spacy 3.5.3__tar.gz → 3.6.0.dev1__tar.gz

{spacy-3.5.3/spacy.egg-info → spacy-3.6.0.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacy
-Version: 3.5.3
+Version: 3.6.0.dev1
 Summary: Industrial-strength Natural Language Processing (NLP) in Python
 Home-page: https://spacy.io
 Author: Explosion
@@ -91,19 +91,20 @@ open-source software, released under the [MIT license](https://github.com/explos
 
 ## 📖 Documentation
 
-| Documentation                                                                                                                                                                                                             |                                                                                                                                                                                                                                                                                                                              |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ⭐️ **[spaCy 101]**                                                                                                                                                                                                       | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                                            |
-| 📚 **[Usage Guides]**                                                                                                                                                                                                     | How to use spaCy and its features.                                                                                                                                                                                                                                                                                           |
-| 🚀 **[New in v3.0]**                                                                                                                                                                                                      | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                                               |
-| 🪐 **[Project Templates]**                                                                                                                                                                                                | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                                          |
-| 🎛 **[API Reference]**                                                                                                                                                                                                     | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                                                      |
-| 📦 **[Models]**                                                                                                                                                                                                           | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                                        |
-| 🌌 **[Universe]**                                                                                                                                                                                                         | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                                               |
-| 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                      |
-| 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                    |
-| 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                 |
-| 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                        |
+| Documentation                 |                                                                        |
+| ----------------------------- | ---------------------------------------------------------------------- |
+| ⭐️ **[spaCy 101]**           | New to spaCy? Here's everything you need to know!                      |
+| 📚 **[Usage Guides]**         | How to use spaCy and its features.                                     |
+| 🚀 **[New in v3.0]**          | New features, backwards incompatibilities and migration guide.         |
+| 🪐 **[Project Templates]**    | End-to-end workflows you can clone, modify and run.                    |
+| 🎛 **[API Reference]**         | The detailed reference for spaCy's API.                                |
+| 📦 **[Models]**               | Download trained pipelines for spaCy.                                  |
+| 🌌 **[Universe]**             | Plugins, extensions, demos and books from the spaCy ecosystem.         |
+| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
+| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
+| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
+| 🛠 **[Changelog]** | Changes and version history. |
+| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
 | <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
 | <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
 
@@ -113,13 +114,13 @@ open-source software, released under the [MIT license](https://github.com/explos
 [api reference]: https://spacy.io/api/
 [models]: https://spacy.io/models
 [universe]: https://spacy.io/universe
+[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode
 [videos]: https://www.youtube.com/c/ExplosionAI
 [online course]: https://course.spacy.io
 [project templates]: https://github.com/explosion/projects
 [changelog]: https://spacy.io/usage#changelog
 [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
 
-
 ## 💬 Where to ask questions
 
 The spaCy project is maintained by the [spaCy team](https://explosion.ai/about).

{spacy-3.5.3 → spacy-3.6.0.dev1}/README.md

@@ -35,19 +35,20 @@ open-source software, released under the [MIT license](https://github.com/explos
 
 ## 📖 Documentation
 
-| Documentation                                                                                                                                                                                                             |                                                                                                                                                                                                                                                                                                                              |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| ⭐️ **[spaCy 101]**                                                                                                                                                                                                       | New to spaCy? Here's everything you need to know!                                                                                                                                                                                                                                                                            |
-| 📚 **[Usage Guides]**                                                                                                                                                                                                     | How to use spaCy and its features.                                                                                                                                                                                                                                                                                           |
-| 🚀 **[New in v3.0]**                                                                                                                                                                                                      | New features, backwards incompatibilities and migration guide.                                                                                                                                                                                                                                                               |
-| 🪐 **[Project Templates]**                                                                                                                                                                                                | End-to-end workflows you can clone, modify and run.                                                                                                                                                                                                                                                                          |
-| 🎛 **[API Reference]**                                                                                                                                                                                                     | The detailed reference for spaCy's API.                                                                                                                                                                                                                                                                                      |
-| 📦 **[Models]**                                                                                                                                                                                                           | Download trained pipelines for spaCy.                                                                                                                                                                                                                                                                                        |
-| 🌌 **[Universe]**                                                                                                                                                                                                         | Plugins, extensions, demos and books from the spaCy ecosystem.                                                                                                                                                                                                                                                               |
-| 👩‍🏫 **[Online Course]**                                                                                                                                                                                                    | Learn spaCy in this free and interactive online course.                                                                                                                                                                                                                                                                      |
-| 📺 **[Videos]**                                                                                                                                                                                                           | Our YouTube channel with video tutorials, talks and more.                                                                                                                                                                                                                                                                    |
-| 🛠 **[Changelog]**                                                                                                                                                                                                         | Changes and version history.                                                                                                                                                                                                                                                                                                 |
-| 💝 **[Contribute]**                                                                                                                                                                                                       | How to contribute to the spaCy project and code base.                                                                                                                                                                                                                                                                        |
+| Documentation                 |                                                                        |
+| ----------------------------- | ---------------------------------------------------------------------- |
+| ⭐️ **[spaCy 101]**           | New to spaCy? Here's everything you need to know!                      |
+| 📚 **[Usage Guides]**         | How to use spaCy and its features.                                     |
+| 🚀 **[New in v3.0]**          | New features, backwards incompatibilities and migration guide.         |
+| 🪐 **[Project Templates]**    | End-to-end workflows you can clone, modify and run.                    |
+| 🎛 **[API Reference]**         | The detailed reference for spaCy's API.                                |
+| 📦 **[Models]**               | Download trained pipelines for spaCy.                                  |
+| 🌌 **[Universe]**             | Plugins, extensions, demos and books from the spaCy ecosystem.         |
+| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
+| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
+| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
+| 🛠 **[Changelog]** | Changes and version history. |
+| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
 | <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
 | <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
 
@@ -57,13 +58,13 @@ open-source software, released under the [MIT license](https://github.com/explos
 [api reference]: https://spacy.io/api/
 [models]: https://spacy.io/models
 [universe]: https://spacy.io/universe
+[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode
 [videos]: https://www.youtube.com/c/ExplosionAI
 [online course]: https://course.spacy.io
 [project templates]: https://github.com/explosion/projects
 [changelog]: https://spacy.io/usage#changelog
 [contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
 
-
 ## 💬 Where to ask questions
 
 The spaCy project is maintained by the [spaCy team](https://explosion.ai/about).

{spacy-3.5.3 → spacy-3.6.0.dev1}/setup.cfg

@@ -49,7 +49,7 @@ install_requires =
 	wasabi>=0.9.1,<1.2.0
 	srsly>=2.4.3,<3.0.0
 	catalogue>=2.0.6,<2.1.0
-	typer>=0.3.0,<0.8.0
+	typer>=0.3.0,<0.10.0
 	pathy>=0.10.0
 	smart-open>=5.2.1,<7.0.0
 	tqdm>=4.38.0,<5.0.0

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.5.3"
+__version__ = "3.6.0.dev1"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/cli/debug_data.py

@@ -7,6 +7,7 @@ import srsly
 from wasabi import Printer, MESSAGES, msg
 import typer
 import math
+import numpy
 
 from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides
 from ._util import import_code, debug_cli, _format_number
@@ -521,9 +522,13 @@ def debug_data(
 
     if "tagger" in factory_names:
         msg.divider("Part-of-speech Tagging")
-        label_list = [label for label in gold_train_data["tags"]]
-        model_labels = _get_labels_from_model(nlp, "tagger")
+        label_list, counts = zip(*gold_train_data["tags"].items())
         msg.info(f"{len(label_list)} label(s) in train data")
+        p = numpy.array(counts)
+        p = p / p.sum()
+        norm_entropy = (-p * numpy.log2(p)).sum() / numpy.log2(len(label_list))
+        msg.info(f"{norm_entropy} is the normalised label entropy")
+        model_labels = _get_labels_from_model(nlp, "tagger")
         labels = set(label_list)
         missing_labels = model_labels - labels
         if missing_labels:

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/cli/evaluate.py

@@ -27,6 +27,7 @@ def evaluate_cli(
     gold_preproc: bool = Opt(False, "--gold-preproc", "-G", help="Use gold preprocessing"),
     displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False),
     displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"),
+    per_component: bool = Opt(False, "--per-component", "-P", help="Return scores per component, only applicable when an output JSON file is specified."),
     # fmt: on
 ):
     """
@@ -50,6 +51,7 @@ def evaluate_cli(
         gold_preproc=gold_preproc,
         displacy_path=displacy_path,
         displacy_limit=displacy_limit,
+        per_component=per_component,
         silent=False,
     )
 
@@ -64,6 +66,7 @@ def evaluate(
     displacy_limit: int = 25,
     silent: bool = True,
     spans_key: str = "sc",
+    per_component: bool = False,
 ) -> Dict[str, Any]:
     msg = Printer(no_print=silent, pretty=not silent)
     fix_random_seed()
@@ -78,44 +81,53 @@ def evaluate(
     corpus = Corpus(data_path, gold_preproc=gold_preproc)
     nlp = util.load_model(model)
     dev_dataset = list(corpus(nlp))
-    scores = nlp.evaluate(dev_dataset)
-    metrics = {
-        "TOK": "token_acc",
-        "TAG": "tag_acc",
-        "POS": "pos_acc",
-        "MORPH": "morph_acc",
-        "LEMMA": "lemma_acc",
-        "UAS": "dep_uas",
-        "LAS": "dep_las",
-        "NER P": "ents_p",
-        "NER R": "ents_r",
-        "NER F": "ents_f",
-        "TEXTCAT": "cats_score",
-        "SENT P": "sents_p",
-        "SENT R": "sents_r",
-        "SENT F": "sents_f",
-        "SPAN P": f"spans_{spans_key}_p",
-        "SPAN R": f"spans_{spans_key}_r",
-        "SPAN F": f"spans_{spans_key}_f",
-        "SPEED": "speed",
-    }
-    results = {}
-    data = {}
-    for metric, key in metrics.items():
-        if key in scores:
-            if key == "cats_score":
-                metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
-            if isinstance(scores[key], (int, float)):
-                if key == "speed":
-                    results[metric] = f"{scores[key]:.0f}"
+    scores = nlp.evaluate(dev_dataset, per_component=per_component)
+    if per_component:
+        data = scores
+        if output is None:
+            msg.warn(
+                "The per-component option is enabled but there is no output JSON file provided to save the scores to."
+            )
+        else:
+            msg.info("Per-component scores will be saved to output JSON file.")
+    else:
+        metrics = {
+            "TOK": "token_acc",
+            "TAG": "tag_acc",
+            "POS": "pos_acc",
+            "MORPH": "morph_acc",
+            "LEMMA": "lemma_acc",
+            "UAS": "dep_uas",
+            "LAS": "dep_las",
+            "NER P": "ents_p",
+            "NER R": "ents_r",
+            "NER F": "ents_f",
+            "TEXTCAT": "cats_score",
+            "SENT P": "sents_p",
+            "SENT R": "sents_r",
+            "SENT F": "sents_f",
+            "SPAN P": f"spans_{spans_key}_p",
+            "SPAN R": f"spans_{spans_key}_r",
+            "SPAN F": f"spans_{spans_key}_f",
+            "SPEED": "speed",
+        }
+        results = {}
+        data = {}
+        for metric, key in metrics.items():
+            if key in scores:
+                if key == "cats_score":
+                    metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
+                if isinstance(scores[key], (int, float)):
+                    if key == "speed":
+                        results[metric] = f"{scores[key]:.0f}"
+                    else:
+                        results[metric] = f"{scores[key]*100:.2f}"
                 else:
-                    results[metric] = f"{scores[key]*100:.2f}"
-            else:
-                results[metric] = "-"
-            data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
+                    results[metric] = "-"
+                data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
 
-    msg.table(results, title="Results")
-    data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
+        msg.table(results, title="Results")
+        data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
 
     if displacy_path:
         factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names]

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/cli/templates/quickstart_training.jinja

@@ -3,7 +3,7 @@ the docs and the init config command. It encodes various best practices and
 can help generate the best possible configuration, given a user's requirements. #}
 {%- set use_transformer = hardware != "cpu" and transformer_data -%}
 {%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
-{%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "spancat", "spancat_singlelabel", "trainable_lemmatizer"] -%}
+{%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "span_finder", "spancat", "spancat_singlelabel", "trainable_lemmatizer"] -%}
 [paths]
 train = null
 dev = null
@@ -28,7 +28,7 @@ lang = "{{ lang }}"
 tok2vec/transformer. #}
 {%- set with_accuracy_or_transformer = (use_transformer or with_accuracy) -%}
 {%- set textcat_needs_features = has_textcat and with_accuracy_or_transformer -%}
-{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "spancat" in components or "spancat_singlelabel" in components or "trainable_lemmatizer" in components or "entity_linker" in components or textcat_needs_features) -%}
+{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "span_finder" in components or "spancat" in components or "spancat_singlelabel" in components or "trainable_lemmatizer" in components or "entity_linker" in components or textcat_needs_features) -%}
 {%- set full_pipeline = ["transformer" if use_transformer else "tok2vec"] + components -%}
 {%- else -%}
 {%- set full_pipeline = components -%}
@@ -127,6 +127,30 @@ grad_factor = 1.0
 @layers = "reduce_mean.v1"
 {% endif -%}
 
