WIP checkpoint: Text filtering service + profanity config

backend/app/services/__init__.py

@@ -0,0 +1 @@
+"""Application services."""

backend/app/services/text_filter.py

@@ -0,0 +1,340 @@
+"""Pluggable server-side text filtering service.
+
+Provides a ``TextFilter`` protocol with a deterministic default
+implementation (profanity/term list with normalization) and a hook
+for third-party providers.
+
+Usage::
+
+    from app.services.text_filter import TextFilter, FilterResult, \
+        ProfanityTextFilter, get_text_filter
+
+    # Default factory reads config from the path below
+    filt = get_text_filter()
+    result = filt.check("Hello wor1d!")
+    # result.action == FilterAction.ALLOW
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+import unicodedata
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from enum import Enum
+from pathlib import Path
+from typing import Any
+
+# ---------------------------------------------------------------------------
+# Enums / Data classes
+# ---------------------------------------------------------------------------
+
+
+class FilterAction(str, Enum):
+    """Action the filter wants the caller to take."""
+
+    ALLOW = "allow"
+    REDACT = "redact"
+    REJECT = "reject"
+
+
+@dataclass(frozen=True)
+class FilterResult:
+    """Immutable result of a single ``TextFilter.check()`` call.
+
+    Attributes:
+        action: What to do with the message.
+        filtered_text: The text after redaction (may equal *text* if
+            action is ``ALLOW``).
+        matched_terms: Sorted list of terms that triggered the filter.
+    """
+
+    action: FilterAction
+    filtered_text: str
+    matched_terms: list[str] = field(default_factory=list)
+
+    @property
+    def is_allowed(self) -> bool:
+        return self.action == FilterAction.ALLOW
+
+    @property
+    def is_rejected(self) -> bool:
+        return self.action == FilterAction.REJECT
+
+    @property
+    def is_redacted(self) -> bool:
+        return self.action == FilterAction.REDACT
+
+
+# ---------------------------------------------------------------------------
+# Protocol / abstract base
+# ---------------------------------------------------------------------------
+
+
+class TextFilter(ABC):
+    """Protocol for server-side text filters.
+
+    Every concrete filter must implement ``check()``.  The default
+    implementation (``ProfanityTextFilter``) is deterministic and
+    requires no external service.  A third-party provider can be
+    plugged in by subclassing ``TextFilter`` and overriding ``check``.
+    """
+
+    @abstractmethod
+    def check(self, text: str) -> FilterResult:
+        """Analyse *text* and return a ``FilterResult``.
+
+        Args:
+            text: Raw message text to filter.
+
+        Returns:
+            A ``FilterResult`` with the decision and any redacted text.
+        """
+
+
+# ---------------------------------------------------------------------------
+# Normalisation helpers
+# ---------------------------------------------------------------------------
+
+# Common leetspeak substitutions (char -> set of possible originals)
+_LEETSPEAK: dict[str, str] = {
+    "0": "o",
+    "1": "i",
+    "3": "e",
+    "4": "a",
+    "5": "s",
+    "7": "t",
+    "8": "b",
+    "9": "g",
+    "@": "a",
+}
+
+# Normalise separators that are often used to obfuscate words
+_SEPARATORS = re.compile(r"[\s_\-\.]+")
+
+
+def _normalize(text: str) -> str:
+    """Case-fold, strip diacritics, and replace leetspeak / separators.
+
+    This produces a canonical form for matching against the term list.
+    """
+    # Case-fold
+    text = text.casefold()
+    # Strip diacritics (e.g. é -> e)
+    text = unicodedata.normalize("NFKD", text)
+    text = "".join(c for c in text if not unicodedata.combining(c))
+    # Replace leetspeak
+    normalized = ""
+    for ch in text:
+        normalized += _LEETSPEAK.get(ch, ch)
+    # Collapse separators
+    normalized = _SEPARATORS.sub("", normalized)
+    return normalized
+
+
+# ---------------------------------------------------------------------------
+# Default implementation
+# ---------------------------------------------------------------------------
+
+# Default config path (relative to project root)
+_DEFAULT_CONFIG_PATH = Path(__file__).resolve().parent.parent.parent / "data" / "text_filter_config.json"
+
+
+@dataclass
+class _FilterPolicy:
+    """Filtering policy loaded from config."""
+
+    mode: str  # "redact" or "reject"
+    redaction_char: str = "*"
+    # Minimum term length to consider (avoids matching single chars)
+    min_term_length: int = 3
+    # If True, match terms case-insensitively after normalisation
+    case_insensitive: bool = True
+    # If True, match whole words only (after normalisation)
+    whole_word: bool = True
+
+
+class ProfanityTextFilter(TextFilter):
+    """Deterministic text filter backed by a JSON term list.
