edsl 0.1.14__py3-none-any.whl → 0.1.40__py3-none-any.whl

edsl/Base.py

@@ -1,77 +1,376 @@
+"""Base class for all classes in the package. It provides rich printing and persistence of objects."""
+
 from abc import ABC, abstractmethod, ABCMeta
-import io
 import gzip
 import json
+from typing import Any, Optional, Union
+from uuid import UUID
 
-from rich.console import Console
-from rich.table import Table
-from IPython.display import display
 
-from edsl.utilities import is_notebook
+class PersistenceMixin:
+    """Mixin for saving and loading objects to and from files."""
 
+    def duplicate(self, add_edsl_version=False):
+        """Return a duplicate of the object."""
+        return self.from_dict(self.to_dict(add_edsl_version=False))
 
-class RichPrintingMixin:
-    def for_console(self):
-        with io.StringIO() as buf:
-            console = Console(file=buf, record=True)
-            table = self.rich_print()
-            console.print(table)
-            return console.export_text()
+    def push(
+        self,
+        description: Optional[str] = None,
+        alias: Optional[str] = None,
+        visibility: Optional[str] = "unlisted",
+        expected_parrot_url: Optional[str] = None,
+    ):
+        """Post the object to coop."""
+        from edsl.coop import Coop
 
-    def __str__(self):
-        return self.for_console()
+        c = Coop(url=expected_parrot_url)
+        return c.create(self, description, alias, visibility)
+
+    def to_yaml(self, add_edsl_version=False, filename: str = None) -> Union[str, None]:
+        import yaml
+
+        output = yaml.dump(self.to_dict(add_edsl_version=add_edsl_version))
+        if not filename:
+            return output
+
+        with open(filename, "w") as f:
+            f.write(output)
 
-    def print(self):
-        if is_notebook():
-            display(self.rich_print())
+    @classmethod
+    def from_yaml(cls, yaml_str: Optional[str] = None, filename: Optional[str] = None):
+        if yaml_str is None and filename is not None:
+            with open(filename, "r") as f:
+                yaml_str = f.read()
+                return cls.from_yaml(yaml_str=yaml_str)
+        elif yaml_str and filename is None:
+            import yaml
+
+            d = yaml.load(yaml_str, Loader=yaml.FullLoader)
+            return cls.from_dict(d)
         else:
-            from rich.console import Console
+            raise ValueError("Either yaml_str or filename must be provided.")
 
-            console = Console()
-            console.print(self.rich_print())
+    def create_download_link(self):
+        from tempfile import NamedTemporaryFile
+        from edsl.scenarios.FileStore import FileStore
 
+        with NamedTemporaryFile(suffix=".json.gz") as f:
+            self.save(f.name)
+            print(f.name)
+            fs = FileStore(path=f.name)
+        return fs.create_link()
 
-class PersistenceMixin:
-    def save(self, filename):
-        with gzip.open(filename, "wb") as f:
-            f.write(json.dumps(self.to_dict()).encode("utf-8"))
+    @classmethod
+    def pull(
+        cls,
+        uuid: Optional[Union[str, UUID]] = None,
+        url: Optional[str] = None,
+        expected_parrot_url: Optional[str] = None,
+    ):
+        """Pull the object from coop."""
+        from edsl.coop import Coop
+        from edsl.coop.utils import ObjectRegistry
+
+        object_type = ObjectRegistry.get_object_type_by_edsl_class(cls)
+        coop = Coop(url=expected_parrot_url)
+        return coop.get(uuid, url, object_type)
 
     @classmethod
-    def load(cls, filename):
+    def delete(cls, uuid: Optional[Union[str, UUID]] = None, url: Optional[str] = None):
+        """Delete the object from coop."""
+        from edsl.coop import Coop
+
+        coop = Coop()
+        return coop.delete(uuid, url)
+
+    @classmethod
+    def patch(
+        cls,
+        uuid: Optional[Union[str, UUID]] = None,
+        url: Optional[str] = None,
+        description: Optional[str] = None,
+        alias: Optional[str] = None,
+        value: Optional[Any] = None,
+        visibility: Optional[str] = None,
+    ):
+        """
+        Patch an uploaded objects attributes.
+        - `description` changes the description of the object on Coop
+        - `value` changes the value of the object on Coop. **has to be an EDSL object**
+        - `visibility` changes the visibility of the object on Coop
+        """
+        from edsl.coop import Coop
+
+        coop = Coop()
+        return coop.patch(uuid, url, description, alias, value, visibility)
+
+    @classmethod
+    def search(cls, query):
+        """Search for objects on coop."""
+        from edsl.coop import Coop
+
+        c = Coop()
+        return c.search(cls, query)
+
+    def store(self, d: dict, key_name: Optional[str] = None):
+        if key_name is None:
+            index = len(d)
+        else:
+            index = key_name
+        d[index] = self
+
+    def save(self, filename, compress=True):
+        """Save the object to a file as zippped JSON.
+
+        >>> obj.save("obj.json.gz")
+
+        """
+        if filename.endswith("json.gz"):
+            import warnings
+
+            filename = filename[:-8]
+        if filename.endswith("json"):
+            filename = filename[:-5]
+
+        if compress:
+            full_file_name = filename + ".json.gz"
+            with gzip.open(full_file_name, "wb") as f:
+                f.write(json.dumps(self.to_dict()).encode("utf-8"))
+        else:
+            full_file_name = filename + ".json"
+            with open(filename + ".json", "w") as f:
+                f.write(json.dumps(self.to_dict()))
+
+        print("Saved to", full_file_name)
+
+    @staticmethod
+    def open_compressed_file(filename):
         with gzip.open(filename, "rb") as f:
             file_contents = f.read()
             file_contents_decoded = file_contents.decode("utf-8")
             d = json.loads(file_contents_decoded)
-            # d = json.loads(f.read().decode("utf-8"))
-        return cls.from_dict(d)
+        return d
 
-    def post(self):
-        from edsl.utilities.pastebin import post
+    @staticmethod
+    def open_regular_file(filename):
+        with open(filename, "r") as f:
+            d = json.loads(f.read())
+        return d
 
-        post(self)
+    @classmethod
+    def load(cls, filename):
+        """Load the object from a file.
+
+        >>> obj = cls.load("obj.json.gz")
+
+        """
+
+        if filename.endswith("json.gz"):
+            d = cls.open_compressed_file(filename)
+        elif filename.endswith("json"):
+            d = cls.open_regular_file(filename)
+        else:
+            try:
+                d = cls.open_compressed_file(filename + ".json.gz")
+            except:
+                d = cls.open_regular_file(filename + ".json")
+            # finally:
+            #    raise ValueError("File must be a json or json.gz file")
+
+        return cls.from_dict(d)
 
 
 class RegisterSubclassesMeta(ABCMeta):
+    """Metaclass for registering subclasses."""
+
     _registry = {}
 
     def __init__(cls, name, bases, nmspc):
+        """Register the class in the registry upon creation."""
         super(RegisterSubclassesMeta, cls).__init__(name, bases, nmspc)
         if cls.__name__ != "Base":
             RegisterSubclassesMeta._registry[cls.__name__] = cls
 
     @staticmethod
-    def get_registry():
-        return dict(RegisterSubclassesMeta._registry)
+    def get_registry(exclude_classes: Optional[list] = None):
+        """Return the registry of subclasses."""
+        if exclude_classes is None:
+            exclude_classes = []
+        return {
+            k: v
+            for k, v in dict(RegisterSubclassesMeta._registry).items()
+            if k not in exclude_classes
+        }
 
