Office365-REST-Python-Client 3.1.0__py3-none-any.whl → 3.2.0__py3-none-any.whl

office365/migration/assessment/scanners/base.py

@@ -3,11 +3,12 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
-from typing import Any, Generic, TypeVar
+from typing import Any, Generic, Optional, TypeVar
 
 from office365.migration.assessment.containers import ScanContainer
 from office365.migration.assessment.issue import AssessmentIssue
 from office365.migration.assessment.report import AssessmentReport
+from office365.runtime.limits import Limit
 
 PayloadT = TypeVar("PayloadT")
 RecordT = TypeVar("RecordT")
@@ -28,60 +29,45 @@ class ScanTarget(Generic[PayloadT]):
 
 @dataclass
 class AssessmentOptions:
-    """Configurable limits/heuristics used by the scanners (no hardcoded magic).
+    """Product-agnostic scanner options.
 
+    Product packages subclass this to seed the thresholds and the ``limits``
+    mapping from their catalog (e.g. ``SharePointAssessmentOptions``).
     ``disabled_scans`` mirrors SMAT's ScanDef.json ``Enabled`` flag: a scan
     listed here does not run and its data is not collected.
     """
 
-    max_path_length: int = 400
-    max_name_length: int = 128
-    invalid_chars: set[str] = field(default_factory=lambda: set(r'~"#%&*:<>?/\{|}'))
-    large_file_bytes: int = 15 * 1024 * 1024 * 1024  # 15GB file-size limit
-    large_site_threshold_gb: float = 500.0  # sites over 500GB migrate slower
-    strip_field_attrs: set[str] = field(default_factory=lambda: {"ColName", "RowOrdinal", "SourceID", "Version"})
-    approval_workflow_fields: set[str] = field(
-        default_factory=lambda: {"_ApprovalStatus", "_ApprovalRespondedBy", "_ApprovalAssignedTo"}
-    )
+    max_path_length: Optional[int] = None
+    max_name_length: Optional[int] = None
+    invalid_chars: set[str] = field(default_factory=set)
+    large_file_bytes: Optional[int] = None
+    large_excel_bytes: Optional[int] = None
+    long_onedrive_url: Optional[int] = None
+    list_view_threshold: Optional[int] = None
+    index_threshold: Optional[int] = None
+    max_list_items: Optional[int] = None
+    lookup_joins: Optional[int] = None
+    unique_scopes: Optional[int] = None
+    recommended_unique_scopes: Optional[int] = None
+    large_site_threshold_gb: Optional[float] = None
+    strip_field_attrs: set[str] = field(default_factory=set)
+    approval_workflow_fields: set[str] = field(default_factory=set)
     disabled_scans: set[str] = field(default_factory=lambda: {"permissions"})
     include_site_admins: bool = False
-    system_field_names: set[str] = field(
-        default_factory=lambda: {
-            "ContentTypeId",
-            "ContentType",
-            "ID",
-            "Created",
-            "Modified",
-            "Author",
-            "Editor",
-            "ComplianceAssetId",
-            "FileLeafRef",
-            "FileDirRef",
-            "FileRef",
-            "File_x0020_Type",
-            "File_x0020_Size",
-            "UniqueId",
-            "Version",
-            "owshiddenversion",
-            "Attachments",
-            "FSObjType",
-            "MetaInfo",
-            "Order",
-            "ScopeId",
-            "PermMask",
-            "EffectivePermMask",
-            "InstanceID",
-            "WorkflowVersion",
-            "_ModerationStatus",
-            "_ModerationComments",
-            "_CopySource",
-            "_HasCopyDestinations",
-            "_CheckinComment",
-            "_ColorHex",
-            "_ColorTag",
-            "_Emoji",
-        }
-    )
+    system_field_names: set[str] = field(default_factory=set)
+    #: Maps each threshold field to its source :class:`Limit` (seeded by the
+    #: product) so findings can reference the authoritative limit.
+    limits: dict[str, Limit] = field(default_factory=dict)
+
+    def limit(self, name: str) -> Limit:
+        """The source :class:`Limit` for a threshold field (from ``limits``)."""
+        limit = self.limits.get(name)
+        if limit is None:
+            value = getattr(self, name, None)
+            if value is None:
+                raise ValueError(f"no limit or value configured for {name!r}")
+            limit = Limit(name, int(value))
+        return limit
 
 
 class BaseScanner(Generic[RecordT]):
@@ -124,8 +110,10 @@ class BaseScanner(Generic[RecordT]):
         location: str,
         message: str,
         suggestion: str = "",
+        risk_code: str = "",
+        limit: Optional[Limit] = None,
     ) -> None:
-        report.issues.append(AssessmentIssue(severity, self.category, location, message, suggestion))
+        report.issues.append(AssessmentIssue(severity, self.category, location, message, suggestion, risk_code, limit))
 
     def run(self, target: ScanTarget[Any], report: AssessmentReport) -> None:
         """Inspect a loaded container payload (target.entity) and flag / record."""

office365/migration/base.py

@@ -7,6 +7,9 @@ from __future__ import annotations
 from dataclasses import asdict, dataclass, field, fields
 from enum import Enum
 
+from office365.runtime.limits import DEFAULT_BATCH_SIZE
+from office365.runtime.operations import OperationStats
+
 
 class ConflictResolution(str, Enum):
     SKIP = "skip"
@@ -69,14 +72,26 @@ class MigrationItem:
     error: str | None = None  # failure message (SPMT "Message")
     error_code: str | None = None  # failure category/code (e.g. exception type name)
     modified: str | None = None  # source last-modified (ISO-8601), for incremental
+    created: str | None = None  # source created (ISO-8601)
+    author_id: int | None = None  # source author user id (system ``AuthorId``)
+    editor_id: int | None = None  # source last-modified-by user id (system ``EditorId``)
+
+
+@dataclass
+class PermissionEntry:
+    """A single principal → role-names grant, used for best-effort ACL preservation.
+
+    Produced by :meth:`DataSource.read_permissions` and consumed by
+    :meth:`DataTarget.apply_permissions`; role names are the target's role
+    definition names (e.g. ``"Read"``, ``"Edit"``, ``"Full Control"``).
+    """
+
+    principal_name: str
+    roles: list[str] = field(default_factory=list)
 
 
 @dataclass
-class MigrationStats:
-    total: int = 0
-    success: int = 0
-    skipped: int = 0
-    errors: int = 0
+class MigrationStats(OperationStats):
     bytes_transferred: int = 0
 
     def summary(self) -> str:
@@ -91,13 +106,23 @@ class MigrationStats:
 @dataclass
 class MigrationOptions:
     conflict_resolution: ConflictResolution = ConflictResolution.SKIP
-    incremental: bool = False  # skip items whose target is at least as new as the source
-    preserve_timestamps: bool = True
+    incremental: bool = False  # skip items at/below the persisted watermark (and target-newer ones)
+    # Fidelity flags. ``preserve_timestamps`` and ``preserve_permissions`` are
+    # applied client-side on a best-effort basis when the adapters support it
+    # (see ``DataSource.read_permissions`` / ``DataTarget.apply_timestamps`` /
+    # ``DataTarget.apply_permissions``); REST cannot restore version history, so
+    # ``preserve_versions`` requires the server-side Migration API
+    # (``MigrationServerJob``). Defaults are False so they are honest no-ops
+    # rather than silently doing nothing.
+    preserve_timestamps: bool = False
     preserve_permissions: bool = False
     preserve_versions: bool = False
     include_patterns: list[str] = field(default_factory=list)
     exclude_patterns: list[str] = field(default_factory=list)
-    batch_size: int = 100
+    # Date window (ISO-8601): skip items created/modified at or before these
+    created_after: str | None = None
+    modified_after: str | None = None
+    batch_size: int = DEFAULT_BATCH_SIZE
     concurrency: int = 1  # parallel workers for bulk file upload / batched writes
 
 

office365/migration/checkpoint.py

@@ -14,8 +14,8 @@ import uuid
 from dataclasses import dataclass, field
 from pathlib import Path
 
-from office365.migration._util import utc_now_iso
 from office365.migration.base import ItemStatus, MigrationItem, MigrationPhase
+from office365.runtime.converters.scalars import utc_now_iso
 