+
+    The config file is a JSON object with:
+
+    .. code-block:: json
+
+        {
+            "mode": "redact",
+            "redaction_char": "*",
+            "min_term_length": 3,
+            "case_insensitive": true,
+            "whole_word": true,
+            "terms": ["badword", "another", ...]
+        }
+
+    Terms are matched after normalisation (case-fold, leetspeak
+    substitution, separator removal, diacritic stripping).
+    """
+
+    def __init__(
+        self,
+        config_path: str | Path | None = None,
+        terms: list[str] | None = None,
+        policy: _FilterPolicy | None = None,
+    ) -> None:
+        """
+        Args:
+            config_path: Path to a JSON config file.  Ignored if *terms*
+                is provided.
+            terms: Inline list of terms (overrides config file).
+            policy: Filter policy.  Defaults to a redact policy.
+        """
+        if terms is not None:
+            self._terms: list[str] = [t.lower() for t in terms]
+        elif config_path is not None:
+            self._terms = self._load_terms(Path(config_path))
+        else:
+            # Try default path
+            if _DEFAULT_CONFIG_PATH.exists():
+                self._terms = self._load_terms(_DEFAULT_CONFIG_PATH)
+            else:
+                self._terms = []
+
+        self._policy = policy or _FilterPolicy(mode="redact")
+        # Pre-compile patterns for each term
+        self._patterns: list[tuple[re.Pattern[str], str]] = []
+        for term in self._terms:
+            if len(term) < self._policy.min_term_length:
+                continue
+            if self._policy.whole_word:
+                pattern = re.compile(
+                    r"(?<!\w)" + re.escape(term) + r"(?!\w)",
+                    re.IGNORECASE if self._policy.case_insensitive else 0,
+                )
+            else:
+                pattern = re.compile(
+                    re.escape(term),
+                    re.IGNORECASE if self._policy.case_insensitive else 0,
+                )
+            self._patterns.append((pattern, term))
+
+    # -- config loading --------------------------------------------------
+
+    @staticmethod
+    def _load_terms(config_path: Path) -> list[str]:
+        """Load terms from a JSON config file."""
+        with open(config_path, "r", encoding="utf-8") as f:
+            data: dict[str, Any] = json.load(f)
+
+        terms: list[str] = []
+        for raw in data.get("terms", []):
+            term = str(raw).strip()
+            if term:
+                terms.append(term.casefold())
+        return terms
+
+    # -- public API ------------------------------------------------------
+
+    def check(self, text: str) -> FilterResult:
+        """Check *text* against the loaded term list.
+
+        Returns a ``FilterResult`` with the appropriate action,
+        filtered text, and matched terms.
+        """
+        if not text:
+            return FilterResult(
+                action=FilterAction.ALLOW,
+                filtered_text=text,
+                matched_terms=[],
+            )
+
+        normalized = _normalize(text)
+        matched_terms: list[str] = []
+
+        # Collect all matches
+        for pattern, term in self._patterns:
+            if pattern.search(normalized):
+                if term not in matched_terms:
+                    matched_terms.append(term)
+
+        if not matched_terms:
+            return FilterResult(
+                action=FilterAction.ALLOW,
+                filtered_text=text,
+                matched_terms=[],
+            )
+
+        matched_terms.sort()
+
+        # Build filtered text by replacing matched terms
+        filtered = text
+        for term in matched_terms:
+            norm_term = _normalize(term)
+            # Find all occurrences in the normalised text and replace in original
+            # We need to map positions from normalised text back to original
+            filtered = self._replace_terms(filtered, term, norm_term)
+
+        action = FilterAction.REJECT if self._policy.mode == "reject" else FilterAction.REDACT
+
+        return FilterResult(
+            action=action,
+            filtered_text=filtered,
+            matched_terms=matched_terms,
+        )
+
+    def _replace_terms(
+        self, text: str, term: str, norm_term: str
+    ) -> str:
+        """Replace occurrences of *term* in *text* with redaction chars.
+
+        Uses normalised text for matching but preserves original casing
+        in the output.
+        """
+        norm_text = _normalize(text)
+        norm_term_len = len(norm_term)
+        result_chars = list(text)
+
+        start = 0
+        while start < len(norm_text):
+            idx = norm_text.find(norm_term, start)
+            if idx == -1:
+                break
+            # Replace characters in original text
+            for i in range(idx, min(idx + norm_term_len, len(result_chars))):
+                result_chars[i] = self._policy.redaction_char
+            start = idx + norm_term_len
+
+        return "".join(result_chars)
+
+    @property
+    def terms(self) -> list[str]:
+        """Read-only access to the loaded term list."""
+        return list(self._terms)
+
+    @property
+    def policy(self) -> _FilterPolicy:
+        """Read-only access to the filter policy."""
+        return self._policy
+
+
+# ---------------------------------------------------------------------------
+# Factory
+# ---------------------------------------------------------------------------
+
+
+def get_text_filter(
+    config_path: str | Path | None = None,
+    terms: list[str] | None = None,
+    policy: _FilterPolicy | None = None,
+) -> TextFilter:
+    """Return a ``TextFilter`` instance.
+
+    By default this creates a ``ProfanityTextFilter``.  To use a
+    third-party provider, subclass ``TextFilter`` and pass an
+    instance here instead.
+    """
+    return ProfanityTextFilter(
+        config_path=config_path,
+        terms=terms,
+        policy=policy,
+    )

docs/planning/social.md

@@ -0,0 +1,170 @@
+# Social — Friends, Chat & Groups — Plan
+
+> **Status:** Planned
+> **Owner:** Platform team
+> **Feature ID:** `social`
+> **Godot version:** 4.6.2 stable
+> **Backend:** FastAPI + SQLAlchemy (async) + PostgreSQL + Redis
+
+## 1. Overview
+
+This document breaks the **Social** feature into user stories and right-sized
+implementation tasks. The feature delivers:
+
+- **Friends & following** — a friend request/accept model plus a one-way follow
+  relationship, with block lists.
+- **Presence & status** — online/offline, custom status message, last-seen.
+- **Chat** — direct messages (DM) and in-experience (world/room) chat with
+  **first-class safety**: server-side text filtering, report-message, and rate
+  limiting.
+- **Groups** — named groups with roles (owner/admin/member) and a simple group
+  page.
+- **Public profiles** — avatar, bio, favorite experiences, and a friends list
+  that respects privacy settings.
+
+## 2. Why chat safety is the differentiator
+
+The platform is explicitly meant to pull adults away from a youth-oriented
+competitor. Chat is the highest-risk surface: it is real-time, user-generated,
+and where abuse happens fastest. Safety is therefore treated as a **blocking
+requirement**, not an add-on:
+
+- Every message passes a **server-side text filter** before it is stored or
+  delivered. The client filter is cosmetic only; the server is authoritative.
+- Every message can be **reported**; reports flow into a moderation queue with
+  actor + reason + audit trail (mirroring `content_moderation.md`).
+- Sending is **rate limited** per user (Redis token bucket) to stop flooding and
+  harassment-by-volume.
+- Report and block are always reachable from a message context in the UI.
+
+## 3. Existing constraints (do not re-build)
+
+- **Auth:** JWT bearer tokens; `get_current_user` / `CurrentUser` dependency in
+  `app/dependencies.py`. All social endpoints reuse this.
+- **DB:** async SQLAlchemy + Alembic; migration `0001_initial` is the head.
+- **Redis:** configured (`REDIS_URL`) but unused so far; adopted here for
+  presence and rate limiting.
+- **Models:** `User`, `World` (owner_id), `Asset` (owner_id, is_public). Avatars
+  and favorite-experience references point at existing rows.
+- **Client:** Godot 4.6.2, minimal `main_menu.gd`; no social UI yet.
+
+## 4. Key design decisions
+
+| Concern | Decision |
+|---|---|
+| Message transport | REST for send/history; **WebSocket** gateway for real-time delivery + presence (matches `networking.md`'s "WebSocket as secondary transport" for chat) |
+| Presence store | Redis (TTL heartbeat) + persisted `last_seen_at` on the user record |
+| Text filtering | Pluggable `TextFilter` interface with a deterministic default (profanity list + normalization) so it runs without external services; third-party hook later |
+| Rate limiting | Redis token-bucket dependency, reusable across all social endpoints |
+| Reports | `message_reports` table + moderation endpoints (list/review/resolve) with audit fields |
+| Friends vs. follow | Friends = mutual (request→accept). Follow = one-way (no approval). Block = hard deny that also hides content and prevents DMs |
+| Privacy | Per-user settings JSON (`profile_visibility`, `friends_list_visibility`, `favorites_visibility`) enforced server-side on every read |
+| Groups | `groups` + `group_members` (role: owner/admin/member) + group page aggregate endpoint |
+| Real-time | One WebSocket endpoint multiplexing presence, DM, and world-chat messages via Redis pub/sub |
+
+## 5. User stories
+
+### US-1 Friends & following
+As a player, I can send a friend request, accept/decline incoming requests,
+unfriend, follow/unfollow other players, and block users so they can't interact
+with me.
+
+**Acceptance criteria**
+- Friend requests are one-directional until accepted; accepted friendships are mutual.
+- Follow is one-way and requires no approval.
+- Block prevents DMs, hides the blocked user's profile/friends interactions, and
+  removes any existing friendship/follow between the two.
+- Duplicate/self requests are rejected idempotently.
+
+### US-2 Presence & status
+As a player, I can see whether my friends are online, their custom status, and
+when they were last seen.
+
+**Acceptance criteria**
+- Online/offline is derived from a server-side heartbeat (Redis TTL), not client claims.
+- `last_seen_at` persists and is visible (subject to privacy settings).
+- Custom status text is optional and length-limited.
+
+### US-3 Public profiles
+As a player, I can view a public profile page showing avatar, bio, favorite
+experiences, and a friends list that respects the owner's privacy settings.
+
+**Acceptance criteria**
+- Avatar and bio are editable by the owner only.
+- Favorite experiences reference existing `World` rows.
+- A viewer sees only the sections the owner's privacy settings allow; blocked
+  users see a restricted view.
+
+### US-4 Chat (DM + in-experience) with safety
+As a player, I can send direct messages and chat inside a world/room. Messages
+are filtered, rate limited, and reportable.
+
+**Acceptance criteria**
+- Server filters message text before storing/delivering; filtered content is either
+  rejected (blocking) or redacted (configurable per filter policy).
+- Send rate is limited per user (token bucket); excess sends get `429`.
+- Every message has a stable id, author, timestamp, and conversation/world scope.
+- Any message can be reported with a reason; reports are stored and reviewable.
+- Real-time delivery over WebSocket with REST fallback for history.
+
+### US-5 Groups
+As a player, I can create a group, join/leave groups, and (as owner/admin)
+manage roles and view a simple group page.
+
+**Acceptance criteria**
+- Each group has exactly one owner and any number of admins/members.
+- Role transitions are authorized (only owner can transfer ownership or promote/demote admins).
+- Group page lists name, description, member list with roles, and member count.
+
+### US-6 Godot client
+As a player, I can access friends, presence, chat, profiles, and groups from the
+game UI.
+
+**Acceptance criteria**
+- An API client handles JWT auth, HTTP, and WebSocket for all social calls.
+- Dedicated screens/panels: friends+presence, DM & world chat (with report),
+  profile page, group page.
+- Client-side filtering is cosmetic; server responses remain authoritative.
+
+## 6. Task breakdown
+
+Right-sized to 1–3 files / one coherent piece of functionality each. Task IDs
+are sequential for dependency chaining.
+
+| # | Task | Story | Depends on |
+|---|------|-------|-----------|
+| 1 | Friends/follow/block models + Alembic migration | US-1 | — |
+| 2 | Friends & follow API router | US-1 | 1 |
+| 3 | Presence & status model + endpoints (Redis heartbeat) | US-2 | — |
+| 4 | Profile model + migration + own-profile endpoints | US-3 | 1 |
+| 5 | Public profile view + favorites + privacy enforcement | US-3 | 2, 4 |
+| 6 | Chat data models + migration (conversations, messages, reports) | US-4 | — |
+| 7 | Text filtering service + profanity config | US-4 | — |
+| 8 | Redis rate-limiting dependency | US-4 | — |
+| 9 | DM chat send/list endpoints (filter + rate limit) | US-4 | 6, 7, 8 |
+| 10 | Report-message endpoint + moderation queue | US-4 | 6, 9 |
+| 11 | In-experience (world/room) chat endpoints | US-4 | 9 |
+| 12 | Real-time WebSocket gateway (presence + DM + world chat) | US-4 | 3, 9, 11 |
+| 13 | Group + membership models + migration | US-5 | — |
+| 14 | Groups API (CRUD, join/leave, roles, group page) | US-5 | 13 |
+| 15 | Godot API client (auth + HTTP + WebSocket) | US-6 | 2 |
+| 16 | Godot friends & presence UI | US-6 | 3, 15 |
+| 17 | Godot chat UI (DM + world chat + report) | US-6 | 12, 15 |
+| 18 | Godot profile page UI | US-6 | 5, 15 |
+| 19 | Godot groups UI + group page | US-6 | 14, 15 |
+
+## 7. Phasing
+
+- **Phase 1 (data + core APIs):** tasks 1–5 (friends, presence, profiles).
+- **Phase 2 (chat safety — the differentiator):** tasks 6–12 (chat + safety +
+  realtime). This is the critical path and highest priority.
+- **Phase 3 (groups):** tasks 13–14.
+- **Phase 4 (client):** tasks 15–19, each landing after its backend dependency.
+
+## 8. Out of scope for this feature
+
+- Age verification / maturity gating (covered by `content_moderation.md`).
+- Voice chat, media/image messages, message editing/deletion history.
+- Third-party profanity/toxicity vendors (the `TextFilter` interface leaves a
+  hook, but the default is deterministic and dependency-free).
+- Mobile push notifications.