FAILURE MAP
← Case archive

FA-47801 / Delimited text / Open access

Two source columns bind to one canonical schema position · case 01

A structured table violates the declared record or column contract.

Verified by executionVariant 1 · 10 checks per implementationDownload source bundle ↓JSON ↗

ROOT CAUSE

Canonical alias collisions are collapsed silently.

VERIFIED REPAIR

Preserve the named invariant at the faulty decision: if name in resolved: return None

Unsuccessful approach: Keeping the last occurrence instead of the first still loses physical identity.

Case contract

Resolve comma header names through an alias map, then produce a permutation into required canonical columns. A header name may follow multiple alias hops; cycles reject. Reject two physical columns resolving to one canonical name, unknown names, or missing required names. Return physical indexes in required 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):
    resolved = []
    for name in data['header'].split(','):
        seen = set()
        while name in data['aliases']:
            if name in seen: return None
            seen.add(name)
            name = data['aliases'][name]
        if name not in data['required']: return None
        if name in resolved: continue
        resolved.append(name)
    if set(resolved) != set(data['required']): return None
    return [resolved.index(name) for name in data['required']]
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('chain', solve(_vary({'header': 'legacy,b', 'aliases': {'legacy': 'old', 'old': 'a'}, 'required': ['a', 'b']})), _vary([0, 1]))
check('reorder', solve(_vary({'header': 'b,@', 'aliases': {'@': 'a'}, 'required': ['a', 'b']})), _vary([1, 0]))
check('cycle', solve(_vary({'header': 'x,b', 'aliases': {'x': 'y', 'y': 'x'}, 'required': ['a', 'b']})), _vary(None))
check('collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a', 'b']})), _vary(None))
check('unknown', solve(_vary({'header': 'a,z', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('missing', solve(_vary({'header': 'a', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('normal', solve(_vary({'header': 'a,b', 'aliases': {}, 'required': ['a', 'b']})), _vary([0, 1]))
check('cycle permutation', solve(_vary({'header': 'b,c,a', 'aliases': {}, 'required': ['a', 'b', 'c']})), _vary([2, 0, 1]))
check('full collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a']})), _vary(None))
check('shared tail', solve(_vary({'header': 'x,y', 'aliases': {'x': 'a', 'y': 'b'}, 'required': ['a', 'b']})), _vary([0, 1]))
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 fixtureActualExpectedOutcome
chain[0, 1][0, 1]Passed
reorder[1, 0][1, 0]Passed
cycleNoneNonePassed
collisionNoneNonePassed
unknownNoneNonePassed
missingNoneNonePassed
normal[0, 1][0, 1]Passed
cycle permutation[2, 0, 1][2, 0, 1]Passed
full collision[0]NoneFailed
shared tail[0, 1][0, 1]Passed

SHA-256 / a8d4bf7600305153fae4bdfceb85ed0cc1f13ca569e4fcc5a11f37a539c02ada

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):
    resolved = []
    for name in data['header'].split(','):
        seen = set()
        while name in data['aliases']:
            if name in seen: return None
            seen.add(name)
            name = data['aliases'][name]
        if name not in data['required']: return None
        if name in resolved: resolved.remove(name)
        resolved.append(name)
    if set(resolved) != set(data['required']): return None
    return [resolved.index(name) for name in data['required']]
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('chain', solve(_vary({'header': 'legacy,b', 'aliases': {'legacy': 'old', 'old': 'a'}, 'required': ['a', 'b']})), _vary([0, 1]))
check('reorder', solve(_vary({'header': 'b,@', 'aliases': {'@': 'a'}, 'required': ['a', 'b']})), _vary([1, 0]))
check('cycle', solve(_vary({'header': 'x,b', 'aliases': {'x': 'y', 'y': 'x'}, 'required': ['a', 'b']})), _vary(None))
check('collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a', 'b']})), _vary(None))
check('unknown', solve(_vary({'header': 'a,z', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('missing', solve(_vary({'header': 'a', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('normal', solve(_vary({'header': 'a,b', 'aliases': {}, 'required': ['a', 'b']})), _vary([0, 1]))
check('cycle permutation', solve(_vary({'header': 'b,c,a', 'aliases': {}, 'required': ['a', 'b', 'c']})), _vary([2, 0, 1]))
check('full collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a']})), _vary(None))
check('shared tail', solve(_vary({'header': 'x,y', 'aliases': {'x': 'a', 'y': 'b'}, 'required': ['a', 'b']})), _vary([0, 1]))
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 fixtureActualExpectedOutcome
chain[0, 1][0, 1]Passed
reorder[1, 0][1, 0]Passed
cycleNoneNonePassed
collisionNoneNonePassed
unknownNoneNonePassed
missingNoneNonePassed
normal[0, 1][0, 1]Passed
cycle permutation[2, 0, 1][2, 0, 1]Passed
full collision[0]NoneFailed
shared tail[0, 1][0, 1]Passed

SHA-256 / fc349ca754f332d9d197bb9585ef3ecc38745a6ff602f8132cc7cbd0b0aa62a6

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):
    resolved = []
    for name in data['header'].split(','):
        seen = set()
        while name in data['aliases']:
            if name in seen: return None
            seen.add(name)
            name = data['aliases'][name]
        if name not in data['required']: return None
        if name in resolved: return None
        resolved.append(name)
    if set(resolved) != set(data['required']): return None
    return [resolved.index(name) for name in data['required']]
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('chain', solve(_vary({'header': 'legacy,b', 'aliases': {'legacy': 'old', 'old': 'a'}, 'required': ['a', 'b']})), _vary([0, 1]))
check('reorder', solve(_vary({'header': 'b,@', 'aliases': {'@': 'a'}, 'required': ['a', 'b']})), _vary([1, 0]))
check('cycle', solve(_vary({'header': 'x,b', 'aliases': {'x': 'y', 'y': 'x'}, 'required': ['a', 'b']})), _vary(None))
check('collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a', 'b']})), _vary(None))
check('unknown', solve(_vary({'header': 'a,z', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('missing', solve(_vary({'header': 'a', 'aliases': {}, 'required': ['a', 'b']})), _vary(None))
check('normal', solve(_vary({'header': 'a,b', 'aliases': {}, 'required': ['a', 'b']})), _vary([0, 1]))
check('cycle permutation', solve(_vary({'header': 'b,c,a', 'aliases': {}, 'required': ['a', 'b', 'c']})), _vary([2, 0, 1]))
check('full collision', solve(_vary({'header': 'old,a', 'aliases': {'old': 'a'}, 'required': ['a']})), _vary(None))
check('shared tail', solve(_vary({'header': 'x,y', 'aliases': {'x': 'a', 'y': 'b'}, 'required': ['a', 'b']})), _vary([0, 1]))
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 fixtureActualExpectedOutcome
chain[0, 1][0, 1]Passed
reorder[1, 0][1, 0]Passed
cycleNoneNonePassed
collisionNoneNonePassed
unknownNoneNonePassed
missingNoneNonePassed
normal[0, 1][0, 1]Passed
cycle permutation[2, 0, 1][2, 0, 1]Passed
full collisionNoneNonePassed
shared tail[0, 1][0, 1]Passed

SHA-256 / 1068010a0bd6ae26a603eebbd5f164e20fc8f1d21be8df72fd6012fbe10bde9d

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 2026-09-29T14:44:44.899486+00:00.

Case digest / 29bb1218a2eb8481189d3d0d0f58026c9fe680070102200631d920b138987ffc