dvt-core 0.52.2__cp310-cp310-macosx_10_9_x86_64.whl

dbt/utils/utils.py

@@ -0,0 +1,408 @@
+import collections
+import decimal
+import functools
+import itertools
+import json
+import os
+import sys
+from datetime import date, datetime, time, timezone
+from enum import Enum
+from pathlib import PosixPath, WindowsPath
+from typing import (
+    AbstractSet,
+    Any,
+    Dict,
+    Iterable,
+    Iterator,
+    List,
+    Mapping,
+    Optional,
+    Sequence,
+    Set,
+    Tuple,
+    Type,
+)
+
+import jinja2
+
+from dbt import flags
+from dbt.exceptions import DuplicateAliasError
+from dbt_common.exceptions import RecursionError
+from dbt_common.helper_types import WarnErrorOptionsV2
+from dbt_common.utils import md5
+
+DECIMALS: Tuple[Type[Any], ...]
+try:
+    import cdecimal  # typing: ignore
+except ImportError:
+    DECIMALS = (decimal.Decimal,)
+else:
+    DECIMALS = (decimal.Decimal, cdecimal.Decimal)
+
+
+class ExitCodes(int, Enum):
+    Success = 0
+    ModelError = 1
+    UnhandledError = 2
+
+
+def coalesce(*args):
+    for arg in args:
+        if arg is not None:
+            return arg
+    return None
+
+
+def get_profile_from_project(project):
+    target_name = project.get("target", {})
+    profile = project.get("outputs", {}).get(target_name, {})
+    return profile
+
+
+def get_model_name_or_none(model):
+    if model is None:
+        name = "<None>"
+
+    elif isinstance(model, str):
+        name = model
+    elif isinstance(model, dict):
+        name = model.get("alias", model.get("name"))
+    elif hasattr(model, "alias"):
+        name = model.alias
+    elif hasattr(model, "name"):
+        name = model.name
+    else:
+        name = str(model)
+    return name
+
+
+def split_path(path):
+    return path.split(os.sep)
+
+
+def get_pseudo_test_path(node_name, source_path):
+    "schema tests all come from schema.yml files. fake a source sql file"
+    source_path_parts = split_path(source_path)
+    source_path_parts.pop()  # ignore filename
+    suffix = ["{}.sql".format(node_name)]
+    pseudo_path_parts = source_path_parts + suffix
+    return os.path.join(*pseudo_path_parts)
+
+
+def get_pseudo_hook_path(hook_name):
+    path_parts = ["hooks", "{}.sql".format(hook_name)]
+    return os.path.join(*path_parts)
+
+
+def get_hash(model):
+    return md5(model.unique_id)
+
+
+def get_hashed_contents(model):
+    return md5(model.raw_code)
+
+
+def flatten_nodes(dep_list):
+    return list(itertools.chain.from_iterable(dep_list))
+
+
+class memoized:
+    """Decorator. Caches a function's return value each time it is called. If
+    called later with the same arguments, the cached value is returned (not
+    reevaluated).
+
+    Taken from https://wiki.python.org/moin/PythonDecoratorLibrary#Memoize"""
+
+    def __init__(self, func) -> None:
+        self.func = func
+        self.cache: Dict[Any, Any] = {}
+
+    def __call__(self, *args):
+        if not isinstance(args, collections.abc.Hashable):
+            # uncacheable. a list, for instance.
+            # better to not cache than blow up.
+            return self.func(*args)
+        if args in self.cache:
+            return self.cache[args]
+        value = self.func(*args)
+        self.cache[args] = value
+        return value
+
+    def __repr__(self):
+        """Return the function's docstring."""
+        return self.func.__doc__
+
+    def __get__(self, obj, objtype):
+        """Support instance methods."""
+        return functools.partial(self.__call__, obj)
+
+
+def add_ephemeral_model_prefix(s: str) -> str:
+    return "__dbt__cte__{}".format(s)
+
+
+def timestring() -> str:
+    """Get the current datetime as an RFC 3339-compliant string"""
+    # isoformat doesn't include the mandatory trailing 'Z' for UTC.
