BanGUI/backend/app/utils/pagination.py

"""Pagination utilities and standardized query parameter handling.

This module provides reusable utilities for implementing consistent pagination
across all endpoints. All paginated endpoints should use these utilities to
ensure a uniform API contract.

Supported Pagination Modes:

1. **Offset-Based (Legacy)** — Uses page number + page_size.
   Query parameters: page (1-based), page_size (1-500)
   ⚠️  Performance degrades on large offsets (OFFSET requires scanning N rows).
   Use for: Small datasets, where performance is not critical.

2. **Cursor-Based (Recommended for large tables)** — Uses keyset pagination.
   Query parameters: cursor (opaque token for next/prev), page_size
   ✓ Constant-time performance regardless of dataset size.
   Use for: Large tables (>100K rows), paginated lists with sorting.

Usage Examples:

**Offset pagination (legacy):**
  ```python
  from app.utils.pagination import PAGINATION_DEFAULTS, create_pagination_metadata

  @router.get("/items")
  async def get_items(
      page: int = Query(default=PAGINATION_DEFAULTS["page"], ge=1),
      page_size: int = Query(
          default=PAGINATION_DEFAULTS["page_size"],
          ge=1,
          le=PAGINATION_DEFAULTS["max_page_size"],
      ),
  ):
      items = [...]
      total = 100
      pagination = create_pagination_metadata(total, page, page_size)
      return MyListResponse(items=items, pagination=pagination)
  ```

**Cursor pagination (recommended):**
  ```python
  from app.utils.pagination import decode_cursor, encode_cursor, PAGINATION_DEFAULTS

  @router.get("/items")
  async def get_items(
      cursor: str | None = Query(None),
      page_size: int = Query(
          default=PAGINATION_DEFAULTS["page_size"],
          ge=1,
          le=PAGINATION_DEFAULTS["max_page_size"],
      ),
  ):
      # Decode cursor to get last_row_id
      last_row_id = decode_cursor(cursor) if cursor else None

      # Fetch items using keyset pagination (WHERE id > last_row_id)
      items, has_more = await repo.get_items_keyset(page_size, last_row_id)

      # Encode cursor for next page (last item's ID)
      next_cursor = encode_cursor(items[-1]["id"]) if items and has_more else None

      pagination = create_keyset_pagination_metadata(items, next_cursor, page_size)
      return MyListResponse(items=items, pagination=pagination)
  ```
"""

import base64
import json
from typing import TYPE_CHECKING, Final

if TYPE_CHECKING:
    from app.models.response import PaginationMetadata

__all__ = [
    "PAGINATION_DEFAULTS",
    "get_offset",
    "compute_total_pages",
    "create_pagination_metadata",
    "encode_cursor",
    "decode_cursor",
    "create_keyset_pagination_metadata",
]

# Standardized pagination defaults
PAGINATION_DEFAULTS: Final[dict[str, int]] = {
    "page": 1,
    "page_size": 100,
    "max_page_size": 500,
}


def get_offset(page: int, page_size: int) -> int:
    """Calculate the database offset for a given page and page size.

    Args:
        page: 1-based page number.
        page_size: Items per page.

    Returns:
        0-based database offset (number of items to skip).

    Raises:
        ValueError: If page or page_size is invalid (< 1).

    Example:
        ```python
        # Page 1, size 10 → offset 0
        assert get_offset(1, 10) == 0

        # Page 2, size 10 → offset 10
        assert get_offset(2, 10) == 10

        # Page 3, size 50 → offset 100
        assert get_offset(3, 50) == 100
        ```
    """
    if page < 1:
        raise ValueError(f"page must be >= 1, got {page}")
    if page_size < 1:
        raise ValueError(f"page_size must be >= 1, got {page_size}")

    return (page - 1) * page_size


def compute_total_pages(total: int, page_size: int) -> int:
    """Calculate the total number of pages needed.

    Args:
        total: Total number of items across all pages.
        page_size: Items per page.

    Returns:
        The number of pages required to hold all items. Always at least 1,
        even when total is 0 (an empty page is still a page).

    Raises:
        ValueError: If page_size is invalid (< 1).

    Example:
        ```python
        assert compute_total_pages(0, 10) == 1
        assert compute_total_pages(10, 10) == 1
        assert compute_total_pages(11, 10) == 2
        assert compute_total_pages(25, 5) == 5
        ```
    """
    if page_size < 1:
        raise ValueError(f"page_size must be >= 1, got {page_size}")

    if total == 0:
        return 1

    # Ceiling division: (total + page_size - 1) // page_size
    return (total + page_size - 1) // page_size


def create_pagination_metadata(total: int, page: int, page_size: int) -> "PaginationMetadata":
    """Create pagination metadata with computed derived fields.

    This factory function computes all pagination-related information in a single
    place, ensuring consistency across all paginated endpoints.

    Args:
        total: Total number of items across all pages.
        page: Current page number (1-based).
        page_size: Items per page.

    Returns:
        :class:`~app.models.response.PaginationMetadata` with computed fields:
        - total_pages: Computed total number of pages needed
        - has_next_page: Whether there is a next page
        - has_prev_page: Whether there is a previous page

    Example:
        ```python
        metadata = create_pagination_metadata(total=150, page=2, page_size=50)
        assert metadata.total_pages == 3
        assert metadata.has_next_page is True
        assert metadata.has_prev_page is True
        ```
    """
    from app.models.response import PaginationMetadata

    total_pages = compute_total_pages(total, page_size)
    has_next_page = page < total_pages
    has_prev_page = page > 1

    return PaginationMetadata(
        page=page,
        page_size=page_size,
        total=total,
        total_pages=total_pages,
        has_next_page=has_next_page,
        has_prev_page=has_prev_page,
    )


# ---------------------------------------------------------------------------
# Cursor-Based Pagination Functions
# ---------------------------------------------------------------------------


def encode_cursor(row_id: int) -> str:
    """Encode a row ID into an opaque cursor token.

    The cursor is a base64-encoded JSON object containing the row ID.
    This format is opaque to the client and must not be modified manually.

    Args:
        row_id: The database row ID to encode.

    Returns:
        Base64-encoded cursor string that can be passed to decode_cursor().

    Raises:
        ValueError: If row_id is invalid (< 1).

    Example:
        ```python
        cursor = encode_cursor(42)
        assert isinstance(cursor, str)
        assert decode_cursor(cursor) == 42
        ```
    """
    if row_id < 1:
        raise ValueError(f"row_id must be >= 1, got {row_id}")

    cursor_data = {"id": row_id}
    json_str = json.dumps(cursor_data, separators=(",", ":"))
    return base64.b64encode(json_str.encode()).decode("ascii")


def decode_cursor(cursor: str) -> int:
    """Decode an opaque cursor token to retrieve the row ID.

    Decodes a base64-encoded JSON object containing the row ID.
    This is the inverse of encode_cursor().

    Args:
        cursor: Cursor string produced by encode_cursor().

    Returns:
        The row ID stored in the cursor.

    Raises:
        ValueError: If cursor is invalid (not base64-decodable or missing 'id' field).

    Example:
        ```python
        cursor = encode_cursor(42)
        assert decode_cursor(cursor) == 42
        ```
    """
    try:
        json_str = base64.b64decode(cursor.encode("ascii")).decode("utf-8")
        cursor_data = json.loads(json_str)
        row_id = cursor_data.get("id")
        if not isinstance(row_id, int) or row_id < 1:
            raise ValueError(f"Invalid cursor: 'id' field must be an integer >= 1, got {row_id}")
        return row_id
    except (ValueError, TypeError, json.JSONDecodeError) as e:
        raise ValueError(f"Invalid cursor format: {e}") from e


def create_keyset_pagination_metadata(
    items: list[dict[str, object]] | list[object],
    next_cursor: str | None,
    page_size: int,
) -> "PaginationMetadata":
    """Create pagination metadata for keyset (cursor-based) pagination.

    This function creates metadata for cursor-based pagination without the need
    to query the total row count. Frontend can determine if there are more pages
    by checking if the returned items count equals page_size.

    Args:
        items: The items returned from the keyset query (fetched count + 1).
        next_cursor: Cursor for fetching the next page, or None if no more pages.
        page_size: The requested page size.

    Returns:
        :class:`~app.models.response.PaginationMetadata` adapted for cursor pagination.
        Note: total and total_pages are set to -1 (unknown), has_prev_page is always False.

    Example:
        ```python
        items = await repo.get_items_keyset(page_size=10, last_row_id=None)
        metadata = create_keyset_pagination_metadata(items, next_cursor, page_size=10)
        assert metadata.total == -1  # Unknown in cursor pagination
        assert metadata.has_next_page == (next_cursor is not None)
        ```
    """
    from app.models.response import PaginationMetadata

    has_next_page = next_cursor is not None

    return PaginationMetadata(
        page=1,
        page_size=page_size,
        total=-1,
        total_pages=-1,
        has_next_page=has_next_page,
        has_prev_page=False,
        cursor=next_cursor,
    )