updates

Backend/venv/lib/python3.12/site-packages/nltk/ccg/__init__.py

@@ -0,0 +1,34 @@
+# Natural Language Toolkit: Combinatory Categorial Grammar
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Graeme Gange <ggange@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+Combinatory Categorial Grammar.
+
+For more information see nltk/doc/contrib/ccg/ccg.pdf
+"""
+
+from nltk.ccg.chart import CCGChart, CCGChartParser, CCGEdge, CCGLeafEdge
+from nltk.ccg.combinator import (
+    BackwardApplication,
+    BackwardBx,
+    BackwardCombinator,
+    BackwardComposition,
+    BackwardSx,
+    BackwardT,
+    DirectedBinaryCombinator,
+    ForwardApplication,
+    ForwardCombinator,
+    ForwardComposition,
+    ForwardSubstitution,
+    ForwardT,
+    UndirectedBinaryCombinator,
+    UndirectedComposition,
+    UndirectedFunctionApplication,
+    UndirectedSubstitution,
+    UndirectedTypeRaise,
+)
+from nltk.ccg.lexicon import CCGLexicon

Backend/venv/lib/python3.12/site-packages/nltk/ccg/api.py

@@ -0,0 +1,358 @@
+# Natural Language Toolkit: CCG Categories
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Graeme Gange <ggange@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+from abc import ABCMeta, abstractmethod
+from functools import total_ordering
+
+from nltk.internals import raise_unorderable_types
+
+
+@total_ordering
+class AbstractCCGCategory(metaclass=ABCMeta):
+    """
+    Interface for categories in combinatory grammars.
+    """
+
+    @abstractmethod
+    def is_primitive(self):
+        """
+        Returns true if the category is primitive.
+        """
+
+    @abstractmethod
+    def is_function(self):
+        """
+        Returns true if the category is a function application.
+        """
+
+    @abstractmethod
+    def is_var(self):
+        """
+        Returns true if the category is a variable.
+        """
+
+    @abstractmethod
+    def substitute(self, substitutions):
+        """
+        Takes a set of (var, category) substitutions, and replaces every
+        occurrence of the variable with the corresponding category.
+        """
+
+    @abstractmethod
+    def can_unify(self, other):
+        """
+        Determines whether two categories can be unified.
+         - Returns None if they cannot be unified
+         - Returns a list of necessary substitutions if they can.
+        """
+
+    # Utility functions: comparison, strings and hashing.
+    @abstractmethod
+    def __str__(self):
+        pass
+
+    def __eq__(self, other):
+        return (
+            self.__class__ is other.__class__
+            and self._comparison_key == other._comparison_key
+        )
+
+    def __ne__(self, other):
+        return not self == other
+
+    def __lt__(self, other):
+        if not isinstance(other, AbstractCCGCategory):
+            raise_unorderable_types("<", self, other)
+        if self.__class__ is other.__class__:
+            return self._comparison_key < other._comparison_key
+        else:
+            return self.__class__.__name__ < other.__class__.__name__
+
+    def __hash__(self):
+        try:
+            return self._hash
+        except AttributeError:
+            self._hash = hash(self._comparison_key)
+            return self._hash
+
+
+class CCGVar(AbstractCCGCategory):
+    """
+    Class representing a variable CCG category.
+    Used for conjunctions (and possibly type-raising, if implemented as a
+    unary rule).
+    """
+
+    _maxID = 0
+
+    def __init__(self, prim_only=False):
+        """Initialize a variable (selects a new identifier)
+
+        :param prim_only: a boolean that determines whether the variable is
+                          restricted to primitives
+        :type prim_only: bool
+        """
+        self._id = self.new_id()
+        self._prim_only = prim_only
+        self._comparison_key = self._id
+
+    @classmethod
+    def new_id(cls):
+        """
+        A class method allowing generation of unique variable identifiers.
+        """
+        cls._maxID = cls._maxID + 1
+        return cls._maxID - 1
+
+    @classmethod
+    def reset_id(cls):
+        cls._maxID = 0
+
+    def is_primitive(self):
+        return False
+
+    def is_function(self):
+        return False
+
+    def is_var(self):
+        return True
+
+    def substitute(self, substitutions):
+        """If there is a substitution corresponding to this variable,
+        return the substituted category.
+        """
+        for var, cat in substitutions:
+            if var == self:
+                return cat
+        return self
+
+    def can_unify(self, other):
+        """If the variable can be replaced with other
+        a substitution is returned.
+        """
+        if other.is_primitive() or not self._prim_only:
+            return [(self, other)]
+        return None
+
+    def id(self):
+        return self._id
+
+    def __str__(self):
+        return "_var" + str(self._id)
+
+
+@total_ordering
+class Direction:
+    """
+    Class representing the direction of a function application.
+    Also contains maintains information as to which combinators
+    may be used with the category.
+    """
+
+    def __init__(self, dir, restrictions):
+        self._dir = dir
+        self._restrs = restrictions
+        self._comparison_key = (dir, tuple(restrictions))
+
+    # Testing the application direction
+    def is_forward(self):
+        return self._dir == "/"
+
+    def is_backward(self):
+        return self._dir == "\\"
+
+    def dir(self):
+        return self._dir
+
+    def restrs(self):
+        """A list of restrictions on the combinators.
+        '.' denotes that permuting operations are disallowed
+        ',' denotes that function composition is disallowed
+        '_' denotes that the direction has variable restrictions.
+        (This is redundant in the current implementation of type-raising)
+        """
+        return self._restrs
+
+    def is_variable(self):
+        return self._restrs == "_"
+
+    # Unification and substitution of variable directions.
+    # Used only if type-raising is implemented as a unary rule, as it
+    # must inherit restrictions from the argument category.
+    def can_unify(self, other):
+        if other.is_variable():
+            return [("_", self.restrs())]
+        elif self.is_variable():
+            return [("_", other.restrs())]
+        else:
+            if self.restrs() == other.restrs():
+                return []
+        return None
+
+    def substitute(self, subs):
+        if not self.is_variable():
+            return self
+
+        for var, restrs in subs:
+            if var == "_":
+                return Direction(self._dir, restrs)
+        return self
+
+    # Testing permitted combinators
+    def can_compose(self):
+        return "," not in self._restrs
+
+    def can_cross(self):
+        return "." not in self._restrs
+
+    def __eq__(self, other):
+        return (
+            self.__class__ is other.__class__
+            and self._comparison_key == other._comparison_key
+        )
+
+    def __ne__(self, other):
+        return not self == other
+
+    def __lt__(self, other):
+        if not isinstance(other, Direction):
+            raise_unorderable_types("<", self, other)
+        if self.__class__ is other.__class__:
+            return self._comparison_key < other._comparison_key
+        else:
+            return self.__class__.__name__ < other.__class__.__name__
+
+    def __hash__(self):
+        try:
+            return self._hash
+        except AttributeError:
+            self._hash = hash(self._comparison_key)
+            return self._hash
+
+    def __str__(self):
+        r_str = ""
+        for r in self._restrs:
+            r_str = r_str + "%s" % r
+        return f"{self._dir}{r_str}"
+
+    # The negation operator reverses the direction of the application
+    def __neg__(self):
+        if self._dir == "/":
+            return Direction("\\", self._restrs)
+        else:
+            return Direction("/", self._restrs)
+
+
+class PrimitiveCategory(AbstractCCGCategory):
+    """
+    Class representing primitive categories.
+    Takes a string representation of the category, and a
+    list of strings specifying the morphological subcategories.
+    """
+
+    def __init__(self, categ, restrictions=[]):
+        self._categ = categ
+        self._restrs = restrictions
+        self._comparison_key = (categ, tuple(restrictions))
+
+    def is_primitive(self):
+        return True
+
+    def is_function(self):
+        return False
+
+    def is_var(self):
+        return False
+
+    def restrs(self):
+        return self._restrs
+
+    def categ(self):
+        return self._categ
+
+    # Substitution does nothing to a primitive category
+    def substitute(self, subs):
+        return self
+
+    # A primitive can be unified with a class of the same
+    # base category, given that the other category shares all
+    # of its subclasses, or with a variable.
+    def can_unify(self, other):
+        if not other.is_primitive():
+            return None
+        if other.is_var():
+            return [(other, self)]
+        if other.categ() == self.categ():
+            for restr in self._restrs:
+                if restr not in other.restrs():
+                    return None
+            return []
+        return None
+
+    def __str__(self):
+        if self._restrs == []:
+            return "%s" % self._categ
+        restrictions = "[%s]" % ",".join(repr(r) for r in self._restrs)
+        return f"{self._categ}{restrictions}"
+
+
+class FunctionalCategory(AbstractCCGCategory):
+    """
+    Class that represents a function application category.
+    Consists of argument and result categories, together with
+    an application direction.
+    """
+
+    def __init__(self, res, arg, dir):
+        self._res = res
+        self._arg = arg
+        self._dir = dir
+        self._comparison_key = (arg, dir, res)
+
+    def is_primitive(self):
+        return False
+
+    def is_function(self):
+        return True
+
+    def is_var(self):
+        return False
+
+    # Substitution returns the category consisting of the
+    # substitution applied to each of its constituents.
+    def substitute(self, subs):
+        sub_res = self._res.substitute(subs)
+        sub_dir = self._dir.substitute(subs)
+        sub_arg = self._arg.substitute(subs)
+        return FunctionalCategory(sub_res, sub_arg, self._dir)
+
+    # A function can unify with another function, so long as its
+    # constituents can unify, or with an unrestricted variable.
+    def can_unify(self, other):
+        if other.is_var():
+            return [(other, self)]
+        if other.is_function():
+            sa = self._res.can_unify(other.res())
+            sd = self._dir.can_unify(other.dir())
+            if sa is not None and sd is not None:
+                sb = self._arg.substitute(sa).can_unify(other.arg().substitute(sa))
+                if sb is not None:
+                    return sa + sb
+        return None
+
+    # Constituent accessors
+    def arg(self):
+        return self._arg
+
+    def res(self):
+        return self._res
+
+    def dir(self):
+        return self._dir
+
+    def __str__(self):
+        return f"({self._res}{self._dir}{self._arg})"

Backend/venv/lib/python3.12/site-packages/nltk/ccg/chart.py

@@ -0,0 +1,480 @@
+# Natural Language Toolkit: Combinatory Categorial Grammar
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Graeme Gange <ggange@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+The lexicon is constructed by calling
+``lexicon.fromstring(<lexicon string>)``.
+
+In order to construct a parser, you also need a rule set.
+The standard English rules are provided in chart as
+``chart.DefaultRuleSet``.
+
+The parser can then be constructed by calling, for example:
+``parser = chart.CCGChartParser(<lexicon>, <ruleset>)``
+
+Parsing is then performed by running
+``parser.parse(<sentence>.split())``.
+
+While this returns a list of trees, the default representation
+of the produced trees is not very enlightening, particularly
+given that it uses the same tree class as the CFG parsers.
+It is probably better to call:
+``chart.printCCGDerivation(<parse tree extracted from list>)``
+which should print a nice representation of the derivation.
+
+This entire process is shown far more clearly in the demonstration:
+python chart.py
+"""
+
+import itertools
+
+from nltk.ccg.combinator import *
+from nltk.ccg.combinator import (
+    BackwardApplication,
+    BackwardBx,
+    BackwardComposition,
+    BackwardSx,
+    BackwardT,
+    ForwardApplication,
+    ForwardComposition,
+    ForwardSubstitution,
+    ForwardT,
+)
+from nltk.ccg.lexicon import Token, fromstring
+from nltk.ccg.logic import *
+from nltk.parse import ParserI
+from nltk.parse.chart import AbstractChartRule, Chart, EdgeI
+from nltk.sem.logic import *
+from nltk.tree import Tree
+
+
+# Based on the EdgeI class from NLTK.
