From 029c80da437ed2318ef27b1e122ec81cb48bc490 Mon Sep 17 00:00:00 2001
From: xxyzz <gitpull@protonmail.com>
Date: Thu, 18 Jan 2024 10:08:09 +0800
Subject: [PATCH 1/2] Remove Optional types in German pydantic models

---
 pyproject.toml                                |   1 -
 src/wiktextract/extractor/de/example.py       |  13 +-
 src/wiktextract/extractor/de/gloss.py         |   1 -
 src/wiktextract/extractor/de/linkage.py       |   1 -
 src/wiktextract/extractor/de/models.py        | 165 ++++++++----------
 src/wiktextract/extractor/de/page.py          |   1 -
 src/wiktextract/extractor/de/pronunciation.py |   1 -
 src/wiktextract/extractor/de/translation.py   |   1 -
 tests/test_de_example.py                      |  23 +--
 tests/test_de_gloss.py                        |   4 +-
 tests/test_de_linkages.py                     |   1 -
 tests/test_de_page.py                         |   1 -
 tests/test_de_pronunciation.py                |   1 -
 tests/test_de_translation.py                  |   1 -
 tools/generate_schema.py                      |   4 +
 15 files changed, 94 insertions(+), 125 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index ef42ff744..181f303dd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -39,7 +39,6 @@ dependencies = [
 
 [project.optional-dependencies]
 dev = [
-    "black",
     "coverage[toml]",
     "mypy",
     "ruff",
diff --git a/src/wiktextract/extractor/de/example.py b/src/wiktextract/extractor/de/example.py
index 67b261e6d..63d8e9a51 100644
--- a/src/wiktextract/extractor/de/example.py
+++ b/src/wiktextract/extractor/de/example.py
@@ -2,8 +2,7 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import LevelNode
-
-from wiktextract.extractor.de.models import Example, Reference, WordEntry
+from wiktextract.extractor.de.models import Example, WordEntry
 from wiktextract.extractor.de.utils import find_and_remove_child, match_senseid
 from wiktextract.page import clean_node
 from wiktextract.wxr_context import WiktextractContext
@@ -80,9 +79,7 @@ def extract_examples(
 def extract_reference(
     wxr: WiktextractContext, example_data: Example, ref_node: WikiNode
 ):
-    reference_data = Reference()
-
-    reference_data.raw_ref = clean_node(wxr, {}, ref_node.children)
+    example_data.raw_ref = clean_node(wxr, {}, ref_node.children)
 
     template_nodes = list(ref_node.find_child(NodeKind.TEMPLATE))
 
@@ -100,9 +97,9 @@ def extract_reference(
         for key, value in template_node.template_parameters.items():
             if isinstance(key, str):
                 key_english = REF_KEY_MAP.get(key.lower(), key.lower())
-                if key_english in reference_data.model_fields:
+                if key_english in example_data.model_fields:
                     setattr(
-                        reference_data, key_english, clean_node(wxr, {}, value)
+                        example_data, key_english, clean_node(wxr, {}, value)
                     )
                 else:
                     wxr.wtp.debug(
@@ -112,5 +109,3 @@ def extract_reference(
 
         # XXX: Treat other templates as well.
         # E.g. https://de.wiktionary.org/wiki/Vorlage:Ref-OWID
-
-    example_data.ref = reference_data
diff --git a/src/wiktextract/extractor/de/gloss.py b/src/wiktextract/extractor/de/gloss.py
index 1e9e5e2ad..7e5d67d91 100644
--- a/src/wiktextract/extractor/de/gloss.py
+++ b/src/wiktextract/extractor/de/gloss.py
@@ -3,7 +3,6 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import LevelNode
-
 from wiktextract.extractor.de.models import Sense, WordEntry
 from wiktextract.extractor.de.utils import find_and_remove_child, match_senseid
 from wiktextract.page import clean_node
diff --git a/src/wiktextract/extractor/de/linkage.py b/src/wiktextract/extractor/de/linkage.py
index 36b4804e8..8434b5fdf 100644
--- a/src/wiktextract/extractor/de/linkage.py
+++ b/src/wiktextract/extractor/de/linkage.py
@@ -2,7 +2,6 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import LevelNode
-
 from wiktextract.extractor.de.models import Linkage, WordEntry
 from wiktextract.extractor.share import split_senseids
 from wiktextract.page import clean_node
diff --git a/src/wiktextract/extractor/de/models.py b/src/wiktextract/extractor/de/models.py
index f6ecaa6b5..a5ebfbcca 100644
--- a/src/wiktextract/extractor/de/models.py
+++ b/src/wiktextract/extractor/de/models.py
@@ -1,10 +1,13 @@
-from typing import Optional
-
 from pydantic import BaseModel, ConfigDict, Field
 
 
 class BaseModelWrap(BaseModel):
-    model_config = ConfigDict(validate_assignment=True, extra="forbid")
+    model_config = ConfigDict(
+        extra="forbid",
+        strict=True,
+        validate_assignment=True,
+        validate_default=True,
+    )
 
 
 class Linkage(BaseModelWrap):
@@ -12,22 +15,20 @@ class Linkage(BaseModelWrap):
 
 
 class Translation(BaseModelWrap):
-    sense: Optional[str] = Field(
-        default=None, description="A gloss of the sense being translated"
+    sense: str = Field(
+        default="", description="A gloss of the sense being translated"
     )
-    word: Optional[str] = Field(default=None, description="Translation term")
-    lang_code: Optional[str] = Field(
-        default=None,
+    word: str = Field(default="", description="Translation term")
+    lang_code: str = Field(
+        default="",
         description="Wiktionary language code of the translation term",
     )
-    lang: Optional[str] = Field(
-        default=None, description="Localized language name"
-    )
-    uncertain: Optional[bool] = Field(
+    lang: str = Field(default="", description="Localized language name")
+    uncertain: bool = Field(
         default=False, description="Translation marked as uncertain"
     )
-    roman: Optional[str] = Field(
-        default=None, description="Transliteration to Roman characters"
+    roman: str = Field(
+        default="", description="Transliteration to Roman characters"
     )
     # senseids: list[str] = Field(
     #     default=[],
@@ -38,63 +39,49 @@ class Translation(BaseModelWrap):
         description="Tags specifying the translated term, usually gender information",
     )
     notes: list[str] = Field(default=[], description="A list of notes")
-    roman: Optional[str] = Field(
-        default=None, description="Transliteration in roman characters"
+    roman: str = Field(
+        default="", description="Transliteration in roman characters"
     )
 
 
-class Reference(BaseModelWrap):
-    raw_ref: str = Field(default=None, description="Raw reference string")
-    url: Optional[str] = Field(
-        default=None, description="A web link. Not necessarily well-formated."
-    )
-    author: Optional[str] = Field(default=None, description="Author's name")
-
-    title: Optional[str] = Field(
-        default=None, description="Title of the reference"
-    )
-    title_complement: Optional[str] = Field(
-        default=None, description="Complement to the title"
-    )
-    pages: Optional[str] = Field(default=None, description="Page numbers")
-    year: Optional[str] = Field(default=None, description="Year of publication")
-    publisher: Optional[str] = Field(default=None, description="Published by")
-    editor: Optional[str] = Field(default=None, description="Editor")
-    translator: Optional[str] = Field(default=None, description="Translator")
-    collection: Optional[str] = Field(
-        default=None,
+class Example(BaseModelWrap):
+    text: str = Field(default="", description="Example usage sentence")
+    # translation: Optional[str] = Field(
+    #     default=None, description="Spanish translation of the example sentence"
+    # )
+    raw_ref: str = Field(default="", description="Raw reference string")
+    url: str = Field(
+        default="", description="A web link. Not necessarily well-formated."
+    )
+    author: str = Field(default="", description="Author's name")
+    title: str = Field(default="", description="Title of the reference")
+    title_complement: str = Field(
+        default="", description="Complement to the title"
+    )
+    pages: str = Field(default="", description="Page numbers")
+    year: str = Field(default="", description="Year of publication")
+    publisher: str = Field(default="", description="Published by")
+    editor: str = Field(default="", description="Editor")
+    translator: str = Field(default="", description="Translator")
+    collection: str = Field(
+        default="",
         description="Name of collection that reference was published in",
     )
-    volume: Optional[str] = Field(default=None, description="Volume number")
-    comment: Optional[str] = Field(
-        default=None, description="Comment on the reference"
-    )
-    day: Optional[str] = Field(default=None, description="Day of publication")
-    month: Optional[str] = Field(
-        default=None, description="Month of publication"
-    )
-    accessdate: Optional[str] = Field(
-        default=None, description="Date of access of online reference"
+    volume: str = Field(default="", description="Volume number")
+    comment: str = Field(default="", description="Comment on the reference")
+    day: str = Field(default="", description="Day of publication")
+    month: str = Field(default="", description="Month of publication")
+    accessdate: str = Field(
+        default="", description="Date of access of online reference"
     )
-
-    date: Optional[str] = Field(default=None, description="Date of publication")
-    number: Optional[str] = Field(default=None, description="Issue number")
+    date: str = Field(default="", description="Date of publication")
+    number: str = Field(default="", description="Issue number")
     # journal: Optional[str] = Field(default=None, description="Name of journal")
     # chapter: Optional[str] = Field(default=None, description="Chapter name")
-    place: Optional[str] = Field(
-        default=None, description="Place of publication"
-    )
+    place: str = Field(default="", description="Place of publication")
     # editor: Optional[str] = Field(default=None, description="Editor")
-    edition: Optional[str] = Field(default=None, description="Edition number")
-    isbn: Optional[str] = Field(default=None, description="ISBN number")
-
-
-class Example(BaseModelWrap):
-    text: str = Field(default=None, description="Example usage sentence")
-    # translation: Optional[str] = Field(
-    #     default=None, description="Spanish translation of the example sentence"
-    # )
-    ref: Optional["Reference"] = Field(default=None, description="")
+    edition: str = Field(default="", description="Edition number")
+    isbn: str = Field(default="", description="ISBN number")
 
