FA-47616 / Delimited text / Open access
A zero-length run silently removes a specified column · case 01
A structured table violates the declared record or column contract.
ROOT CAUSE
Zero runs are accepted despite requiring at least one represented cell.
VERIFIED REPAIR
Preserve the named invariant at the faulty decision: if count <= 0: return None
Unsuccessful approach: Clamping to one changes an invalid encoding into invented data.
Case contract
Parse a bounded compact comma row. A field count*value expands value count times; fields lacking star occur once. Count is positive ASCII decimal and cumulative width cannot exceed budget. Split at first star; an empty value is valid. Return expanded cells.
Why this case matters
Delimited interchange needs explicit framing, schema and field semantics at ingestion and emission boundaries.
1 / The failure
Exit 1"""Failure Map reference implementation. Python standard library only."""
import json
def _vary(value):
if value == '@END': return 3 + 4*N
if isinstance(value, str): return value.replace('@', 'cell' * N)
if isinstance(value, list): return [_vary(x) for x in value]
if isinstance(value, dict): return {_vary(k): _vary(v) for k,v in value.items()}
return value
N = 1
observations = []
def solve(data):
out = []
for cell in data['row'].split(','):
if '*' in cell:
count, value = cell.split('*', 1)
if not count.isascii() or not count.isdecimal(): return None
count = int(count)
if count < 0: return None
else: count, value = 1, cell
if len(out) + count > data['budget']: return None
out.extend([value] * count)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('expanded', solve(_vary({'row': '2*@,x', 'budget': 3})), _vary(['@', '@', 'x']))
check('star value', solve(_vary({'row': '2*a*b', 'budget': 2})), _vary(['a*b', 'a*b']))
check('empty repeated', solve(_vary({'row': '2*', 'budget': 2})), _vary(['', '']))
check('zero', solve(_vary({'row': '0*x', 'budget': 2})), _vary(None))
check('negative', solve(_vary({'row': '-1*x', 'budget': 2})), _vary(None))
check('aggregate limit', solve(_vary({'row': '2*x,2*y', 'budget': 3})), _vary(None))
check('exact limit', solve(_vary({'row': '3*@', 'budget': 3})), _vary(['@', '@', '@']))
check('ordinary', solve(_vary({'row': '@,z', 'budget': 2})), _vary(['@', 'z']))
check('space value', solve(_vary({'row': ' @ ', 'budget': 1})), _vary([' @ ']))
check('empty field', solve(_vary({'row': '', 'budget': 1})), _vary(['']))
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| expanded | ['cell', 'cell', 'x'] | ['cell', 'cell', 'x'] | Passed |
| star value | ['a*b', 'a*b'] | ['a*b', 'a*b'] | Passed |
| empty repeated | ['', ''] | ['', ''] | Passed |
| zero | [] | None | Failed |
| negative | None | None | Passed |
| aggregate limit | None | None | Passed |
| exact limit | ['cell', 'cell', 'cell'] | ['cell', 'cell', 'cell'] | Passed |
| ordinary | ['cell', 'z'] | ['cell', 'z'] | Passed |
| space value | [' cell '] | [' cell '] | Passed |
| empty field | [''] | [''] | Passed |
SHA-256 / c4c6dba4b0c009129f05032cdf484a260580755d445d593794dc70ac4b48d9a5
2 / The unsuccessful fix
Exit 1"""Failure Map reference implementation. Python standard library only."""
