JOURNAL-lex — Adversary

2026-06-15T00:12Z — Cold start

Read phase plan lex.md. Builder has not pushed any code yet (only seed commit 13c0db5). Initialized REVIEW, BACKLOG, JOURNAL files. Waiting for Builder to push work.

DoD gates to verify:

D1: numbers (integers and floats)
D2: operators & parens
D3: whitespace & errors (LexError)
D4: tests green (python -m unittest -q)

2026-06-15T00:20Z — Verification complete

Builder pushed claim(D1-D4). Pulled, ran cold verification, ran break-it probes. All four gates PASS. No vetoes. Wrote verdicts to REVIEW-lex.md. Adversary probes: empty string, lone dot, whitespace-only, double-dot, 1.2.3, position accuracy — all held.

JOURNAL-lex — Builder

2026-06-15 — Implementation

Read phase plan. Built calc/lexer.py and calc/test_lexer.py from scratch.

Implementation choices

Token is a dataclass with kind: str and value: int | float | str | None
NUMBER value is int (no dot) or float (dot present)
LexError message includes repr of the offending char and its 0-based position
Leading dot (.5) and trailing dot (10.) are valid floats (scanned by loop: stops when second dot seen)
Single lone dot is an error (raw == '.')

Test run output

python -m unittest -q
----------------------------------------------------------------------
Ran 21 tests in 0.000s
OK

Verification commands output

$ python -c "from calc.lexer import tokenize; print([(t.kind,t.value) for t in tokenize('3.5*(1-2)')])"
[('NUMBER', 3.5), ('STAR', '*'), ('LPAREN', '('), ('NUMBER', 1), ('MINUS', '-'), ('NUMBER', 2), ('RPAREN', ')'), ('EOF', None)]

$ python -c "from calc.lexer import tokenize; tokenize('1 @ 2')"
calc.lexer.LexError: Unexpected character '@' at position 2

1.7 KiB Raw Blame History