Merge pull request 'revamp-file-discover' (#33) from revamp-file-discover into devel

Reviewed-on: #33

gawa/blog/migrations/0002_alter_blogpost_slug.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.2.5 on 2023-10-02 19:03
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('blog', '0001_initial'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='blogpost',
+            name='slug',
+            field=models.SlugField(unique=True),
+        ),
+    ]

gawa/blog/models.py

@@ -76,7 +76,7 @@ class BlogPost(Searchable):
     body_de = models.TextField(blank=True,
                                default="""This aritcle is not available in english.""")
     category = models.ForeignKey(
-        Category, on_delete=models.SET_DEFAULT, null=False,
+        Category, on_delete=models.SET_DEFAULT, blank=False,
         default=Category.get_or_create_uncategorized)
     thumbnail = models.ImageField(
         blank=True,
@@ -85,7 +85,15 @@ class BlogPost(Searchable):
     featured = models.BooleanField(default=False)
     langs = models.CharField(
         default=DEFAULT_LANGS.__repr__(), max_length=64)
-    slug = models.SlugField()
+    slug = models.SlugField(unique=True, blank=False)
+
+    def save(self):
+        # check if the slug is empty if we remove whitespaces
+        if len(self.slug.strip()) == 0:
+            logger.error(
+                f"trying to save '{self.__class__}' with empty slug: {self}")
+            raise ValueError(f"trying to save '{self.__class__}' with empty slug: {self}")
+        super().save()
 
     def regenerate(self):
         """
@@ -228,72 +236,30 @@ class BlogPost(Searchable):
 
         files = [f for f in os.listdir(data_dir) if (
             data_dir.joinpath(f)).is_file()]
-        logger.debug(f"discovered files: {files}")
 
-        # finding lang and title
-        regex = r"^(en|de)-(.*)\.md"
-        # TODO: only find toml files
+        # find the meta file
+        regex = r"^(.*)\.toml"
 
-        # filepath, language codes, slug
-        files = [[f, cls.DEFAULT_LANGS, ""] for f in files]
+        # filepath, slug
+        files = [[f, ""] for f in files]
         for file in files:
             # parse file name
             try:
                 matches = re.match(regex, file[0])
                 if matches is None:
-                    logger.warning(
-                        f"Data file '{file[0]}' does not fit to the filename\
-                        regex")
+                    # file is not a toml / meta file
                     files.remove(file)
+                    continue
                 else:
                     current_lang = matches.group(1)
-                    file[1][current_lang] = True
-                    file[2] = matches.group(2)
-            except Exception as e:
-                logger.error(e)
-                files.remove(file)
+                    file[1] = matches.group(1)
 
-        # PERF:
-        # Optimize for single loop, should be doable and better design
-
-        # collapse diffrent versions
-        for file in files:
-            try:
-                if [_f[2] for _f in files].count(file[2]) >= 2:
-                    logger.debug(f"multiple versions of '{file[2]}'")
-                    versions = [_f for _f in files if _f[2] == file[2]]
-                    lang: dict[str, bool] = file[1]
-                    for version in versions:
-                        for key in version[1]:
-                            lang[key] |= version[1][key]
-                else:
-                    # only a single version of this file
-                    continue
-            except Exception as e:
-                logger.error(
-                    f"Could not combine BlogPosts for '{file[0]}': {e}")
-
-        # TODO: not needed when relying on toml files
-        try:
-            # deduplicate
-            _files = []
-            for f in [[_f[1], _f[2]]
-                      for _f in files]:   # dont care about fname
-                if f not in _files:
-                    _files.append(f)
-            files = _files
-            logger.debug(f"to save: {files}")
-        except Exception as e:
-            logger.error(f"Could not dedup BlogPosts: {e}")
-
-        for file in files:
-            try:
-                obj = BlogPost(langs=file[0], slug=file[1])
+                obj = BlogPost(slug=file[1])
                 obj.sync_file()
                 obj.regenerate()
-                obj.save()
             except Exception as e:
                 logger.error(f"Could not create BlogPost for '{file[1]}': {e}")
+                files.remove(file)
 
     class Meta:
         verbose_name = _("blog post")

gawa/start/models.py

@@ -59,7 +59,7 @@ class Searchable(models.Model):
             obj.regenerate()
 
     def __str__(self):
-        return f"{{<{self.__class__.__name__}>\"{self.slug}\"}}"
+        return f"{{<{self.__class__.__name__}>\"{self.title_en}\"}}"
 
     def regenerate(self):
         """
@@ -75,7 +75,7 @@ class Searchable(models.Model):
 
 class StaticSite(Searchable):
     """
-    This model represents any static site, such as start:index, 
+    This model represents any static site, such as start:index,
     that should show up in search.
 
     Every searchable view should inherit from start.views.SearchableView.