import json
def _vary(value):
if value == '@END': return 3 + 4*N
if isinstance(value, str): return value.replace('@', 'cell' * N)
if isinstance(value, list): return [_vary(x) for x in value]
if isinstance(value, dict): return {_vary(k): _vary(v) for k,v in value.items()}
return value
N = 1
observations = []
def solve(data):
out = []
for cell in data['row'].split(','):
if '*' in cell:
count, value = cell.split('*', 1)
if not count.isascii() or not count.isdecimal(): return None
count = int(count)
if count <= 0: count = 1
else: count, value = 1, cell
if len(out) + count > data['budget']: return None
out.extend([value] * count)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('expanded', solve(_vary({'row': '2*@,x', 'budget': 3})), _vary(['@', '@', 'x']))
check('star value', solve(_vary({'row': '2*a*b', 'budget': 2})), _vary(['a*b', 'a*b']))
check('empty repeated', solve(_vary({'row': '2*', 'budget': 2})), _vary(['', '']))
check('zero', solve(_vary({'row': '0*x', 'budget': 2})), _vary(None))
check('negative', solve(_vary({'row': '-1*x', 'budget': 2})), _vary(None))
check('aggregate limit', solve(_vary({'row': '2*x,2*y', 'budget': 3})), _vary(None))
check('exact limit', solve(_vary({'row': '3*@', 'budget': 3})), _vary(['@', '@', '@']))
check('ordinary', solve(_vary({'row': '@,z', 'budget': 2})), _vary(['@', 'z']))
check('space value', solve(_vary({'row': ' @ ', 'budget': 1})), _vary([' @ ']))
check('empty field', solve(_vary({'row': '', 'budget': 1})), _vary(['']))
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| expanded | ['cell', 'cell', 'x'] | ['cell', 'cell', 'x'] | Passed |
| star value | ['a*b', 'a*b'] | ['a*b', 'a*b'] | Passed |
| empty repeated | ['', ''] | ['', ''] | Passed |
| zero | ['x'] | None | Failed |
| negative | None | None | Passed |
| aggregate limit | None | None | Passed |
| exact limit | ['cell', 'cell', 'cell'] | ['cell', 'cell', 'cell'] | Passed |
| ordinary | ['cell', 'z'] | ['cell', 'z'] | Passed |
| space value | [' cell '] | [' cell '] | Passed |
| empty field | [''] | [''] | Passed |
SHA-256 / d68e2f33922465b514c75549e8185e4cde772ca341e223cdc9d8493421a7bf1e
3 / The verified repair
Exit 0"""Failure Map reference implementation. Python standard library only."""
import json
def _vary(value):
if value == '@END': return 3 + 4*N
if isinstance(value, str): return value.replace('@', 'cell' * N)
if isinstance(value, list): return [_vary(x) for x in value]
if isinstance(value, dict): return {_vary(k): _vary(v) for k,v in value.items()}
return value
N = 1
observations = []
def solve(data):
out = []
for cell in data['row'].split(','):
if '*' in cell:
count, value = cell.split('*', 1)
if not count.isascii() or not count.isdecimal(): return None
count = int(count)
if count <= 0: return None
else: count, value = 1, cell
if len(out) + count > data['budget']: return None
out.extend([value] * count)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('expanded', solve(_vary({'row': '2*@,x', 'budget': 3})), _vary(['@', '@', 'x']))
check('star value', solve(_vary({'row': '2*a*b', 'budget': 2})), _vary(['a*b', 'a*b']))
check('empty repeated', solve(_vary({'row': '2*', 'budget': 2})), _vary(['', '']))
check('zero', solve(_vary({'row': '0*x', 'budget': 2})), _vary(None))
check('negative', solve(_vary({'row': '-1*x', 'budget': 2})), _vary(None))
check('aggregate limit', solve(_vary({'row': '2*x,2*y', 'budget': 3})), _vary(None))
check('exact limit', solve(_vary({'row': '3*@', 'budget': 3})), _vary(['@', '@', '@']))
check('ordinary', solve(_vary({'row': '@,z', 'budget': 2})), _vary(['@', 'z']))
check('space value', solve(_vary({'row': ' @ ', 'budget': 1})), _vary([' @ ']))
check('empty field', solve(_vary({'row': '', 'budget': 1})), _vary(['']))
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
| Boundary fixture | Actual | Expected | Outcome |
|---|---|---|---|
| expanded | ['cell', 'cell', 'x'] | ['cell', 'cell', 'x'] | Passed |
| star value | ['a*b', 'a*b'] | ['a*b', 'a*b'] | Passed |
| empty repeated | ['', ''] | ['', ''] | Passed |
| zero | None | None | Passed |
| negative | None | None | Passed |
| aggregate limit | None | None | Passed |
| exact limit | ['cell', 'cell', 'cell'] | ['cell', 'cell', 'cell'] | Passed |
| ordinary | ['cell', 'z'] | ['cell', 'z'] | Passed |
| space value | [' cell '] | [' cell '] | Passed |
| empty field | [''] | [''] | Passed |
SHA-256 / 63773b057cc3b84576a3f7026468a14689432628cf8fb8f96357624fb853bab5
Verification & scope
Deterministic bounded in-memory model. No claim of complete CSV or external format conformance. This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.
Observations recorded using Python 3.12.14 at 2026-09-29T14:44:43.138012+00:00.
Case digest / b00d7bcb031d4fa45ae28dfc279723e459c46d3b5c3830a2859871e19fd80c98