 
 @dataclass

office365/migration/outlook/assessor.py

@@ -9,12 +9,12 @@ dispatches to the registered scans. Reuses the shared :class:`AssessmentReport`
 
 from __future__ import annotations
 
-from office365.migration._util import coerce_int
 from office365.migration.assessment.containers import ScanContainer
 from office365.migration.assessment.report import AssessmentReport
 from office365.migration.assessment.runner import ScanRunner
 from office365.migration.outlook.registry import outlook_scan_pairs
 from office365.migration.outlook.scanner import MailFolderData, OutlookOptions
+from office365.runtime.converters.scalars import parse_int
 
 # Graph mailFolder properties the walker selects
 _FOLDER_COLUMNS = ["displayName", "totalItemCount", "unreadItemCount", "childFolderCount"]
@@ -45,9 +45,9 @@ class MailboxAssessor:
                 path = f"{parent_path}/{name}" if parent_path else name
                 folder_data = MailFolderData(
                     path=path,
-                    item_count=coerce_int(folder.total_item_count),
-                    unread_count=coerce_int(folder.unread_item_count),
-                    child_count=coerce_int(folder.child_folder_count),
+                    item_count=parse_int(folder.total_item_count),
+                    unread_count=parse_int(folder.unread_item_count),
+                    child_count=parse_int(folder.child_folder_count),
                 )
                 self.folder_count += 1
                 self.message_count += folder_data.item_count or 0

office365/migration/package/__init__.py

@@ -0,0 +1,82 @@
+"""SharePoint Migration API package — manifest XML models + a package builder.
+
+Assembles the XML manifest documents and content blobs ingested by the server-side
+Migration API (``Site.create_migration_job`` / ``create_migration_job_encrypted``).
+Covers the **document-library subset** (webs, lists, folders, files, versions).
+"""
+
+from __future__ import annotations
+
+from office365.migration.package.builder import DEFAULT_NAMESPACE, Package, PackageBuilder
+from office365.migration.package.manifest_xml import (
+    EXPORT_SETTINGS_NS,
+    LOOKUP_LIST_MAP_NS,
+    MANIFEST_NS,
+    REQUIREMENTS_NS,
+    ROOT_OBJECT_MAP_NS,
+    SOURCE_TYPES,
+    SYSTEM_DATA_NS,
+    USER_GROUP_MAP_NS,
+    VIEW_FORMS_LIST_NS,
+    Assignment,
+    DeploymentObject,
+    ExportSettings,
+    Group,
+    Manifest,
+    ManifestElement,
+    ManifestObject,
+    Role,
+    RoleAssignment,
+    RootObject,
+    RootObjectMap,
+    SharedWithEvent,
+    SystemData,
+    SystemObject,
+    User,
+    UserGroupMap,
+    empty_document,
+)
+from office365.migration.package.staging import (
+    AzureBlobStaging,
+    BlobStaging,
+    FileSystemStaging,
+    Staging,
+    create_staging,
+)
+
+__all__ = [
+    "DEFAULT_NAMESPACE",
+    "EXPORT_SETTINGS_NS",
+    "LOOKUP_LIST_MAP_NS",
+    "MANIFEST_NS",
+    "REQUIREMENTS_NS",
+    "ROOT_OBJECT_MAP_NS",
+    "SOURCE_TYPES",
+    "SYSTEM_DATA_NS",
+    "USER_GROUP_MAP_NS",
+    "VIEW_FORMS_LIST_NS",
+    "Assignment",
+    "AzureBlobStaging",
+    "BlobStaging",
+    "DeploymentObject",
+    "ExportSettings",
+    "FileSystemStaging",
+    "Group",
+    "Manifest",
+    "ManifestElement",
+    "ManifestObject",
+    "Package",
+    "PackageBuilder",
+    "Role",
+    "RoleAssignment",
+    "RootObject",
+    "RootObjectMap",
+    "SharedWithEvent",
+    "Staging",
+    "SystemData",
+    "SystemObject",
+    "User",
+    "UserGroupMap",
+    "create_staging",
+    "empty_document",
+]