Initial commit

backend/venv/Lib/site-packages/nltk/tree/__init__.py

@@ -0,0 +1,52 @@
+# Natural Language Toolkit: Machine Translation
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Tom Aarsen <>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+NLTK Tree Package
+
+This package may be used for representing hierarchical language
+structures, such as syntax trees and morphological trees.
+"""
+
+# TODO: add LabelledTree (can be used for dependency trees)
+
+from nltk.tree.immutable import (
+    ImmutableMultiParentedTree,
+    ImmutableParentedTree,
+    ImmutableProbabilisticTree,
+    ImmutableTree,
+)
+from nltk.tree.parented import MultiParentedTree, ParentedTree
+from nltk.tree.parsing import bracket_parse, sinica_parse
+from nltk.tree.prettyprinter import TreePrettyPrinter
+from nltk.tree.probabilistic import ProbabilisticTree
+from nltk.tree.transforms import (
+    chomsky_normal_form,
+    collapse_unary,
+    un_chomsky_normal_form,
+)
+from nltk.tree.tree import Tree
+
+__all__ = [
+    "ImmutableMultiParentedTree",
+    "ImmutableParentedTree",
+    "ImmutableProbabilisticTree",
+    "ImmutableTree",
+    "MultiParentedTree",
+    "ParentedTree",
+    "bracket_parse",
+    "sinica_parse",
+    "TreePrettyPrinter",
+    "ProbabilisticTree",
+    "chomsky_normal_form",
+    "collapse_unary",
+    "un_chomsky_normal_form",
+    "Tree",
+]

backend/venv/Lib/site-packages/nltk/tree/immutable.py

@@ -0,0 +1,124 @@
+# Natural Language Toolkit: Text Trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Tom Aarsen <>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+from nltk.probability import ProbabilisticMixIn
+from nltk.tree.parented import MultiParentedTree, ParentedTree
+from nltk.tree.tree import Tree
+
+
+class ImmutableTree(Tree):
+    def __init__(self, node, children=None):
+        super().__init__(node, children)
+        # Precompute our hash value.  This ensures that we're really
+        # immutable.  It also means we only have to calculate it once.
+        try:
+            self._hash = hash((self._label, tuple(self)))
+        except (TypeError, ValueError) as e:
+            raise ValueError(
+                "%s: node value and children " "must be immutable" % type(self).__name__
+            ) from e
+
+    def __setitem__(self, index, value):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __setslice__(self, i, j, value):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __delitem__(self, index):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __delslice__(self, i, j):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __iadd__(self, other):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __imul__(self, other):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def append(self, v):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def extend(self, v):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def pop(self, v=None):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def remove(self, v):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def reverse(self):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def sort(self):
+        raise ValueError("%s may not be modified" % type(self).__name__)
+
+    def __hash__(self):
+        return self._hash
+
+    def set_label(self, value):
+        """
+        Set the node label.  This will only succeed the first time the
+        node label is set, which should occur in ImmutableTree.__init__().
+        """
+        if hasattr(self, "_label"):
+            raise ValueError("%s may not be modified" % type(self).__name__)
+        self._label = value
+
+
+class ImmutableProbabilisticTree(ImmutableTree, ProbabilisticMixIn):
+    def __init__(self, node, children=None, **prob_kwargs):
+        ImmutableTree.__init__(self, node, children)
+        ProbabilisticMixIn.__init__(self, **prob_kwargs)
+        self._hash = hash((self._label, tuple(self), self.prob()))
+
+    # We have to patch up these methods to make them work right:
+    def _frozen_class(self):
+        return ImmutableProbabilisticTree
+
+    def __repr__(self):
+        return f"{Tree.__repr__(self)} [{self.prob()}]"
+
+    def __str__(self):
+        return f"{self.pformat(margin=60)} [{self.prob()}]"
+
+    def copy(self, deep=False):
+        if not deep:
+            return type(self)(self._label, self, prob=self.prob())
+        else:
+            return type(self).convert(self)
+
+    @classmethod
+    def convert(cls, val):
+        if isinstance(val, Tree):
+            children = [cls.convert(child) for child in val]
+            if isinstance(val, ProbabilisticMixIn):
+                return cls(val._label, children, prob=val.prob())
+            else:
+                return cls(val._label, children, prob=1.0)
+        else:
+            return val
+
+
+class ImmutableParentedTree(ImmutableTree, ParentedTree):
+    pass
+
+
+class ImmutableMultiParentedTree(ImmutableTree, MultiParentedTree):
+    pass
+
+
+__all__ = [
+    "ImmutableProbabilisticTree",
+    "ImmutableTree",
+    "ImmutableParentedTree",
+    "ImmutableMultiParentedTree",
+]

backend/venv/Lib/site-packages/nltk/tree/parented.py

@@ -0,0 +1,590 @@
+# Natural Language Toolkit: Text Trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Tom Aarsen <>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+import warnings
+from abc import ABCMeta, abstractmethod
+
+from nltk.tree.tree import Tree
+from nltk.util import slice_bounds
+
+
+######################################################################
+## Parented trees
+######################################################################
+class AbstractParentedTree(Tree, metaclass=ABCMeta):
+    """
+    An abstract base class for a ``Tree`` that automatically maintains
+    pointers to parent nodes.  These parent pointers are updated
+    whenever any change is made to a tree's structure.  Two subclasses
+    are currently defined:
+
+      - ``ParentedTree`` is used for tree structures where each subtree
+        has at most one parent.  This class should be used in cases
+        where there is no"sharing" of subtrees.
+
+      - ``MultiParentedTree`` is used for tree structures where a
+        subtree may have zero or more parents.  This class should be
+        used in cases where subtrees may be shared.
+
+    Subclassing
+    ===========
+    The ``AbstractParentedTree`` class redefines all operations that
+    modify a tree's structure to call two methods, which are used by
+    subclasses to update parent information:
+
+      - ``_setparent()`` is called whenever a new child is added.
+      - ``_delparent()`` is called whenever a child is removed.
+    """
+
+    def __init__(self, node, children=None):
+        super().__init__(node, children)
+        # If children is None, the tree is read from node, and
+        # all parents will be set during parsing.
+        if children is not None:
+            # Otherwise we have to set the parent of the children.
+            # Iterate over self, and *not* children, because children
+            # might be an iterator.
+            for i, child in enumerate(self):
+                if isinstance(child, Tree):
+                    self._setparent(child, i, dry_run=True)
+            for i, child in enumerate(self):
+                if isinstance(child, Tree):
+                    self._setparent(child, i)
+
+    # ////////////////////////////////////////////////////////////
+    # Parent management
+    # ////////////////////////////////////////////////////////////
+    @abstractmethod
+    def _setparent(self, child, index, dry_run=False):
+        """
+        Update the parent pointer of ``child`` to point to ``self``.  This
+        method is only called if the type of ``child`` is ``Tree``;
+        i.e., it is not called when adding a leaf to a tree.  This method
+        is always called before the child is actually added to the
+        child list of ``self``.
+
+        :type child: Tree
+        :type index: int
+        :param index: The index of ``child`` in ``self``.
+        :raise TypeError: If ``child`` is a tree with an impropriate
+            type.  Typically, if ``child`` is a tree, then its type needs
+            to match the type of ``self``.  This prevents mixing of
+            different tree types (single-parented, multi-parented, and
+            non-parented).
+        :param dry_run: If true, the don't actually set the child's
+            parent pointer; just check for any error conditions, and
+            raise an exception if one is found.
+        """
+
+    @abstractmethod
+    def _delparent(self, child, index):
+        """
+        Update the parent pointer of ``child`` to not point to self.  This
+        method is only called if the type of ``child`` is ``Tree``; i.e., it
+        is not called when removing a leaf from a tree.  This method
+        is always called before the child is actually removed from the
+        child list of ``self``.
+
+        :type child: Tree
+        :type index: int
+        :param index: The index of ``child`` in ``self``.
+        """
+
+    # ////////////////////////////////////////////////////////////
+    # Methods that add/remove children
+    # ////////////////////////////////////////////////////////////
+    # Every method that adds or removes a child must make
+    # appropriate calls to _setparent() and _delparent().
+
+    def __delitem__(self, index):
+        # del ptree[start:stop]
+        if isinstance(index, slice):
+            start, stop, step = slice_bounds(self, index, allow_step=True)
+            # Clear all the children pointers.
+            for i in range(start, stop, step):
+                if isinstance(self[i], Tree):
+                    self._delparent(self[i], i)
+            # Delete the children from our child list.
+            super().__delitem__(index)
+
+        # del ptree[i]
+        elif isinstance(index, int):
+            if index < 0:
+                index += len(self)
+            if index < 0:
+                raise IndexError("index out of range")
+            # Clear the child's parent pointer.
+            if isinstance(self[index], Tree):
+                self._delparent(self[index], index)
+            # Remove the child from our child list.
+            super().__delitem__(index)
+
+        elif isinstance(index, (list, tuple)):
+            # del ptree[()]
+            if len(index) == 0:
+                raise IndexError("The tree position () may not be deleted.")
+            # del ptree[(i,)]
+            elif len(index) == 1:
+                del self[index[0]]
+            # del ptree[i1, i2, i3]
+            else:
+                del self[index[0]][index[1:]]
+
+        else:
+            raise TypeError(
+                "%s indices must be integers, not %s"
+                % (type(self).__name__, type(index).__name__)
+            )
+
+    def __setitem__(self, index, value):
+        # ptree[start:stop] = value
+        if isinstance(index, slice):
+            start, stop, step = slice_bounds(self, index, allow_step=True)
+            # make a copy of value, in case it's an iterator
+            if not isinstance(value, (list, tuple)):
+                value = list(value)
+            # Check for any error conditions, so we can avoid ending
+            # up in an inconsistent state if an error does occur.
+            for i, child in enumerate(value):
+                if isinstance(child, Tree):
+                    self._setparent(child, start + i * step, dry_run=True)
+            # clear the child pointers of all parents we're removing
+            for i in range(start, stop, step):
+                if isinstance(self[i], Tree):
+                    self._delparent(self[i], i)
+            # set the child pointers of the new children.  We do this
+            # after clearing *all* child pointers, in case we're e.g.
+            # reversing the elements in a tree.
+            for i, child in enumerate(value):
+                if isinstance(child, Tree):
+                    self._setparent(child, start + i * step)
+            # finally, update the content of the child list itself.
+            super().__setitem__(index, value)
+
+        # ptree[i] = value
+        elif isinstance(index, int):
+            if index < 0:
+                index += len(self)
+            if index < 0:
+                raise IndexError("index out of range")
+            # if the value is not changing, do nothing.
+            if value is self[index]:
+                return
+            # Set the new child's parent pointer.
+            if isinstance(value, Tree):
+                self._setparent(value, index)
+            # Remove the old child's parent pointer
+            if isinstance(self[index], Tree):
+                self._delparent(self[index], index)
+            # Update our child list.
+            super().__setitem__(index, value)
+
+        elif isinstance(index, (list, tuple)):
+            # ptree[()] = value
+            if len(index) == 0:
+                raise IndexError("The tree position () may not be assigned to.")
+            # ptree[(i,)] = value
+            elif len(index) == 1:
+                self[index[0]] = value
+            # ptree[i1, i2, i3] = value
+            else:
+                self[index[0]][index[1:]] = value
+
+        else:
+            raise TypeError(
+                "%s indices must be integers, not %s"
+                % (type(self).__name__, type(index).__name__)
+            )
+
+    def append(self, child):
+        if isinstance(child, Tree):
+            self._setparent(child, len(self))
+        super().append(child)
+
+    def extend(self, children):
+        for child in children:
+            if isinstance(child, Tree):
+                self._setparent(child, len(self))
+            super().append(child)
+
+    def insert(self, index, child):
+        # Handle negative indexes.  Note that if index < -len(self),
+        # we do *not* raise an IndexError, unlike __getitem__.  This
+        # is done for consistency with list.__getitem__ and list.index.
+        if index < 0:
+            index += len(self)
+        if index < 0:
+            index = 0
+        # Set the child's parent, and update our child list.
+        if isinstance(child, Tree):
+            self._setparent(child, index)
+        super().insert(index, child)
+
+    def pop(self, index=-1):
+        if index < 0:
+            index += len(self)
+        if index < 0:
+            raise IndexError("index out of range")
+        if isinstance(self[index], Tree):
+            self._delparent(self[index], index)
+        return super().pop(index)
+
+    # n.b.: like `list`, this is done by equality, not identity!
+    # To remove a specific child, use del ptree[i].
+    def remove(self, child):
+        index = self.index(child)
+        if isinstance(self[index], Tree):
+            self._delparent(self[index], index)
+        super().remove(child)
+
+    # We need to implement __getslice__ and friends, even though
+    # they're deprecated, because otherwise list.__getslice__ will get
+    # called (since we're subclassing from list).  Just delegate to
+    # __getitem__ etc., but use max(0, start) and max(0, stop) because
+    # because negative indices are already handled *before*
+    # __getslice__ is called; and we don't want to double-count them.
+    if hasattr(list, "__getslice__"):
+
+        def __getslice__(self, start, stop):
+            return self.__getitem__(slice(max(0, start), max(0, stop)))
+
+        def __delslice__(self, start, stop):
+            return self.__delitem__(slice(max(0, start), max(0, stop)))
+
+        def __setslice__(self, start, stop, value):
+            return self.__setitem__(slice(max(0, start), max(0, stop)), value)
+
+    def __getnewargs__(self):
+        """Method used by the pickle module when un-pickling.
+        This method provides the arguments passed to ``__new__``
+        upon un-pickling. Without this method, ParentedTree instances
+        cannot be pickled and unpickled in Python 3.7+ onwards.
+
+        :return: Tuple of arguments for ``__new__``, i.e. the label
+            and the children of this node.
+        :rtype: Tuple[Any, List[AbstractParentedTree]]
+        """
+        return (self._label, list(self))
+
+
+class ParentedTree(AbstractParentedTree):
+    """
+    A ``Tree`` that automatically maintains parent pointers for
+    single-parented trees.  The following are methods for querying
+    the structure of a parented tree: ``parent``, ``parent_index``,
+    ``left_sibling``, ``right_sibling``, ``root``, ``treeposition``.
+
+    Each ``ParentedTree`` may have at most one parent.  In
+    particular, subtrees may not be shared.  Any attempt to reuse a
+    single ``ParentedTree`` as a child of more than one parent (or
+    as multiple children of the same parent) will cause a
+    ``ValueError`` exception to be raised.
+
+    ``ParentedTrees`` should never be used in the same tree as ``Trees``
+    or ``MultiParentedTrees``.  Mixing tree implementations may result
+    in incorrect parent pointers and in ``TypeError`` exceptions.
+    """
+
+    def __init__(self, node, children=None):
+        self._parent = None
+        """The parent of this Tree, or None if it has no parent."""
+        super().__init__(node, children)
+        if children is None:
+            # If children is None, the tree is read from node.
+            # After parsing, the parent of the immediate children
+            # will point to an intermediate tree, not self.
+            # We fix this by brute force:
+            for i, child in enumerate(self):
+                if isinstance(child, Tree):
+                    child._parent = None
+                    self._setparent(child, i)
+
+    def _frozen_class(self):
+        from nltk.tree.immutable import ImmutableParentedTree
+
+        return ImmutableParentedTree
+
+    def copy(self, deep=False):
+        if not deep:
+            warnings.warn(
+                f"{self.__class__.__name__} objects do not support shallow copies. Defaulting to a deep copy."
+            )
+        return super().copy(deep=True)
+
+    # /////////////////////////////////////////////////////////////////
+    # Methods
+    # /////////////////////////////////////////////////////////////////
+
+    def parent(self):
+        """The parent of this tree, or None if it has no parent."""
+        return self._parent
+
+    def parent_index(self):
+        """
+        The index of this tree in its parent.  I.e.,
+        ``ptree.parent()[ptree.parent_index()] is ptree``.  Note that
+        ``ptree.parent_index()`` is not necessarily equal to
+        ``ptree.parent.index(ptree)``, since the ``index()`` method
+        returns the first child that is equal to its argument.
+        """
+        if self._parent is None:
+            return None
+        for i, child in enumerate(self._parent):
+            if child is self:
+                return i
+        assert False, "expected to find self in self._parent!"
+
+    def left_sibling(self):
+        """The left sibling of this tree, or None if it has none."""
+        parent_index = self.parent_index()
+        if self._parent and parent_index > 0:
+            return self._parent[parent_index - 1]
+        return None  # no left sibling
+
+    def right_sibling(self):
+        """The right sibling of this tree, or None if it has none."""
+        parent_index = self.parent_index()
+        if self._parent and parent_index < (len(self._parent) - 1):
+            return self._parent[parent_index + 1]
+        return None  # no right sibling
+
+    def root(self):
+        """
+        The root of this tree.  I.e., the unique ancestor of this tree
+        whose parent is None.  If ``ptree.parent()`` is None, then
+        ``ptree`` is its own root.
+        """
+        root = self
+        while root.parent() is not None:
+            root = root.parent()
+        return root
+
+    def treeposition(self):
+        """
+        The tree position of this tree, relative to the root of the
+        tree.  I.e., ``ptree.root[ptree.treeposition] is ptree``.
+        """
+        if self.parent() is None:
+            return ()
+        else:
+            return self.parent().treeposition() + (self.parent_index(),)
+
+    # /////////////////////////////////////////////////////////////////
+    # Parent Management
+    # /////////////////////////////////////////////////////////////////
+
+    def _delparent(self, child, index):
+        # Sanity checks
+        assert isinstance(child, ParentedTree)
+        assert self[index] is child
+        assert child._parent is self
+
+        # Delete child's parent pointer.
+        child._parent = None
+
+    def _setparent(self, child, index, dry_run=False):
+        # If the child's type is incorrect, then complain.
+        if not isinstance(child, ParentedTree):
+            raise TypeError("Can not insert a non-ParentedTree into a ParentedTree")
+
+        # If child already has a parent, then complain.
+        if hasattr(child, "_parent") and child._parent is not None:
+            raise ValueError("Can not insert a subtree that already has a parent.")
+
+        # Set child's parent pointer & index.
+        if not dry_run:
+            child._parent = self
+
+
+class MultiParentedTree(AbstractParentedTree):
+    """
+    A ``Tree`` that automatically maintains parent pointers for
+    multi-parented trees.  The following are methods for querying the
+    structure of a multi-parented tree: ``parents()``, ``parent_indices()``,
+    ``left_siblings()``, ``right_siblings()``, ``roots``, ``treepositions``.
+
+    Each ``MultiParentedTree`` may have zero or more parents.  In
+    particular, subtrees may be shared.  If a single
+    ``MultiParentedTree`` is used as multiple children of the same
+    parent, then that parent will appear multiple times in its
+    ``parents()`` method.
+
+    ``MultiParentedTrees`` should never be used in the same tree as
+    ``Trees`` or ``ParentedTrees``.  Mixing tree implementations may
+    result in incorrect parent pointers and in ``TypeError`` exceptions.
+    """
+
+    def __init__(self, node, children=None):
+        self._parents = []
+        """A list of this tree's parents.  This list should not
+           contain duplicates, even if a parent contains this tree
+           multiple times."""
+        super().__init__(node, children)
+        if children is None:
+            # If children is None, the tree is read from node.
+            # After parsing, the parent(s) of the immediate children
+            # will point to an intermediate tree, not self.
+            # We fix this by brute force:
+            for i, child in enumerate(self):
+                if isinstance(child, Tree):
+                    child._parents = []
+                    self._setparent(child, i)
+
+    def _frozen_class(self):
+        from nltk.tree.immutable import ImmutableMultiParentedTree
+
+        return ImmutableMultiParentedTree
+
+    # /////////////////////////////////////////////////////////////////
+    # Methods
+    # /////////////////////////////////////////////////////////////////
+
+    def parents(self):
+        """
+        The set of parents of this tree.  If this tree has no parents,
+        then ``parents`` is the empty set.  To check if a tree is used
+        as multiple children of the same parent, use the
+        ``parent_indices()`` method.
+
+        :type: list(MultiParentedTree)
+        """
+        return list(self._parents)
+
+    def left_siblings(self):
+        """
+        A list of all left siblings of this tree, in any of its parent
+        trees.  A tree may be its own left sibling if it is used as
+        multiple contiguous children of the same parent.  A tree may
+        appear multiple times in this list if it is the left sibling
+        of this tree with respect to multiple parents.
+
+        :type: list(MultiParentedTree)
+        """
+        return [
+            parent[index - 1]
+            for (parent, index) in self._get_parent_indices()
+            if index > 0
+        ]
+
+    def right_siblings(self):
+        """
+        A list of all right siblings of this tree, in any of its parent
+        trees.  A tree may be its own right sibling if it is used as
+        multiple contiguous children of the same parent.  A tree may
+        appear multiple times in this list if it is the right sibling
+        of this tree with respect to multiple parents.
+
+        :type: list(MultiParentedTree)
+        """
+        return [
+            parent[index + 1]
+            for (parent, index) in self._get_parent_indices()
+            if index < (len(parent) - 1)
+        ]
+
+    def _get_parent_indices(self):
+        return [
+            (parent, index)
+            for parent in self._parents
+            for index, child in enumerate(parent)
+            if child is self
+        ]
+
+    def roots(self):
+        """
+        The set of all roots of this tree.  This set is formed by
+        tracing all possible parent paths until trees with no parents
+        are found.
+
+        :type: list(MultiParentedTree)
+        """
+        return list(self._get_roots_helper({}).values())
+
+    def _get_roots_helper(self, result):
+        if self._parents:
+            for parent in self._parents:
+                parent._get_roots_helper(result)
+        else:
+            result[id(self)] = self
+        return result
+
+    def parent_indices(self, parent):
+        """
+        Return a list of the indices where this tree occurs as a child
+        of ``parent``.  If this child does not occur as a child of
+        ``parent``, then the empty list is returned.  The following is
+        always true::
+
+          for parent_index in ptree.parent_indices(parent):
+              parent[parent_index] is ptree
+        """
+        if parent not in self._parents:
+            return []
+        else:
+            return [index for (index, child) in enumerate(parent) if child is self]
+
+    def treepositions(self, root):
+        """
+        Return a list of all tree positions that can be used to reach
+        this multi-parented tree starting from ``root``.  I.e., the
+        following is always true::
+
+          for treepos in ptree.treepositions(root):
+              root[treepos] is ptree
+        """
+        if self is root:
+            return [()]
+        else:
+            return [
+                treepos + (index,)
+                for parent in self._parents
+                for treepos in parent.treepositions(root)
+                for (index, child) in enumerate(parent)
+                if child is self
+            ]
+
+    # /////////////////////////////////////////////////////////////////
+    # Parent Management
+    # /////////////////////////////////////////////////////////////////
+
+    def _delparent(self, child, index):
+        # Sanity checks
+        assert isinstance(child, MultiParentedTree)
+        assert self[index] is child
+        assert len([p for p in child._parents if p is self]) == 1
+
+        # If the only copy of child in self is at index, then delete
+        # self from child's parent list.
+        for i, c in enumerate(self):
+            if c is child and i != index:
+                break
+        else:
+            child._parents.remove(self)
+
+    def _setparent(self, child, index, dry_run=False):
+        # If the child's type is incorrect, then complain.
+        if not isinstance(child, MultiParentedTree):
+            raise TypeError(
+                "Can not insert a non-MultiParentedTree into a MultiParentedTree"
+            )
+
+        # Add self as a parent pointer if it's not already listed.
+        if not dry_run:
+            for parent in child._parents:
+                if parent is self:
+                    break
+            else:
+                child._parents.append(self)
+
+
+__all__ = [
+    "ParentedTree",
+    "MultiParentedTree",
+]

