rearch and rename

.github/workflows/ci.yml

@@ -7,11 +7,11 @@ on:
 
 jobs:
   pytest:
-    name: Unit tests (gacdi_manifest)
+    name: Unit tests (mcdi)
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: cli_tools/gacdi_manifest
+        working-directory: cli_tools/mcdi
     strategy:
       matrix:
         python-version: ["3.9", "3.11"]
@@ -36,9 +36,9 @@ jobs:
       - name: Install planemo
         run: python -m pip install planemo
       - name: Lint manifest_gdc
-        run: planemo lint --skip citations tools/manifest_gdc
+        run: planemo lint tools/manifest_gdc
       - name: Lint manifest_downloader
-        run: planemo lint --skip citations tools/manifest_downloader
+        run: planemo lint tools/manifest_downloader
 
   planemo-test-manifest-downloader:
     name: Test Galaxy tool (manifest_downloader)
@@ -54,19 +54,19 @@ jobs:
       - name: Read version from package __init__.py
         id: version
         run: |
-          VERSION=$(grep -m1 '^__version__' cli_tools/gacdi_manifest/gacdi_manifest/__init__.py | sed -E 's/__version__ = "(.*)"/\1/')
+          VERSION=$(grep -m1 '^__version__' cli_tools/mcdi/mcdi/__init__.py | sed -E 's/__version__ = "(.*)"/\1/')
           echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
 
       # Built locally and never pushed: this only has to exist for this job's
       # own `planemo test --docker` step to resolve the tag manifest_downloader.xml
       # references. The real, published image is built and pushed by
       # containers.yml, only on merge to main.
-      - name: Build gacdi-manifest image (local only, not pushed)
+      - name: Build mcdi image (local only, not pushed)
         run: |
           docker build \
-            --build-arg GACDI_BUILD=${{ github.sha }} \
-            -t quay.io/goeckslab/gacdi-manifest:${{ steps.version.outputs.version }} \
-            cli_tools/gacdi_manifest
+            --build-arg MCDI_BUILD=${{ github.sha }} \
+            -t quay.io/goeckslab/mcdi:${{ steps.version.outputs.version }} \
+            cli_tools/mcdi
 
       - name: Test
         run: planemo test --docker tools/manifest_downloader

.github/workflows/containers.yml

@@ -1,25 +1,24 @@
-name: Build and push manifest container
-
-# Builds the manifest-builder image and pushes it to Quay whenever
-# cli_tools/gacdi_manifest changes on main, or manually. The image tag is
-# always taken from gacdi_manifest/__init__.py's __version__ (the single
-# source of truth for versioning; pyproject.toml's version is derived from it
-# via hatchling) and the job refuses to overwrite a tag that already exists on
-# Quay, so a forgotten version bump fails the build instead of silently
-# clobbering the published image. Requires repository secrets QUAY_USERNAME
-# and QUAY_TOKEN (Quay robot account).
+name: Build and push mcdi container
+
+# Builds the mcdi image and pushes it to Quay whenever cli_tools/mcdi changes
+# on main, or manually. The image tag is always taken from mcdi/__init__.py's
+# __version__ (the single source of truth for versioning; pyproject.toml's
+# version is derived from it via hatchling) and the job refuses to overwrite
+# a tag that already exists on Quay, so a forgotten version bump fails the
+# build instead of silently clobbering the published image. Requires
+# repository secrets QUAY_USERNAME and QUAY_TOKEN (Quay robot account).
 on:
   push:
     branches: ["main"]
     paths:
-      - "cli_tools/gacdi_manifest/**"
+      - "cli_tools/mcdi/**"
   workflow_dispatch:
 
 env:
   REGISTRY: quay.io
   # Must match the <container> namespace in tools/manifest_gdc/macros.xml.
   ORG: goeckslab
-  IMAGE: gacdi-manifest
+  IMAGE: mcdi
 
 jobs:
   manifest:
@@ -30,7 +29,7 @@ jobs:
       - name: Read version from package __init__.py
         id: version
         run: |
-          VERSION=$(grep -m1 '^__version__' cli_tools/gacdi_manifest/gacdi_manifest/__init__.py | sed -E 's/__version__ = "(.*)"/\1/')
+          VERSION=$(grep -m1 '^__version__' cli_tools/mcdi/mcdi/__init__.py | sed -E 's/__version__ = "(.*)"/\1/')
           echo "version=${VERSION}" >> "$GITHUB_OUTPUT"
 
