Pagination added and search and filtering moved to backend

backend/app/services/link_service.py

@@ -3,6 +3,8 @@
 
 from datetime import datetime, timezone
 import json
+import re
+from urllib.parse import urlparse
 from uuid import uuid4
 
 from backend.app.core.security import clean_url
@@ -136,23 +138,93 @@ def find_owned_link_by_title(user_id: str, title: str) -> dict | None:
     return record
 
 
-def list_public_links(username: str | None = None):
+def _tokenize_search(value: str) -> list[str]:
+    return [group1 or group2 for group1, group2 in re.findall(r'"([^"]+)"|(\S+)', value or '')]
+
+
+def _parse_search_query(value: str) -> dict:
+    groups = [[]]
+    excluded = []
+    sites = []
+    for token in _tokenize_search(value):
+        if token.upper() == 'OR':
+            groups.append([])
+            continue
+        is_excluded = token.startswith('-') and len(token) > 1
+        term = token[1:] if is_excluded else token
+        site_match = re.match(r'^site:(\S+)$', term, re.IGNORECASE)
+        if site_match and not is_excluded:
+            sites.append(site_match.group(1).lower())
+            continue
+        if is_excluded:
+            excluded.append(term.lower())
+        else:
+            groups[-1].append(term.lower())
+    return {'groups': [group for group in groups if group], 'excluded': excluded, 'sites': sites}
+
+
+def _searchable_text(record: dict) -> str:
+    parts = [record.get('title'), record.get('url'), record.get('comment'), record.get('username'), *(record.get('tags') or [])]
+    return ' '.join(part for part in parts if part).lower()
+
+
+def _matches_search(record: dict, query: str) -> bool:
+    if not query or not query.strip():
+        return True
+    parsed = _parse_search_query(query)
+    text = _searchable_text(record)
+
+    def site_matches(site: str) -> bool:
+        hostname = (urlparse(record.get('url') or '').hostname or '').lower()
+        return hostname == site or hostname.endswith(f'.{site}')
+
+    matches_site = all(site_matches(site) for site in parsed['sites'])
+    matches_group = not parsed['groups'] or any(all(term in text for term in group) for group in parsed['groups'])
+    excludes_term = any(term in text for term in parsed['excluded'])
+    return matches_site and matches_group and not excludes_term
+
+
+def list_public_links(
+    username: str | None = None,
+    tag: str | None = None,
+    search: str | None = None,
+    sort: str = 'newest',
+    page: int = 1,
+    page_size: int | None = None,
+) -> dict:
+    order = 'ASC' if sort == 'oldest' else 'DESC'
     with get_connection() as conn:
         rows = conn.execute(
-            '''
+            f'''
             SELECT links.*, users.username, users.avatar_url, users.bio
             FROM links
             JOIN users ON users.id = links.user_id
             WHERE links.is_public = 1
               AND (? IS NULL OR users.username = ?)
-            ORDER BY created_at DESC
+              AND (
+                ? IS NULL OR links.id IN (
+                    SELECT link_tags.link_id FROM link_tags
+                    JOIN tags ON tags.id = link_tags.tag_id
+                    WHERE lower(tags.name) = lower(?)
+                )
+              )
+            ORDER BY links.created_at {order}
             ''',
-            (username, username),
+            (username, username, tag, tag),
         ).fetchall()
         records = [dict(row) for row in rows]
         for record in records:
             record['tags'] = get_link_tags(conn, record['id'])
-    return records
+
+    if search:
+        records = [record for record in records if _matches_search(record, search)]
+
+    total = len(records)
+    if page_size:
+        start = max(page - 1, 0) * page_size
+        records = records[start:start + page_size]
+
+    return {'items': records, 'total': total}
 
 
 def get_public_profile(username: str) -> dict | None: