fix: merge main, address code review feedback for security fix PR #816

- Merge origin/main into branch (resolve conflict in integrations_dashboard.html) - Add defensive JSON parsing with try/except for integration.config - Wrap tester() call in try/except to prevent 500 errors from bad config - Add i18n key integrations.connection_test_failed_fallback in en.json - Reference i18n key in template JS fallback message - Update SECURITY_AUDIT.md: add fix date (2026-03-23), update doc date - Remove accidental revert.sh file - Fix missing MagicMock/patch imports in test file - Add tests for invalid JSON config and tester exception error paths Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com> Agent-Logs-Url: https://github.com/christianlouis/DocuElevate/sessions/daebb70e-059a-4601-8864-88eef49f99cf
2026-03-23 16:21:09 +00:00
parent 41d6f682c0
commit 1a195a96bd
359 changed files with 139902 additions and 2252 deletions
@@ -84,6 +84,19 @@ class FileRecord(Base):
    # Processing pipeline assigned to this file (NULL = use system default)
    pipeline_id = Column(Integer, ForeignKey(_PIPELINES_ID_FK), nullable=True, index=True)

+    # Detected document language (ISO 639-1 code, e.g. "de", "en", "fr")
+    # Extracted from AI metadata during processing; cached here for fast access.
+    detected_language = Column(String(10), nullable=True)
+
+    # Default-language translation of the extracted text.
+    # Stored when the detected language differs from the user's/system default
+    # document language.  Only the original text and this translation are persisted;
+    # other languages are translated on the fly via the AI provider.
+    default_language_text = Column(Text, nullable=True)
+
+    # ISO 639-1 code of the default-language translation stored above (e.g. "en").
+    default_language_code = Column(String(10), nullable=True)
+
    # Timestamp when we inserted this record
    created_at = Column(DateTime(timezone=True), server_default=func.now(), index=True)

@@ -198,6 +211,28 @@ class WebhookConfig(Base):
    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())


+class AutomationHook(Base):
+    """Zapier / Make.com compatible webhook subscription for automation triggers.
+
+    External automation platforms subscribe to DocuElevate events via the REST
+    hooks protocol.  When an event fires, DocuElevate POSTs a Zapier-compatible
+    flat JSON payload to ``target_url``.  The ``hook_type`` field records which
+    platform created the subscription (informational only).
+    """
+
+    __tablename__ = "automation_hooks"
+
+    id = Column(Integer, primary_key=True, index=True)
+    target_url = Column(String, nullable=False)  # URL to POST events to
+    secret = Column(String, nullable=True)  # Optional HMAC-SHA256 signing secret
+    events = Column(Text, nullable=False)  # JSON list of subscribed event names
+    is_active = Column(Boolean, default=True, nullable=False)
+    hook_type = Column(String(50), nullable=False, default="generic")  # zapier | make | generic
+    description = Column(String, nullable=True)  # Optional human-readable label
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+
 class LocalUser(Base):
    """A locally-registered user authenticated by email and bcrypt password.

@@ -282,6 +317,12 @@ class UserProfile(Base):
    # NULL means "auto-detect from browser Accept-Language header"
    preferred_language = Column(String(10), nullable=True)

+    # Default document language for translated versions (ISO 639-1 code).
+    # When a document's detected language differs from this value, the system
+    # automatically generates and stores a translation into this language.
+    # NULL means "use the global DEFAULT_DOCUMENT_LANGUAGE setting".
+    default_document_language = Column(String(10), nullable=True)
+
    # UI colour scheme preference: "light" | "dark" | "system" (NULL = "system")
    preferred_theme = Column(String(10), nullable=True)

@@ -584,6 +625,7 @@ class IntegrationType:
    EMAIL = "EMAIL"
    PAPERLESS = "PAPERLESS"
    RCLONE = "RCLONE"
+    SHAREPOINT = "SHAREPOINT"
    ICLOUD = "ICLOUD"

    ALL = {
@@ -601,6 +643,7 @@ class IntegrationType:
        EMAIL,
        PAPERLESS,
        RCLONE,
+        SHAREPOINT,
        ICLOUD,
    }

@@ -765,6 +808,9 @@ class ApiToken(Base):
    created_at = Column(DateTime(timezone=True), server_default=func.now())
    revoked_at = Column(DateTime(timezone=True), nullable=True)

+    # Optional expiry: if set, the token is rejected after this timestamp.
+    expires_at = Column(DateTime(timezone=True), nullable=True)
+

 class SharedLink(Base):
    """Shareable, time-limited or view-limited document link.
@@ -916,6 +962,51 @@ class ScheduledJob(Base):
    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())


