dexverse-cli 0.1.3__tar.gz → 0.1.3.post2__tar.gz

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/.gitignore

@@ -1,12 +1,12 @@
-.venv/
-.venv-smoke/
-.venv-smoke-*/
-.smoke-work/
-.artifact-inspect/
-.manifest/
-.pytest_cache/
-.mypy_cache/
-.ruff_cache/
-__pycache__/
-*.py[cod]
-dist/
+.venv/
+.venv-smoke/
+.venv-smoke-*/
+.smoke-work/
+.artifact-inspect/
+.manifest/
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+__pycache__/
+*.py[cod]
+dist/

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/.python-version

@@ -1 +1 @@
-3.10
+3.10

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: dexverse-cli
-Version: 0.1.3
+Version: 0.1.3.post2
 Summary: Download, pack, and unpack DexVerse datasets
 Requires-Python: >=3.10
 Requires-Dist: av<17,>=14
@@ -43,6 +43,8 @@ type manifest.json | dexverse-dl download --manifest - --out ./dataset
 A manifest is either a JSON file list or an object containing `files`. Each
 file requires `download_url` and `file_name`. Optional fields are
 `storage_path`, `file_size`, `sha256`, `meta_data`, and `data_protocol`.
+Unknown top-level keys next to `files` (for example the `query_conditions` /
+`export_info` blocks written by the web batch export) are ignored.
 `data_protocol` is retained in the downloaded metadata sidecar. Downloaded metadata is
 stored in a versioned sidecar and becomes `task_instruction.json` when the
 corresponding HDF5 file is unpacked; only top-level `data_protocol` is removed

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/pyproject.toml

@@ -1,68 +1,68 @@
-[build-system]
-requires = ["hatchling>=1.27"]
-build-backend = "hatchling.build"
-
-[project]
-name = "dexverse-cli"
-version = "0.1.3"
-description = "Download, pack, and unpack DexVerse datasets"
-readme = "src/dexverse_cli/README.md"
-requires-python = ">=3.10"
-dependencies = [
-  "av>=14,<17",
-  "h5py>=3.11,<4",
-  "httpx>=0.28,<1",
-  "numpy>=1.26,<3",
-  "pillow>=10,<13",
-  "rich>=13.9,<15",
-  "typer>=0.16,<1",
-]
-
-[project.optional-dependencies]
-jetson = [
-  "PyGObject>=3.42,<4; platform_system == 'Linux'",
-]
-
-[project.scripts]
-dexverse-dl = "dexverse_cli.cli:app"
-
-[dependency-groups]
-dev = [
-  "mypy>=1.15,<2",
-  "pytest>=8.3,<10",
-  "ruff>=0.11,<1",
-]
-
-[tool.hatch.build.targets.wheel]
-packages = ["src/dexverse_cli"]
-
-[tool.hatch.build.targets.sdist]
-include = [
-  "/pyproject.toml",
-  "/uv.lock",
-  "/.python-version",
-  "/src/dexverse_cli",
-]
-
-[tool.pytest.ini_options]
-addopts = "-ra"
-testpaths = ["tests"]
-
-[tool.ruff]
-target-version = "py310"
-line-length = 120
-
-[tool.ruff.lint]
-select = ["E", "F", "I", "UP", "B", "SIM", "RUF", "TID252"]
-
-[tool.ruff.lint.flake8-tidy-imports]
-ban-relative-imports = "all"
-
-[tool.ruff.lint.per-file-ignores]
-"tests/**/*.py" = ["TID252"]
-
-[tool.mypy]
-python_version = "3.10"
-strict = true
-warn_unreachable = true
-ignore_missing_imports = true
+[build-system]
+requires = ["hatchling>=1.27"]
+build-backend = "hatchling.build"
+
+[project]
+name = "dexverse-cli"
+version = "0.1.3.post2"
+description = "Download, pack, and unpack DexVerse datasets"
+readme = "src/dexverse_cli/README.md"
+requires-python = ">=3.10"
+dependencies = [
+  "av>=14,<17",
+  "h5py>=3.11,<4",
+  "httpx>=0.28,<1",
+  "numpy>=1.26,<3",
+  "pillow>=10,<13",
+  "rich>=13.9,<15",
+  "typer>=0.16,<1",
+]
+
+[project.optional-dependencies]
+jetson = [
+  "PyGObject>=3.42,<4; platform_system == 'Linux'",
+]
+
+[project.scripts]
+dexverse-dl = "dexverse_cli.cli:app"
+
+[dependency-groups]
+dev = [
+  "mypy>=1.15,<2",
+  "pytest>=8.3,<10",
+  "ruff>=0.11,<1",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/dexverse_cli"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+  "/pyproject.toml",
+  "/uv.lock",
+  "/.python-version",
+  "/src/dexverse_cli",
+]
+
+[tool.pytest.ini_options]
+addopts = "-ra"
+testpaths = ["tests"]
+
+[tool.ruff]
+target-version = "py310"
+line-length = 120
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "UP", "B", "SIM", "RUF", "TID252"]
+
+[tool.ruff.lint.flake8-tidy-imports]
+ban-relative-imports = "all"
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**/*.py" = ["TID252"]
+
+[tool.mypy]
+python_version = "3.10"
+strict = true
+warn_unreachable = true
+ignore_missing_imports = true

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/src/dexverse_cli/README.md

@@ -1,107 +1,109 @@
-# dexverse-cli
-
-`dexverse-cli` downloads DexVerse dataset manifests over HTTP(S), packs strict
-raw sessions into versioned HDF5 files, and unpacks HDF5 sessions. It requires
-Python 3.10 or newer.
-
-## Install
-
-```console
-pip install dexverse-cli
-```
-
-## Download
-
-Read a manifest from a file:
-
-```console
-dexverse-dl download --manifest manifest.json --out ./dataset
-```
-
-Or pipe a short-lived manifest directly to stdin:
-
-```console
-type manifest.json | dexverse-dl download --manifest - --out ./dataset
-```
-
-A manifest is either a JSON file list or an object containing `files`. Each
-file requires `download_url` and `file_name`. Optional fields are
-`storage_path`, `file_size`, `sha256`, `meta_data`, and `data_protocol`.
-`data_protocol` is retained in the downloaded metadata sidecar. Downloaded metadata is
-stored in a versioned sidecar and becomes `task_instruction.json` when the
-corresponding HDF5 file is unpacked; only top-level `data_protocol` is removed
-from that algorithm-facing projection.
-
-Downloads use bounded parallelism, retries, and compatible partial-file resume.
-Within a manifest, the first occurrence of a target path keeps its name; later
-occurrences receive `-1`, `-2`, etc. before the final extension (for example,
-`episode1.hdf5`, `episode1-1.hdf5`, `episode1-2.hdf5`). Numbering skips names and
-paths already claimed by other entries, including partial files and metadata.
-Different relative directories remain independent. Names are assigned in manifest
-order, with Windows case-insensitive matching, before any downloads start.
-Rerunning the same manifest preserves the assigned names for skipping and resume;
-existing files on disk do not trigger new suffixes. This is not cross-batch name
-allocation: changing the manifest entries or their order can change the mapping.
-When `sha256` is present it is always checked before the final file is replaced.
-TLS certificate verification is disabled by default for internal endpoints;
-pass `--secure` to enable certificate verification.
-
-## Pack
-
-Pack one raw session, or the immediate session directories under a parent:
-
-```console
-dexverse-dl pack --input ./raw/session --output ./packed --format jpeg
-```
-
-JPEG is the platform-independent default. Packing validates the complete raw
-inventory, every image, all camera stream relationships, and pose data before
-transactionally replacing an output. Camera and pose counts may differ; pose is
-linearly aligned to the deterministic reference camera timeline.
-
-Jetson MP4 packing is optional:
-
-```console
-pip install "dexverse-cli[jetson]"
-dexverse-dl pack --input ./raw/session --output ./packed --format video
-```
-
-The Python extra does not install native Jetson GStreamer components. Video
-packing reports an explicit error unless the required hardware pipeline is
-available. JPEG packing, download, help, and unpack do not import GStreamer.
-
-## Unpack
-
-Unpack one HDF5 file:
-
-```console
-dexverse-dl unpack --input ./packed/session.hdf5 --output ./restored
-```
-
-Or recursively unpack `*.hdf5` files while preserving their relative paths:
-
-```console
-dexverse-dl unpack --input-dir ./packed --output ./restored
-```
-
-Unpacking validates the complete versioned schema before transactionally
-publishing a restored session. It also retains the supported unversioned HDF5
-read path.
-
-## Convert
-
-Convert one supported HDF5 file:
-
-```console
-dexverse-dl convert --input ./dataset/session.hdf5 --output ./restored
-```
-
-Or recursively convert `*.hdf5` files while preserving their relative paths:
-
-```console
-dexverse-dl convert --input-dir ./dataset --output ./restored
-```
-
-`convert` is the compatibility alias for `unpack`; it retains the same options,
-target mapping, legacy HDF5 support, exit codes, and `converted=...` summary.
-Batches continue after an item failure but exit with status 1 if any item fails.
+# dexverse-cli
+
+`dexverse-cli` downloads DexVerse dataset manifests over HTTP(S), packs strict
+raw sessions into versioned HDF5 files, and unpacks HDF5 sessions. It requires
+Python 3.10 or newer.
+
+## Install
+
+```console
+pip install dexverse-cli
+```
+
+## Download
+
+Read a manifest from a file:
+
+```console
+dexverse-dl download --manifest manifest.json --out ./dataset
+```
+
+Or pipe a short-lived manifest directly to stdin:
+
+```console
+type manifest.json | dexverse-dl download --manifest - --out ./dataset
+```
+
+A manifest is either a JSON file list or an object containing `files`. Each
+file requires `download_url` and `file_name`. Optional fields are
+`storage_path`, `file_size`, `sha256`, `meta_data`, and `data_protocol`.
+Unknown top-level keys next to `files` (for example the `query_conditions` /
+`export_info` blocks written by the web batch export) are ignored.
+`data_protocol` is retained in the downloaded metadata sidecar. Downloaded metadata is
+stored in a versioned sidecar and becomes `task_instruction.json` when the
+corresponding HDF5 file is unpacked; only top-level `data_protocol` is removed
+from that algorithm-facing projection.
+
+Downloads use bounded parallelism, retries, and compatible partial-file resume.
+Within a manifest, the first occurrence of a target path keeps its name; later
+occurrences receive `-1`, `-2`, etc. before the final extension (for example,
+`episode1.hdf5`, `episode1-1.hdf5`, `episode1-2.hdf5`). Numbering skips names and
+paths already claimed by other entries, including partial files and metadata.
+Different relative directories remain independent. Names are assigned in manifest
+order, with Windows case-insensitive matching, before any downloads start.
+Rerunning the same manifest preserves the assigned names for skipping and resume;
+existing files on disk do not trigger new suffixes. This is not cross-batch name
+allocation: changing the manifest entries or their order can change the mapping.
+When `sha256` is present it is always checked before the final file is replaced.
+TLS certificate verification is disabled by default for internal endpoints;
+pass `--secure` to enable certificate verification.
+
+## Pack
+
+Pack one raw session, or the immediate session directories under a parent:
+
+```console
+dexverse-dl pack --input ./raw/session --output ./packed --format jpeg
+```
+
+JPEG is the platform-independent default. Packing validates the complete raw
+inventory, every image, all camera stream relationships, and pose data before
+transactionally replacing an output. Camera and pose counts may differ; pose is
+linearly aligned to the deterministic reference camera timeline.
+
+Jetson MP4 packing is optional:
+
+```console
+pip install "dexverse-cli[jetson]"
+dexverse-dl pack --input ./raw/session --output ./packed --format video
+```
+
+The Python extra does not install native Jetson GStreamer components. Video
+packing reports an explicit error unless the required hardware pipeline is
+available. JPEG packing, download, help, and unpack do not import GStreamer.
+
+## Unpack
+
+Unpack one HDF5 file:
+
+```console
+dexverse-dl unpack --input ./packed/session.hdf5 --output ./restored
+```
+
+Or recursively unpack `*.hdf5` files while preserving their relative paths:
+
+```console
+dexverse-dl unpack --input-dir ./packed --output ./restored
+```
+
+Unpacking validates the complete versioned schema before transactionally
+publishing a restored session. It also retains the supported unversioned HDF5
+read path.
+
+## Convert
+
+Convert one supported HDF5 file:
+
+```console
+dexverse-dl convert --input ./dataset/session.hdf5 --output ./restored
+```
+
+Or recursively convert `*.hdf5` files while preserving their relative paths:
+
+```console
+dexverse-dl convert --input-dir ./dataset --output ./restored
+```
+
+`convert` is the compatibility alias for `unpack`; it retains the same options,
+target mapping, legacy HDF5 support, exit codes, and `converted=...` summary.
+Batches continue after an item failure but exit with status 1 if any item fails.

dexverse_cli-0.1.3.post2/src/dexverse_cli/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.3.post2"

{dexverse_cli-0.1.3 → dexverse_cli-0.1.3.post2}/src/dexverse_cli/alignment.py

@@ -1,45 +1,45 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-
-import numpy as np
-import numpy.typing as npt
-
-from dexverse_cli.raw_schema import RawSessionV1
-
-
-@dataclass(frozen=True, slots=True)
-class AlignedPoseV1:
-    data: npt.NDArray[np.float32]
-    timestamps: npt.NDArray[np.uint64]
-    columns: tuple[str, ...]
-
-
-class PackAlignmentPolicyV1:
-    """Linearly align pose values to the deterministic reference camera timeline."""
-
-    name = "linear_pose_to_reference_camera_v1"
-
-    def align(self, session: RawSessionV1) -> AlignedPoseV1:
-        target = np.asarray(
-            [record.timestamp for record in session.records_by_camera[session.reference_camera]],
-            dtype=np.float64,
-        )
-        timestamps = np.asarray(
-            [record.timestamp_ns for record in session.records_by_camera[session.reference_camera]],
-            dtype=np.uint64,
-        )
-        columns = session.pose_columns
-        result = np.empty((target.size, len(columns)), dtype=np.float32)
-        source_times = np.asarray([frame.timestamp for frame in session.pose_frames], dtype=np.float64)
-        for column_index, column in enumerate(columns):
-            values = np.asarray(
-                [frame.data[column] for frame in session.pose_frames],
-                dtype=np.float64,
-            )
-            if values.size == 1:
-                aligned = np.full(target.shape, values[0], dtype=np.float64)
-            else:
-                aligned = np.interp(target, source_times, values)
-            result[:, column_index] = aligned.astype(np.float32)
-        return AlignedPoseV1(result, timestamps, columns)
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+import numpy as np
+import numpy.typing as npt
+
+from dexverse_cli.raw_schema import RawSessionV1
+
+
+@dataclass(frozen=True, slots=True)
+class AlignedPoseV1:
+    data: npt.NDArray[np.float32]
+    timestamps: npt.NDArray[np.uint64]
+    columns: tuple[str, ...]
+
+
+class PackAlignmentPolicyV1:
+    """Linearly align pose values to the deterministic reference camera timeline."""
+
+    name = "linear_pose_to_reference_camera_v1"
+
+    def align(self, session: RawSessionV1) -> AlignedPoseV1:
+        target = np.asarray(
+            [record.timestamp for record in session.records_by_camera[session.reference_camera]],
+            dtype=np.float64,
+        )
+        timestamps = np.asarray(
+            [record.timestamp_ns for record in session.records_by_camera[session.reference_camera]],
+            dtype=np.uint64,
+        )
+        columns = session.pose_columns
+        result = np.empty((target.size, len(columns)), dtype=np.float32)
+        source_times = np.asarray([frame.timestamp for frame in session.pose_frames], dtype=np.float64)
+        for column_index, column in enumerate(columns):
+            values = np.asarray(
+                [frame.data[column] for frame in session.pose_frames],
+                dtype=np.float64,
+            )
+            if values.size == 1:
+                aligned = np.full(target.shape, values[0], dtype=np.float64)
+            else:
+                aligned = np.interp(target, source_times, values)
+            result[:, column_index] = aligned.astype(np.float32)
+        return AlignedPoseV1(result, timestamps, columns)