn slash_after_special_variable_divides() {
ucmd()
.arg("{ print NR / 2, NF/NR } END { RSTART = 8; print RSTART / 2 / 2; NR = 6; NR /= 2; print NR }")
.pipe_in("a b\nc d\n")

@sylvestre sylvestre Oct 24, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

could you please also cover NR /= 2 here?
and maybe add NR/=1 to lexer_test_regex_ambiguity in lexer/src/tests.rs

@jayhemnani9910 jayhemnani9910 Oct 24, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added both in f15885c: NR /= 2 in slash_after_special_variable_divides, and NR/=1 in lexer_test_regex_ambiguity (it fails on main, where /=1 starts a regex). The test sets NR first (NR = 6; NR /= 2), because on main NR in END after a file is still 0 (#140), and gawk keeps NR an integer, so NR /= 2 in a main rule truncates there.

.succeeds()
.stdout_only("0.5 2\n1 1\n2\n3\n");
}
Loading