avrokit 0.0.7__tar.gz → 0.1.2__tar.gz

{avrokit-0.0.7 → avrokit-0.1.2}/Makefile

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-.PHONY: install test test-coverage lint lint-fix typecheck format build publish lock check license-check bump help
+.PHONY: install test test-coverage lint fix typecheck format build publish lock check license-check bump help
 
 help: ## Display this help
 	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-20s\033[0m %s\n", $$1, $$2}'
@@ -25,9 +25,6 @@ test-coverage: ## Run tests with coverage report
 lint: ## Run ruff linter
 	uv run ruff check .
 
-lint-fix: ## Run ruff linter and apply fixes
-	uv run ruff check --fix .
-
 typecheck: ## Run type checker
 	uv run ty check
 
@@ -40,6 +37,10 @@ bump: ## Bump version: make bump part=patch|minor|major
 lock: ## Update the lockfile
 	uv lock
 
+fix: ## Run ruff linter and apply fixes
+	uv run ruff format .
+	uv run ruff check --fix .
+
 check: lint typecheck format test license-check ## Run all checks (lint, typecheck, format, test)
 
 license-check: ## Check that all files have REUSE license headers

{avrokit-0.0.7 → avrokit-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: avrokit
-Version: 0.0.7
+Version: 0.1.2
 Summary: Python utilities for working with Avro data files
 Project-URL: Homepage, https://github.com/brandtg/avrokit
 Project-URL: Repository, https://github.com/brandtg/avrokit
@@ -12,10 +12,12 @@ Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
-Requires-Python: >=3.12
+Requires-Python: >=3.10
 Requires-Dist: avro>=1.12.1
 Requires-Dist: boto3-stubs[s3]>=1.38.8
 Requires-Dist: datetime-truncate>=1.1.1
@@ -23,6 +25,7 @@ Requires-Dist: filelock>=3.18.0
 Requires-Dist: pyarrow>=22.0.0
 Requires-Dist: requests>=2.32.3
 Requires-Dist: types-requests>=2.32.0.20250328
+Requires-Dist: typing-extensions>=4.12.0
 Provides-Extra: all
 Requires-Dist: boto3>=1.38.7; extra == 'all'
 Requires-Dist: google-cloud-storage>=3.6.0; extra == 'all'
@@ -80,7 +83,6 @@ pip install avrokit[all]
 ```bash
 git clone https://github.com/brandtg/avrokit.git
 cd avrokit
-poetry env use python3.12
 make install
 ```
 
@@ -321,15 +323,12 @@ avrokit toparquet INPUT.avro OUTPUT.parquet
 ### Prerequisites
 
 - Python 3.12+
-- Poetry
+- uv
 - Docker (for GCS/S3 integration tests)
 
 ### Setup
 
 ```bash
-# Set up Python environment
-poetry env use python3.12
-
 # Install dependencies
 make install
 
@@ -347,7 +346,7 @@ make test
 make test-coverage
 
 # Run tests in parallel (default)
-poetry run pytest -n auto
+uv run pytest -n auto
 ```
 
 ### Code Quality

{avrokit-0.0.7 → avrokit-0.1.2}/README.md

@@ -44,7 +44,6 @@ pip install avrokit[all]
 ```bash
 git clone https://github.com/brandtg/avrokit.git
 cd avrokit
-poetry env use python3.12
 make install
 ```
 
@@ -285,15 +284,12 @@ avrokit toparquet INPUT.avro OUTPUT.parquet
 ### Prerequisites
 
 - Python 3.12+
-- Poetry
+- uv
 - Docker (for GCS/S3 integration tests)
 
 ### Setup
 
 ```bash
-# Set up Python environment
-poetry env use python3.12
-
 # Install dependencies
 make install
 
@@ -311,7 +307,7 @@ make test
 make test-coverage
 
 # Run tests in parallel (default)
-poetry run pytest -n auto
+uv run pytest -n auto
 ```
 
 ### Code Quality

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/io/reader.py

@@ -6,10 +6,11 @@ from __future__ import annotations
 
 from collections.abc import Generator, Iterator, Sequence
 from contextlib import contextmanager
-from typing import IO, Any, Self, cast
+from typing import IO, Any, cast
 
 from avro.datafile import DataFileReader
 from avro.io import DatumReader
+from typing_extensions import Self
 
 from ..url import URL
 

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/io/writer.py

@@ -10,18 +10,13 @@ from collections.abc import Generator, Mapping, Sequence
 from contextlib import contextmanager
 from datetime import datetime
 from itertools import groupby
-from typing import (
-    IO,
-    Any,
-    Literal,
-    Protocol,
-    Self,
-)
+from typing import IO, Any, Literal, Protocol
 
 from avro.datafile import NULL_CODEC, DataFileWriter
 from avro.io import DatumWriter
 from avro.schema import Schema
 from datetime_truncate import truncate as truncate_datetime
+from typing_extensions import Self
 
 from avrokit.url.utils import flatten_urls
 

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/tools/httpserver.py

@@ -17,6 +17,7 @@ from avro.io import DatumReader
 
 from ..io import avro_reader, avro_schema, avro_writer, read_avro_schema
 from ..url import URL, parse_url
+from .tojson import AvroJsonEncoder
 
 logger = logging.getLogger(__name__)
 
