fluidattacks-core 5.1.0__tar.gz → 6.0.0__tar.gz

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fluidattacks-core
-Version: 5.1.0
+Version: 6.0.0
 Summary: Fluid Attacks Core Library
 Author-email: Development <development@fluidattacks.com>
 License: MPL-2.0
@@ -14,10 +14,10 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Provides-Extra: aio
 Requires-Dist: uvloop>=0.21.0; extra == "aio"
-Provides-Extra: authz
 Provides-Extra: git
 Requires-Dist: aiohttp>=3.10.0; extra == "git"
 Requires-Dist: aiofiles>=23.2.1; extra == "git"
+Requires-Dist: anyio>=4.7.0; extra == "git"
 Requires-Dist: boto3>=1.34; extra == "git"
 Requires-Dist: botocore>=1.40.18; extra == "git"
 Requires-Dist: GitPython>=3.1.41; extra == "git"
@@ -48,6 +48,7 @@ Requires-Dist: tree-sitter>=0.25.2; extra == "serializers"
 Requires-Dist: tree-sitter-dart-orchard==0.3.2; extra == "serializers"
 Provides-Extra: cpg
 Requires-Dist: aioboto3>=13.3.0; extra == "cpg"
+Requires-Dist: anyio>=4.7.0; extra == "cpg"
 Requires-Dist: platformdirs>=4.3.8; extra == "cpg"
 Provides-Extra: filesystem
 Provides-Extra: sarif
@@ -55,7 +56,6 @@ Requires-Dist: pydantic>=2.12.3; extra == "sarif"
 Provides-Extra: semver
 Provides-Extra: all
 Requires-Dist: fluidattacks-core[aio]; extra == "all"
-Requires-Dist: fluidattacks-core[authz]; extra == "all"
 Requires-Dist: fluidattacks-core[cpg]; extra == "all"
 Requires-Dist: fluidattacks-core[filesystem]; extra == "all"
 Requires-Dist: fluidattacks-core[git]; extra == "all"

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core/aio/tasks.py

@@ -1,6 +1,6 @@
 import asyncio
 import logging
-from collections.abc import AsyncGenerator, AsyncIterator, Awaitable, Coroutine, Iterable
+from collections.abc import AsyncGenerator, AsyncIterator, Awaitable, Coroutine, Iterable, Iterator
 from contextlib import suppress
 from typing import Any, Literal, TypeVar, cast, overload
 
@@ -134,6 +134,23 @@ async def _consume_generator(
         await queue.put(_GENERATOR_DONE_SENTINEL)
 
 
+def _start_initial_generator_tasks(
+    gen_iter: Iterator[AsyncGenerator[T, None]],
+    limit: int,
+    queue: asyncio.Queue[T | object],
+    active_generators: list[int],
+) -> list[asyncio.Task[None]]:
+    tasks: list[asyncio.Task[None]] = []
+    # Start initial tasks up to the limit
+    for _ in range(limit):
+        try:
+            gen = next(gen_iter)
+            tasks.append(asyncio.create_task(_consume_generator(gen, queue, active_generators)))
+        except StopIteration:
+            break
+    return tasks
+
+
 async def merge_async_generators(
     generators: Iterable[AsyncGenerator[T, None]],
     limit: int,
@@ -170,18 +187,8 @@ async def merge_async_generators(
 
     queue: asyncio.Queue[T | object] = asyncio.Queue()
     active_generators = [0]  # Use list to allow modification in nested function
-    tasks: list[asyncio.Task[None]] = []
-
     gen_iter = iter(generators)
-
-    # Start initial tasks up to the limit
-    for _ in range(limit):
-        try:
-            gen = next(gen_iter)
-            tasks.append(asyncio.create_task(_consume_generator(gen, queue, active_generators)))
-        except StopIteration:
-            break
-
+    tasks = _start_initial_generator_tasks(gen_iter, limit, queue, active_generators)
     # Keep track of how many generators we expect to finish
     expected_done_signals = len(tasks)
     done_signals_received = 0

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core/cpg/__init__.py

@@ -3,6 +3,7 @@ import hashlib
 from contextlib import suppress
 from pathlib import Path
 
+import anyio
 from aioboto3 import Session
 from platformdirs import user_cache_dir
 