+    return datetime.now(timezone.utc).replace(tzinfo=None).isoformat() + "Z"
+
+
+def humanize_execution_time(execution_time: int) -> str:
+    minutes, seconds = divmod(execution_time, 60)
+    hours, minutes = divmod(minutes, 60)
+
+    return f" in {int(hours)} hours {int(minutes)} minutes and {seconds:0.2f} seconds"
+
+
+class JSONEncoder(json.JSONEncoder):
+    """A 'custom' json encoder that does normal json encoder things, but also
+    handles `Decimal`s and `Undefined`s. Decimals can lose precision because
+    they get converted to floats. Undefined's are serialized to an empty string
+    """
+
+    def default(self, obj):
+        if isinstance(obj, DECIMALS):
+            return float(obj)
+        elif isinstance(obj, (datetime, date, time)):
+            return obj.isoformat()
+        elif isinstance(obj, jinja2.Undefined):
+            return ""
+        elif isinstance(obj, Exception):
+            return repr(obj)
+        elif hasattr(obj, "to_dict"):
+            # if we have a to_dict we should try to serialize the result of
+            # that!
+            return obj.to_dict(omit_none=True)
+        else:
+            return super().default(obj)
+
+
+class Translator:
+    def __init__(self, aliases: Mapping[str, str], recursive: bool = False) -> None:
+        self.aliases = aliases
+        self.recursive = recursive
+
+    def translate_mapping(self, kwargs: Mapping[str, Any]) -> Dict[str, Any]:
+        result: Dict[str, Any] = {}
+
+        for key, value in kwargs.items():
+            canonical_key = self.aliases.get(key, key)
+            if canonical_key in result:
+                raise DuplicateAliasError(kwargs, self.aliases, canonical_key)
+            result[canonical_key] = self.translate_value(value)
+        return result
+
+    def translate_sequence(self, value: Sequence[Any]) -> List[Any]:
+        return [self.translate_value(v) for v in value]
+
+    def translate_value(self, value: Any) -> Any:
+        if self.recursive:
+            if isinstance(value, Mapping):
+                return self.translate_mapping(value)
+            elif isinstance(value, (list, tuple)):
+                return self.translate_sequence(value)
+        return value
+
+    def translate(self, value: Mapping[str, Any]) -> Dict[str, Any]:
+        try:
+            return self.translate_mapping(value)
+        except RuntimeError as exc:
+            if "maximum recursion depth exceeded" in str(exc):
+                raise RecursionError("Cycle detected in a value passed to translate!")
+            raise
+
+
+def translate_aliases(
+    kwargs: Dict[str, Any],
+    aliases: Dict[str, str],
+    recurse: bool = False,
+) -> Dict[str, Any]:
+    """Given a dict of keyword arguments and a dict mapping aliases to their
+    canonical values, canonicalize the keys in the kwargs dict.
+
+    If recurse is True, perform this operation recursively.
+
+    :returns: A dict containing all the values in kwargs referenced by their
+        canonical key.
+    :raises: `AliasError`, if a canonical key is defined more than once.
+    """
+    translator = Translator(aliases, recurse)
+    return translator.translate(kwargs)
+
+
+# Note that this only affects hologram json validation.
+# It has no effect on mashumaro serialization.
+# Q: Can this be removed?
+def restrict_to(*restrictions):
+    """Create the metadata for a restricted dataclass field"""
+    return {"restrict": list(restrictions)}
+
+
+def coerce_dict_str(value: Any) -> Optional[Dict[str, Any]]:
+    """For annoying mypy reasons, this helper makes dealing with nested dicts
+    easier. You get either `None` if it's not a Dict[str, Any], or the
+    Dict[str, Any] you expected (to pass it to dbtClassMixin.from_dict(...)).
+    """
+    if isinstance(value, dict) and all(isinstance(k, str) for k in value):
+        return value
+    else:
+        return None
+
+
+def _coerce_decimal(value):
+    if isinstance(value, DECIMALS):
+        return float(value)
+    return value
+
+
+def fqn_search(root: Dict[str, Any], fqn: List[str]) -> Iterator[Dict[str, Any]]:
+    """Iterate into a nested dictionary, looking for keys in the fqn as levels.
+    Yield the level config.
+    """
+    yield root
+
+    for level in fqn:
+        level_config = root.get(level, None)
+        if not isinstance(level_config, dict):
+            break
+        # This used to do a 'deepcopy',
+        # but it didn't seem to be necessary
+        yield level_config
+        root = level_config
+
+
+StringMap = Mapping[str, Any]
+StringMapList = List[StringMap]
+StringMapIter = Iterable[StringMap]
+
+
+class MultiDict(Mapping[str, Any]):
+    """Implement the mapping protocol using a list of mappings. The most
+    recently added mapping "wins".
