Session 16WhjkBRkUOk

Found 26 matches
/home/byk/Code/institutional-transition-lab/src/institution_lab/governance_adjudication.py:
  Line 10: import zipfile

  Line 67: MAX_ARCHIVE_MEMBERS = 128

  Line 68: MAX_ARCHIVE_MEMBER_BYTES = 16 * 1024 * 1024

  Line 69: MAX_ARCHIVE_EXPANDED_BYTES = 64 * 1024 * 1024

  Line 180: 		with zipfile.ZipFile(io.BytesIO(artifact)) as archive:

  Line 181: 			infos = archive.infolist()

  Line 182: 			if len(infos) > MAX_ARCHIVE_MEMBERS:

  Line 183: 				raise ValueError("artifact member count exceeds limit")

  Line 184: 			member_counts = Counter(info.filename for info in infos)

  Line 185: 			for member_name, count in member_counts.items():

  Line 187: 					raise ValueError(f"artifact member is not unique: {member_name}")

  Line 188: 			if sum(info.file_size for info in infos) > MAX_ARCHIVE_EXPANDED_BYTES:

  Line 190: 			members = {

  Line 194: 			for member_name, durable_bytes in members.items():

  Line 196: 					info = archive.getinfo(member_name)

  Line 198: ...

Found 26 matches
/home/byk/Code/institutional-transition-lab/tests/test_governance_adjudication.py:
  Line 8: import zipfile

  Line 37: MAX_TEST_ARCHIVE_MEMBERS = 256

  Line 52: 		"artifact": tmp_path / "artifact.zip",

  Line 65: 	with zipfile.ZipFile(paths["artifact"], "w") as archive:

  Line 66: 		archive.writestr("documents.json", paths["documents"].read_bytes())

  Line 67: 		archive.writestr(

  Line 190: 						"filename": None,

  Line 687: 	artifact = tmp_path / "artifact.zip"

  Line 703: 	with zipfile.ZipFile(artifact, "w") as archive:

  Line 704: 		archive.writestr("documents.json", documents.read_bytes())

  Line 705: 		archive.writestr("v1.2-adjudication-package.json", coding_package.read_bytes())

  Line 733: 	artifact = tmp_path / "artifact.zip"

  Line 743: 	with zipfile.ZipFile(artifact, "w") as archive:

  Line 744: 		archive.writestr("documents.json", b"different documents")

  Line 745: 		archive.writestr("v1.2-adjudication-package.json", ...

Found 27 matches
/home/byk/Code/institutional-transition-lab/src/institution_lab/governance_adjudication.py:
  Line 80: def canonical_sha256(value: Any) -> str:

  Line 90: def _bytes_sha256(payload: bytes) -> str:

  Line 94: def _read_regular_file(path: Path, *, max_bytes: int = MAX_INPUT_BYTES) -> bytes:

  Line 112: def file_sha256(path: Path) -> str:

  Line 116: def _reject_duplicate_keys(pairs: list[tuple[str, Any]]) -> dict[str, Any]:

  Line 125: def _reject_non_finite_number(value: str) -> None:

  Line 129: def _parse_json_object(payload: bytes, label: str) -> dict[str, Any]:

  Line 143: def _validate_manifest_identity(manifest: Any) -> None:

  Line 157: def _verify_input_payloads(

  Line 220: def verify_input_manifest(

  Line 242: def _duplicates(values: list[str]) -> set[str]:

  Line 247: def _source_index(document: dict[str, Any]) -> dict[str, str]:

  Line 263: def _evidence_errors(

  Line 290: def _response_for(record: dict[str, Any], source: str) -> dict[str, ...

<path>/home/byk/Code/institutional-transition-lab/src/institution_lab/governance_adjudication.py</path>
<type>file</type>
<content>
55: }
56: CLAIM_FIELDS = {
57: 	"record_class",
58: 	"event_kind",
59: 	"title",
60: 	"announced_on",
61: 	"effective_on",
62: 	"affected_scope",
63: 	"body_patch_relation",
64: }
65: MAX_INPUT_BYTES = 16 * 1024 * 1024
66: MAX_ARTIFACT_BYTES = 32 * 1024 * 1024
67: MAX_ARCHIVE_MEMBERS = 128
68: MAX_ARCHIVE_MEMBER_BYTES = 16 * 1024 * 1024
69: MAX_ARCHIVE_EXPANDED_BYTES = 64 * 1024 * 1024
70: 
71: 
72: @dataclass(frozen=True)
73: class VerifiedInputBundle:
74: 	pins: dict[str, Any]

(Showing lines 55-74 of 946. Use offset=75 to continue.)
</content>

<path>/home/byk/Code/institutional-transition-lab/src/institution_lab/governance_adjudication.py</path>
<type>file</type>
<content>
157: def _verify_input_payloads(
158: 	manifest: Any,
159: 	*,
160: 	artifact: bytes,
161: 	documents: bytes,
162: 	coding_package: bytes,
163: 	protocol: bytes,
164: 	coding_schema: bytes,
165: 	adjudication_schema: bytes,
166: ) -> VerifiedInputBundle:
167: 	_validate_manifest_identity(manifest)
168: 	computed = {
169: 		"artifact_sha256": _bytes_sha256(artifact),
170: 		"documents_file_sha256": _bytes_sha256(documents),
171: 		"coding_package_file_sha256": _bytes_sha256(coding_package),
172: 		"protocol_sha256": _bytes_sha256(protocol),
173: 		"coding_schema_sha256": _bytes_sha256(coding_schema),
174: 		"adjudication_schema_sha256": _bytes_sha256(adjudication_schema),
175: 	}
176: 	for field, value in computed.items():
177: 		if manifest.get(field) != value:
178: 			raise ValueError(f"input manifest mismatch: {field}")
179: 	try:
180: 		with ...

<path>/home/byk/Code/institutional-transition-lab/tests/test_governance_adjudication.py</path>
<type>file</type>
<content>
860: 		)
861: 	)
862: 	paths["summary_json"].write_text('{"canonicalization_gate":"open"}\n')
863: 
864: 	with pytest.raises(ValueError, match="duplicate JSON key: artifact_sha256"):
865: 		_run_cli(monkeypatch, paths)
866: 
867: 	assert json.loads(paths["summary_json"].read_text())["canonicalization_gate"] == "closed"
868: 
869: 
870: def test_input_manifest_rejects_non_object() -> None:
871: 	with pytest.raises(ValueError, match="input manifest must be an object"):
872: 		verify_input_manifest(
873: 			[],  # type: ignore[arg-type]
874: 			artifact=Path("unused"),
875: 			documents=Path("unused"),
876: 			coding_package=Path("unused"),
877: 			protocol=Path("unused"),
878: 			coding_schema=Path("unused"),
879: 			adjudication_schema=Path("unused"),
880: 		)
881: 
882: 
883: def test_input_manifest_rejects_duplicate_artifact_members(
884: 	tmp_path: Path,
885: ...

Python 3.12.3
/usr/bin/bash: line 1: pytest: command not found

/home/byk/.local/bin/uv

No files found

drwxr-xr-x 3 byk byk 4096 Sep  9 04:59 /tmp/opencode

Using CPython 3.13.11
Creating virtual environment at: /tmp/opencode/itl-zip-audit-venv
   Building institutional-transition-lab @ file:///home/byk/Code/institutional-transition-lab
Downloading ruff (9.8MiB)
Downloading pygments (1.2MiB)
 Downloaded pygments
      Built institutional-transition-lab @ file:///home/byk/Code/institutional-transition-lab
 Downloaded ruff
Installed 12 packages in 18ms
============================= test session starts ==============================
platform linux -- Python 3.13.11, pytest-8.4.2, pluggy-1.6.0
rootdir: /home/byk/Code/institutional-transition-lab
configfile: pyproject.toml
collected 2 items

tests/test_governance_adjudication.py ..                                 [100%]

============================== 2 passed in 0.17s ===============================

<4s4B4HL2L5H2L
b'PK\x01\x02'
0 1 2 3 4 5 6 9 10 11 12 13 14 15 16 17 18
('orig_filename', 'filename', 'date_time', 'compress_type', '_compresslevel', 'comment', 'extra', 'create_system', 'create_version', 'extract_version', 'reserved', 'flag_bits', 'volume', 'internal_attr', 'external_attr', 'header_offset', 'CRC', 'compress_size', 'file_size', '_raw_time', '_end_offset')

    def __init__(self, filename="NoName", date_time=(1980,1,1,0,0,0)):
        self.orig_filename = filename   # Original file name in archive

        # Terminate the file name at the first null byte and
        # ensure paths always use forward slashes as the directory separator.
        filename = _sanitize_filename(filename)

        self.filename = filename        # Normalized file name
        self.date_time = date_time      # year, month, day, hour, min, sec

        if date_time[0] < 1980:
            raise ValueError('ZIP does not support timestamps before 1980')

        # Standard values:
        self.compress_type = ZIP_STORED # Type of compression for the file
        self._compresslevel = None      # Level for the compressor
        self.comment = b""              # Comment for each file
        self.extra = b""                # ZIP extra data
        if sys.platform == 'win32':
            self.create_system = 0          # System which created ZIP archive
        else:
 ...

def _sanitize_filename(filename):
    """Terminate the file name at the first null byte and
    ensure paths always use forward slashes as the directory separator."""

    # Terminate the file name at the first null byte.  Null bytes in file
    # names are used as tricks by viruses in archives.
    null_byte = filename.find(chr(0))
    if null_byte >= 0:
        filename = filename[0:null_byte]
    # This is used to ensure paths in generated ZIP files always use
    # forward slashes as the directory separator, as required by the
    # ZIP format specification.
    if os.sep != "/" and os.sep in filename:
        filename = filename.replace(os.sep, "/")
    if os.altsep and os.altsep != "/" and os.altsep in filename:
        filename = filename.replace(os.altsep, "/")
    return filename

'' ok '' '' False
'/' ok '/' '/' True
'../x' ok '../x' '../x' False
'/x' ok '/x' '/x' False
'C:/x' ok 'C:/x' 'C:/x' False
'x\\y' ok 'x\\y' 'x\\y' False

    def open(self, name, mode="r", pwd=None, *, force_zip64=False):
        """Return file-like object for 'name'.

        name is a string for the file name within the ZIP file, or a ZipInfo
        object.

        mode should be 'r' to read a file already in the ZIP file, or 'w' to
        write to a file newly added to the archive.

        pwd is the password to decrypt files (only used for reading).

        When writing, if the file size is not known in advance but may exceed
        2 GiB, pass force_zip64 to use the ZIP64 format, which can handle large
        files.  If the size is known in advance, it is best to pass a ZipInfo
        instance for name, with zinfo.file_size set.
        """
        if mode not in {"r", "w"}:
            raise ValueError('open() requires mode "r" or "w"')
        if pwd and (mode == "w"):
            raise ValueError("pwd is only supported for reading files")
        if not self.fp:
            raise ValueError(
                "Attempt to ...

count=128: ACCEPT
count=129: REJECT ValueError: artifact member count exceeds limit
exact duplicate required name: REJECT ValueError: artifact member is not unique: documents.json
dot-segment collision: ACCEPT
case collision: ACCEPT
backslash collision: ACCEPT
repeated-separator collision: ACCEPT
Unicode-normalization collision: ACCEPT
empty name: ACCEPT
absolute POSIX name: ACCEPT
absolute backslash name: ACCEPT
drive-prefixed name: ACCEPT
parent traversal: ACCEPT
directory by trailing slash: ACCEPT
Unix symlink mode: ACCEPT
Unix character-device mode: ACCEPT
Unix block-device mode: ACCEPT
Unix FIFO mode: ACCEPT
Unix socket mode: ACCEPT
Unix directory mode: ACCEPT
DOS volume-label attribute: ACCEPT
DOS directory attribute: ACCEPT
DOS device attribute: ACCEPT
traditional-encryption flag: ACCEPT
strong-encryption flag: ACCEPT
unsupported compression method 99: ACCEPT
nonzero starting disk: ACCEPT
unknown creator system: ACCEPT
nonzero reserved extractor-system byte: ACCEPT
impossible ...

No files found

(no output)

?? src/institution_lab/governance_adjudication.py
?? tests/test_governance_adjudication.py

<path>/home/byk/Code/institutional-transition-lab/tests/test_governance_adjudication.py</path>
<type>file</type>
<content>
33: 	RIGHT_KINDS,
34: )
35: 
36: ROOT = Path(__file__).parents[1]
37: MAX_TEST_ARCHIVE_MEMBERS = 256
38: 
39: 
40: def _write_pinned_cli_inputs(

(Showing lines 33-40 of 1024. Use offset=41 to continue.)
</content>

Found 4 matches
/home/byk/Code/institutional-transition-lab/tests/test_governance_adjudication.py:
  Line 772: 	with pytest.raises(ValueError, match="artifact member mismatch: documents.json"):

  Line 889: 		pytest.warns(UserWarning, match="Duplicate name"),

  Line 896: 	with pytest.raises(ValueError, match="artifact member is not unique: documents.json"):

  Line 919: 	with pytest.raises(ValueError, match="artifact member count exceeds limit"):

c686c4878409e68b958dd61850a59e9234416d817fc2fa3246fc728d51ebe0a5  src/institution_lab/governance_adjudication.py
abf64b5e78a616d53b703dee5291ce7bf23fa9156fe59263a702e01cb8667bc5  tests/test_governance_adjudication.py

c686c4878409e68b958dd61850a59e9234416d817fc2fa3246fc728d51ebe0a5  src/institution_lab/governance_adjudication.py
abf64b5e78a616d53b703dee5291ce7bf23fa9156fe59263a702e01cb8667bc5  tests/test_governance_adjudication.py

    def _RealGetContents(self):
        """Read in the table of contents for the ZIP file."""
        fp = self.fp
        try:
            endrec = _EndRecData(fp)
        except OSError:
            raise BadZipFile("File is not a zip file")
        if not endrec:
            raise BadZipFile("File is not a zip file")
        if self.debug > 1:
            print(endrec)
        size_cd = endrec[_ECD_SIZE]             # bytes in central directory
        offset_cd = endrec[_ECD_OFFSET]         # offset of central directory
        self._comment = endrec[_ECD_COMMENT]    # archive comment

        # "concat" is zero, unless zip was concatenated to another file
        concat = endrec[_ECD_LOCATION] - size_cd - offset_cd

        if self.debug > 2:
            inferred = concat + offset_cd
            print("given, inferred, offset", offset_cd, inferred, concat)
        # self.start_dir:  Position of start of central directory
        self.start_dir = offset_cd + concat
        if ...

    def _decodeExtra(self, filename_crc):
        # Try to decode the extra field.
        extra = self.extra
        unpack = struct.unpack
        while len(extra) >= 4:
            tp, ln = unpack('<HH', extra[:4])
            if ln+4 > len(extra):
                raise BadZipFile("Corrupt extra field %04x (size=%d)" % (tp, ln))
            if tp == 0x0001:
                data = extra[4:ln+4]
                # ZIP64 extension (large files and/or large archives)
                try:
                    if self.file_size in (0xFFFF_FFFF_FFFF_FFFF, 0xFFFF_FFFF):
                        field = "File size"
                        self.file_size, = unpack('<Q', data[:8])
                        data = data[8:]
                    if self.compress_size == 0xFFFF_FFFF:
                        field = "Compress size"
                        self.compress_size, = unpack('<Q', data[:8])
                        data = data[8:]
                    if self.header_offset == 0xFFFF_FFFF:
        ...

Unicode-path-extra required-name alias: ACCEPT
duplicate Unicode-path extra fields: ACCEPT
trailing malformed central extra-field bytes: ACCEPT

EOCD claims one entry while central directory contains three: ACCEPT
EOCD claims nonzero disk numbers: ACCEPT