@@ -83,7 +84,7 @@ async def generate_cpg(
     exclude: list[Path] | None = None,
 ) -> Path | None:
     cache_dir = Path(user_cache_dir("sifts"))
-    cache_dir.mkdir(parents=True, exist_ok=True)
+    await anyio.Path(cache_dir).mkdir(parents=True, exist_ok=True)
     try:
         relative_path = working_dir.relative_to(await _get_repo_top_level(working_dir))
     except ValueError:
@@ -134,7 +135,7 @@ async def get_cpg(
     repo_nickname: str,
 ) -> Path | None:
     cache_dir = Path(user_cache_dir("sifts"))
-    cache_dir.mkdir(parents=True, exist_ok=True)
+    await anyio.Path(cache_dir).mkdir(parents=True, exist_ok=True)
     try:
         relative_path = working_dir.relative_to(await _get_repo_top_level(working_dir))
     except ValueError:

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core/filesystem/__init__.py

@@ -17,6 +17,61 @@ if TYPE_CHECKING:
     from collections.abc import Iterable
 
 
+# Language priority mapping (higher number = higher priority)
+# This helps resolve conflicts between similar languages
+_LANGUAGE_PRIORITIES = {
+    Language.TypeScript: 10,  # TypeScript has priority over JavaScript
+    Language.JavaScript: 5,
+    Language.Kotlin: 8,  # Kotlin has priority over Java
+    Language.Java: 6,
+    Language.Rust: 9,  # Rust has priority over C
+    Language.C: 4,
+    Language.Scala: 7,  # Scala has priority over Java
+    Language.Dart: 8,  # Dart has priority over JavaScript
+    Language.Python: 7,
+    Language.Go: 8,
+    Language.PHP: 6,
+    Language.Ruby: 6,
+    Language.CSharp: 7,
+    Language.Swift: 8,
+}
+
+
+def _calculate_language_score(
+    names: set[str],
+    markers: dict[str, set[str] | list[str]],
+) -> int:
+    exacts: set[str] = {n.casefold() for n in markers["names"]}
+    patterns: list[str] = list(markers["globs"])
+    # Check exact name matches (higher confidence)
+    score = len([n for n in exacts if n in names]) * 10
+    # Check glob pattern matches (lower confidence)
+    glob_matches = sum(1 for f in names if any(fnmatch(f, pat) for pat in patterns))
+    return score + glob_matches * 5
+
+
+def _resolve_language_conflicts(
+    hits: list[Language],
+    language_scores: dict[Language, int],
+) -> list[Language]:
+    # Resolve conflicts using priority system.
+    if len(hits) <= 1:
+        return hits
+    # Sort by priority (descending) and then by confidence score (descending)
+    hits.sort(
+        key=lambda lang: (_LANGUAGE_PRIORITIES.get(lang, 0), language_scores.get(lang, 0)),
+        reverse=True,
+    )
+    # Remove lower priority languages that conflict with higher priority ones
+    resolved_hits: list[Language] = []
+    for lang in hits:
+        # Check if this language conflicts with any already resolved language
+        conflicts = _get_language_conflicts(lang)
+        if not any(conflict in resolved_hits for conflict in conflicts):
+            resolved_hits.append(lang)
+    return resolved_hits
+
+
 def _detect_languages_in_dir(files: Iterable[str]) -> list[Language]:
     """Return programming languages detected in a directory via exact filenames or glob patterns.
 
@@ -24,74 +79,15 @@ def _detect_languages_in_dir(files: Iterable[str]) -> list[Language]:
     """
     names = {f.casefold() for f in files}
     hits: list[Language] = []
-
-    # Language priority mapping (higher number = higher priority)
-    # This helps resolve conflicts between similar languages
-    language_priorities = {
-        Language.TypeScript: 10,  # TypeScript has priority over JavaScript
-        Language.JavaScript: 5,
-        Language.Kotlin: 8,  # Kotlin has priority over Java
-        Language.Java: 6,
-        Language.Rust: 9,  # Rust has priority over C
-        Language.C: 4,
-        Language.Scala: 7,  # Scala has priority over Java
-        Language.Dart: 8,  # Dart has priority over JavaScript
-        Language.Python: 7,
-        Language.Go: 8,
-        Language.PHP: 6,
-        Language.Ruby: 6,
-        Language.CSharp: 7,
-        Language.Swift: 8,
-    }
-
-    # Track confidence scores for each language
     language_scores: dict[Language, int] = {}
 