+    """
+
+    def __init__(self, sources: Optional[StringMapList] = None) -> None:
+        super().__init__()
+        self.sources: StringMapList
+
+        if sources is None:
+            self.sources = []
+        else:
+            self.sources = sources
+
+    def add_from(self, sources: StringMapIter):
+        self.sources.extend(sources)
+
+    def add(self, source: StringMap):
+        self.sources.append(source)
+
+    def _keyset(self) -> AbstractSet[str]:
+        # return the set of keys
+        keys: Set[str] = set()
+        for entry in self._itersource():
+            keys.update(entry)
+        return keys
+
+    def _itersource(self) -> StringMapIter:
+        return reversed(self.sources)
+
+    def __iter__(self) -> Iterator[str]:
+        # we need to avoid duplicate keys
+        return iter(self._keyset())
+
+    def __len__(self):
+        return len(self._keyset())
+
+    def __getitem__(self, name: str) -> Any:
+        for entry in self._itersource():
+            if name in entry:
+                return entry[name]
+        raise KeyError(name)
+
+    def __contains__(self, name) -> bool:
+        return any((name in entry for entry in self._itersource()))
+
+
+# This is used to serialize the args in the run_results and in the logs.
+# We do this separately because there are a few fields that don't serialize,
+# i.e. PosixPath, WindowsPath, and types. It also includes args from both
+# cli args and flags, which is more complete than just the cli args.
+# If new args are added that are false by default (particularly in the
+# global options) they should be added to the 'default_false_keys' list.
+def args_to_dict(args):
+    var_args = vars(args).copy()
+    # update the args with the flags, which could also come from environment
+    # variables or project_flags
+    flag_dict = flags.get_flag_dict()
+    var_args.update(flag_dict)
+    dict_args = {}
+    # remove args keys that clutter up the dictionary
+    for key in var_args:
+        if key.lower() in var_args and key == key.upper():
+            # skip all capped keys being introduced by Flags in dbt.cli.flags
+            continue
+        if key in ["cls", "mp_context"]:
+            continue
+        if var_args[key] is None:
+            continue
+        # TODO: add more default_false_keys
+        default_false_keys = (
+            "debug",
+            "full_refresh",
+            "fail_fast",
+            "warn_error",
+            "single_threaded",
+            "log_cache_events",
+            "store_failures",
+            "use_experimental_parser",
+        )
+        default_empty_yaml_dict_keys = ("vars", "warn_error_options")
+        if key in default_false_keys and var_args[key] is False:
+            continue
+        if key in default_empty_yaml_dict_keys and var_args[key] == "{}":
+            continue
+        # this was required for a test case
+        if isinstance(var_args[key], PosixPath) or isinstance(var_args[key], WindowsPath):
+            var_args[key] = str(var_args[key])
+        if isinstance(var_args[key], WarnErrorOptionsV2):
+            var_args[key] = var_args[key].to_dict()
+
+        dict_args[key] = var_args[key]
+    return dict_args
+
+
+# Taken from https://github.com/python/cpython/blob/3.11/Lib/distutils/util.py
+# This is a copy of the function from distutils.util, which was removed in Python 3.12.
+def strtobool(val: str) -> bool:
+    """Convert a string representation of truth to True or False.
+
+    True values are 'y', 'yes', 't', 'true', 'on', and '1'; false values
+    are 'n', 'no', 'f', 'false', 'off', and '0'.  Raises ValueError if
+    'val' is anything else.
+    """
+    val = val.lower()
+    if val in ("y", "yes", "t", "true", "on", "1"):
+        return True
+    elif val in ("n", "no", "f", "false", "off", "0"):
+        return False
+    else:
+        raise ValueError("invalid truth value %r" % (val,))
+
+
+def try_get_max_rss_kb() -> Optional[int]:
+    """Attempts to get the high water mark for this process's memory use via
+    the most reliable and accurate mechanism available through the host OS.
+    Currently only implemented for Linux."""
+    if sys.platform == "linux" and os.path.isfile("/proc/self/status"):
+        try:
+            # On Linux, the most reliable documented mechanism for getting the RSS
+            # high-water-mark comes from the line confusingly labeled VmHWM in the
+            # /proc/self/status virtual file.