+# A number of the properties of the EdgeI interface don't
+# transfer well to CCGs, however.
+class CCGEdge(EdgeI):
+    def __init__(self, span, categ, rule):
+        self._span = span
+        self._categ = categ
+        self._rule = rule
+        self._comparison_key = (span, categ, rule)
+
+    # Accessors
+    def lhs(self):
+        return self._categ
+
+    def span(self):
+        return self._span
+
+    def start(self):
+        return self._span[0]
+
+    def end(self):
+        return self._span[1]
+
+    def length(self):
+        return self._span[1] - self.span[0]
+
+    def rhs(self):
+        return ()
+
+    def dot(self):
+        return 0
+
+    def is_complete(self):
+        return True
+
+    def is_incomplete(self):
+        return False
+
+    def nextsym(self):
+        return None
+
+    def categ(self):
+        return self._categ
+
+    def rule(self):
+        return self._rule
+
+
+class CCGLeafEdge(EdgeI):
+    """
+    Class representing leaf edges in a CCG derivation.
+    """
+
+    def __init__(self, pos, token, leaf):
+        self._pos = pos
+        self._token = token
+        self._leaf = leaf
+        self._comparison_key = (pos, token.categ(), leaf)
+
+    # Accessors
+    def lhs(self):
+        return self._token.categ()
+
+    def span(self):
+        return (self._pos, self._pos + 1)
+
+    def start(self):
+        return self._pos
+
+    def end(self):
+        return self._pos + 1
+
+    def length(self):
+        return 1
+
+    def rhs(self):
+        return self._leaf
+
+    def dot(self):
+        return 0
+
+    def is_complete(self):
+        return True
+
+    def is_incomplete(self):
+        return False
+
+    def nextsym(self):
+        return None
+
+    def token(self):
+        return self._token
+
+    def categ(self):
+        return self._token.categ()
+
+    def leaf(self):
+        return self._leaf
+
+
+class BinaryCombinatorRule(AbstractChartRule):
+    """
+    Class implementing application of a binary combinator to a chart.
+    Takes the directed combinator to apply.
+    """
+
+    NUMEDGES = 2
+
+    def __init__(self, combinator):
+        self._combinator = combinator
+
+    # Apply a combinator
+    def apply(self, chart, grammar, left_edge, right_edge):
+        # The left & right edges must be touching.
+        if not (left_edge.end() == right_edge.start()):
+            return
+
+        # Check if the two edges are permitted to combine.
+        # If so, generate the corresponding edge.
+        if self._combinator.can_combine(left_edge.categ(), right_edge.categ()):
+            for res in self._combinator.combine(left_edge.categ(), right_edge.categ()):
+                new_edge = CCGEdge(
+                    span=(left_edge.start(), right_edge.end()),
+                    categ=res,
+                    rule=self._combinator,
+                )
+                if chart.insert(new_edge, (left_edge, right_edge)):
+                    yield new_edge
+
+    # The representation of the combinator (for printing derivations)
+    def __str__(self):
+        return "%s" % self._combinator
+
+
+# Type-raising must be handled slightly differently to the other rules, as the
+# resulting rules only span a single edge, rather than both edges.
+
+
+class ForwardTypeRaiseRule(AbstractChartRule):
+    """
+    Class for applying forward type raising
+    """
+
+    NUMEDGES = 2
+
+    def __init__(self):
+        self._combinator = ForwardT
+
+    def apply(self, chart, grammar, left_edge, right_edge):
+        if not (left_edge.end() == right_edge.start()):
+            return
+
+        for res in self._combinator.combine(left_edge.categ(), right_edge.categ()):
+            new_edge = CCGEdge(span=left_edge.span(), categ=res, rule=self._combinator)
+            if chart.insert(new_edge, (left_edge,)):
+                yield new_edge
+
+    def __str__(self):
+        return "%s" % self._combinator
+
+
+class BackwardTypeRaiseRule(AbstractChartRule):
+    """
+    Class for applying backward type raising.
+    """
+
+    NUMEDGES = 2
+
+    def __init__(self):
+        self._combinator = BackwardT
+
+    def apply(self, chart, grammar, left_edge, right_edge):
+        if not (left_edge.end() == right_edge.start()):
+            return
+
+        for res in self._combinator.combine(left_edge.categ(), right_edge.categ()):
+            new_edge = CCGEdge(span=right_edge.span(), categ=res, rule=self._combinator)
+            if chart.insert(new_edge, (right_edge,)):
+                yield new_edge
+
+    def __str__(self):
+        return "%s" % self._combinator
+
+
+# Common sets of combinators used for English derivations.
+ApplicationRuleSet = [
+    BinaryCombinatorRule(ForwardApplication),
+    BinaryCombinatorRule(BackwardApplication),
+]
+CompositionRuleSet = [
+    BinaryCombinatorRule(ForwardComposition),
+    BinaryCombinatorRule(BackwardComposition),
+    BinaryCombinatorRule(BackwardBx),
+]
+SubstitutionRuleSet = [
+    BinaryCombinatorRule(ForwardSubstitution),
+    BinaryCombinatorRule(BackwardSx),
+]
+TypeRaiseRuleSet = [ForwardTypeRaiseRule(), BackwardTypeRaiseRule()]
+
+# The standard English rule set.
+DefaultRuleSet = (
+    ApplicationRuleSet + CompositionRuleSet + SubstitutionRuleSet + TypeRaiseRuleSet
+)
+
+
+class CCGChartParser(ParserI):
+    """
+    Chart parser for CCGs.
+    Based largely on the ChartParser class from NLTK.
+    """
+
+    def __init__(self, lexicon, rules, trace=0):
+        self._lexicon = lexicon
+        self._rules = rules
+        self._trace = trace
+
+    def lexicon(self):
+        return self._lexicon
+
+    # Implements the CYK algorithm
+    def parse(self, tokens):
+        tokens = list(tokens)
+        chart = CCGChart(list(tokens))
+        lex = self._lexicon
+
+        # Initialize leaf edges.
+        for index in range(chart.num_leaves()):
+            for token in lex.categories(chart.leaf(index)):
+                new_edge = CCGLeafEdge(index, token, chart.leaf(index))
+                chart.insert(new_edge, ())
+
+        # Select a span for the new edges
+        for span in range(2, chart.num_leaves() + 1):
+            for start in range(0, chart.num_leaves() - span + 1):
+                # Try all possible pairs of edges that could generate
+                # an edge for that span
+                for part in range(1, span):
+                    lstart = start
+                    mid = start + part
+                    rend = start + span
+
+                    for left in chart.select(span=(lstart, mid)):
+                        for right in chart.select(span=(mid, rend)):
+                            # Generate all possible combinations of the two edges
+                            for rule in self._rules:
+                                edges_added_by_rule = 0
+                                for newedge in rule.apply(chart, lex, left, right):
+                                    edges_added_by_rule += 1
+
+        # Output the resulting parses
+        return chart.parses(lex.start())
+
+
+class CCGChart(Chart):
+    def __init__(self, tokens):
+        Chart.__init__(self, tokens)
+
+    # Constructs the trees for a given parse. Unfortnunately, the parse trees need to be
+    # constructed slightly differently to those in the default Chart class, so it has to
+    # be reimplemented
+    def _trees(self, edge, complete, memo, tree_class):
+        assert complete, "CCGChart cannot build incomplete trees"
+
+        if edge in memo:
+            return memo[edge]
+
+        if isinstance(edge, CCGLeafEdge):
+            word = tree_class(edge.token(), [self._tokens[edge.start()]])
+            leaf = tree_class((edge.token(), "Leaf"), [word])
+            memo[edge] = [leaf]
+            return [leaf]
+
+        memo[edge] = []
+        trees = []
+
+        for cpl in self.child_pointer_lists(edge):
+            child_choices = [self._trees(cp, complete, memo, tree_class) for cp in cpl]
+            for children in itertools.product(*child_choices):
+                lhs = (
+                    Token(
+                        self._tokens[edge.start() : edge.end()],
+                        edge.lhs(),
+                        compute_semantics(children, edge),
+                    ),
+                    str(edge.rule()),
+                )
+                trees.append(tree_class(lhs, children))
+
+        memo[edge] = trees
+        return trees
+
+
+def compute_semantics(children, edge):
+    if children[0].label()[0].semantics() is None:
+        return None
+
+    if len(children) == 2:
+        if isinstance(edge.rule(), BackwardCombinator):
+            children = [children[1], children[0]]
+
+        combinator = edge.rule()._combinator
+        function = children[0].label()[0].semantics()
+        argument = children[1].label()[0].semantics()
+
+        if isinstance(combinator, UndirectedFunctionApplication):
+            return compute_function_semantics(function, argument)
+        elif isinstance(combinator, UndirectedComposition):
+            return compute_composition_semantics(function, argument)
+        elif isinstance(combinator, UndirectedSubstitution):
+            return compute_substitution_semantics(function, argument)
+        else:
+            raise AssertionError("Unsupported combinator '" + combinator + "'")
+    else:
+        return compute_type_raised_semantics(children[0].label()[0].semantics())
+
+
+# --------
+# Displaying derivations
+# --------
+def printCCGDerivation(tree):
+    # Get the leaves and initial categories
+    leafcats = tree.pos()
+    leafstr = ""
+    catstr = ""
+
+    # Construct a string with both the leaf word and corresponding
+    # category aligned.
+    for leaf, cat in leafcats:
+        str_cat = "%s" % cat
+        nextlen = 2 + max(len(leaf), len(str_cat))
+        lcatlen = (nextlen - len(str_cat)) // 2
+        rcatlen = lcatlen + (nextlen - len(str_cat)) % 2
+        catstr += " " * lcatlen + str_cat + " " * rcatlen
+        lleaflen = (nextlen - len(leaf)) // 2
+        rleaflen = lleaflen + (nextlen - len(leaf)) % 2
+        leafstr += " " * lleaflen + leaf + " " * rleaflen
+    print(leafstr.rstrip())
+    print(catstr.rstrip())
+
+    # Display the derivation steps
+    printCCGTree(0, tree)
+
+
+# Prints the sequence of derivation steps.
+def printCCGTree(lwidth, tree):
+    rwidth = lwidth
+
+    # Is a leaf (word).
+    # Increment the span by the space occupied by the leaf.
+    if not isinstance(tree, Tree):
+        return 2 + lwidth + len(tree)
+
+    # Find the width of the current derivation step
+    for child in tree:
+        rwidth = max(rwidth, printCCGTree(rwidth, child))
+
+    # Is a leaf node.
+    # Don't print anything, but account for the space occupied.
+    if not isinstance(tree.label(), tuple):
+        return max(
+            rwidth, 2 + lwidth + len("%s" % tree.label()), 2 + lwidth + len(tree[0])
+        )
+
+    (token, op) = tree.label()
+
+    if op == "Leaf":
+        return rwidth
+
+    # Pad to the left with spaces, followed by a sequence of '-'
+    # and the derivation rule.
+    print(lwidth * " " + (rwidth - lwidth) * "-" + "%s" % op)
+    # Print the resulting category on a new line.
