dalia_dif 0.0.17__tar.gz → 0.0.19__tar.gz

{dalia_dif-0.0.17 → dalia_dif-0.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dalia_dif
-Version: 0.0.17
+Version: 0.0.19
 Summary: Tools for DALIA's data model for open educational resources
 Keywords: snekpack,cookiecutter,open educational resources,educational resources,training
 Author: Charles Tapley Hoyt
@@ -39,9 +39,9 @@ Maintainer: Charles Tapley Hoyt
 Maintainer-email: Charles Tapley Hoyt <cthoyt@gmail.com>
 Requires-Python: >=3.10
 Project-URL: Bug Tracker, https://github.com/data-literacy-alliance/dalia-dif/issues
-Project-URL: Documentation, https://dalia-dif.readthedocs.io
 Project-URL: Homepage, https://github.com/data-literacy-alliance/dalia-dif
 Project-URL: Repository, https://github.com/data-literacy-alliance/dalia-dif.git
+Project-URL: Documentation, https://dalia-dif.readthedocs.io
 Provides-Extra: export
 Provides-Extra: fti
 Description-Content-Type: text/markdown

{dalia_dif-0.0.17 → dalia_dif-0.0.19}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "dalia_dif"
-version = "0.0.17"
+version = "0.0.19"
 description = "Tools for DALIA's data model for open educational resources"
 readme = "README.md"
 authors = [
@@ -250,7 +250,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.0.17"
+current_version = "0.0.19"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{dalia_dif-0.0.17 → dalia_dif-0.0.19}/src/dalia_dif/cli.py

@@ -18,10 +18,19 @@ def main() -> None:
 @main.command()
 @click.option("--dif-version", type=click.Choice(["1.3"]), default="1.3")
 @click.option("--ignore-missing-description", is_flag=True)
+@click.option("--communities-path", type=Path)
 @click.argument("location")
-def validate(location: str, dif_version: str, ignore_missing_description: bool) -> None:
+def validate(
+    location: str, dif_version: str, ignore_missing_description: bool, communities_path: Path | None
+) -> None:
     """Validate a local/remote file or local folder of DIF-encoded CSVs."""
     from dalia_dif.dif13 import read_dif13
+    from dalia_dif.dif13.community import get_communities_dict
+
+    if communities_path is not None:
+        community_dict = get_communities_dict(communities_path)
+    else:
+        community_dict = {}
 
     fail = False
     p = Path(location)
@@ -36,6 +45,7 @@ def validate(location: str, dif_version: str, ignore_missing_description: bool)
                 path,
                 error_accumulator=errors,
                 ignore_missing_description=ignore_missing_description,
+                custom_community_dict=community_dict,
             )
             if errors:
                 fail = True

dalia_dif-0.0.19/src/dalia_dif/dif13/community/__init__.py

@@ -0,0 +1,84 @@
+"""Code for curated DALIA communities."""
+
+import csv
+from collections import Counter
+from pathlib import Path
+from typing import Any, TypeAlias
+
+from pydantic import UUID4, AnyHttpUrl, BaseModel, Field
+
+HERE = Path(__file__).parent.resolve()
+COMMUNITIES_PATH = HERE / "dalia_communities.csv"
+
+
+class Community(BaseModel):
+    """A data model for communities."""
+
+    uuid: UUID4
+    title: str
+    ror: str | None = None
+    website: AnyHttpUrl | None = None
+    synonyms: list[str] = Field(default_factory=list)
+
+
+RENAMES = {
+    "ID": "uuid",
+    "ROR": "ror",
+    "Website": "website",
+    "Synonyms": "synonyms",
+    "Title": "title",
+}
+
+
+def _process(row: dict[str, Any]) -> Community:
+    row = {RENAMES[k]: v for k, v in row.items() if v}
+    if synonyms_raw := row.pop("synonyms", None):
+        row["synonyms"] = [s.strip() for s in synonyms_raw.split("|")]
+    return Community.model_validate(row)
+
+
+def read_communities(path: Path) -> list[Community]:
+    """Read communities."""
+    with open(path, newline="") as csvfile:
+        return [_process(row) for row in csv.DictReader(csvfile)]
+
+
+CommunityDict: TypeAlias = dict[str, str]
+
+
+def get_communities_dict(path: Path) -> CommunityDict:
+    """Get a mapping from names/synonyms to UUID strings."""
+    rv = {}
+    for community in read_communities(path):
+        rv[community.title] = str(community.uuid)
+        for synonym in community.synonyms:
+            rv[synonym] = str(community.uuid)
+    return rv
+
+
+def _read_mapping() -> dict[str, str]:
+    rv = {}
+    for community in read_communities(COMMUNITIES_PATH):
+        rv[community.title] = str(community.uuid)
+        for synonym in community.synonyms:
+            rv[synonym] = str(community.uuid)
+    return rv
+
+
+LOOKUP_DICT_COMMUNITIES: CommunityDict = get_communities_dict(COMMUNITIES_PATH)
+
+MISSING_COMMUNITIES: Counter[str] = Counter()
+
+
+def get_community_labels() -> dict[str, str]:
+    """Get community labels."""
+    return {
+        str(community.uuid): COMMUNITY_RELABELS.get(community.title, community.title)
+        for community in read_communities(COMMUNITIES_PATH)
+    }
+
+
+COMMUNITY_RELABELS = {
+    "Nationale Forschungsdateninfrastruktur (NFDI)": "NFDI",
+    "HeFDI - Hessische Forschungsdateninfrastrukturen": "HeFDI",
+}

{dalia_dif-0.0.17 → dalia_dif-0.0.19}/src/dalia_dif/dif13/reader.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 import logging
 import re
-from collections import Counter
+from collections import ChainMap, Counter
 from pathlib import Path
 from typing import TextIO
 
@@ -17,7 +17,7 @@ from pystow.utils import safe_open_dict_reader
 from rdflib import URIRef
 from tqdm import tqdm
 
-from .community import LOOKUP_DICT_COMMUNITIES
+from .community import LOOKUP_DICT_COMMUNITIES, CommunityDict
 from .model import (
     AuthorDIF13,
     EducationalResourceDIF13,
@@ -102,6 +102,7 @@ def read_dif13(
     error_accumulator: list[str] | None = None,
     converter: curies.Converter | None = None,
     ignore_missing_description: bool = False,
+    custom_community_dict: CommunityDict | None = None,
 ) -> list[EducationalResourceDIF13]:
     """Parse DALIA records."""
     if isinstance(path, str) and (path.startswith("http://") or path.startswith("https://")):
@@ -139,6 +140,7 @@ def read_dif13(
                     error_accumulator=error_accumulator,
                     converter=converter,
                     ignore_missing_description=ignore_missing_description,
+                    custom_community_dict=custom_community_dict,
                 )
             )
             is not None
@@ -164,13 +166,18 @@ def parse_dif13_row(  # noqa:C901
     error_accumulator: list[str] | None = None,
     converter: curies.Converter | None = None,
     ignore_missing_description: bool = False,
+    custom_community_dict: CommunityDict | None = None,
 ) -> EducationalResourceDIF13 | None:
     """Convert a row in a DALIA curation file to a resource, or return none if unable."""
     if isinstance(file_name, Path):
         file_name = file_name.name
 
     supporting_communities, recommending_communities = _process_communities(
-        file_name, idx, row, error_accumulator=error_accumulator
+        file_name,
+        idx,
+        row,
+        error_accumulator=error_accumulator,
+        custom_community_dict=custom_community_dict,
     )
 
     external_uris = _pop_split(row, "Link")
@@ -473,8 +480,10 @@ def _process_communities(
     row: dict[str, str],
     *,
     error_accumulator: list[str] | None = None,
+    custom_community_dict: CommunityDict | None = None,
 ) -> tuple[list[URIRef], list[URIRef]]:
     supporting, recommending = [], []
+    community_dict = ChainMap(custom_community_dict or {}, LOOKUP_DICT_COMMUNITIES)
     for community in _pop_split(row, "Community"):
         match = COMMUNITY_RELATION_RE.search(community)
         if not match:
@@ -489,7 +498,7 @@ def _process_communities(
         name = match.group("name").strip()
         relation = match.group("relation")
 
-        community_uuid = LOOKUP_DICT_COMMUNITIES.get(name, None)
+        community_uuid = community_dict.get(name, None)
         if not community_uuid:
             if not MISSING_COMMUNITIES[name]:
                 _log(

{dalia_dif-0.0.17 → dalia_dif-0.0.19}/src/dalia_dif/version.py

@@ -12,7 +12,7 @@ __all__ = [
     "get_version",
 ]
 
-VERSION = "0.0.17"
+VERSION = "0.0.19"
 
 
 def get_git_hash() -> str:

dalia_dif-0.0.17/src/dalia_dif/dif13/community/__init__.py

@@ -1,40 +0,0 @@
-"""Code for curated DALIA communities."""
-
-import csv
-from collections import Counter
-from pathlib import Path
-
-HERE = Path(__file__).parent.resolve()
-COMMUNITIES_PATH = HERE / "dalia_communities.csv"
-
-
-def _read_mapping() -> dict[str, str]:
-    rv = {}
-    with open(COMMUNITIES_PATH, newline="") as csvfile:
-        for row in csv.DictReader(csvfile):
-            rv[row["Title"]] = row["ID"]
-            for synonym in row["Synonyms"].split("|"):
-                rv[synonym] = row["ID"]
-    return rv
-
-
-LOOKUP_DICT_COMMUNITIES = _read_mapping()
-
-del _read_mapping
-
-MISSING_COMMUNITIES: Counter[str] = Counter()
-
-
-def get_community_labels() -> dict[str, str]:
-    """Get community labels."""
-    with open(COMMUNITIES_PATH, newline="") as csvfile:
-        return {
-            row["ID"]: COMMUNITY_RELABELS.get(row["Title"], row["Title"])
-            for row in csv.DictReader(csvfile)
-        }
-
-
-COMMUNITY_RELABELS = {
-    "Nationale Forschungsdateninfrastruktur (NFDI)": "NFDI",
-    "HeFDI - Hessische Forschungsdateninfrastrukturen": "HeFDI",
-}