rasa-pro 3.12.0.dev1__py3-none-any.whl

rasa/shared/data.py

@@ -0,0 +1,249 @@
+import os
+import shutil
+import tempfile
+import uuid
+from enum import Enum
+from pathlib import Path
+from typing import (
+    Any,
+    Protocol,
+    TYPE_CHECKING,
+    Text,
+    Optional,
+    Union,
+    List,
+    Callable,
+    Set,
+    Iterable,
+    runtime_checkable,
+)
+
+import structlog
+
+if TYPE_CHECKING:
+    from rasa.core.channels import UserMessage
+    from rasa.shared.core.domain import Domain
+    from rasa.shared.nlu.training_data.message import Message
+
+YAML_FILE_EXTENSIONS = [".yml", ".yaml"]
+JSON_FILE_EXTENSIONS = [".json"]
+TRAINING_DATA_EXTENSIONS = set(JSON_FILE_EXTENSIONS + YAML_FILE_EXTENSIONS)
+
+structlogger = structlog.get_logger()
+
+
+def yaml_file_extension() -> Text:
+    """Return YAML file extension."""
+    return YAML_FILE_EXTENSIONS[0]
+
+
+def is_likely_yaml_file(file_path: Union[Text, Path]) -> bool:
+    """Check if a file likely contains yaml.
+
+    Arguments:
+        file_path: path to the file
+
+    Returns:
+        `True` if the file likely contains data in yaml format, `False` otherwise.
+    """
+    return Path(file_path).suffix in set(YAML_FILE_EXTENSIONS)
+
+
+def is_likely_json_file(file_path: Text) -> bool:
+    """Check if a file likely contains json.
+
+    Arguments:
+        file_path: path to the file
+
+    Returns:
+        `True` if the file likely contains data in json format, `False` otherwise.
+    """
+    return Path(file_path).suffix in set(JSON_FILE_EXTENSIONS)
+
+
+def get_core_directory(paths: Optional[Union[Text, List[Text]]]) -> Text:
+    """Recursively collects all Core training files from a list of paths.
+
+    Args:
+        paths: List of paths to training files or folders containing them.
+
+    Returns:
+        Path to temporary directory containing all found Core training files.
+    """
+    from rasa.shared.core.training_data.story_reader.yaml_story_reader import (
+        YAMLStoryReader,
+    )
+
+    core_files = get_data_files(paths, YAMLStoryReader.is_stories_file)
+    return _copy_files_to_new_dir(core_files)
+
+
+def get_nlu_directory(paths: Optional[Union[Text, List[Text]]]) -> Text:
+    """Recursively collects all NLU training files from a list of paths.
+
+    Args:
+        paths: List of paths to training files or folders containing them.
+
+    Returns:
+        Path to temporary directory containing all found NLU training files.
+    """
+    nlu_files = get_data_files(paths, is_nlu_file)
+    return _copy_files_to_new_dir(nlu_files)
+
+
+def get_data_files(
+    paths: Optional[Union[Text, List[Text]]], filter_predicate: Callable[[Text], bool]
+) -> List[Text]:
+    """Recursively collects all training files from a list of paths.
+
+    Args:
+        paths: List of paths to training files or folders containing them.
+        filter_predicate: property to use when filtering the paths, e.g. `is_nlu_file`.
+
+    Returns:
+        Paths of training data files.
+    """
+    data_files = set()
+
+    if paths is None:
+        paths = []
+    elif isinstance(paths, str):
+        paths = [paths]
+
+    for path in set(paths):
+        if not path:
+            continue
+
+        if is_valid_filetype(path):
+            if filter_predicate(path):
+                data_files.add(os.path.abspath(path))
+        else:
+            new_data_files = _find_data_files_in_directory(path, filter_predicate)
+            data_files.update(new_data_files)
+
+    return sorted(data_files)
+
+
+def _find_data_files_in_directory(
