From d757dec5c4fc7618dac7a7831504f7611ff75eb4 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Wed, 17 Aug 2022 12:13:54 +0200
Subject: [PATCH] Remove intify_attrs(_do_deprecated) (#11319)

---
 spacy/attrs.pyx                | 71 +---------------------------------
 spacy/tests/lang/test_attrs.py |  8 ----
 spacy/tokenizer.pyx            |  4 +-
 spacy/vocab.pyx                |  3 +-
 4 files changed, 4 insertions(+), 82 deletions(-)

diff --git a/spacy/attrs.pyx b/spacy/attrs.pyx
index dc8eed7c3..7b6fd9e94 100644
--- a/spacy/attrs.pyx
+++ b/spacy/attrs.pyx
@@ -97,7 +97,7 @@ NAMES = [key for key, value in sorted(IDS.items(), key=lambda item: item[1])]
 locals().update(IDS)
 
 
-def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
+def intify_attrs(stringy_attrs, strings_map=None):
     """
     Normalize a dictionary of attributes, converting them to ints.
 
@@ -109,75 +109,6 @@ def intify_attrs(stringy_attrs, strings_map=None, _do_deprecated=False):
         converted to ints.
     """
     inty_attrs = {}
-    if _do_deprecated:
-        if "F" in stringy_attrs:
-            stringy_attrs["ORTH"] = stringy_attrs.pop("F")
-        if "L" in stringy_attrs:
-            stringy_attrs["LEMMA"] = stringy_attrs.pop("L")
-        if "pos" in stringy_attrs:
-            stringy_attrs["TAG"] = stringy_attrs.pop("pos")
-        if "morph" in stringy_attrs:
-            morphs = stringy_attrs.pop("morph")
-        if "number" in stringy_attrs:
-            stringy_attrs.pop("number")
-        if "tenspect" in stringy_attrs:
-            stringy_attrs.pop("tenspect")
-        morph_keys = [
-            "PunctType",
-            "PunctSide",
-            "Other",
-            "Degree",
-            "AdvType",
-            "Number",
-            "VerbForm",
-            "PronType",
-            "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:
-                stringy_attrs.pop(key)
-            elif key.lower() in stringy_attrs:
-                stringy_attrs.pop(key.lower())
-            elif key.upper() in stringy_attrs:
-                stringy_attrs.pop(key.upper())
     for name, value in stringy_attrs.items():
         int_key = intify_attr(name)
         if int_key is not None:
diff --git a/spacy/tests/lang/test_attrs.py b/spacy/tests/lang/test_attrs.py
index 1c27c1744..1e1bae08c 100644
--- a/spacy/tests/lang/test_attrs.py
+++ b/spacy/tests/lang/test_attrs.py
@@ -26,14 +26,6 @@ def test_attrs_idempotence(text):
     assert intify_attrs(int_attrs) == {LEMMA: 10, IS_ALPHA: True}
 
 
-@pytest.mark.parametrize("text", ["dog"])
-def test_attrs_do_deprecated(text):
-    int_attrs = intify_attrs(
-        {"F": text, "is_alpha": True}, strings_map={text: 10}, _do_deprecated=True
-    )
-    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}
diff --git a/spacy/tokenizer.pyx b/spacy/tokenizer.pyx
index 0e75b5f7a..972633a2f 100644
--- a/spacy/tokenizer.pyx
+++ b/spacy/tokenizer.pyx
@@ -582,7 +582,7 @@ cdef class Tokenizer:
         substrings (iterable): A sequence of dicts, where each dict describes
             a token and its attributes.
         """
-        attrs = [intify_attrs(spec, _do_deprecated=True) for spec in substrings]
+        attrs = [intify_attrs(spec) for spec in substrings]
         orth = "".join([spec[ORTH] for spec in attrs])
         if chunk != orth:
             raise ValueError(Errors.E997.format(chunk=chunk, orth=orth, token_attrs=substrings))
@@ -650,7 +650,7 @@ cdef class Tokenizer:
             url_match = re.compile("a^").match
         special_cases = {}
         for orth, special_tokens in self.rules.items():
-            special_cases[orth] = [intify_attrs(special_token, strings_map=self.vocab.strings, _do_deprecated=True) for special_token in special_tokens]
+            special_cases[orth] = [intify_attrs(special_token, strings_map=self.vocab.strings) for special_token in special_tokens]
         tokens = []
         for substring in text.split():
             suffixes = []
diff --git a/spacy/vocab.pyx b/spacy/vocab.pyx
index 428cadd82..af7d97933 100644
--- a/spacy/vocab.pyx
+++ b/spacy/vocab.pyx
@@ -268,8 +268,7 @@ cdef class Vocab:
         cdef int i
         tokens = <TokenC*>self.mem.alloc(len(substrings) + 1, sizeof(TokenC))
         for i, props in enumerate(substrings):
-            props = intify_attrs(props, strings_map=self.strings,
-                                 _do_deprecated=True)
+            props = intify_attrs(props, strings_map=self.strings)
             token = &tokens[i]
             # Set the special tokens up to have arbitrary attributes
             lex = <LexemeC*>self.get_by_orth(self.mem, props[ORTH])