backend/venv/Lib/site-packages/nltk/tree/parsing.py

@@ -0,0 +1,66 @@
+# Natural Language Toolkit: Text Trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Tom Aarsen <>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+import re
+
+from nltk.tree.tree import Tree
+
+######################################################################
+## Parsing
+######################################################################
+
+
+def bracket_parse(s):
+    """
+    Use Tree.read(s, remove_empty_top_bracketing=True) instead.
+    """
+    raise NameError("Use Tree.read(s, remove_empty_top_bracketing=True) instead.")
+
+
+def sinica_parse(s):
+    """
+    Parse a Sinica Treebank string and return a tree.  Trees are represented as nested brackettings,
+    as shown in the following example (X represents a Chinese character):
+    S(goal:NP(Head:Nep:XX)|theme:NP(Head:Nhaa:X)|quantity:Dab:X|Head:VL2:X)#0(PERIODCATEGORY)
+
+    :return: A tree corresponding to the string representation.
+    :rtype: Tree
+    :param s: The string to be converted
+    :type s: str
+    """
+    tokens = re.split(r"([()| ])", s)
+    for i in range(len(tokens)):
+        if tokens[i] == "(":
+            tokens[i - 1], tokens[i] = (
+                tokens[i],
+                tokens[i - 1],
+            )  # pull nonterminal inside parens
+        elif ":" in tokens[i]:
+            fields = tokens[i].split(":")
+            if len(fields) == 2:  # non-terminal
+                tokens[i] = fields[1]
+            else:
+                tokens[i] = "(" + fields[-2] + " " + fields[-1] + ")"
+        elif tokens[i] == "|":
+            tokens[i] = ""
+
+    treebank_string = " ".join(tokens)
+    return Tree.fromstring(treebank_string, remove_empty_top_bracketing=True)
+
+
+#    s = re.sub(r'^#[^\s]*\s', '', s)  # remove leading identifier
+#    s = re.sub(r'\w+:', '', s)       # remove role tags
+
+#    return s
+
+__all__ = [
+    "bracket_parse",
+    "sinica_parse",
+]

backend/venv/Lib/site-packages/nltk/tree/prettyprinter.py

@@ -0,0 +1,627 @@
+# Natural Language Toolkit: ASCII visualization of NLTK trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Andreas van Cranenburgh <A.W.vanCranenburgh@uva.nl>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+Pretty-printing of discontinuous trees.
+Adapted from the disco-dop project, by Andreas van Cranenburgh.
+https://github.com/andreasvc/disco-dop
+
+Interesting reference (not used for this code):
+T. Eschbach et al., Orth. Hypergraph Drawing, Journal of
+Graph Algorithms and Applications, 10(2) 141--157 (2006)149.
+https://jgaa.info/accepted/2006/EschbachGuentherBecker2006.10.2.pdf
+"""
+
+import re
+
+try:
+    from html import escape
+except ImportError:
+    from cgi import escape
+
+from collections import defaultdict
+from operator import itemgetter
+
+from nltk.tree.tree import Tree
+from nltk.util import OrderedDict
+
+ANSICOLOR = {
+    "black": 30,
+    "red": 31,
+    "green": 32,
+    "yellow": 33,
+    "blue": 34,
+    "magenta": 35,
+    "cyan": 36,
+    "white": 37,
+}
+
+
+class TreePrettyPrinter:
+    """
+    Pretty-print a tree in text format, either as ASCII or Unicode.
+    The tree can be a normal tree, or discontinuous.
+
+    ``TreePrettyPrinter(tree, sentence=None, highlight=())``
+    creates an object from which different visualizations can be created.
+
+    :param tree: a Tree object.
+    :param sentence: a list of words (strings). If `sentence` is given,
+        `tree` must contain integers as leaves, which are taken as indices
+        in `sentence`. Using this you can display a discontinuous tree.
+    :param highlight: Optionally, a sequence of Tree objects in `tree` which
+        should be highlighted. Has the effect of only applying colors to nodes
+        in this sequence (nodes should be given as Tree objects, terminals as
+        indices).
+
+    >>> from nltk.tree import Tree
+    >>> tree = Tree.fromstring('(S (NP Mary) (VP walks))')
+    >>> print(TreePrettyPrinter(tree).text())
+    ... # doctest: +NORMALIZE_WHITESPACE
+          S
+      ____|____
+     NP        VP
+     |         |
+    Mary     walks
+    """
+
+    def __init__(self, tree, sentence=None, highlight=()):
+        if sentence is None:
+            leaves = tree.leaves()
+            if (
+                leaves
+                and all(len(a) > 0 for a in tree.subtrees())
+                and all(isinstance(a, int) for a in leaves)
+            ):
+                sentence = [str(a) for a in leaves]
+            else:
+                # this deals with empty nodes (frontier non-terminals)
+                # and multiple/mixed terminals under non-terminals.
+                tree = tree.copy(True)
+                sentence = []
+                for a in tree.subtrees():
+                    if len(a) == 0:
+                        a.append(len(sentence))
+                        sentence.append(None)
+                    elif any(not isinstance(b, Tree) for b in a):
+                        for n, b in enumerate(a):
+                            if not isinstance(b, Tree):
+                                a[n] = len(sentence)
+                                if type(b) == tuple:
+                                    b = "/".join(b)
+                                sentence.append("%s" % b)
+        self.nodes, self.coords, self.edges, self.highlight = self.nodecoords(
+            tree, sentence, highlight
+        )
+
+    def __str__(self):
+        return self.text()
+
+    def __repr__(self):
+        return "<TreePrettyPrinter with %d nodes>" % len(self.nodes)
+
+    @staticmethod
+    def nodecoords(tree, sentence, highlight):
+        """
+        Produce coordinates of nodes on a grid.
+
+        Objective:
+
+        - Produce coordinates for a non-overlapping placement of nodes and
+            horizontal lines.
+        - Order edges so that crossing edges cross a minimal number of previous
+            horizontal lines (never vertical lines).
+
+        Approach:
+
+        - bottom up level order traversal (start at terminals)
+        - at each level, identify nodes which cannot be on the same row
+        - identify nodes which cannot be in the same column
+        - place nodes into a grid at (row, column)
+        - order child-parent edges with crossing edges last
+
+        Coordinates are (row, column); the origin (0, 0) is at the top left;
+        the root node is on row 0. Coordinates do not consider the size of a
+        node (which depends on font, &c), so the width of a column of the grid
+        should be automatically determined by the element with the greatest
+        width in that column. Alternatively, the integer coordinates could be
+        converted to coordinates in which the distances between adjacent nodes
+        are non-uniform.
+
+        Produces tuple (nodes, coords, edges, highlighted) where:
+
+        - nodes[id]: Tree object for the node with this integer id
+        - coords[id]: (n, m) coordinate where to draw node with id in the grid
+        - edges[id]: parent id of node with this id (ordered dictionary)
+        - highlighted: set of ids that should be highlighted
+        """
+
+        def findcell(m, matrix, startoflevel, children):
+            """
+            Find vacant row, column index for node ``m``.
+            Iterate over current rows for this level (try lowest first)
+            and look for cell between first and last child of this node,
+            add new row to level if no free row available.
+            """
+            candidates = [a for _, a in children[m]]
+            minidx, maxidx = min(candidates), max(candidates)
+            leaves = tree[m].leaves()
+            center = scale * sum(leaves) // len(leaves)  # center of gravity
+            if minidx < maxidx and not minidx < center < maxidx:
+                center = sum(candidates) // len(candidates)
+            if max(candidates) - min(candidates) > 2 * scale:
+                center -= center % scale  # round to unscaled coordinate
+                if minidx < maxidx and not minidx < center < maxidx:
+                    center += scale
+            if ids[m] == 0:
+                startoflevel = len(matrix)
+            for rowidx in range(startoflevel, len(matrix) + 1):
+                if rowidx == len(matrix):  # need to add a new row
+                    matrix.append(
+                        [
+                            vertline if a not in (corner, None) else None
+                            for a in matrix[-1]
+                        ]
+                    )
+                row = matrix[rowidx]
+                if len(children[m]) == 1:  # place unaries directly above child
+                    return rowidx, next(iter(children[m]))[1]
+                elif all(
+                    a is None or a == vertline
+                    for a in row[min(candidates) : max(candidates) + 1]
+                ):
+                    # find free column
+                    for n in range(scale):
+                        i = j = center + n
+                        while j > minidx or i < maxidx:
+                            if i < maxidx and (
+                                matrix[rowidx][i] is None or i in candidates
+                            ):
+                                return rowidx, i
+                            elif j > minidx and (
+                                matrix[rowidx][j] is None or j in candidates
+                            ):
+                                return rowidx, j
+                            i += scale
+                            j -= scale
+            raise ValueError(
+                "could not find a free cell for:\n%s\n%s"
+                "min=%d; max=%d" % (tree[m], minidx, maxidx, dumpmatrix())
+            )
+
+        def dumpmatrix():
+            """Dump matrix contents for debugging purposes."""
+            return "\n".join(
+                "%2d: %s" % (n, " ".join(("%2r" % i)[:2] for i in row))
+                for n, row in enumerate(matrix)
+            )
+
+        leaves = tree.leaves()
+        if not all(isinstance(n, int) for n in leaves):
+            raise ValueError("All leaves must be integer indices.")
+        if len(leaves) != len(set(leaves)):
+            raise ValueError("Indices must occur at most once.")
+        if not all(0 <= n < len(sentence) for n in leaves):
+            raise ValueError(
+                "All leaves must be in the interval 0..n "
+                "with n=len(sentence)\ntokens: %d indices: "
+                "%r\nsentence: %s" % (len(sentence), tree.leaves(), sentence)
+            )
+        vertline, corner = -1, -2  # constants
+        tree = tree.copy(True)
+        for a in tree.subtrees():
+            a.sort(key=lambda n: min(n.leaves()) if isinstance(n, Tree) else n)
+        scale = 2
+        crossed = set()
+        # internal nodes and lexical nodes (no frontiers)
+        positions = tree.treepositions()
+        maxdepth = max(map(len, positions)) + 1
+        childcols = defaultdict(set)
+        matrix = [[None] * (len(sentence) * scale)]
+        nodes = {}
+        ids = {a: n for n, a in enumerate(positions)}
+        highlighted_nodes = {
+            n for a, n in ids.items() if not highlight or tree[a] in highlight
+        }
+        levels = {n: [] for n in range(maxdepth - 1)}
+        terminals = []
+        for a in positions:
+            node = tree[a]
+            if isinstance(node, Tree):
+                levels[maxdepth - node.height()].append(a)
+            else:
+                terminals.append(a)
+
+        for n in levels:
+            levels[n].sort(key=lambda n: max(tree[n].leaves()) - min(tree[n].leaves()))
+        terminals.sort()
+        positions = set(positions)
+
+        for m in terminals:
+            i = int(tree[m]) * scale
+            assert matrix[0][i] is None, (matrix[0][i], m, i)
+            matrix[0][i] = ids[m]
+            nodes[ids[m]] = sentence[tree[m]]
+            if nodes[ids[m]] is None:
+                nodes[ids[m]] = "..."
+                highlighted_nodes.discard(ids[m])
+            positions.remove(m)
+            childcols[m[:-1]].add((0, i))
+
+        # add other nodes centered on their children,
+        # if the center is already taken, back off
+        # to the left and right alternately, until an empty cell is found.
+        for n in sorted(levels, reverse=True):
+            nodesatdepth = levels[n]
+            startoflevel = len(matrix)
+            matrix.append(
+                [vertline if a not in (corner, None) else None for a in matrix[-1]]
+            )
+            for m in nodesatdepth:  # [::-1]:
+                if n < maxdepth - 1 and childcols[m]:
+                    _, pivot = min(childcols[m], key=itemgetter(1))
+                    if {
+                        a[:-1]
+                        for row in matrix[:-1]
+                        for a in row[:pivot]
+                        if isinstance(a, tuple)
+                    } & {
+                        a[:-1]
+                        for row in matrix[:-1]
+                        for a in row[pivot:]
+                        if isinstance(a, tuple)
+                    }:
+                        crossed.add(m)
+
+                rowidx, i = findcell(m, matrix, startoflevel, childcols)
+                positions.remove(m)
+
+                # block positions where children of this node branch out
+                for _, x in childcols[m]:
+                    matrix[rowidx][x] = corner
+                # assert m == () or matrix[rowidx][i] in (None, corner), (
+                #         matrix[rowidx][i], m, str(tree), ' '.join(sentence))
+                # node itself
+                matrix[rowidx][i] = ids[m]
+                nodes[ids[m]] = tree[m]
+                # add column to the set of children for its parent
+                if len(m) > 0:
+                    childcols[m[:-1]].add((rowidx, i))
+        assert len(positions) == 0
+
+        # remove unused columns, right to left
+        for m in range(scale * len(sentence) - 1, -1, -1):
+            if not any(isinstance(row[m], (Tree, int)) for row in matrix):
+                for row in matrix:
+                    del row[m]
+
+        # remove unused rows, reverse
+        matrix = [
+            row
+            for row in reversed(matrix)
+            if not all(a is None or a == vertline for a in row)
+        ]
+
+        # collect coordinates of nodes
+        coords = {}
+        for n, _ in enumerate(matrix):
+            for m, i in enumerate(matrix[n]):
+                if isinstance(i, int) and i >= 0:
+                    coords[i] = n, m
+
