backend/scraper: Add parser methods for Language

We can expect a number of scraper sources to either give languages as
ISO 639-3 or as their English name, so it makes sense to implement a
simple parser method on our side.

2 files changed, 65 insertions, 0 deletions

diff --git a/src/hircine/scraper/types.py b/src/hircine/scraper/types.py
index 534792b..23cb634 100644
--- a/src/hircine/scraper/types.py
+++ b/src/hircine/scraper/types.py
@@ -137,6 +137,38 @@ class Language:
     def __bool__(self):
         return self.value is not None
 
+    @classmethod
+    def from_iso_639_3(cls, string):
+        """
+        Returns a new instance of this class given a case-insensitive ISO 639-3
+        language code.
+
+        :param str string: The ISO 639-3 language code.
+        :raise: :exc:`~hircine.scraper.ScrapeWarning` if the language code could
+                not be parsed.
+        """
+        try:
+            return Language(value=hircine.enums.Language[string.upper()])
+        except KeyError as e:
+            raise ScrapeWarning(
+                f"Could not parse language code: '{string}' as ISO 639-3"
+            ) from e
+
+    @classmethod
+    def from_name(cls, string):
+        """
+        Returns a new instance of this class given a case-insensitive language name.
+        Permissible language names are defined in :class:`hircine.enums.Language`.
+
+        :param str string: The language name.
+        :raise: :exc:`~hircine.scraper.ScrapeWarning` if the language name could
+                not be parsed.
+        """
+        try:
+            return Language(value=hircine.enums.Language(string.capitalize()))
+        except ValueError as e:
+            raise ScrapeWarning(f"Could not parse language name: '{string}'") from e
+
 
 @dataclass(frozen=True)
 class Direction:
diff --git a/tests/scrapers/test_types.py b/tests/scrapers/test_types.py
index ee6b802..33f9f89 100644
--- a/tests/scrapers/test_types.py
+++ b/tests/scrapers/test_types.py
@@ -2,6 +2,7 @@ from datetime import date
 
 import pytest
 
+import hircine.enums as enums
 from hircine.api.types import ScrapedComic
 from hircine.scraper import ScrapeWarning
 from hircine.scraper.types import (
@@ -130,3 +131,35 @@ def test_scraped_comic_silently_ignores_empty(item, attr, empty):
     comic = ScrapedComic.from_generator(gen())
 
     assert getattr(comic, attr) == empty
+
+
+@pytest.mark.parametrize(
+    "input,want",
+    [
+        ("EN", Language(value=enums.Language.EN)),
+        ("de", Language(value=enums.Language.DE)),
+    ],
+)
+def test_language_from_iso_639_3(input, want):
+    assert Language.from_iso_639_3(input) == want
+
+
+def test_language_from_iso_639_3_fails():
+    with pytest.raises(ScrapeWarning, match="Could not parse language code:"):
+        Language.from_iso_639_3("ENG")
+
+
+@pytest.mark.parametrize(
+    "input,want",
+    [
+        ("English", Language(value=enums.Language.EN)),
+        ("german", Language(value=enums.Language.DE)),
+    ],
+)
+def test_language_from_name(input, want):
+    assert Language.from_name(input) == want
+
+
+def test_language_from_name_fails():
+    with pytest.raises(ScrapeWarning, match="Could not parse language name:"):
+        Language.from_name("nonexistent")