Implement naive concepts, basic autocomplete

README.md

@@ -2,7 +2,7 @@
 
 Infrastructure for relaying and exchanging mathematical concepts.
 
-For a demonstration of a page with at least one link, see for example `{baseurl}/concept/Q1369621/`.
+For a demonstration of a page with at least one link, see for example `{baseurl}/concept/Schwartz%20space/`.
 
 ## Notes on installation and usage
 

web/concepts/management/commands/compute_concepts.py

@@ -0,0 +1,103 @@
+import logging
+from typing import Dict, List
+
+from concepts.models import Concept, Item, Link
+from django.core.management.base import BaseCommand
+from django.db.models import Q
+from django.db.utils import IntegrityError
+
+
+class UnionFind:
+    def __init__(self, size):
+        self.parent = [i for i in range(size)]
+        self.rank = [0] * size
+
+    def find(self, x):
+        if self.parent[x] != x:
+            self.parent[x] = self.find(self.parent[x])
+        return self.parent[x]
+
+    def union(self, x, y):
+        root_x = self.find(x)
+        root_y = self.find(y)
+
+        if root_x != root_y:
+            if self.rank[root_x] < self.rank[root_y]:
+                self.parent[root_x] = root_y
+            elif self.rank[root_x] > self.rank[root_y]:
+                self.parent[root_y] = root_x
+            else:
+                self.parent[root_y] = root_x
+                self.rank[root_x] += 1
+
+    def get_components(self):
+        components = {}
+        for i in range(len(self.parent)):
+            root = self.find(i)
+            if root not in components:
+                components[root] = [i]
+            else:
+                components[root].append(i)
+        return components
+
+
+class Command(BaseCommand):
+    num_to_id: List[str] = []
+    id_to_num: Dict[str, int] = {}
+    id_to_item: Dict[str, Item] = {}
+
+    def union(self, uf, link: Link):
+        uf.union(self.id_to_num[link.source.id], self.id_to_num[link.destination.id])
+
+    def handle(self, *args, **options):
+        # all items that do not appear in an edge are components
+        singletons = Item.objects.filter(
+            incoming_items__isnull=True, outgoing_items__isnull=True
+        )
+        count_duplicates = 0
+        for i in singletons:
+            new_concept = Concept(name=i.name, description=i.description)
+            try:
+                new_concept.save()
+            except IntegrityError:
+                count_duplicates += 1
+                logging.log(
+                    logging.WARNING,
+                    f" A concept named '{new_concept.name}' already exists.",
+                )
+            i.concept = new_concept
+
+        print("compute non-singletons")
+        # now deal with those that do not have a concept yet
+        print(
+            Item.objects.filter(
+                Q(incoming_items__isnull=False) | Q(outgoing_items__isnull=False)
+            ).query
+        )
+        for i in Item.objects.filter(
+            Q(incoming_items__isnull=False) | Q(outgoing_items__isnull=False)
+        ):
+            self.num_to_id.append(i.id)
+            self.id_to_item[i.id] = i
+        for i, id in enumerate(self.num_to_id):
+            self.id_to_num[id] = i
+        uf = UnionFind(len(self.num_to_id))
+        for link in Link.objects.all():
+            self.union(uf, link)
+        for v in uf.get_components().values():
+            # first check if WD is one of the items
+            items = list(map(lambda i: self.id_to_item[self.num_to_id[i]], v))
+            items.sort(key=Item.source_key())
+            new_concept = Concept(name=items[0].name, description=items[0].description)
+            try:
+                new_concept.save()
+            except IntegrityError:
+                logging.log(
+                    logging.WARNING,
+                    f" A concept named '{new_concept.name}' already exists.",
+                )
+                new_concept = Concept.objects.get(name=items[0].name)
+            print(f"linking {new_concept.id}")
+            for item in items:
+                item.concept = new_concept
+                item.save()

web/concepts/management/commands/link_same.py

@@ -0,0 +1,18 @@
+from concepts.models import Item, Link
+from django.core.management.base import BaseCommand
+from django.db.models import Count
+
+
+class Command(BaseCommand):
+    def handle(self, *args, **options):
+        print("link same")
+        for name_count in (
+            Item.objects.all()
+            .values("name")
+            .annotate(total=Count("name"))
+            .filter(total__gte=2)
+        ):
+            items = Item.objects.filter(name=name_count["name"])
+            for i in range(len(items) - 1):
+                for j in range(i + 1, len(items)):
+                    Link.save_new(items[i], items[j], Link.Label.NAME_EQ)

web/concepts/migrations/0006_remove_item_links_link.py

@@ -0,0 +1,62 @@
+# Generated by Django 4.2.6 on 2023-11-17 18:33
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("concepts", "0005_alter_item_options_alter_item_source"),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name="item",
+            name="links",
+        ),
+        migrations.CreateModel(
+            name="Link",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "label",
+                    models.CharField(
+                        choices=[
+                            ("Wd", "Wikidata"),
+                            ("AUm", "Agda Unimath"),
+                            ("eq", "same name"),
+                        ],
+                        max_length=4,
+                    ),
+                ),
+                (
+                    "destination",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="incoming_items",
+                        to="concepts.item",
+                    ),
+                ),
+                (
+                    "source",
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE,
+                        related_name="outgoing_items",
+                        to="concepts.item",
+                    ),
+                ),
+            ],
+            options={
+                "ordering": ["source", "destination", "label"],
+                "unique_together": {("source", "destination", "label")},
+            },
+        ),
+    ]