+        # move crossed edges last
+        positions = sorted(
+            (a for level in levels.values() for a in level),
+            key=lambda a: a[:-1] in crossed,
+        )
+
+        # collect edges from node to node
+        edges = OrderedDict()
+        for i in reversed(positions):
+            for j, _ in enumerate(tree[i]):
+                edges[ids[i + (j,)]] = ids[i]
+
+        return nodes, coords, edges, highlighted_nodes
+
+    def text(
+        self,
+        nodedist=1,
+        unicodelines=False,
+        html=False,
+        ansi=False,
+        nodecolor="blue",
+        leafcolor="red",
+        funccolor="green",
+        abbreviate=None,
+        maxwidth=16,
+    ):
+        """
+        :return: ASCII art for a discontinuous tree.
+
+        :param unicodelines: whether to use Unicode line drawing characters
+            instead of plain (7-bit) ASCII.
+        :param html: whether to wrap output in html code (default plain text).
+        :param ansi: whether to produce colors with ANSI escape sequences
+            (only effective when html==False).
+        :param leafcolor, nodecolor: specify colors of leaves and phrasal
+            nodes; effective when either html or ansi is True.
+        :param abbreviate: if True, abbreviate labels longer than 5 characters.
+            If integer, abbreviate labels longer than `abbr` characters.
+        :param maxwidth: maximum number of characters before a label starts to
+            wrap; pass None to disable.
+        """
+        if abbreviate == True:
+            abbreviate = 5
+        if unicodelines:
+            horzline = "\u2500"
+            leftcorner = "\u250c"
+            rightcorner = "\u2510"
+            vertline = " \u2502 "
+            tee = horzline + "\u252C" + horzline
+            bottom = horzline + "\u2534" + horzline
+            cross = horzline + "\u253c" + horzline
+            ellipsis = "\u2026"
+        else:
+            horzline = "_"
+            leftcorner = rightcorner = " "
+            vertline = " | "
+            tee = 3 * horzline
+            cross = bottom = "_|_"
+            ellipsis = "."
+
+        def crosscell(cur, x=vertline):
+            """Overwrite center of this cell with a vertical branch."""
+            splitl = len(cur) - len(cur) // 2 - len(x) // 2 - 1
+            lst = list(cur)
+            lst[splitl : splitl + len(x)] = list(x)
+            return "".join(lst)
+
+        result = []
+        matrix = defaultdict(dict)
+        maxnodewith = defaultdict(lambda: 3)
+        maxnodeheight = defaultdict(lambda: 1)
+        maxcol = 0
+        minchildcol = {}
+        maxchildcol = {}
+        childcols = defaultdict(set)
+        labels = {}
+        wrapre = re.compile(
+            "(.{%d,%d}\\b\\W*|.{%d})" % (maxwidth - 4, maxwidth, maxwidth)
+        )
+        # collect labels and coordinates
+        for a in self.nodes:
+            row, column = self.coords[a]
+            matrix[row][column] = a
+            maxcol = max(maxcol, column)
+            label = (
+                self.nodes[a].label()
+                if isinstance(self.nodes[a], Tree)
+                else self.nodes[a]
+            )
+            if abbreviate and len(label) > abbreviate:
+                label = label[:abbreviate] + ellipsis
+            if maxwidth and len(label) > maxwidth:
+                label = wrapre.sub(r"\1\n", label).strip()
+            label = label.split("\n")
+            maxnodeheight[row] = max(maxnodeheight[row], len(label))
+            maxnodewith[column] = max(maxnodewith[column], max(map(len, label)))
+            labels[a] = label
+            if a not in self.edges:
+                continue  # e.g., root
+            parent = self.edges[a]
+            childcols[parent].add((row, column))
+            minchildcol[parent] = min(minchildcol.get(parent, column), column)
+            maxchildcol[parent] = max(maxchildcol.get(parent, column), column)
+        # bottom up level order traversal
+        for row in sorted(matrix, reverse=True):
+            noderows = [
+                ["".center(maxnodewith[col]) for col in range(maxcol + 1)]
+                for _ in range(maxnodeheight[row])
+            ]
+            branchrow = ["".center(maxnodewith[col]) for col in range(maxcol + 1)]
+            for col in matrix[row]:
+                n = matrix[row][col]
+                node = self.nodes[n]
+                text = labels[n]
+                if isinstance(node, Tree):
+                    # draw horizontal branch towards children for this node
+                    if n in minchildcol and minchildcol[n] < maxchildcol[n]:
+                        i, j = minchildcol[n], maxchildcol[n]
+                        a, b = (maxnodewith[i] + 1) // 2 - 1, maxnodewith[j] // 2
+                        branchrow[i] = ((" " * a) + leftcorner).ljust(
+                            maxnodewith[i], horzline
+                        )
+                        branchrow[j] = (rightcorner + (" " * b)).rjust(
+                            maxnodewith[j], horzline
+                        )
+                        for i in range(minchildcol[n] + 1, maxchildcol[n]):
+                            if i == col and any(a == i for _, a in childcols[n]):
+                                line = cross
+                            elif i == col:
+                                line = bottom
+                            elif any(a == i for _, a in childcols[n]):
+                                line = tee
+                            else:
+                                line = horzline
+                            branchrow[i] = line.center(maxnodewith[i], horzline)
+                    else:  # if n and n in minchildcol:
+                        branchrow[col] = crosscell(branchrow[col])
+                text = [a.center(maxnodewith[col]) for a in text]
+                color = nodecolor if isinstance(node, Tree) else leafcolor
+                if isinstance(node, Tree) and node.label().startswith("-"):
+                    color = funccolor
+                if html:
+                    text = [escape(a, quote=False) for a in text]
+                    if n in self.highlight:
+                        text = [f"<font color={color}>{a}</font>" for a in text]
+                elif ansi and n in self.highlight:
+                    text = ["\x1b[%d;1m%s\x1b[0m" % (ANSICOLOR[color], a) for a in text]
+                for x in range(maxnodeheight[row]):
+                    # draw vertical lines in partially filled multiline node
+                    # labels, but only if it's not a frontier node.
+                    noderows[x][col] = (
+                        text[x]
+                        if x < len(text)
+                        else (vertline if childcols[n] else " ").center(
+                            maxnodewith[col], " "
+                        )
+                    )
+            # for each column, if there is a node below us which has a parent
+            # above us, draw a vertical branch in that column.
+            if row != max(matrix):
+                for n, (childrow, col) in self.coords.items():
+                    if n > 0 and self.coords[self.edges[n]][0] < row < childrow:
+                        branchrow[col] = crosscell(branchrow[col])
+                        if col not in matrix[row]:
+                            for noderow in noderows:
+                                noderow[col] = crosscell(noderow[col])
+                branchrow = [
+                    a + ((a[-1] if a[-1] != " " else b[0]) * nodedist)
+                    for a, b in zip(branchrow, branchrow[1:] + [" "])
+                ]
+                result.append("".join(branchrow))
+            result.extend(
+                (" " * nodedist).join(noderow) for noderow in reversed(noderows)
+            )
+        return "\n".join(reversed(result)) + "\n"
+
+    def svg(self, nodecolor="blue", leafcolor="red", funccolor="green"):
+        """
+        :return: SVG representation of a tree.
+        """
+        fontsize = 12
+        hscale = 40
+        vscale = 25
+        hstart = vstart = 20
+        width = max(col for _, col in self.coords.values())
+        height = max(row for row, _ in self.coords.values())
+        result = [
+            '<svg version="1.1" xmlns="http://www.w3.org/2000/svg" '
+            'width="%dem" height="%dem" viewBox="%d %d %d %d">'
+            % (
+                width * 3,
+                height * 2.5,
+                -hstart,
+                -vstart,
+                width * hscale + 3 * hstart,
+                height * vscale + 3 * vstart,
+            )
+        ]
+
+        children = defaultdict(set)
+        for n in self.nodes:
+            if n:
+                children[self.edges[n]].add(n)
+
+        # horizontal branches from nodes to children
+        for node in self.nodes:
+            if not children[node]:
+                continue
+            y, x = self.coords[node]
+            x *= hscale
+            y *= vscale
+            x += hstart
+            y += vstart + fontsize // 2
+            childx = [self.coords[c][1] for c in children[node]]
+            xmin = hstart + hscale * min(childx)
+            xmax = hstart + hscale * max(childx)
+            result.append(
+                '\t<polyline style="stroke:black; stroke-width:1; fill:none;" '
+                'points="%g,%g %g,%g" />' % (xmin, y, xmax, y)
+            )
+            result.append(
+                '\t<polyline style="stroke:black; stroke-width:1; fill:none;" '
+                'points="%g,%g %g,%g" />' % (x, y, x, y - fontsize // 3)
+            )
+
+        # vertical branches from children to parents
+        for child, parent in self.edges.items():
+            y, _ = self.coords[parent]
+            y *= vscale
+            y += vstart + fontsize // 2
+            childy, childx = self.coords[child]
+            childx *= hscale
+            childy *= vscale
+            childx += hstart
+            childy += vstart - fontsize
+            result += [
+                '\t<polyline style="stroke:white; stroke-width:10; fill:none;"'
+                ' points="%g,%g %g,%g" />' % (childx, childy, childx, y + 5),
+                '\t<polyline style="stroke:black; stroke-width:1; fill:none;"'
+                ' points="%g,%g %g,%g" />' % (childx, childy, childx, y),
+            ]
+
+        # write nodes with coordinates
+        for n, (row, column) in self.coords.items():
+            node = self.nodes[n]
+            x = column * hscale + hstart
+            y = row * vscale + vstart
+            if n in self.highlight:
+                color = nodecolor if isinstance(node, Tree) else leafcolor
+                if isinstance(node, Tree) and node.label().startswith("-"):
+                    color = funccolor
+            else:
+                color = "black"
+            result += [
+                '\t<text style="text-anchor: middle; fill: %s; '
+                'font-size: %dpx;" x="%g" y="%g">%s</text>'
+                % (
+                    color,
+                    fontsize,
+                    x,
+                    y,
+                    escape(
+                        node.label() if isinstance(node, Tree) else node, quote=False
+                    ),
+                )
+            ]
+
+        result += ["</svg>"]
+        return "\n".join(result)
+
+
+def test():
+    """Do some tree drawing tests."""
+
+    def print_tree(n, tree, sentence=None, ansi=True, **xargs):
+        print()
+        print('{}: "{}"'.format(n, " ".join(sentence or tree.leaves())))
+        print(tree)
+        print()
+        drawtree = TreePrettyPrinter(tree, sentence)
+        try:
+            print(drawtree.text(unicodelines=ansi, ansi=ansi, **xargs))
+        except (UnicodeDecodeError, UnicodeEncodeError):
+            print(drawtree.text(unicodelines=False, ansi=False, **xargs))
+
+    from nltk.corpus import treebank
+
+    for n in [0, 1440, 1591, 2771, 2170]:
+        tree = treebank.parsed_sents()[n]
+        print_tree(n, tree, nodedist=2, maxwidth=8)
+    print()
+    print("ASCII version:")
+    print(TreePrettyPrinter(tree).text(nodedist=2))
+
+    tree = Tree.fromstring(
+        "(top (punct 8) (smain (noun 0) (verb 1) (inf (verb 5) (inf (verb 6) "
+        "(conj (inf (pp (prep 2) (np (det 3) (noun 4))) (verb 7)) (inf (verb 9)) "
+        "(vg 10) (inf (verb 11)))))) (punct 12))",
+        read_leaf=int,
+    )
+    sentence = (
+        "Ze had met haar moeder kunnen gaan winkelen ,"
+        " zwemmen of terrassen .".split()
+    )
+    print_tree("Discontinuous tree", tree, sentence, nodedist=2)
+
+
+__all__ = ["TreePrettyPrinter"]
+
+if __name__ == "__main__":
+    test()

backend/venv/Lib/site-packages/nltk/tree/probabilistic.py

@@ -0,0 +1,74 @@
+# Natural Language Toolkit: Text Trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Tom Aarsen <>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+
+from nltk.internals import raise_unorderable_types
+from nltk.probability import ProbabilisticMixIn
+from nltk.tree.immutable import ImmutableProbabilisticTree
+from nltk.tree.tree import Tree
+
+######################################################################
+## Probabilistic trees
+######################################################################
+
+
+class ProbabilisticTree(Tree, ProbabilisticMixIn):
+    def __init__(self, node, children=None, **prob_kwargs):
+        Tree.__init__(self, node, children)
+        ProbabilisticMixIn.__init__(self, **prob_kwargs)
+
+    # We have to patch up these methods to make them work right:
+    def _frozen_class(self):
+        return ImmutableProbabilisticTree
+
+    def __repr__(self):
+        return f"{Tree.__repr__(self)} (p={self.prob()!r})"
+
+    def __str__(self):
+        return f"{self.pformat(margin=60)} (p={self.prob():.6g})"
+
+    def copy(self, deep=False):
+        if not deep:
+            return type(self)(self._label, self, prob=self.prob())
+        else:
+            return type(self).convert(self)
+
+    @classmethod
+    def convert(cls, val):
+        if isinstance(val, Tree):
+            children = [cls.convert(child) for child in val]
+            if isinstance(val, ProbabilisticMixIn):
+                return cls(val._label, children, prob=val.prob())
+            else:
+                return cls(val._label, children, prob=1.0)
+        else:
+            return val
+
+    def __eq__(self, other):
+        return self.__class__ is other.__class__ and (
+            self._label,
+            list(self),
+            self.prob(),
+        ) == (other._label, list(other), other.prob())
+
+    def __lt__(self, other):
+        if not isinstance(other, Tree):
+            raise_unorderable_types("<", self, other)
+        if self.__class__ is other.__class__:
+            return (self._label, list(self), self.prob()) < (
+                other._label,
+                list(other),
+                other.prob(),
+            )
+        else:
+            return self.__class__.__name__ < other.__class__.__name__
+
+
+__all__ = ["ProbabilisticTree"]

backend/venv/Lib/site-packages/nltk/tree/transforms.py

@@ -0,0 +1,337 @@
+# Natural Language Toolkit: Tree Transformations
+#
+# Copyright (C) 2005-2007 Oregon Graduate Institute
+# Author: Nathan Bodenstab <bodenstab@cslu.ogi.edu>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+r"""
+A collection of methods for tree (grammar) transformations used
+in parsing natural language.
+
+Although many of these methods are technically grammar transformations
+(ie. Chomsky Norm Form), when working with treebanks it is much more
+natural to visualize these modifications in a tree structure.  Hence,
+we will do all transformation directly to the tree itself.
+Transforming the tree directly also allows us to do parent annotation.
+A grammar can then be simply induced from the modified tree.
+
+The following is a short tutorial on the available transformations.
+
+ 1. Chomsky Normal Form (binarization)
+
+    It is well known that any grammar has a Chomsky Normal Form (CNF)
+    equivalent grammar where CNF is defined by every production having
+    either two non-terminals or one terminal on its right hand side.
+    When we have hierarchically structured data (ie. a treebank), it is
+    natural to view this in terms of productions where the root of every
+    subtree is the head (left hand side) of the production and all of
+    its children are the right hand side constituents.  In order to
+    convert a tree into CNF, we simply need to ensure that every subtree
+    has either two subtrees as children (binarization), or one leaf node
+    (non-terminal).  In order to binarize a subtree with more than two
+    children, we must introduce artificial nodes.
+
+    There are two popular methods to convert a tree into CNF: left
+    factoring and right factoring.  The following example demonstrates
+    the difference between them.  Example::
+
+     Original       Right-Factored     Left-Factored
+
+          A              A                      A
+        / | \          /   \                  /   \
+       B  C  D   ==>  B    A|<C-D>   OR   A|<B-C>  D
+                            /  \          /  \
+                           C    D        B    C
+
+ 2. Parent Annotation
+
+    In addition to binarizing the tree, there are two standard
+    modifications to node labels we can do in the same traversal: parent
+    annotation and Markov order-N smoothing (or sibling smoothing).
+
+    The purpose of parent annotation is to refine the probabilities of
+    productions by adding a small amount of context.  With this simple
+    addition, a CYK (inside-outside, dynamic programming chart parse)
+    can improve from 74% to 79% accuracy.  A natural generalization from
+    parent annotation is to grandparent annotation and beyond.  The
+    tradeoff becomes accuracy gain vs. computational complexity.  We
+    must also keep in mind data sparcity issues.  Example::
+
+     Original       Parent Annotation
+
+          A                A^<?>
+        / | \             /   \
+       B  C  D   ==>  B^<A>    A|<C-D>^<?>     where ? is the
+                                 /  \          parent of A
+                             C^<A>   D^<A>
+
+
+ 3. Markov order-N smoothing
+
+    Markov smoothing combats data sparcity issues as well as decreasing
+    computational requirements by limiting the number of children
+    included in artificial nodes.  In practice, most people use an order
+    2 grammar.  Example::
+
+      Original       No Smoothing       Markov order 1   Markov order 2   etc.
+
+       __A__            A                      A                A
+      / /|\ \         /   \                  /   \            /   \
+     B C D E F  ==>  B    A|<C-D-E-F>  ==>  B   A|<C>  ==>   B  A|<C-D>
+                            /   \               /   \            /   \
+                           C    ...            C    ...         C    ...
+
+
+
+    Annotation decisions can be thought about in the vertical direction
+    (parent, grandparent, etc) and the horizontal direction (number of
+    siblings to keep).  Parameters to the following functions specify
+    these values.  For more information see:
+
+    Dan Klein and Chris Manning (2003) "Accurate Unlexicalized
+    Parsing", ACL-03.  https://www.aclweb.org/anthology/P03-1054
+
+ 4. Unary Collapsing
+
+    Collapse unary productions (ie. subtrees with a single child) into a
+    new non-terminal (Tree node).  This is useful when working with
+    algorithms that do not allow unary productions, yet you do not wish
+    to lose the parent information.  Example::
+
+       A
+       |
+       B   ==>   A+B
+      / \        / \
+     C   D      C   D
+
+"""
+
+from nltk.tree.tree import Tree
+
+
+def chomsky_normal_form(
+    tree, factor="right", horzMarkov=None, vertMarkov=0, childChar="|", parentChar="^"
+):
+    # assume all subtrees have homogeneous children
+    # assume all terminals have no siblings
+
+    # A semi-hack to have elegant looking code below.  As a result,
+    # any subtree with a branching factor greater than 999 will be incorrectly truncated.
+    if horzMarkov is None:
+        horzMarkov = 999
+
+    # Traverse the tree depth-first keeping a list of ancestor nodes to the root.
+    # I chose not to use the tree.treepositions() method since it requires
+    # two traversals of the tree (one to get the positions, one to iterate
+    # over them) and node access time is proportional to the height of the node.
+    # This method is 7x faster which helps when parsing 40,000 sentences.
+
+    nodeList = [(tree, [tree.label()])]
+    while nodeList != []:
+        node, parent = nodeList.pop()
+        if isinstance(node, Tree):
+            # parent annotation
+            parentString = ""
+            originalNode = node.label()
+            if vertMarkov != 0 and node != tree and isinstance(node[0], Tree):
+                parentString = "{}<{}>".format(parentChar, "-".join(parent))
+                node.set_label(node.label() + parentString)
+                parent = [originalNode] + parent[: vertMarkov - 1]
+
+            # add children to the agenda before we mess with them
+            for child in node:
+                nodeList.append((child, parent))
+
+            # chomsky normal form factorization
+            if len(node) > 2:
+                childNodes = [child.label() for child in node]
+                nodeCopy = node.copy()
+                node[0:] = []  # delete the children
+
+                curNode = node
+                numChildren = len(nodeCopy)
+                for i in range(1, numChildren - 1):
+                    if factor == "right":
+                        newHead = "{}{}<{}>{}".format(
+                            originalNode,
+                            childChar,
+                            "-".join(
+                                childNodes[i : min([i + horzMarkov, numChildren])]
+                            ),
+                            parentString,
+                        )  # create new head
+                        newNode = Tree(newHead, [])
+                        curNode[0:] = [nodeCopy.pop(0), newNode]
+                    else:
+                        newHead = "{}{}<{}>{}".format(
+                            originalNode,
+                            childChar,
+                            "-".join(
+                                childNodes[max([numChildren - i - horzMarkov, 0]) : -i]
+                            ),
+                            parentString,
+                        )
+                        newNode = Tree(newHead, [])
+                        curNode[0:] = [newNode, nodeCopy.pop()]
+
+                    curNode = newNode
+
+                curNode[0:] = [child for child in nodeCopy]
+
+
+def un_chomsky_normal_form(
+    tree, expandUnary=True, childChar="|", parentChar="^", unaryChar="+"
+):
+    # Traverse the tree-depth first keeping a pointer to the parent for modification purposes.
+    nodeList = [(tree, [])]
+    while nodeList != []:
+        node, parent = nodeList.pop()
+        if isinstance(node, Tree):
+            # if the node contains the 'childChar' character it means that
+            # it is an artificial node and can be removed, although we still need
+            # to move its children to its parent
+            childIndex = node.label().find(childChar)
+            if childIndex != -1:
+                nodeIndex = parent.index(node)
+                parent.remove(parent[nodeIndex])
+                # Generated node was on the left if the nodeIndex is 0 which
+                # means the grammar was left factored.  We must insert the children
+                # at the beginning of the parent's children
+                if nodeIndex == 0:
+                    parent.insert(0, node[0])
+                    parent.insert(1, node[1])
+                else:
+                    parent.extend([node[0], node[1]])
+
+                # parent is now the current node so the children of parent will be added to the agenda
+                node = parent
+            else:
+                parentIndex = node.label().find(parentChar)
+                if parentIndex != -1:
+                    # strip the node name of the parent annotation
+                    node.set_label(node.label()[:parentIndex])
+
+                # expand collapsed unary productions
+                if expandUnary == True:
+                    unaryIndex = node.label().find(unaryChar)
+                    if unaryIndex != -1:
+                        newNode = Tree(
+                            node.label()[unaryIndex + 1 :], [i for i in node]
+                        )
+                        node.set_label(node.label()[:unaryIndex])
+                        node[0:] = [newNode]
+
+            for child in node:
+                nodeList.append((child, node))
+
+
+def collapse_unary(tree, collapsePOS=False, collapseRoot=False, joinChar="+"):
+    """
+    Collapse subtrees with a single child (ie. unary productions)
+    into a new non-terminal (Tree node) joined by 'joinChar'.
+    This is useful when working with algorithms that do not allow
+    unary productions, and completely removing the unary productions
+    would require loss of useful information.  The Tree is modified
+    directly (since it is passed by reference) and no value is returned.
+
+    :param tree: The Tree to be collapsed
+    :type  tree: Tree
+    :param collapsePOS: 'False' (default) will not collapse the parent of leaf nodes (ie.
+                        Part-of-Speech tags) since they are always unary productions
+    :type  collapsePOS: bool
+    :param collapseRoot: 'False' (default) will not modify the root production
+                         if it is unary.  For the Penn WSJ treebank corpus, this corresponds
+                         to the TOP -> productions.
+    :type collapseRoot: bool
+    :param joinChar: A string used to connect collapsed node values (default = "+")
+    :type  joinChar: str
+    """
+
+    if collapseRoot == False and isinstance(tree, Tree) and len(tree) == 1:
+        nodeList = [tree[0]]
+    else:
+        nodeList = [tree]
+
+    # depth-first traversal of tree
+    while nodeList != []:
+        node = nodeList.pop()
+        if isinstance(node, Tree):
+            if (
+                len(node) == 1
+                and isinstance(node[0], Tree)
+                and (collapsePOS == True or isinstance(node[0, 0], Tree))
+            ):
+                node.set_label(node.label() + joinChar + node[0].label())
+                node[0:] = [child for child in node[0]]
+                # since we assigned the child's children to the current node,
+                # evaluate the current node again
+                nodeList.append(node)
+            else:
+                for child in node:
+                    nodeList.append(child)
+
+
+#################################################################
+# Demonstration
+#################################################################
+
+
+def demo():
+    """
+    A demonstration showing how each tree transform can be used.
+    """
+
+    from copy import deepcopy
+
+    from nltk.draw.tree import draw_trees
+    from nltk.tree.tree import Tree
+
+    # original tree from WSJ bracketed text
+    sentence = """(TOP
+  (S
+    (S
+      (VP
+        (VBN Turned)
+        (ADVP (RB loose))
+        (PP
+          (IN in)
+          (NP
+            (NP (NNP Shane) (NNP Longman) (POS 's))
+            (NN trading)
+            (NN room)))))
+    (, ,)
+    (NP (DT the) (NN yuppie) (NNS dealers))
+    (VP (AUX do) (NP (NP (RB little)) (ADJP (RB right))))
+    (. .)))"""
+    t = Tree.fromstring(sentence, remove_empty_top_bracketing=True)
+
+    # collapse subtrees with only one child
+    collapsedTree = deepcopy(t)
+    collapse_unary(collapsedTree)
+
+    # convert the tree to CNF
+    cnfTree = deepcopy(collapsedTree)
+    chomsky_normal_form(cnfTree)
+
+    # convert the tree to CNF with parent annotation (one level) and horizontal smoothing of order two
+    parentTree = deepcopy(collapsedTree)
+    chomsky_normal_form(parentTree, horzMarkov=2, vertMarkov=1)
+
+    # convert the tree back to its original form (used to make CYK results comparable)
+    original = deepcopy(parentTree)
+    un_chomsky_normal_form(original)
+
+    # convert tree back to bracketed text
+    sentence2 = original.pprint()
+    print(sentence)
+    print(sentence2)
+    print("Sentences the same? ", sentence == sentence2)
+
+    draw_trees(t, collapsedTree, cnfTree, parentTree, original)
+
+
+if __name__ == "__main__":
+    demo()
+
+__all__ = ["chomsky_normal_form", "un_chomsky_normal_form", "collapse_unary"]

backend/venv/Lib/site-packages/nltk/tree/tree.py

@@ -0,0 +1,982 @@
+# Natural Language Toolkit: Text Trees
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+#         Peter Ljunglöf <peter.ljunglof@gu.se>
+#         Nathan Bodenstab <bodenstab@cslu.ogi.edu> (tree transforms)
+#         Eric Kafe <kafe.eric@gmail.com> (Tree.fromlist())
+#         Mohaned mashaly<mohaned.mashaly12@gmail.com> (Deprecating methods)
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+Class for representing hierarchical language structures, such as
+syntax trees and morphological trees.
+"""
+
+import re
+
+from nltk.grammar import Nonterminal, Production
+from nltk.internals import deprecated
+
+######################################################################
+## Trees
+######################################################################
+
+
+class Tree(list):
+    r"""
+    A Tree represents a hierarchical grouping of leaves and subtrees.
+    For example, each constituent in a syntax tree is represented by a single Tree.
+
+    A tree's children are encoded as a list of leaves and subtrees,
+    where a leaf is a basic (non-tree) value; and a subtree is a
+    nested Tree.
+
+        >>> from nltk.tree import Tree
+        >>> print(Tree(1, [2, Tree(3, [4]), 5]))
+        (1 2 (3 4) 5)
+        >>> vp = Tree('VP', [Tree('V', ['saw']),
+        ...                  Tree('NP', ['him'])])
+        >>> s = Tree('S', [Tree('NP', ['I']), vp])
+        >>> print(s)
+        (S (NP I) (VP (V saw) (NP him)))
+        >>> print(s[1])
+        (VP (V saw) (NP him))
+        >>> print(s[1,1])
+        (NP him)
+        >>> t = Tree.fromstring("(S (NP I) (VP (V saw) (NP him)))")
+        >>> s == t
+        True
+        >>> t[1][1].set_label('X')
+        >>> t[1][1].label()
+        'X'
+        >>> print(t)
+        (S (NP I) (VP (V saw) (X him)))
+        >>> t[0], t[1,1] = t[1,1], t[0]
+        >>> print(t)
+        (S (X him) (VP (V saw) (NP I)))
+
+    The length of a tree is the number of children it has.
+
+        >>> len(t)
+        2
+
+    The set_label() and label() methods allow individual constituents
+    to be labeled.  For example, syntax trees use this label to specify
+    phrase tags, such as "NP" and "VP".
+
+    Several Tree methods use "tree positions" to specify
+    children or descendants of a tree.  Tree positions are defined as
+    follows:
+
+      - The tree position *i* specifies a Tree's *i*\ th child.
+      - The tree position ``()`` specifies the Tree itself.
+      - If *p* is the tree position of descendant *d*, then
+        *p+i* specifies the *i*\ th child of *d*.
+
+    I.e., every tree position is either a single index *i*,
+    specifying ``tree[i]``; or a sequence *i1, i2, ..., iN*,
+    specifying ``tree[i1][i2]...[iN]``.
+
+    Construct a new tree.  This constructor can be called in one
+    of two ways:
+
+    - ``Tree(label, children)`` constructs a new tree with the
+        specified label and list of children.
+
+    - ``Tree.fromstring(s)`` constructs a new tree by parsing the string ``s``.
+    """
+
+    def __init__(self, node, children=None):
+        if children is None:
+            raise TypeError(
+                "%s: Expected a node value and child list " % type(self).__name__
+            )
+        elif isinstance(children, str):
+            raise TypeError(
+                "%s() argument 2 should be a list, not a "
+                "string" % type(self).__name__
+            )
+        else:
+            list.__init__(self, children)
+            self._label = node
+
+    # ////////////////////////////////////////////////////////////
+    # Comparison operators
+    # ////////////////////////////////////////////////////////////
+
+    def __eq__(self, other):
+        return self.__class__ is other.__class__ and (self._label, list(self)) == (
+            other._label,
+            list(other),
+        )
+
+    def __lt__(self, other):
+        if not isinstance(other, Tree):
+            # raise_unorderable_types("<", self, other)
+            # Sometimes children can be pure strings,
+            # so we need to be able to compare with non-trees:
+            return self.__class__.__name__ < other.__class__.__name__
+        elif self.__class__ is other.__class__:
+            return (self._label, list(self)) < (other._label, list(other))
+        else:
+            return self.__class__.__name__ < other.__class__.__name__
+
+    # @total_ordering doesn't work here, since the class inherits from a builtin class
+    __ne__ = lambda self, other: not self == other
+    __gt__ = lambda self, other: not (self < other or self == other)
+    __le__ = lambda self, other: self < other or self == other
+    __ge__ = lambda self, other: not self < other
+
+    # ////////////////////////////////////////////////////////////
+    # Disabled list operations
+    # ////////////////////////////////////////////////////////////
+
+    def __mul__(self, v):
+        raise TypeError("Tree does not support multiplication")
+
+    def __rmul__(self, v):
+        raise TypeError("Tree does not support multiplication")
+
+    def __add__(self, v):
+        raise TypeError("Tree does not support addition")
+
+    def __radd__(self, v):
+        raise TypeError("Tree does not support addition")
+
+    # ////////////////////////////////////////////////////////////
+    # Indexing (with support for tree positions)
+    # ////////////////////////////////////////////////////////////
+
+    def __getitem__(self, index):
+        if isinstance(index, (int, slice)):
+            return list.__getitem__(self, index)
+        elif isinstance(index, (list, tuple)):
+            if len(index) == 0:
+                return self
+            elif len(index) == 1:
+                return self[index[0]]
+            else:
+                return self[index[0]][index[1:]]
+        else:
+            raise TypeError(
+                "%s indices must be integers, not %s"
+                % (type(self).__name__, type(index).__name__)
+            )
+
+    def __setitem__(self, index, value):
+        if isinstance(index, (int, slice)):
+            return list.__setitem__(self, index, value)
+        elif isinstance(index, (list, tuple)):
+            if len(index) == 0:
+                raise IndexError("The tree position () may not be " "assigned to.")
+            elif len(index) == 1:
+                self[index[0]] = value
+            else:
+                self[index[0]][index[1:]] = value
+        else:
+            raise TypeError(
+                "%s indices must be integers, not %s"
+                % (type(self).__name__, type(index).__name__)
+            )
+
+    def __delitem__(self, index):
+        if isinstance(index, (int, slice)):
+            return list.__delitem__(self, index)
+        elif isinstance(index, (list, tuple)):
+            if len(index) == 0:
+                raise IndexError("The tree position () may not be deleted.")
+            elif len(index) == 1:
+                del self[index[0]]
+            else:
+                del self[index[0]][index[1:]]
+        else:
+            raise TypeError(
+                "%s indices must be integers, not %s"
+                % (type(self).__name__, type(index).__name__)
+            )
+
+    # ////////////////////////////////////////////////////////////
+    # Basic tree operations
+    # ////////////////////////////////////////////////////////////
+    @deprecated("Use label() instead")
+    def _get_node(self):
+        """Outdated method to access the node value; use the label() method instead."""
+
+    @deprecated("Use set_label() instead")
+    def _set_node(self, value):
+        """Outdated method to set the node value; use the set_label() method instead."""
+
+    node = property(_get_node, _set_node)
+
+    def label(self):
+        """
+        Return the node label of the tree.
+
+            >>> t = Tree.fromstring('(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))')
+            >>> t.label()
+            'S'
+
+        :return: the node label (typically a string)
+        :rtype: any
+        """
+        return self._label
+
+    def set_label(self, label):
+        """
+        Set the node label of the tree.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.set_label("T")
+            >>> print(t)
+            (T (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))
+
+        :param label: the node label (typically a string)
+        :type label: any
+        """
+        self._label = label
+
+    def leaves(self):
+        """
+        Return the leaves of the tree.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.leaves()
+            ['the', 'dog', 'chased', 'the', 'cat']
+
+        :return: a list containing this tree's leaves.
+            The order reflects the order of the
+            leaves in the tree's hierarchical structure.
+        :rtype: list
+        """
+        leaves = []
+        for child in self:
+            if isinstance(child, Tree):
+                leaves.extend(child.leaves())
+            else:
+                leaves.append(child)
+        return leaves
+
+    def flatten(self):
+        """
+        Return a flat version of the tree, with all non-root non-terminals removed.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> print(t.flatten())
+            (S the dog chased the cat)
+
+        :return: a tree consisting of this tree's root connected directly to
+            its leaves, omitting all intervening non-terminal nodes.
+        :rtype: Tree
+        """
+        return Tree(self.label(), self.leaves())
+
+    def height(self):
+        """
+        Return the height of the tree.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.height()
+            5
+            >>> print(t[0,0])
+            (D the)
+            >>> t[0,0].height()
+            2
+
+        :return: The height of this tree.  The height of a tree
+            containing no children is 1; the height of a tree
+            containing only leaves is 2; and the height of any other
+            tree is one plus the maximum of its children's
+            heights.
+        :rtype: int
+        """
+        max_child_height = 0
+        for child in self:
+            if isinstance(child, Tree):
+                max_child_height = max(max_child_height, child.height())
+            else:
+                max_child_height = max(max_child_height, 1)
+        return 1 + max_child_height
+
+    def treepositions(self, order="preorder"):
+        """
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.treepositions() # doctest: +ELLIPSIS
+            [(), (0,), (0, 0), (0, 0, 0), (0, 1), (0, 1, 0), (1,), (1, 0), (1, 0, 0), ...]
+            >>> for pos in t.treepositions('leaves'):
+            ...     t[pos] = t[pos][::-1].upper()
+            >>> print(t)
+            (S (NP (D EHT) (N GOD)) (VP (V DESAHC) (NP (D EHT) (N TAC))))
+
+        :param order: One of: ``preorder``, ``postorder``, ``bothorder``,
+            ``leaves``.
+        """
+        positions = []
+        if order in ("preorder", "bothorder"):
+            positions.append(())
+        for i, child in enumerate(self):
+            if isinstance(child, Tree):
+                childpos = child.treepositions(order)
+                positions.extend((i,) + p for p in childpos)
+            else:
+                positions.append((i,))
+        if order in ("postorder", "bothorder"):
+            positions.append(())
+        return positions
+
+    def subtrees(self, filter=None):
+        """
+        Generate all the subtrees of this tree, optionally restricted
+        to trees matching the filter function.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> for s in t.subtrees(lambda t: t.height() == 2):
+            ...     print(s)
+            (D the)
+            (N dog)
+            (V chased)
+            (D the)
+            (N cat)
+
+        :type filter: function
+        :param filter: the function to filter all local trees
+        """
+        if not filter or filter(self):
+            yield self
+        for child in self:
+            if isinstance(child, Tree):
+                yield from child.subtrees(filter)
+
+    def productions(self):
+        """
+        Generate the productions that correspond to the non-terminal nodes of the tree.
+        For each subtree of the form (P: C1 C2 ... Cn) this produces a production of the
+        form P -> C1 C2 ... Cn.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.productions() # doctest: +NORMALIZE_WHITESPACE
+            [S -> NP VP, NP -> D N, D -> 'the', N -> 'dog', VP -> V NP, V -> 'chased',
+            NP -> D N, D -> 'the', N -> 'cat']
+
+        :rtype: list(Production)
+        """
+
+        if not isinstance(self._label, str):
+            raise TypeError(
+                "Productions can only be generated from trees having node labels that are strings"
+            )
+
+        prods = [Production(Nonterminal(self._label), _child_names(self))]
+        for child in self:
+            if isinstance(child, Tree):
+                prods += child.productions()
+        return prods
+
+    def pos(self):
+        """
+        Return a sequence of pos-tagged words extracted from the tree.
+
+            >>> t = Tree.fromstring("(S (NP (D the) (N dog)) (VP (V chased) (NP (D the) (N cat))))")
+            >>> t.pos()
+            [('the', 'D'), ('dog', 'N'), ('chased', 'V'), ('the', 'D'), ('cat', 'N')]
+
+        :return: a list of tuples containing leaves and pre-terminals (part-of-speech tags).
+            The order reflects the order of the leaves in the tree's hierarchical structure.
+        :rtype: list(tuple)
+        """
+        pos = []
+        for child in self:
+            if isinstance(child, Tree):
+                pos.extend(child.pos())
+            else:
+                pos.append((child, self._label))
+        return pos
+
+    def leaf_treeposition(self, index):
+        """
+        :return: The tree position of the ``index``-th leaf in this
+            tree.  I.e., if ``tp=self.leaf_treeposition(i)``, then
+            ``self[tp]==self.leaves()[i]``.
+
+        :raise IndexError: If this tree contains fewer than ``index+1``
+            leaves, or if ``index<0``.
+        """
+        if index < 0:
+            raise IndexError("index must be non-negative")
+
+        stack = [(self, ())]
+        while stack:
+            value, treepos = stack.pop()
+            if not isinstance(value, Tree):
+                if index == 0:
+                    return treepos
+                else:
+                    index -= 1
+            else:
+                for i in range(len(value) - 1, -1, -1):
+                    stack.append((value[i], treepos + (i,)))
+
+        raise IndexError("index must be less than or equal to len(self)")
+
+    def treeposition_spanning_leaves(self, start, end):
+        """
+        :return: The tree position of the lowest descendant of this
+            tree that dominates ``self.leaves()[start:end]``.
+        :raise ValueError: if ``end <= start``
+        """
+        if end <= start:
+            raise ValueError("end must be greater than start")
+        # Find the tree positions of the start & end leaves, and
+        # take the longest common subsequence.
+        start_treepos = self.leaf_treeposition(start)
+        end_treepos = self.leaf_treeposition(end - 1)
+        # Find the first index where they mismatch:
+        for i in range(len(start_treepos)):
+            if i == len(end_treepos) or start_treepos[i] != end_treepos[i]:
+                return start_treepos[:i]
+        return start_treepos
+
+    # ////////////////////////////////////////////////////////////
+    # Transforms
+    # ////////////////////////////////////////////////////////////
+
+    def chomsky_normal_form(
+        self,
+        factor="right",
+        horzMarkov=None,
+        vertMarkov=0,
+        childChar="|",
+        parentChar="^",
+    ):
+        """
+        This method can modify a tree in three ways:
+
+          1. Convert a tree into its Chomsky Normal Form (CNF)
+             equivalent -- Every subtree has either two non-terminals
+             or one terminal as its children.  This process requires
+             the creation of more"artificial" non-terminal nodes.
+          2. Markov (vertical) smoothing of children in new artificial
+             nodes
+          3. Horizontal (parent) annotation of nodes
+
+        :param factor: Right or left factoring method (default = "right")
+        :type  factor: str = [left|right]
+        :param horzMarkov: Markov order for sibling smoothing in artificial nodes (None (default) = include all siblings)
+        :type  horzMarkov: int | None
+        :param vertMarkov: Markov order for parent smoothing (0 (default) = no vertical annotation)
+        :type  vertMarkov: int | None
+        :param childChar: A string used in construction of the artificial nodes, separating the head of the
+                          original subtree from the child nodes that have yet to be expanded (default = "|")
+        :type  childChar: str
+        :param parentChar: A string used to separate the node representation from its vertical annotation
+        :type  parentChar: str
+        """
+        from nltk.tree.transforms import chomsky_normal_form
+
+        chomsky_normal_form(self, factor, horzMarkov, vertMarkov, childChar, parentChar)
+
+    def un_chomsky_normal_form(
+        self, expandUnary=True, childChar="|", parentChar="^", unaryChar="+"
+    ):
+        """
+        This method modifies the tree in three ways:
+
+          1. Transforms a tree in Chomsky Normal Form back to its
+             original structure (branching greater than two)
+          2. Removes any parent annotation (if it exists)
+          3. (optional) expands unary subtrees (if previously