 
 class Sense(BaseModelWrap):
@@ -120,19 +107,19 @@ class Sense(BaseModelWrap):
     # subsenses: list["Sense"] = Field(
     #     default=[], description="List of subsenses"
     # )
-    senseid: Optional[str] = Field(
-        default=None, description="Sense number used in Wiktionary"
+    senseid: str = Field(
+        default="", description="Sense number used in Wiktionary"
     )
-    translations: Optional[list[Translation]] = []
-    antonyms: Optional[list[Linkage]] = []
-    derived: Optional[list[Linkage]] = []
-    hyponyms: Optional[list[Linkage]] = []
-    hypernyms: Optional[list[Linkage]] = []
-    holonyms: Optional[list[Linkage]] = []
-    expressions: Optional[list[Linkage]] = []
-    coordinate_terms: Optional[list[Linkage]] = []
-    proverbs: Optional[list[Linkage]] = []
-    synonyms: Optional[list[Linkage]] = []
+    translations: list[Translation] = []
+    antonyms: list[Linkage] = []
+    derived: list[Linkage] = []
+    hyponyms: list[Linkage] = []
+    hypernyms: list[Linkage] = []
+    holonyms: list[Linkage] = []
+    expressions: list[Linkage] = []
+    coordinate_terms: list[Linkage] = []
+    proverbs: list[Linkage] = []
+    synonyms: list[Linkage] = []
 
 
 class Sound(BaseModelWrap):
@@ -161,18 +148,18 @@ class Sound(BaseModelWrap):
     tags: list[str] = Field(
         default=[], description="Specifying the variant of the pronunciation"
     )
-    pass
 
 
 class WordEntry(BaseModelWrap):
     """
-    WordEntry is a dictionary containing lexical information of a single word extracted from Wiktionary with wiktextract.
+    WordEntry is a dictionary containing lexical information of a single word
+    extracted from Wiktionary with wiktextract.
     """
 
     model_config = ConfigDict(title="German Wiktionary")
 
     word: str = Field(description="word string")
-    pos: str = Field(default=None, description="Part of speech type")
+    pos: str = Field(default="", description="Part of speech type")
     # pos_title: str = Field(default=None, description="Original POS title")
     lang_code: str = Field(
         description="Wiktionary language code", examples=["es"]
@@ -180,19 +167,19 @@ class WordEntry(BaseModelWrap):
     lang: str = Field(
         description="Localized language name of the word", examples=["español"]
     )
-    senses: Optional[list[Sense]] = []
+    senses: list[Sense] = []
     # categories: list[str] = Field(
     #     default=[],
     #     description="list of non-disambiguated categories for the word",
     # )
-    translations: Optional[list[Translation]] = []
-    sounds: Optional[list[Sound]] = []
-    antonyms: Optional[list[Linkage]] = []
-    derived: Optional[list[Linkage]] = []
-    hyponyms: Optional[list[Linkage]] = []
-    hypernyms: Optional[list[Linkage]] = []
-    holonyms: Optional[list[Linkage]] = []
-    expressions: Optional[list[Linkage]] = []
-    coordinate_terms: Optional[list[Linkage]] = []
-    proverbs: Optional[list[Linkage]] = []
-    synonyms: Optional[list[Linkage]] = []
+    translations: list[Translation] = []
+    sounds: list[Sound] = []
+    antonyms: list[Linkage] = []
+    derived: list[Linkage] = []
+    hyponyms: list[Linkage] = []
+    hypernyms: list[Linkage] = []
+    holonyms: list[Linkage] = []
+    expressions: list[Linkage] = []
+    coordinate_terms: list[Linkage] = []
+    proverbs: list[Linkage] = []
+    synonyms: list[Linkage] = []
diff --git a/src/wiktextract/extractor/de/page.py b/src/wiktextract/extractor/de/page.py
index eda765405..2a6071112 100644
--- a/src/wiktextract/extractor/de/page.py
+++ b/src/wiktextract/extractor/de/page.py
@@ -5,7 +5,6 @@
 from mediawiki_langcodes import name_to_code
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import LevelNode
-
 from wiktextract.extractor.de.models import WordEntry
 from wiktextract.wxr_context import WiktextractContext
 
diff --git a/src/wiktextract/extractor/de/pronunciation.py b/src/wiktextract/extractor/de/pronunciation.py
index 43563fa29..7c3e09195 100644
--- a/src/wiktextract/extractor/de/pronunciation.py
+++ b/src/wiktextract/extractor/de/pronunciation.py
@@ -3,7 +3,6 @@
 from mediawiki_langcodes import code_to_name
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import LevelNode
-
 from wiktextract.extractor.de.models import Sound, WordEntry
 from wiktextract.extractor.share import create_audio_url_dict
 from wiktextract.page import clean_node
diff --git a/src/wiktextract/extractor/de/translation.py b/src/wiktextract/extractor/de/translation.py
index cf58373f7..e0710a25d 100644
--- a/src/wiktextract/extractor/de/translation.py
+++ b/src/wiktextract/extractor/de/translation.py
@@ -5,7 +5,6 @@
 from mediawiki_langcodes import code_to_name
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import TemplateNode
-
 from wiktextract.extractor.de.models import Translation, WordEntry
 from wiktextract.page import clean_node
 from wiktextract.wxr_context import WiktextractContext
diff --git a/tests/test_de_example.py b/tests/test_de_example.py
index a95667f0a..3ba757f8e 100644
--- a/tests/test_de_example.py
+++ b/tests/test_de_example.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.example import extract_examples, extract_reference
 from wiktextract.extractor.de.models import Example, Sense, WordEntry
@@ -72,7 +71,7 @@ def test_de_extract_example_with_reference(self):
                     "examples": [
                         {
                             "text": "example1",
-                            "ref": {"raw_ref": "ref1A"},
+                            "raw_ref": "ref1A",
                         },
                     ],
                     "senseid": "1",
@@ -95,15 +94,13 @@ def test_de_extract_reference_from_literatur_template(self):
         self.assertEqual(
             example_data.model_dump(exclude_defaults=True),
             {
-                "ref": {
-                    "raw_ref": "Expanded template, Seite 273. ISBN 978-3-89029-459-9.",
-                    "title": "Viva Warszawa",
-                    "author": "Steffen Möller",
-                    "title_complement": "Polen für Fortgeschrittene",
-                    "publisher": "Piper",
-                    "place": "München/Berlin",
-                    "year": "2015",
-                }
+                "raw_ref": "Expanded template, Seite 273. ISBN 978-3-89029-459-9.",
+                "title": "Viva Warszawa",
+                "author": "Steffen Möller",
+                "title_complement": "Polen für Fortgeschrittene",
+                "publisher": "Piper",
+                "place": "München/Berlin",
+                "year": "2015",
             },
         )
 
@@ -124,8 +121,6 @@ def test_de_extract_reference_from_templates_without_named_args(self):
         self.assertEqual(
             example_data.model_dump(exclude_defaults=True),
             {
-                "ref": {
-                    "raw_ref": "Expanded template",
-                }
+                "raw_ref": "Expanded template",
             },
         )
diff --git a/tests/test_de_gloss.py b/tests/test_de_gloss.py
index 6eeb264fa..39cdcee82 100644
--- a/tests/test_de_gloss.py
+++ b/tests/test_de_gloss.py
@@ -1,9 +1,7 @@
 import unittest
-from collections import defaultdict
 from unittest.mock import patch
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.gloss import (
     extract_glosses,
@@ -265,7 +263,7 @@ def test_de_extract_tags_from_gloss_text(self):
                 "input": "Drama von Samuel Beckett: Menschliche Existenz in der Endphase des Verfalls und der vergeblichen Suche nach einem Ausweg",
                 "expected_tags": None,
                 "expected_gloss": "Drama von Samuel Beckett: Menschliche Existenz in der Endphase des Verfalls und der vergeblichen Suche nach einem Ausweg",
-            }
+            },
             # Add more test cases as needed
         ]
         for case in test_cases:
diff --git a/tests/test_de_linkages.py b/tests/test_de_linkages.py
index 7de216833..e74d92b4a 100644
--- a/tests/test_de_linkages.py
+++ b/tests/test_de_linkages.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.linkage import extract_linkages
 from wiktextract.extractor.de.models import Sense, WordEntry
diff --git a/tests/test_de_page.py b/tests/test_de_page.py
index 77e11e7a1..925214e5b 100644
--- a/tests/test_de_page.py
+++ b/tests/test_de_page.py
@@ -3,7 +3,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.models import WordEntry
 from wiktextract.extractor.de.page import parse_page, parse_section
diff --git a/tests/test_de_pronunciation.py b/tests/test_de_pronunciation.py
index 19047dc8b..773d9b30d 100644
--- a/tests/test_de_pronunciation.py
+++ b/tests/test_de_pronunciation.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.models import Sound
 from wiktextract.extractor.de.pronunciation import (
diff --git a/tests/test_de_translation.py b/tests/test_de_translation.py
index 21e204939..badd6f7ed 100644
--- a/tests/test_de_translation.py
+++ b/tests/test_de_translation.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.de.models import Sense, Translation, WordEntry
 from wiktextract.extractor.de.translation import (
diff --git a/tools/generate_schema.py b/tools/generate_schema.py
index e224406f2..3fd0a084e 100644
--- a/tools/generate_schema.py
+++ b/tools/generate_schema.py
@@ -27,6 +27,10 @@ def main() -> None:
             model_schema[
                 "$schema"
             ] = "https://json-schema.org/draft/2020-12/schema"
+            if "description" in model_schema:
+                model_schema["description"] = model_schema[
+                    "description"
+                ].replace("\n", " ")
             with (output_path / f"{lang_code}.json").open(
                 "w", encoding="utf-8"
             ) as f:

From fb1f63b44e16334d0fa8269440c85479e7bbcf7c Mon Sep 17 00:00:00 2001
From: xxyzz <gitpull@protonmail.com>
Date: Thu, 18 Jan 2024 13:29:46 +0800
Subject: [PATCH 2/2] Remove Optional types in Spanish pydantic models

---
 src/wiktextract/extractor/es/example.py       |  52 +++---
 src/wiktextract/extractor/es/gloss.py         |   3 +-
 src/wiktextract/extractor/es/models.py        | 150 ++++++++----------
 src/wiktextract/extractor/es/page.py          |   7 +-
 src/wiktextract/extractor/es/pronunciation.py |   6 +-
 tests/test_es_etymology.py                    |   1 -
 tests/test_es_example.py                      |  28 ++--
 tests/test_es_gloss.py                        |   1 -
 tests/test_es_page.py                         |   1 -
 tests/test_es_pronunciation.py                |   1 -
 tests/test_es_translation.py                  |   1 -
 11 files changed, 106 insertions(+), 145 deletions(-)

diff --git a/src/wiktextract/extractor/es/example.py b/src/wiktextract/extractor/es/example.py
index b9996d945..82f680884 100644
--- a/src/wiktextract/extractor/es/example.py
+++ b/src/wiktextract/extractor/es/example.py
@@ -1,9 +1,9 @@
 import re
-from typing import Optional, Tuple, Union
+from typing import Optional, Union
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import WikiNodeChildrenList
-from wiktextract.extractor.es.models import Example, Reference, Sense
+from wiktextract.extractor.es.models import Example, Sense
 from wiktextract.page import clean_node
 from wiktextract.wxr_context import WiktextractContext
 
@@ -24,7 +24,7 @@
 
 def clean_text_and_url_from_text_nodes(
     wxr: WiktextractContext, nodes: WikiNodeChildrenList
-) -> Tuple[str, Optional[str]]:
+) -> tuple[str, Optional[str]]:
     if not nodes:
         return "", None
 
@@ -45,7 +45,7 @@ def clean_text_and_url_from_text_nodes(
     return text, url
 
 
-def add_template_params_to_reference(
+def add_template_params_to_example(
     wxr: WiktextractContext,
     params: Optional[
         dict[
@@ -53,15 +53,15 @@ def add_template_params_to_reference(
             Union[str, WikiNode, list[Union[str, WikiNode]]],
         ]
     ],
-    reference: Reference,
+    example: Example,
 ):
     for key in params.keys():
         if isinstance(key, int):
             continue
 
         ref_key = EXAMPLE_TEMPLATE_KEY_MAPPING.get(key, key)
-        if ref_key in reference.model_fields:
-            setattr(reference, ref_key, clean_node(wxr, {}, params.get(key)))
+        if ref_key in example.model_fields:
+            setattr(example, ref_key, clean_node(wxr, {}, params.get(key)))
         else:
             wxr.wtp.debug(
                 f"Unknown key {key} in example template {params}",
@@ -73,7 +73,6 @@ def process_example_template(
     wxr: WiktextractContext,
     sense_data: Sense,
     template_node: WikiNode,
-    reference: Reference,
 ):
     params = template_node.template_parameters
     text_nodes = params.get(1)
@@ -86,13 +85,13 @@ def process_example_template(
 
     example = Example(text=text)
 
-    if url:
-        example.ref = Reference(url=url)
+    if url is not None:
+        example.url = url
 
     if template_node.template_name == "ejemplo_y_trad":
         example.translation = clean_node(wxr, {}, params.get(2))
 
-    add_template_params_to_reference(wxr, params, reference)
+    add_template_params_to_example(wxr, params, example)
 
     sense_data.examples.append(example)
 
@@ -104,15 +103,15 @@ def extract_example(
 ):
     rest: WikiNodeChildrenList = []
 
-    reference = Reference()
     for node in nodes:
         if isinstance(node, WikiNode) and node.kind == NodeKind.TEMPLATE:
             if node.template_name in ["ejemplo", "ejemplo_y_trad"]:
-                process_example_template(wxr, sense_data, node, reference)
+                process_example_template(wxr, sense_data, node)
             else:
                 rest.append(node)
         elif isinstance(node, WikiNode) and node.kind == NodeKind.URL:
-            reference.url = clean_node(wxr, {}, node)
+            if len(sense_data.examples) > 0:
+                sense_data.examples[-1].url = clean_node(wxr, {}, node)
         else:
             rest.append(node)
 
@@ -125,9 +124,6 @@ def extract_example(
             sortid="extractor/es/example/extract_example/87",
         )
 
-    if sense_data.examples and reference.model_dump(exclude_defaults=True):
-        sense_data.examples[-1].ref = reference
-
 
 def process_example_list(
     wxr: WiktextractContext,
@@ -145,34 +141,28 @@ def process_example_list(
 
         text, url = clean_text_and_url_from_text_nodes(wxr, text_nodes)
 
-        if not text:
+        if len(text) == 0:
             continue
 
         example = Example(text=text)
-        if url:
-            example.ref = Reference(url=url)
+        if url is not None:
+            example.url = url
 
         for template_node in template_nodes:
-            reference = Reference()
             if template_node.template_name == "cita libro":
-                add_template_params_to_reference(
-                    wxr, template_node.template_parameters, reference
+                add_template_params_to_example(
+                    wxr, template_node.template_parameters, example
                 )
-                if reference.model_dump(exclude_defaults=True):
-                    example.ref = reference
 
         sense_data.examples.append(example)
 
     # If no example was found in sublists, assume example is in list_item.children directly.
     if not sense_data.examples:
         text, url = clean_text_and_url_from_text_nodes(wxr, list_item.children)
-
         text = re.sub(r"^(Ejemplos?:?)", "", text).strip()
-
-        if not text:
+        if len(text) == 0:
             return
         example = Example(text=text)
-        if url:
-            example.ref = Reference(url=url)
-
+        if url is not None:
+            example.url = url
         sense_data.examples.append(example)
diff --git a/src/wiktextract/extractor/es/gloss.py b/src/wiktextract/extractor/es/gloss.py
index b8bb567c4..a8dfb649f 100644
--- a/src/wiktextract/extractor/es/gloss.py
+++ b/src/wiktextract/extractor/es/gloss.py
@@ -2,7 +2,6 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import WikiNodeChildrenList
-
 from wiktextract.extractor.es.models import Sense, WordEntry
 from wiktextract.extractor.es.sense_data import process_sense_data_list
 from wiktextract.page import clean_node
@@ -15,7 +14,7 @@ def extract_gloss(
     list_node: WikiNode,
 ) -> None:
     for list_item in list_node.find_child(NodeKind.LIST_ITEM):
-        gloss_data = Sense(glosses=[])
+        gloss_data = Sense()
 
