os-normalizer 0.3.2__tar.gz → 0.4.0__tar.gz

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/CHANGELOG.md

@@ -3,7 +3,19 @@
 All notable changes to this project are documented here.
 This file adheres to Keep a Changelog and Semantic Versioning.
 
-## [Unreleased]
+## [0.3.3] - 2025-09-21
+
+- Added: `tests/case_utils.py` to share parametrization helpers across suites.
+- Added: Platform-specific suites for clearer test changes.
+- Removed: Legacy `tests/test_os_normalizer.py` harness now that coverage lives beside each platform.
+
+## [0.3.2] - 2025-09-11
+
+- Added: More `pyproject.toml` metadata (description, keywords, classifiers, project URLs).
+- Added: `LICENSE` (MIT) and referenced it from project metadata.
+- Added: `RELEASING.md` with step-by-step TestPyPI/PyPI instructions.
+- Changed: Switched to Hatchling build backend via `[build-system]` in `pyproject.toml`.
+- Changed: Exclude dev artifacts from sdist (`tests/`, caches, lockfiles, egg-info).
 
 ## [0.3.1] - 2025-09-09
 
@@ -28,7 +40,8 @@ This file adheres to Keep a Changelog and Semantic Versioning.
 
 - Initial release.
 
-[Unreleased]: https://github.com/johnscillieri/os-normalizer/compare/v0.3.1...HEAD
+[Unreleased]: https://github.com/johnscillieri/os-normalizer/compare/v0.3.3...HEAD
+[0.3.3]: https://github.com/johnscillieri/os-normalizer/compare/v0.3.2...v0.3.3
 [0.3.1]: https://github.com/johnscillieri/os-normalizer/compare/v0.3.0...v0.3.1
 [0.3.0]: https://github.com/johnscillieri/os-normalizer/compare/v0.2.0...v0.3.0
 [0.2.0]: https://github.com/johnscillieri/os-normalizer/compare/v0.1.0...v0.2.0

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: os-normalizer
-Version: 0.3.2
+Version: 0.4.0
 Summary: Normalize raw OS strings/metadata into structured data (family, product, version, arch).
 Project-URL: Homepage, https://github.com/johnscillieri/os-normalizer
 Project-URL: Repository, https://github.com/johnscillieri/os-normalizer

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/constants.py

@@ -17,8 +17,27 @@ ARCH_SYNONYMS = {
 }
 
 # Windows build map (build number range -> product name, marketing channel)
+# Notes:
+# - This focuses on common client builds; server detection is handled separately
+#   and this map is not applied if a server product was already detected.
+# - Marketing/channel labels use common public naming where applicable
+#   (e.g., 21H2/22H2 for Windows 10/11, RTM/SPx for older releases).
 WINDOWS_BUILD_MAP = [
-    # Windows 10
+    # NT era (pre-Windows 10)
+    (1381, 1381, "Windows NT 4.0", "RTM"),
+    (2195, 2195, "Windows 2000", "RTM"),
+    (2600, 2600, "Windows XP", "RTM"),
+    # NT 5.2 builds are ambiguous (XP x64 vs Server 2003); keep consistent label
+    (3790, 3790, "Windows XP x64/Server 2003", "RTM"),
+    # Vista/7/8/8.1
+    (6000, 6000, "Windows Vista", "RTM"),
+    (6001, 6001, "Windows Vista", "SP1"),
+    (6002, 6002, "Windows Vista", "SP2"),
+    (7600, 7600, "Windows 7", "RTM"),
+    (7601, 7601, "Windows 7", "SP1"),
+    (9200, 9200, "Windows 8", "RTM"),
+    (9600, 9600, "Windows 8.1", "RTM"),
+    # Windows 10 (builds and marketing versions)
     (10240, 10240, "Windows 10", "1507"),
     (10586, 10586, "Windows 10", "1511"),
     (14393, 14393, "Windows 10", "1607"),
@@ -30,7 +49,7 @@ WINDOWS_BUILD_MAP = [
     (19041, 19045, "Windows 10", "2004/20H2/21H1/21H2/22H2"),
     # Windows 11
     (22000, 22000, "Windows 11", "21H2"),
-    (22621, 22630, "Windows 11", "22H2"),
+    (22621, 22621, "Windows 11", "22H2"),
     (22631, 25999, "Windows 11", "23H2"),
     (26100, 26199, "Windows 11", "24H2"),
 ]
@@ -80,8 +99,29 @@ MACOS_DARWIN_MAP = {
     22: ("macOS", "13", "Ventura"),
     23: ("macOS", "14", "Sonoma"),
     24: ("macOS", "15", "Sequoia"),
+    25: ("macOS", "26", "Tahoe"),
 }
 
+# Windows Server build map (build number range -> product name, marketing channel)
+# This is consulted only when the input looks server-like or when an explicit
+# Windows Server product is already detected. Client mapping will not override
+# explicit server detections.
+WINDOWS_SERVER_BUILD_MAP = [
+    # Legacy server releases aligned with Vista/7/8/8.1
+    (3790, 3790, "Windows Server 2003", "RTM"),
+    (6001, 6001, "Windows Server 2008", "RTM"),  # 6001 corresponds to 2008 RTM
+    (6002, 6002, "Windows Server 2008", "SP2"),
+    (7600, 7600, "Windows Server 2008 R2", "RTM"),
+    (7601, 7601, "Windows Server 2008 R2", "SP1"),
+    (9200, 9200, "Windows Server 2012", "RTM"),
+    (9600, 9600, "Windows Server 2012 R2", "RTM"),
+    # NT 10.0 based server releases
+    (14393, 14393, "Windows Server 2016", "1607"),
+    (17763, 17763, "Windows Server 2019", "1809"),
+    (20348, 20348, "Windows Server 2022", "21H2"),
+    # Windows Server 2025 (vNext) uses the 26100 train alongside client 24H2
+    (26100, 26199, "Windows Server 2025", "24H2"),
+]
+
 # Cisco train names (used for codename detection)
 CISCO_TRAIN_NAMES = {"Everest", "Fuji", "Gibraltar", "Amsterdam", "Denali"}
-

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/parsers/__init__.py

@@ -6,11 +6,10 @@ from .bsd import parse_bsd
 from .network import parse_network
 
 __all__ = [
-    "parse_windows",
-    "parse_macos",
+    "parse_bsd",
     "parse_linux",
+    "parse_macos",
     "parse_mobile",
-    "parse_bsd",
     "parse_network",
+    "parse_windows",
 ]
-

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/parsers/linux.py

@@ -18,7 +18,7 @@ LINUX_VER_FALLBACK_RE = re.compile(
 
 
 def parse_linux(text: str, data: dict[str, Any], p: OSData) -> OSData:
-    """Populate an OSData instance with Linux‑specific details."""
+    """Populate an OSData instance with Linux-specific details."""
     p.kernel_name = "linux"
 
     osrel = _coerce_os_release(data.get("os_release")) if isinstance(data, dict) else None
@@ -37,7 +37,7 @@ def parse_linux(text: str, data: dict[str, Any], p: OSData) -> OSData:
     return p
 
 
-def _coerce_os_release(obj: Any) -> Optional[dict[str, Any]]:
+def _coerce_os_release(obj: Any) -> dict[str, Any] | None:
     if isinstance(obj, str):
         return parse_os_release(obj)
     if isinstance(obj, dict):
@@ -45,7 +45,7 @@ def _coerce_os_release(obj: Any) -> Optional[dict[str, Any]]:
     return None
 
 
-def _extract_kernel_version(text: str) -> Optional[str]:
+def _extract_kernel_version(text: str) -> str | None:
     m = KERNEL_RE.search(text)
     if m:
         return m.group(2)
@@ -66,6 +66,14 @@ def _apply_os_release(osrel: dict[str, Any], p: OSData) -> None:
 
     p.pretty_name = osrel.get("PRETTY_NAME") or osrel.get("NAME")
 
