7 Commits
Author SHA1 Message Date
kato b0487be39e feat: implement isolated model worker with auto-restart and hot-reload
Tests / Go and GTK tests (push) Successful in 1m38s
Release / Tests before release (push) Successful in 1m34s
Release / Build and publish release (push) Successful in 2m24s
Introduce a supervised child process for capture, VAD, and recognition,
enabling automatic restart on crash/hang and hot-reload via SIGHUP.
Add `--model-auto-restart`, `--model-timeout`, and
`--model-shutdown-timeout` options. Refactor `Run()` with lifecycle
hooks for proper process group cleanup. Update README with new
behavior and CLI flags.
2026-07-17 01:47:37 +03:00
kato b3ed538820 ci(release): add patchelf to CI workflows and update release documentation
Tests / Go and GTK tests (push) Canceled after 40s
Release / Tests before release (push) Successful in 1m44s
Release / Build and publish release (push) Successful in 3m2s
- Install patchelf in both build and release jobs to support runtime library relocation.
- Update release notes to describe the private desktop runtime archive.
- Clarify in README that development builds require GTK4 dev libraries, while release archives are self-contained with lib/ directory.
- Adjust troubleshooting and release procedure to reflect new offline runtime packaging.
2026-07-16 22:09:38 +03:00
kato 76bc3d8185 ci: add nodejs24 and nodejs24-bin to CI dependencies
Tests / Go and GTK tests (push) Successful in 1m38s
Release / Tests before release (push) Successful in 2m5s
Release / Build and publish release (push) Successful in 3m23s
2026-07-16 20:48:42 +03:00
kato 449626bffa docs: add CI/release documentation and ignore dist directory
Tests / Go and GTK tests (push) Failing after 1m8s
Add `/dist/` to `.gitignore` to exclude locally built distribution
artifacts. Document the Gitea Actions workflow, release tagging, and
branch protection setup in the README.
2026-07-16 19:40:21 +03:00
kato 13ddebbf98 feat(overlay): improve provisional text display and line splitting 2026-07-16 19:27:39 +03:00
kato 2f5ca41ac3 feat: add --overlay-font-family option for caption font customization
Allow users to specify a custom font family for the overlay captions via
a new --overlay-font-family flag, defaulting to "Sans". Validation
ensures the font family is not empty. Updated README, config, and tests.
2026-07-16 18:09:09 +03:00
kato 192666dd43 fix(overlay): enforce text wrap width to prevent overflow beyond screen
Add `gtk_label_set_width_chars` to set a concrete width for label allocation,
ensuring long sentences wrap within the configured max-chars bubble width
instead of extending off-screen.
2026-07-16 18:06:00 +03:00
20 changed files with 1432 additions and 63 deletions
+115
View File
@@ -0,0 +1,115 @@
name: Release
on:
push:
tags:
- 'v*'
permissions:
code: read
jobs:
test:
name: Tests before release
runs-on: ubuntu-latest
container: registry.fedoraproject.org/fedora:44
steps:
- name: Validate release tag
shell: bash
run: |
set -Eeuo pipefail
[[ "${GITHUB_REF_NAME}" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]] || {
printf 'Tag must match vMAJOR.MINOR.BUG; got %s\n' "${GITHUB_REF_NAME}" >&2
exit 1
}
- name: Install system dependencies
run: >-
dnf install -y
bzip2 curl gcc gcc-c++ git gtk4-devel gtk4-layer-shell-devel
jq libX11-devel libXfixes-devel nodejs24 nodejs24-bin patchelf pkgconf-pkg-config
pulseaudio-utils ShellCheck tar gzip binutils
- name: Check out repository
uses: https://github.com/actions/checkout@v4
- name: Install the Go version from go.mod
shell: bash
run: |
set -Eeuo pipefail
go_version="$(awk '$1 == "go" { print $2 }' go.mod)"
curl --fail --location --silent --show-error \
"https://go.dev/dl/go${go_version}.linux-amd64.tar.gz" \
--output /tmp/go.tar.gz
rm -rf /usr/local/go
tar -C /usr/local -xzf /tmp/go.tar.gz
ln -sf /usr/local/go/bin/go /usr/local/bin/go
ln -sf /usr/local/go/bin/gofmt /usr/local/bin/gofmt
go version
- name: Run tests and static checks
run: ./scripts/ci/test.sh
publish:
name: Build and publish release
needs: test
permissions:
code: read
releases: write
runs-on: ubuntu-latest
container: registry.fedoraproject.org/fedora:44
steps:
- name: Install system dependencies
run: >-
dnf install -y
bzip2 curl gcc gcc-c++ git gtk4-devel gtk4-layer-shell-devel
jq libX11-devel libXfixes-devel nodejs24 nodejs24-bin patchelf pkgconf-pkg-config
pulseaudio-utils ShellCheck tar gzip binutils
- name: Check out repository and tags
uses: https://github.com/actions/checkout@v4
with:
fetch-depth: 0
- name: Install the Go version from go.mod
shell: bash
run: |
set -Eeuo pipefail
go_version="$(awk '$1 == "go" { print $2 }' go.mod)"
curl --fail --location --silent --show-error \
"https://go.dev/dl/go${go_version}.linux-amd64.tar.gz" \
--output /tmp/go.tar.gz
rm -rf /usr/local/go
tar -C /usr/local -xzf /tmp/go.tar.gz
ln -sf /usr/local/go/bin/go /usr/local/bin/go
ln -sf /usr/local/go/bin/gofmt /usr/local/bin/gofmt
go version
- name: Build portable release archive
run: ./scripts/ci/package-release.sh "${GITHUB_REF_NAME}"
- name: Generate release notes
shell: bash
run: |
set -Eeuo pipefail
previous_tag="$(git describe --tags --abbrev=0 "${GITHUB_REF_NAME}^" --match 'v[0-9]*' 2>/dev/null || true)"
{
printf 'Automated Captioneer release for `%s`.\n\n' "${GITHUB_REF_NAME}"
printf 'The Linux x86_64 archive contains both Captioneer commands and a private desktop runtime with GTK4, GTK4 Layer Shell, and Sherpa/ONNX libraries. Models are downloaded separately with `scripts/download-models.sh`.\n'
if [[ -n "$previous_tag" ]]; then
printf '\nChanges since `%s`:\n\n' "$previous_tag"
git log --no-merges --pretty='- %s (`%h`)' "${previous_tag}..${GITHUB_REF_NAME}"
fi
} > dist/release-notes.md
- name: Publish Gitea release
env:
GITEA_API_URL: ${{ gitea.api_url }}
GITEA_REPOSITORY: ${{ gitea.repository }}
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
RELEASE_TAG: ${{ gitea.ref_name }}
RELEASE_NOTES: dist/release-notes.md
run: >-
./scripts/ci/publish-release.sh
"dist/captioneer-${GITHUB_REF_NAME}-linux-amd64.tar.gz"
"dist/captioneer-${GITHUB_REF_NAME}-linux-amd64.tar.gz.sha256"
+43
View File
@@ -0,0 +1,43 @@
name: Tests
on:
pull_request:
push:
branches:
- '**'
permissions:
code: read
jobs:
test:
name: Go and GTK tests
runs-on: ubuntu-latest
container: registry.fedoraproject.org/fedora:44
steps:
- name: Install system dependencies
run: >-
dnf install -y
bzip2 curl gcc gcc-c++ git gtk4-devel gtk4-layer-shell-devel
jq libX11-devel libXfixes-devel nodejs24 nodejs24-bin pkgconf-pkg-config
pulseaudio-utils ShellCheck tar gzip binutils
- name: Check out repository
uses: https://github.com/actions/checkout@v4
- name: Install the Go version from go.mod
shell: bash
run: |
set -Eeuo pipefail
go_version="$(awk '$1 == "go" { print $2 }' go.mod)"
curl --fail --location --silent --show-error \
"https://go.dev/dl/go${go_version}.linux-amd64.tar.gz" \
--output /tmp/go.tar.gz
rm -rf /usr/local/go
tar -C /usr/local -xzf /tmp/go.tar.gz
ln -sf /usr/local/go/bin/go /usr/local/bin/go
ln -sf /usr/local/go/bin/gofmt /usr/local/bin/gofmt
go version
- name: Run tests and static checks
run: ./scripts/ci/test.sh
+1
View File
@@ -5,3 +5,4 @@ models/silero_vad_v5.onnx
# Locally built executable.
/captioneer
/build/
/dist/
+37 -7
View File
@@ -11,7 +11,7 @@ Captioneer provides two commands:
## Setup
The terminal command requires Linux x86_64, Go 1.26.2 or newer, `pactl`, and `parec`. The desktop command additionally needs GTK4 and GTK4 Layer Shell development/runtime libraries. PipeWire works through its PulseAudio compatibility layer.
The terminal command requires Linux x86_64, Go 1.26.2 or newer, `pactl`, and `parec`. Building the desktop command from source additionally needs GTK4 and GTK4 Layer Shell development libraries. Published release archives carry the desktop runtime libraries. PipeWire works through its PulseAudio compatibility layer.
Download the large recognition models once:
@@ -50,6 +50,14 @@ Final captions use stdout; diagnostics and overload warnings use stderr. This ma
Press <kbd>Ctrl</kbd>+<kbd>C</kbd> to stop. Captioneer stops `parec` and flushes pending audio before exiting.