         definition: WikiNodeChildrenList = []
         other: WikiNodeChildrenList = []
diff --git a/src/wiktextract/extractor/es/models.py b/src/wiktextract/extractor/es/models.py
index bc5104a37..afcb27954 100644
--- a/src/wiktextract/extractor/es/models.py
+++ b/src/wiktextract/extractor/es/models.py
@@ -1,17 +1,20 @@
-from typing import Optional
-
 from pydantic import BaseModel, ConfigDict, Field
 
 
 class BaseModelWrap(BaseModel):
-    model_config = ConfigDict(validate_assignment=True, extra="forbid")
+    model_config = ConfigDict(
+        extra="forbid",
+        strict=True,
+        validate_assignment=True,
+        validate_default=True,
+    )
 
 
 class Linkage(BaseModelWrap):
     word: str
-    note: Optional[str] = Field(default=None)
-    alternative_spelling: Optional[str] = Field(
-        default=None, description="Alternative spelling of the word"
+    note: str = ""
+    alternative_spelling: str = Field(
+        default="", description="Alternative spelling of the word"
     )
 
 
@@ -29,15 +32,15 @@ class Translation(BaseModelWrap):
         description="Tags specifying the translated term, usually gender information",
     )
     notes: list[str] = Field(default=[], description="A list of notes")
-    roman: Optional[str] = Field(
-        default=None, description="Transliteration in roman characters"
+    roman: str = Field(
+        default="", description="Transliteration in roman characters"
     )
 
 
 class EtymologyTemplate(BaseModelWrap):
     name: str = Field(default="", description="Template's name.")
-    args: Optional[dict[str, str]] = Field(
-        default=None, description="Arguments given to the template, if any."
+    args: dict[str, str] = Field(
+        default={}, description="Arguments given to the template, if any."
     )
     expansion: str = Field(
         default="",
@@ -45,39 +48,28 @@ class EtymologyTemplate(BaseModelWrap):
     )
 
 
-class Reference(BaseModelWrap):
-    url: Optional[str] = Field(default=None, description="A web link")
-    first_name: Optional[str] = Field(
-        default=None, description="Author's first name"
-    )
-    last_name: Optional[str] = Field(
-        default=None, description="Author's last name"
-    )
-    title: Optional[str] = Field(
-        default=None, description="Title of the reference"
-    )
-    pages: Optional[str] = Field(default=None, description="Page numbers")
-    year: Optional[str] = Field(default=None, description="Year of publication")
-    date: Optional[str] = Field(default=None, description="Date of publication")
-    journal: Optional[str] = Field(default=None, description="Name of journal")
-    chapter: Optional[str] = Field(default=None, description="Chapter name")
-    place: Optional[str] = Field(
-        default=None, description="Place of publication"
-    )
-    editor: Optional[str] = Field(default=None, description="Editor")
-
-
 class Example(BaseModelWrap):
     text: str = Field(description="Example usage sentence")
-    translation: Optional[str] = Field(
-        default=None, description="Spanish translation of the example sentence"
-    )
-    ref: Optional["Reference"] = Field(default=None, description="")
+    translation: str = Field(
+        default="", description="Spanish translation of the example sentence"
+    )
+    url: str = Field(default="", description="A web link")
+    first_name: str = Field(default="", description="Author's first name")
+    last_name: str = Field(default="", description="Author's last name")
+    title: str = Field(default="", description="Title of the reference")
+    pages: str = Field(default="", description="Page numbers")
+    year: str = Field(default="", description="Year of publication")
+    date: str = Field(default="", description="Date of publication")
+    journal: str = Field(default="", description="Name of journal")
+    chapter: str = Field(default="", description="Chapter name")
+    place: str = Field(default="", description="Place of publication")
+    editor: str = Field(default="", description="Editor")
 
 
 class Sense(BaseModelWrap):
     glosses: list[str] = Field(
-        description="list of gloss strings for the word sense (usually only one). This has been cleaned, and should be straightforward text with no tagging."
+        default=[],
+        description="list of gloss strings for the word sense (usually only one). This has been cleaned, and should be straightforward text with no tagging.",
     )
     tags: list[str] = Field(
         default=[],
@@ -93,37 +85,35 @@ class Sense(BaseModelWrap):
     # subsenses: list["Sense"] = Field(
     #     default=[], description="List of subsenses"
     # )
-    senseid: Optional[str] = Field(
-        default=None, description="Sense number used in Wiktionary"
+    senseid: str = Field(
+        default="", description="Sense number used in Wiktionary"
     )
-    antonyms: Optional[list[Linkage]] = []
-    compounds: Optional[list[Linkage]] = []
-    derived: Optional[list[Linkage]] = []
-    hyponyms: Optional[list[Linkage]] = []
-    hypernyms: Optional[list[Linkage]] = []
-    idioms: Optional[list[Linkage]] = []
-    meronyms: Optional[list[Linkage]] = []
-    related: Optional[list[Linkage]] = []
-    synonyms: Optional[list[Linkage]] = []
+    antonyms: list[Linkage] = []
+    compounds: list[Linkage] = []
+    derived: list[Linkage] = []
+    hyponyms: list[Linkage] = []
+    hypernyms: list[Linkage] = []
+    idioms: list[Linkage] = []
+    meronyms: list[Linkage] = []
+    related: list[Linkage] = []
+    synonyms: list[Linkage] = []
 
