Refactor error messages to remove hardcoded strings (#10729)

* Use custom error msg instead of hardcoded string: replaced remaining hardcoded error message strings.

* Use custom error msg instead of hardcoded string: fixing faulty Errors import.

spacy/errors.py

@@ -905,7 +905,15 @@ class Errors(metaclass=ErrorsWithCodes):
     E1026 = ("Edit tree has an invalid format:\n{errors}")
     E1027 = ("AlignmentArray only supports slicing with a step of 1.")
     E1028 = ("AlignmentArray only supports indexing using an int or a slice.")
-    
+    E1029 = ("Edit tree cannot be applied to form.")
+    E1030 = ("Edit tree identifier out of range.")
+    E1031 = ("Could not find gold transition - see logs above.")
+    E1032 = ("`{var}` should not be {forbidden}, but received {value}.")
+    E1033 = ("Dimension {name} invalid -- only nO, nF, nP")
+    E1034 = ("Node index {i} out of bounds ({length})")
+    E1035 = ("Token index {i} out of bounds ({length})")
+    E1036 = ("Cannot index into NoneNode")
+
 
 # Deprecated model shortcuts, only used in errors and warnings
 OLD_MODEL_SHORTCUTS = {

spacy/ml/parser_model.pyx

@@ -11,6 +11,7 @@ import numpy.random
 from thinc.api import Model, CupyOps, NumpyOps
 
 from .. import util
+from ..errors import Errors
 from ..typedefs cimport weight_t, class_t, hash_t
 from ..pipeline._parser_internals.stateclass cimport StateClass
 
@@ -411,7 +412,7 @@ cdef class precompute_hiddens:
         elif name == "nO":
             return self.nO
         else:
-            raise ValueError(f"Dimension {name} invalid -- only nO, nF, nP")
+            raise ValueError(Errors.E1033.format(name=name))
 
     def set_dim(self, name, value):
         if name == "nF":
@@ -421,7 +422,7 @@ cdef class precompute_hiddens:
         elif name == "nO":
             self.nO = value
         else:
-            raise ValueError(f"Dimension {name} invalid -- only nO, nF, nP")
+            raise ValueError(Errors.E1033.format(name=name))
 
     def __call__(self, X, bint is_train):
         if is_train:

spacy/pipeline/_edit_tree_internals/edit_trees.pyx

@@ -132,7 +132,7 @@ cdef class EditTrees:
             could not be applied to the form.
         """
         if tree_id >= self.trees.size():
-            raise IndexError("Edit tree identifier out of range")
+            raise IndexError(Errors.E1030)
 
         lemma_pieces = []
         try:
@@ -154,7 +154,7 @@ cdef class EditTrees:
             match_node = tree.inner.match_node
 
             if match_node.prefix_len + match_node.suffix_len > len(form_part):
-                raise ValueError("Edit tree cannot be applied to form")
+                raise ValueError(Errors.E1029)
 
             suffix_start = len(form_part) - match_node.suffix_len
 
@@ -169,7 +169,7 @@ cdef class EditTrees:
             if form_part == self.strings[tree.inner.subst_node.orig]:
                 lemma_pieces.append(self.strings[tree.inner.subst_node.subst])
             else:
-                raise ValueError("Edit tree cannot be applied to form")
+                raise ValueError(Errors.E1029)
 
     cpdef unicode tree_to_str(self, uint32_t tree_id):
         """Return the tree as a string. The tree tree string is formatted
@@ -187,7 +187,7 @@ cdef class EditTrees:
         """
 
         if tree_id >= self.trees.size():
-            raise IndexError("Edit tree identifier out of range")
+            raise IndexError(Errors.E1030)
 
         cdef EditTreeC tree = self.trees[tree_id]
         cdef SubstNodeC subst_node

spacy/pipeline/_parser_internals/arc_eager.pyx

@@ -824,7 +824,7 @@ cdef class ArcEager(TransitionSystem):
             for i in range(self.n_moves):
                 print(self.get_class_name(i), is_valid[i], costs[i])
             print("Gold sent starts?", is_sent_start(&gold_state, state.B(0)), is_sent_start(&gold_state, state.B(1)))
-            raise ValueError("Could not find gold transition - see logs above.")
+            raise ValueError(Errors.E1031)
 
     def get_oracle_sequence_from_state(self, StateClass state, ArcEagerGold gold, _debug=None):
         cdef int i

spacy/tokens/graph.pyx

@@ -9,6 +9,8 @@ cimport cython
 import weakref
 from preshed.maps cimport map_get_unless_missing
 from murmurhash.mrmr cimport hash64
+
+from .. import Errors
 from ..typedefs cimport hash_t
 from ..strings import get_string_id
 from ..structs cimport EdgeC, GraphC
@@ -68,7 +70,7 @@ cdef class Node:
         """
         cdef int length = graph.c.nodes.size()
         if i >= length or -i >= length:
-            raise IndexError(f"Node index {i} out of bounds ({length})")
+            raise IndexError(Errors.E1034.format(i=i, length=length))
         if i < 0:
             i += length
         self.graph = graph
@@ -88,7 +90,7 @@ cdef class Node:
         """Get a token index from the node's set of tokens."""
         length = self.graph.c.nodes[self.i].size()
         if i >= length or -i >= length:
-            raise IndexError(f"Token index {i} out of bounds ({length})")
+            raise IndexError(Errors.E1035.format(i=i, length=length))
         if i < 0:
             i += length
         return self.graph.c.nodes[self.i][i]
@@ -306,7 +308,7 @@ cdef class NoneNode(Node):
         self.i = -1
 
     def __getitem__(self, int i):
-        raise IndexError("Cannot index into NoneNode.")
+        raise IndexError(Errors.E1036)
 
     def __len__(self):
         return 0

spacy/tokens/span.pyx

@@ -730,7 +730,7 @@ cdef class Span:
 
         def __set__(self, int start):
             if start < 0:
-                raise IndexError("TODO")
+                raise IndexError(Errors.E1032.format(var="start", forbidden="< 0", value=start))
             self.c.start = start
 
     property end:
@@ -739,7 +739,7 @@ cdef class Span:
 
         def __set__(self, int end):
             if end < 0:
-                raise IndexError("TODO")
+                raise IndexError(Errors.E1032.format(var="end", forbidden="< 0", value=end))
             self.c.end = end
 
     property start_char:
@@ -748,7 +748,7 @@ cdef class Span:
 
         def __set__(self, int start_char):
             if start_char < 0:
-                raise IndexError("TODO")
+                raise IndexError(Errors.E1032.format(var="start_char", forbidden="< 0", value=start_char))
             self.c.start_char = start_char
 
     property end_char:
@@ -757,7 +757,7 @@ cdef class Span:
 
         def __set__(self, int end_char):
             if end_char < 0:
-                raise IndexError("TODO")
+                raise IndexError(Errors.E1032.format(var="end_char", forbidden="< 0", value=end_char))
             self.c.end_char = end_char
 
     property label: