release 0.3.0

Adds "Programming Language :: Python :: 3.12" to the package classifiers definition Bump github actions/checkout to v4 (from v3) Increase HTTPX timeout to 30 seconds from 5 seconds Improve generate_filepath rendering of paths with user-home ~ Loosen package dependencies to allow upgrades beyond current minor version Update dev-packages to make sure latest development packages in use Add 14x new exec end-to-end tests covering all sub-commands and option variations Improve type handing and use generic `generate_filepath()` function Hide --metadata-path option by default since it's an unusual use case scenario and likely to cause confusion
threatpatrols · Jan 21, 2024 · 6e931be · 6e931be
1 parent 80cca7a
commit 6e931be
Show file tree

Hide file tree

Showing 22 changed files with 723 additions and 79 deletions.
diff --git a/.github/workflows/build-tests.yml b/.github/workflows/build-tests.yml
@@ -9,9 +9,9 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - uses: NiklasRosenstein/slap@gha/install/v1
 
     - name: Set up Python ${{ matrix.python-version }}

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "hibp-downloader"
-version = "0.2.1"
+version = "0.3.0"
 description = "Efficiently download HIBP new pwned password data by hash-prefix for a local-copy"
 authors = ["Nicholas de Jong <[email protected]>"]
 license = "BSD-3-Clause"
@@ -14,6 +14,11 @@ classifiers = [
     "Environment :: Console",
     "Intended Audience :: System Administrators",
     "License :: OSI Approved :: BSD License",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
 ]
 keywords = ["hibp-downloader", "hibp", "haveibeenpwned", "haveibeenpwned-downloader", "sha1", "ntlm"]
 
@@ -28,26 +33,26 @@ hibp-downloader = "hibp_downloader.main:entrypoint"
 
 [tool.poetry.dependencies]
 python = "^3.8"
-"httpx[http2]" = "^0.25"        # https://pypi.org/project/httpx/#history
-httpcore = ">=0.17.2"           # https://pypi.org/project/httpcore/#history
-"typer[all]" = "^0.9"           # https://pypi.org/project/typer/#history
-shellingham = "^1.5"            # https://pypi.org/project/shellingham/#history
-aiofiles = "^23.0"              # https://pypi.org/project/aiofiles/#history
+"httpx[http2]" = ">=0.21"       # https://pypi.org/project/httpx/#history
+httpcore = ">=0.14"             # https://pypi.org/project/httpcore/#history
+aiofiles = ">=0.8"              # https://pypi.org/project/aiofiles/#history
+"typer[all]" = ">=0.9.0"        # https://pypi.org/project/typer/#history
+shellingham = ">=1.3.0"         # https://pypi.org/project/shellingham/#history
 
 [tool.poetry.dev-dependencies]
-black = "^23.11"                # https://pypi.org/project/black/#history
-flake8 = "^6.1"                 # https://pypi.org/project/flake8/#history
-isort = "^5.12"                 # https://pypi.org/project/isort/#history
-mypy = "^1.7"                   # https://pypi.org/project/mypy/#history
-pycln = "^2.3"                  # https://pypi.org/project/pycln/#history
+black = "^23.12"                # https://pypi.org/project/black/#history
+flake8 = "^7.0"                 # https://pypi.org/project/flake8/#history
+isort = "^5.13"                 # https://pypi.org/project/isort/#history
+mypy = "^1.8"                   # https://pypi.org/project/mypy/#history
+pycln = "^2.4"                  # https://pypi.org/project/pycln/#history
 pytest = "^7.4"                 # https://pypi.org/project/pytest/#history
-safety = "^2.4.0b1"             # https://pypi.org/project/safety/#history
-urllib3 = "~2.0"                # https://pypi.org/project/urllib3/#history
+safety = "^3.0.1"               # https://pypi.org/project/safety/#history
+urllib3 = "~2.1"                # https://pypi.org/project/urllib3/#history
 types-aiofiles = "23.2"         # https://pypi.org/project/types-aiofiles/#history
 # NB: pip installs in .readthedocs.yml need to be kept up-to-date manually
 novella = "^0.2"                # https://pypi.org/project/novella/#history
 pydoc-markdown = "^4.8"         # https://pypi.org/project/pydoc-markdown/#history
-mkdocs-material = "^9.4"        # https://pypi.org/project/mkdocs-material/#history
+mkdocs-material = "^9.5"        # https://pypi.org/project/mkdocs-material/#history
 
 [tool.poetry.plugins."slap.plugins.check"]
 changelog = "slap.ext.checks.changelog:ChangelogValidationCheckPlugin"

diff --git a/src/hibp_downloader/__init__.py b/src/hibp_downloader/__init__.py
@@ -9,10 +9,11 @@
 from .models import AppContext
 
 __title__ = "HIBP Downloader"
-__version__ = "0.2.1"
+__version__ = "0.3.0"
 
 LOGGER_NAME = "hibp-downloader"
 PWNEDPASSWORDS_API_URL = "https://api.pwnedpasswords.com"
+HTTPX_TIMEOUT_SECONDS = 30
 LOCAL_CACHE_TTL_DEFAULT = 12 * 3600
 MULTIPROCESSING_PROCESSES_DEFAULT = int(cpu_count() if cpu_count() else 4)  # type: ignore[arg-type]
 MULTIPROCESSING_PREFIXES_CHUNK_SIZE = 10

diff --git a/src/hibp_downloader/commands/hibp_download.py b/src/hibp_downloader/commands/hibp_download.py
@@ -75,9 +75,11 @@ def main(
             help="Number of hash-prefixes to consume (asynchronously) per iteration per process",
         ),
     ] = MULTIPROCESSING_PREFIXES_CHUNK_SIZE,
-    force: Annotated[bool, typer.Option(help="Same as setting --local_cache_ttl=0 and --ignore-etag")] = False,
+    force: Annotated[
+        bool, typer.Option("--force", help="Same as setting --local_cache_ttl=0 and --ignore-etag")
+    ] = False,
     ignore_etag: Annotated[
-        bool, typer.Option(help="Do not use request etag headers to manage local/remote cached data")
+        bool, typer.Option("--ignore-etag", help="Do not use request etag headers to manage local/remote cached data")
     ] = False,
     local_cache_ttl: Annotated[
         int,
@@ -115,8 +117,8 @@ def main(
     work_queue: Queue = Queue()
     worker_args = WorkerArgs(
         hash_type=hash_type,
-        data_path=Path(os.path.join(app_context.data_path, hash_type.value)),  # type: ignore[arg-type]
-        metadata_path=Path(os.path.join(app_context.metadata_path, hash_type.value)),  # type: ignore[arg-type]
+        data_path=app_context.data_path,  # type: ignore[arg-type]
+        metadata_path=app_context.metadata_path,  # type: ignore[arg-type]
         encoding_type=ENCODING_TYPE,
         ignore_etag=ignore_etag,
         local_cache_ttl=local_cache_ttl,
@@ -188,8 +190,8 @@ async def pwnedpasswords_get_store_gather(result_queue: Queue, hash_prefixes: tu
 async def pwnedpasswords_get_and_store_async(
     prefix: str,
     hash_type: HashType,
-    data_path: str,
-    metadata_path: str,
+    data_path: Path,
+    metadata_path: Path,
     encoding_type: str,
     ignore_etag: bool,
     local_cache_ttl: int,
@@ -207,9 +209,16 @@ async def pwnedpasswords_get_and_store_async(
 
     # get existing metadata if available
     metadata_existing = await load_metadata(
-        prefix=prefix, metadata_path=metadata_path, data_path=data_path, datafile_suffix=datafile_suffix
+        metadata_path=metadata_path,
+        data_path=data_path,
+        prefix=prefix,
+        hash_type=hash_type.value,
+        datafile_suffix=datafile_suffix,
     )
 
+    if not metadata_existing:
+        logger.debug(f"No existing metadata, will generate new metadata for {prefix!r}")
+
     etag = None
     if metadata_existing.data_source:
         if metadata_existing.server_timestamp:
@@ -239,6 +248,7 @@ async def pwnedpasswords_get_and_store_async(
     if binary:
         await save_datafile(
             data_path=data_path,
+            hash_type=hash_type,
             prefix=prefix,
             content=binary,
             filename_suffix=datafile_suffix,
@@ -249,7 +259,7 @@ async def pwnedpasswords_get_and_store_async(
         PrefixMetadataDataSource.local_source_ttl_cache,
         PrefixMetadataDataSource.unknown_source_status,
     ):
-        await save_metadatafile(metadata_path=metadata_path, prefix=prefix, metadata=metadata)
+        await save_metadatafile(metadata_path=metadata_path, hash_type=hash_type, prefix=prefix, metadata=metadata)
 
     return metadata
 
@@ -284,7 +294,7 @@ async def pwnedpasswords_get(
     if response.status_code == 304:  # HTTP 304 Not Modified status
         metadata.data_source = PrefixMetadataDataSource.local_source_etag_match
     elif response.status_code == 200:
-        if response.headers.get("cf-cache-status").upper() == "HIT":
+        if response.headers.get("cf-cache-status").upper() == "HIT":  # Fragile: relies on HIBP hosted via Cloudflare
             metadata.data_source = PrefixMetadataDataSource.remote_source_remote_cache
         else:
             metadata.data_source = PrefixMetadataDataSource.remote_source_origin_source
@@ -301,7 +311,7 @@ def results_queue_processor(q: Queue):
         metadata_items = q.get()
         if metadata_items == QUEUE_WORKER_EXIT_SENTINEL:
             running_stats.end_trigger()
-            logger.info(f"Finished in {round(running_stats.run_time/60,1)}min")
+            logger.info(f"Finished in {round(running_stats.run_time / 60, 1)}min")
             break
 
         if metadata_items:
@@ -319,7 +329,7 @@ def results_queue_processor(q: Queue):
                 f"~{int(running_stats.bytes_processed_rate_total / APPROX_GZIP_BYTES_PER_HASH)}H/s] "
                 f"api=[{int(running_stats.request_rate_total)}req/s "
                 f"{to_mbytes(running_stats.bytes_received_sum, 1)}MB] "
-                f"runtime={round(running_stats.run_time/60,1)}min"
+                f"runtime={round(running_stats.run_time / 60, 1)}min"
             )
 
 

diff --git a/src/hibp_downloader/commands/hibp_generate.py b/src/hibp_downloader/commands/hibp_generate.py
@@ -78,7 +78,7 @@ async def pwnedpasswords_datastore_sorted_gather(filename, hash_type, first_hash
         output = ""
         for k, v in dict(sorted({k: v for d in results for k, v in d.items()}.items())).items():
             output = f"{output}\n{v}"
-        await append_stringfile(filename=filename, content=output)
+        await append_stringfile(filepath=filename, content=output)
 
 
 async def pwnedpasswords_datastore_sorted_async(prefix, hash_type):
@@ -88,12 +88,13 @@ async def pwnedpasswords_datastore_sorted_async(prefix, hash_type):
     else:
         raise HibpDownloaderException(f"Unsupported ENCODING_TYPE {ENCODING_TYPE}")
 
-    source_data = await load_datafile(
-        data_path=os.path.join(app_context.data_path, hash_type),
+    datafile_content, datafile_filepath = await load_datafile(
+        data_path=app_context.data_path,
+        hash_type=hash_type,
         prefix=prefix,
-        filename_suffix=filename_suffix,
+        datafile_suffix=filename_suffix,
         decompression_type=decompression_mode,
         prepend_prefix=True,
     )
 
-    return {prefix: source_data}
+    return {prefix: datafile_content, f"{prefix}_datafile": datafile_filepath}
diff --git a/src/hibp_downloader/commands/hibp_query.py b/src/hibp_downloader/commands/hibp_query.py
@@ -26,7 +26,8 @@ def main(
         typer.Option(
             prompt=True,
             hide_input=True,
-            help="Cleartext password string to query the local data store",
+            help="Cleartext password string to query the --data-path content; prompts for hidden STDIN if not "
+            "supplied as CLI option.",
             envvar="HIBPDL_PASSWORD",
         ),
     ],
@@ -84,18 +85,22 @@ async def pwnedpasswords_query_datastore(password_hashed: str, hash_type: HashTy
     }
 
     try:
-        source_data = await load_datafile(
-            data_path=os.path.join(app_context.data_path, hash_type),  # type: ignore[arg-type]
+        datafile_content, datafile_filepath = await load_datafile(
+            data_path=app_context.data_path,  # type: ignore[arg-type]
+            hash_type=hash_type,
             prefix=prefix,
-            filename_suffix=filename_suffix,
+            datafile_suffix=filename_suffix,
             decompression_type=decompression_mode,
             prepend_prefix=True,
         )
     except HibpDownloaderException as e:
         result["status"] = str(e)
         return stdout_json(result)
 
-    for line in source_data.split("\n"):
+    if datafile_filepath:
+        result["data_file"] = str(datafile_filepath)
+
+    for line in datafile_content.split("\n"):
         if password_hashed.upper() in line:
             line_parts = line.split(":")
             if len(line_parts) >= 2:

diff --git a/src/hibp_downloader/lib/app.py b/src/hibp_downloader/lib/app.py
@@ -48,14 +48,17 @@ def main(
             help="Path where metadata is saved; by default both data and metadata are saved in the same --data-path",
             envvar="HIBPDL_METADATA_PATH",
             show_envvar=False,
+            hidden=False if app_context.debug else True,
         ),
     ] = "",
     debug: Annotated[
-        bool, typer.Option(help="Set logging to debug-level messages", envvar="HIBPDL_DEBUG", show_envvar=False)
+        bool,
+        typer.Option("--debug", help="Set logging to debug-level messages", envvar="HIBPDL_DEBUG", show_envvar=False),
     ] = False,
     quiet: Annotated[
         bool,
         typer.Option(
+            "--quiet",
             help="Set logging to fatal-level messages; overrides --debug option",
             envvar="HIBPDL_QUIET",
             show_envvar=False,