@@ -195,7 +196,9 @@ class AvroHTTPRequestHandler(BaseHTTPRequestHandler):
                     self.send_header("Content-type", "application/jsonl")
                     self.end_headers()
                     for record in reader:
-                        self.wfile.write(json.dumps(record).encode("utf-8"))
+                        self.wfile.write(
+                            json.dumps(record, cls=AvroJsonEncoder).encode("utf-8")
+                        )
                         self.wfile.write(b"\n")
             elif self._is_avro_binary(accept):
                 with data_url as f:

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/tools/tojson.py

@@ -5,11 +5,24 @@
 import argparse
 import json
 import sys
+from datetime import date, datetime, time
+from decimal import Decimal
 
 from ..io import avro_reader
 from ..url import flatten_urls, parse_url
 
 
+class AvroJsonEncoder(json.JSONEncoder):
+    """Encodes Avro logical types (datetime, date, time, decimal) as JSON."""
+
+    def default(self, o: object) -> object:
+        if isinstance(o, datetime | date | time):
+            return o.isoformat()
+        if isinstance(o, Decimal):
+            return str(o)
+        return super().default(o)
+
+
 class ToJsonTool:
     """
     Dumps Avro data file(s) as JSON, record per line.
@@ -30,5 +43,5 @@ class ToJsonTool:
         for url in urls:
             with avro_reader(url) as reader:
                 for record in reader:
-                    json.dump(record, sys.stdout)
+                    json.dump(record, sys.stdout, cls=AvroJsonEncoder)
                     sys.stdout.write("\n")

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/url/base.py

@@ -4,10 +4,11 @@
 
 from __future__ import annotations
 
+import fnmatch
 from abc import ABC, abstractmethod
 from collections.abc import Sequence
 from typing import IO, Any
-from urllib.parse import urlparse
+from urllib.parse import urlparse, urlunparse
 
 
 class URL(ABC):
@@ -22,13 +23,44 @@ class URL(ABC):
     def __str__(self) -> str:
         return self.url
 
-    @abstractmethod
     def expand(self) -> Sequence[URL]:
         """
         Expands the URL into all the URLs that represent concrete resources.
+
+        If the final path element contains glob wildcards, the parent path is
+        expanded and the results are filtered client-side with fnmatch.
+        """
+        if self._has_glob():
+            return self._expand_glob()
+        return self._expand()
+
+    @abstractmethod
+    def _expand(self) -> Sequence[URL]:
+        """
+        Expands the URL into all the URLs that represent concrete resources.
         """
         ...
 
+    def _has_glob(self) -> bool:
+        return any(c in self.parsed_url.path for c in "*?[")
+
+    def _expand_glob(self) -> Sequence[URL]:
+        path = self.parsed_url.path
+        wildcard_idx = min(idx for idx in (path.find(c) for c in "*?[") if idx != -1)
+        prefix = path[:wildcard_idx]
+        parent = self._with_path(prefix)
+        return [
+            url
+            for url in parent.expand()
+            if url.url != parent.url and fnmatch.fnmatch(url.parsed_url.path, path)
+        ]
+
+    def _with_path(self, path: str) -> URL:
+        new_url = urlunparse(
+            (self.parsed_url.scheme, self.parsed_url.netloc, path, "", "", "")
+        )
+        return type(self)(new_url, mode=self.mode)
+
     @abstractmethod
     def delete(self) -> None:
         """

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/url/file.py

@@ -6,7 +6,9 @@ import glob
 import os
 import shutil
 from collections.abc import Sequence
-from typing import IO, Any, override
+from typing import IO, Any
+
+from typing_extensions import override
 
 from .base import URL
 
@@ -19,20 +21,7 @@ class FileURL(URL):
         self.fh: IO[Any] | None = None
 
     @override
-    def expand(self) -> Sequence[URL]:
-        # Check if the path contains wildcard characters
-        if "*" in self.path or "?" in self.path or "[" in self.path:
-            # Use glob to expand the pattern
-            matches = glob.glob(self.path)
-            if not matches:
-                # No matches found, return empty list
-                return []
-            # Return sorted list of FileURL objects for all matches
-            return [
-                FileURL(self.prefix + match, mode=self.mode)
-                for match in sorted(matches)
-            ]
-
+    def _expand(self) -> Sequence[URL]:
         # If it's a regular file or doesn't exist (no expansion needed)
         if os.path.isfile(self.path) or not os.path.exists(self.path):
             return [self]
@@ -46,6 +35,15 @@ class FileURL(URL):
                 )
         return acc
 
+    @override
+    def _expand_glob(self) -> Sequence[URL]:
+        matches = glob.glob(self.path)
+        if not matches:
+            return []
+        return [
+            FileURL(self.prefix + match, mode=self.mode) for match in sorted(matches)
+        ]
+
     @override
     def delete(self) -> None:
         # If it's a wildcard pattern, expand and delete all matching files

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/url/google.py

@@ -7,11 +7,12 @@ import os
 import tempfile
 from collections.abc import Generator, Sequence
 from contextlib import contextmanager
-from typing import IO, Any, cast, override
+from typing import IO, Any, cast
 
 from google.api_core.exceptions import NotFound
 from google.auth.credentials import AnonymousCredentials
 from google.cloud import storage
+from typing_extensions import override
 
 from .base import URL
 
@@ -58,7 +59,7 @@ class GoogleCloudStorageURL(URL):
         return self.url == value.url
 
     @override
-    def expand(self) -> Sequence[URL]:
+    def _expand(self) -> Sequence[URL]:
         with google_cloud_storage_client() as client:
             try:
                 path = self.path

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/url/http.py

@@ -5,9 +5,10 @@
 import io
 import tempfile
 from collections.abc import Sequence
-from typing import IO, Any, override
+from typing import IO, Any
 
 import requests
+from typing_extensions import override
 
 from .base import URL
 
@@ -35,7 +36,7 @@ class HttpURL(URL):
         self._current_request_buffer: IO[Any] | None = None
 
     @override
-    def expand(self) -> Sequence[URL]:
+    def _expand(self) -> Sequence[URL]:
         # N.b. no way to "expand" an HTTP URL, i.e. discover sub resources
         return [self]
 
@@ -57,9 +58,12 @@ class HttpURL(URL):
         try:
             response = requests.head(self.url, timeout=5)
             if response.ok:
-                return int(response.headers.get("Content-Length", 0))
+                content_length = response.headers.get("Content-Length")
+                if content_length is not None:
+                    return int(content_length)
+                return 0
             return 0
-        except requests.RequestException:
+        except (requests.RequestException, ValueError):
             return 0
 
     @override

{avrokit-0.0.7 → avrokit-0.1.2}/avrokit/url/s3.py

@@ -6,10 +6,11 @@ import io
 import tempfile
 from collections.abc import Sequence
 from contextlib import contextmanager
-from typing import IO, Any, cast, override
+from typing import IO, Any, cast
 
 import boto3
 from mypy_boto3_s3 import S3Client
+from typing_extensions import override
 
 from .base import URL
 
@@ -33,7 +34,7 @@ class S3URL(URL):
         self._current_local_stream: IO[Any] | None = None
 
     @override
-    def expand(self) -> Sequence[URL]:
+    def _expand(self) -> Sequence[URL]:
         with s3_client() as client:
             path = self.path
             if not path.endswith("/"):
@@ -48,7 +49,9 @@ class S3URL(URL):
                     for obj in page["Contents"]:
                         key = obj.get("Key")
                         if key:
-                            urls.append(S3URL(self._append_path(key), mode=self.mode))
+                            urls.append(
+                                S3URL(f"s3://{self.bucket}/{key}", mode=self.mode)
+                            )
             if not urls:
                 # N.b. we also include URLs that don't exist yet here because there is nothing to expand
                 return [self]

{avrokit-0.0.7 → avrokit-0.1.2}/pyproject.toml

@@ -4,18 +4,20 @@
 
 [project]
 name = "avrokit"
-version = "0.0.7"
+version = "0.1.2"
 description = "Python utilities for working with Avro data files"
 authors = [{ name = "Greg Brandt", email = "brandt.greg@gmail.com" }]
 license = "Apache-2.0"
 readme = "README.md"
-requires-python = ">=3.12"
+requires-python = ">=3.10"
 keywords = ["avro", "data", "serialization", "gcs", "s3", "parquet"]
 classifiers = [
   "Development Status :: 3 - Alpha",
   "Intended Audience :: Developers",
   "License :: OSI Approved :: Apache Software License",
   "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Topic :: Software Development :: Libraries :: Python Modules",
   "Typing :: Typed",
@@ -28,6 +30,7 @@ dependencies = [
   "boto3-stubs[s3]>=1.38.8",
   "types-requests>=2.32.0.20250328",
   "pyarrow>=22.0.0",
+  "typing-extensions>=4.12.0",
 ]
 
 [project.optional-dependencies]
@@ -66,6 +69,7 @@ filterwarnings = ["ignore::DeprecationWarning:botocore.*"]
 
 [tool.ruff]
 exclude = []
+target-version = "py310"
 
 [tool.ruff.lint]
 select = ["E", "F", "I", "UP"]