Skip to content

climate_ref_core.regression.manifest #

Manifest model and digest utilities for test case regression bundles.

The manifest (manifest.json) lives alongside a test case's regression data. It records: - schema: the manifest schema version (SCHEMA_VERSION). - test_case_version: a monotonic, author-bumped integer coupling the committed bundle to its native outputs. - committed: sha256 digests of the committed regression JSON artefacts, computed over the exact placeholder-substituted bytes as they sit on disk, so that a CI recompute is deterministic. - native: digests of the curated native output files, authored ONLY by mint.

Digests use sha256 throughout for hashing files.

COMMITTED_BUNDLE_FILES = ('series.json', 'diagnostic.json', 'output.json') module-attribute #

The committed CMEC artefacts tracked in git.

Their digests are tracked in :attr:Manifest.committed.

SCHEMA_VERSION = 1 module-attribute #

Current manifest schema version.

Manifest #

The on-disk manifest for a test case regression bundle.

Serialised as manifest.json with stable key ordering and a trailing newline, so repeated dumps are byte-identical.

Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
@frozen
class Manifest:
    """
    The on-disk manifest for a test case regression bundle.

    Serialised as ``manifest.json`` with stable key ordering and a trailing newline,
    so repeated dumps are byte-identical.
    """

    schema: int
    """Manifest schema version; equals :data:`SCHEMA_VERSION` for current manifests."""

    test_case_version: int
    """Monotonic, author-bumped version coupling the bundle to its native outputs."""

    committed: dict[str, str]
    """Digests of committed regression JSON artefacts: ``{relpath: sha256}``."""

    native: dict[str, NativeEntry]
    """Digests of curated native output files: ``{relpath: NativeEntry}``."""

    catalog_hash: str | None = None
    """Hash of the test case input ``catalog.yaml`` (its ``_metadata.hash``) that produced this baseline.
    This couples the baseline to its inputs.
    The CI gate fails a case whose live catalog hash no longer matches this value.
    """

    @classmethod
    def load(cls, path: Path) -> Manifest:
        """
        Load a manifest from ``manifest.json``.

        Parameters
        ----------
        path
            Path to the manifest file.

        Returns
        -------
        :
            The parsed manifest.

        Raises
        ------
        ValueError
            If the manifest is missing required keys or has malformed native entries
            (e.g. hand-edited or written by an incompatible version).
        """
        return cls.loads(path.read_text(encoding="utf-8"), source=str(path))

    @classmethod
    def loads(cls, text: str, *, source: str = "<string>") -> Manifest:
        """
        Parse a manifest from its JSON text.

        Used when the manifest does not live on disk at parse time,
        e.g. when reading the base-branch copy via ``git show`` for the CI coupling gate.

        Parameters
        ----------
        text
            The manifest JSON.
        source
            A label for the text's origin, used in error messages.

        Returns
        -------
        :
            The parsed manifest.

        Raises
        ------
        ValueError
            If the manifest is missing required keys or has malformed native entries
            (e.g. hand-edited or written by an incompatible version).
        """
        data = json.loads(text)
        missing = [key for key in ("schema", "test_case_version", "committed", "native") if key not in data]
        if missing:
            raise ValueError(
                f"Invalid manifest {source}: missing required keys {missing}. "
                "The manifest may be corrupted or written by an incompatible version; "
                "regenerate it with `ref test-cases run --force-regen`."
            )
        schema = data["schema"]
        if isinstance(schema, bool) or not isinstance(schema, int) or schema != SCHEMA_VERSION:
            raise ValueError(
                f"Invalid manifest {source}: unsupported schema {schema!r}, "
                f"expected {SCHEMA_VERSION}. The manifest was written by an incompatible "
                "version; regenerate it with `ref test-cases run --force-regen`."
            )
        try:
            native = {
                relpath: NativeEntry(sha256=entry["sha256"], size=entry["size"])
                for relpath, entry in data["native"].items()
            }
        except (KeyError, TypeError, AttributeError) as exc:
            raise ValueError(
                f"Invalid manifest {source}: malformed 'native' entry ({exc!r}). "
                "Each entry must be a mapping with 'sha256' and 'size' keys."
            ) from exc
        # Reject hand-edited or hostile manifests that could escape the
        # destination directory or carry a malformed digest when materialised.
        for relpath, entry in native.items():
            try:
                safe_path(relpath, label="native path")
            except ValueError as exc:
                raise ValueError(f"Invalid manifest {source}: {exc}") from exc
            _validate_digest(entry.sha256)
            if isinstance(entry.size, bool) or not isinstance(entry.size, int) or entry.size < 0:
                raise ValueError(
                    f"Invalid manifest {source}: native entry {relpath!r} has invalid size "
                    f"{entry.size!r}; expected a non-negative integer."
                )
        return cls(
            schema=data["schema"],
            test_case_version=data["test_case_version"],
            committed=dict(data["committed"]),
            native=native,
            # TODO: remove optonality when all manifests have this field.
            catalog_hash=data.get("catalog_hash"),
        )