 
 class Spelling(BaseModelWrap):
-    alternative: Optional[str] = Field(
-        default=None, description="Alternative spelling with same pronunciation"
+    alternative: str = Field(
+        default="", description="Alternative spelling with same pronunciation"
     )
-    note: Optional[str] = Field(
-        default=None, description="Note regarding alternative spelling"
+    note: str = Field(
+        default="", description="Note regarding alternative spelling"
     )
-    same_pronunciation: Optional[bool] = Field(
-        default=None,
+    same_pronunciation: bool = Field(
+        default="",
         description="Whether the alternative spelling has the same pronunciation as the default spelling",
     )
 
 
 class Sound(BaseModelWrap):
-    ipa: str = Field(
-        default="", description="International Phonetic Alphabet"
-    )
+    ipa: str = Field(default="", description="International Phonetic Alphabet")
     phonetic_transcription: str = Field(
         default="", description="Phonetic transcription, less exact than IPA."
     )
@@ -135,9 +125,7 @@ class Sound(BaseModelWrap):
     roman: str = Field(
         default="", description="Translitaration to Roman characters"
     )
-    syllabic: str = Field(
-        default="", description="Syllabic transcription"
-    )
+    syllabic: str = Field(default="", description="Syllabic transcription")
     tags: list[str] = Field(
         default=[], description="Specifying the variant of the pronunciation"
     )
@@ -151,39 +139,39 @@ class WordEntry(BaseModelWrap):
     model_config = ConfigDict(title="Spanish Wiktionary")
 
     word: str = Field(description="word string")
-    pos: str = Field(default=None, description="Part of speech type")
-    pos_title: str = Field(default=None, description="Original POS title")
+    pos: str = Field(default="", description="Part of speech type")
+    pos_title: str = Field(default="", description="Original POS title")
     lang_code: str = Field(
         description="Wiktionary language code", examples=["es"]
     )
     lang: str = Field(
         description="Localized language name of the word", examples=["español"]
     )
-    senses: Optional[list[Sense]] = []
+    senses: list[Sense] = []
     categories: list[str] = Field(
         default=[],
         description="list of non-disambiguated categories for the word",
     )
-    sounds: Optional[list[Sound]] = []
-    spellings: Optional[list[Spelling]] = []
-    translations: Optional[list[Translation]] = []
-    etymology_text: Optional[str] = Field(
-        default=None, description="Etymology section as cleaned text."
+    sounds: list[Sound] = []
+    spellings: list[Spelling] = []
+    translations: list[Translation] = []
+    etymology_text: str = Field(
+        default="", description="Etymology section as cleaned text."
     )
-    etymology_templates: Optional[list[EtymologyTemplate]] = Field(
-        default=None,
+    etymology_templates: list[EtymologyTemplate] = Field(
+        default=[],
         description="Templates and their arguments and expansions from the etymology section.",
     )
-    etymology_number: Optional[int] = Field(
-        default=None,
+    etymology_number: int = Field(
+        default=0,
         description="For words with multiple numbered etymologies, this contains the number of the etymology under which this entry appeared.",
     )
-    antonyms: Optional[list[Linkage]] = []
-    compounds: Optional[list[Linkage]] = []
-    derived: Optional[list[Linkage]] = []
-    hyponyms: Optional[list[Linkage]] = []
-    hypernyms: Optional[list[Linkage]] = []
-    idioms: Optional[list[Linkage]] = []
-    meronyms: Optional[list[Linkage]] = []
-    related: Optional[list[Linkage]] = []
-    synonyms: Optional[list[Linkage]] = []
+    antonyms: list[Linkage] = []
+    compounds: list[Linkage] = []
+    derived: list[Linkage] = []
+    hyponyms: list[Linkage] = []
+    hypernyms: list[Linkage] = []
+    idioms: list[Linkage] = []
+    meronyms: list[Linkage] = []
+    related: list[Linkage] = []
+    synonyms: list[Linkage] = []
diff --git a/src/wiktextract/extractor/es/page.py b/src/wiktextract/extractor/es/page.py
index 6602cc38a..4ee7872e5 100644
--- a/src/wiktextract/extractor/es/page.py
+++ b/src/wiktextract/extractor/es/page.py
@@ -4,7 +4,6 @@
 
 from wikitextprocessor import NodeKind, WikiNode
 from wikitextprocessor.parser import WikiNodeChildrenList
-
 from wiktextract.extractor.es.etymology import process_etymology_block
 from wiktextract.extractor.es.example import extract_example
 from wiktextract.extractor.es.gloss import extract_gloss
@@ -194,10 +193,8 @@ def process_pos_block(
     """
 
     child_nodes = list(pos_level_node.filter_empty_str_child())
-
-    sense_children: WikiNodeChildrenList = (
-        []
-    )  # All non-gloss nodes that add additional information to a sense
+    # All non-gloss nodes that add additional information to a sense
+    sense_children: WikiNodeChildrenList = []
 
     for child in child_nodes:
         if (
diff --git a/src/wiktextract/extractor/es/pronunciation.py b/src/wiktextract/extractor/es/pronunciation.py
index 7d62eb945..64ede513c 100644
--- a/src/wiktextract/extractor/es/pronunciation.py
+++ b/src/wiktextract/extractor/es/pronunciation.py
@@ -126,8 +126,8 @@ def process_pron_graf_template(
 
         main_sound = variations[0]
         for key in main_sound.model_fields_set:
-        # because "tags" is a field that is never 'set' (just appended to)
-        # it apparently doesn't appear in mode_fields_set.
+            # because "tags" is a field that is never 'set' (just appended to)
+            # it apparently doesn't appear in mode_fields_set.
             for i, other_variation in variations.items():
                 if i == 0:
                     continue
@@ -139,7 +139,7 @@ def process_pron_graf_template(
                     continue
                 if not other_variation.tags:
                     other_variation.tags = main_sound.tags.copy()
-            
+
         for sound in variations.values():
             if len(sound.model_dump(exclude_defaults=True)) > 0:
                 sound_data.append(sound)
diff --git a/tests/test_es_etymology.py b/tests/test_es_etymology.py
index dbe69b371..7527f1438 100644
--- a/tests/test_es_etymology.py
+++ b/tests/test_es_etymology.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.es.etymology import process_etymology_block
 from wiktextract.extractor.es.models import WordEntry
diff --git a/tests/test_es_example.py b/tests/test_es_example.py
index e81a71d6c..eaf922b46 100644
--- a/tests/test_es_example.py
+++ b/tests/test_es_example.py
@@ -36,9 +36,7 @@ def test_es_extract_example(self):
                 "expected": [
                     {
                         "text": "Nos gusta lo oscuro, y por eso triunfa la Necroporra, sea ético o no",
-                        "ref": {
-                            "url": "https://www.menzig.es/a/necroporra-fantamorto-porra-famosos-muertos/"
-                        },
+                        "url": "https://www.menzig.es/a/necroporra-fantamorto-porra-famosos-muertos/",
                     }
                 ],
             },
@@ -48,9 +46,7 @@ def test_es_extract_example(self):
                 "expected": [
                     {
                         "text": """Papel: más viejo que Matusalén, pero graduado "cum laude" en eficacia publicitaria""",
-                        "ref": {
-                            "url": "https://www.marketingdirecto.com/marketing-general/publicidad/papel-mas-viejo-matusalen-pero-graduado-cum-laude-eficacia-publicitaria"
-                        },
+                        "url": "https://www.marketingdirecto.com/marketing-general/publicidad/papel-mas-viejo-matusalen-pero-graduado-cum-laude-eficacia-publicitaria",
                     }
                 ],
             },
@@ -60,14 +56,12 @@ def test_es_extract_example(self):
                 "expected": [
                     {
                         "text": "Era persona inteligente, culta, que me permitía zapotear los libros y me hacía comentarios sobre ellos y sus autores",
-                        "ref": {
-                            "title": "Memorias intelectuales",
-                            "first_name": "Jaime",
-                            "last_name": "Jaramillo Uribe",
-                            "pages": "19",
-                            "url": "https://books.google.com.co/books?id=X9MSAQAAIAAJ&q=zapotear",
-                            "year": "2007",
-                        },
+                        "title": "Memorias intelectuales",
+                        "first_name": "Jaime",
+                        "last_name": "Jaramillo Uribe",
+                        "pages": "19",
+                        "url": "https://books.google.com.co/books?id=X9MSAQAAIAAJ&q=zapotear",
+                        "year": "2007",
                     }
                 ],
             },
@@ -119,10 +113,8 @@ def test_es_process_example_list(self):
                 "expected": [
                     {
                         "text": "«Apoyado contra el quicio de la puerta, adivina, de pronto, a su marido.»",
-                        "ref": {
-                            "first_name": "María Luisa",
-                            "last_name": "Bombal",
-                        },
+                        "first_name": "María Luisa",
+                        "last_name": "Bombal",
                     }
                 ],
             },
diff --git a/tests/test_es_gloss.py b/tests/test_es_gloss.py
index 5105821ad..6aff6cfe3 100644
--- a/tests/test_es_gloss.py
+++ b/tests/test_es_gloss.py
@@ -2,7 +2,6 @@
 from typing import List
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.es.gloss import extract_gloss
 from wiktextract.extractor.es.models import WordEntry
diff --git a/tests/test_es_page.py b/tests/test_es_page.py
index 9e98a043b..fb8125501 100644
--- a/tests/test_es_page.py
+++ b/tests/test_es_page.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.es.models import WordEntry
 from wiktextract.extractor.es.page import parse_entries
diff --git a/tests/test_es_pronunciation.py b/tests/test_es_pronunciation.py
index 20f5167ed..f12d622da 100644
--- a/tests/test_es_pronunciation.py
+++ b/tests/test_es_pronunciation.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.es.models import WordEntry
 from wiktextract.extractor.es.pronunciation import (
diff --git a/tests/test_es_translation.py b/tests/test_es_translation.py
index a902e95dc..49c499824 100644
--- a/tests/test_es_translation.py
+++ b/tests/test_es_translation.py
@@ -1,7 +1,6 @@
 import unittest
 
 from wikitextprocessor import Wtp
-
 from wiktextract.config import WiktionaryConfig
 from wiktextract.extractor.es.models import WordEntry
 from wiktextract.extractor.es.translation import extract_translation