FA-47441 / Delimited text / Open access
A quoted null marker is coerced to missing data · case 01
A structured table violates the declared record or column contract.
ROOT CAUSE
Null conversion loses the quote-origin bit from the lexer.
VERIFIED REPAIR
Preserve the named invariant at the faulty decision: if not quoted and text == 'NULL':
Unsuccessful approach: Case-folding the marker creates a different unsupported null spelling.
Case contract
Read already lexed cells represented as [text, was_quoted]. Only unquoted NULL is null. An unquoted empty cell is absent, encoded as {missing:True}; quoted empties are empty strings. Unquoted !DEFAULT expands to supplied default. Ordinary whitespace is significant.
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 text, quoted in data['cells']:
if text == 'NULL': out.append(None)
elif not quoted and text == '': out.append({'missing': True})
elif not quoted and text == '!DEFAULT': out.append(data['default'])
else: out.append(text)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('null origin', solve(_vary({'cells': [['NULL', False], ['NULL', True]], 'default': '@'})), _vary([None, 'NULL']))
check('empty origin', solve(_vary({'cells': [['', False], ['', True]], 'default': '@'})), _vary([{'missing': True}, '']))
check('default origin', solve(_vary({'cells': [['!DEFAULT', False], ['!DEFAULT', True]], 'default': '@'})), _vary(['@', '!DEFAULT']))
check('spaces', solve(_vary({'cells': [[' NULL ', False], [' ', True]], 'default': '@'})), _vary([' NULL ', ' ']))
check('case', solve(_vary({'cells': [['null', False]], 'default': '@'})), _vary(['null']))
check('normal', solve(_vary({'cells': [['@', False]], 'default': 'z'})), _vary(['@']))
check('no columns', solve(_vary({'cells': [], 'default': '@'})), _vary([]))
check('bare space', solve(_vary({'cells': [[' ', False]], 'default': '@'})), _vary([' ']))
check('unknown directive', solve(_vary({'cells': [['!hello', False]], 'default': '@'})), _vary(['!hello']))
check('typed default', solve(_vary({'cells': [['!DEFAULT', False]], 'default': 7})), _vary([7]))
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 |
|---|---|---|---|
| null origin | [None, None] | [None, 'NULL'] | Failed |
| empty origin | [{'missing': True}, ''] | [{'missing': True}, ''] | Passed |
| default origin | ['cell', '!DEFAULT'] | ['cell', '!DEFAULT'] | Passed |
| spaces | [' NULL ', ' '] | [' NULL ', ' '] | Passed |
| case | ['null'] | ['null'] | Passed |
| normal | ['cell'] | ['cell'] | Passed |
| no columns | [] | [] | Passed |
| bare space | [' '] | [' '] | Passed |
| unknown directive | ['!hello'] | ['!hello'] | Passed |
| typed default | [7] | [7] | Passed |
SHA-256 / cf97484a3cd7e45a0e7a71860448e24d1111849bcd31ae55b0728f44f8ff83af
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 text, quoted in data['cells']:
if text.upper() == 'NULL' and not quoted: out.append(None)
elif not quoted and text == '': out.append({'missing': True})
elif not quoted and text == '!DEFAULT': out.append(data['default'])
else: out.append(text)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('null origin', solve(_vary({'cells': [['NULL', False], ['NULL', True]], 'default': '@'})), _vary([None, 'NULL']))
check('empty origin', solve(_vary({'cells': [['', False], ['', True]], 'default': '@'})), _vary([{'missing': True}, '']))
check('default origin', solve(_vary({'cells': [['!DEFAULT', False], ['!DEFAULT', True]], 'default': '@'})), _vary(['@', '!DEFAULT']))
check('spaces', solve(_vary({'cells': [[' NULL ', False], [' ', True]], 'default': '@'})), _vary([' NULL ', ' ']))
check('case', solve(_vary({'cells': [['null', False]], 'default': '@'})), _vary(['null']))
check('normal', solve(_vary({'cells': [['@', False]], 'default': 'z'})), _vary(['@']))
check('no columns', solve(_vary({'cells': [], 'default': '@'})), _vary([]))
check('bare space', solve(_vary({'cells': [[' ', False]], 'default': '@'})), _vary([' ']))
check('unknown directive', solve(_vary({'cells': [['!hello', False]], 'default': '@'})), _vary(['!hello']))
check('typed default', solve(_vary({'cells': [['!DEFAULT', False]], 'default': 7})), _vary([7]))
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 |
|---|---|---|---|
| null origin | [None, 'NULL'] | [None, 'NULL'] | Passed |
| empty origin | [{'missing': True}, ''] | [{'missing': True}, ''] | Passed |
| default origin | ['cell', '!DEFAULT'] | ['cell', '!DEFAULT'] | Passed |
| spaces | [' NULL ', ' '] | [' NULL ', ' '] | Passed |
| case | [None] | ['null'] | Failed |
| normal | ['cell'] | ['cell'] | Passed |
| no columns | [] | [] | Passed |
| bare space | [' '] | [' '] | Passed |
| unknown directive | ['!hello'] | ['!hello'] | Passed |
| typed default | [7] | [7] | Passed |
SHA-256 / 7cbeb89bde2b4f3dd86871f8f8c83d7b6c71eabda3c335efddf081e420e98b93
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 text, quoted in data['cells']:
if not quoted and text == 'NULL': out.append(None)
elif not quoted and text == '': out.append({'missing': True})
elif not quoted and text == '!DEFAULT': out.append(data['default'])
else: out.append(text)
return out
def check(label, actual, expected):
observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('null origin', solve(_vary({'cells': [['NULL', False], ['NULL', True]], 'default': '@'})), _vary([None, 'NULL']))
check('empty origin', solve(_vary({'cells': [['', False], ['', True]], 'default': '@'})), _vary([{'missing': True}, '']))
check('default origin', solve(_vary({'cells': [['!DEFAULT', False], ['!DEFAULT', True]], 'default': '@'})), _vary(['@', '!DEFAULT']))
check('spaces', solve(_vary({'cells': [[' NULL ', False], [' ', True]], 'default': '@'})), _vary([' NULL ', ' ']))
check('case', solve(_vary({'cells': [['null', False]], 'default': '@'})), _vary(['null']))
check('normal', solve(_vary({'cells': [['@', False]], 'default': 'z'})), _vary(['@']))
check('no columns', solve(_vary({'cells': [], 'default': '@'})), _vary([]))
check('bare space', solve(_vary({'cells': [[' ', False]], 'default': '@'})), _vary([' ']))
check('unknown directive', solve(_vary({'cells': [['!hello', False]], 'default': '@'})), _vary(['!hello']))
check('typed default', solve(_vary({'cells': [['!DEFAULT', False]], 'default': 7})), _vary([7]))
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 |
|---|---|---|---|
| null origin | [None, 'NULL'] | [None, 'NULL'] | Passed |
| empty origin | [{'missing': True}, ''] | [{'missing': True}, ''] | Passed |
| default origin | ['cell', '!DEFAULT'] | ['cell', '!DEFAULT'] | Passed |
| spaces | [' NULL ', ' '] | [' NULL ', ' '] | Passed |
| case | ['null'] | ['null'] | Passed |
| normal | ['cell'] | ['cell'] | Passed |
| no columns | [] | [] | Passed |
| bare space | [' '] | [' '] | Passed |
| unknown directive | ['!hello'] | ['!hello'] | Passed |
| typed default | [7] | [7] | Passed |
SHA-256 / b98970a593fb05d078fcc9fdc54c8292a657af691f44a73438939e286aaba864
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 2026-09-29T14:44:41.532674+00:00.
Case digest / 297e595e41ed6f5103491c6ead818e0470131b0d3461ed37cdca3bc12b0f7816