     for lang, markers in CONFIG_MARKERS.items():
-        exacts: set[str] = {n.casefold() for n in markers["names"]}
-        patterns: list[str] = list(markers["globs"])
-
-        score = 0
-
-        # Check exact name matches (higher confidence)
-        exact_matches = [n for n in exacts if n in names]
-        if exact_matches:
-            score += len(exact_matches) * 10  # Each exact match adds 10 points
-
-        # Check glob pattern matches (lower confidence)
-        glob_matches = 0
-        for f in names:
-            if any(fnmatch(f, pat) for pat in patterns):
-                glob_matches += 1
-        if glob_matches:
-            score += glob_matches * 5  # Each glob match adds 5 points
-
+        score = _calculate_language_score(names, markers)
         if score > 0:
             language_scores[lang] = score
             hits.append(lang)
 
-    # Resolve conflicts using priority system
-    if len(hits) > 1:
-        # Sort by priority (descending) and then by confidence score (descending)
-        hits.sort(
-            key=lambda lang: (
-                language_priorities.get(lang, 0),
-                language_scores.get(lang, 0),
-            ),
-            reverse=True,
-        )
-
-        # Remove lower priority languages that conflict with higher priority ones
-        resolved_hits = []
-        for lang in hits:
-            # Check if this language conflicts with any already resolved language
-            conflicts = _get_language_conflicts(lang)
-            if not any(conflict in resolved_hits for conflict in conflicts):
-                resolved_hits.append(lang)
-
-        hits = resolved_hits
-
-    return hits
+    return _resolve_language_conflicts(hits, language_scores)
 
 
 def _get_language_conflicts(lang: Language) -> set[Language]:
@@ -181,8 +177,9 @@ def _scan_dir(
 
     if langs:
         language = langs[0] if len(langs) == 1 else Language.Unknown
-        exclusions = [sp[0].relative_to(dir_path).as_posix() for sp in subprojects]
-        exclusions = _optimize_exclusions(exclusions)
+        exclusions = _optimize_exclusions(
+            [sp[0].relative_to(dir_path).as_posix() for sp in subprojects]
+        )
         return [(dir_path, language, exclusions), *subprojects]
 
     # if there is no project here, simply propagate the subprojects

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core/git/download_file.py

@@ -1,14 +1,32 @@
 import logging
-from pathlib import Path
 
 import aiofiles
 import aiohttp
+import anyio
 
 from .constants import DEFAULT_DOWNLOAD_BUFFER_SIZE
 
 LOGGER = logging.getLogger(__name__)
 
 
+async def _write_response_to_file(
+    response: aiohttp.ClientResponse,
+    destination_path: str,
+    download_buffer_size: int,
+) -> bool:
+    async with aiofiles.open(destination_path, "wb") as file:
+        while True:
+            try:
+                chunk = await response.content.read(download_buffer_size)
+            except TimeoutError:
+                LOGGER.exception("Read timeout for path %s", destination_path)
+                return False
+            if not chunk:
+                break
+            await file.write(chunk)
+    return await anyio.Path(destination_path).exists()
+
+
 async def download_file(
     *,
     url: str,
@@ -26,15 +44,4 @@ async def download_file(
                 )
                 return False
 
-            async with aiofiles.open(destination_path, "wb") as file:
-                while True:
-                    try:
-                        chunk = await response.content.read(download_buffer_size)
-                    except TimeoutError:
-                        LOGGER.exception("Read timeout for path %s", destination_path)
-                        return False
-                    if not chunk:
-                        break
-                    await file.write(chunk)
-
-            return Path(destination_path).exists()
+            return await _write_response_to_file(response, destination_path, download_buffer_size)

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core/git/download_repo.py

@@ -5,6 +5,7 @@ import tarfile
 import tempfile
 from pathlib import Path
 
+import anyio
 from git import GitError
 from git.cmd import Git
 from git.repo import Repo
@@ -87,7 +88,7 @@ async def download_repo_from_s3(
     *,
     download_buffer_size: int = DEFAULT_DOWNLOAD_BUFFER_SIZE,
 ) -> bool:
-    destination_path.parent.mkdir(parents=True, exist_ok=True)
+    await anyio.Path(destination_path.parent).mkdir(parents=True, exist_ok=True)
     with tempfile.TemporaryDirectory(prefix="fluidattacks_", ignore_cleanup_errors=True) as tmpdir:
         tmp_path = Path(tmpdir)
         file_path = tmp_path / "repo.tar.gz"
@@ -104,7 +105,7 @@ async def download_repo_from_s3(
             with tarfile.open(file_path, "r:gz") as tar_handler:
                 _safe_extract_tar(tar_handler, tmp_path)
 
-            extracted_dirs = [d for d in tmp_path.iterdir() if d.is_dir()]
+            extracted_dirs = [d async for d in anyio.Path(tmp_path).iterdir() if await d.is_dir()]
             if not extracted_dirs:
                 LOGGER.error("No directory found in the extracted archive: %s", destination_path)
                 return False
@@ -116,7 +117,7 @@ async def download_repo_from_s3(
                 )
             extracted_dir = extracted_dirs[0]
 
-            if destination_path.exists():
+            if await anyio.Path(destination_path).exists():
                 shutil.rmtree(destination_path)
 
             shutil.move(extracted_dir, destination_path)
@@ -127,10 +128,10 @@ async def download_repo_from_s3(
             )
             return False
 
-    if not await reset_repo(str(destination_path.absolute())):
+    if not await reset_repo(str(destination_path)):
         shutil.rmtree(destination_path, ignore_errors=True)
         return False
 
-    delete_out_of_scope_files(git_ignore or [], str(destination_path.absolute()))
+    delete_out_of_scope_files(git_ignore or [], str(destination_path))
 
     return True

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fluidattacks-core
-Version: 5.1.0
+Version: 6.0.0
 Summary: Fluid Attacks Core Library
 Author-email: Development <development@fluidattacks.com>
 License: MPL-2.0
@@ -14,10 +14,10 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Provides-Extra: aio
 Requires-Dist: uvloop>=0.21.0; extra == "aio"
-Provides-Extra: authz
 Provides-Extra: git
 Requires-Dist: aiohttp>=3.10.0; extra == "git"
 Requires-Dist: aiofiles>=23.2.1; extra == "git"
+Requires-Dist: anyio>=4.7.0; extra == "git"
 Requires-Dist: boto3>=1.34; extra == "git"
 Requires-Dist: botocore>=1.40.18; extra == "git"
 Requires-Dist: GitPython>=3.1.41; extra == "git"
@@ -48,6 +48,7 @@ Requires-Dist: tree-sitter>=0.25.2; extra == "serializers"
 Requires-Dist: tree-sitter-dart-orchard==0.3.2; extra == "serializers"
 Provides-Extra: cpg
 Requires-Dist: aioboto3>=13.3.0; extra == "cpg"
+Requires-Dist: anyio>=4.7.0; extra == "cpg"
 Requires-Dist: platformdirs>=4.3.8; extra == "cpg"
 Provides-Extra: filesystem
 Provides-Extra: sarif
@@ -55,7 +56,6 @@ Requires-Dist: pydantic>=2.12.3; extra == "sarif"
 Provides-Extra: semver
 Provides-Extra: all
 Requires-Dist: fluidattacks-core[aio]; extra == "all"
-Requires-Dist: fluidattacks-core[authz]; extra == "all"
 Requires-Dist: fluidattacks-core[cpg]; extra == "all"
 Requires-Dist: fluidattacks-core[filesystem]; extra == "all"
 Requires-Dist: fluidattacks-core[git]; extra == "all"

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core.egg-info/SOURCES.txt

@@ -12,9 +12,6 @@ fluidattacks_core/aio/processes.py
 fluidattacks_core/aio/runners.py
 fluidattacks_core/aio/tasks.py
 fluidattacks_core/aio/threads.py
-fluidattacks_core/authz/__init__.py
-fluidattacks_core/authz/py.typed
-fluidattacks_core/authz/types.py
 fluidattacks_core/cpg/__init__.py
 fluidattacks_core/cpg/joern.py
 fluidattacks_core/filesystem/__init__.py

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/fluidattacks_core.egg-info/requires.txt

@@ -4,7 +4,6 @@ uvloop>=0.21.0
 
 [all]
 fluidattacks-core[aio]
-fluidattacks-core[authz]
 fluidattacks-core[cpg]
 fluidattacks-core[filesystem]
 fluidattacks-core[git]
@@ -14,10 +13,9 @@ fluidattacks-core[sarif]
 fluidattacks-core[semver]
 fluidattacks-core[serializers]
 
-[authz]
-
 [cpg]
 aioboto3>=13.3.0
+anyio>=4.7.0
 platformdirs>=4.3.8
 
 [filesystem]
@@ -25,6 +23,7 @@ platformdirs>=4.3.8
 [git]
 aiohttp>=3.10.0
 aiofiles>=23.2.1
+anyio>=4.7.0
 boto3>=1.34
 botocore>=1.40.18
 GitPython>=3.1.41

{fluidattacks_core-5.1.0 → fluidattacks_core-6.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "fluidattacks-core"
-version = "5.1.0"
+version = "6.0.0"
 description = "Fluid Attacks Core Library"
 authors = [{ name = "Development", email = "development@fluidattacks.com" }]
 license = { text = "MPL-2.0" }
@@ -21,10 +21,10 @@ dependencies = []
 
 [project.optional-dependencies]
 aio = ["uvloop>=0.21.0"]
-authz = []
 git = [
   "aiohttp>=3.10.0",
   "aiofiles>=23.2.1",
+  "anyio>=4.7.0",
   "boto3>=1.34",
   "botocore>=1.40.18",
   "GitPython>=3.1.41",
@@ -50,13 +50,12 @@ serializers = [
   "tree-sitter>=0.25.2",
   "tree-sitter-dart-orchard==0.3.2",
 ]
-cpg = ["aioboto3>=13.3.0", "platformdirs>=4.3.8"]
+cpg = ["aioboto3>=13.3.0", "anyio>=4.7.0", "platformdirs>=4.3.8"]
 filesystem = []
 sarif = ["pydantic>=2.12.3"]
 semver = []
 all = [
   "fluidattacks-core[aio]",
-  "fluidattacks-core[authz]",
   "fluidattacks-core[cpg]",
   "fluidattacks-core[filesystem]",
   "fluidattacks-core[git]",
@@ -73,11 +72,11 @@ dev = [
   "botocore-stubs==1.35.71",
   "datamodel-code-generator>=0.35.0",
   "deptry==0.24.0",
-  "import-linter==2.5.2",
-  "mypy==1.18.2",
+  "import-linter==2.9",
+  "mypy==1.19.1",
   "pytest-asyncio>=1.1.0",
-  "pytest==8.4.1",
-  "ruff==0.14.0",
+  "pytest==9.0.2",
+  "ruff==0.15.0",
   "types-aioboto3[s3]>=15.1.0",
   "types-aiofiles==24.1.0.20240626",
   "types-simplejson>=3.20.0.20250822",

fluidattacks_core-5.1.0/fluidattacks_core/authz/types.py

@@ -1,75 +0,0 @@
-from __future__ import (
-    annotations,
-)
-
-from dataclasses import (
-    dataclass,
-)
-from typing import (
-    Literal,
-    TypedDict,
-)
-
-AuthzType = Literal[
-    "admin",
-    "user",
-    "organization",
-    "group",
-    "root",
-]
-
-AuthzRelation = Literal[
-    "admin",
-    "parent",
-    "customer_manage",
-    "customer_write",
-    "customer_read",
-    "fluid_manage",
-    "fluid_write",
-    "fluid_read",
-    "manage",
-    "write",
-    "read",
-]
-
-
-@dataclass(frozen=True, kw_only=True)
-class AuthzConditionFluidEmail:
-    email: str
-
-    class _ReturnTypeContext(TypedDict):
-        email: str
-
-    class _ReturnType(TypedDict):
-        name: Literal["fluid_email"]
-        context: AuthzConditionFluidEmail._ReturnTypeContext
-
-    def __call__(self) -> _ReturnType:
-        return {
-            "name": "fluid_email",
-            "context": {"email": self.email},
-        }
-
-
-@dataclass(frozen=True, kw_only=True)
-class AuthzTuple:
-    user_type: AuthzType
-    user: str
-    relation: AuthzRelation
-    object_type: AuthzType
-    object: str
-    condition: AuthzConditionFluidEmail | None = None
-
-    class _ReturnType(TypedDict):
-        user: str
-        relation: AuthzRelation
-        object: str
-        condition: AuthzConditionFluidEmail._ReturnType | None
-
-    def __call__(self) -> _ReturnType:
-        return {
-            "user": f"{self.user_type}:{self.user}",
-            "relation": self.relation,
-            "object": f"{self.object_type}:{self.object}",
-            "condition": self.condition() if self.condition else None,
-        }