Game line names across languages; RSubtitle; editor in three columns

tests/test_catalog.py

@@ -49,11 +49,34 @@ def test_synthetic_catalog_names_and_search(synth_game):
 
 
 def test_characters_csv_covers_user_lists():
-    chars = load_characters()
-    assert len(chars) > 3000
+    chars = load_characters(lang="ITA")
+    assert len(chars) > 3000 and len(load_characters()) > 2500     # most labels apply in every language
+    # the lists name ITA sounds by position (wemscan): NAME_i = variation i of the ITA WAD entry (alias NAME#i)
     src = os.path.join(catalog_dir(), "source", "ita", "Joker.txt")
     first = open(src).readline().strip()[:-4]
-    assert "Joker" in chars[first.lower()]
+    base, i = first.rsplit("_", 1)
+    ita = read_csv(os.path.join(catalog_dir(), "ITA.csv"))
+    s = next(s for s in ita if first.lower() in {n.lower() for n in s.names()} or
+             "%s#%s" % (base, i) in s.aliases)
+    assert "Joker" in s.character
+    # every labelled ITA sound keeps its label (takes of one line, NAME#k, share it), and most labels reach INT
+    assert sum(1 for x in ita if x.character) >= 3366
+    assert sum(1 for x in read_csv(os.path.join(catalog_dir(), "INT.csv")) if x.character) > 2900
+
+
+def test_line_names_agree_across_languages_and_subtitles():
+    """Speech sounds carry the game's line name: the same names in every language, and a linked subtitle's
+    sound has the subtitle's line name (positions inside WAD entries differ per language: findings 20)."""
+    from ackit import subtitles
+    ita = {s.name for s in read_csv(os.path.join(catalog_dir(), "ITA.csv")) if s.group == "Speech"}
+    intl = {s.name for s in read_csv(os.path.join(catalog_dir(), "INT.csv")) if s.group == "Speech"}
+    assert len(ita & intl) > 0.97 * len(ita)
+    snd = {s.key: s for s in read_csv(os.path.join(catalog_dir(), "ITA.csv"))}
+    rows = [r for r in subtitles.read_texts(os.path.join(catalog_dir(), "SUB_ITA.csv"), "ITA") if r.sound in snd]
+    same = sum(1 for r in rows if snd[r.sound].name.split("#")[0] == r.speech)
+    assert len(rows) > 8000 and same > 0.99 * len(rows)
+    hdr = next(csv.reader(open(os.path.join(catalog_dir(), "characters.csv"), encoding="utf-8")))
+    assert hdr == ["name", "character", "language"]
 
 
 def test_shipped_csvs_are_consistent():
@@ -87,8 +110,8 @@ def test_real_game_uses_shipped_catalog(real_game_dir):
     bank = read_csv(os.path.join(catalog_dir(), "BANK.csv"))
     assert len(cat.sounds) == 10816 + 651 + sum(1 for s in bank if s.language in ("", "ITA"))
     assert {s.language for s in cat.sounds if s.archive == "BANK"} == {"", "ITA"}
-    s = cat.resolve("Speech_TAPE_JOKER_1_4")
-    assert s.category == "Interview tapes" and s.size == 44985
+    s = cat.resolve("Speech_TAPE_JOKER_1#4")             # position 4 in the ITA entry (the user's list name)
+    assert s.category == "Interview tapes" and s.size == 44985 and s.name.startswith("Speech_TAPE_JOKER_1_")
     assert len(cat.heads) == 396 and sum(len(v) for v in cat.heads.values()) == 2101
     b = cat.resolve("Play_BatmanDeviceImpact_Wood_1")
     assert b.archive == "BANK" and b.group == "SFX"