Update Catalan language data (#8308)

* Update Catalan language data

Update Catalan language data based on contributions from the Text Mining
Unit at the Barcelona Supercomputing Center:

https://github.com/TeMU-BSC/spacy4release/tree/main/lang_data

* Update tokenizer settings for UD Catalan AnCora

Update for UD Catalan AnCora v2.7 with merged multi-word tokens.

* Update test

* Move prefix patternt to more generic infix pattern

* Clean up

setup.cfg

@@ -65,7 +65,7 @@ console_scripts =
 
 [options.extras_require]
 lookups =
-    spacy_lookups_data>=1.0.0,<1.1.0
+    spacy_lookups_data>=1.0.1,<1.1.0
 transformers =
     spacy_transformers>=1.0.1,<1.1.0
 ray =

spacy/lang/ca/__init__.py

@@ -1,15 +1,23 @@
+from typing import Optional
+
+from thinc.api import Model
+
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
-from .punctuation import TOKENIZER_INFIXES
+from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
+from .syntax_iterators import SYNTAX_ITERATORS
 from ...language import Language
+from .lemmatizer import CatalanLemmatizer
 
 
 class CatalanDefaults(Language.Defaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
     infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
     stop_words = STOP_WORDS
     lex_attr_getters = LEX_ATTRS
+    syntax_iterators = SYNTAX_ITERATORS
 
 
 class Catalan(Language):
@@ -17,4 +25,16 @@ class Catalan(Language):
     Defaults = CatalanDefaults
 
 
+@Catalan.factory(
+    "lemmatizer",
+    assigns=["token.lemma"],
+    default_config={"model": None, "mode": "rule", "overwrite": False},
+    default_score_weights={"lemma_acc": 1.0},
+)
+def make_lemmatizer(
+    nlp: Language, model: Optional[Model], name: str, mode: str, overwrite: bool
+):
+    return CatalanLemmatizer(nlp.vocab, model, name, mode=mode, overwrite=overwrite)
+
+
 __all__ = ["Catalan"]

spacy/lang/ca/lemmatizer.py

@@ -0,0 +1,81 @@
+from typing import List, Tuple
+
+from ...pipeline import Lemmatizer
+from ...tokens import Token
+
+
+class CatalanLemmatizer(Lemmatizer):
+    """
+    Copied from French Lemmatizer
+    Catalan language lemmatizer applies the default rule based lemmatization
+    procedure with some modifications for better Catalan language support.
+
+    The parts of speech 'ADV', 'PRON', 'DET', 'ADP' and 'AUX' are added to use
+    the rule-based lemmatization. As a last resort, the lemmatizer checks in
+    the lookup table.
+    """
+
+    @classmethod
+    def get_lookups_config(cls, mode: str) -> Tuple[List[str], List[str]]:
+        if mode == "rule":
+            required = ["lemma_lookup", "lemma_rules", "lemma_exc", "lemma_index"]
+            return (required, [])
+        else:
+            return super().get_lookups_config(mode)
+
+    def rule_lemmatize(self, token: Token) -> List[str]:
+        cache_key = (token.orth, token.pos)
+        if cache_key in self.cache:
+            return self.cache[cache_key]
+        string = token.text
+        univ_pos = token.pos_.lower()
+        if univ_pos in ("", "eol", "space"):
+            return [string.lower()]
+        elif "lemma_rules" not in self.lookups or univ_pos not in (
+            "noun",
+            "verb",
+            "adj",
+            "adp",
+            "adv",
+            "aux",
+            "cconj",
+            "det",
+            "pron",
+            "punct",
+            "sconj",
+        ):
+            return self.lookup_lemmatize(token)
+        index_table = self.lookups.get_table("lemma_index", {})
+        exc_table = self.lookups.get_table("lemma_exc", {})
+        rules_table = self.lookups.get_table("lemma_rules", {})
+        lookup_table = self.lookups.get_table("lemma_lookup", {})
+        index = index_table.get(univ_pos, {})
+        exceptions = exc_table.get(univ_pos, {})
+        rules = rules_table.get(univ_pos, [])
+        string = string.lower()
+        forms = []
+        if string in index:
+            forms.append(string)
+            self.cache[cache_key] = forms
+            return forms
+        forms.extend(exceptions.get(string, []))
+        oov_forms = []
+        if not forms:
+            for old, new in rules:
+                if string.endswith(old):
+                    form = string[: len(string) - len(old)] + new
+                    if not form:
+                        pass
+                    elif form in index or not form.isalpha():
+                        forms.append(form)
+                    else:
+                        oov_forms.append(form)
+        if not forms:
+            forms.extend(oov_forms)
+        if not forms and string in lookup_table.keys():
+            forms.append(self.lookup_lemmatize(token)[0])
+        if not forms:
+            forms.append(string)
+        forms = list(set(forms))
+        self.cache[cache_key] = forms
+        return forms

spacy/lang/ca/punctuation.py

@@ -1,12 +1,46 @@
-from ..punctuation import TOKENIZER_INFIXES
-from ..char_classes import ALPHA
+from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
+from ..char_classes import CURRENCY
+from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
+from ..char_classes import merge_chars, _units
 
 
 ELISION = " ' ’ ".strip().replace(" ", "").replace("\n", "")
 
 
-_infixes = TOKENIZER_INFIXES + [
-    r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION)
+_infixes = (
+    LIST_ELLIPSES
+    + LIST_ICONS
+    + [
+        r"(?<=[0-9])[+\-\*^](?=[0-9-])",
+        r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
+            al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
+        ),
+        r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
+        r"(?<=[{a}][{el}])(?=[{a}0-9])".format(a=ALPHA, el=ELISION),
     ]
+)
+
+_units = _units.replace("% ", "")
+UNITS = merge_chars(_units)
+
+_suffixes = (
+    LIST_PUNCT
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_ICONS
+    + [r"-", "—", "–"]
+    + [
+        r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
+        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
+        r"(?<=[0-9])(?:{u})".format(u=UNITS),
+        r"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(
+            al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
+        ),
+        r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
+    ]
+)
 
 TOKENIZER_INFIXES = _infixes
+TOKENIZER_SUFFIXES = _suffixes

spacy/lang/ca/syntax_iterators.py

@@ -0,0 +1,46 @@
+from ...symbols import NOUN, PROPN
+from ...errors import Errors
+
+
+def noun_chunks(doclike):
+    """Detect base noun phrases from a dependency parse. Works on Doc and Span."""
+    # fmt: off
+    labels = ["nsubj", "nsubj:pass", "obj", "obl", "iobj", "ROOT", "appos", "nmod", "nmod:poss"]
+    # fmt: on
+    doc = doclike.doc  # Ensure works on both Doc and Span.
+    if not doc.has_annotation("DEP"):
+        raise ValueError(Errors.E029)
+    np_deps = [doc.vocab.strings[label] for label in labels]
+    np_label = doc.vocab.strings.add("NP")
+    prev_end = -1
+    for i, word in enumerate(doclike):
+        if word.pos not in (NOUN, PROPN):
+            continue
+        # Prevent nested chunks from being produced
+        if word.left_edge.i <= prev_end:
+            continue
+        if word.dep in np_deps:
+            left = word.left_edge.i
+            right = word.right_edge.i + 1
+            # leave prepositions and punctuation out of the left side of the chunk
+            if word.left_edge.pos_ == "ADP" or word.left_edge.pos_ == "PUNCT":
+                left = word.left_edge.i + 1
+            prev_end = word.right_edge.i
+            # leave subordinated clauses and appositions out of the chunk
+            a = word.i + 1
+            while a < word.right_edge.i:
+                paraula = doc[a]
+                if paraula.pos_ == "VERB":
+                    right = paraula.left_edge.i
+                    prev_end = paraula.left_edge.i - 1
+                elif paraula.dep_ == "appos":
+                    right = paraula.left_edge.i + 1
+                    prev_end = paraula.left_edge.i - 1
+                a += 1
+            # leave punctuation out of the right side of the chunk
+            if word.right_edge.pos_ == "PUNCT":
+                right = right - 1
+            yield left, right, np_label
+
+
+SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}

spacy/lang/ca/tokenizer_exceptions.py

@@ -24,6 +24,13 @@ for exc_data in [
     {ORTH: "núm", NORM: "número"},
     {ORTH: "St.", NORM: "sant"},
     {ORTH: "Sta.", NORM: "santa"},
+    {ORTH: "'l"},
+    {ORTH: "'ls"},
+    {ORTH: "'m"},
+    {ORTH: "'n"},
+    {ORTH: "'ns"},
+    {ORTH: "'s"},
+    {ORTH: "'t"},
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 

spacy/tests/lang/ca/test_text.py

@@ -12,13 +12,13 @@ def test_ca_tokenizer_handles_long_text(ca_tokenizer):
     una gerra de cervesa. Ens asseiem -fotògraf i periodista- en una terrassa buida."""
 
     tokens = ca_tokenizer(text)
-    assert len(tokens) == 138
+    assert len(tokens) == 140
 
 
 @pytest.mark.parametrize(
     "text,length",
     [
-        ("Perquè va anar-hi?", 6),
+        ("Perquè va anar-hi?", 4),
         ("“Ah no?”", 5),
         ("""Sí! "Anem", va contestar el Joan Carles""", 11),
         ("Van córrer aprox. 10km", 5),

spacy/tests/lang/test_lemmatizers.py

@@ -8,7 +8,7 @@ from spacy.util import get_lang_class
 # Only include languages with no external dependencies
 # excluded: ru, uk
 # excluded for custom tables: es, pl
-LANGUAGES = ["bn", "el", "en", "fa", "fr", "nb", "nl", "sv"]
+LANGUAGES = ["bn", "ca", "el", "en", "fa", "fr", "nb", "nl", "sv"]
 # fmt: on