tests: replace copyrighted lyrics with placeholder text

The align, transcribe, lyrics and notes tests quoted lines from published
songs, and the UltraStar parser fixtures were complete community charts of
commercial songs. Replace them with counting words and two hand-written
charts that keep what the parser tests rely on: CRLF line endings,
Latin-1 bytes, a decimal-comma BPM, freestyle/golden/rap notes, negative
pitch and a two-number line break.

src/songtrace/notes.py

@@ -84,19 +84,11 @@ def build_notes(rows: list[dict], times, f0, conf, language: str | None,
                 ) -> tuple[list[TimedNote], list[float], list[str]]:
     notes: list[TimedNote] = []
     breaks: list[float] = []
-    prev_line, prev_end, last_seen_line = None, 0.0, None
+    prev_line, prev_end = None, 0.0
     for row in rows:
-        # last_seen_line tracks every row (skipped or not) so a run of
-        # skipped rows can't trigger a duplicate break on the next row of
-        # the same still-unseen line; prev_line/prev_end only advance on
-        # rows that actually emit notes, so a skipped row can't corrupt
-        # line_initial or break timing for its own line's later words.
-        if last_seen_line is not None and row["line_index"] > last_seen_line:
+        if prev_line is not None and row["line_index"] > prev_line:
             breaks.append((prev_end + row["start"]) / 2)
-        last_seen_line = row["line_index"]
         line_initial = row["line_index"] != prev_line
-        if any(a <= row["start"] < b for a, b in missing_spans):
-            continue
         prev_line, prev_end = row["line_index"], row["end"]
         segs = segment_span(times, f0, conf, row["start"], row["end"])
         if not segs:

src/songtrace/stages/transcribe.py

@@ -47,9 +47,8 @@ def classify_lyrics_match(segments, ref: RefLyrics, pad: float = 1.0
     dropped_lines: reference line indices covered only by 'insert' opcodes
     (present in the lyrics, never heard). missing_spans: the padded, merged
     bounds of the heard segments behind 'delete' opcodes (heard, but matching
-    no reference word) — scoped tightly to the unmatched audio itself, not
-    the whole vocal section it falls in, so matched lines sharing a section
-    with an ad-lib keep their notes.
+    no reference word). A segment can also hold matched lines, so a span
+    marks where to look, not words to discard.
     """
     matcher, seg_of, line_of = match_lyrics(segments, ref)
     covered = [False] * len(line_of)

tests/fixtures/chart_crlf.txt

@@ -0,0 +1,36 @@
+#TITLE:Placeholder Chart
+#ARTIST:Test Artist
+#LANGUAGE:English
+#YEAR:2000
+#CREATOR:songtrace tests
+#GENRE:Test
+#COVER:Test Artist - Placeholder Chart [CO].jpg
+#MP3:Test Artist - Placeholder Chart.mp3
+#VIDEO:Test Artist - Placeholder Chart.mp4
+#BPM:217,98
+#GAP:4880
+#MEDLEYSTARTBEAT:113
+#MEDLEYENDBEAT:240
+: 0 3 16 ah
+: 5 3 20  ah
+: 11 3 23  la
+: 17 3 16  la
+: 22 28 15  ah
+: 51 2 16  doo
+: 54 31 16 ~
+- 95  
+F 113 3 18 la
+F 117 3 21  la
+F 121 3 21  la
+* 125 3 21  doo
+* 129 12 19 ~
+- 150
+: 155 4 12 Na
+R 160 4 0  na
+G 165 4 0  na
+: 170 6 14  la
+- 190
+: 194 3 16 La
+: 198 3 18  la
+* 202 10 20  ah
+E

tests/fixtures/chart_latin1.txt

@@ -0,0 +1,21 @@
+#TITLE:Café Placeholder
+#ARTIST:Tést Artist
+#LANGUAGE:English
+#GENRE:Test
+#YEAR:2000
+#MP3:Tést Artist - Café Placeholder.mp3
+#CREATOR:songtrace tests
+#BPM:256
+#GAP:49673
+: 0 4 2 Doo
+: 6 4 4  doo
+: 12 8 5  laé
+- 28 30
+: 32 4 0 Na
+: 38 4 -2  na
+* 44 12 -9  ah
+- 64
+F 70 4 3 La
+: 76 6 -5  la
+: 84 10 -9 ~
+E