web/concepts/migrations/0007_concept_item_concept.py

@@ -0,0 +1,42 @@
+# Generated by Django 4.2.6 on 2023-11-18 11:48
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ("concepts", "0006_remove_item_links_link"),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name="Concept",
+            fields=[
+                (
+                    "id",
+                    models.BigAutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                ("name", models.CharField(max_length=200, null=True, unique=True)),
+                ("description", models.TextField(null=True)),
+            ],
+            options={
+                "ordering": ["name", "description"],
+            },
+        ),
+        migrations.AddField(
+            model_name="item",
+            name="concept",
+            field=models.ForeignKey(
+                blank=True,
+                null=True,
+                on_delete=django.db.models.deletion.SET_NULL,
+                to="concepts.concept",
+            ),
+        ),
+    ]

web/concepts/models.py

@@ -1,4 +1,15 @@
+import logging
+
 from django.db import models
+from django.db.utils import IntegrityError
+
+
+class Concept(models.Model):
+    name = models.CharField(max_length=200, null=True, unique=True)
+    description = models.TextField(null=True)
+
+    class Meta:
+        ordering = ["name", "description"]
 
 
 class Item(models.Model):
@@ -14,20 +25,80 @@ class Source(models.TextChoices):
     url = models.URLField(max_length=200)
     name = models.CharField(max_length=200, null=True)
     description = models.TextField(null=True)
-    links = models.ManyToManyField("self", blank=True)
+    concept = models.ForeignKey(
+        Concept,
+        models.SET_NULL,
+        blank=True,
+        null=True,
+    )
 
     class Meta:
         ordering = ["name", "source", "identifier"]
         unique_together = ["source", "identifier"]
 
-    def get_link(self):
-        return {"name": self.name, "source": self.source, "url": self.url}
+    @staticmethod
+    def source_key():
+        SOURCES = [
+            Item.Source.WIKIDATA,
+            Item.Source.NLAB,
+            Item.Source.MATHWORLD,
+            Item.Source.WIKIPEDIA_EN,
+            Item.Source.AGDA_UNIMATH,
+        ]
+        return lambda item: SOURCES.index(item.source)
+
+    def to_dict(self):
+        return {"name": self.name, "source": self.get_source_display(), "url": self.url}
 
-    def get_links(self):
-        return [linked_item.get_link() for linked_item in self.links.all()]
+    def get_linked_items(self):
+        linked_destinations = Link.objects.filter(source=self.id).map(
+            lambda link: link.destination
+        )
+        linked_sources = Link.objects.filter(destination=self.id).map(
+            lambda link: link.source
+        )
+        return set(linked_sources + linked_destinations)
+
+    def get_linked_item_urls(self):
+        return [i.get_url() for i in self.get_linked_items()]
 
     def __str__(self):
         if self.name:
             return f"{self.get_source_display()}: {self.identifier} ({self.name})"
         else:
             return f"{self.get_source_display()}: {self.identifier}"
+
+
+class Link(models.Model):
+    class Label(models.TextChoices):
+        WIKIDATA = "Wd", "Wikidata"
+        AGDA_UNIMATH = "AUm", "Agda Unimath"
+        NAME_EQ = "eq", "same name"
+
+    source = models.ForeignKey(
+        Item, on_delete=models.CASCADE, related_name="outgoing_items"
+    )
+    destination = models.ForeignKey(
+        Item, on_delete=models.CASCADE, related_name="incoming_items"
+    )
+    label = models.CharField(max_length=4, choices=Label.choices)
+
+    class Meta:
+        ordering = ["source", "destination", "label"]
+        unique_together = ["source", "destination", "label"]
+
+    @staticmethod
+    def save_new(source: Item, destination: Item, label: Label):
+        try:
+            new_link = Link.objects.create(
+                source=source, destination=destination, label=label
+            )
+            new_link.save()
+        except IntegrityError:
+            logging.log(
+                logging.WARNING,
+                f" Link from {source} to {destination} repeated in {label}.",
+            )
+
+    def __str__(self):
+        return f"{self.source} -[{self.get_label_display()}]-> {self.destination}"

web/concepts/templates/base.html

@@ -0,0 +1,30 @@
+<!doctype html>
+{% load static %}
+<html lang="en">
+  <head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1">
+    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@picocss/pico@1/css/pico.min.css">
+    <link rel="stylesheet" href="{% static 'concepts/mathswitch.css' %}">
+    <title>mathswitch</title>
+    <meta
+      name="description"
+      content="Infrastructure for relaying and exchanging mathematical concepts."
+    />
+  </head>
+  <body>
+    <header class="container">
+      <hgroup>
+        <h1>mathswitch</h1>
+        <p>Infrastructure for relaying and exchanging mathematical concepts.</p>
+      </hgroup>
+    </header>
+    <main class="container">
+        {% block content %}
+        {% endblock %}
+    </main>
+    <footer class="container">
+        <img class="powered-by-wikidata" alt="Powered by Wikidata" />
+    </footer>
+  </body>
+</html>