+    str_res = "%s" % (token.categ())
+    if token.semantics() is not None:
+        str_res += " {" + str(token.semantics()) + "}"
+    respadlen = (rwidth - lwidth - len(str_res)) // 2 + lwidth
+    print(respadlen * " " + str_res)
+    return rwidth
+
+
+### Demonstration code
+
+# Construct the lexicon
+lex = fromstring(
+    """
+    :- S, NP, N, VP    # Primitive categories, S is the target primitive
+
+    Det :: NP/N         # Family of words
+    Pro :: NP
+    TV :: VP/NP
+    Modal :: (S\\NP)/VP # Backslashes need to be escaped
+
+    I => Pro             # Word -> Category mapping
+    you => Pro
+
+    the => Det
+
+    # Variables have the special keyword 'var'
+    # '.' prevents permutation
+    # ',' prevents composition
+    and => var\\.,var/.,var
+
+    which => (N\\N)/(S/NP)
+
+    will => Modal # Categories can be either explicit, or families.
+    might => Modal
+
+    cook => TV
+    eat => TV
+
+    mushrooms => N
+    parsnips => N
+    bacon => N
+    """
+)
+
+
+def demo():
+    parser = CCGChartParser(lex, DefaultRuleSet)
+    for parse in parser.parse("I might cook and eat the bacon".split()):
+        printCCGDerivation(parse)
+
+
+if __name__ == "__main__":
+    demo()

Backend/venv/lib/python3.12/site-packages/nltk/ccg/combinator.py

@@ -0,0 +1,340 @@
+# Natural Language Toolkit: Combinatory Categorial Grammar
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Graeme Gange <ggange@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+"""
+CCG Combinators
+"""
+
+from abc import ABCMeta, abstractmethod
+
+from nltk.ccg.api import FunctionalCategory
+
+
+class UndirectedBinaryCombinator(metaclass=ABCMeta):
+    """
+    Abstract class for representing a binary combinator.
+    Merely defines functions for checking if the function and argument
+    are able to be combined, and what the resulting category is.
+
+    Note that as no assumptions are made as to direction, the unrestricted
+    combinators can perform all backward, forward and crossed variations
+    of the combinators; these restrictions must be added in the rule
+    class.
+    """
+
+    @abstractmethod
+    def can_combine(self, function, argument):
+        pass
+
+    @abstractmethod
+    def combine(self, function, argument):
+        pass
+
+
+class DirectedBinaryCombinator(metaclass=ABCMeta):
+    """
+    Wrapper for the undirected binary combinator.
+    It takes left and right categories, and decides which is to be
+    the function, and which the argument.
+    It then decides whether or not they can be combined.
+    """
+
+    @abstractmethod
+    def can_combine(self, left, right):
+        pass
+
+    @abstractmethod
+    def combine(self, left, right):
+        pass
+
+
+class ForwardCombinator(DirectedBinaryCombinator):
+    """
+    Class representing combinators where the primary functor is on the left.
+
+    Takes an undirected combinator, and a predicate which adds constraints
+    restricting the cases in which it may apply.
+    """
+
+    def __init__(self, combinator, predicate, suffix=""):
+        self._combinator = combinator
+        self._predicate = predicate
+        self._suffix = suffix
+
+    def can_combine(self, left, right):
+        return self._combinator.can_combine(left, right) and self._predicate(
+            left, right
+        )
+
+    def combine(self, left, right):
+        yield from self._combinator.combine(left, right)
+
+    def __str__(self):
+        return f">{self._combinator}{self._suffix}"
+
+
+class BackwardCombinator(DirectedBinaryCombinator):
+    """
+    The backward equivalent of the ForwardCombinator class.
+    """
+
+    def __init__(self, combinator, predicate, suffix=""):
+        self._combinator = combinator
+        self._predicate = predicate
+        self._suffix = suffix
+
+    def can_combine(self, left, right):
+        return self._combinator.can_combine(right, left) and self._predicate(
+            left, right
+        )
+
+    def combine(self, left, right):
+        yield from self._combinator.combine(right, left)
+
+    def __str__(self):
+        return f"<{self._combinator}{self._suffix}"
+
+
+class UndirectedFunctionApplication(UndirectedBinaryCombinator):
+    """
+    Class representing function application.
+    Implements rules of the form:
+    X/Y Y -> X (>)
+    And the corresponding backwards application rule
+    """
+
+    def can_combine(self, function, argument):
+        if not function.is_function():
+            return False
+
+        return not function.arg().can_unify(argument) is None
+
+    def combine(self, function, argument):
+        if not function.is_function():
+            return
+
+        subs = function.arg().can_unify(argument)
+        if subs is None:
+            return
+
+        yield function.res().substitute(subs)
+
+    def __str__(self):
+        return ""
+
+
+# Predicates for function application.
+
+
+# Ensures the left functor takes an argument on the right
+def forwardOnly(left, right):
+    return left.dir().is_forward()
+
+
+# Ensures the right functor takes an argument on the left
+def backwardOnly(left, right):
+    return right.dir().is_backward()
+
+
+# Application combinator instances
+ForwardApplication = ForwardCombinator(UndirectedFunctionApplication(), forwardOnly)
+BackwardApplication = BackwardCombinator(UndirectedFunctionApplication(), backwardOnly)
+
+
+class UndirectedComposition(UndirectedBinaryCombinator):
+    """
+    Functional composition (harmonic) combinator.
+    Implements rules of the form
+    X/Y Y/Z -> X/Z (B>)
+    And the corresponding backwards and crossed variations.
+    """
+
+    def can_combine(self, function, argument):
+        # Can only combine two functions, and both functions must
+        # allow composition.