+class ClassificationRuleModel(Base):
+    """Custom document classification rule.
+
+    Rules are evaluated during the ``classify`` pipeline step to assign a
+    category to a document.  System-wide rules have ``owner_id IS NULL``;
+    user-specific rules belong to a single owner.
+    """
+
+    __tablename__ = "classification_rules"
+
+    id = Column(Integer, primary_key=True, index=True)
+
+    # NULL = system-wide rule visible to all users.
+    owner_id = Column(String, nullable=True, index=True)
+
+    # Human-readable rule name (unique per owner).
+    name = Column(String(255), nullable=False)
+
+    # Target category (e.g. "invoice", "contract", "receipt").
+    category = Column(String(100), nullable=False, index=True)
+
+    # Rule type: "filename_pattern", "content_keyword", or "metadata_match".
+    rule_type = Column(String(50), nullable=False)
+
+    # The matching pattern:
+    #   - filename_pattern: a regex
+    #   - content_keyword: pipe-separated keywords
+    #   - metadata_match: "field=value"
+    pattern = Column(String(1000), nullable=False)
+
+    # Higher priority rules are evaluated first (default 0).
+    priority = Column(Integer, nullable=False, default=0)
+
+    # Whether pattern matching is case-sensitive.
+    case_sensitive = Column(Boolean, nullable=False, default=False)
+
+    # Disabled rules are skipped during classification.
+    enabled = Column(Boolean, nullable=False, default=True)
+
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+    __table_args__ = (UniqueConstraint("owner_id", "name", name="uq_classification_rules_owner_name"),)
+
+
 class MobileDevice(Base):
    """Registered mobile device for push notifications.

@@ -950,6 +1041,86 @@ class MobileDevice(Base):
    __table_args__ = (UniqueConstraint("owner_id", "push_token", name="uq_mobile_device_owner_token"),)


+class UserSession(Base):
+    """Server-side session tracking for invalidation and device management.
+
+    Each row represents an active browser or app session.  The ``session_token``
+    is stored in the user's cookie and validated on every authenticated request.
+    Revoking a row (``is_revoked=True``) immediately terminates that session
+    on the next request.
+    """
+
+    __tablename__ = "user_sessions"
+
+    id = Column(Integer, primary_key=True, index=True)
+
+    # Cryptographically random token stored in the session cookie.
+    session_token = Column(String(128), unique=True, nullable=False, index=True)
+
+    # Stable owner identifier — matches FileRecord.owner_id.
+    user_id = Column(String, nullable=False, index=True)
+
+    # Client metadata for display in the session management UI.
+    ip_address = Column(String(45), nullable=True)
+    user_agent = Column(String(512), nullable=True)
+    device_info = Column(String(255), nullable=True)
+
+    is_revoked = Column(Boolean, nullable=False, default=False)
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    last_active_at = Column(DateTime(timezone=True), server_default=func.now())
+    expires_at = Column(DateTime(timezone=True), nullable=False)
+    revoked_at = Column(DateTime(timezone=True), nullable=True)
+
+
+class QRLoginChallenge(Base):
+    """Time-limited QR code login challenge for mobile app authentication.
+
+    A logged-in web user generates a challenge that produces a QR code.  The
+    mobile app scans the QR code and calls the claim endpoint with the
+    ``challenge_token``.  The server verifies the challenge is still valid,
+    unclaimed, and unexpired, then issues an API token for the mobile app.
+
+    Security properties:
+    * Time-bound (default 2 minutes).
+    * Single-use (``is_claimed`` prevents replay).
+    * Cryptographically random 64-byte token.
+    * Bound to the creating user — only that user's mobile device receives a
+      token.
+    """
+
+    __tablename__ = "qr_login_challenges"
+
+    id = Column(Integer, primary_key=True, index=True)
+
+    # Cryptographically random token encoded in the QR code.
+    challenge_token = Column(String(128), unique=True, nullable=False, index=True)
+
+    # The user who created this challenge (from the web session).
+    user_id = Column(String, nullable=False, index=True)
+
+    # Whether the challenge has been successfully claimed by a mobile app.
+    is_claimed = Column(Boolean, nullable=False, default=False)
+
+    # Whether the challenge has been explicitly cancelled or expired.
+    is_cancelled = Column(Boolean, nullable=False, default=False)
+
+    # IP address of the web client that created the challenge.
+    created_by_ip = Column(String(45), nullable=True)
+
+    # IP address of the mobile client that claimed the challenge.
+    claimed_by_ip = Column(String(45), nullable=True)
+
+    # Device name provided by the mobile app when claiming.
+    device_name = Column(String(255), nullable=True)
+
+    # The API token ID that was issued to the mobile app (for audit trail).
+    issued_token_id = Column(Integer, nullable=True)
+
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    expires_at = Column(DateTime(timezone=True), nullable=False)
+    claimed_at = Column(DateTime(timezone=True), nullable=True)
+
+
 class ComplianceTemplate(Base):
    """Pre-built compliance configuration templates (GDPR, HIPAA, SOC2).