+    if not p.codename and p.pretty_name:
+        # Fallback: try to extract codename from parenthetical in pretty name (e.g. "Debian ... (buster)")
+        m = re.search(r"\(([^)]+)\)", str(p.pretty_name))
+        if m:
+            candidate = m.group(1).strip()
+            if candidate:
+                p.codename = candidate.title()
+
     _apply_version_id(osrel.get("VERSION_ID"), p)
 
     vcode = osrel.get("VERSION_CODENAME")
@@ -78,7 +86,9 @@ def _apply_os_release(osrel: dict[str, Any], p: OSData) -> None:
     p.vendor = _vendor_for_distro(p.distro) if p.distro else p.vendor
 
     name = osrel.get("NAME")
-    p.product = (name if name else (p.distro or "Linux")).replace('"', "") if isinstance(name, str) else (p.distro or "Linux")
+    p.product = (
+        (name if name else (p.distro or "Linux")).replace('"', "") if isinstance(name, str) else (p.distro or "Linux")
+    )
 
     # Precision from version parts
     if p.version_patch is not None:
@@ -103,7 +113,7 @@ def _apply_version_id(vid: Any, p: OSData) -> None:
         p.version_patch = int(parts[2])
 
 
-def _vendor_for_distro(distro: Optional[str]) -> Optional[str]:
+def _vendor_for_distro(distro: str | None) -> str | None:
     vendor_by_distro = {
         "ubuntu": "Canonical",
         "debian": "Debian",

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/parsers/network/fortinet.py

@@ -30,9 +30,7 @@ def parse_fortinet(text: str, p: OSData) -> OSData:
         if len(nums) >= 3:
             p.version_patch = int(nums[2])
         p.version_build = v
-        p.precision = (
-            "patch" if p.version_patch is not None else ("minor" if p.version_minor is not None else "major")
-        )
+        p.precision = "patch" if p.version_patch is not None else ("minor" if p.version_minor is not None else "major")
 
     bld = FORTI_BUILD_RE.search(text)
     if bld:

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/parsers/network/netgear.py

@@ -6,9 +6,7 @@ from os_normalizer.helpers import update_confidence
 from os_normalizer.models import OSData
 
 NETGEAR_RE = re.compile(r"\bnetgear\b|\bfirmware\b", re.IGNORECASE)
-NETGEAR_VER_RE = re.compile(
-    r"\bV(\d+\.\d+\.\d+(?:\.\d+)?(?:_\d+\.\d+\.\d+)?)\b", re.IGNORECASE
-)
+NETGEAR_VER_RE = re.compile(r"\bV(\d+\.\d+\.\d+(?:\.\d+)?(?:_\d+\.\d+\.\d+)?)\b", re.IGNORECASE)
 NETGEAR_MODEL_RE = re.compile(r"\b([RN][0-9]{3,4}[A-Z]?)\b", re.IGNORECASE)
 
 
@@ -29,9 +27,7 @@ def parse_netgear(text: str, p: OSData) -> OSData:
         if len(nums) >= 3:
             p.version_patch = int(nums[2])
         p.version_build = v
-        p.precision = (
-            "patch" if p.version_patch is not None else ("minor" if p.version_minor is not None else "major")
-        )
+        p.precision = "patch" if p.version_patch is not None else ("minor" if p.version_minor is not None else "major")
 
     mdl = NETGEAR_MODEL_RE.search(text)
     if mdl:

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/os_normalizer/parsers/windows.py

@@ -10,6 +10,7 @@ from typing import Any, Optional
 
 from os_normalizer.constants import (
     WINDOWS_BUILD_MAP,
+    WINDOWS_SERVER_BUILD_MAP,
     WINDOWS_NT_CLIENT_MAP,
     WINDOWS_NT_SERVER_MAP,
 )
@@ -18,14 +19,18 @@ from os_normalizer.models import OSData
 
 # Regex patterns used only by the Windows parser
 WIN_EDITION_RE = re.compile(
-    r"\b(professional|enterprise|home|education|ltsc|datacenter)\b",
+    r"\b(professional|pro|enterprise|home|education|ltsc|datacenter|standard)\b",
     re.IGNORECASE,
 )
 WIN_SP_RE = re.compile(r"\bSP\s?([0-9]+)\b", re.IGNORECASE)
 WIN_BUILD_RE = re.compile(r"\bbuild\s?(\d{4,6})\b", re.IGNORECASE)
 WIN_NT_RE = re.compile(r"\bnt\s?(\d+)\.(\d+)\b", re.IGNORECASE)
 WIN_FULL_NT_BUILD_RE = re.compile(r"\b(10)\.(0)\.(\d+)(?:\.(\d+))?\b")
-WIN_CHANNEL_RE = re.compile(r"\b(20H2|21H2|22H2|23H2|24H2|19H2|18H2|17H2|2004|1909|1809|1709|1511|1507)\b", re.IGNORECASE)
+WIN_GENERIC_VERSION_RE = re.compile(r"\b(\d+)\.(\d+)\.(\d{3,6})(?:\.(\d+))?\b")
+WIN_CHANNEL_RE = re.compile(
+    r"\b(24H2|23H2|22H2|21H2|21H1|20H2|2004|1909|1903|1809|1803|1709|1703|1607|1511|1507)\b",
+    re.IGNORECASE,
+)
 
 
 def parse_windows(text: str, data: dict[str, Any], p: OSData) -> OSData:
@@ -47,7 +52,7 @@ def parse_windows(text: str, data: dict[str, Any], p: OSData) -> OSData:
     _apply_full_kernel_and_channel(text, p)
 
     # 5) Build number + marketing channel (fallback when only 'build 22631' is present)
-    _apply_build_mapping(text, p)
+    _apply_build_mapping(text, p, server_like)
 
     # 6) Precision and version_major if applicable
     _finalize_precision_and_version(p)
@@ -59,6 +64,9 @@ def parse_windows(text: str, data: dict[str, Any], p: OSData) -> OSData:
 
 
 def _detect_product_from_text(t: str) -> str:
+    # Normalize common typos before matching
+    t = t.replace("windws", "windows")
+
     if "windows 11" in t or "win11" in t:
         return "Windows 11"
     if "windows 10" in t or "win10" in t:
@@ -75,19 +83,23 @@ def _detect_product_from_text(t: str) -> str:
         return "Windows 98"
 
     # Server explicit names
-    if "windows server 2022" in t or "win2k22" in t or "win2022" in t:
+    if "windows server 2012 r2" in t or "windows 2012 r2" in t or "win2k12r2" in t or "win2012r2" in t:
+        return "Windows Server 2012 R2"
+    if "windows server 2022" in t or "windows 2022" in t or "win2k22" in t or "win2022" in t:
         return "Windows Server 2022"
-    if "windows server 2019" in t or "win2k19" in t or "win2019" in t:
+    if "windows server 2019" in t or "windows 2019" in t or "win2k19" in t or "win2019" in t:
         return "Windows Server 2019"
-    if "windows server 2016" in t or "win2k16" in t or "win2016" in t:
+    if "windows server 2016" in t or "windows 2016" in t or "win2k16" in t or "win2016" in t:
         return "Windows Server 2016"
-    if "windows server 2012" in t or "win2k12" in t or "win2012" in t:
+    if "windows server 2012" in t or "windows 2012" in t or "win2k12" in t or "win2012" in t:
         return "Windows Server 2012"
-    if "windows server 2008" in t or "win2k8" in t or "win2008" in t:
+    if "windows server 2008 r2" in t or "windows 2008 r2" in t or "win2k8r2" in t or "win2008r2" in t:
+        return "Windows Server 2008 R2"
+    if "windows server 2008" in t or "windows 2008" in t or "win2k8" in t or "win2008" in t:
         return "Windows Server 2008"
-    if "windows server 2003" in t or "win2k3" in t or "win2003" in t:
+    if "windows server 2003" in t or "windows 2003" in t or "win2k3" in t or "win2003" in t:
         return "Windows Server 2003"
-    if "windows server 2000" in t or "win2k" in t or "win2000" in t:
+    if "windows server 2000" in t or "windows 2000" in t or "win2k" in t or "win2000" in t:
         return "Windows Server 2000"
 
