file title parsing

gawa/blog/models.py

@@ -24,6 +24,7 @@ MD = markdown.Markdown(extensions=EXTENSIONS, extension_configs=EXTENSION_CONFIG
 
 import pathlib
 import os
+import re
 
 class Category(models.Model):
     """
@@ -145,6 +146,8 @@ class BlogPost(Searchable):
 
         Caution: Will delete all Blog Posts
         """
+        logger.name = logger.name + ".sync_all"
+
         # delete all existing objects
         BlogPost.objects.all().delete()
 
@@ -155,9 +158,24 @@ class BlogPost(Searchable):
         if not data_dir.is_dir():
             logger.error(f"'{cls.DATA_DIR} is not a directory'")
 
-        files = [f for f in os.listdir(data_dir) if os.path.isfile(f)]
+        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"
+
+        # filepath, language code, slug
+        files = [(f, "", "") for f in files]
+        for f in files:
+            try:
+                matches = re.match(regex, f[0])
+                lang = matches.group(1)
+                titl = matches.group(2)
+                f = (f[0], lang, titl)
+                logger.debug(f"discovered file tup: {f}")
+            except Exception as e:
+                logger.debug(e)
+                files.remove(f)
 
     class Meta:
         verbose_name = _("blog post")