+    directory: Text, filter_property: Callable[[Text], bool]
+) -> Set[Text]:
+    filtered_files = set()
+
+    for root, _, files in os.walk(directory, followlinks=True):
+        # we sort the files here to ensure consistent order for repeatable training
+        # results
+        for f in sorted(files):
+            full_path = os.path.join(root, f)
+
+            if not is_valid_filetype(full_path):
+                continue
+
+            if filter_property(full_path):
+                filtered_files.add(full_path)
+
+    return filtered_files
+
+
+def is_valid_filetype(path: Union[Path, Text]) -> bool:
+    """Checks if given file has a supported extension.
+
+    Args:
+        path: Path to the source file.
+
+    Returns:
+        `True` is given file has supported extension, `False` otherwise.
+    """
+    return Path(path).is_file() and Path(path).suffix in TRAINING_DATA_EXTENSIONS
+
+
+def is_nlu_file(file_path: Text) -> bool:
+    """Checks if a file is a Rasa compatible nlu file.
+
+    Args:
+        file_path: Path of the file which should be checked.
+
+    Returns:
+        `True` if it's a nlu file, otherwise `False`.
+    """
+    from rasa.shared.nlu.training_data import loading as nlu_loading
+
+    return nlu_loading.guess_format(file_path) != nlu_loading.UNK
+
+
+def is_config_file(file_path: Text) -> bool:
+    """Checks whether the given file path is a Rasa config file.
+
+    Args:
+        file_path: Path of the file which should be checked.
+
+    Returns:
+        `True` if it's a Rasa config file, otherwise `False`.
+    """
+    file_name = os.path.basename(file_path)
+
+    return file_name in ["config.yml", "config.yaml"]
+
+
+def _copy_files_to_new_dir(files: Iterable[Text]) -> Text:
+    directory = tempfile.mkdtemp()
+    for f in files:
+        # makes sure files do not overwrite each other, hence the prefix
+        unique_prefix = uuid.uuid4().hex
+        unique_file_name = unique_prefix + "_" + os.path.basename(f)
+        shutil.copy2(f, os.path.join(directory, unique_file_name))
+
+    return directory
+
+
+class TrainingType(Enum):
+    """Enum class for defining explicitly what training types exist."""
+
+    NLU = 1
+    CORE = 2
+    BOTH = 3
+    END_TO_END = 4
+
+    @property
+    def model_type(self) -> Text:
+        """Returns the type of model which this training yields."""
+        if self == TrainingType.NLU:
+            return "nlu"
+        if self == TrainingType.CORE:
+            return "core"
+        return "rasa"
+
+
+@runtime_checkable
+class RegexReader(Protocol):
+    def unpack_regex_message(self, message: "Message", **kwargs: Any) -> "Message": ...
+
+
+def create_regex_pattern_reader(
+    message: "UserMessage", domain: "Domain"
+) -> Optional[RegexReader]:
+    """Create a new instance of a class to unpack regex patterns.
+
+    Args:
+        message: The user message to unpack.
+        domain: The domain of the assistant.
+    """
+    from rasa.shared.core.command_payload_reader import CommandPayloadReader
+    from rasa.shared.core.training_data.story_reader.yaml_story_reader import (
+        YAMLStoryReader,
+    )
+
+    if message.text is None:
+        structlogger.warning(
+            "empty.user.message",
+            user_text="None",
+        )
+        return None
+
+    reader: Union[CommandPayloadReader, YAMLStoryReader, None] = None
+
+    if message.text.startswith("/SetSlots"):
+        reader = CommandPayloadReader()
+    elif message.text.startswith("/"):
+        reader = YAMLStoryReader(domain)
+
+    return reader if isinstance(reader, RegexReader) else None

rasa/shared/engine/caching.py

@@ -0,0 +1,26 @@
+import os
+from pathlib import Path
+
+
+DEFAULT_CACHE_LOCATION = Path(".rasa", "cache")
+DEFAULT_CACHE_NAME = "cache.db"
+DEFAULT_CACHE_SIZE_MB = 1000
+
+CACHE_LOCATION_ENV = "RASA_CACHE_DIRECTORY"
+CACHE_DB_NAME_ENV = "RASA_CACHE_NAME"
+CACHE_SIZE_ENV = "RASA_MAX_CACHE_SIZE"
+
+
+def get_local_cache_location() -> Path:
+    """Returns the location of the local cache."""
+    return Path(os.environ.get(CACHE_LOCATION_ENV, DEFAULT_CACHE_LOCATION))
+
+
+def get_max_cache_size() -> float:
+    """Returns the maximum cache size."""
+    return float(os.environ.get(CACHE_SIZE_ENV, DEFAULT_CACHE_SIZE_MB))
+
+
+def get_cache_database_name() -> str:
+    """Returns the database name in the cache."""
+    return os.environ.get(CACHE_DB_NAME_ENV, DEFAULT_CACHE_NAME)

rasa/shared/exceptions.py

@@ -0,0 +1,167 @@
+import json
+from typing import Optional, Text, Dict, Any
+
+import jsonschema
+from ruamel.yaml.error import (
+    MarkedYAMLError,
+    MarkedYAMLWarning,
+    MarkedYAMLFutureWarning,
+)
+
+
+class RasaException(Exception):
+    """Base exception class for all errors raised by Rasa Pro.
+
+    These exceptions result from invalid use cases and will be reported
+    to the users, but will be ignored in telemetry.
+    """
+
+
+class RasaCoreException(RasaException):
+    """Basic exception for errors raised by Rasa Core."""
+
+
+class InvalidParameterException(RasaException, ValueError):
+    """Raised when an invalid parameter is used."""
+
+
+class YamlException(RasaException):
+    """Raised if there is an error reading yaml."""
+
+    def __init__(self, filename: Optional[Text] = None) -> None:
+        """Create exception.
+
+        Args:
+        filename: optional file the error occurred in
+        """
+        self.filename = filename
+
+    def file_error_message(self) -> str:
+        if self.filename:
+            return f"Error in '{self.filename}'."
+        else:
+            return "Error found."
+
+    def __str__(self) -> str:
+        msg = self.file_error_message()
+        if self.__cause__:
+            msg += f" {self.__cause__}"
+        return msg
+
+
+class YamlSyntaxException(YamlException):
+    """Raised when a YAML file can not be parsed properly due to a syntax error."""
+
+    def __init__(
+        self,
+        filename: Optional[Text] = None,
+        underlying_yaml_exception: Optional[Exception] = None,
+    ) -> None:
+        super(YamlSyntaxException, self).__init__(filename)
+
+        self.underlying_yaml_exception = underlying_yaml_exception
+
+    def __str__(self) -> Text:
+        exception_text = self.file_error_message()
+        exception_text += " Failed to read YAML."
+
+        if self.underlying_yaml_exception:
+            if isinstance(
+                self.underlying_yaml_exception,
+                (MarkedYAMLError, MarkedYAMLWarning, MarkedYAMLFutureWarning),
+            ):
+                self.underlying_yaml_exception.note = None
+            if isinstance(
+                self.underlying_yaml_exception,
+                (MarkedYAMLWarning, MarkedYAMLFutureWarning),
+            ):
+                self.underlying_yaml_exception.warn = None
+            exception_text += f" {self.underlying_yaml_exception}"
+
+        if self.filename:
+            exception_text = exception_text.replace(
+                'in "<unicode string>"', f'in "{self.filename}"'
+            )
+
+        exception_text += (
+            "\n\nYou can use https://yamlchecker.com/ to validate the "
+            "YAML syntax of your file."
+        )
+        return exception_text
+
+
+class FileNotFoundException(RasaException, FileNotFoundError):
+    """Raised when a file, expected to exist, doesn't exist."""
+
+
+class FileIOException(RasaException):
+    """Raised if there is an error while doing file IO."""
+
+
+class InvalidConfigException(ValueError, RasaException):
+    """Raised if an invalid configuration is encountered."""
+
+
+class UnsupportedFeatureException(RasaCoreException):
+    """Raised if a requested feature is not supported."""
+
+
+class SchemaValidationError(RasaException, jsonschema.ValidationError):
+    """Raised if schema validation via `jsonschema` failed."""
+
+
+class InvalidEntityFormatException(RasaException, json.JSONDecodeError):
+    """Raised if the format of an entity is invalid."""
+
+    @classmethod
+    def create_from(
+        cls, other: json.JSONDecodeError, msg: Text
+    ) -> "InvalidEntityFormatException":
+        """Creates `InvalidEntityFormatException` from `JSONDecodeError`."""
+        return cls(msg, other.doc, other.pos)
+
+
+class ConnectionException(RasaException):
+    """Raised when a connection to a 3rd party service fails.
+
+    It's used by our broker and tracker store classes, when
+    they can't connect to services like postgres, dynamoDB, mongo.
+    """
+
+
+class ProviderClientAPIException(RasaException):
+    """Raised for errors that occur during API interactions
+    with LLM / embedding providers.
+
+    Attributes:
+        original_exception (Exception): The original exception that was
+            caught and led to this custom exception.
+        message: (Optional[str]): Optional explanation of the error.
+    """
+
+    def __init__(
+        self,
+        original_exception: Exception,
+        message: Optional[str] = None,
+        info: Optional[Dict[Text, Any]] = None,
+    ):
+        super().__init__(
+            f"{message if message is not None else ''}"
+            f"\nOriginal error: {original_exception})"
+        )
+        self.message = message
+        self.original_exception = original_exception
+        self.info = info
+
+    def __str__(self) -> Text:
+        s = f"{self.__class__.__name__}:"
+        if self.message is not None:
+            s += f"\n{self.message}"
+        s += f"\nOriginal error: {self.original_exception}\n"
+        if self.info:
+            s += f"\nInfo: \n{self.info}\n"
+        return s
+
+
+class ProviderClientValidationError(RasaException):
+    """Raised for errors that occur during validation of the API client."""