+             collapsed with collapseUnary(...) )
+
+        :param expandUnary: Flag to expand unary or not (default = True)
+        :type  expandUnary: bool
+        :param childChar: A string separating the head node from its children in an artificial node (default = "|")
+        :type  childChar: str
+        :param parentChar: A string separating the node label from its parent annotation (default = "^")
+        :type  parentChar: str
+        :param unaryChar: A string joining two non-terminals in a unary production (default = "+")
+        :type  unaryChar: str
+        """
+        from nltk.tree.transforms import un_chomsky_normal_form
+
+        un_chomsky_normal_form(self, expandUnary, childChar, parentChar, unaryChar)
+
+    def collapse_unary(self, collapsePOS=False, collapseRoot=False, joinChar="+"):
+        """
+        Collapse subtrees with a single child (ie. unary productions)
+        into a new non-terminal (Tree node) joined by 'joinChar'.
+        This is useful when working with algorithms that do not allow
+        unary productions, and completely removing the unary productions
+        would require loss of useful information.  The Tree is modified
+        directly (since it is passed by reference) and no value is returned.
+
+        :param collapsePOS: 'False' (default) will not collapse the parent of leaf nodes (ie.
+                            Part-of-Speech tags) since they are always unary productions
+        :type  collapsePOS: bool
+        :param collapseRoot: 'False' (default) will not modify the root production
+                             if it is unary.  For the Penn WSJ treebank corpus, this corresponds
+                             to the TOP -> productions.
+        :type collapseRoot: bool
+        :param joinChar: A string used to connect collapsed node values (default = "+")
+        :type  joinChar: str
+        """
+        from nltk.tree.transforms import collapse_unary
+
+        collapse_unary(self, collapsePOS, collapseRoot, joinChar)
+
+    # ////////////////////////////////////////////////////////////
+    # Convert, copy
+    # ////////////////////////////////////////////////////////////
+
+    @classmethod
+    def convert(cls, tree):
+        """
+        Convert a tree between different subtypes of Tree.  ``cls`` determines
+        which class will be used to encode the new tree.
+
+        :type tree: Tree
+        :param tree: The tree that should be converted.
+        :return: The new Tree.
+        """
+        if isinstance(tree, Tree):
+            children = [cls.convert(child) for child in tree]
+            return cls(tree._label, children)
+        else:
+            return tree
+
+    def __copy__(self):
+        return self.copy()
+
+    def __deepcopy__(self, memo):
+        return self.copy(deep=True)
+
+    def copy(self, deep=False):
+        if not deep:
+            return type(self)(self._label, self)
+        else:
+            return type(self).convert(self)
+
+    def _frozen_class(self):
+        from nltk.tree.immutable import ImmutableTree
+
+        return ImmutableTree
+
+    def freeze(self, leaf_freezer=None):
+        frozen_class = self._frozen_class()
+        if leaf_freezer is None:
+            newcopy = frozen_class.convert(self)
+        else:
+            newcopy = self.copy(deep=True)
+            for pos in newcopy.treepositions("leaves"):
+                newcopy[pos] = leaf_freezer(newcopy[pos])
+            newcopy = frozen_class.convert(newcopy)
+        hash(newcopy)  # Make sure the leaves are hashable.
+        return newcopy
+
+    # ////////////////////////////////////////////////////////////
+    # Parsing
+    # ////////////////////////////////////////////////////////////
+
+    @classmethod
+    def fromstring(
+        cls,
+        s,
+        brackets="()",
+        read_node=None,
+        read_leaf=None,
+        node_pattern=None,
+        leaf_pattern=None,
+        remove_empty_top_bracketing=False,
+    ):
+        """
+        Read a bracketed tree string and return the resulting tree.
+        Trees are represented as nested brackettings, such as::
+
+          (S (NP (NNP John)) (VP (V runs)))
+
+        :type s: str
+        :param s: The string to read
+
+        :type brackets: str (length=2)
+        :param brackets: The bracket characters used to mark the
+            beginning and end of trees and subtrees.
+
+        :type read_node: function
+        :type read_leaf: function
+        :param read_node, read_leaf: If specified, these functions
+            are applied to the substrings of ``s`` corresponding to
+            nodes and leaves (respectively) to obtain the values for
+            those nodes and leaves.  They should have the following
+            signature:
+
+               read_node(str) -> value
+
+            For example, these functions could be used to process nodes
+            and leaves whose values should be some type other than
+            string (such as ``FeatStruct``).
+            Note that by default, node strings and leaf strings are
+            delimited by whitespace and brackets; to override this
+            default, use the ``node_pattern`` and ``leaf_pattern``
+            arguments.
+
+        :type node_pattern: str
+        :type leaf_pattern: str
+        :param node_pattern, leaf_pattern: Regular expression patterns
+            used to find node and leaf substrings in ``s``.  By
+            default, both nodes patterns are defined to match any
+            sequence of non-whitespace non-bracket characters.
+
+        :type remove_empty_top_bracketing: bool
+        :param remove_empty_top_bracketing: If the resulting tree has
+            an empty node label, and is length one, then return its
+            single child instead.  This is useful for treebank trees,
+            which sometimes contain an extra level of bracketing.
+
+        :return: A tree corresponding to the string representation ``s``.
+            If this class method is called using a subclass of Tree,
+            then it will return a tree of that type.
+        :rtype: Tree
+        """
+        if not isinstance(brackets, str) or len(brackets) != 2:
+            raise TypeError("brackets must be a length-2 string")
+        if re.search(r"\s", brackets):
+            raise TypeError("whitespace brackets not allowed")
+        # Construct a regexp that will tokenize the string.
+        open_b, close_b = brackets
+        open_pattern, close_pattern = (re.escape(open_b), re.escape(close_b))
+        if node_pattern is None:
+            node_pattern = rf"[^\s{open_pattern}{close_pattern}]+"
+        if leaf_pattern is None:
+            leaf_pattern = rf"[^\s{open_pattern}{close_pattern}]+"
+        token_re = re.compile(
+            r"%s\s*(%s)?|%s|(%s)"
+            % (open_pattern, node_pattern, close_pattern, leaf_pattern)
+        )
+        # Walk through each token, updating a stack of trees.
+        stack = [(None, [])]  # list of (node, children) tuples
+        for match in token_re.finditer(s):
+            token = match.group()
+            # Beginning of a tree/subtree
+            if token[0] == open_b:
+                if len(stack) == 1 and len(stack[0][1]) > 0:
+                    cls._parse_error(s, match, "end-of-string")
+                label = token[1:].lstrip()
+                if read_node is not None:
+                    label = read_node(label)
+                stack.append((label, []))
+            # End of a tree/subtree
+            elif token == close_b:
+                if len(stack) == 1:
+                    if len(stack[0][1]) == 0:
+                        cls._parse_error(s, match, open_b)
+                    else:
+                        cls._parse_error(s, match, "end-of-string")
+                label, children = stack.pop()
+                stack[-1][1].append(cls(label, children))
+            # Leaf node
+            else:
+                if len(stack) == 1:
+                    cls._parse_error(s, match, open_b)
+                if read_leaf is not None:
+                    token = read_leaf(token)
+                stack[-1][1].append(token)
+
+        # check that we got exactly one complete tree.
+        if len(stack) > 1:
+            cls._parse_error(s, "end-of-string", close_b)
+        elif len(stack[0][1]) == 0:
+            cls._parse_error(s, "end-of-string", open_b)
+        else:
+            assert stack[0][0] is None
+            assert len(stack[0][1]) == 1
+        tree = stack[0][1][0]
+
+        # If the tree has an extra level with node='', then get rid of
+        # it.  E.g.: "((S (NP ...) (VP ...)))"
+        if remove_empty_top_bracketing and tree._label == "" and len(tree) == 1:
+            tree = tree[0]
+        # return the tree.
+        return tree
+
+    @classmethod
+    def _parse_error(cls, s, match, expecting):
+        """
+        Display a friendly error message when parsing a tree string fails.
+        :param s: The string we're parsing.
+        :param match: regexp match of the problem token.
+        :param expecting: what we expected to see instead.
+        """
+        # Construct a basic error message
+        if match == "end-of-string":
+            pos, token = len(s), "end-of-string"
+        else:
+            pos, token = match.start(), match.group()
+        msg = "%s.read(): expected %r but got %r\n%sat index %d." % (
+            cls.__name__,
+            expecting,
+            token,
+            " " * 12,
+            pos,
+        )
+        # Add a display showing the error token itsels:
+        s = s.replace("\n", " ").replace("\t", " ")
+        offset = pos
+        if len(s) > pos + 10:
+            s = s[: pos + 10] + "..."
+        if pos > 10:
+            s = "..." + s[pos - 10 :]
+            offset = 13
+        msg += '\n{}"{}"\n{}^'.format(" " * 16, s, " " * (17 + offset))
+        raise ValueError(msg)
+
+    @classmethod
+    def fromlist(cls, l):
+        """
+        :type l: list
+        :param l: a tree represented as nested lists
+
+        :return: A tree corresponding to the list representation ``l``.
+        :rtype: Tree
+
+        Convert nested lists to a NLTK Tree
+        """
+        if type(l) == list and len(l) > 0:
+            label = repr(l[0])
+            if len(l) > 1:
+                return Tree(label, [cls.fromlist(child) for child in l[1:]])
+            else:
+                return label
+
+    # ////////////////////////////////////////////////////////////
+    # Visualization & String Representation
+    # ////////////////////////////////////////////////////////////
+
+    def draw(self):
+        """
+        Open a new window containing a graphical diagram of this tree.
+        """
+        from nltk.draw.tree import draw_trees
+
+        draw_trees(self)
+
+    def pretty_print(self, sentence=None, highlight=(), stream=None, **kwargs):
+        """
+        Pretty-print this tree as ASCII or Unicode art.
+        For explanation of the arguments, see the documentation for
+        `nltk.tree.prettyprinter.TreePrettyPrinter`.
+        """
+        from nltk.tree.prettyprinter import TreePrettyPrinter
+
+        print(TreePrettyPrinter(self, sentence, highlight).text(**kwargs), file=stream)
+
+    def __repr__(self):
+        childstr = ", ".join(repr(c) for c in self)
+        return "{}({}, [{}])".format(
+            type(self).__name__,
+            repr(self._label),
+            childstr,
+        )
+
+    def _repr_svg_(self):
+        from svgling import draw_tree
+
+        return draw_tree(self)._repr_svg_()
+
+    def __str__(self):
+        return self.pformat()
+
+    def pprint(self, **kwargs):
+        """
+        Print a string representation of this Tree to 'stream'
+        """
+
+        if "stream" in kwargs:
+            stream = kwargs["stream"]
+            del kwargs["stream"]
+        else:
+            stream = None
+        print(self.pformat(**kwargs), file=stream)
+
+    def pformat(self, margin=70, indent=0, nodesep="", parens="()", quotes=False):
+        """
+        :return: A pretty-printed string representation of this tree.
+        :rtype: str
+        :param margin: The right margin at which to do line-wrapping.
+        :type margin: int
+        :param indent: The indentation level at which printing
+            begins.  This number is used to decide how far to indent
+            subsequent lines.
+        :type indent: int
+        :param nodesep: A string that is used to separate the node
+            from the children.  E.g., the default value ``':'`` gives
+            trees like ``(S: (NP: I) (VP: (V: saw) (NP: it)))``.
+        """
+
+        # Try writing it on one line.
+        s = self._pformat_flat(nodesep, parens, quotes)
+        if len(s) + indent < margin:
+            return s
+
+        # If it doesn't fit on one line, then write it on multi-lines.
+        if isinstance(self._label, str):
+            s = f"{parens[0]}{self._label}{nodesep}"
+        else:
+            s = f"{parens[0]}{repr(self._label)}{nodesep}"
+        for child in self:
+            if isinstance(child, Tree):
+                s += (
+                    "\n"
+                    + " " * (indent + 2)
+                    + child.pformat(margin, indent + 2, nodesep, parens, quotes)
+                )
+            elif isinstance(child, tuple):
+                s += "\n" + " " * (indent + 2) + "/".join(child)
+            elif isinstance(child, str) and not quotes:
+                s += "\n" + " " * (indent + 2) + "%s" % child
+            else:
+                s += "\n" + " " * (indent + 2) + repr(child)
+        return s + parens[1]
+
+    def pformat_latex_qtree(self):
+        r"""
+        Returns a representation of the tree compatible with the
+        LaTeX qtree package. This consists of the string ``\Tree``
+        followed by the tree represented in bracketed notation.
+
+        For example, the following result was generated from a parse tree of
+        the sentence ``The announcement astounded us``::
+
+          \Tree [.I'' [.N'' [.D The ] [.N' [.N announcement ] ] ]
+              [.I' [.V'' [.V' [.V astounded ] [.N'' [.N' [.N us ] ] ] ] ] ] ]
+
+        See https://www.ling.upenn.edu/advice/latex.html for the LaTeX
+        style file for the qtree package.
+
+        :return: A latex qtree representation of this tree.
+        :rtype: str
+        """
+        reserved_chars = re.compile(r"([#\$%&~_\{\}])")
+
+        pformat = self.pformat(indent=6, nodesep="", parens=("[.", " ]"))
+        return r"\Tree " + re.sub(reserved_chars, r"\\\1", pformat)
+
+    def _pformat_flat(self, nodesep, parens, quotes):
+        childstrs = []
+        for child in self:
+            if isinstance(child, Tree):
+                childstrs.append(child._pformat_flat(nodesep, parens, quotes))
+            elif isinstance(child, tuple):
+                childstrs.append("/".join(child))
+            elif isinstance(child, str) and not quotes:
+                childstrs.append("%s" % child)
+            else:
+                childstrs.append(repr(child))
+        if isinstance(self._label, str):
+            return "{}{}{} {}{}".format(
+                parens[0],
+                self._label,
+                nodesep,
+                " ".join(childstrs),
+                parens[1],
+            )
+        else:
+            return "{}{}{} {}{}".format(
+                parens[0],
+                repr(self._label),
+                nodesep,
+                " ".join(childstrs),
+                parens[1],
+            )
+
+
+def _child_names(tree):
+    names = []
+    for child in tree:
+        if isinstance(child, Tree):
+            names.append(Nonterminal(child._label))
+        else:
+            names.append(child)
+    return names
+
+
+######################################################################
+## Demonstration
+######################################################################
+
+
+def demo():
+    """
+    A demonstration showing how Trees and Trees can be
+    used.  This demonstration creates a Tree, and loads a
+    Tree from the Treebank corpus,
+    and shows the results of calling several of their methods.
+    """
+
+    from nltk import ProbabilisticTree, Tree
+
+    # Demonstrate tree parsing.
+    s = "(S (NP (DT the) (NN cat)) (VP (VBD ate) (NP (DT a) (NN cookie))))"
+    t = Tree.fromstring(s)
+    print("Convert bracketed string into tree:")
+    print(t)
+    print(t.__repr__())
+
+    print("Display tree properties:")
+    print(t.label())  # tree's constituent type
+    print(t[0])  # tree's first child
+    print(t[1])  # tree's second child
+    print(t.height())
+    print(t.leaves())
+    print(t[1])
+    print(t[1, 1])
+    print(t[1, 1, 0])
+
+    # Demonstrate tree modification.
+    the_cat = t[0]
+    the_cat.insert(1, Tree.fromstring("(JJ big)"))
+    print("Tree modification:")
+    print(t)
+    t[1, 1, 1] = Tree.fromstring("(NN cake)")
+    print(t)
+    print()
+
+    # Tree transforms
+    print("Collapse unary:")
+    t.collapse_unary()
+    print(t)
+    print("Chomsky normal form:")
+    t.chomsky_normal_form()
+    print(t)
+    print()
+
+    # Demonstrate probabilistic trees.
+    pt = ProbabilisticTree("x", ["y", "z"], prob=0.5)
+    print("Probabilistic Tree:")
+    print(pt)
+    print()
+
+    # Demonstrate parsing of treebank output format.
+    t = Tree.fromstring(t.pformat())
+    print("Convert tree to bracketed string and back again:")
+    print(t)
+    print()
+
+    # Demonstrate LaTeX output
+    print("LaTeX output:")
+    print(t.pformat_latex_qtree())
+    print()
+
+    # Demonstrate Productions
+    print("Production output:")
+    print(t.productions())
+    print()
+
+    # Demonstrate tree nodes containing objects other than strings
+    t.set_label(("test", 3))
+    print(t)
+
+
+__all__ = [
+    "Tree",
+]