Sherpa recognition, Silero VAD, and audio capture run in an isolated worker process. The terminal or GTK process stays responsive if native inference crashes or hangs: Captioneer restarts the worker automatically after a failure, and Ctrl+C force-kills only that worker if it cannot flush within the configured shutdown timeout. Send `SIGHUP` to the parent Captioneer PID to hot-reload the models without closing the terminal or overlay:
```bash
kill -HUP <captioneer-parent-pid>
```
An automatic or manual restart begins a fresh capture/transcription session; audio being processed by the failed worker cannot be recovered.
## Desktop overlay
The simplest Bazzite development command is:
@@ -64,7 +72,9 @@ Use `--output=both` to keep terminal output as well:
./scripts/distrobox/run.sh --mode=vad --output=both
```
In VAD mode, a 500 ms pause finalizes the current caption and starts the next line. The overlay keeps up to six completed lines above the active provisional caption; each completed line remains visible for at least three seconds and gradually fades from white to a restrained gray as it ages. If a seventh line arrives sooner, the hard six-line cap removes the oldest. Text is left-aligned inside the centered, fixed-width dark bubble. Pointer input passes through the window by default. Empty completed captions hide the overlay.
In VAD mode, a 500 ms pause finalizes the current speech segment. Captioneer splits that transcript again at sentence punctuation and at word-safe boundaries of at most 64 characters, so continuous speech does not become one enormous paragraph. The live provisional view keeps the latest three digestible chunks and grows vertically without ellipsizing them. Completed chunks remain visible for at least three seconds, receive extra time based on their word count, and gradually fade from white to a restrained gray as they age. When several chunks finalize together, their removal is staggered in reading order instead of deleting the whole block at once. Up to six completed chunks remain above the provisional text; if a seventh arrives, the oldest is removed. Blank recognition results never erase completed text before its reading lifetime expires.
Text is left-aligned inside the centered, fixed-width dark bubble and wraps at its configured width instead of extending off-screen. Pointer input passes through the window by default.
To build outside the helper script, install GTK4 and GTK4 Layer Shell development packages, then run:
@@ -96,6 +106,9 @@ Layer Shell and X11 hints are requests, not universal guarantees. Same-layer win
| `--models-dir=models` | `models` | Directory containing `parakeet-tdt-v2/` and `silero_vad_v5.onnx`. |
| `--threads=2` | `2` | CPU threads used by recognition and VAD. |
| `--preview-threshold-dbfs=-45` | `-45` | RMS threshold that starts a provisional VAD caption. Raise it to reject background audio; lower it for quiet speech. |
| `--model-auto-restart=true` | `true` | Restart the isolated model worker after a crash, capture failure, or timeout. Set `false` to report the failure and exit instead. |
| `--model-timeout=30s` | `30s` | Maximum model startup, continuously busy processing time, or missing-heartbeat period before the worker is considered hung. `0s` disables hang detection. |
| `--model-shutdown-timeout=2s` | `2s` | Time allowed for pending-audio flush and model cleanup after Ctrl+C or reload before the worker is force-killed. |
### Desktop-only options
@@ -105,6 +118,7 @@ Layer Shell and X11 hints are requests, not universal guarantees. Same-layer win
| `--overlay-backend=auto|wayland|x11` | `auto` | Let GTK detect the backend, or require one explicitly. |
| `--overlay-opacity=0.90` | `0.90` | Dark bubble opacity from `0` to `1`. |
| `--overlay-font-size=28` | `28` | Font size in logical pixels. |
| `--overlay-font-family=Sans` | `Sans` | GTK/Pango font family for final and provisional captions. |
| `--overlay-bottom-margin=100` | `100` | Bottom margin in logical pixels. |
| `--overlay-max-width=1200` | `1200` | Fixed caption-bubble width; it is capped at 80% of the selected monitor. |
| `--overlay-monitor=auto` | `auto` | `auto`, a zero-based monitor index, or a connector name such as `DP-1`. |
@@ -114,9 +128,9 @@ Layer Shell and X11 hints are requests, not universal guarantees. Same-layer win
Examples:
```bash
# Larger text, longer final-caption visibility
# Larger text, a custom font, and longer final-caption visibility
./scripts/distrobox/run.sh --mode=vad --output=overlay \
--overlay-font-size=34 --overlay-final-timeout=6s
--overlay-font-size=34 --overlay-font-family="Noto Sans" --overlay-final-timeout=6s
# Explicit XWayland/X11 route on the cursor's monitor
./scripts/distrobox/run.sh --mode=vad --output=both --overlay-backend=x11
@@ -162,11 +176,12 @@ Captioneer itself has no environment-based application configuration; use the co
- **Processing overload warning:** inference fell behind and the oldest 100 ms packet was dropped. Try more `--threads` or a longer `--chunk-duration`.
- **Overlay is not always above other windows:** read the backend warning. On Wayland this usually means the compositor lacks Layer Shell; add a compositor rule for the `Captioneer Overlay` window if supported.
- **Overlay initialization fails:** `--output=overlay` exits with the error. `--output=both` warns and continues terminal-only.
- **Desktop binary misses shared libraries on Bazzite:** use `scripts/distrobox/run.sh`; container-built GTK binaries are not self-contained.
- **A locally built desktop binary misses shared libraries:** use `scripts/distrobox/run.sh` or install the matching GTK4 and GTK4 Layer Shell runtime packages. The desktop command in a published release carries these application libraries in its private `lib/` directory; keep the extracted directory together.
- **The model worker repeatedly restarts:** inspect the warning on stderr. Slow machines may need a larger `--model-timeout`; use `--model-auto-restart=false` when diagnosing a persistent crash so Captioneer exits on the first failure.
## Development
The transcription pipeline emits presentation-neutral events. `output/terminal` and `output/overlay` consume those events independently; GTK stays on its main OS thread while capture and recognition run on a worker.
The transcription pipeline emits presentation-neutral events. `output/terminal` and `output/overlay` consume those events independently; GTK stays on its main OS thread while capture, VAD, and recognition run in a supervised child process. Caption events and health messages cross a private pipe, and the child is placed in its own process group so its `parec` process can be stopped or replaced with it.
```text
src/app/ capture/model/process lifecycle
@@ -198,8 +213,23 @@ distrobox enter --no-workdir captioneer-dev -- bash -lc '
Run this from the repository root. The build and run helpers resolve that path automatically.
## Gitea Actions and releases
The `Tests` workflow runs the normal and GTK-tagged Go tests, `go vet`, and ShellCheck for every pull request and branch push. To make it mandatory for pull requests, open the repository's **Settings → Branches**, edit the protection rule for `master`, enable required status checks, and select **Tests / Go and GTK tests** after its first run. Workflow files can report the check, but the branch-protection rule is what prevents merging when it fails.
Pushing a tag that exactly follows `vMAJOR.MINOR.BUG` runs the same test suite first, then builds and publishes a Gitea release:
```bash
git tag v1.3.519
git push origin v1.3.519
```
The release contains a checksummed Linux x86_64 archive with `captioneer`, `captioneer-desktop`, and a private runtime containing GTK4, GTK4 Layer Shell, Sherpa/ONNX, and their linked non-glibc dependencies. Extract the whole archive and run `./captioneer-desktop`; do not move the executable away from its adjacent `lib/` directory. Models, `pactl`, `parec`, host fonts, the display server, graphics drivers, and glibc remain host-provided.
The release workflow uses Gitea's built-in `GITEA_TOKEN`; no personal token is required. In **Settings → Actions → General**, allow the workflow token `Read` access to code and `Write` access to releases. Gitea clamps workflow permissions to those repository settings, so a more restrictive maximum produces an actionable HTTP 403 during publishing.
## License
Captioneer is licensed under the [Apache License 2.0](LICENSE). Sherpa-Onnx is Apache-2.0 licensed, GTK4 is LGPL-2.1-or-later, and GTK4 Layer Shell is MIT licensed. Captioneer links to the system GTK libraries rather than copying their source into the project.
Captioneer is licensed under the [Apache License 2.0](LICENSE). Sherpa-Onnx is Apache-2.0 licensed, GTK4 is LGPL-2.1-or-later, and GTK4 Layer Shell is MIT licensed. Release archives dynamically link and redistribute the required shared libraries; `RUNTIME-LIBRARIES.tsv` records their source packages and `third-party-licenses/` contains the installed license notices supplied by those packages. Local source builds continue to link against the system libraries.
Version 1 intentionally has no animation, persisted caption history, runtime dragging, background-free mode, capture exclusion, Flatpak, desktop entry, or autostart integration.
+218
View File
@@ -0,0 +1,218 @@
#!/usr/bin/env bash
set -Eeuo pipefail
repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
cd -- "$repo_root"
for command in go ldd patchelf readelf rpm; do
command -v "$command" >/dev/null 2>&1 || {
printf 'captioneer: %s is required to build a release archive\n' "$command" >&2
exit 1
}
done
tag=${1:-}
if [[ ! "$tag" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
printf 'captioneer: release tag must match vMAJOR.MINOR.BUG, got %q\n' "$tag" >&2
exit 1
fi
platform=linux-amd64
archive_name="captioneer-${tag}-${platform}.tar.gz"
package_name="captioneer-${tag}-${platform}"
package_dir="dist/$package_name"
rm -rf -- "$package_dir"
rm -f -- "dist/$archive_name" "dist/$archive_name.sha256"
mkdir -p -- \
"$package_dir/lib" \
"$package_dir/scripts" \
"$package_dir/third-party-licenses"
# The Sherpa Go module embeds an absolute build-machine RPATH. Add a portable
# build-time fallback; the final paths are normalized after dependency copying.
# shellcheck disable=SC2016 # $ORIGIN must remain literal for the ELF loader.
CGO_LDFLAGS='-Wl,-rpath,$ORIGIN/lib' \
go build -trimpath -o "$package_dir/captioneer" ./src/cmd/captioneer
# shellcheck disable=SC2016 # $ORIGIN must remain literal for the ELF loader.
CGO_LDFLAGS='-Wl,-rpath,$ORIGIN/lib' \
go build -trimpath -tags gtk \
-o "$package_dir/captioneer-desktop" ./src/cmd/captioneer-desktop
sherpa_dir="$(go list -m -f '{{.Dir}}' github.com/k2-fsa/sherpa-onnx-go-linux)"
sherpa_lib_dir="$sherpa_dir/lib/x86_64-unknown-linux-gnu"
declare -A bundled_libraries=()
declare -A copied_license_packages=()
manifest_entries="$(mktemp)"
trap 'rm -f -- "$manifest_entries"' EXIT
is_host_runtime_library() {
case "$1" in
ld-linux*.so* | libc.so.* | libm.so.* | libmvec.so.* | libdl.so.* | \
libpthread.so.* | librt.so.* | libresolv.so.* | libanl.so.* | \
libutil.so.* | libnss_*.so.* | libthread_db.so.* | libBrokenLocale.so.*)
return 0
;;
esac
return 1
}
copy_package_licenses() {
local package=$1
local license_path relative_path destination
[[ -z "${copied_license_packages[$package]:-}" ]] || return 0
copied_license_packages["$package"]=1
while IFS= read -r license_path; do
[[ -f "$license_path" && "$license_path" == /usr/share/licenses/* ]] || continue
relative_path="${license_path#/usr/share/licenses/}"
destination="$package_dir/third-party-licenses/$relative_path"
mkdir -p -- "$(dirname -- "$destination")"
cp -L -- "$license_path" "$destination"
done < <(rpm -ql "$package" 2>/dev/null || true)
}
bundle_library() {
local source=$1
local provider=${2:-}
local library_name resolved_source destination package
library_name="$(basename -- "$source")"
is_host_runtime_library "$library_name" && return
resolved_source="$(readlink -f -- "$source")"
[[ -f "$resolved_source" ]] || {
printf 'captioneer: runtime library not found: %s\n' "$source" >&2
exit 1
}
if [[ -n "${bundled_libraries[$library_name]:-}" ]]; then
if ! cmp -s -- "$resolved_source" "${bundled_libraries[$library_name]}"; then
printf 'captioneer: conflicting runtime libraries named %s\n' "$library_name" >&2
exit 1
fi
return
fi
destination="$package_dir/lib/$library_name"
cp -L -- "$resolved_source" "$destination"
bundled_libraries["$library_name"]="$resolved_source"
if [[ -z "$provider" ]] && command -v rpm >/dev/null 2>&1; then
package="$(rpm -qf --queryformat '%{NAME}\n' "$resolved_source" 2>/dev/null | head -n 1 || true)"
if [[ -n "$package" ]]; then
provider="$(rpm -q --queryformat '%{NAME}-%{VERSION}-%{RELEASE}.%{ARCH}' "$package")"
copy_package_licenses "$package"
fi
fi
provider=${provider:-unidentified-system-package}
printf '%s\t%s\n' "$library_name" "$provider" >> "$manifest_entries"
}
bundle_library "$sherpa_lib_dir/libsherpa-onnx-c-api.so" \
'github.com/k2-fsa/sherpa-onnx-go-linux'
bundle_library "$sherpa_lib_dir/libonnxruntime.so" \
'github.com/k2-fsa/sherpa-onnx-go-linux'
# ldd reports the complete linked dependency closure. Copy everything needed by
# either command except glibc and its loader, which must match the host system.
for executable in \
"$package_dir/captioneer" \
"$package_dir/captioneer-desktop"; do
ldd_output="$(ldd "$executable")"
if grep -Fq 'not found' <<< "$ldd_output"; then
printf 'captioneer: unresolved release dependencies for %s:\n%s\n' \
"$executable" "$ldd_output" >&2
exit 1
fi
while IFS= read -r library_path; do
[[ -n "$library_path" ]] || continue
if [[ "$library_path" == "$repo_root/$package_dir/lib/"* ]]; then
continue
fi
bundle_library "$library_path"
done < <(
awk '
$2 == "=>" && $3 ~ /^\// { print $3 }
$1 ~ /^\// { print $1 }
' <<< "$ldd_output"
)
done
{
printf 'Library\tProvider\n'
sort -u -- "$manifest_entries"
} > "$package_dir/RUNTIME-LIBRARIES.tsv"
# Give every object a location-relative path. Patching each library is required
# because an upstream RUNPATH (for example, Tinysparql's Fedora path) otherwise
# prevents the executable's path from resolving that library's own children.
# This avoids LD_LIBRARY_PATH, which would leak into spawned pactl/parec tools.
for library in "$package_dir"/lib/*; do
chmod u+w -- "$library"
# shellcheck disable=SC2016 # $ORIGIN must remain literal for the ELF loader.
patchelf --set-rpath '$ORIGIN' "$library"
chmod 0755 -- "$library"
done
for executable in captioneer captioneer-desktop; do
# shellcheck disable=SC2016 # $ORIGIN must remain literal for the ELF loader.
patchelf --set-rpath '$ORIGIN/lib' "$package_dir/$executable"
done
cp -- README.md LICENSE "$package_dir/"
cp -- scripts/download-models.sh "$package_dir/scripts/"
for executable in captioneer captioneer-desktop; do
dynamic_section="$(readelf -d "$package_dir/$executable")"
# shellcheck disable=SC2016 # Verify the literal ELF-loader token.
if [[ "$dynamic_section" != *'$ORIGIN/lib'* ]]; then
printf 'captioneer: %s is missing its private-runtime RUNPATH\n' \
"$executable" >&2
exit 1
fi
done
[[ -f "$package_dir/lib/libgtk4-layer-shell.so.0" ]] || {
printf 'captioneer: GTK4 Layer Shell was not included in the release runtime\n' >&2
exit 1
}
for library in "$package_dir"/lib/*; do
# shellcheck disable=SC2016 # Verify the literal ELF-loader token.
[[ "$(patchelf --print-rpath "$library")" == '$ORIGIN' ]] || {
printf 'captioneer: %s is missing its private dependency RUNPATH\n' \
"$(basename -- "$library")" >&2
exit 1
}
done
# Verify the archive itself contains every linked non-glibc dependency instead
# of allowing the build container's installed libraries to mask an omission.
for object in \
"$package_dir/captioneer" \
"$package_dir/captioneer-desktop" \
"$package_dir"/lib/*; do
while IFS= read -r needed_library; do
is_host_runtime_library "$needed_library" && continue
[[ -f "$package_dir/lib/$needed_library" ]] || {
printf 'captioneer: %s requires unbundled library %s\n' \
"$(basename -- "$object")" "$needed_library" >&2
exit 1
}
done < <(patchelf --print-needed "$object")
