feat: import fruit DB from XML — scripts/import_fruits.py (story #03)

Adds a repeatable Python import script that populates fruits, fruit_synonyms,
and fruit_images from 03-data/obstsorten.xml and the three image directories.
Idempotent: deletes synonyms and images per fruit before re-inserting; upserts
fruit row by osdb_number. Reads DATABASE_URL from env.

- map_typ: 23 XML typ codes → 17-value fruit_type enum; aggregate types coerced
  with logged warning; typ='p' (2 entries) mapped to Pfirsiche
- parse_synonyms: comma-split with whitespace/newline strip, empty filter
- parse_date: YYYYMMDD → date, fallback None → DB default NOW()
- find_images: globs {id}_*_s0.* across einzelfruechte/blueten/baume dirs
- 42 unit tests (no DB required) cover all mapping, parsing, and glob logic
- Makefile test target extended to include Python test suite
- 03-data/ and obstsorten.zip added to .gitignore (large binary data)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-06-17 13:24:29 +02:00
co-authored by Claude Sonnet 4.6
parent 841f53fac8
commit 4d4c5f399f
4 changed files with 421 additions and 1 deletions
+178
View File
@@ -0,0 +1,178 @@
import os
import tempfile
import unittest
from datetime import date
from import_fruits import map_typ, parse_synonyms, parse_date, find_images
class TestMapTyp(unittest.TestCase):
def test_maps_a_to_apfelsorten(self):
self.assertEqual(map_typ("a"), "Apfelsorten")
def test_maps_b_to_birnensorten(self):
self.assertEqual(map_typ("b"), "Birnensorten")
def test_maps_bq_aggregate_to_birnensorten(self):
self.assertEqual(map_typ("bq"), "Birnensorten")
def test_maps_q_to_quittensorten(self):
self.assertEqual(map_typ("q"), "Quittensorten")
def test_maps_apr_to_aprikosen(self):
self.assertEqual(map_typ("apr"), "Aprikosen")
def test_maps_aprpfi_aggregate_to_aprikosen(self):
self.assertEqual(map_typ("aprpfi"), "Aprikosen")
def test_maps_pfi_to_pfirsiche(self):
self.assertEqual(map_typ("pfi"), "Pfirsiche")
def test_maps_p_to_pfirsiche(self):
self.assertEqual(map_typ("p"), "Pfirsiche")
def test_maps_mir_to_mirabellen(self):
self.assertEqual(map_typ("mir"), "Mirabellen")
def test_maps_mirren_aggregate_to_mirabellen(self):
self.assertEqual(map_typ("mirren"), "Mirabellen")
def test_maps_ren_to_renekloden(self):
self.assertEqual(map_typ("ren"), "Renekloden")
def test_maps_pfl_to_pflaumen(self):
self.assertEqual(map_typ("pfl"), "Pflaumen")
def test_maps_pflzwe_aggregate_to_pflaumen(self):
self.assertEqual(map_typ("pflzwe"), "Pflaumen")
def test_maps_zwe_to_zwetschen(self):
self.assertEqual(map_typ("zwe"), "Zwetschen")
def test_maps_k_aggregate_to_sauerkirschen(self):
self.assertEqual(map_typ("k"), "Sauerkirschen")
def test_maps_bo_aggregate_to_brombeeren(self):
self.assertEqual(map_typ("bo"), "Brombeeren")
def test_maps_bob_to_brombeeren(self):
self.assertEqual(map_typ("bob"), "Brombeeren")
def test_maps_boe_to_erdbeeren(self):
self.assertEqual(map_typ("boe"), "Erdbeeren")
def test_maps_boh_to_himbeeren(self):
self.assertEqual(map_typ("boh"), "Himbeeren")
def test_maps_boj_to_johannisbeeren(self):
self.assertEqual(map_typ("boj"), "Johannisbeeren")
def test_maps_bos_to_stachelbeeren(self):
self.assertEqual(map_typ("bos"), "Stachelbeeren")
def test_maps_wei_to_wein(self):
self.assertEqual(map_typ("wei"), "Wein")
def test_maps_w_to_wein(self):
self.assertEqual(map_typ("w"), "Wein")
def test_maps_x_aggregate_to_apfelsorten(self):
self.assertEqual(map_typ("x"), "Apfelsorten")
def test_returns_none_for_unknown_typ(self):
self.assertIsNone(map_typ("zzz"))
class TestParseSynonyms(unittest.TestCase):
def test_splits_by_comma(self):
self.assertEqual(parse_synonyms("Boskop, Boskoop"), ["Boskop", "Boskoop"])
def test_strips_whitespace_and_newlines(self):
result = parse_synonyms("\nBoskop Renette [IH.1],\nBoskoop\n")
self.assertEqual(result, ["Boskop Renette [IH.1]", "Boskoop"])
def test_filters_empty_parts(self):
self.assertEqual(parse_synonyms(" , , Boskop ,"), ["Boskop"])
def test_empty_string_returns_empty_list(self):
self.assertEqual(parse_synonyms(""), [])
def test_single_synonym_no_comma(self):
self.assertEqual(parse_synonyms("White Paradise"), ["White Paradise"])
def test_none_returns_empty_list(self):
self.assertEqual(parse_synonyms(None), [])
class TestParseDate(unittest.TestCase):
def test_parses_yyyymmdd(self):
self.assertEqual(parse_date("20070806"), date(2007, 8, 6))
def test_empty_string_returns_none(self):
self.assertIsNone(parse_date(""))
def test_none_returns_none(self):
self.assertIsNone(parse_date(None))
def test_invalid_format_returns_none(self):
self.assertIsNone(parse_date("not-a-date"))
class TestFindImages(unittest.TestCase):
def setUp(self):
self.tmpdir = tempfile.mkdtemp()
self.ef_dir = os.path.join(self.tmpdir, "einzelfruechte")
self.bl_dir = os.path.join(self.tmpdir, "blueten")
self.bau_dir = os.path.join(self.tmpdir, "baume")
for d in (self.ef_dir, self.bl_dir, self.bau_dir):
os.makedirs(d)
def _touch(self, path, content=b"img"):
with open(path, "wb") as f:
f.write(content)
def test_finds_fruit_image(self):
self._touch(os.path.join(self.ef_dir, "adams_apfel_ef_s0.jpg"))
imgs = find_images("adams_apfel", self.tmpdir)
types = [i["image_type"] for i in imgs]
self.assertIn("fruit", types)
def test_finds_flower_image(self):
self._touch(os.path.join(self.bl_dir, "adams_apfel_frucht_s0.jpg"))
imgs = find_images("adams_apfel", self.tmpdir)
types = [i["image_type"] for i in imgs]
self.assertIn("flower", types)
def test_finds_tree_image(self):
self._touch(os.path.join(self.bau_dir, "adams_apfel_bau_s0.jpg"))
imgs = find_images("adams_apfel", self.tmpdir)
types = [i["image_type"] for i in imgs]
self.assertIn("tree", types)
def test_skips_tn_files(self):
self._touch(os.path.join(self.ef_dir, "adams_apfel_ef_tn.jpg"))
imgs = find_images("adams_apfel", self.tmpdir)
self.assertEqual(imgs, [])
def test_returns_empty_when_no_match(self):
imgs = find_images("unknown_fruit", self.tmpdir)
self.assertEqual(imgs, [])
def test_image_contains_bytes_and_filename(self):
content = b"\x89PNG\r\n"
self._touch(os.path.join(self.ef_dir, "adams_apfel_ef_s0.jpg"), content)
imgs = find_images("adams_apfel", self.tmpdir)
self.assertEqual(len(imgs), 1)
self.assertEqual(imgs[0]["data"], content)
self.assertEqual(imgs[0]["filename"], "adams_apfel_ef_s0.jpg")
def test_finds_all_three_types(self):
self._touch(os.path.join(self.ef_dir, "abbe_fetel_ef_s0.jpg"))
self._touch(os.path.join(self.bl_dir, "abbe_fetel_frucht_s0.jpg"))
self._touch(os.path.join(self.bau_dir, "abbe_fetel_bau_s0.jpg"))
imgs = find_images("abbe_fetel", self.tmpdir)
self.assertEqual(len(imgs), 3)
if __name__ == "__main__":
unittest.main()