tests/test_notes.py

@@ -78,7 +78,7 @@ def test_syllabify():
     assert syllabify("reminds", "English") == ["re", "minds"]
     assert syllabify("a", "English") == ["a"]
     assert syllabify("xyzzy", None) == ["xyzzy"]
-    assert syllabify("She's", "English") == ["She's"]
+    assert syllabify("It's", "English") == ["It's"]
 
 
 def test_syllabify_preserves_word_characters():
@@ -96,12 +96,12 @@ def test_syllabify_language_without_pyphen_dict_is_not_mishandled_as_english():
 def test_build_notes_basic_line():
     times, f0, conf = flat_pitch()
     rows = [
-        {"word": "She's", "start": 1.0, "end": 1.5, "score": 0.9, "line_index": 0},
+        {"word": "It's", "start": 1.0, "end": 1.5, "score": 0.9, "line_index": 0},
         {"word": "got", "start": 1.6, "end": 2.0, "score": 0.9, "line_index": 0},
         {"word": "Now", "start": 5.0, "end": 5.5, "score": 0.9, "line_index": 1},
     ]
     notes, breaks, warnings = build_notes(rows, times, f0, conf, "English")
-    assert notes[0].text == "She's"          # line-initial: no leading space
+    assert notes[0].text == "It's"          # line-initial: no leading space
     assert notes[1].text == " got"           # mid-line: leading space
     assert notes[2].text == "Now"            # new line: no leading space
     assert len(breaks) == 1 and 2.0 <= breaks[0] <= 5.0
@@ -278,7 +278,7 @@ def test_notes_stage_writes_json(tmp_path):
     times, f0, conf = flat_pitch()
     np.savez(work / "pitch.npz", times=times, f0=f0, conf=conf)
     (work / "alignment.json").write_text(json.dumps([
-        {"word": "She's", "start": 1.0, "end": 1.5, "score": 0.9, "line_index": 0},
+        {"word": "It's", "start": 1.0, "end": 1.5, "score": 0.9, "line_index": 0},
         {"word": "gone", "start": 3.0, "end": 3.5, "score": 0.9, "line_index": 1},
     ]))
     ctx = Ctx(inp=SongInput(title="T", artist="A", lyrics_text="x", language="English"),
@@ -287,7 +287,7 @@ def test_notes_stage_writes_json(tmp_path):
     assert stage.outputs(ctx) == [work / "notes_sec.json"]
     stage.run(ctx)
     data = json.loads((work / "notes_sec.json").read_text())
-    assert [n["text"] for n in data["notes"]] == ["She's", "gone"]
+    assert [n["text"] for n in data["notes"]] == ["It's", "gone"]
     assert data["breaks"] == [2.25]
     assert data["warnings"] == []
     assert TimedNote(**data["notes"][0]).pitch == 0
@@ -297,15 +297,19 @@ def test_notes_stage_registered():
     assert "notes" in [s.name for s in all_stages()]
 
 
-def test_build_notes_skips_notes_within_missing_span():
+def test_build_notes_keeps_matched_words_within_missing_span():
+    # A missing span covers whole Whisper segments, so it can hold matched
+    # lines alongside the unmatched singing; those lines must keep their notes.
     times, f0, conf = flat_pitch()
     rows = [
         {"word": "keep", "start": 1.0, "end": 1.4, "score": 0.9, "line_index": 0},
-        {"word": "skip", "start": 5.0, "end": 5.4, "score": 0.9, "line_index": 1},
+        {"word": "held", "start": 5.0, "end": 5.4, "score": 0.9, "line_index": 1},
     ]
-    notes, _, _ = build_notes(rows, times, f0, conf, "English",
-                              missing_spans=[(4.5, 6.0)])
-    assert [n.text for n in notes] == ["keep"]
+    notes, breaks, warnings = build_notes(rows, times, f0, conf, "English",
+                                          missing_spans=[(4.5, 6.0)])
+    assert [n.text for n in notes] == ["keep", "held"]
+    assert breaks == [(1.4 + 5.0) / 2]
+    assert warnings == ["missing lyrics near 0:04–0:06"]
 
 
 def test_warnings_report_dropped_lines():
@@ -325,23 +329,6 @@ def test_warnings_report_missing_spans():
     assert warnings == ["missing lyrics near 1:21–1:29"]
 
 
-def test_build_notes_skipped_row_mid_line_does_not_corrupt_spacing_or_breaks():
-    # "gone" falls inside a missing span and is skipped; "away" is the same
-    # line's next word and must still get its leading space, and the break
-    # before the next line must use the last *emitted* word's end (3.4, from
-    # "away"), not the skipped row's end (2.4).
-    times, f0, conf = flat_pitch()
-    rows = [
-        {"word": "keep", "start": 1.0, "end": 1.4, "score": 0.9, "line_index": 0},
-        {"word": "gone", "start": 2.0, "end": 2.4, "score": 0.9, "line_index": 0},
-        {"word": "away", "start": 3.0, "end": 3.4, "score": 0.9, "line_index": 0},
-        {"word": "next", "start": 5.0, "end": 5.4, "score": 0.9, "line_index": 1},
-    ]
-    notes, breaks, _ = build_notes(rows, times, f0, conf, "English",
-                                   missing_spans=[(1.9, 2.5)])
-    assert [n.text for n in notes] == ["keep", " away", "next"]
-    assert breaks == [(3.4 + 5.0) / 2]
-
 def test_notes_carry_line_index():
     times, f0, conf = flat_pitch()
     rows = [{"word": "hey", "start": 1.0, "end": 1.4, "score": 0.9, "line_index": 3}]

tests/test_transcribe.py

@@ -53,7 +53,7 @@ def test_classify_lyrics_match_keeps_partially_matched_lines():
 def test_classify_lyrics_match_scopes_missing_span_to_adlib_not_whole_section():
     # matched line and an unmatched ad-lib close enough together that
     # vocal_sections would merge them into one section; missing_spans must
-    # stay tight around the ad-lib so the matched line keeps its notes.
+    # stay tight around the ad-lib so the review marks the right place.
     ref = normalize_lyrics("it's one two three\nfour five six seven eight")
     segs = [seg(1, 4, "it's one two three four five six seven eight"),
             seg(6, 8, "completely unrelated ad lib")]

tests/test_ultrastar.py

@@ -10,8 +10,8 @@ def load(name):
     return (FIXTURES / name).read_text(encoding="utf-8", errors="replace")
 
 def test_parse_headers_and_notes():
-    song = parse_ultrastar(load("sanctuary.txt"))
-    assert get_header(song, "artist") == "Utada Hikaru"
+    song = parse_ultrastar(load("chart_crlf.txt"))
+    assert get_header(song, "artist") == "Test Artist"
     assert parse_bpm(get_header(song, "BPM")) == 217.98
     first = song.body[0]
     assert first == Note(kind=":", beat=0, length=3, pitch=16, text="ah")
@@ -19,16 +19,16 @@ def test_parse_headers_and_notes():
     assert any(n.kind == "F" for n in song.body if isinstance(n, Note))
 
 def test_note_text_keeps_leading_space():
-    song = parse_ultrastar(load("sanctuary.txt"))
+    song = parse_ultrastar(load("chart_crlf.txt"))
     notes = [n for n in song.body if isinstance(n, Note)]
     assert notes[1].text == " ah"
 
 def test_negative_pitch():
-    song = parse_ultrastar(load("sweet_child.txt"))
+    song = parse_ultrastar(load("chart_latin1.txt"))
     assert any(n.pitch == -9 for n in song.body if isinstance(n, Note))
 
 def test_round_trip():
-    for name in ("sweet_child.txt", "sanctuary.txt"):
+    for name in ("chart_latin1.txt", "chart_crlf.txt"):
         song = parse_ultrastar(load(name))
         again = parse_ultrastar(serialize_ultrastar(song))
         assert again == song