fix(subtitle_gen): stop millisecond rounding from overflowing timestamps

_ts_srt/_ts_vtt computed the seconds and millisecond fields independently:
`ms = int(round((seconds % 1) * 1000))`. When the fractional part is >= 0.9995
that rounds to 1000, emitting a malformed 4-digit `…,1000` value with no carry
into the seconds field (and, at 59.9999/3599.9999, no carry into minutes/hours).
For example 0.9999s became `00:00:00,1000` instead of `00:00:01,000`. ASR word
and segment end-times routinely land on such fractional boundaries, and the
resulting cue is rejected or mistimed by strict SRT/VTT parsers (ffmpeg
subtitles filter, VLC, browser WebVTT).

Decompose from a single rounded total-milliseconds value so the carry
propagates across all fields. Both formatters now share one `_hmsms` helper.
This commit is contained in:
0xDevNinja
2026-07-07 15:29:03 +05:30
parent de348f15e3
commit bcd8eb6e53
3 changed files with 68 additions and 11 deletions

View File

@@ -0,0 +1,49 @@
"""Regression tests: SRT/VTT timestamp formatting must not overflow milliseconds.
`_ts_srt` / `_ts_vtt` computed the seconds and millisecond fields independently:
`ms = int(round((seconds % 1) * 1000))`. When the fractional part is >= 0.9995,
that rounds to 1000, emitting a malformed 4-digit `…,1000` with no carry into
the seconds (and, at boundaries, minutes/hours) field — e.g. 0.9999s ->
`00:00:00,1000` instead of `00:00:01,000`. Such timestamps are rejected by
strict SRT/VTT parsers (ffmpeg subtitles filter, VLC, browser WebVTT).
"""
import re
import sys
from pathlib import Path
PROJECT_ROOT = Path(__file__).resolve().parent.parent.parent
sys.path.insert(0, str(PROJECT_ROOT))
from tools.subtitle.subtitle_gen import SubtitleGen # noqa: E402
_SRT_RE = re.compile(r"^\d{2}:\d{2}:\d{2},\d{3}$")
_VTT_RE = re.compile(r"^\d{2}:\d{2}:\d{2}\.\d{3}$")
def test_millisecond_carry_does_not_overflow():
# Every fractional part >= 0.9995 must carry into the next second, never
# emit a 4-digit millisecond field.
assert SubtitleGen._ts_srt(0.9999) == "00:00:01,000"
assert SubtitleGen._ts_vtt(0.9999) == "00:00:01.000"
assert SubtitleGen._ts_srt(1.9996) == "00:00:02,000"
def test_carry_propagates_across_minute_and_hour_boundaries():
assert SubtitleGen._ts_srt(59.9999) == "00:01:00,000"
assert SubtitleGen._ts_srt(3599.9999) == "01:00:00,000"
assert SubtitleGen._ts_srt(7261.9999) == "02:01:02,000"
def test_normal_values_unchanged():
assert SubtitleGen._ts_srt(0.0) == "00:00:00,000"
assert SubtitleGen._ts_srt(1.5) == "00:00:01,500"
assert SubtitleGen._ts_srt(0.4994) == "00:00:00,499"
assert SubtitleGen._ts_vtt(83.25) == "00:01:23.250"
def test_all_outputs_are_well_formed():
# Sweep values that land on and around the dangerous boundary.
for t in (0.0, 0.4995, 0.9995, 0.9999, 1.0, 59.9995, 3599.9999, 12345.9999):
assert _SRT_RE.match(SubtitleGen._ts_srt(t)), SubtitleGen._ts_srt(t)
assert _VTT_RE.match(SubtitleGen._ts_vtt(t)), SubtitleGen._ts_vtt(t)