Intify IOB (#9738)

* added iob to int

* added tests

* added iob strings

* added error

* blacked attrs

* Update spacy/tests/lang/test_attrs.py

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update spacy/attrs.pyx

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* added iob strings as global

* minor refinement with iob

* removed iob strings from token

* changed to uppercase

* cleaned and went back to master version

* imported iob from attrs

* Update and format errors

* Support and test both str and int ENT_IOB key

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

spacy/attrs.pyx

@@ -1,3 +1,6 @@
+from .errors import Errors
+
+IOB_STRINGS = ("", "I", "O", "B")
 
 IDS = {
     "": NULL_ATTR,
@@ -64,7 +67,6 @@ IDS = {
     "FLAG61": FLAG61,
     "FLAG62": FLAG62,
     "FLAG63": FLAG63,
-
     "ID": ID,
     "ORTH": ORTH,
     "LOWER": LOWER,
@@ -72,7 +74,6 @@ IDS = {
     "SHAPE": SHAPE,
     "PREFIX": PREFIX,
     "SUFFIX": SUFFIX,
-
     "LENGTH": LENGTH,
     "LEMMA": LEMMA,
     "POS": POS,
@@ -87,7 +88,7 @@ IDS = {
     "SPACY": SPACY,
     "LANG": LANG,
     "MORPH": MORPH,
-    "IDX": IDX
+    "IDX": IDX,
 }
 
 
@@ -109,28 +110,66 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
     """
     inty_attrs = {}
     if _do_deprecated:
-        if 'F' in stringy_attrs:
+        if "F" in stringy_attrs:
             stringy_attrs["ORTH"] = stringy_attrs.pop("F")
-        if 'L' in stringy_attrs:
+        if "L" in stringy_attrs:
             stringy_attrs["LEMMA"] = stringy_attrs.pop("L")
-        if 'pos' in stringy_attrs:
+        if "pos" in stringy_attrs:
             stringy_attrs["TAG"] = stringy_attrs.pop("pos")
-        if 'morph' in stringy_attrs:
+        if "morph" in stringy_attrs:
-            morphs = stringy_attrs.pop('morph')
+            morphs = stringy_attrs.pop("morph")
-        if 'number' in stringy_attrs:
+        if "number" in stringy_attrs:
-            stringy_attrs.pop('number')
+            stringy_attrs.pop("number")
-        if 'tenspect' in stringy_attrs:
+        if "tenspect" in stringy_attrs:
-            stringy_attrs.pop('tenspect')
+            stringy_attrs.pop("tenspect")
         morph_keys = [
-            'PunctType', 'PunctSide', 'Other', 'Degree', 'AdvType', 'Number',
+            "PunctType",
-            'VerbForm', 'PronType', 'Aspect', 'Tense', 'PartType', 'Poss',
+            "PunctSide",
-            'Hyph', 'ConjType', 'NumType', 'Foreign', 'VerbType', 'NounType',
+            "Other",
-            'Gender', 'Mood', 'Negative', 'Tense', 'Voice', 'Abbr',
+            "Degree",
-            'Derivation', 'Echo', 'Foreign', 'NameType', 'NounType', 'NumForm',
+            "AdvType",
-            'NumValue', 'PartType', 'Polite', 'StyleVariant',
+            "Number",
-            'PronType', 'AdjType', 'Person', 'Variant', 'AdpType',
+            "VerbForm",
-            'Reflex', 'Negative', 'Mood', 'Aspect', 'Case',
+            "PronType",
-            'Polarity', 'PrepCase', 'Animacy' # U20
+            "Aspect",
+            "Tense",
+            "PartType",
+            "Poss",
+            "Hyph",
+            "ConjType",
+            "NumType",
+            "Foreign",
+            "VerbType",
+            "NounType",
+            "Gender",
+            "Mood",
+            "Negative",
+            "Tense",
+            "Voice",
+            "Abbr",
+            "Derivation",
+            "Echo",
+            "Foreign",
+            "NameType",
+            "NounType",
+            "NumForm",
+            "NumValue",
+            "PartType",
+            "Polite",
+            "StyleVariant",
+            "PronType",
+            "AdjType",
+            "Person",
+            "Variant",
+            "AdpType",
+            "Reflex",
+            "Negative",
+            "Mood",
+            "Aspect",
+            "Case",
+            "Polarity",
+            "PrepCase",
+            "Animacy",  # U20
         ]
         for key in morph_keys:
             if key in stringy_attrs:
@@ -142,8 +181,13 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
     for name, value in stringy_attrs.items():
         int_key = intify_attr(name)
         if int_key is not None:
+            if int_key == ENT_IOB:
+                if value in IOB_STRINGS:
+                    value = IOB_STRINGS.index(value)
+                elif isinstance(value, str):
+                    raise ValueError(Errors.E1025.format(value=value))
             if strings_map is not None and isinstance(value, str):
-                if hasattr(strings_map, 'add'):
+                if hasattr(strings_map, "add"):
                     value = strings_map.add(value)
                 else:
                     value = strings_map[value]

spacy/errors.py

@@ -888,11 +888,14 @@ class Errors(metaclass=ErrorsWithCodes):
     E1021 = ("`pos` value \"{pp}\" is not a valid Universal Dependencies tag. "
              "Non-UD tags should use the `tag` property.")
     E1022 = ("Words must be of type str or int, but input is of type '{wtype}'")
-    E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't exist.")
+    E1023 = ("Couldn't read EntityRuler from the {path}. This file doesn't "
-    E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler patterns.")
+             "exist.")
+    E1024 = ("A pattern with ID \"{ent_id}\" is not present in EntityRuler "
+             "patterns.")
+    E1025 = ("Cannot intify the value '{value}' as an IOB string. The only "
+             "supported values are: 'I', 'O', 'B' and ''")
     
 
-
 # Deprecated model shortcuts, only used in errors and warnings
 OLD_MODEL_SHORTCUTS = {
     "en": "en_core_web_sm", "de": "de_core_news_sm", "es": "es_core_news_sm",

spacy/tests/lang/test_attrs.py

@@ -1,4 +1,5 @@
 import pytest
+from spacy.attrs import intify_attrs, ENT_IOB
 
 from spacy.attrs import IS_ALPHA, LEMMA, NORM, ORTH, intify_attrs
 from spacy.lang.en.stop_words import STOP_WORDS
@@ -33,6 +34,38 @@ def test_attrs_do_deprecated(text):
     assert int_attrs == {ORTH: 10, IS_ALPHA: True}
 
 
+def test_attrs_ent_iob_intify():
+    int_attrs = intify_attrs({"ENT_IOB": ""})
+    assert int_attrs == {ENT_IOB: 0}
+
+    int_attrs = intify_attrs({"ENT_IOB": "I"})
+    assert int_attrs == {ENT_IOB: 1}
+
+    int_attrs = intify_attrs({"ENT_IOB": "O"})
+    assert int_attrs == {ENT_IOB: 2}
+
+    int_attrs = intify_attrs({"ENT_IOB": "B"})
+    assert int_attrs == {ENT_IOB: 3}
+
+    int_attrs = intify_attrs({ENT_IOB: ""})
+    assert int_attrs == {ENT_IOB: 0}
+
+    int_attrs = intify_attrs({ENT_IOB: "I"})
+    assert int_attrs == {ENT_IOB: 1}
+
+    int_attrs = intify_attrs({ENT_IOB: "O"})
+    assert int_attrs == {ENT_IOB: 2}
+
+    int_attrs = intify_attrs({ENT_IOB: "B"})
+    assert int_attrs == {ENT_IOB: 3}
+
+    with pytest.raises(ValueError):
+        int_attrs = intify_attrs({"ENT_IOB": "XX"})
+
+    with pytest.raises(ValueError):
+        int_attrs = intify_attrs({ENT_IOB: "XX"})
+
+
 @pytest.mark.parametrize("text,match", [(",", True), (" ", False), ("a", False)])
 def test_lex_attrs_is_punct(text, match):
     assert is_punct(text) == match

spacy/tokens/token.pyx

@@ -20,6 +20,7 @@ from .doc cimport set_children_from_heads
 
 from .. import parts_of_speech
 from ..errors import Errors, Warnings
+from ..attrs import IOB_STRINGS
 from .underscore import Underscore, get_ext_args
 
 
@@ -745,7 +746,7 @@ cdef class Token:
 
     @classmethod
     def iob_strings(cls):
-        return ("", "I", "O", "B")
+        return IOB_STRINGS
 
     @property
     def ent_iob_(self):