Merge branch 'master' into fix/enum-python-types

requirements.txt

@@ -9,7 +9,7 @@ murmurhash>=0.28.0,<1.1.0
 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,<1.0.0
+typer-slim>=0.3.0,<1.0.0
 weasel>=0.1.0,<0.5.0
 # Third party dependencies
 numpy>=2.0.0,<3.0.0

setup.cfg

@@ -55,7 +55,7 @@ install_requires =
     catalogue>=2.0.6,<2.1.0
     weasel>=0.1.0,<0.5.0
     # Third-party dependencies
-    typer>=0.3.0,<1.0.0
+    typer-slim>=0.3.0,<1.0.0
     tqdm>=4.38.0,<5.0.0
     numpy>=1.15.0; python_version < "3.9"
     numpy>=1.19.0; python_version >= "3.9"

spacy/cli/debug_model.py

@@ -170,7 +170,7 @@ def debug_model(
         msg.divider(f"STEP 3 - prediction")
         msg.info(str(prediction))
 
-    msg.good(f"Succesfully ended analysis - model looks good.")
+    msg.good(f"Successfully ended analysis - model looks good.")
 
 
 def _sentences():

spacy/pipeline/lemmatizer.py

@@ -218,7 +218,10 @@ class Lemmatizer(Pipe):
                 if not form:
                     pass
                 elif form in index or not form.isalpha():
-                    forms.append(form)
+                    if form in index:
+                        forms.insert(0, form)
+                    else:
+                        forms.append(form)
                 else:
                     oov_forms.append(form)
         # Remove duplicates but preserve the ordering of applied "rules"

spacy/tests/pipeline/test_textcat.py

@@ -260,7 +260,7 @@ labels = ['label1', 'label2']
 )
 @pytest.mark.issue(6908)
 def test_issue6908(component_name):
-    """Test intializing textcat with labels in a list"""
+    """Test initializing textcat with labels in a list"""
 
     def create_data(out_file):
         nlp = spacy.blank("en")

spacy/tests/test_language.py

@@ -740,7 +740,7 @@ def test_pass_doc_to_pipeline(nlp, n_process):
     assert len(doc.cats) > 0
     if isinstance(get_current_ops(), NumpyOps) or n_process < 2:
         # Catch warnings to ensure that all worker processes exited
-        # succesfully.
+        # successfully.
         with warnings.catch_warnings():
             warnings.simplefilter("error")
             docs = nlp.pipe(docs, n_process=n_process)

website/docs/api/cython.mdx

@@ -32,7 +32,7 @@ we use all four in different places, as they all have different utility:
 
 The most important classes in spaCy are defined as `cdef class` objects. The
 underlying data for these objects is usually gathered into a struct, which is
-usually named `c`. For instance, the [`Lexeme`](/api/cython-classses#lexeme)
+usually named `c`. For instance, the [`Lexeme`](/api/cython-classes#lexeme)
 class holds a [`LexemeC`](/api/cython-structs#lexemec) struct, at `Lexeme.c`.
 This lets you shed the Python container, and pass a pointer to the underlying
 data into C-level functions.

website/meta/universe.json

@@ -1,5 +1,74 @@
 {
     "resources": [
+        {
+            "id": "TeNs",
+            "title": "Temporal Expressions Normalization spaCy",
+            "thumb": "https://github-production-user-asset-6210df.s3.amazonaws.com/40547052/433595900-fae3c9d9-7181-4d8b-8b49-e6dc4fca930b.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20250414%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20250414T235545Z&X-Amz-Expires=300&X-Amz-Signature=e21d3c06300ceb15fa1dadd7cb60081cc9f1b35e5a7bfd07f6e8b90dd7fad9d0&X-Amz-SignedHeaders=host",
+            "url": "https://pypi.org/project/temporal-normalization-spacy/",
+            "slogan": "A temporal expression normalization plugin for Romanian using rule-based methods and DBpedia mappings.",
+            "description": "**[Temporal Expressions Normalization spaCy (TeNs)](https://github.com/iliedorobat/timespan-normalization-spacy)** is a powerful pipeline component for spaCy that seamlessly identifies and parses date entities in text. It leverages the **[Temporal Expressions Normalization Framework]( https://github.com/iliedorobat/timespan-normalization)** to recognize a wide variety of date formats using an extensive set of regular expressions (RegEx), ensuring robust and adaptable date extraction across diverse textual sources.\n\nUnlike conventional solutions that primarily focus on well-structured date formats, TeNs excels in handling real-world text by **identifying** not only standard date representations but also **abbreviated, informal, or even misspelled temporal expressions.** This makes it particularly effective for processing noisy or unstructured data, such as historical records, user-generated content, and scanned documents with OCR inaccuracies.",
+            "github": "iliedorobat/timespan-normalization-spacy",
+            "pip": "temporal-normalization-spacy",
+            "code_example": [
+                "import subprocess",
+                "",
+                "import spacy",
+                "",
+                "from temporal_normalization.commons.print_utils import console",
+                "from temporal_normalization.index import create_normalized_component, TemporalNormalization  # noqa: F401",
+                "",
+                "",
+                "try:",
+                "    # Load the spaCy model if it has already been downloaded",
+                "    nlp = spacy.load('ro_core_news_sm')",
+                "except OSError:",
+                "    console.warning(f'Started downloading ro_core_news_sm...')",
+                "    # Download the Romanian model if it wasn't already downloaded",
+                "    subprocess.run(['python', '-m', 'spacy', 'download', 'ro_core_news_sm'])",
+                "    # Load the spaCy model",
+                "    nlp = spacy.load('ro_core_news_sm')",
+                "",
+                "# Add 'temporal_normalization' component to the spaCy pipeline",
+                "nlp.add_pipe('temporal_normalization', last=True)",
+                "doc = nlp('Sec al II-lea a.ch. - I d.ch reprezintă o perioadă de mari schimbări.')",
+                "",
+                "# Display information about the identified and normalized dates in the text.",
+                "for entity in doc.ents:",
+                "    edges = entity._.time_series.edges",
+                "",
+                "    print('Start Edge:')",
+                "    print(edges.start.serialize('\\t'))",
+                "    print()",
+                "",
+                "    print('End Edge:')",
+                "    print(edges.end.serialize('\\t'))",
+                "    print()",
+                "",
+                "    print('Periods:')",
+                "    for period in entity._.time_series.periods:",
+                "        print(period.serialize('\\t'))",
+                "        print()",
+                "    print('---------------------')"
+            ],
+            "code_language": "python",
+            "author": "Ilie Cristian Dorobat",
+            "author_links": {
+                "github": "iliedorobat",
+                "website": "https://iliedorobat.ro/"
+            },
+            "category": [
+                "pipeline",
+                "standalone"
+            ],
+            "tags": [
+                "temporal",
+                "normalization",
+                "date",
+                "romanian",
+                "temporal-expression",
+                "dbpedia"
+            ]
+        },
         {
             "id": "spacy-vscode",
             "title": "spaCy Visual Studio Code Extension",