    def dump(self, path: Path) -> None:
        """
        Write the manifest to ``manifest.json``.

        Keys are stably ordered (``sort_keys=True``) and a trailing newline is added,
        so ``dump`` followed by ``load`` round-trips byte-identically.

        Parameters
        ----------
        path
            Path to write the manifest to.
        """
        payload = {
            "schema": self.schema,
            "test_case_version": self.test_case_version,
            "catalog_hash": self.catalog_hash,
            "committed": self.committed,
            "native": {relpath: asdict(entry) for relpath, entry in self.native.items()},
        }
        text = json.dumps(payload, indent=2, sort_keys=True) + "\n"
        path.write_text(text, encoding="utf-8")

    @classmethod
    def seed_v1(cls, committed_digests: dict[str, str], catalog_hash: str | None = None) -> Manifest:
        """
        Create an initial manifest at ``test_case_version == 1`` with no native outputs.

        Parameters
        ----------
        committed_digests
            Digests of the committed regression JSON artefacts.
        catalog_hash
            Hash of the input ``catalog.yaml`` that produced the baseline, if known.

        Returns
        -------
        :
            A fresh manifest with ``test_case_version=1`` and ``native={}``.
        """
        return cls(
            schema=SCHEMA_VERSION,
            test_case_version=1,
            committed=dict(committed_digests),
            catalog_hash=catalog_hash,
            native={},
        )

catalog_hash = None class-attribute instance-attribute #

Hash of the test case input catalog.yaml (its _metadata.hash) that produced this baseline. This couples the baseline to its inputs. The CI gate fails a case whose live catalog hash no longer matches this value.

committed instance-attribute #

Digests of committed regression JSON artefacts: {relpath: sha256}.

native instance-attribute #

Digests of curated native output files: {relpath: NativeEntry}.

schema instance-attribute #

Manifest schema version; equals :data:SCHEMA_VERSION for current manifests.

test_case_version instance-attribute #

Monotonic, author-bumped version coupling the bundle to its native outputs.

dump(path) #

Write the manifest to manifest.json.

Keys are stably ordered (sort_keys=True) and a trailing newline is added, so dump followed by load round-trips byte-identically.

Parameters:

Name Type Description Default
path Path

Path to write the manifest to.

 required
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
def dump(self, path: Path) -> None:
    """
    Write the manifest to ``manifest.json``.

    Keys are stably ordered (``sort_keys=True``) and a trailing newline is added,
    so ``dump`` followed by ``load`` round-trips byte-identically.

    Parameters
    ----------
    path
        Path to write the manifest to.
    """
    payload = {
        "schema": self.schema,
        "test_case_version": self.test_case_version,
        "catalog_hash": self.catalog_hash,
        "committed": self.committed,
        "native": {relpath: asdict(entry) for relpath, entry in self.native.items()},
    }
    text = json.dumps(payload, indent=2, sort_keys=True) + "\n"
    path.write_text(text, encoding="utf-8")

load(path) classmethod #

Load a manifest from manifest.json.

Parameters:

Name Type Description Default
path Path

Path to the manifest file.

 required

Returns:

Type Description
Manifest

The parsed manifest.

Raises:

Type Description
ValueError

If the manifest is missing required keys or has malformed native entries (e.g. hand-edited or written by an incompatible version).
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
@classmethod
def load(cls, path: Path) -> Manifest:
    """
    Load a manifest from ``manifest.json``.

    Parameters
    ----------
    path
        Path to the manifest file.

    Returns
    -------
    :
        The parsed manifest.

    Raises
    ------
    ValueError
        If the manifest is missing required keys or has malformed native entries
        (e.g. hand-edited or written by an incompatible version).
    """
    return cls.loads(path.read_text(encoding="utf-8"), source=str(path))

loads(text, *, source='<string>') classmethod #

Parse a manifest from its JSON text.

Used when the manifest does not live on disk at parse time, e.g. when reading the base-branch copy via git show for the CI coupling gate.

Parameters:

Name Type Description Default
text str

The manifest JSON.

 required
source str

A label for the text's origin, used in error messages.

 '<string>'

Returns:

Type Description
Manifest

The parsed manifest.

Raises:

Type Description
ValueError

If the manifest is missing required keys or has malformed native entries (e.g. hand-edited or written by an incompatible version).
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
@classmethod
def loads(cls, text: str, *, source: str = "<string>") -> Manifest:
    """
    Parse a manifest from its JSON text.

    Used when the manifest does not live on disk at parse time,
    e.g. when reading the base-branch copy via ``git show`` for the CI coupling gate.

    Parameters
    ----------
    text
        The manifest JSON.
    source
        A label for the text's origin, used in error messages.

    Returns
    -------
    :
        The parsed manifest.

    Raises
    ------
    ValueError
        If the manifest is missing required keys or has malformed native entries
        (e.g. hand-edited or written by an incompatible version).
    """
    data = json.loads(text)
    missing = [key for key in ("schema", "test_case_version", "committed", "native") if key not in data]
    if missing:
        raise ValueError(
            f"Invalid manifest {source}: missing required keys {missing}. "
            "The manifest may be corrupted or written by an incompatible version; "
            "regenerate it with `ref test-cases run --force-regen`."
        )
    schema = data["schema"]
    if isinstance(schema, bool) or not isinstance(schema, int) or schema != SCHEMA_VERSION:
        raise ValueError(
            f"Invalid manifest {source}: unsupported schema {schema!r}, "
            f"expected {SCHEMA_VERSION}. The manifest was written by an incompatible "
            "version; regenerate it with `ref test-cases run --force-regen`."
        )
    try:
        native = {
            relpath: NativeEntry(sha256=entry["sha256"], size=entry["size"])
            for relpath, entry in data["native"].items()
        }
    except (KeyError, TypeError, AttributeError) as exc:
        raise ValueError(
            f"Invalid manifest {source}: malformed 'native' entry ({exc!r}). "
            "Each entry must be a mapping with 'sha256' and 'size' keys."
        ) from exc
    # Reject hand-edited or hostile manifests that could escape the
    # destination directory or carry a malformed digest when materialised.
    for relpath, entry in native.items():
        try:
            safe_path(relpath, label="native path")
        except ValueError as exc:
            raise ValueError(f"Invalid manifest {source}: {exc}") from exc
        _validate_digest(entry.sha256)
        if isinstance(entry.size, bool) or not isinstance(entry.size, int) or entry.size < 0:
            raise ValueError(
                f"Invalid manifest {source}: native entry {relpath!r} has invalid size "
                f"{entry.size!r}; expected a non-negative integer."
            )
    return cls(
        schema=data["schema"],
        test_case_version=data["test_case_version"],
        committed=dict(data["committed"]),
        native=native,
        # TODO: remove optonality when all manifests have this field.
        catalog_hash=data.get("catalog_hash"),
    )

seed_v1(committed_digests, catalog_hash=None) classmethod #

Create an initial manifest at test_case_version == 1 with no native outputs.

Parameters:

Name Type Description Default
committed_digests dict[str, str]

Digests of the committed regression JSON artefacts.

 required
catalog_hash str | None

Hash of the input catalog.yaml that produced the baseline, if known.

 None

Returns:

Type Description
Manifest

A fresh manifest with test_case_version=1 and native={}.
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
@classmethod
def seed_v1(cls, committed_digests: dict[str, str], catalog_hash: str | None = None) -> Manifest:
    """
    Create an initial manifest at ``test_case_version == 1`` with no native outputs.

    Parameters
    ----------
    committed_digests
        Digests of the committed regression JSON artefacts.
    catalog_hash
        Hash of the input ``catalog.yaml`` that produced the baseline, if known.

    Returns
    -------
    :
        A fresh manifest with ``test_case_version=1`` and ``native={}``.
    """
    return cls(
        schema=SCHEMA_VERSION,
        test_case_version=1,
        committed=dict(committed_digests),
        catalog_hash=catalog_hash,
        native={},
    )

NativeEntry #

A single curated native output file recorded in the manifest.

Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
110
111
112
113
114
115
116
117
118
@frozen
class NativeEntry:
    """A single curated native output file recorded in the manifest."""

    sha256: str
    """Hex-encoded sha256 digest of the curated file."""

    size: int
    """Size of the curated file in bytes."""

sha256 instance-attribute #

Hex-encoded sha256 digest of the curated file.

size instance-attribute #

Size of the curated file in bytes.

compute_committed_digests(regression_dir) #

Compute sha256 digests of the committed regression JSON artefacts.

The digests are taken over the bytes exactly as they sit on disk (placeholder text included), so a CI recompute is deterministic. Only files that exist are included.

Parameters:

Name Type Description Default
regression_dir Path

The test case regression/ directory.

 required

Returns:

Type Description
dict[str, str]

Mapping of {relpath: sha256} for each present committed artefact.
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
def compute_committed_digests(regression_dir: Path) -> dict[str, str]:
    """
    Compute sha256 digests of the committed regression JSON artefacts.

    The digests are taken over the bytes exactly as they sit on disk (placeholder text included),
    so a CI recompute is deterministic. Only files that exist are included.

    Parameters
    ----------
    regression_dir
        The test case ``regression/`` directory.

    Returns
    -------
    :
        Mapping of ``{relpath: sha256}`` for each present committed artefact.
    """
    digests: dict[str, str] = {}
    for relpath in COMMITTED_BUNDLE_FILES:
        candidate = regression_dir / relpath
        if candidate.exists():
            digests[relpath] = sha256_file(candidate)
    return digests

sha256_bytes(data) #

Compute the sha256 digest of an in-memory byte string.

Parameters:

Name Type Description Default
data bytes

The bytes to hash.

 required

Returns:

Type Description
str

The hex-encoded sha256 digest.
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
def sha256_bytes(data: bytes) -> str:
    """
    Compute the sha256 digest of an in-memory byte string.

    Parameters
    ----------
    data
        The bytes to hash.

    Returns
    -------
    :
        The hex-encoded sha256 digest.
    """
    return hashlib.sha256(data).hexdigest()

sha256_file(path) #

Compute the sha256 digest of a file.

Reuses :func:pooch.hashes.file_hash so the digest agrees with pooch elsewhere.

Parameters:

Name Type Description Default
path Path

Path to the file to hash.

 required

Returns:

Type Description
str

The hex-encoded sha256 digest.
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
def sha256_file(path: Path) -> str:
    """
    Compute the sha256 digest of a file.

    Reuses :func:`pooch.hashes.file_hash` so the digest agrees with pooch elsewhere.

    Parameters
    ----------
    path
        Path to the file to hash.

    Returns
    -------
    :
        The hex-encoded sha256 digest.
    """
    return pooch.hashes.file_hash(str(path), alg="sha256")

verify_committed_integrity(manifest, regression_dir) #

Check that the committed regression artefacts match the manifest digests.

Used by the CI integrity check. An empty return value means the bundle is intact.

Parameters:

Name Type Description Default
manifest Manifest

The manifest holding the expected committed digests.

 required
regression_dir Path

The test case regression/ directory to verify against.

 required

Returns:

Type Description
list[str]

A list of human-readable mismatch descriptions; empty when everything matches.
Source code in packages/climate-ref-core/src/climate_ref_core/regression/manifest.py 
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
def verify_committed_integrity(manifest: Manifest, regression_dir: Path) -> list[str]:
    """
    Check that the committed regression artefacts match the manifest digests.

    Used by the CI integrity check. An empty return value means the bundle is intact.

    Parameters
    ----------
    manifest
        The manifest holding the expected committed digests.
    regression_dir
        The test case ``regression/`` directory to verify against.

    Returns
    -------
    :
        A list of human-readable mismatch descriptions; empty when everything matches.
    """
    mismatches: list[str] = []
    for relpath, expected in manifest.committed.items():
        candidate = regression_dir / relpath
        if not candidate.exists():
            mismatches.append(
                f"{relpath}: missing on disk — expected at {candidate} (manifest sha256 {expected})"
            )
            continue
        actual = sha256_file(candidate)
        if actual != expected:
            mismatches.append(
                f"{relpath}: content differs from manifest — {candidate} "
                f"(manifest sha256 {expected}, on-disk sha256 {actual})"
            )
    return mismatches