+            with open("/proc/self/status") as f:
+                for line in f:
+                    if line.startswith("VmHWM:"):
+                        return int(str.split(line)[1])
+        except Exception:
+            pass
+
+    return None

dbt/version.py

@@ -0,0 +1,268 @@
+import glob
+import importlib
+import importlib.util
+import json
+import os
+import re
+from importlib import metadata as importlib_metadata
+from pathlib import Path
+from typing import Iterator, List, Optional, Tuple
+
+import requests
+
+import dbt_common.semver as semver
+from dbt_common.ui import green, yellow
+
+PYPI_VERSION_URL = "https://pypi.org/pypi/dbt-core/json"
+
+
+def get_version_information() -> str:
+    installed = get_installed_version()
+    latest = get_latest_version()
+
+    core_msg_lines, core_info_msg = _get_core_msg_lines(installed, latest)
+
+    # Add DVT version info (must be [name, version, message] format)
+    core_msg_lines.append(["DVT", __dvt_version__, ""])
+
+    core_msg = _format_core_msg(core_msg_lines)
+    plugin_version_msg = _get_plugins_msg()
+
+    msg_lines = [core_msg]
+
+    if core_info_msg != "":
+        msg_lines.append(core_info_msg)
+
+    msg_lines.append(plugin_version_msg)
+    msg_lines.append("")
+
+    return "\n\n".join(msg_lines)
+
+
+def get_installed_version() -> semver.VersionSpecifier:
+    return semver.VersionSpecifier.from_version_string(__version__)
+
+
+def get_latest_version(
+    version_url: str = PYPI_VERSION_URL,
+) -> Optional[semver.VersionSpecifier]:
+    try:
+        resp = requests.get(version_url, timeout=1)
+        data = resp.json()
+        version_string = data["info"]["version"]
+    except (json.JSONDecodeError, KeyError, requests.RequestException):
+        return None
+
+    return semver.VersionSpecifier.from_version_string(version_string)
+
+
+def _get_core_msg_lines(
+    installed: semver.VersionSpecifier,
+    latest: Optional[semver.VersionSpecifier],
+) -> Tuple[List[List[str]], str]:
+    installed_s = installed.to_version_string(skip_matcher=True)
+    installed_line = ["installed", installed_s, ""]
+    update_info = ""
+
+    if latest is None:
+        update_info = (
+            "  The latest version of dbt-core could not be determined!\n"
+            "  Make sure that the following URL is accessible:\n"
+            f"  {PYPI_VERSION_URL}"
+        )
+        return [installed_line], update_info
+
+    latest_s = latest.to_version_string(skip_matcher=True)
+    latest_line = ["latest", latest_s, green("Up to date!")]
+
+    if installed > latest:
+        latest_line[2] = yellow("Ahead of latest version!")
+    elif installed < latest:
+        latest_line[2] = yellow("Update available!")
+        update_info = (
+            "  Your version of dbt-core is out of date!\n"
+            "  You can find instructions for upgrading here:\n"
+            "  https://docs.getdbt.com/docs/installation"
+        )
+
+    return [
+        installed_line,
+        latest_line,
+    ], update_info
+
+
+def _format_core_msg(lines: List[List[str]]) -> str:
+    msg = "Core:\n"
+    msg_lines = []
+
+    for name, version, update_msg in _pad_lines(lines, seperator=":"):
+        line_msg = f"  - {name} {version}"
+        if update_msg != "":
+            line_msg += f" - {update_msg}"
+        msg_lines.append(line_msg)
+
+    return msg + "\n".join(msg_lines)
+
+
+def _get_plugins_msg() -> str:
+    msg_lines = ["Plugins:"]
+
+    plugins = []
+    display_update_msg = False
+    for name, version_s in _get_dbt_plugins_info():
+        compatability_msg, needs_update = _get_plugin_msg_info(name, version_s, installed)
+        if needs_update:
+            display_update_msg = True
+        plugins.append([name, version_s, compatability_msg])
+
+    for plugin in _pad_lines(plugins, seperator=":"):
+        msg_lines.append(_format_single_plugin(plugin, ""))
+
+    if display_update_msg:
+        update_msg = (
+            "  At least one plugin is out of date with dbt-core.\n"
+            "  You can find instructions for upgrading here:\n"
+            "  https://docs.getdbt.com/docs/installation"
+        )
+        msg_lines += ["", update_msg]
+
+    return "\n".join(msg_lines)
+
+
+def _get_plugin_msg_info(
+    name: str, version_s: str, core: semver.VersionSpecifier
+) -> Tuple[str, bool]:
+    plugin = semver.VersionSpecifier.from_version_string(version_s)
+    latest_plugin = get_latest_version(version_url=get_package_pypi_url(name))
+
+    needs_update = False
+
+    if not latest_plugin:
+        compatibility_msg = yellow("Could not determine latest version")
+        return (compatibility_msg, needs_update)
+
+    if plugin < latest_plugin:
+        compatibility_msg = yellow("Update available!")
+        needs_update = True
+    elif plugin > latest_plugin:
+        compatibility_msg = yellow("Ahead of latest version!")
+    else:
+        compatibility_msg = green("Up to date!")
+
+    return (compatibility_msg, needs_update)
+
+
+def _format_single_plugin(plugin: List[str], update_msg: str) -> str:
+    name, version_s, compatability_msg = plugin
+    msg = f"  - {name} {version_s} - {compatability_msg}"
+    if update_msg != "":
+        msg += f"\n{update_msg}\n"
+    return msg
+
+
+def _pad_lines(lines: List[List[str]], seperator: str = "") -> List[List[str]]:
+    if len(lines) == 0:
+        return []
+
+    # count the max line length for each column in the line
+    counter = [0] * len(lines[0])
+    for line in lines:
+        for i, item in enumerate(line):
+            counter[i] = max(counter[i], len(item))
+
+    result: List[List[str]] = []
+    for i, line in enumerate(lines):
+        # add another list to hold padded strings
+        if len(result) == i:
+            result.append([""] * len(line))
+
+        # iterate over columns in the line
+        for j, item in enumerate(line):
+            # the last column does not need padding
+            if j == len(line) - 1:
+                result[i][j] = item
+                continue
+
+            # if the following column has no length
+            # the string does not need padding
+            if counter[j + 1] == 0:
+                result[i][j] = item
+                continue
+
+            # only add the seperator to the first column
+            offset = 0
+            if j == 0 and seperator != "":
+                item += seperator
+                offset = len(seperator)
+
+            result[i][j] = item.ljust(counter[j] + offset)
+
+    return result
+
+
+def get_package_pypi_url(package_name: str) -> str:
+    return f"https://pypi.org/pypi/dbt-{package_name}/json"
+
+
+def _get_dbt_plugins_info() -> Iterator[Tuple[str, str]]:
+    for plugin_name in _get_adapter_plugin_names():
+        if plugin_name == "core":
+            continue
+        try:
+            mod = importlib.import_module(f"dbt.adapters.{plugin_name}.__version__")
+        except ImportError:
+            # not an adapter
+            continue
+        yield plugin_name, mod.version
+
+
+def _get_adapter_plugin_names() -> Iterator[str]:
+    spec = importlib.util.find_spec("dbt.adapters")
+    # If None, then nothing provides an importable 'dbt.adapters', so we will
+    # not be reporting plugin versions today
+    if spec is None or spec.submodule_search_locations is None:
+        return
+
+    for adapters_path in spec.submodule_search_locations:
+        version_glob = os.path.join(adapters_path, "*", "__version__.py")
+        for version_path in glob.glob(version_glob):
+            # the path is like .../dbt/adapters/{plugin_name}/__version__.py
+            # except it could be \\ on windows!
+            plugin_root, _ = os.path.split(version_path)
+            _, plugin_name = os.path.split(plugin_root)
+            yield plugin_name
+
+
+def _resolve_version() -> str:
+    """
+    Resolve dbt version for DVT-core.
+
+    DVT-core is built on dbt-core 1.10.15 and must report this version
+    for package compatibility. The actual DVT version is tracked separately.
+    """
+    # DVT-core is based on dbt-core 1.10.15
+    # We must report this version for dbt package ecosystem compatibility
+    return "1.10.15"
+
+
+def _resolve_dvt_version() -> str:
+    """Get the actual DVT-core package version."""
+    try:
+        return importlib_metadata.version("dvt-core")
+    except importlib_metadata.PackageNotFoundError:
+        # Fall back to reading from pyproject.toml in development
+        pyproject_path = Path(__file__).resolve().parents[1] / "pyproject.toml"
+        if not pyproject_path.exists():
+            return "unknown"
+
+        text = pyproject_path.read_text(encoding="utf-8")
+        match = re.search(r'^version\s*=\s*"(?P<version>[^"]+)"', text, re.MULTILINE)
+        if match:
+            return match.group("version")
+
+        return "unknown"
+
+
+__version__ = _resolve_version()  # This is the dbt version (1.10.15)
+__dvt_version__ = _resolve_dvt_version()  # This is the actual DVT version (0.1.2)
+installed = get_installed_version()