summary refs log tree commit diff
path: root/pkgs/tools/misc/parquet-tools
diff options
context:
space:
mode:
authorPhillip Cloud <417981+cpcloud@users.noreply.github.com>2021-11-21 20:56:43 -0500
committerGitHub <noreply@github.com>2021-11-21 20:56:43 -0500
commit09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b (patch)
treeddaa2ca90eb66c186cb205fb5b2f7a267263d01b /pkgs/tools/misc/parquet-tools
parent622cd51bd756822ceb9662e38fc1cc870c6b9e87 (diff)
downloadnixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar.gz
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar.bz2
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar.lz
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar.xz
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.tar.zst
nixpkgs-09454d0f4a23f79d884de9d6ff0d3dfe5ea1e97b.zip
parquet-tools: init at 0.2.9 (#142562)
Diffstat (limited to 'pkgs/tools/misc/parquet-tools')
-rw-r--r--pkgs/tools/misc/parquet-tools/default.nix69
1 files changed, 69 insertions, 0 deletions
diff --git a/pkgs/tools/misc/parquet-tools/default.nix b/pkgs/tools/misc/parquet-tools/default.nix
new file mode 100644
index 00000000000..0ba909e1f60
--- /dev/null
+++ b/pkgs/tools/misc/parquet-tools/default.nix
@@ -0,0 +1,69 @@
+{ lib
+, fetchFromGitHub
+, fetchpatch
+, python3Packages
+}:
+
+with python3Packages;
+
+buildPythonApplication rec {
+  pname = "parquet-tools";
+  version = "0.2.9";
+  disabled = pythonOlder "3.8";
+
+  format = "pyproject";
+
+  src = fetchFromGitHub {
+    owner = "ktrueda";
+    repo = "parquet-tools";
+    rev = version;
+    sha256 = "0aw0x7lhagp4dwis09fsizr7zbhdpliav0ns5ll5qny7x4m6rkfy";
+  };
+
+  patches = [
+    (fetchpatch {
+      url = "https://github.com/ktrueda/parquet-tools/commit/1c70a07e1c9f17c8890d23aad3ded5dd6c706cb3.patch";
+      sha256 = "08j1prdqj8ksw8gwiyj7ivshk82ahmywbzmywclw52nlnniig0sa";
+    })
+  ];
+
+  postPatch = ''
+    substituteInPlace pyproject.toml \
+      --replace 'thrift = "^0.13.0"' 'thrift = "*"' \
+      --replace 'halo = "^0.0.29"' 'halo = "*"'
+    substituteInPlace tests/test_inspect.py \
+      --replace "parquet-cpp-arrow version 5.0.0" "parquet-cpp-arrow version 6.0.0" \
+      --replace "serialized_size: 2222" "serialized_size: 2221"
+  '';
+
+  nativeBuildInputs = [ poetry-core ];
+
+  propagatedBuildInputs = [
+    boto3
+    colorama
+    halo
+    pandas
+    pyarrow
+    tabulate
+    thrift
+  ];
+
+  checkInputs = [
+    pytestCheckHook
+    moto
+    pytest-mock
+  ];
+
+  disabledTests = [
+    # these tests try to read python code as parquet and fail
+    "test_local_wildcard"
+    "test_local_and_s3_wildcard_files"
+  ];
+
+  meta = with lib; {
+    description = "A CLI tool for parquet files";
+    homepage = "https://github.com/ktrueda/parquet-tools";
+    license = licenses.mit;
+    maintainers = with maintainers; [ cpcloud ];
+  };
+}