done
# --help exits before display/model initialization while still exercising the
# dynamic loader through the same executable release users invoke.
"$package_dir/captioneer-desktop" --help >/dev/null 2>&1
tar -C dist -czf "dist/$archive_name" "$package_name"
(
cd -- dist
sha256sum "$archive_name" > "$archive_name.sha256"
)
printf '%s\n' "$repo_root/dist/$archive_name"
printf '%s\n' "$repo_root/dist/$archive_name.sha256"
+80
View File
@@ -0,0 +1,80 @@
#!/usr/bin/env bash
set -Eeuo pipefail
: "${GITEA_API_URL:?GITEA_API_URL is required}"
: "${GITEA_REPOSITORY:?GITEA_REPOSITORY is required}"
: "${GITEA_TOKEN:?GITEA_TOKEN is required}"
: "${RELEASE_TAG:?RELEASE_TAG is required}"
: "${RELEASE_NOTES:?RELEASE_NOTES is required}"
if [[ ! "$RELEASE_TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
printf 'captioneer: release tag must match vMAJOR.MINOR.BUG, got %q\n' "$RELEASE_TAG" >&2
exit 1
fi
if (( $# == 0 )); then
printf 'captioneer: at least one release asset is required\n' >&2
exit 1
fi
for asset in "$@"; do
[[ -f "$asset" ]] || { printf 'captioneer: release asset not found: %s\n' "$asset" >&2; exit 1; }
done
api_base="${GITEA_API_URL%/}/repos/$GITEA_REPOSITORY"
authorization="Authorization: token $GITEA_TOKEN"
release_response="$(mktemp)"
trap 'rm -f -- "$release_response"' EXIT
status="$(curl --silent --show-error --output "$release_response" --write-out '%{http_code}' \
--header "$authorization" \
"$api_base/releases/tags/$RELEASE_TAG")"
release_payload="$(jq -n \
--arg tag "$RELEASE_TAG" \
--arg name "Captioneer $RELEASE_TAG" \
--rawfile body "$RELEASE_NOTES" \
'{tag_name: $tag, name: $name, body: $body, draft: false, prerelease: false}')"
case "$status" in
200)
release_id="$(jq -er '.id' "$release_response")"
curl --fail-with-body --silent --show-error \
--request PATCH \
--header "$authorization" \
--header 'Content-Type: application/json' \
--data "$release_payload" \
"$api_base/releases/$release_id" > "$release_response"
;;
404)
curl --fail-with-body --silent --show-error \
--request POST \
--header "$authorization" \
--header 'Content-Type: application/json' \
--data "$release_payload" \
"$api_base/releases" > "$release_response"
release_id="$(jq -er '.id' "$release_response")"
;;
*)
printf 'captioneer: Gitea release lookup failed with HTTP %s\n' "$status" >&2
cat "$release_response" >&2
exit 1
;;
esac
for asset in "$@"; do
asset_name="$(basename -- "$asset")"
while IFS= read -r attachment_id; do
[[ -n "$attachment_id" ]] || continue
curl --fail-with-body --silent --show-error \
--request DELETE \
--header "$authorization" \
"$api_base/releases/$release_id/assets/$attachment_id" >/dev/null
done < <(jq -r --arg name "$asset_name" '.assets[]? | select(.name == $name) | .id' "$release_response")
curl --fail-with-body --silent --show-error \
--request POST \
--header "$authorization" \
--form "attachment=@$asset" \
"$api_base/releases/$release_id/assets?name=$asset_name" >/dev/null
printf 'Uploaded %s\n' "$asset_name"
done
+19
View File
@@ -0,0 +1,19 @@
#!/usr/bin/env bash
set -Eeuo pipefail
repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd -P)"
cd -- "$repo_root"
go test ./...
go test -tags gtk ./...
go vet ./...
go vet -tags gtk ./...
shellcheck \
scripts/download-models.sh \
scripts/distrobox/common.sh \
scripts/distrobox/build.sh \
scripts/distrobox/run.sh \
scripts/ci/test.sh \
scripts/ci/package-release.sh \
scripts/ci/publish-release.sh
+36 -6
View File
@@ -14,15 +14,28 @@ import (
"tea.chunkbyte.com/kato/captioneer/src/output"
)
func Run(ctx context.Context, settings config.Settings, sink output.Sink, diagnostics io.Writer) error {
if err := capture.ValidatePrograms(); err != nil {
type directHooks struct {
ready func() error
busy func() error
idle func() error
}
func runDirect(ctx context.Context, settings config.Settings, sink output.Sink, diagnostics io.Writer, hooks directHooks) error {
if err := hooks.busy(); err != nil {
return err
}
resources, err := models.New(settings)
if idleErr := hooks.idle(); err == nil {
err = idleErr
}
if err != nil {
return err
}
defer resources.Close()
defer func() {
_ = hooks.busy()
resources.Close()
_ = hooks.idle()
}()
ctx, cancel := context.WithCancel(ctx)
defer cancel()
@@ -32,24 +45,41 @@ func Run(ctx context.Context, settings config.Settings, sink output.Sink, diagno
return fmt.Errorf("find default output monitor: %w", err)
}
fmt.Fprintf(diagnostics, "Capturing from: %s\n", monitorSource)
fmt.Fprintln(diagnostics, "Press Ctrl+C to stop.")
packets, waitCapture, err := capture.Packets(ctx, monitorSource)
if err != nil {
return fmt.Errorf("start system-audio capture: %w", err)
}
if err := hooks.ready(); err != nil {
cancel()
_ = waitCapture()
return err
}
processor := captions.New(settings, resources, sink.Publish)
var processErr error
for packet := range packets {
if err := processor.Accept(packet); err != nil {
if err := hooks.busy(); err != nil {
processErr = err
cancel()
break
}
acceptErr := processor.Accept(packet)
idleErr := hooks.idle()
if acceptErr != nil || idleErr != nil {
err := errors.Join(acceptErr, idleErr)
processErr = fmt.Errorf("publish caption: %w", err)
cancel()
break
}
}
if processErr == nil {
processErr = processor.Flush()
if err := hooks.busy(); err != nil {
processErr = err
} else {
processErr = processor.Flush()
processErr = errors.Join(processErr, hooks.idle())
}
}
captureErr := waitCapture()
if captureErr != nil && ctx.Err() == nil {
+361
View File
@@ -0,0 +1,361 @@
package app
import (
"context"
"encoding/json"
"errors"
"fmt"
"io"
"os"
"os/exec"
"os/signal"
"strings"
"syscall"
"time"
"tea.chunkbyte.com/kato/captioneer/src/capture"
"tea.chunkbyte.com/kato/captioneer/src/config"
"tea.chunkbyte.com/kato/captioneer/src/models"
"tea.chunkbyte.com/kato/captioneer/src/output"
)
const modelRestartDelay = time.Second
type attemptResult uint8
const (
attemptStopped attemptResult = iota + 1
attemptReload
attemptFailed
attemptFatal
)
type workerHealth struct {
startedAt time.Time
lastSeen time.Time
ready bool
busySince time.Time
}
func (h *workerHealth) observe(messageType string, now time.Time) {
h.lastSeen = now
switch messageType {
case messageReady:
h.ready = true
h.busySince = time.Time{}
case messageBusy:
if h.busySince.IsZero() {
h.busySince = now
}
case messageIdle:
h.busySince = time.Time{}
}
}
func (h workerHealth) timeoutError(now time.Time, timeout time.Duration) error {
if timeout == 0 {
return nil
}
if !h.ready && now.Sub(h.startedAt) >= timeout {
return fmt.Errorf("model worker did not become ready within %s", timeout)
}
if !h.busySince.IsZero() && now.Sub(h.busySince) >= timeout {
return fmt.Errorf("model operation exceeded %s", timeout)
}
if h.ready && now.Sub(h.lastSeen) >= timeout {
return fmt.Errorf("model worker heartbeat was silent for %s", timeout)
}
return nil
}
// Run supervises an isolated process containing capture, VAD, and recognition.
// Presentation stays in this process, so the native model can be replaced
// without restarting the terminal or GTK main loop.
func Run(ctx context.Context, settings config.Settings, sink output.Sink, diagnostics io.Writer) error {
if err := capture.ValidatePrograms(); err != nil {
return err
}
if err := models.Validate(settings); err != nil {
return err
}
fmt.Fprintln(diagnostics, "Press Ctrl+C to stop. Send SIGHUP to hot-reload the model worker.")
reload := make(chan os.Signal, 1)
signal.Notify(reload, syscall.SIGHUP)
defer signal.Stop(reload)
for {
result, err := runWorkerAttempt(ctx, settings, sink, diagnostics, reload)
if ctx.Err() != nil {
return nil
}
switch result {
case attemptStopped:
return nil
case attemptFatal:
return err
case attemptReload:
fmt.Fprintln(diagnostics, "Reloading model worker.")
continue
case attemptFailed:
if !settings.ModelAutoRestart {
return err
}
fmt.Fprintf(diagnostics, "warning: %v; restarting model worker in %s\n", err, modelRestartDelay)
}
timer := time.NewTimer(modelRestartDelay)
select {
case <-ctx.Done():
if !timer.Stop() {
<-timer.C
}
return nil
case <-reload:
if !timer.Stop() {
<-timer.C
}
fmt.Fprintln(diagnostics, "Reloading model worker.")
case <-timer.C:
}
}
}
func runWorkerAttempt(
ctx context.Context,
settings config.Settings,
sink output.Sink,
diagnostics io.Writer,
reload <-chan os.Signal,
) (attemptResult, error) {
cmd, protocol, err := startModelWorker(settings, diagnostics)
if err != nil {
return attemptFailed, fmt.Errorf("start model worker: %w", err)
}
defer protocol.Close()
messages := make(chan workerMessage)
protocolDone := make(chan error, 1)
go readWorkerMessages(protocol, messages, protocolDone)
wait := make(chan error, 1)
go func() { wait <- cmd.Wait() }()
checkInterval := 250 * time.Millisecond
if settings.ModelTimeout > 0 && settings.ModelTimeout < checkInterval {
checkInterval = settings.ModelTimeout / 2
if checkInterval <= 0 {
checkInterval = time.Millisecond
}
}
ticker := time.NewTicker(checkInterval)
defer ticker.Stop()
startedAt := time.Now()
health := workerHealth{startedAt: startedAt, lastSeen: startedAt}
messageChannel := (<-chan workerMessage)(messages)
waitChannel := (<-chan error)(wait)
contextDone := ctx.Done()
var stopTimer *time.Timer
var stopDeadline <-chan time.Time
var stopping bool
var desiredResult attemptResult
var desiredErr error
var processDone bool
var processErr error
var protocolClosed bool
var protocolErr error
var workerFailure string
beginStop := func(result attemptResult, stopErr error) {
if stopping {
if result == attemptFatal {
desiredResult = result
desiredErr = errors.Join(desiredErr, stopErr)
}
return
}
stopping = true
desiredResult = result
desiredErr = stopErr
if err := signalWorkerGroup(cmd, syscall.SIGTERM); err != nil {
desiredErr = errors.Join(desiredErr, err)
}
stopTimer = time.NewTimer(settings.ModelShutdownTimeout)
stopDeadline = stopTimer.C
}
for {
if processDone && protocolClosed {
if stopTimer != nil && !stopTimer.Stop() {
select {
case <-stopTimer.C:
default:
}
}
if stopping {
return desiredResult, desiredErr
}
// The worker may have crashed before its parec child. A process group
// remains signalable after its leader exits, so clean up any survivors
// before starting a replacement worker.