+{% if "span_finder" in components -%}
+[components.span_finder]
+factory = "span_finder"
+max_length = null
+min_length = null
+scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.span_finder.model]
+@architectures = "spacy.SpanFinder.v1"
+
+[components.span_finder.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = 2
+
+[components.span_finder.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+
+[components.span_finder.model.tok2vec.pooling]
+@layers = "reduce_mean.v1"
+{% endif -%}
+
 {% if "spancat" in components -%}
 [components.spancat]
 factory = "spancat"
@@ -331,6 +355,7 @@ maxout_pieces = 3
 {% if "morphologizer" in components %}
 [components.morphologizer]
 factory = "morphologizer"
+label_smoothing = 0.05
 
 [components.morphologizer.model]
 @architectures = "spacy.Tagger.v2"
@@ -344,6 +369,7 @@ width = ${components.tok2vec.model.encode.width}
 {% if "tagger" in components %}
 [components.tagger]
 factory = "tagger"
+label_smoothing = 0.05
 
 [components.tagger.model]
 @architectures = "spacy.Tagger.v2"
@@ -390,6 +416,27 @@ nO = null
 width = ${components.tok2vec.model.encode.width}
 {% endif %}
 
+{% if "span_finder" in components %}
+[components.span_finder]
+factory = "span_finder"
+max_length = null
+min_length = null
+scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
+spans_key = "sc"
+threshold = 0.5
+
+[components.span_finder.model]
+@architectures = "spacy.SpanFinder.v1"
+
+[components.span_finder.model.scorer]
+@layers = "spacy.LinearLogistic.v1"
+nO = 2
+
+[components.span_finder.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+{% endif %}
+
 {% if "spancat" in components %}
 [components.spancat]
 factory = "spancat"

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/errors.py

@@ -970,6 +970,13 @@ class Errors(metaclass=ErrorsWithCodes):
     E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
              "or use `auto_select_port=True` to pick an available port automatically.")
     E1051 = ("'allow_overlap' can only be False when max_positive is 1, but found 'max_positive': {max_positive}.")
+    E1052 = ("Unable to copy spans: the character offsets for the span at "
+             "index {i} in the span group do not align with the tokenization "
+             "in the target doc.")
+    E1053 = ("Both 'min_length' and 'max_length' should be larger than 0, but found"
+             " 'min_length': {min_length}, 'max_length': {max_length}")
+    E1054 = ("The text, including whitespace, must match between reference and "
+             "predicted docs when training {component}.")
 
 
 # Deprecated model shortcuts, only used in errors and warnings

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/git_info.py

@@ -1,3 +1,3 @@
 # THIS FILE IS GENERATED FROM SPACY SETUP.PY
 #
-GIT_VERSION = "512241e12"
+GIT_VERSION = "0f9d2b01f"

{spacy-3.5.3 → spacy-3.6.0.dev1}/spacy/lang/la/__init__.py

@@ -2,12 +2,14 @@ from ...language import Language, BaseDefaults
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
 from .stop_words import STOP_WORDS
 from .lex_attrs import LEX_ATTRS
+from .syntax_iterators import SYNTAX_ITERATORS
 
 
 class LatinDefaults(BaseDefaults):
     tokenizer_exceptions = TOKENIZER_EXCEPTIONS
     stop_words = STOP_WORDS
     lex_attr_getters = LEX_ATTRS
+    syntax_iterators = SYNTAX_ITERATORS
 
 
 class Latin(Language):

spacy-3.6.0.dev1/spacy/lang/la/examples.py

@@ -0,0 +1,22 @@
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.la.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+# > Caes. BG 1.1
+# > Cic. De Amic. 1
+# > V. Georg. 1.1-5
+# > Gen. 1:1
+# > Galileo, Sid. Nunc.
+# > van Schurman, Opusc. arg. 1
+
+sentences = [
+    "Gallia est omnis divisa in partes tres, quarum unam incolunt Belgae, aliam Aquitani, tertiam qui ipsorum lingua Celtae, nostra Galli appellantur.",
+    "Q. Mucius augur multa narrare de C. Laelio socero suo memoriter et iucunde solebat nec dubitare illum in omni sermone appellare sapientem.",
+    "Quid faciat laetas segetes, quo sidere terram uertere, Maecenas, ulmisque adiungere uitis conueniat, quae cura boum, qui cultus habendo sit pecori, apibus quanta experientia parcis, hinc canere incipiam",
+    "In principio creavit Deus caelum et terram.",
+    "Quo sumpto, intelligatur lunaris globus, cuius maximus circulus CAF, centrum vero E, dimetiens CF, qui ad Terre diametrum est ut duo ad septem.",
+    "Cuicunque natura indita sunt principia, seu potentiae principiorum omnium artium, ac scientiarum, ei conveniunt omnes artes ac scientiae.",
+]

spacy-3.6.0.dev1/spacy/lang/la/lex_attrs.py

@@ -0,0 +1,33 @@
+from ...attrs import LIKE_NUM
+import re
+
+# cf. Goyvaerts/Levithan 2009; case-insensitive, allow 4
+roman_numerals_compile = re.compile(
+    r"(?i)^(?=[MDCLXVI])M*(C[MD]|D?C{0,4})(X[CL]|L?X{0,4})(I[XV]|V?I{0,4})$"
+)
+
+_num_words = """unus una unum duo duae tres tria quattuor quinque sex septem octo novem decem undecim duodecim tredecim quattuordecim quindecim sedecim septendecim duodeviginti undeviginti viginti triginta quadraginta quinquaginta sexaginta septuaginta octoginta nonaginta centum ducenti ducentae ducenta trecenti trecentae trecenta quadringenti quadringentae quadringenta quingenti quingentae quingenta sescenti sescentae sescenta septingenti septingentae septingenta octingenti octingentae octingenta nongenti nongentae nongenta mille
+""".split()
+
+_num_words += [item.replace("v", "u") for item in _num_words]
+_num_words = set(_num_words)
+
+_ordinal_words = """primus prima primum secundus secunda secundum tertius tertia tertium quartus quarta quartum quintus quinta quintum sextus sexta sextum septimus septima septimum octavus octava octavum nonus nona nonum decimus decima decimum undecimus undecima undecimum duodecimus duodecima duodecimum duodevicesimus duodevicesima duodevicesimum undevicesimus undevicesima undevicesimum vicesimus vicesima vicesimum tricesimus tricesima tricesimum quadragesimus quadragesima quadragesimum quinquagesimus quinquagesima quinquagesimum sexagesimus sexagesima sexagesimum septuagesimus septuagesima septuagesimum octogesimus octogesima octogesimum nonagesimus nonagesima nonagesimum centesimus centesima centesimum ducentesimus ducentesima ducentesimum trecentesimus trecentesima trecentesimum quadringentesimus quadringentesima quadringentesimum quingentesimus quingentesima quingentesimum sescentesimus sescentesima sescentesimum septingentesimus septingentesima septingentesimum octingentesimus octingentesima octingentesimum nongentesimus nongentesima nongentesimum millesimus millesima millesimum""".split()
+
+_ordinal_words += [item.replace("v", "u") for item in _ordinal_words]
+_ordinal_words = set(_ordinal_words)
+
+
+def like_num(text):
+    if text.isdigit():
+        return True
+    if roman_numerals_compile.match(text):
+        return True
+    if text.lower() in _num_words:
+        return True
+    if text.lower() in _ordinal_words:
+        return True
+    return False
+
+
+LEX_ATTRS = {LIKE_NUM: like_num}

