Release kanopy-ai 0.5.0

README.md

@@ -131,6 +131,10 @@ outputs. Each entry has a stable `id`, a `kind`, a `format`, and a `version`
 token that only changes when the bytes change, so a synchronizing client can
 skip work it has already done:
 
+`size_bytes` is populated for stored files and is `None` for tables, camera
+poses, and packages rendered on demand; downloading those assets is the first
+time their final byte size is known.
+
 ```python
 for output in kanopy.list_job_outputs(job_id):
     if output["kind"] != "merged_point_cloud":
@@ -202,8 +206,16 @@ re-authentication.
 
 ## Pagination
 
-List methods return a `Page`. Offset pagination is used by default. Pass
-`cursor=""` to start keyset pagination, then use `page.next_cursor`:
+List methods return a `Page`. Offset pagination is used by default. For a full
+scan, the iterator helpers handle keyset cursors automatically:
+
+```python
+for job in kanopy.iter_jobs(limit=100):
+    print(job["id"], job["status"])
+```
+
+Pass `cursor=""` directly when you need page boundaries or pagination
+metadata, then use `page.next_cursor`:
 
 ```python
 page = kanopy.list_jobs(cursor="", limit=100)

scripts/check_dist.py

@@ -69,7 +69,8 @@ def sdist_names(path: Path) -> set[str]:
 
 for required in REQUIRED_LICENSE_FILES:
     if not any(
-        name.endswith(f".dist-info/licenses/{required}") for name in wheel_contents
+        name.endswith((f".dist-info/{required}", f".dist-info/licenses/{required}"))
+        for name in wheel_contents
     ):
         raise SystemExit(f"wheel is missing {required}")
 

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = kanopy-ai
-version = 0.4.0
+version = 0.5.0
 description = Python SDK for the Kanopy infrastructure inspection API
 long_description = file: README.md
 long_description_content_type = text/markdown

src/kanopy/__init__.py

@@ -5,4 +5,4 @@
 from .models import Page
 
 __all__ = ["DEFAULT_BASE_URL", "Kanopy", "KanopyError", "KanopyUploadError", "Page"]
-__version__ = "0.4.0"
+__version__ = "0.5.0"

src/kanopy/client.py

@@ -7,7 +7,7 @@
 import json
 import math
 import time
-from collections.abc import Callable, Iterable, Mapping, Sequence
+from collections.abc import Callable, Iterable, Iterator, Mapping, Sequence
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from contextlib import ExitStack
 from os import PathLike
@@ -237,6 +237,20 @@ def list_projects(
         )
         return self._page(response)
 
+    def iter_projects(self, *, limit: int = 100) -> Iterator[JsonObject]:
+        """Yield every accessible project using stable cursor pagination."""
+        cursor = ""
+        seen_cursors: set[str] = set()
+        while True:
+            page = self.list_projects(cursor=cursor, limit=limit)
+            yield from page.items
+            if not page.next_cursor:
+                return
+            if page.next_cursor in seen_cursors:
+                raise RuntimeError("Kanopy API returned a repeated project cursor")
+            seen_cursors.add(page.next_cursor)
+            cursor = page.next_cursor
+
     def create_project(
         self, *, name: str, description: str | None = None
     ) -> JsonObject:
@@ -271,12 +285,36 @@ def list_jobs(
         limit: int = 50,
         cursor: str | None = None,
         project_id: str | None = None,
+        skip_count: bool = False,
     ) -> Page[JsonObject]:
         params = self._pagination_params(skip=skip, limit=limit, cursor=cursor)
         if project_id is not None:
             params["project_id"] = project_id
+        if skip_count:
+            params["skip_count"] = True
         return self._page(self._request("GET", "/jobs", params=params))
 
+    def iter_jobs(
+        self, *, limit: int = 100, project_id: str | None = None
+    ) -> Iterator[JsonObject]:
+        """Yield every accessible job using stable cursor pagination."""
+        cursor = ""
+        seen_cursors: set[str] = set()
+        while True:
+            page = self.list_jobs(
+                cursor=cursor,
+                limit=limit,
+                project_id=project_id,
+                skip_count=bool(cursor),
+            )
+            yield from page.items
+            if not page.next_cursor:
+                return
+            if page.next_cursor in seen_cursors:
+                raise RuntimeError("Kanopy API returned a repeated job cursor")
+            seen_cursors.add(page.next_cursor)
+            cursor = page.next_cursor
+
     def list_project_jobs(
         self, project_id: str, *, skip: int = 0, limit: int = 50
     ) -> Page[JsonObject]: