upgrade schema, resolvers, panel added

2025-05-16 09:23:48 +03:00
parent 8a60bec73a
commit 2d382be794
80 changed files with 8641 additions and 1100 deletions
--- a/utils/init.py
+++ b/utils/init.py
@@ -1 +0,0 @@
- 
--- a/utils/extract_text.py
+++ b/utils/extract_text.py
@@ -2,26 +2,48 @@
 Модуль для обработки HTML-фрагментов
 """

+import trafilatura
+
+
+def extract_text(html: str) -> str:
+    """
+    Извлекает текст из HTML-фрагмента.
+
+    Args:
+        html: HTML-фрагмент
+
+    Returns:
+        str: Текст из HTML-фрагмента
+    """
+    return trafilatura.extract(
+        wrap_html_fragment(html),
+        include_comments=False,
+        include_tables=False,
+        include_images=False,
+        include_formatting=False,
+    )
+
+
 def wrap_html_fragment(fragment: str) -> str:
    """
    Оборачивает HTML-фрагмент в полную HTML-структуру для корректной обработки.
-    
+
    Args:
        fragment: HTML-фрагмент для обработки
-        
+
    Returns:
        str: Полный HTML-документ
-        
+
    Example:
        >>> wrap_html_fragment("<p>Текст параграфа</p>")
        '<!DOCTYPE html><html><head><meta charset="utf-8"></head><body><p>Текст параграфа</p></body></html>'
    """
    if not fragment or not fragment.strip():
        return fragment
-        
+
    # Проверяем, является ли контент полным HTML-документом
-    is_full_html = fragment.strip().startswith('<!DOCTYPE') or fragment.strip().startswith('<html')
-    
+    is_full_html = fragment.strip().startswith("<!DOCTYPE") or fragment.strip().startswith("<html")
+
    # Если это фрагмент, оборачиваем его в полный HTML-документ
    if not is_full_html:
        return f"""<!DOCTYPE html>
@@ -34,5 +56,5 @@ def wrap_html_fragment(fragment: str) -> str:
 {fragment}
 </body>
 </html>"""
-    
-    return fragment
+
+    return fragment
--- a/utils/generate_slug.py
+++ b/utils/generate_slug.py
@@ -0,0 +1,65 @@
+import re
+from urllib.parse import quote_plus
+
+from auth.orm import Author
+from services.db import local_session
+
+
+def replace_translit(src):
+    ruchars = "абвгдеёжзийклмнопрстуфхцчшщъыьэюя."
+    enchars = [
+        "a",
+        "b",
+        "v",
+        "g",
+        "d",
+        "e",
+        "yo",
+        "zh",
+        "z",
+        "i",
+        "y",
+        "k",
+        "l",
+        "m",
+        "n",
+        "o",
+        "p",
+        "r",
+        "s",
+        "t",
+        "u",
+        "f",
+        "h",
+        "c",
+        "ch",
+        "sh",
+        "sch",
+        "",
+        "y",
+        "'",
+        "e",
+        "yu",
+        "ya",
+        "-",
+    ]
+    return src.translate(str.maketrans(ruchars, enchars))
+
+
+def generate_unique_slug(src):
+    print("[resolvers.auth] generating slug from: " + src)
+    slug = replace_translit(src.lower())
+    slug = re.sub("[^0-9a-zA-Z]+", "-", slug)
+    if slug != src:
+        print("[resolvers.auth] translited name: " + slug)
+    c = 1
+    with local_session() as session:
+        user = session.query(Author).where(Author.slug == slug).first()
+        while user:
+            user = session.query(Author).where(Author.slug == slug).first()
+            slug = slug + "-" + str(c)
+            c += 1
+        if not user:
+            unique_slug = slug
+            print("[resolvers.auth] " + unique_slug)
+            return quote_plus(unique_slug.replace("'", "")).replace("+", "-")