+        if not (function.is_function() and argument.is_function()):
+            return False
+        if function.dir().can_compose() and argument.dir().can_compose():
+            return not function.arg().can_unify(argument.res()) is None
+        return False
+
+    def combine(self, function, argument):
+        if not (function.is_function() and argument.is_function()):
+            return
+        if function.dir().can_compose() and argument.dir().can_compose():
+            subs = function.arg().can_unify(argument.res())
+            if subs is not None:
+                yield FunctionalCategory(
+                    function.res().substitute(subs),
+                    argument.arg().substitute(subs),
+                    argument.dir(),
+                )
+
+    def __str__(self):
+        return "B"
+
+
+# Predicates for restricting application of straight composition.
+def bothForward(left, right):
+    return left.dir().is_forward() and right.dir().is_forward()
+
+
+def bothBackward(left, right):
+    return left.dir().is_backward() and right.dir().is_backward()
+
+
+# Predicates for crossed composition
+def crossedDirs(left, right):
+    return left.dir().is_forward() and right.dir().is_backward()
+
+
+def backwardBxConstraint(left, right):
+    # The functors must be crossed inwards
+    if not crossedDirs(left, right):
+        return False
+    # Permuting combinators must be allowed
+    if not left.dir().can_cross() and right.dir().can_cross():
+        return False
+    # The resulting argument category is restricted to be primitive
+    return left.arg().is_primitive()
+
+
+# Straight composition combinators
+ForwardComposition = ForwardCombinator(UndirectedComposition(), forwardOnly)
+BackwardComposition = BackwardCombinator(UndirectedComposition(), backwardOnly)
+
+# Backward crossed composition
+BackwardBx = BackwardCombinator(
+    UndirectedComposition(), backwardBxConstraint, suffix="x"
+)
+
+
+class UndirectedSubstitution(UndirectedBinaryCombinator):
+    r"""
+    Substitution (permutation) combinator.
+    Implements rules of the form
+    Y/Z (X\Y)/Z -> X/Z (<Sx)
+    And other variations.
+    """
+
+    def can_combine(self, function, argument):
+        if function.is_primitive() or argument.is_primitive():
+            return False
+
+        # These could potentially be moved to the predicates, as the
+        # constraints may not be general to all languages.
+        if function.res().is_primitive():
+            return False
+        if not function.arg().is_primitive():
+            return False
+
+        if not (function.dir().can_compose() and argument.dir().can_compose()):
+            return False
+        return (function.res().arg() == argument.res()) and (
+            function.arg() == argument.arg()
+        )
+
+    def combine(self, function, argument):
+        if self.can_combine(function, argument):
+            yield FunctionalCategory(
+                function.res().res(), argument.arg(), argument.dir()
+            )
+
+    def __str__(self):
+        return "S"
+
+
+# Predicate for forward substitution
+def forwardSConstraint(left, right):
+    if not bothForward(left, right):
+        return False
+    return left.res().dir().is_forward() and left.arg().is_primitive()
+
+
+# Predicate for backward crossed substitution
+def backwardSxConstraint(left, right):
+    if not left.dir().can_cross() and right.dir().can_cross():
+        return False
+    if not bothForward(left, right):
+        return False
+    return right.res().dir().is_backward() and right.arg().is_primitive()
+
+
+# Instances of substitution combinators
+ForwardSubstitution = ForwardCombinator(UndirectedSubstitution(), forwardSConstraint)
+BackwardSx = BackwardCombinator(UndirectedSubstitution(), backwardSxConstraint, "x")
+
+
+# Retrieves the left-most functional category.
+# ie, (N\N)/(S/NP) => N\N
+def innermostFunction(categ):
+    while categ.res().is_function():
+        categ = categ.res()
+    return categ
+
+
+class UndirectedTypeRaise(UndirectedBinaryCombinator):
+    """
+    Undirected combinator for type raising.
+    """
+
+    def can_combine(self, function, arg):
+        # The argument must be a function.
+        # The restriction that arg.res() must be a function
+        # merely reduces redundant type-raising; if arg.res() is
+        # primitive, we have:
+        # X Y\X =>(<T) Y/(Y\X) Y\X =>(>) Y
+        # which is equivalent to
+        # X Y\X =>(<) Y
+        if not (arg.is_function() and arg.res().is_function()):
+            return False
+
+        arg = innermostFunction(arg)
+
+        # left, arg_categ are undefined!
+        subs = left.can_unify(arg_categ.arg())
+        if subs is not None:
+            return True
+        return False
+
+    def combine(self, function, arg):
+        if not (
+            function.is_primitive() and arg.is_function() and arg.res().is_function()
+        ):
+            return
+
+        # Type-raising matches only the innermost application.
+        arg = innermostFunction(arg)
+
+        subs = function.can_unify(arg.arg())
+        if subs is not None:
+            xcat = arg.res().substitute(subs)
+            yield FunctionalCategory(
+                xcat, FunctionalCategory(xcat, function, arg.dir()), -(arg.dir())
+            )
+
+    def __str__(self):
+        return "T"
+
+
+# Predicates for type-raising
+# The direction of the innermost category must be towards
+# the primary functor.
+# The restriction that the variable must be primitive is not
+# common to all versions of CCGs; some authors have other restrictions.
+def forwardTConstraint(left, right):
+    arg = innermostFunction(right)
+    return arg.dir().is_backward() and arg.res().is_primitive()
+
+
+def backwardTConstraint(left, right):
+    arg = innermostFunction(left)
+    return arg.dir().is_forward() and arg.res().is_primitive()
+
+
+# Instances of type-raising combinators
+ForwardT = ForwardCombinator(UndirectedTypeRaise(), forwardTConstraint)
+BackwardT = BackwardCombinator(UndirectedTypeRaise(), backwardTConstraint)

Backend/venv/lib/python3.12/site-packages/nltk/ccg/lexicon.py

@@ -0,0 +1,338 @@
+# Natural Language Toolkit: Combinatory Categorial Grammar
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Graeme Gange <ggange@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+"""
+CCG Lexicons
+"""
+
+import re
+from collections import defaultdict
+
+from nltk.ccg.api import CCGVar, Direction, FunctionalCategory, PrimitiveCategory
+from nltk.internals import deprecated
+from nltk.sem.logic import Expression
+
+# ------------
+# Regular expressions used for parsing components of the lexicon
+# ------------
+
+# Parses a primitive category and subscripts
+PRIM_RE = re.compile(r"""([A-Za-z]+)(\[[A-Za-z,]+\])?""")
+
+# Separates the next primitive category from the remainder of the
+# string
+NEXTPRIM_RE = re.compile(r"""([A-Za-z]+(?:\[[A-Za-z,]+\])?)(.*)""")
+
+# Separates the next application operator from the remainder
+APP_RE = re.compile(r"""([\\/])([.,]?)([.,]?)(.*)""")
+
+# Parses the definition of the right-hand side (rhs) of either a word or a family
+LEX_RE = re.compile(r"""([\S_]+)\s*(::|[-=]+>)\s*(.+)""", re.UNICODE)
+
+# Parses the right hand side that contains category and maybe semantic predicate
+RHS_RE = re.compile(r"""([^{}]*[^ {}])\s*(\{[^}]+\})?""", re.UNICODE)
+
+# Parses the semantic predicate
+SEMANTICS_RE = re.compile(r"""\{([^}]+)\}""", re.UNICODE)
+
+# Strips comments from a line
+COMMENTS_RE = re.compile("""([^#]*)(?:#.*)?""")
+
+
+class Token:
+    """
+    Class representing a token.
+
+    token => category {semantics}
+    e.g. eat => S\\var[pl]/var {\\x y.eat(x,y)}
+
+    * `token` (string)
+    * `categ` (string)
+    * `semantics` (Expression)
+    """
+
+    def __init__(self, token, categ, semantics=None):
+        self._token = token
+        self._categ = categ
+        self._semantics = semantics
+
+    def categ(self):
+        return self._categ
+
+    def semantics(self):
+        return self._semantics
+
+    def __str__(self):
+        semantics_str = ""
+        if self._semantics is not None:
+            semantics_str = " {" + str(self._semantics) + "}"
+        return "" + str(self._categ) + semantics_str
+
+    def __cmp__(self, other):
+        if not isinstance(other, Token):
+            return -1
+        return cmp((self._categ, self._semantics), other.categ(), other.semantics())
+
+
+class CCGLexicon:
+    """
+    Class representing a lexicon for CCG grammars.
+
+    * `primitives`: The list of primitive categories for the lexicon
+    * `families`: Families of categories
+    * `entries`: A mapping of words to possible categories
+    """
+
+    def __init__(self, start, primitives, families, entries):
+        self._start = PrimitiveCategory(start)
+        self._primitives = primitives
+        self._families = families
+        self._entries = entries
+
+    def categories(self, word):
+        """
+        Returns all the possible categories for a word
+        """
+        return self._entries[word]
+
+    def start(self):
+        """
+        Return the target category for the parser
+        """
+        return self._start
+
+    def __str__(self):
+        """
+        String representation of the lexicon. Used for debugging.
+        """
+        string = ""
+        first = True
+        for ident in sorted(self._entries):
+            if not first:
+                string = string + "\n"
+            string = string + ident + " => "
+
+            first = True
+            for cat in self._entries[ident]:
+                if not first:
+                    string = string + " | "
+                else:
+                    first = False
+                string = string + "%s" % cat
+        return string
+
+
+# -----------
+# Parsing lexicons
+# -----------
+
+
+def matchBrackets(string):
+    """
+    Separate the contents matching the first set of brackets from the rest of
+    the input.
+    """
+    rest = string[1:]
+    inside = "("
+
+    while rest != "" and not rest.startswith(")"):
+        if rest.startswith("("):
+            (part, rest) = matchBrackets(rest)
+            inside = inside + part
+        else:
+            inside = inside + rest[0]
+            rest = rest[1:]
+    if rest.startswith(")"):
+        return (inside + ")", rest[1:])
+    raise AssertionError("Unmatched bracket in string '" + string + "'")
+
+
+def nextCategory(string):
+    """
+    Separate the string for the next portion of the category from the rest
+    of the string
+    """
+    if string.startswith("("):
+        return matchBrackets(string)
+    return NEXTPRIM_RE.match(string).groups()
+
+
+def parseApplication(app):
+    """
+    Parse an application operator
+    """
+    return Direction(app[0], app[1:])
+
+
+def parseSubscripts(subscr):
+    """
+    Parse the subscripts for a primitive category
+    """
+    if subscr:
+        return subscr[1:-1].split(",")
+    return []
+
+
+def parsePrimitiveCategory(chunks, primitives, families, var):
+    """
+    Parse a primitive category
+
+    If the primitive is the special category 'var', replace it with the
+    correct `CCGVar`.
+    """
+    if chunks[0] == "var":
+        if chunks[1] is None:
+            if var is None:
+                var = CCGVar()
+            return (var, var)
+
+    catstr = chunks[0]
+    if catstr in families:
+        (cat, cvar) = families[catstr]
+        if var is None:
+            var = cvar
+        else:
+            cat = cat.substitute([(cvar, var)])
+        return (cat, var)
+
+    if catstr in primitives:
+        subscrs = parseSubscripts(chunks[1])
+        return (PrimitiveCategory(catstr, subscrs), var)
+    raise AssertionError(
+        "String '" + catstr + "' is neither a family nor primitive category."
+    )
+
+
+def augParseCategory(line, primitives, families, var=None):
+    """
+    Parse a string representing a category, and returns a tuple with
+    (possibly) the CCG variable for the category
+    """
+    (cat_string, rest) = nextCategory(line)
+
+    if cat_string.startswith("("):
+        (res, var) = augParseCategory(cat_string[1:-1], primitives, families, var)
+
+    else:
+        (res, var) = parsePrimitiveCategory(
+            PRIM_RE.match(cat_string).groups(), primitives, families, var
+        )
+
+    while rest != "":
+        app = APP_RE.match(rest).groups()
+        direction = parseApplication(app[0:3])
+        rest = app[3]
+
+        (cat_string, rest) = nextCategory(rest)
+        if cat_string.startswith("("):
+            (arg, var) = augParseCategory(cat_string[1:-1], primitives, families, var)
+        else:
+            (arg, var) = parsePrimitiveCategory(
+                PRIM_RE.match(cat_string).groups(), primitives, families, var
+            )
+        res = FunctionalCategory(res, arg, direction)
+
+    return (res, var)
+
+
+def fromstring(lex_str, include_semantics=False):
+    """
+    Convert string representation into a lexicon for CCGs.
+    """
+    CCGVar.reset_id()
+    primitives = []
+    families = {}
+    entries = defaultdict(list)
+    for line in lex_str.splitlines():
+        # Strip comments and leading/trailing whitespace.
+        line = COMMENTS_RE.match(line).groups()[0].strip()
+        if line == "":
+            continue
+
+        if line.startswith(":-"):
+            # A line of primitive categories.
+            # The first one is the target category
+            # ie, :- S, N, NP, VP
+            primitives = primitives + [
+                prim.strip() for prim in line[2:].strip().split(",")
+            ]
+        else:
+            # Either a family definition, or a word definition
+            (ident, sep, rhs) = LEX_RE.match(line).groups()
+            (catstr, semantics_str) = RHS_RE.match(rhs).groups()
+            (cat, var) = augParseCategory(catstr, primitives, families)
+
+            if sep == "::":
+                # Family definition
+                # ie, Det :: NP/N
+                families[ident] = (cat, var)
+            else:
+                semantics = None
+                if include_semantics is True:
+                    if semantics_str is None:
+                        raise AssertionError(
+                            line
+                            + " must contain semantics because include_semantics is set to True"
+                        )
+                    else:
+                        semantics = Expression.fromstring(
+                            SEMANTICS_RE.match(semantics_str).groups()[0]
+                        )
+                # Word definition
+                # ie, which => (N\N)/(S/NP)
+                entries[ident].append(Token(ident, cat, semantics))
+    return CCGLexicon(primitives[0], primitives, families, entries)
+
+
+@deprecated("Use fromstring() instead.")
+def parseLexicon(lex_str):
+    return fromstring(lex_str)
+
+
+openccg_tinytiny = fromstring(
+    """
+    # Rather minimal lexicon based on the openccg `tinytiny' grammar.
+    # Only incorporates a subset of the morphological subcategories, however.
+    :- S,NP,N                    # Primitive categories
+    Det :: NP/N                  # Determiners
+    Pro :: NP
+    IntransVsg :: S\\NP[sg]    # Tensed intransitive verbs (singular)
+    IntransVpl :: S\\NP[pl]    # Plural
+    TransVsg :: S\\NP[sg]/NP   # Tensed transitive verbs (singular)
+    TransVpl :: S\\NP[pl]/NP   # Plural
+
+    the => NP[sg]/N[sg]
+    the => NP[pl]/N[pl]
+
+    I => Pro
+    me => Pro
+    we => Pro
+    us => Pro
+
+    book => N[sg]
+    books => N[pl]
+
+    peach => N[sg]
+    peaches => N[pl]
+
+    policeman => N[sg]
+    policemen => N[pl]
+
+    boy => N[sg]
+    boys => N[pl]
+
+    sleep => IntransVsg
+    sleep => IntransVpl
+
+    eat => IntransVpl
+    eat => TransVpl
+    eats => IntransVsg
+    eats => TransVsg
+
+    see => TransVpl
+    sees => TransVsg
+    """
+)

Backend/venv/lib/python3.12/site-packages/nltk/ccg/logic.py

@@ -0,0 +1,63 @@
+# Natural Language Toolkit: Combinatory Categorial Grammar
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Tanin Na Nakorn (@tanin)
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+"""
+Helper functions for CCG semantics computation
+"""
+
+import copy
+
+from nltk.sem.logic import *
+
+
+def compute_type_raised_semantics(semantics):
+    semantics_copy = copy.deepcopy(semantics)
+    core = semantics_copy
+    parent = None
+    while isinstance(core, LambdaExpression):
+        parent = core
+        core = core.term
+
+    var = Variable("F")
+    while var in core.free():
+        var = unique_variable(pattern=var)
+    core = ApplicationExpression(FunctionVariableExpression(var), core)
+
+    if parent is not None:
+        parent.term = core
+    else:
+        semantics_copy = core
+
+    return LambdaExpression(var, semantics_copy)
+
+
+def compute_function_semantics(function, argument):
+    return ApplicationExpression(function, argument).simplify()
+
+
+def compute_composition_semantics(function, argument):
+    assert isinstance(argument, LambdaExpression), (
+        "`" + str(argument) + "` must be a lambda expression"
+    )
+    return LambdaExpression(
+        argument.variable, ApplicationExpression(function, argument.term).simplify()
+    )
+
+
+def compute_substitution_semantics(function, argument):
+    assert isinstance(function, LambdaExpression) and isinstance(
+        function.term, LambdaExpression
+    ), ("`" + str(function) + "` must be a lambda expression with 2 arguments")
+    assert isinstance(argument, LambdaExpression), (
+        "`" + str(argument) + "` must be a lambda expression"
+    )
+
+    new_argument = ApplicationExpression(
+        argument, VariableExpression(function.variable)
+    ).simplify()
+    new_term = ApplicationExpression(function.term, new_argument).simplify()
+
+    return LambdaExpression(function.variable, new_term)