@@ -1021,3 +1192,97 @@ class PipelineRoutingRule(Base):

    created_at = Column(DateTime(timezone=True), server_default=func.now())
    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+
+class DocumentComment(Base):
+    """Threaded comment on a document.
+
+    Supports threaded replies via ``parent_id`` and @mentions via the
+    ``mentions`` column (comma-separated user identifiers).
+    """
+
+    __tablename__ = "document_comments"
+
+    id = Column(Integer, primary_key=True, index=True)
+    file_id = Column(Integer, ForeignKey(_FILES_ID_FK), nullable=False, index=True)
+    user_id = Column(String, nullable=False, index=True)
+    parent_id = Column(Integer, ForeignKey("document_comments.id"), nullable=True, index=True)
+    body = Column(Text, nullable=False)
+    mentions = Column(Text, nullable=True)
+    is_resolved = Column(Boolean, nullable=False, default=False, server_default="0")
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+
+class DocumentAnnotation(Base):
+    """Text annotation on a specific page and position of a PDF document.
+
+    Stores the bounding-box coordinates (``x``, ``y``, ``width``,
+    ``height``) relative to the page dimensions so that the annotation
+    can be rendered on top of the PDF viewer.
+    """
+
+    __tablename__ = "document_annotations"
+
+    id = Column(Integer, primary_key=True, index=True)
+    file_id = Column(Integer, ForeignKey(_FILES_ID_FK), nullable=False, index=True)
+    user_id = Column(String, nullable=False, index=True)
+    page = Column(Integer, nullable=False)
+    x = Column(Float, nullable=False)
+    y = Column(Float, nullable=False)
+    width = Column(Float, nullable=False, default=0)
+    height = Column(Float, nullable=False, default=0)
+    content = Column(Text, nullable=False)
+    annotation_type = Column(String(50), nullable=False, default="note", server_default="note")
+    color = Column(String(20), nullable=True)
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+
+# ---------------------------------------------------------------------------
+# File sharing
+# ---------------------------------------------------------------------------
+
+# Valid roles for FileShare.role
+FILE_SHARE_ROLE_VIEWER = "viewer"
+FILE_SHARE_ROLE_EDITOR = "editor"
+FILE_SHARE_ROLES = (FILE_SHARE_ROLE_VIEWER, FILE_SHARE_ROLE_EDITOR)
+
+
+class FileShare(Base):
+    """Grants a named user access to a ``FileRecord`` owned by someone else.
+
+    The ``owner_id`` column records who created the share (must be the file
+    owner).  ``shared_with_user_id`` is the recipient's stable user
+    identifier (the same kind of string used in ``FileRecord.owner_id``).
+
+    Roles
+    -----
+    ``viewer``  — can read the file, comments, and annotations; may add
+                  comments/annotations; cannot delete or share.
+    ``editor``  — all viewer rights plus the ability to edit document
+                  metadata; cannot delete or re-share.
+
+    Only the file owner may create, update, or revoke shares.
+    """
+
+    __tablename__ = "file_shares"
+
+    id = Column(Integer, primary_key=True, index=True)
+
+    # The document being shared.
+    file_id = Column(Integer, ForeignKey(_FILES_ID_FK), nullable=False, index=True)
+
+    # The user who granted the share (must match FileRecord.owner_id).
+    owner_id = Column(String, nullable=False, index=True)
+
+    # The user receiving the share.
+    shared_with_user_id = Column(String, nullable=False, index=True)
+
+    # "viewer" or "editor"
+    role = Column(String(20), nullable=False, default=FILE_SHARE_ROLE_VIEWER)
+
+    created_at = Column(DateTime(timezone=True), server_default=func.now())
+    updated_at = Column(DateTime(timezone=True), server_default=func.now(), onupdate=func.now())
+
+    __table_args__ = (UniqueConstraint("file_id", "shared_with_user_id", name="uq_file_share_file_user"),)