cleanupErr := signalWorkerGroup(cmd, syscall.SIGKILL)
if protocolErr != nil {
return attemptFailed, errors.Join(fmt.Errorf("model worker protocol: %w", protocolErr), cleanupErr)
}
if workerFailure != "" {
return attemptFailed, errors.Join(errors.New(workerFailure), cleanupErr)
}
if processErr != nil {
return attemptFailed, errors.Join(fmt.Errorf("model worker exited: %w", processErr), cleanupErr)
}
return attemptFailed, errors.Join(errors.New("model worker exited unexpectedly"), cleanupErr)
}
select {
case <-contextDone:
contextDone = nil
beginStop(attemptStopped, nil)
case <-reload:
beginStop(attemptReload, nil)
case message, ok := <-messageChannel:
if !ok {
messageChannel = nil
protocolClosed = true
protocolErr = <-protocolDone
if !processDone && !stopping {
beginStop(attemptFailed, errors.New("model worker protocol closed unexpectedly"))
}
continue
}
now := time.Now()
health.observe(message.Type, now)
switch message.Type {
case messageReady:
fmt.Fprintln(diagnostics, "Model worker ready.")
case messageBusy, messageIdle:
case messageHeartbeat:
case messageCaption:
if message.Event == nil {
beginStop(attemptFailed, errors.New("model worker sent an empty caption event"))
continue
}
if err := sink.Publish(*message.Event); err != nil {
beginStop(attemptFatal, fmt.Errorf("publish caption: %w", err))
}
case messageFailure:
workerFailure = message.Error
default:
beginStop(attemptFailed, fmt.Errorf("unknown model worker message %q", message.Type))
}
case err := <-waitChannel:
waitChannel = nil
processDone = true
processErr = err
case now := <-ticker.C:
if !stopping {
if err := health.timeoutError(now, settings.ModelTimeout); err != nil {
beginStop(attemptFailed, err)
}
}
case <-stopDeadline:
stopDeadline = nil
if !processDone {
fmt.Fprintf(diagnostics, "warning: model worker did not stop within %s; force-killing it\n", settings.ModelShutdownTimeout)
if err := signalWorkerGroup(cmd, syscall.SIGKILL); err != nil {
desiredErr = errors.Join(desiredErr, err)
}
}
}
}
}
func startModelWorker(settings config.Settings, diagnostics io.Writer) (*exec.Cmd, *os.File, error) {
executable, err := os.Executable()
if err != nil {
return nil, nil, err
}
encodedSettings, err := encodeWorkerSettings(settings)
if err != nil {
return nil, nil, err
}
protocolRead, protocolWrite, err := os.Pipe()
if err != nil {
return nil, nil, err
}
cmd := exec.Command(executable)
cmd.Env = workerEnvironment(encodedSettings)
cmd.ExtraFiles = []*os.File{protocolWrite}
cmd.Stdout = diagnostics
cmd.Stderr = diagnostics
cmd.SysProcAttr = &syscall.SysProcAttr{
Setpgid: true,
Pdeathsig: syscall.SIGKILL,
}
if err := cmd.Start(); err != nil {
protocolRead.Close()
protocolWrite.Close()
return nil, nil, err
}
if err := protocolWrite.Close(); err != nil {
_ = signalWorkerGroup(cmd, syscall.SIGKILL)
_ = cmd.Wait()
protocolRead.Close()
return nil, nil, err
}
return cmd, protocolRead, nil
}
func workerEnvironment(encodedSettings string) []string {
environment := make([]string, 0, len(os.Environ())+2)
for _, item := range os.Environ() {
if strings.HasPrefix(item, modelWorkerEnvironment+"=") ||
strings.HasPrefix(item, modelSettingsEnvironment+"=") {
continue
}
environment = append(environment, item)
}
return append(environment,
modelWorkerEnvironment+"=1",
modelSettingsEnvironment+"="+encodedSettings,
)
}
func readWorkerMessages(protocol io.Reader, messages chan<- workerMessage, done chan<- error) {
defer close(messages)
decoder := json.NewDecoder(protocol)
for {
var message workerMessage
if err := decoder.Decode(&message); err != nil {
if errors.Is(err, io.EOF) {
done <- nil
} else {
done <- err
}
return
}
messages <- message
}
}
func signalWorkerGroup(cmd *exec.Cmd, signal syscall.Signal) error {
if cmd.Process == nil {
return nil
}
err := syscall.Kill(-cmd.Process.Pid, signal)
if errors.Is(err, syscall.ESRCH) {
return nil
}
if err != nil {
return fmt.Errorf("signal model worker: %w", err)
}
return nil
}
+66
View File
@@ -0,0 +1,66 @@
package app
import (
"strings"
"testing"
"time"
"tea.chunkbyte.com/kato/captioneer/src/config"
)
func TestWorkerHealthDetectsStartupAndOperationTimeouts(t *testing.T) {
started := time.Unix(100, 0)
health := workerHealth{startedAt: started, lastSeen: started}
if err := health.timeoutError(started.Add(time.Second), 2*time.Second); err != nil {
t.Fatalf("healthy startup reported a timeout: %v", err)
}
if err := health.timeoutError(started.Add(2*time.Second), 2*time.Second); err == nil ||
!strings.Contains(err.Error(), "did not become ready") {
t.Fatalf("startup timeout = %v", err)
}
health.observe(messageReady, started.Add(2*time.Second))
health.observe(messageBusy, started.Add(3*time.Second))
if err := health.timeoutError(started.Add(4*time.Second), 2*time.Second); err != nil {
t.Fatalf("healthy operation reported a timeout: %v", err)
}
if err := health.timeoutError(started.Add(5*time.Second), 2*time.Second); err == nil ||
!strings.Contains(err.Error(), "operation exceeded") {
t.Fatalf("operation timeout = %v", err)
}
health.observe(messageIdle, started.Add(5*time.Second))
health.observe(messageHeartbeat, started.Add(6*time.Second))
if err := health.timeoutError(started.Add(7*time.Second), 2*time.Second); err != nil {
t.Fatalf("idle worker reported a timeout: %v", err)
}
if err := health.timeoutError(started.Add(8*time.Second), 2*time.Second); err == nil ||
!strings.Contains(err.Error(), "heartbeat was silent") {
t.Fatalf("heartbeat timeout = %v", err)
}
}
func TestWorkerSettingsRoundTrip(t *testing.T) {
want := config.Settings{
Mode: config.ModeVAD,
ChunkDuration: time.Second,
ModelsDir: "models with spaces",
Threads: 3,
PreviewThresholdDB: -42,
ModelAutoRestart: true,
ModelTimeout: 12 * time.Second,
ModelShutdownTimeout: 2 * time.Second,
}
encoded, err := encodeWorkerSettings(want)
if err != nil {
t.Fatal(err)
}
got, err := decodeWorkerSettings(encoded)
if err != nil {
t.Fatal(err)
}
if got != want {
t.Fatalf("settings round trip = %#v, want %#v", got, want)
}
}
+152
View File
@@ -0,0 +1,152 @@
package app
import (
"context"
"encoding/base64"
"encoding/json"
"errors"
"fmt"
"io"
"os"
"os/signal"
"sync"
"syscall"
"time"
"tea.chunkbyte.com/kato/captioneer/src/captions"
"tea.chunkbyte.com/kato/captioneer/src/config"
)
const (
modelWorkerEnvironment = "CAPTIONEER_INTERNAL_MODEL_WORKER"
modelSettingsEnvironment = "CAPTIONEER_INTERNAL_MODEL_SETTINGS"
modelProtocolFD = 3
)
const (
messageReady = "ready"
messageBusy = "busy"
messageIdle = "idle"
messageCaption = "caption"
messageFailure = "failure"
messageHeartbeat = "heartbeat"
)
type workerMessage struct {
Type string `json:"type"`
Event *captions.Event `json:"event,omitempty"`
Error string `json:"error,omitempty"`
}
type workerReporter struct {
mu sync.Mutex
encoder *json.Encoder
}
func (r *workerReporter) send(message workerMessage) error {
r.mu.Lock()
defer r.mu.Unlock()
return r.encoder.Encode(message)
}
type protocolSink struct {
reporter *workerReporter
}
func (s protocolSink) Publish(event captions.Event) error {
return s.reporter.send(workerMessage{Type: messageCaption, Event: &event})
}
func (protocolSink) Close() error { return nil }
// IsModelWorker reports whether this process was created as Captioneer's
// private inference worker. The environment marker is intentionally internal.