spacy-3.6.0.dev1/spacy/lang/la/syntax_iterators.py

@@ -0,0 +1,85 @@
+from typing import Union, Iterator, Tuple
+from ...tokens import Doc, Span
+from ...symbols import NOUN, PROPN, PRON, VERB, AUX
+from ...errors import Errors
+
+# NB: Modified from da on suggestion from https://github.com/explosion/spaCy/issues/7457#issuecomment-800349751 [PJB]
+
+
+def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:
+    def is_verb_token(tok):
+        return tok.pos in [VERB, AUX]
+
+    def get_left_bound(root):
+        left_bound = root
+        for tok in reversed(list(root.lefts)):
+            if tok.dep in np_left_deps:
+                left_bound = tok
+        return left_bound
+
+    def get_right_bound(doc, root):
+        right_bound = root
+        for tok in root.rights:
+            if tok.dep in np_right_deps:
+                right = get_right_bound(doc, tok)
+                if list(
+                    filter(
+                        lambda t: is_verb_token(t) or t.dep in stop_deps,
+                        doc[root.i : right.i],
+                    )
+                ):
+                    break
+                else:
+                    right_bound = right
+        return right_bound
+
+    def get_bounds(doc, root):
+        return get_left_bound(root), get_right_bound(doc, root)
+
+    doc = doclike.doc  # Ensure works on both Doc and Span.
+
+    if not doc.has_annotation("DEP"):
+        raise ValueError(Errors.E029)
+
+    if not len(doc):
+        return
+
+    left_labels = [
+        "det",
+        "fixed",
+        "nmod:poss",
+        "amod",
+        "flat",
+        "goeswith",
+        "nummod",
+        "appos",
+    ]
+    right_labels = [
+        "fixed",
+        "nmod:poss",
+        "amod",
+        "flat",
+        "goeswith",
+        "nummod",
+        "appos",
+        "nmod",
+        "det",
+    ]
+    stop_labels = ["punct"]
+
+    np_label = doc.vocab.strings.add("NP")
+    np_left_deps = [doc.vocab.strings.add(label) for label in left_labels]
+    np_right_deps = [doc.vocab.strings.add(label) for label in right_labels]
+    stop_deps = [doc.vocab.strings.add(label) for label in stop_labels]
+
+    prev_right = -1
+    for token in doclike:
+        if token.pos in [PROPN, NOUN, PRON]:
+            left, right = get_bounds(doc, token)
+            if left.i <= prev_right:
+                continue
+            yield left.i, right.i + 1, np_label
+            prev_right = right.i
+
+
+SYNTAX_ITERATORS = {"noun_chunks": noun_chunks}

spacy-3.6.0.dev1/spacy/lang/la/tokenizer_exceptions.py

@@ -0,0 +1,26 @@
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+from ...symbols import ORTH
+from ...util import update_exc
+
+
+## TODO: Look into systematically handling u/v
+_exc = {
+    "mecum": [{ORTH: "me"}, {ORTH: "cum"}],
+    "tecum": [{ORTH: "te"}, {ORTH: "cum"}],
+    "nobiscum": [{ORTH: "nobis"}, {ORTH: "cum"}],
+    "vobiscum": [{ORTH: "vobis"}, {ORTH: "cum"}],
+    "uobiscum": [{ORTH: "uobis"}, {ORTH: "cum"}],
+}
+
+_abbrev_exc = """A. A.D. Aa. Aaa. Acc. Agr. Ap. Apr. April. A.U.C. Aug. C. Caes. Caess. Cc. Cn. Coll. Cons. Conss. Cos. Coss. D. D.N. Dat. Dd. Dec. Decemb. Decembr. F. Feb. Febr. Februar. Ian. Id. Imp. Impp. Imppp. Iul. Iun. K. Kal. L. M'. M. Mai. Mam. Mar. Mart. Med. N. Nn. Nob. Non. Nov. Novemb. Oct. Octob. Opet. Ord. P. Paul. Pf. Pl. Plur. Post. Pp. Prid. Pro. Procos. Q. Quint. S. S.C. Scr. Sept. Septemb. Ser. Sert. Sex. Sext. St. Sta. Suff. T. Ti. Trib. V. Vol. Vop. Vv.""".split()
+
+_abbrev_exc += [item.lower() for item in _abbrev_exc]
+_abbrev_exc += [item.upper() for item in _abbrev_exc]
+_abbrev_exc += [item.replace("v", "u").replace("V", "U") for item in _abbrev_exc]
+
+_abbrev_exc += ["d.N."]
+
+for orth in set(_abbrev_exc):
+    _exc[orth] = [{ORTH: orth}]
+
+TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)

spacy-3.6.0.dev1/spacy/lang/ms/__init__.py

@@ -0,0 +1,24 @@
+from .stop_words import STOP_WORDS
+from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .lex_attrs import LEX_ATTRS
+from .syntax_iterators import SYNTAX_ITERATORS
+from ...language import Language, BaseDefaults
+
+
+class MalayDefaults(BaseDefaults):
+    tokenizer_exceptions = TOKENIZER_EXCEPTIONS
+    prefixes = TOKENIZER_PREFIXES
+    suffixes = TOKENIZER_SUFFIXES
+    infixes = TOKENIZER_INFIXES
+    syntax_iterators = SYNTAX_ITERATORS
+    lex_attr_getters = LEX_ATTRS
+    stop_words = STOP_WORDS
+
+
+class Malay(Language):
+    lang = "ms"
+    Defaults = MalayDefaults
+
+
+__all__ = ["Malay"]