       - uses: docker/setup-buildx-action@v3
@@ -46,16 +45,16 @@ jobs:
           IMAGE_REF="${{ env.REGISTRY }}/${{ env.ORG }}/${{ env.IMAGE }}:${{ steps.version.outputs.version }}"
           if docker buildx imagetools inspect "$IMAGE_REF" >/dev/null 2>&1; then
             echo "Tag ${{ steps.version.outputs.version }} already exists at $IMAGE_REF." >&2
-            echo "Bump __version__ in gacdi_manifest/__init__.py before pushing again." >&2
+            echo "Bump __version__ in mcdi/__init__.py before pushing again." >&2
             exit 1
           fi
 
       - name: Build & push
         uses: docker/build-push-action@v6
         with:
-          context: cli_tools/gacdi_manifest
-          file: cli_tools/gacdi_manifest/Dockerfile
+          context: cli_tools/mcdi
+          file: cli_tools/mcdi/Dockerfile
           push: true
           build-args: |
-            GACDI_BUILD=${{ github.sha }}
+            MCDI_BUILD=${{ github.sha }}
           tags: ${{ env.REGISTRY }}/${{ env.ORG }}/${{ env.IMAGE }}:${{ steps.version.outputs.version }}

.shed.yml

@@ -7,8 +7,8 @@ long_description: |
   ready for gdc-client or the GaCDI GDC importer, together with an enriched metadata table that
   joins sample barcodes and clinical/molecular annotations (GDC fields, cBioPortal subtypes, and
   optional user-uploaded annotations) plus a match/precision report.
-homepage_url: https://github.com/paulocilasjr/GaCDI
-remote_repository_url: https://github.com/paulocilasjr/GaCDI
+homepage_url: https://github.com/goeckslab/GaCDI
+remote_repository_url: https://github.com/goeckslab/GaCDI
 type: unrestricted
 categories:
   - Data Source

cli_tools/gacdi_manifest/Dockerfile → cli_tools/mcdi/Dockerfile

@@ -1,9 +1,9 @@
 FROM python:3.12-alpine
 WORKDIR /app
-# build from gacdi parent directory
+# build from the mcdi parent directory
 COPY . .
 RUN pip install --no-cache-dir .
 # Build identifier (e.g. git SHA) so a run can report exactly which code it used.
-ARG GACDI_BUILD=local
-ENV GACDI_BUILD=${GACDI_BUILD}
-CMD ["gacdi-manifest", "--help"]
+ARG MCDI_BUILD=local
+ENV MCDI_BUILD=${MCDI_BUILD}
+CMD ["mcdi", "--help"]

cli_tools/gacdi_manifest/README.md → cli_tools/mcdi/README.md

@@ -2,9 +2,10 @@
 
 Galaxy Cancer Data Importers (GaCDI) provides Galaxy tools for importing cancer
 datasets from major public and controlled-access cancer data repositories into
-Galaxy histories. This package provides two commands: `gacdi-manifest` builds
-a manifest from filters, and `gacdi-download` downloads the files a GDC or PDC
-manifest lists (whether built here or exported from a portal).
+Galaxy histories. This package provides one command, `mcdi` (Multi-Commons Data
+Importer), with two subcommands: `mcdi manifest` builds a manifest from
+filters, and `mcdi download` downloads the files a GDC or PDC manifest lists
+(whether built here or exported from a portal).
 
 ## Manifest Builder (this branch)
 
@@ -33,11 +34,11 @@ table, which is joined back to the downloaded files by barcode afterwards.
 
 ```bash
 # Preview how many files match before building
-gacdi-manifest gdc --project TCGA-BRCA --data-type "Slide Image" --count-only \
+mcdi manifest gdc --project TCGA-BRCA --data-type "Slide Image" --count-only \
   --manifest-out m.txt --metadata-out meta.tsv --report-out report.tsv
 
 # Build a slide-image manifest enriched with cBioPortal subtypes + a custom table
-gacdi-manifest gdc \
+mcdi manifest gdc \
   --project TCGA-BRCA --data-type "Slide Image" --access open \
   --cbioportal-study brca_tcga_pan_can_atlas_2018 \
   --cbioportal-attrs SUBTYPE,ER_STATUS_BY_IHC,PR_STATUS_BY_IHC,HER2_STATUS \
@@ -46,7 +47,7 @@ gacdi-manifest gdc \
   --manifest-out gdc_manifest.txt --metadata-out metadata.tsv --report-out report.tsv
 
 # Discover a study's cBioPortal attribute ids
-gacdi-manifest gdc --cbioportal-study brca_tcga_pan_can_atlas_2018 \
+mcdi manifest gdc --cbioportal-study brca_tcga_pan_can_atlas_2018 \
   --cbioportal-list-attrs --manifest-out m.txt --metadata-out meta.tsv --report-out report.tsv
 ```
 
@@ -88,8 +89,8 @@ annotations (e.g. labels for an image ML model).
 
 ## Downloading files from a manifest
 
-`gacdi-download` fetches the files listed in a GDC or PDC manifest — either
-one built by `gacdi-manifest gdc` above, or one exported directly from a
+`mcdi download` fetches the files listed in a GDC or PDC manifest — either
+one built by `mcdi manifest gdc` above, or one exported directly from a
 portal:
 
 - **GDC**: build a file cart in the [GDC portal](https://portal.gdc.cancer.gov)
@@ -101,8 +102,8 @@ portal:
   re-export if downloads start failing.
 
 ```bash
-gacdi-download --manifest gdc_manifest.txt --output-dir downloads/
-gacdi-download --manifest pdc_manifest.csv --output-dir downloads/ --verify-checksum
+mcdi download --manifest gdc_manifest.txt --output-dir downloads/
+mcdi download --manifest pdc_manifest.csv --output-dir downloads/ --verify-checksum
 ```
 
 The data commons is auto-detected from the manifest's header row; pass
@@ -123,7 +124,7 @@ environment variable or `--token-file`:
 
 ```bash
 export GDC_TOKEN="$(cat gdc-user-token.txt)"
-gacdi-download --manifest gdc_manifest.txt --output-dir downloads/
+mcdi download --manifest gdc_manifest.txt --output-dir downloads/
 ```
 
 PDC downloads use pre-signed URLs embedded in the manifest and need no token.
@@ -139,15 +140,15 @@ interrupted runs can simply be re-run.
 
 ## Runtime environment
 
-The tool ships a pinned container (`quay.io/<org>/gacdi-manifest`) referenced from
+The tool ships a pinned container (`quay.io/<org>/mcdi`) referenced from
 the wrapper, with Python + `requests` Conda requirements as a fallback. The Quay
 namespace (`paulocilasjr`) is a placeholder — update `@QUAY_ORG@` in
 `tools/manifest_gdc/macros.xml`, `containers/Dockerfile.manifest`, and the workflow
 before publishing.
 
 ```bash
-docker build -f containers/Dockerfile.manifest -t gacdi-manifest:dev .
-docker run --rm gacdi-manifest:dev gacdi-manifest gdc --help
+docker build -f containers/Dockerfile.manifest -t mcdi:dev .
+docker run --rm mcdi:dev mcdi manifest gdc --help
 ```
 
 ## Development

cli_tools/gacdi_manifest/gacdi_manifest/__init__.py → cli_tools/mcdi/mcdi/__init__.py

@@ -1,26 +1,26 @@
-"""GaCDI Manifest Builder + Downloader.
+"""MCDI — Multi-Commons Data Importer.
 
-Two commands sharing one package:
+One command, two subcommands:
 
-- ``gacdi-manifest`` (:mod:`gacdi_manifest.manifest`): filter-driven generation of
+- ``mcdi manifest`` (:mod:`mcdi.manifest`): filter-driven generation of
   download manifests (and enriched metadata tables) for NIH/NCI cancer data
   repositories, starting with the NCI Genomic Data Commons (GDC). The builder
   emits a deliberate *two-file split*: a lean, CLI/importer-ready manifest
   (``id/filename/md5/size/state``) and a rich metadata table joining
   clinical/molecular annotations by barcode, plus a match report so selections
   and joins are never silently wrong.
-- ``gacdi-download`` (:mod:`gacdi_manifest.download`): downloads the files listed
+- ``mcdi download`` (:mod:`mcdi.download`): downloads the files listed
   in a GDC or PDC manifest, auto-detecting which commons it came from.
 """
 
 import os
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 
 # Build identifier baked into the container image at build time (e.g. the git
 # commit SHA). Lets you confirm the exact code a run used, even when the version
 # number hasn't changed. Empty for local/editable installs.
-BUILD = os.environ.get("GACDI_BUILD", "").strip()
+BUILD = os.environ.get("MCDI_BUILD", "").strip()
 
 
 def version_string() -> str:

