Search spelling suggestions across every list

tests/test_core/test_spellfix.py

@@ -0,0 +1,191 @@
+"""Correcting a misspelled search word without wrecking an identifier.
+
+Pure arithmetic over a word list, so it is tested that way. The cases that
+matter most are the ones where it must REFUSE: a wrong suggestion is acted on,
+and here that means the wrong bay or the wrong cartridge.
+"""
+
+from shopdb.core.services.spellfix import (
+    Vocabulary, damerau_levenshtein, max_distance,
+)
+
+SHOPFLOOR = [
+    'Keyence vision system', 'Genspect', 'Telesis part marker',
+    'wax-trace', 'Zebra ZT411', 'calibration', 'Haas Automation',
+    'CSF16', 'CSF17', 'MT-1042', 'FC733SY3', 'printer', 'grinder',
+]
+
+
+def vocab():
+    return Vocabulary(SHOPFLOOR)
+
+
+# ------------------------------------------------------------------ distance
+
+def test_a_transposition_costs_one_edit_not_two():
+    """The commonest typing error. Plain Levenshtein charges two, which pushes
+    a real typo past the threshold on a short word."""
+    assert damerau_levenshtein('keyecne', 'keyence') == 1
+
+
+def test_distance_allowed_scales_with_length():
+    assert max_distance('bay') == 1
+    assert max_distance('grinder') == 2
+    assert max_distance('calibration') == 3
+
+
+# ------------------------------------------------------------------ suggests
+
+def test_it_corrects_vocabulary_no_dictionary_would_hold():
+    assert vocab().suggest('keyecne') == 'keyence'
+    assert vocab().suggest('genspct') == 'genspect'
+    assert vocab().suggest('telisis') == 'telesis'
+
+
+def test_a_word_that_is_already_right_is_left_alone():
+    assert vocab().suggest('keyence') is None
+    assert vocab().suggest('printer') is None
+
+
+def test_a_word_nothing_resembles_gets_no_guess():
+    """A wrong suggestion costs more than no suggestion."""
+    assert vocab().suggest('helicopter') is None
+
+
+# ------------------------------------------------------- identifier guards
+
+def test_an_asset_number_is_never_corrected_to_a_different_one():
+    """THE case this exists for. CSF16 to CSF17 is one edit and a different bay.
+
+    Both are in the vocabulary, so without the digit guard the near miss is
+    exactly the kind of thing edit distance loves to 'fix'.
+    """
+    assert vocab().suggest('csf18') is None
+    assert vocab().suggest('mt-1043') is None
+
+
+def test_a_typo_in_the_letters_of_an_identifier_still_corrects():
+    """The guard is on the DIGITS, not on identifiers as a whole: the digits
+    have to match, and here they do."""
+    assert vocab().suggest('cfs16') == 'csf16'
+
+
+def test_the_first_character_must_match():
+    """Typos land in the middle and at the end. Requiring the first key costs
+    little recall and removes most of the nonsense."""
+    assert vocab().suggest('teyence') is None
+
+
+def test_a_tie_produces_no_suggestion():
+    """Two equally good answers means there is no answer. CSF16 and CSF17 are
+    both one edit from CSF1x, and offering either implies a confidence that is
+    not there - but the digit guard rejects both first, so build a case where
+    only the tie is in play."""
+    tied = Vocabulary(['barn', 'bard'])
+    assert tied.suggest('bare') is None
+
+
+# ---------------------------------------------------------------- queries
+
+def test_a_multi_word_query_corrects_only_what_is_wrong():
+    assert vocab().suggest_query('keyecne calibration') == 'keyence calibration'
+
+
+def test_a_query_that_is_entirely_fine_returns_none():
+    assert vocab().suggest_query('keyence calibration') is None
+
+
+def test_short_words_are_left_alone():
+    """Below three characters there is not enough word to correct."""
+    assert vocab().suggest('cs') is None
+    assert vocab().suggest_query('cs') is None
+
+
+def test_the_vocabulary_comes_from_the_data():
+    """A vendor added this morning is correctable this morning."""
+    fresh = vocab()
+    assert fresh.suggest('renishw') is None
+    fresh.add('Renishaw')
+    assert fresh.suggest('renishw') == 'renishaw'
+
+
+# ------------------------------------------------------- wired into search
+
+def test_a_search_that_finds_nothing_offers_a_spelling(client, db, auth_headers):
+    """End to end: the vocabulary is harvested from real rows, and a misspelled
+    query that returns no results comes back with a better spelling."""
+    from shopdb.core.models import Vendor
+    from shopdb.extensions import cache
+
+    db.session.add(Vendor(vendor='Keyence'))
+    db.session.commit()
+    cache.delete('search_vocabulary')
+
+    resp = client.get('/api/search?q=keyecne', headers=auth_headers)
+    assert resp.status_code == 200
+    data = resp.get_json()['data']
+    assert data['results'] == []
+    assert data.get('suggestion') == 'keyence'
+
+
+def test_a_search_that_finds_something_offers_nothing(client, db, auth_headers):
+    from shopdb.core.models import Vendor
+    from shopdb.extensions import cache
+
+    db.session.add(Vendor(vendor='Keyence'))
+    db.session.commit()
+    cache.delete('search_vocabulary')
+
+    resp = client.get('/api/search?q=keyence', headers=auth_headers)
+    assert 'suggestion' not in resp.get_json()['data']
+
+
+def test_a_mistyped_asset_number_is_not_corrected_to_a_real_one(
+        client, db, auth_headers):
+    """The guard, through the endpoint. CSF17 exists; CSF18 does not; and the
+    answer to "CSF18" must be no results and NO suggestion, not a different
+    bay."""
+    from shopdb.core.models import Asset, AssetType
+    from shopdb.extensions import cache
+
+    assettype = AssetType.query.first() or AssetType(assettype='machine')
+    if not assettype.assettypeid:
+        db.session.add(assettype)
+        db.session.flush()
+    db.session.add(Asset(assetnumber='CSF17', assettypeid=assettype.assettypeid))
+    db.session.commit()
+    cache.delete('search_vocabulary')
+
+    resp = client.get('/api/search?q=CSF18', headers=auth_headers)
+    data = resp.get_json()['data']
+    assert data['results'] == []
+    assert 'suggestion' not in data
+
+
+def test_the_suggest_endpoint_serves_any_page(client, db, auth_headers):
+    """The shared endpoint every list uses, rather than a suggestion key added
+    to thirty search routes."""
+    from shopdb.core.models import Vendor
+    from shopdb.extensions import cache
+
+    db.session.add(Vendor(vendor='Keyence'))
+    db.session.commit()
+    cache.delete('search_vocabulary')
+
+    resp = client.get('/api/search/suggest?q=keyecne', headers=auth_headers)
+    assert resp.status_code == 200
+    assert resp.get_json()['data']['suggestion'] == 'keyence'
+
+
+def test_the_suggest_endpoint_says_null_rather_than_guessing(client, db,
+                                                             auth_headers):
+    from shopdb.extensions import cache
+    cache.delete('search_vocabulary')
+    resp = client.get('/api/search/suggest?q=helicopter', headers=auth_headers)
+    assert resp.get_json()['data']['suggestion'] is None
+
+
+def test_the_suggest_endpoint_ignores_a_too_short_query(client, auth_headers):
+    resp = client.get('/api/search/suggest?q=c', headers=auth_headers)
+    assert resp.status_code == 200
+    assert resp.get_json()['data']['suggestion'] is None