     if "windows" in t:
@@ -97,7 +109,20 @@ def _detect_product_from_text(t: str) -> str:
 
 def _detect_edition(text: str) -> str | None:
     m = WIN_EDITION_RE.search(text)
-    return m.group(1).title() if m else None
+    if not m:
+        return None
+    token = m.group(1).lower()
+    norm = {
+        "pro": "Professional",
+        "professional": "Professional",
+        "enterprise": "Enterprise",
+        "home": "Home",
+        "education": "Education",
+        "ltsc": "LTSC",
+        "datacenter": "Datacenter",
+        "standard": "Standard",
+    }
+    return norm.get(token, token.title())
 
 
 def _parse_service_pack(text: str, p: OSData) -> None:
@@ -138,26 +163,42 @@ def _apply_nt_mapping(text: str, p: OSData, server_like: bool) -> None:
         p.product = product
 
 
-def _apply_build_mapping(text: str, p: OSData) -> None:
+def _apply_build_mapping(text: str, p: OSData, server_like: bool) -> None:
     m = WIN_BUILD_RE.search(text)
     if not m:
         return
     build_num = int(m.group(1))
     p.version_build = str(build_num)
 
-    # Kernel version for recent Windows 10/11
-    if (p.product == "Windows 10/11") or ("10.0" in text):
-        p.kernel_version = f"{10}.{0}.{build_num}"
-    else:
-        p.kernel_version = None
+    # Kernel version string
+    if not p.kernel_version:
+        if (p.product == "Windows 10/11") or ("10.0" in text):
+            p.kernel_version = f"10.0.{build_num}"
+        else:
+            nt_mm = WIN_NT_RE.search(text)
+            if nt_mm:
+                maj, minr = int(nt_mm.group(1)), int(nt_mm.group(2))
+                p.kernel_version = f"{maj}.{minr}.{build_num}"
 
-    # Only apply client build mapping if current product isn't an explicit Server
     is_server_product = isinstance(p.product, str) and "server" in p.product.lower()
-    if not is_server_product:
+    if is_server_product or server_like:
+        # Apply server build mapping; do not override explicit server product names
+        for lo, hi, product_name, marketing in WINDOWS_SERVER_BUILD_MAP:
+            if lo <= build_num <= hi:
+                if not p.product or p.product in ("Windows", "Windows 10/11"):
+                    p.product = product_name
+                # Only set channel for modern Server (2016+)
+                if build_num >= 14393:
+                    p.channel = p.channel or marketing
+                break
+    else:
+        # Apply client build mapping
         for lo, hi, product_name, marketing in WINDOWS_BUILD_MAP:
             if lo <= build_num <= hi:
-                p.product = product_name
-                p.channel = marketing
+                # Only use build map to set product for Windows 10/11 trains
+                if build_num >= 10240:
+                    p.product = product_name
+                    p.channel = p.channel or marketing
                 break
 
 
@@ -177,6 +218,14 @@ def _apply_full_kernel_and_channel(text: str, p: OSData) -> None:
     if ch and not p.channel:
         p.channel = ch.group(1).upper()
 
+    if not p.kernel_version:
+        m2 = WIN_GENERIC_VERSION_RE.search(text)
+        if m2:
+            major, minor, build, suffix = m2.groups()
+            p.kernel_version = f"{major}.{minor}.{build}{('.' + suffix) if suffix else ''}"
+            p.version_build = p.version_build or build
+            p.evidence.setdefault("nt_version", f"{major}.{minor}")
+
 
 def _finalize_precision_and_version(p: OSData) -> None:
     if p.version_build:

{os_normalizer-0.3.2 → os_normalizer-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "os-normalizer"
-version = "0.3.2"
+version = "0.4.0"
 description = "Normalize raw OS strings/metadata into structured data (family, product, version, arch)."
 readme = "README.md"
 requires-python = ">=3.11"