 
-class Base(RichPrintingMixin, PersistenceMixin, ABC, metaclass=RegisterSubclassesMeta):
-    @abstractmethod
-    def example():
-        """This method should be implemented by subclasses."""
-        raise NotImplementedError("This method is not implemented yet.")
+class DiffMethodsMixin:
+    def __sub__(self, other):
+        """Return the difference between two objects."""
+        from edsl.BaseDiff import BaseDiff
+
+        return BaseDiff(self, other)
+
+
+def is_iterable(obj):
+    try:
+        iter(obj)
+    except TypeError:
+        return False
+    return True
+
+
+class RepresentationMixin:
+    def json(self):
+        return json.loads(json.dumps(self.to_dict(add_edsl_version=False)))
+
+    def to_dataset(self):
+        from edsl.results.Dataset import Dataset
+
+        return Dataset.from_edsl_object(self)
+
+    def view(self):
+        "Displays an interactive / perspective view of the object"
+        return self.to_dataset().view()
+
+    # def print(self, format="rich"):
+    #     return self.to_dataset().table()
+
+    def display_dict(self):
+        display_dict = {}
+        d = self.to_dict(add_edsl_version=False)
+        for key, value in d.items():
+            if isinstance(value, dict):
+                for k, v in value.items():
+                    display_dict[f"{key}:{k}"] = v
+            elif isinstance(value, list):
+                for i, v in enumerate(value):
+                    display_dict[f"{key}:{i}"] = v
+            else:
+                display_dict[key] = value
+        return display_dict
+
+    def print(self, format="rich"):
+        from rich.table import Table
+        from rich.console import Console
+
+        table = Table(title=self.__class__.__name__)
+        table.add_column("Key", style="bold")
+        table.add_column("Value", style="bold")
+
+        for key, value in self.display_dict().items():
+            table.add_row(key, str(value))
+
+        console = Console(record=True)
+        console.print(table)
+
+    def help(obj):
+        """
+        Extract all public instance methods and their docstrings from a class instance.
+
+        Args:
+            obj: The instance to inspect
+
+        Returns:
+            dict: A dictionary where keys are method names and values are their docstrings
+        """
+        import inspect
+
+        if inspect.isclass(obj):
+            raise TypeError("Please provide a class instance, not a class")
+
+        methods = {}
+
+        # Get all members of the instance
+        for name, member in inspect.getmembers(obj):
+            # Skip private and special methods (those starting with underscore)
+            if name.startswith("_"):
+                continue
+
+            # Check if it's specifically an instance method
+            if inspect.ismethod(member):
+                # Get the docstring (or empty string if none exists)
+                docstring = inspect.getdoc(member) or ""
+                methods[name] = docstring
+
+        from edsl.results.Dataset import Dataset
+
+        d = Dataset(
+            [
+                {"method": list(methods.keys())},
+                {"documentation": list(methods.values())},
+            ]
+        )
+        return d
+
+    def _repr_html_(self):
+        from edsl.results.TableDisplay import TableDisplay
+
+        if hasattr(self, "_summary"):
+            summary_dict = self._summary()
+            summary_line = "".join([f" {k}: {v};" for k, v in summary_dict.items()])
+            class_name = self.__class__.__name__
+            docs = getattr(self, "__documentation__", "")
+            return (
+                "<p>"
+                + f"<a href='{docs}'>{class_name}</a>"
+                + summary_line
+                + "</p>"
+                + self.table()._repr_html_()
+            )
+        else:
+            class_name = self.__class__.__name__
+            documenation = getattr(self, "__documentation__", "")
+            summary_line = "<p>" + f"<a href='{documenation}'>{class_name}</a>" + "</p>"
+            display_dict = self.display_dict()
+            return (
+                summary_line
+                + TableDisplay.from_dictionary_wide(display_dict)._repr_html_()
+            )
+
+    def __str__(self):
+        return self.__repr__()
+
+
+class HashingMixin:
+    def __hash__(self) -> int:
+        """Return a hash of the question."""
+        from edsl.utilities.utilities import dict_hash
+
+        return dict_hash(self.to_dict(add_edsl_version=False))
+
+    def __eq__(self, other):
+        """Return whether two objects are equal."""
+        return hash(self) == hash(other)
+
+
+class Base(
+    RepresentationMixin,
+    PersistenceMixin,
+    DiffMethodsMixin,
+    HashingMixin,
+    ABC,
+    metaclass=RegisterSubclassesMeta,
+):
+    """Base class for all classes in the package."""
+
+    def keys(self):
+        """Return the keys of the object."""
+        _keys = list(self.to_dict().keys())
+        if "edsl_version" in _keys:
+            _keys.remove("edsl_version")
+        if "edsl_class_name" in _keys:
+            _keys.remove("edsl_class_name")
+        return _keys
+
+    def values(self):
+        """Return the values of the object."""
+        data = self.to_dict()
+        keys = self.keys()
+        return {data[key] for key in keys}
 
     @abstractmethod
-    def rich_print():
+    def example():
         """This method should be implemented by subclasses."""
         raise NotImplementedError("This method is not implemented yet.")
 
@@ -80,6 +379,16 @@ class Base(RichPrintingMixin, PersistenceMixin, ABC, metaclass=RegisterSubclasse
         """This method should be implemented by subclasses."""
         raise NotImplementedError("This method is not implemented yet.")
 
+    def to_json(self):
+        return json.dumps(self.to_dict())
+
+    def store(self, d: dict, key_name: Optional[str] = None):
+        if key_name is None:
+            index = len(d)
+        else:
+            index = key_name
+        d[index] = self
+
     @abstractmethod
     def from_dict():
         """This method should be implemented by subclasses."""
@@ -91,6 +400,7 @@ class Base(RichPrintingMixin, PersistenceMixin, ABC, metaclass=RegisterSubclasse
         raise NotImplementedError("This method is not implemented yet.")
 
     def show_methods(self, show_docstrings=True):
+        """Show the methods of the object."""
         public_methods_with_docstrings = [
             (method, getattr(self, method).__doc__)
             for method in dir(self)

edsl/BaseDiff.py

@@ -0,0 +1,260 @@
+import difflib
+import json
+from typing import Any, Dict, Tuple
+from collections import UserList
+import inspect
+
+
+class BaseDiffCollection(UserList):
+    def __init__(self, diffs=None):
+        if diffs is None:
+            diffs = []
+        super().__init__(diffs)
+
+    def apply(self, obj: Any):
+        for diff in self:
+            obj = diff.apply(obj)
+        return obj
+
+    def add_diff(self, diff) -> "BaseDiffCollection":
+        self.append(diff)
+        return self
+
+
+class DummyObject:
+    def __init__(self, object_dict):
+        self.object_dict = object_dict
+
+    def to_dict(self):
+        return self.object_dict
+
+
+class BaseDiff:
+    def __init__(
+        self, obj1: Any, obj2: Any, added=None, removed=None, modified=None, level=0
+    ):
+        self.level = level
+
+        self.obj1 = obj1
+        self.obj2 = obj2
+
+        if "sort" in inspect.signature(obj1.to_dict).parameters:
+            self._dict1 = obj1.to_dict(sort=True)
+            self._dict2 = obj2.to_dict(sort=True)
+        else:
+            self._dict1 = obj1.to_dict()
+            self._dict2 = obj2.to_dict()
+        self._obj_class = type(obj1)
+
+        self.added = added
+        self.removed = removed
+        self.modified = modified
+
+    def __bool__(self):
+        return bool(self.added or self.removed or self.modified)
+
+    @property
+    def added(self):
+        if self._added is None:
+            self._added = self._find_added()
+        return self._added
+
+    def __add__(self, other):
+        return self.apply(other)
+
+    @added.setter
+    def added(self, value):
+        self._added = value if value is not None else self._find_added()
+
+    @property
+    def removed(self):
+        if self._removed is None:
+            self._removed = self._find_removed()
+        return self._removed
+
+    @removed.setter
+    def removed(self, value):
+        self._removed = value if value is not None else self._find_removed()
+
+    @property
+    def modified(self):
+        if self._modified is None:
+            self._modified = self._find_modified()
+        return self._modified
+
+    @modified.setter
+    def modified(self, value):
+        self._modified = value if value is not None else self._find_modified()
+
+    def _find_added(self) -> Dict[Any, Any]:
+        return {k: self._dict2[k] for k in self._dict2 if k not in self._dict1}
+
+    def _find_removed(self) -> Dict[Any, Any]:
+        return {k: self._dict1[k] for k in self._dict1 if k not in self._dict2}
+
+    def _find_modified(self) -> Dict[Any, Tuple[Any, Any, str]]:
+        modified = {}
+        for k in self._dict1:
+            if k in self._dict2 and self._dict1[k] != self._dict2[k]:
+                if isinstance(self._dict1[k], str) and isinstance(self._dict2[k], str):
+                    diff = self._diff_strings(self._dict1[k], self._dict2[k])
+                    modified[k] = (self._dict1[k], self._dict2[k], diff)
+                elif isinstance(self._dict1[k], dict) and isinstance(
+                    self._dict2[k], dict
+                ):
+                    diff = self._diff_dicts(self._dict1[k], self._dict2[k])
+                    modified[k] = (self._dict1[k], self._dict2[k], diff)
+                elif isinstance(self._dict1[k], list) and isinstance(
+                    self._dict2[k], list
+                ):
+                    d1 = dict(zip(range(len(self._dict1[k])), self._dict1[k]))
+                    d2 = dict(zip(range(len(self._dict2[k])), self._dict2[k]))
+                    diff = BaseDiff(
+                        DummyObject(d1), DummyObject(d2), level=self.level + 1
+                    )
+                    modified[k] = (self._dict1[k], self._dict2[k], diff)
+                else:
+                    modified[k] = (self._dict1[k], self._dict2[k], "")
+        return modified
+
+    @staticmethod
+    def is_json(string_that_could_be_json: str) -> bool:
+        try:
+            json.loads(string_that_could_be_json)
+            return True
+        except json.JSONDecodeError:
+            return False
+
+    def _diff_dicts(self, dict1: Dict[str, Any], dict2: Dict[str, Any]) -> str:
+        diff = BaseDiff(DummyObject(dict1), DummyObject(dict2), level=self.level + 1)
+        return diff
+
+    def _diff_strings(self, str1: str, str2: str) -> str:
+        if self.is_json(str1) and self.is_json(str2):
+            diff = self._diff_dicts(json.loads(str1), json.loads(str2))
+            return diff
+        diff = difflib.ndiff(str1.splitlines(), str2.splitlines())
+        return diff
+
+    def apply(self, obj: Any):
+        """Apply the diff to the object."""
+
+        new_obj_dict = obj.to_dict()
+        for k, v in self.added.items():
+            new_obj_dict[k] = v
+        for k in self.removed.keys():
+            del new_obj_dict[k]
+        for k, (v1, v2, diff) in self.modified.items():
+            new_obj_dict[k] = v2
+
+        return obj.from_dict(new_obj_dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        return {
+            "added": self.added,
+            "removed": self.removed,
+            "modified": self.modified,
+            "obj1": self._dict1,
+            "obj2": self._dict2,
+            "obj_class": self._obj_class.__name__,
+            "level": self.level,
+        }
+
+    @classmethod
+    def from_dict(cls, diff_dict: Dict[str, Any], obj1: Any, obj2: Any):
+        return cls(
+            obj1=obj1,
+            obj2=obj2,
+            added=diff_dict["added"],
+            removed=diff_dict["removed"],
+            modified=diff_dict["modified"],
+            level=diff_dict["level"],
+        )
+
+    class Results(UserList):
+        def __init__(self, prepend=" ", level=0):
+            super().__init__()
+            self.prepend = prepend
+            self.level = level
+
+        def append(self, item):
+            super().append(self.prepend * self.level + item)
+
+    def __str__(self):
+        prepend = " "
+        result = self.Results(level=self.level, prepend="\t")
+        if self.added:
+            result.append("Added keys and values:")
+            for k, v in self.added.items():
+                result.append(prepend + f"  {k}: {v}")
+        if self.removed:
+            result.append("Removed keys and values:")
+            for k, v in self.removed.items():
+                result.append(f"  {k}: {v}")
+        if self.modified:
+            result.append("Modified keys and values:")
+            for k, (v1, v2, diff) in self.modified.items():
+                result.append(f"Key: {k}:")
+                result.append(f"    Old value: {v1}")
+                result.append(f"    New value: {v2}")
+                if diff:
+                    result.append(f"    Diff:")
+                    try:
+                        for line in diff:
+                            result.append(f"      {line}")
+                    except:
+                        result.append(f"      {diff}")
+        return "\n".join(result)
+
+    def __repr__(self):
+        return (
+            f"BaseDiff(obj1={self.obj1!r}, obj2={self.obj2!r}, added={self.added!r}, "
+            f"removed={self.removed!r}, modified={self.modified!r})"
+        )
+
+    def add_diff(self, diff) -> "BaseDiffCollection":
+        return BaseDiffCollection([self, diff])
+
+
+if __name__ == "__main__":
+    from edsl import Question
+
+    q_ft = Question.example("free_text")
+    q_mc = Question.example("multiple_choice")
+
+    diff1 = q_ft - q_mc
+    assert q_ft == q_mc + diff1
+    assert q_ft == diff1.apply(q_mc)
+    # new_q_mc = diff1.apply(q_ft)
+    # assert new_q_mc == q_mc
+
+    # new_q_mc = q_ft + diff1
+    # assert new_q_mc == q_mc
+
+    # new_q_mc = diff1 + q_ft
+    # assert new_q_mc == q_mc
+
+    # ## Test chain of diffs
+    q0 = Question.example("free_text")
+    q1 = q0.copy()
+    q1.question_text = "Why is Buzzard's Bay so named?"
+    diff1 = q1 - q0
+    q2 = q1.copy()
+    q2.question_name = "buzzard_bay"
+    diff2 = q2 - q1
+
+    diff_chain = diff1.add_diff(diff2)
+
+    new_q2 = diff_chain.apply(q0)
+    assert new_q2 == q2
+
+    new_q2 = diff_chain + q0
+    assert new_q2 == q2
+
+    # new_diffs = diff1.add_diff(diff1).add_diff(diff1)
+    # assert len(new_diffs) == 3
+
+    # q0 = Question.example("free_text")
+    # q1 = Question.example("free_text")
+    # q1.question_text = "Why is Buzzard's Bay so named?"
+    # q2 = q1.copy()