Prevent 0-length mem alloc (#6653)

* prevent 0-length mem alloc by adding asserts

* fix lexeme mem allocation

spacy/morphology.pyx

@@ -133,8 +133,9 @@ cdef class Morphology:
         """
         cdef MorphAnalysisC tag
         tag.length = len(field_feature_pairs)
-        tag.fields = <attr_t*>self.mem.alloc(tag.length, sizeof(attr_t))
-        tag.features = <attr_t*>self.mem.alloc(tag.length, sizeof(attr_t))
+        if tag.length > 0:
+            tag.fields = <attr_t*>self.mem.alloc(tag.length, sizeof(attr_t))
+            tag.features = <attr_t*>self.mem.alloc(tag.length, sizeof(attr_t))
         for i, (field, feature) in enumerate(field_feature_pairs):
             tag.fields[i] = field
             tag.features[i] = feature

spacy/pipeline/_parser_internals/arc_eager.pyx

@@ -65,6 +65,7 @@ cdef GoldParseStateC create_gold_state(Pool mem, const StateC* state,
     cdef GoldParseStateC gs
     gs.length = len(heads)
     gs.stride = 1
+    assert gs.length > 0
     gs.labels = <attr_t*>mem.alloc(gs.length, sizeof(gs.labels[0]))
     gs.heads = <int32_t*>mem.alloc(gs.length, sizeof(gs.heads[0]))
     gs.n_kids = <int32_t*>mem.alloc(gs.length, sizeof(gs.n_kids[0]))
@@ -126,6 +127,7 @@ cdef GoldParseStateC create_gold_state(Pool mem, const StateC* state,
                 1
             )
     # Make an array of pointers, pointing into the gs_kids_flat array.
+    assert gs.length > 0
     gs.kids = <int32_t**>mem.alloc(gs.length, sizeof(int32_t*))
     for i in range(gs.length):
         if gs.n_kids[i] != 0:

spacy/pipeline/_parser_internals/ner.pyx

@@ -63,6 +63,7 @@ cdef GoldNERStateC create_gold_state(
     Example example
 ) except *:
     cdef GoldNERStateC gs
+    assert example.x.length > 0
     gs.ner = <Transition*>mem.alloc(example.x.length, sizeof(Transition))
     ner_tags = example.get_aligned_ner()
     for i, ner_tag in enumerate(ner_tags):

spacy/tokenizer.pyx

@@ -258,6 +258,7 @@ cdef class Tokenizer:
             tokens = doc.c
         # Otherwise create a separate array to store modified tokens
         else:
+            assert max_length > 0
             tokens = <TokenC*>mem.alloc(max_length, sizeof(TokenC))
         # Modify tokenization according to filtered special cases
         offset = self._retokenize_special_spans(doc, tokens, span_data)

spacy/tokens/doc.pyx

@@ -225,6 +225,7 @@ cdef class Doc:
         # Guarantee self.lex[i-x], for any i >= 0 and x < padding is in bounds
         # However, we need to remember the true starting places, so that we can
         # realloc.
+        assert size + (PADDING*2) > 0
         data_start = <TokenC*>self.mem.alloc(size + (PADDING*2), sizeof(TokenC))
         cdef int i
         for i in range(size + (PADDING*2)):
@@ -1177,6 +1178,7 @@ cdef class Doc:
         other.length = self.length
         other.max_length = self.max_length
         buff_size = other.max_length + (PADDING*2)
+        assert buff_size > 0
         tokens = <TokenC*>other.mem.alloc(buff_size, sizeof(TokenC))
         memcpy(tokens, self.c - PADDING, buff_size * sizeof(TokenC))
         other.c = &tokens[PADDING]

spacy/vocab.pyx

@@ -164,7 +164,7 @@ cdef class Vocab:
         if len(string) < 3 or self.length < 10000:
             mem = self.mem
         cdef bint is_oov = mem is not self.mem
-        lex = <LexemeC*>mem.alloc(sizeof(LexemeC), 1)
+        lex = <LexemeC*>mem.alloc(1, sizeof(LexemeC))
         lex.orth = self.strings.add(string)
         lex.length = len(string)
         if self.vectors is not None: