codedx 0.2.0__tar.gz → 0.3.1__tar.gz

codedx-0.3.1/CHANGELOG.md

@@ -0,0 +1,23 @@
+# Changelog
+
+## 0.3.1 — 2026-06-08
+
+- Migrate KSH97-P downloads from Socialstyrelsen to Ehälsomyndigheten Confluence
+
+## 0.3.0 — 2026-06-08
+
+### Added
+
+- `chapter_to_roman(chapter)` — convert chapter number (int, `"1"`, or `"01"`) to Roman numeral (`"I"`–`"XXII"`)
+- `roman_to_chapter(roman)` — convert Roman numeral chapter to int 1–22; case-insensitive
+- `get_range(chapter_code)` — extract code range string from a chapter title (e.g. `"01"` → `"A00-B99"`)
+- All three exported from `codedx` top-level
+
+## 0.2.0
+
+- ICD-10-SE and history file now downloaded from Ehälsomyndigheten (replacing Socialstyrelsen URLs)
+- Retired code lookup now uses the comprehensive history file (`historik-icd-10-se-1997-2026.xlsx`) covering all codes 1997–2026, instead of the partial inactivation list
+
+## 0.1.0
+
+- Initial release: ICD-10-SE, WHO ICD-10, ICD-10-CM, KSH97-P, rehab code lookups

{codedx-0.2.0 → codedx-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codedx
-Version: 0.2.0
+Version: 0.3.1
 Summary: Swedish medical coding used for diagnosis codes
 Author-email: Ludvig Hult <ludvig.hult@gmail.com>
 Requires-Python: >=3.12
@@ -46,13 +46,14 @@ Dots are dropped throughout, matching what is typically found in databases: `A01
 pip install codedx
 ```
 
-Downloads data at install time from Ehälsomyndigheten, WHO, and CDC. Raw files are not redistributed due to licence restrictions.
+Downloads data at install time. Raw files are not redistributed due to licence restrictions.
 
-## Changelog
+## Data sources
 
-### 0.2.0
-- ICD-10-SE and history file now downloaded from Ehälsomyndigheten (replacing Socialstyrelsen URLs)
-- Retired code lookup now uses the comprehensive history file (`historik-icd-10-se-1997-2026.xlsx`) covering all codes 1997–2026, instead of the partial inactivation list
+Classification files come from two Swedish authorities:
 
-### 0.1.0
-- Initial release
+**Ehälsomyndigheten** maintains ICD-10-SE and KSH97-P. Files are downloaded from their Confluence collaboration platform. KSH97-P (primary care classification) is being phased out in favour of ICD-10-SE.
+
+**Socialstyrelsen** retains responsibility for the NordDRG system and the associated rehab function codes (UA/UB series). These files are downloaded from Socialstyrelsen's website.
+
+WHO ICD-10 (English) and ICD-10-CM are downloaded from WHO and the US CDC respectively.

{codedx-0.2.0 → codedx-0.3.1}/README.md

@@ -36,13 +36,14 @@ Dots are dropped throughout, matching what is typically found in databases: `A01
 pip install codedx
 ```
 
-Downloads data at install time from Ehälsomyndigheten, WHO, and CDC. Raw files are not redistributed due to licence restrictions.
+Downloads data at install time. Raw files are not redistributed due to licence restrictions.
 
-## Changelog
+## Data sources
 
-### 0.2.0
-- ICD-10-SE and history file now downloaded from Ehälsomyndigheten (replacing Socialstyrelsen URLs)
-- Retired code lookup now uses the comprehensive history file (`historik-icd-10-se-1997-2026.xlsx`) covering all codes 1997–2026, instead of the partial inactivation list
+Classification files come from two Swedish authorities:
 
-### 0.1.0
-- Initial release
+**Ehälsomyndigheten** maintains ICD-10-SE and KSH97-P. Files are downloaded from their Confluence collaboration platform. KSH97-P (primary care classification) is being phased out in favour of ICD-10-SE.
+
+**Socialstyrelsen** retains responsibility for the NordDRG system and the associated rehab function codes (UA/UB series). These files are downloaded from Socialstyrelsen's website.
+
+WHO ICD-10 (English) and ICD-10-CM are downloaded from WHO and the US CDC respectively.

{codedx-0.2.0 → codedx-0.3.1}/hatch_build.py

@@ -5,6 +5,7 @@ import zipfile
 
 import certifi
 from hatchling.builders.hooks.plugin.interface import BuildHookInterface
+from hatchling.metadata.plugin.interface import MetadataHookInterface
 
 _DATA = pathlib.Path("src/codedx/data")
 
@@ -32,8 +33,8 @@ _MULTI_ZIPS = [
         "ksh97p.zip",
         "KSH97-P tables (~400 KB)",
         [
-            ("ksh97p_2015.xls", "https://www.socialstyrelsen.se/globalassets/sharepoint-dokument/dokument-webb/klassifikationer-och-koder/klassificering-kodtextfil-ksh97-p-2015.xls"),
-            ("ksh97p_se_en.xls", "https://www.socialstyrelsen.se/globalassets/sharepoint-dokument/dokument-webb/klassifikationer-och-koder/klassificering-kodtextfil-ksh97-primarvard-svensk-engelsk.xls"),
+            ("ksh97p_2015.xls", "https://samarbetsyta.ehalsomyndigheten.se/download/attachments/451267034/klassificering-kodtextfil-ksh97-p-2015.xls?version=2&modificationDate=1779623720433&api=v2"),
+            ("ksh97p_se_en.xls", "https://samarbetsyta.ehalsomyndigheten.se/download/attachments/451267034/klassificering-kodtextfil-ksh97-primarvard-svensk-engelsk.xls?version=1&modificationDate=1779623743547&api=v2"),
         ],
     ),
     (
@@ -60,6 +61,16 @@ def _download(url: str, dest: pathlib.Path) -> None:
             f.write(chunk)
 
