FA-47961 / Delimited text / Open access

Header disambiguation computes a suffix but emits the raw name · case 01

A structured table violates the declared record or column contract.

Verified by executionVariant 1 · 8 checks per implementationDownload source bundle ↓JSON ↗

ROOT CAUSE

The resolved name is discarded at emission.

VERIFIED REPAIR

Preserve the named invariant at the faulty decision: out.append(candidate)

Unsuccessful approach: Stripping suffixes after resolution recreates the collision.

Case contract

Assign unique output names to repeated raw column names. First occurrence keeps its name; later duplicates append _2, _3, etc, skipping names already present anywhere in the raw header and names already assigned. Empty raw names use column<one-based-position> before collision handling. Preserve order.

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):
    raw = data.split(',')
    base = [name if name else 'column' + str(i+1) for i,name in enumerate(raw)]
    reserved, used, out = set(base), set(), []
    for name in base:
        candidate = name
        suffix = 2
        while candidate in used:
            candidate = name + '_' + str(suffix)
            suffix += 1
            while candidate in reserved:
                candidate = name + '_' + str(suffix)
                suffix += 1
        out.append(name)
        used.add(candidate)
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('duplicates', solve(_vary('@,@,@')), _vary(['@', '@_2', '@_3']))
check('reserved', solve(_vary('a,a,a_2')), _vary(['a', 'a_3', 'a_2']))
check('multiple reserves', solve(_vary('a,a,a_2,a_3')), _vary(['a', 'a_4', 'a_2', 'a_3']))
check('blanks', solve(_vary(',x,')), _vary(['column1', 'x', 'column3']))
check('ordinary', solve(_vary('a,b')), _vary(['a', 'b']))
check('nested base', solve(_vary('a,a,a_2,a_2')), _vary(['a', 'a_3', 'a_2', 'a_2_2']))
check('empty', solve(_vary('')), _vary(['column1']))
check('reserved generated', solve(_vary('column2,,column2')), _vary(['column2', 'column2_2', 'column2_3']))
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
duplicates	`['cell', 'cell', 'cell']`	`['cell', 'cell_2', 'cell_3']`	Failed
reserved	`['a', 'a', 'a_2']`	`['a', 'a_3', 'a_2']`	Failed
multiple reserves	`['a', 'a', 'a_2', 'a_3']`	`['a', 'a_4', 'a_2', 'a_3']`	Failed
blanks	`['column1', 'x', 'column3']`	`['column1', 'x', 'column3']`	Passed
ordinary	`['a', 'b']`	`['a', 'b']`	Passed
nested base	`['a', 'a', 'a_2', 'a_2']`	`['a', 'a_3', 'a_2', 'a_2_2']`	Failed
empty	`['column1']`	`['column1']`	Passed
reserved generated	`['column2', 'column2', 'column2']`	`['column2', 'column2_2', 'column2_3']`	Failed

SHA-256 / 11b18f19058c8d7261ac2e8550396b5bb48282da255c2e926fe9af7466db138f

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):
    raw = data.split(',')
    base = [name if name else 'column' + str(i+1) for i,name in enumerate(raw)]
    reserved, used, out = set(base), set(), []
    for name in base:
        candidate = name
        suffix = 2
        while candidate in used:
            candidate = name + '_' + str(suffix)
            suffix += 1
            while candidate in reserved:
                candidate = name + '_' + str(suffix)
                suffix += 1
        out.append(candidate.split('_')[0])
        used.add(candidate)
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('duplicates', solve(_vary('@,@,@')), _vary(['@', '@_2', '@_3']))
check('reserved', solve(_vary('a,a,a_2')), _vary(['a', 'a_3', 'a_2']))
check('multiple reserves', solve(_vary('a,a,a_2,a_3')), _vary(['a', 'a_4', 'a_2', 'a_3']))
check('blanks', solve(_vary(',x,')), _vary(['column1', 'x', 'column3']))
check('ordinary', solve(_vary('a,b')), _vary(['a', 'b']))
check('nested base', solve(_vary('a,a,a_2,a_2')), _vary(['a', 'a_3', 'a_2', 'a_2_2']))
check('empty', solve(_vary('')), _vary(['column1']))
check('reserved generated', solve(_vary('column2,,column2')), _vary(['column2', 'column2_2', 'column2_3']))
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
duplicates	`['cell', 'cell', 'cell']`	`['cell', 'cell_2', 'cell_3']`	Failed
reserved	`['a', 'a', 'a']`	`['a', 'a_3', 'a_2']`	Failed
multiple reserves	`['a', 'a', 'a', 'a']`	`['a', 'a_4', 'a_2', 'a_3']`	Failed
blanks	`['column1', 'x', 'column3']`	`['column1', 'x', 'column3']`	Passed
ordinary	`['a', 'b']`	`['a', 'b']`	Passed
nested base	`['a', 'a', 'a', 'a']`	`['a', 'a_3', 'a_2', 'a_2_2']`	Failed
empty	`['column1']`	`['column1']`	Passed
reserved generated	`['column2', 'column2', 'column2']`	`['column2', 'column2_2', 'column2_3']`	Failed

SHA-256 / 35110d7c6b328b55a5559a737fa88c5bfa02f24948acd23433ad328ad26df5f7

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):
    raw = data.split(',')
    base = [name if name else 'column' + str(i+1) for i,name in enumerate(raw)]
    reserved, used, out = set(base), set(), []
    for name in base:
        candidate = name
        suffix = 2
        while candidate in used:
            candidate = name + '_' + str(suffix)
            suffix += 1
            while candidate in reserved:
                candidate = name + '_' + str(suffix)
                suffix += 1
        out.append(candidate)
        used.add(candidate)
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('duplicates', solve(_vary('@,@,@')), _vary(['@', '@_2', '@_3']))
check('reserved', solve(_vary('a,a,a_2')), _vary(['a', 'a_3', 'a_2']))
check('multiple reserves', solve(_vary('a,a,a_2,a_3')), _vary(['a', 'a_4', 'a_2', 'a_3']))
check('blanks', solve(_vary(',x,')), _vary(['column1', 'x', 'column3']))
check('ordinary', solve(_vary('a,b')), _vary(['a', 'b']))
check('nested base', solve(_vary('a,a,a_2,a_2')), _vary(['a', 'a_3', 'a_2', 'a_2_2']))
check('empty', solve(_vary('')), _vary(['column1']))
check('reserved generated', solve(_vary('column2,,column2')), _vary(['column2', 'column2_2', 'column2_3']))
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
duplicates	`['cell', 'cell_2', 'cell_3']`	`['cell', 'cell_2', 'cell_3']`	Passed
reserved	`['a', 'a_3', 'a_2']`	`['a', 'a_3', 'a_2']`	Passed
multiple reserves	`['a', 'a_4', 'a_2', 'a_3']`	`['a', 'a_4', 'a_2', 'a_3']`	Passed
blanks	`['column1', 'x', 'column3']`	`['column1', 'x', 'column3']`	Passed
ordinary	`['a', 'b']`	`['a', 'b']`	Passed
nested base	`['a', 'a_3', 'a_2', 'a_2_2']`	`['a', 'a_3', 'a_2', 'a_2_2']`	Passed
empty	`['column1']`	`['column1']`	Passed
reserved generated	`['column2', 'column2_2', 'column2_3']`	`['column2', 'column2_2', 'column2_3']`	Passed

SHA-256 / fb4f4c33c5e2de48d6932ee009ec47fcbfbb0b5994c9917f6343315548438bfe

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 2026-09-29T14:44:46.393919+00:00.

Case digest / 850428df95bb9f2811cf649d7192e8e90d87d10ba0b0584801a4fe71344990a8