FAILURE MAP
← Case archive

FA-47406 / Delimited text / Open access

Raw newlines are accepted inside a one-record TSV API · 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 single-record reader permits physical row terminators as cell data.

VERIFIED REPAIR

Preserve the named invariant at the faulty decision: elif ch in '\r\n': return None

Unsuccessful approach: Rejecting carriage returns alone still admits a raw line feed.

Case contract

Decode TSV fields with exactly four escapes: backslash-t, backslash-n, backslash-r, backslash-backslash. Raw tabs split fields, raw newlines are forbidden; unknown and dangling escapes reject the row. Empty input is one empty field.

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, field, escaped = [], [], False
    for ch in data:
        if escaped:
            if ch not in 'tnr\\': return None
            field.append({'t':'\t','n':'\n','r':'\r','\\':'\\'}[ch])
            escaped = False
        elif ch == '\\': escaped = True
        elif ch == '\t':
            out.append(''.join(field))
            field = []
        elif False: return None
        else: field.append(ch)
    if escaped: return None
    out.append(''.join(field))
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('mapped escapes', solve(_vary('@\\tA\\nB\\rC\\\\D')), _vary(['@\tA\nB\rC\\D']))
check('separators', solve(_vary('@\t\tZ')), _vary(['@', '', 'Z']))
check('escaped backslash then t', solve(_vary('\\\\t')), _vary(['\\t']))
check('unknown', solve(_vary('\\q')), _vary(None))
check('dangling', solve(_vary('@\\')), _vary(None))
check('raw newline', solve(_vary('@\nZ')), _vary(None))
check('empty', solve(_vary('')), _vary(['']))
check('leading trailing', solve(_vary('\t@\t')), _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 fixtureActualExpectedOutcome
mapped escapes['cell\tA\nB\rC\\D']['cell\tA\nB\rC\\D']Passed
separators['cell', '', 'Z']['cell', '', 'Z']Passed
escaped backslash then t['\\t']['\\t']Passed
unknownNoneNonePassed
danglingNoneNonePassed
raw newline['cell\nZ']NoneFailed
empty['']['']Passed
leading trailing['', 'cell', '']['', 'cell', '']Passed

SHA-256 / 04ef1b64beea97a4918c4cbf6a5cd549dc9273215e04540b0130af0196766098

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, field, escaped = [], [], False
    for ch in data:
        if escaped:
            if ch not in 'tnr\\': return None
            field.append({'t':'\t','n':'\n','r':'\r','\\':'\\'}[ch])
            escaped = False
        elif ch == '\\': escaped = True
        elif ch == '\t':
            out.append(''.join(field))
            field = []
        elif ch == '\r': return None
        else: field.append(ch)
    if escaped: return None
    out.append(''.join(field))
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('mapped escapes', solve(_vary('@\\tA\\nB\\rC\\\\D')), _vary(['@\tA\nB\rC\\D']))
check('separators', solve(_vary('@\t\tZ')), _vary(['@', '', 'Z']))
check('escaped backslash then t', solve(_vary('\\\\t')), _vary(['\\t']))
check('unknown', solve(_vary('\\q')), _vary(None))
check('dangling', solve(_vary('@\\')), _vary(None))
check('raw newline', solve(_vary('@\nZ')), _vary(None))
check('empty', solve(_vary('')), _vary(['']))
check('leading trailing', solve(_vary('\t@\t')), _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 fixtureActualExpectedOutcome
mapped escapes['cell\tA\nB\rC\\D']['cell\tA\nB\rC\\D']Passed
separators['cell', '', 'Z']['cell', '', 'Z']Passed
escaped backslash then t['\\t']['\\t']Passed
unknownNoneNonePassed
danglingNoneNonePassed
raw newline['cell\nZ']NoneFailed
empty['']['']Passed
leading trailing['', 'cell', '']['', 'cell', '']Passed

SHA-256 / ea47dc5cf65fed7eeca18086ec4b38e0d3879e9b089ebb514d21a30c109d788c

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, field, escaped = [], [], False
    for ch in data:
        if escaped:
            if ch not in 'tnr\\': return None
            field.append({'t':'\t','n':'\n','r':'\r','\\':'\\'}[ch])
            escaped = False
        elif ch == '\\': escaped = True
        elif ch == '\t':
            out.append(''.join(field))
            field = []
        elif ch in '\r\n': return None
        else: field.append(ch)
    if escaped: return None
    out.append(''.join(field))
    return out
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('mapped escapes', solve(_vary('@\\tA\\nB\\rC\\\\D')), _vary(['@\tA\nB\rC\\D']))
check('separators', solve(_vary('@\t\tZ')), _vary(['@', '', 'Z']))
check('escaped backslash then t', solve(_vary('\\\\t')), _vary(['\\t']))
check('unknown', solve(_vary('\\q')), _vary(None))
check('dangling', solve(_vary('@\\')), _vary(None))
check('raw newline', solve(_vary('@\nZ')), _vary(None))
check('empty', solve(_vary('')), _vary(['']))
check('leading trailing', solve(_vary('\t@\t')), _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 fixtureActualExpectedOutcome
mapped escapes['cell\tA\nB\rC\\D']['cell\tA\nB\rC\\D']Passed
separators['cell', '', 'Z']['cell', '', 'Z']Passed
escaped backslash then t['\\t']['\\t']Passed
unknownNoneNonePassed
danglingNoneNonePassed
raw newlineNoneNonePassed
empty['']['']Passed
leading trailing['', 'cell', '']['', 'cell', '']Passed

SHA-256 / 98c681e1d643b08c156bd53a4503ea6ecd2ea6bf8f46c1fef0a558a502918826

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 2026-09-29T14:44:41.103548+00:00.

Case digest / 117a965544c8411a9fe17d8603bd35f39031a5258199fc461711355d6d795353