 
+class CustomMetadataHook(MetadataHookInterface):
+    def update(self, metadata: dict) -> None:
+        readme = pathlib.Path("README.md").read_text(encoding="utf-8")
+        changelog = pathlib.Path("CHANGELOG.md").read_text(encoding="utf-8")
+        metadata["readme"] = {
+            "content-type": "text/markdown",
+            "text": readme + "\n\n" + changelog,
+        }
+
+
 class CustomBuildHook(BuildHookInterface):
     def initialize(self, version, build_data):
         if self.target_name != "wheel":

{codedx-0.2.0 → codedx-0.3.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "codedx"
-version = "0.2.0"
+version = "0.3.1"
 description = "Swedish medical coding used for diagnosis codes"
 readme = "README.md"
 authors = [
@@ -25,6 +25,8 @@ exclude = [
     "/.gitignore",
 ]
 
+[tool.hatch.metadata.hooks.custom]
+
 [tool.hatch.build.hooks.custom]
 
 [dependency-groups]

{codedx-0.2.0 → codedx-0.3.1}/src/codedx/__init__.py

@@ -1,6 +1,6 @@
 import pathlib
 
-__version__ = "0.2.0"
+__version__ = "0.3.0"
 _CACHE_DIR = pathlib.Path.home() / ".cache" / "codedx" / f"v{__version__}"
 
 from codedx._core import (  # noqa: E402
@@ -14,6 +14,7 @@ from codedx._core import (  # noqa: E402
     is_rehab_code,
     is_retired_icd10se_code,
 )
+from codedx.chapters import chapter_to_roman, roman_to_chapter, get_range  # noqa: E402
 
 __all__ = [
     "get_name",
@@ -25,4 +26,7 @@ __all__ = [
     "is_ksh97p_code",
     "is_rehab_code",
     "is_retired_icd10se_code",
+    "chapter_to_roman",
+    "roman_to_chapter",
+    "get_range",
 ]

codedx-0.3.1/src/codedx/chapters.py

@@ -0,0 +1,55 @@
+"""Chapter and block numeral/range utilities for ICD-10."""
+
+import re
+
+_INT_TO_ROMAN: dict[int, str] = {
+    1: "I", 2: "II", 3: "III", 4: "IV", 5: "V", 6: "VI", 7: "VII",
+    8: "VIII", 9: "IX", 10: "X", 11: "XI", 12: "XII", 13: "XIII",
+    14: "XIV", 15: "XV", 16: "XVI", 17: "XVII", 18: "XVIII",
+    19: "XIX", 20: "XX", 21: "XXI", 22: "XXII",
+}
+
+_ROMAN_TO_INT: dict[str, int] = {v: k for k, v in _INT_TO_ROMAN.items()}
+
+_RANGE_RE = re.compile(r'\(([A-Z]\d{2}(?:\.\d)?-[A-Z]\d{2}(?:\.\d)?)\)')
+
+
+def chapter_to_roman(chapter: int | str) -> str:
+    """Convert chapter number to Roman numeral. Accepts 1, '1', or '01'."""
+    n = int(chapter)
+    try:
+        return _INT_TO_ROMAN[n]
+    except KeyError:
+        raise ValueError(f"Chapter number {n!r} out of range 1–22") from None
+
+
+def roman_to_chapter(roman: str) -> int:
+    """Convert Roman numeral chapter (e.g. 'XVIII') to integer 1–22. Case-insensitive."""
+    try:
+        return _ROMAN_TO_INT[roman.upper()]
+    except KeyError:
+        raise ValueError(f"Unknown Roman numeral {roman!r}") from None
+
+
+def get_range(code: str) -> str:
+    """Return the code range string for a chapter.
+
+    Chapter '01' → 'A00-B99'  (extracted from title)
+    """
+    import polars as pl
+    from codedx._core import icd10se_table
+
+    try:
+        row = icd10se_table.row(by_predicate=pl.col("Code") == code, named=True)
+    except Exception:
+        raise ValueError(f"Code {code!r} not found in ICD-10-SE") from None
+
+    if row["Level"] != "Chapter":
+        raise ValueError(f"Code {code!r} is level {row['Level']!r}, not Chapter")
+    m = _RANGE_RE.search(row["Titel"])
+    if m:
+        return m.group(1)
+    raise ValueError(f"No range found in chapter title: {row['Titel']!r}")
+
+
+__all__ = ["chapter_to_roman", "roman_to_chapter", "get_range"]

{codedx-0.2.0 → codedx-0.3.1}/src/codedx/icd10who.py

@@ -5,13 +5,7 @@ import pathlib
 import polars as pl
 
 from codedx import _CACHE_DIR
-
-_ROMAN = {
-    "I": 1, "II": 2, "III": 3, "IV": 4, "V": 5, "VI": 6, "VII": 7,
-    "VIII": 8, "IX": 9, "X": 10, "XI": 11, "XII": 12, "XIII": 13,
-    "XIV": 14, "XV": 15, "XVI": 16, "XVII": 17, "XVIII": 18,
-    "XIX": 19, "XX": 20, "XXI": 21, "XXII": 22,
-}
+from codedx.chapters import _ROMAN_TO_INT as _ROMAN
 
 
 def _build(work_dir: pathlib.Path) -> pl.DataFrame: