[O] Separate tags from categories

.github/workflows/generator.py

@@ -1,13 +1,14 @@
 import json
 import os
 import re
+from collections import Counter
 from datetime import datetime, date
 from pathlib import Path
 
 import yaml
 
 
-class EnhancedJSONEncoder(json.JSONEncoder):
+class Encoder(json.JSONEncoder):
     def default(self, o: object) -> object:
         # Support encoding datetime
         if isinstance(o, (datetime, date)):
@@ -17,8 +18,9 @@ class EnhancedJSONEncoder(json.JSONEncoder):
 
 
 if __name__ == '__main__':
+    posts = []
+
     # Loop through all blog posts
-    metas = []
     for b in os.listdir('content/posts'):
         if not b.endswith('.md'):
             continue
@@ -27,27 +29,31 @@ if __name__ == '__main__':
         file = 'content/posts/' + b
         with open(file, 'r', encoding='utf-8') as f:
             yml, md = re.split('---+\n', f.read().strip())[1:]
-            meta = {**yaml.safe_load(yml), 'file': file}
-            metas.append(meta)
-            meta.setdefault('tags', [])
+            post = {**yaml.safe_load(yml), 'file': file}
+            posts.append(post)
+            post.setdefault('tags', [])
 
             # Parse date
-            if 'date' not in meta:
+            if 'date' not in post:
                 try:
-                    meta['date'] = date(int(b[:4]), int(b[5:7]), int(b[8:10]))
+                    post['date'] = date(int(b[:4]), int(b[5:7]), int(b[8:10]))
                 except:
                     pass
 
             # Convert image path
-            if 'title_image' in meta and '/' not in meta['title_image']:
-                meta['title_image'] = 'content/images/' + meta['title_image']
+            if 'title_image' in post and '/' not in post['title_image']:
+                post['title_image'] = 'content/images/' + post['title_image']
 
-            meta['content'] = md.strip()
+            post['content'] = md.strip()
 
-    metas.sort(key=lambda x: x['date'], reverse=True)
+    posts.sort(key=lambda x: x['date'], reverse=True)
 
-    metas_path = Path('content/generated/metas.json')
-    metas_path.parent.mkdir(exist_ok=True, parents=True)
-    with open(metas_path, 'w', encoding='utf-8') as f:
-        f.write('[\n    ' + ',\n    '.join(
-            json.dumps(m, cls=EnhancedJSONEncoder, ensure_ascii=False) for m in metas) + '\n]')
+    # Count tags and categories
+    tags = Counter([t for p in posts for t in p['tags']])
+    cats = Counter([p['category'] for p in posts if 'category' in p])
+    tags, cats = [[(k, c[k]) for k in c] for c in [tags, cats]]
+    print(tags, cats)
+
+    mp = Path('content/generated/metas.json')
+    mp.parent.mkdir(exist_ok=True, parents=True)
+    mp.write_text(json.dumps(posts, cls=Encoder, ensure_ascii=False, indent=2), 'utf-8')

content/posts/2021-10-14 十五秒的记忆.md

@@ -3,6 +3,7 @@ title: Clive Wearing 的日记
 subtitle: 十五秒的记忆、开心又无意义的人生、人的自私愿望
 title_image: "2021-10-14 Clive Wearing journal.png"
 tags: [心理]
+category: 想想想
 ---
 
 这是一个海马体因为脑炎失效的人写的一段日记——他没办法形成新的长期记忆，只拥有十五秒的短期记忆，因此他的时间是静止的，一遍一遍重复地体验着康复后第一次苏醒的喜悦。

content/posts/2021-12-07 651层.md

@@ -2,6 +2,7 @@
 title: 651层
 title_image: "2021-12-07 earth.jpg"
 tags: [梦]
+category: 梦
 ---
 
 今天又做了一个特别特别奇怪的梦，试试把它写成一段故事w