cli_tools/mcdi/mcdi/cli.py

@@ -0,0 +1,42 @@
+"""``mcdi`` — Multi-Commons Data Importer: single entry point for the ``manifest`` and ``download`` subcommands."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+import sys
+
+from . import version_string
+from .download import cli as download_cli
+from .errors import ManifestError
+from .manifest import cli as manifest_cli
+
+log = logging.getLogger("mcdi")
+
+
+def build_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(prog="mcdi", description="MCDI: Multi-Commons Data Importer.")
+    parser.add_argument("--version", action="version", version=f"mcdi {version_string()}")
+    sub = parser.add_subparsers(dest="command", required=True, metavar="COMMAND")
+    manifest_cli.add_arguments(sub)
+    download_cli.add_arguments(sub)
+    return parser
+
+
+def main(argv: list[str] | None = None) -> int:
+    args = build_parser().parse_args(argv)
+    logging.basicConfig(
+        level=logging.DEBUG if getattr(args, "verbose", False) else logging.INFO,
+        format="%(levelname)s %(name)s: %(message)s",
+    )
+    # Emit the running version to the job log so it is visible in Galaxy's job info.
+    log.info("mcdi %s", version_string())
+    try:
+        return args.func(args)
+    except ManifestError as exc:
+        log.error("%s", exc)
+        return exc.exit_code
+
+
+if __name__ == "__main__":  # pragma: no cover
+    sys.exit(main())

cli_tools/gacdi_manifest/gacdi_manifest/download/cli.py → cli_tools/mcdi/mcdi/download/cli.py

@@ -1,26 +1,24 @@
-"""CLI: ``gacdi-download`` — download the files listed in a GDC or PDC manifest."""
+"""``mcdi download`` — download the files listed in a GDC or PDC manifest."""
 
 from __future__ import annotations
 
 import argparse
 import logging
-import sys
 from pathlib import Path
 
-from .. import version_string
-from ..errors import InputError, ManifestError
+from ..errors import InputError
 from . import config, engine
 from .sources import SOURCES, detect_source
 
-log = logging.getLogger("gacdi_manifest.download")
+log = logging.getLogger("mcdi.download")
 
 
-def build_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(
-        prog="gacdi-download",
-        description="Download files listed in a GDC or PDC manifest.",
+def add_arguments(subparsers: argparse._SubParsersAction) -> argparse.ArgumentParser:
+    """Attach the ``download`` subcommand to ``subparsers``."""
+    parser = subparsers.add_parser(
+        "download",
+        help="Download files listed in a GDC or PDC manifest.",
     )
-    parser.add_argument("--version", action="version", version=f"gacdi-download {version_string()}")
     parser.add_argument("--manifest", required=True, type=Path, help="Path to the exported manifest file")
     parser.add_argument("--output-dir", required=True, type=Path, help="Directory to download files into")
     parser.add_argument(
@@ -39,10 +37,11 @@ def build_parser() -> argparse.ArgumentParser:
         help="Path to a file containing a GDC auth token (overrides GDC_TOKEN env var)",
     )
     parser.add_argument("--verbose", action="store_true")
+    parser.set_defaults(func=run)
     return parser
 
 
-def _run(args: argparse.Namespace) -> int:
+def run(args: argparse.Namespace) -> int:
     if not args.manifest.is_file():
         raise InputError(f"manifest not found: {args.manifest}")
 
@@ -76,21 +75,3 @@ def _run(args: argparse.Namespace) -> int:
         f"{len(mismatches)} checksum mismatch(es)"
     )
     return 1 if failed or mismatches else 0
-
-
-def main(argv: list[str] | None = None) -> int:
-    args = build_parser().parse_args(argv)
-    logging.basicConfig(
-        level=logging.DEBUG if args.verbose else logging.INFO,
-        format="%(levelname)s %(name)s: %(message)s",
-    )
-    log.info("gacdi-download %s", version_string())
-    try:
-        return _run(args)
-    except ManifestError as exc:
-        log.error("%s", exc)
-        return exc.exit_code
-
-
-if __name__ == "__main__":  # pragma: no cover
-    sys.exit(main())

cli_tools/gacdi_manifest/gacdi_manifest/download/engine.py → cli_tools/mcdi/mcdi/download/engine.py

@@ -24,7 +24,7 @@ def build_session() -> requests.Session:
         retries=RETRY_TOTAL,
         backoff=RETRY_BACKOFF,
         allowed_methods=frozenset({"GET", "HEAD"}),
-        user_agent=f"gacdi-manifest/{version_string()}",
+        user_agent=f"mcdi/{version_string()}",
     )
 
 

cli_tools/gacdi_manifest/gacdi_manifest/manifest/cbioportal.py → cli_tools/mcdi/mcdi/manifest/cbioportal.py

@@ -21,7 +21,7 @@
 
 from ..errors import ApiError
 
-log = logging.getLogger("gacdi_manifest.manifest.cbioportal")
+log = logging.getLogger("mcdi.manifest.cbioportal")
 
 DEFAULT_BASE = "https://www.cbioportal.org/api"