func IsModelWorker() bool {
return os.Getenv(modelWorkerEnvironment) == "1"
}
func encodeWorkerSettings(settings config.Settings) (string, error) {
data, err := json.Marshal(settings)
if err != nil {
return "", err
}
return base64.RawStdEncoding.EncodeToString(data), nil
}
func decodeWorkerSettings(value string) (config.Settings, error) {
data, err := base64.RawStdEncoding.DecodeString(value)
if err != nil {
return config.Settings{}, fmt.Errorf("decode model worker settings: %w", err)
}
var settings config.Settings
if err := json.Unmarshal(data, &settings); err != nil {
return config.Settings{}, fmt.Errorf("parse model worker settings: %w", err)
}
if err := settings.Validate(); err != nil {
return config.Settings{}, fmt.Errorf("validate model worker settings: %w", err)
}
return settings, nil
}
// RunModelWorker owns all Sherpa/VAD resources in the supervised child. It
// returns a process exit code so command entrypoints can call os.Exit.
func RunModelWorker(diagnostics io.Writer) int {
protocol := os.NewFile(uintptr(modelProtocolFD), "captioneer-model-protocol")
if protocol == nil {
fmt.Fprintln(diagnostics, "captioneer: model worker protocol is unavailable")
return 1
}
defer protocol.Close()
syscall.CloseOnExec(modelProtocolFD)
settings, err := decodeWorkerSettings(os.Getenv(modelSettingsEnvironment))
if err != nil {
fmt.Fprintf(diagnostics, "captioneer: %v\n", err)
return 1
}
ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM)
defer stop()
reporter := &workerReporter{encoder: json.NewEncoder(protocol)}
hooks := directHooks{
ready: func() error { return reporter.send(workerMessage{Type: messageReady}) },
busy: func() error { return reporter.send(workerMessage{Type: messageBusy}) },
idle: func() error { return reporter.send(workerMessage{Type: messageIdle}) },
}
heartbeatInterval := time.Second
if settings.ModelTimeout > 0 && settings.ModelTimeout < 4*heartbeatInterval {
heartbeatInterval = settings.ModelTimeout / 4
if heartbeatInterval <= 0 {
heartbeatInterval = time.Millisecond
}
}
heartbeatContext, stopHeartbeat := context.WithCancel(ctx)
heartbeatDone := make(chan struct{})
go func() {
defer close(heartbeatDone)
ticker := time.NewTicker(heartbeatInterval)
defer ticker.Stop()
for {
select {
case <-heartbeatContext.Done():
return
case <-ticker.C:
if reporter.send(workerMessage{Type: messageHeartbeat}) != nil {
return
}
}
}
}()
err = runDirect(ctx, settings, protocolSink{reporter: reporter}, diagnostics, hooks)
stopHeartbeat()
<-heartbeatDone
if err == nil || errors.Is(err, context.Canceled) {
return 0
}
_ = reporter.send(workerMessage{Type: messageFailure, Error: err.Error()})
fmt.Fprintf(diagnostics, "captioneer: model worker: %v\n", err)
return 1
}
+2
View File
@@ -10,6 +10,7 @@ import (
"os/exec"
"strings"
"sync"
"syscall"
"tea.chunkbyte.com/kato/captioneer/src/audio"
)
@@ -41,6 +42,7 @@ func Packets(ctx context.Context, monitorSource string) (<-chan []float32, func(
"--latency-msec=50",
)
cmd.Stderr = os.Stderr
cmd.SysProcAttr = &syscall.SysProcAttr{Pdeathsig: syscall.SIGKILL}
stdout, err := cmd.StdoutPipe()
if err != nil {
return nil, nil, err
+4
View File
@@ -20,6 +20,10 @@ import (
)
func main() {
if app.IsModelWorker() {
os.Exit(app.RunModelWorker(os.Stderr))
}
runtime.LockOSThread()
defer runtime.UnlockOSThread()
+4
View File
@@ -13,6 +13,10 @@ import (
)
func main() {
if app.IsModelWorker() {
os.Exit(app.RunModelWorker(os.Stderr))
}
settings := config.Parse()
if err := settings.Validate(); err != nil {
log.Fatal(err)
+29 -5
View File
@@ -4,12 +4,16 @@ package config
import (
"errors"
"flag"
"strings"
"time"
)
const (
DefaultModelsDir = "models"
DefaultOverlayFontFamily = "Sans"
MinimumOverlayFinalLifetime = 3 * time.Second
DefaultModelTimeout = 30 * time.Second
DefaultModelShutdownTimeout = 2 * time.Second
)
type Mode string
@@ -20,11 +24,14 @@ const (
)
type Settings struct {
Mode Mode
ChunkDuration time.Duration
ModelsDir string
Threads int
PreviewThresholdDB float64
Mode Mode
ChunkDuration time.Duration
ModelsDir string
Threads int
PreviewThresholdDB float64
ModelAutoRestart bool
ModelTimeout time.Duration
ModelShutdownTimeout time.Duration
}
func Parse() Settings {
@@ -35,6 +42,9 @@ func Parse() Settings {
flag.StringVar(&settings.ModelsDir, "models-dir", DefaultModelsDir, "directory containing downloaded Sherpa models")
flag.IntVar(&settings.Threads, "threads", 2, "CPU threads used by recognition and VAD")
flag.Float64Var(&settings.PreviewThresholdDB, "preview-threshold-dbfs", -45, "RMS dBFS threshold used to begin VAD previews")
flag.BoolVar(&settings.ModelAutoRestart, "model-auto-restart", true, "restart the isolated model worker after a crash or timeout")
flag.DurationVar(&settings.ModelTimeout, "model-timeout", DefaultModelTimeout, "maximum model startup or processing time; zero disables hang detection")
flag.DurationVar(&settings.ModelShutdownTimeout, "model-shutdown-timeout", DefaultModelShutdownTimeout, "time allowed for model flush and cleanup before force-killing the worker")
flag.Parse()
settings.Mode = Mode(mode)
return settings
@@ -60,6 +70,7 @@ type OverlaySettings struct {
Backend OverlayBackend
Opacity float64
FontSize int
FontFamily string
BottomMargin int
MaxWidth int
Monitor string
@@ -84,10 +95,14 @@ func ParseDesktop() DesktopSettings {
flags.StringVar(&desktop.ModelsDir, "models-dir", DefaultModelsDir, "directory containing downloaded Sherpa models")
flags.IntVar(&desktop.Threads, "threads", 2, "CPU threads used by recognition and VAD")
flags.Float64Var(&desktop.PreviewThresholdDB, "preview-threshold-dbfs", -45, "RMS dBFS threshold used to begin VAD previews")
flags.BoolVar(&desktop.ModelAutoRestart, "model-auto-restart", true, "restart the isolated model worker after a crash or timeout")
flags.DurationVar(&desktop.ModelTimeout, "model-timeout", DefaultModelTimeout, "maximum model startup or processing time; zero disables hang detection")
flags.DurationVar(&desktop.ModelShutdownTimeout, "model-shutdown-timeout", DefaultModelShutdownTimeout, "time allowed for model flush and cleanup before force-killing the worker")
flags.StringVar(&output, "output", "", "caption output: terminal, overlay, or both (required)")
flags.StringVar(&backend, "overlay-backend", "auto", "display backend: auto, wayland, or x11")
flags.Float64Var(&desktop.Overlay.Opacity, "overlay-opacity", 0.90, "caption background opacity from 0 to 1")
flags.IntVar(&desktop.Overlay.FontSize, "overlay-font-size", 28, "caption font size in logical pixels")
flags.StringVar(&desktop.Overlay.FontFamily, "overlay-font-family", DefaultOverlayFontFamily, "caption font family")
flags.IntVar(&desktop.Overlay.BottomMargin, "overlay-bottom-margin", 100, "distance from the monitor bottom in logical pixels")
flags.IntVar(&desktop.Overlay.MaxWidth, "overlay-max-width", 1200, "fixed caption width in logical pixels before the monitor safety cap")
flags.StringVar(&desktop.Overlay.Monitor, "overlay-monitor", "auto", "monitor selection: auto, numeric index, or connector name")
@@ -110,6 +125,12 @@ func (s Settings) Validate() error {
if s.Threads <= 0 {
return errors.New("--threads must be positive")
}
if s.ModelTimeout < 0 {
return errors.New("--model-timeout cannot be negative")
}
if s.ModelShutdownTimeout <= 0 {
return errors.New("--model-shutdown-timeout must be positive")
}
return nil
}
@@ -129,6 +150,9 @@ func (s DesktopSettings) Validate() error {
if s.Overlay.FontSize <= 0 {
return errors.New("--overlay-font-size must be positive")
}
if strings.TrimSpace(s.Overlay.FontFamily) == "" {
return errors.New("--overlay-font-family cannot be empty")
}
if s.Overlay.BottomMargin < 0 {
return errors.New("--overlay-bottom-margin cannot be negative")
}
+18 -4
View File
@@ -6,7 +6,12 @@ import (
)
func TestSettingsValidate(t *testing.T) {
valid := Settings{Mode: ModeFixed, ChunkDuration: time.Second, Threads: 1}
valid := Settings{
Mode: ModeFixed,
ChunkDuration: time.Second,
Threads: 1,
ModelShutdownTimeout: DefaultModelShutdownTimeout,
}
if err := valid.Validate(); err != nil {
t.Fatalf("valid settings failed: %v", err)
}
@@ -17,10 +22,16 @@ func TestSettingsValidate(t *testing.T) {
func validDesktopSettings() DesktopSettings {
return DesktopSettings{
Settings: Settings{Mode: ModeVAD, ChunkDuration: time.Second, Threads: 2},
Output: OutputOverlay,
Settings: Settings{
Mode: ModeVAD,
ChunkDuration: time.Second,
Threads: 2,
ModelTimeout: DefaultModelTimeout,
ModelShutdownTimeout: DefaultModelShutdownTimeout,
},
Output: OutputOverlay,
Overlay: OverlaySettings{
Backend: BackendAuto, Opacity: 0.9, FontSize: 28, BottomMargin: 100,
Backend: BackendAuto, Opacity: 0.9, FontSize: 28, FontFamily: DefaultOverlayFontFamily, BottomMargin: 100,
MaxWidth: 1200, Monitor: "auto", FinalTimeout: 4 * time.Second, ClickThrough: true,
},
}
@@ -40,11 +51,14 @@ func TestDesktopSettingsValidate(t *testing.T) {
{"negative opacity", func(s *DesktopSettings) { s.Overlay.Opacity = -0.1 }},
{"large opacity", func(s *DesktopSettings) { s.Overlay.Opacity = 1.1 }},
{"zero font", func(s *DesktopSettings) { s.Overlay.FontSize = 0 }},
{"empty font family", func(s *DesktopSettings) { s.Overlay.FontFamily = " " }},
{"negative margin", func(s *DesktopSettings) { s.Overlay.BottomMargin = -1 }},
{"zero width", func(s *DesktopSettings) { s.Overlay.MaxWidth = 0 }},
{"empty monitor", func(s *DesktopSettings) { s.Overlay.Monitor = "" }},
{"negative timeout", func(s *DesktopSettings) { s.Overlay.FinalTimeout = -time.Second }},
{"short timeout", func(s *DesktopSettings) { s.Overlay.FinalTimeout = time.Second }},
{"negative model timeout", func(s *DesktopSettings) { s.ModelTimeout = -time.Second }},
{"zero model shutdown timeout", func(s *DesktopSettings) { s.ModelShutdownTimeout = 0 }},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
+5
View File
@@ -25,6 +25,11 @@ type Resources struct {
vad *sherpa.VoiceActivityDetector
}
func Validate(settings config.Settings) error {
_, err := validatePaths(settings.ModelsDir, settings.Mode)
return err
}
func New(settings config.Settings) (*Resources, error) {
paths, err := validatePaths(settings.ModelsDir, settings.Mode)
if err != nil {
+63 -17
View File
@@ -246,10 +246,27 @@ static gboolean captioneer_window_close(GtkWindow *window, gpointer data) {
return TRUE;
}
static char *captioneer_font_family_rule(const char *font_family) {
GString *rule = g_string_new("font-family: \"");
for (const char *character = font_family; *character != '\0'; character++) {
if (*character == '\\' || *character == '\"') {
g_string_append_c(rule, '\\');
}
if (*character == '\n' || *character == '\r' || *character == '\t') {
g_string_append_c(rule, ' ');
} else {
g_string_append_c(rule, *character);
}
}
g_string_append(rule, "\";");
return g_string_free(rule, FALSE);
}
static CaptioneerOverlay *captioneer_overlay_new(
const char *backend,
double opacity,
int font_size,
const char *font_family,
int bottom_margin,
int max_width,
const char *monitor_selection,
@@ -354,6 +371,9 @@ static CaptioneerOverlay *captioneer_overlay_new(
gtk_label_set_xalign(GTK_LABEL(labels[i]), 0.0f);
gtk_label_set_wrap(GTK_LABEL(labels[i]), TRUE);
gtk_label_set_wrap_mode(GTK_LABEL(labels[i]), PANGO_WRAP_WORD_CHAR);
// width-chars gives GTK a concrete allocation width, so wrapping happens
// before a long sentence can widen the bubble beyond the screen.
gtk_label_set_width_chars(GTK_LABEL(labels[i]), max_chars);
gtk_label_set_max_width_chars(GTK_LABEL(labels[i]), max_chars);
gtk_widget_set_halign(labels[i], GTK_ALIGN_FILL);
gtk_box_append(GTK_BOX(box), labels[i]);
@@ -363,23 +383,27 @@ static CaptioneerOverlay *captioneer_overlay_new(
// view state, rather than GTK ellipsizing, enforces its six-entry limit.
gtk_label_set_lines(GTK_LABEL(overlay->final_label), -1);
gtk_label_set_ellipsize(GTK_LABEL(overlay->final_label), PANGO_ELLIPSIZE_NONE);
gtk_label_set_lines(GTK_LABEL(overlay->preview_label), 2);
gtk_label_set_ellipsize(GTK_LABEL(overlay->preview_label), PANGO_ELLIPSIZE_END);
// Provisional text is already split and bounded by the Go view state. Let
// GTK allocate all of those lines instead of replacing overflow with "…".
gtk_label_set_lines(GTK_LABEL(overlay->preview_label), -1);
gtk_label_set_ellipsize(GTK_LABEL(overlay->preview_label), PANGO_ELLIPSIZE_NONE);
gtk_widget_add_css_class(overlay->final_label, "captioneer-final");
gtk_widget_add_css_class(overlay->preview_label, "captioneer-preview");
gtk_window_set_child(overlay->window, box);
char *font_family_rule = captioneer_font_family_rule(font_family);
char *css = g_strdup_printf(
"window.captioneer-overlay { background-color: transparent; box-shadow: none; }"
".captioneer-bubble { background-color: rgba(0, 0, 0, %.3f); border-radius: 12px; padding: 14px 22px; }"
".captioneer-final { color: rgba(255, 255, 255, 1.0); font-size: %dpx; }"
".captioneer-preview { color: rgba(255, 255, 255, 0.78); font-size: %dpx; }",
opacity, font_size, font_size);
".captioneer-final { color: rgba(255, 255, 255, 1.0); font-size: %dpx; %s }"
".captioneer-preview { color: rgba(255, 255, 255, 0.78); font-size: %dpx; %s }",
opacity, font_size, font_family_rule, font_size, font_family_rule);
GtkCssProvider *provider = gtk_css_provider_new();
gtk_css_provider_load_from_string(provider, css);
gtk_style_context_add_provider_for_display(display, GTK_STYLE_PROVIDER(provider), GTK_STYLE_PROVIDER_PRIORITY_APPLICATION);
g_object_unref(provider);
g_free(css);
g_free(font_family_rule);
gtk_widget_realize(GTK_WIDGET(overlay->window));
GdkSurface *surface = gtk_native_get_surface(GTK_NATIVE(overlay->window));
@@ -449,21 +473,29 @@ import (
"tea.chunkbyte.com/kato/captioneer/src/config"
)
const finalFadeRefreshInterval = 200 * time.Millisecond
const (
finalFadeRefreshInterval = 200 * time.Millisecond
averageGlyphWidthFactor = 0.58
minimumLineCharacters = 20
maximumLineCharacters = 64
)
type Sink struct {
native *C.CaptioneerOverlay
finalTimeout time.Duration
finalTimer *time.Timer
state viewState
mu sync.RWMutex
closed bool
native *C.CaptioneerOverlay
finalTimeout time.Duration
finalTimer *time.Timer
lineCharacters int
state viewState
mu sync.RWMutex
closed bool
}
func New(settings config.OverlaySettings) (*Sink, string, error) {
backend := C.CString(string(settings.Backend))
fontFamily := C.CString(settings.FontFamily)
monitor := C.CString(settings.Monitor)
defer C.free(unsafe.Pointer(backend))
defer C.free(unsafe.Pointer(fontFamily))
defer C.free(unsafe.Pointer(monitor))
var warningMessage *C.char
@@ -472,6 +504,7 @@ func New(settings config.OverlaySettings) (*Sink, string, error) {
backend,
C.double(settings.Opacity),
C.int(settings.FontSize),
fontFamily,
C.int(settings.BottomMargin),
C.int(settings.MaxWidth),
monitor,
@@ -487,7 +520,11 @@ func New(settings config.OverlaySettings) (*Sink, string, error) {
}
return nil, warning, errors.New(message)
}
return &Sink{native: native, finalTimeout: settings.FinalTimeout}, warning, nil
return &Sink{
native: native,
finalTimeout: settings.FinalTimeout,
lineCharacters: overlayLineCharacters(settings),
}, warning, nil
}
func (s *Sink) Publish(event captions.Event) error {
@@ -497,17 +534,26 @@ func (s *Sink) Publish(event captions.Event) error {
return errors.New("overlay is closed")
}
now := time.Now()
s.state.Apply(event, now, s.finalTimeout)
if event.Kind == captions.Final || event.Kind == captions.Hide {
s.stopFinalTimer()
}
s.state.Apply(event, now, s.finalTimeout, s.lineCharacters)
if event.Kind == captions.Final {
s.stopFinalTimer()
s.scheduleFinalRefresh(now)
}
s.postState()
return nil
}
func overlayLineCharacters(settings config.OverlaySettings) int {
characters := int(float64(settings.MaxWidth) / (float64(settings.FontSize) * averageGlyphWidthFactor))
if characters < minimumLineCharacters {
return minimumLineCharacters
}
if characters > maximumLineCharacters {
return maximumLineCharacters
}
return characters
}
func (s *Sink) refreshFinals() {
s.mu.Lock()
defer s.mu.Unlock()
+113 -11
View File
@@ -3,16 +3,20 @@ package overlay
import (
"fmt"
"html"
"math"
"strings"
"time"
"unicode/utf8"
"tea.chunkbyte.com/kato/captioneer/src/captions"
)
const (
maxVisibleFinalLines = 6
maxVisiblePreviewLines = 3
oldestLineBrightness = 0.65
defaultLineFadeDuration = 3 * time.Second
readingWordsPerSecond = 3.0
)
type finalLine struct {
@@ -26,26 +30,39 @@ type viewState struct {
Provisional string
}
func (s *viewState) Apply(event captions.Event, now time.Time, finalTimeout time.Duration) {
func (s *viewState) Apply(event captions.Event, now time.Time, finalTimeout time.Duration, maxLineCharacters int) {
switch event.Kind {
case captions.Provisional:
s.Provisional = strings.TrimSpace(event.Text)
chunks := splitCaptionText(event.Text, maxLineCharacters)
if len(chunks) > maxVisiblePreviewLines {
chunks = chunks[len(chunks)-maxVisiblePreviewLines:]
}
s.Provisional = strings.Join(chunks, "\n")
case captions.Final:
text := strings.TrimSpace(event.Text)
if text == "" {
chunks := splitCaptionText(event.Text, maxLineCharacters)
if len(chunks) == 0 {
return
}
line := finalLine{CreatedAt: now, Text: text}
if finalTimeout > 0 {
line.ExpiresAt = now.Add(finalTimeout)
if len(chunks) > maxVisibleFinalLines {
chunks = chunks[len(chunks)-maxVisibleFinalLines:]
}
expiresAt := now
for _, text := range chunks {
line := finalLine{CreatedAt: now, Text: text}
if finalTimeout > 0 {
expiresAt = expiresAt.Add(readingLifetime(text, finalTimeout))
line.ExpiresAt = expiresAt
}
s.Finals = append(s.Finals, line)
}
s.Finals = append(s.Finals, line)
if len(s.Finals) > maxVisibleFinalLines {
s.Finals = s.Finals[len(s.Finals)-maxVisibleFinalLines:]
}
s.Provisional = ""
case captions.Hide:
*s = viewState{}
// A blank recognition result must not erase completed captions before
// their individual reading lifetimes have elapsed.
s.Provisional = ""
}
}
@@ -84,7 +101,11 @@ func (s viewState) FinalMarkup(now time.Time, lineLifetime time.Duration) string
if i > 0 {
markup.WriteByte('\n')
}
brightness := lineBrightness(now.Sub(line.CreatedAt), fadeDuration)
lineFadeDuration := fadeDuration
if !line.ExpiresAt.IsZero() {
lineFadeDuration = line.ExpiresAt.Sub(line.CreatedAt)
}
brightness := lineBrightness(now.Sub(line.CreatedAt), lineFadeDuration)
channel := int(brightness*255 + 0.5)
fmt.Fprintf(&markup, `<span foreground="#%02X%02X%02X">`, channel, channel, channel)
markup.WriteString(html.EscapeString(line.Text))
@@ -99,13 +120,94 @@ func (s viewState) NeedsFadeRefresh(now time.Time, lineLifetime time.Duration) b
fadeDuration = defaultLineFadeDuration
}
for _, line := range s.Finals {
if now.Sub(line.CreatedAt) < fadeDuration {
lineFadeDuration := fadeDuration
if !line.ExpiresAt.IsZero() {
lineFadeDuration = line.ExpiresAt.Sub(line.CreatedAt)
}
if now.Sub(line.CreatedAt) < lineFadeDuration {
return true
}
}
return false
}
func splitCaptionText(text string, maxCharacters int) []string {
if maxCharacters < 1 {
maxCharacters = 1
}
words := strings.Fields(text)
if len(words) == 0 {
return nil
}
var chunks []string
var current strings.Builder
currentCharacters := 0
flush := func() {
if currentCharacters == 0 {
return
}
chunks = append(chunks, current.String())
current.Reset()
currentCharacters = 0
}
for _, word := range words {
wordCharacters := utf8.RuneCountInString(word)
if wordCharacters > maxCharacters {
flush()
runes := []rune(word)
for len(runes) > maxCharacters {
chunks = append(chunks, string(runes[:maxCharacters]))
runes = runes[maxCharacters:]
}
if len(runes) > 0 {
current.WriteString(string(runes))
currentCharacters = len(runes)
}
} else {
separatorCharacters := 0
if currentCharacters > 0 {
separatorCharacters = 1
}
if currentCharacters+separatorCharacters+wordCharacters > maxCharacters {
flush()
separatorCharacters = 0
}
if separatorCharacters > 0 {
current.WriteByte(' ')
currentCharacters++
}
current.WriteString(word)
currentCharacters += wordCharacters
}
if endsSentence(word) {
flush()
}
}
flush()
return chunks
}
func endsSentence(word string) bool {
trimmed := strings.TrimRight(word, `"'”’)]}`)
return strings.HasSuffix(trimmed, ".") || strings.HasSuffix(trimmed, "!") || strings.HasSuffix(trimmed, "?")
}
func readingLifetime(text string, minimum time.Duration) time.Duration {
if minimum <= 0 {
return 0
}
words := len(strings.Fields(text))
readingSeconds := math.Ceil(float64(words) / readingWordsPerSecond)
readingTime := time.Duration(readingSeconds * float64(time.Second))
if readingTime < minimum {
return minimum
}
return readingTime
}
func (s viewState) NextFinalExpiry() time.Time {
if len(s.Finals) == 0 {
return time.Time{}
+66 -13
View File
@@ -7,29 +7,31 @@ import (
"tea.chunkbyte.com/kato/captioneer/src/captions"
)
const testLineCharacters = 80
func TestViewStateKeepsCompletedLinesAboveNewProvisional(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Provisional, Text: " first draft "}, now, 4*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: " first final "}, now, 4*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: " second final "}, now, 4*time.Second)
state.Apply(captions.Event{Kind: captions.Provisional, Text: " next draft "}, now, 4*time.Second)
state.Apply(captions.Event{Kind: captions.Provisional, Text: " first draft "}, now, 4*time.Second, testLineCharacters)
state.Apply(captions.Event{Kind: captions.Final, Text: " first final "}, now, 4*time.Second, testLineCharacters)
state.Apply(captions.Event{Kind: captions.Final, Text: " second final "}, now, 4*time.Second, testLineCharacters)
state.Apply(captions.Event{Kind: captions.Provisional, Text: " next draft "}, now, 4*time.Second, testLineCharacters)
if state.FinalText() != "first final\nsecond final" || state.Provisional != "next draft" {
t.Fatalf("unexpected rows: %#v", state)
}
state.Apply(captions.Event{Kind: captions.Hide}, now, 4*time.Second)
if state.FinalText() != "" || state.Provisional != "" {
t.Fatalf("hide did not clear rows: %#v", state)
state.Apply(captions.Event{Kind: captions.Hide}, now, 4*time.Second, testLineCharacters)
if state.FinalText() != "first final\nsecond final" || state.Provisional != "" {
t.Fatalf("blank result erased completed captions: %#v", state)
}
}
func TestViewStateExpiresEachCompletedLineAfterItsOwnLifetime(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Final, Text: "first"}, now, 3*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: "second"}, now.Add(time.Second), 3*time.Second)
state.Apply(captions.Event{Kind: captions.Provisional, Text: "draft"}, now, 3*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: "first"}, now, 3*time.Second, testLineCharacters)
state.Apply(captions.Event{Kind: captions.Final, Text: "second"}, now.Add(time.Second), 3*time.Second, testLineCharacters)
state.Apply(captions.Event{Kind: captions.Provisional, Text: "draft"}, now, 3*time.Second, testLineCharacters)
if state.ExpireFinal(now.Add(2999 * time.Millisecond)) {
t.Fatal("completed line expired early")
@@ -46,7 +48,7 @@ func TestViewStateLimitsVisibleCompletedLines(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
for i := 0; i <= maxVisibleFinalLines; i++ {
state.Apply(captions.Event{Kind: captions.Final, Text: string(rune('a' + i))}, now, 3*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: string(rune('a' + i))}, now, 3*time.Second, testLineCharacters)
}
if len(state.Finals) != maxVisibleFinalLines || state.FinalText() != "b\nc\nd\ne\nf\ng" {
t.Fatalf("unexpected completed-line limit: %#v", state)
@@ -56,7 +58,7 @@ func TestViewStateLimitsVisibleCompletedLines(t *testing.T) {
func TestViewStateZeroTimeoutDoesNotExpire(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Final, Text: "final"}, now, 0)
state.Apply(captions.Event{Kind: captions.Final, Text: "final"}, now, 0, testLineCharacters)
if state.ExpireFinal(now.Add(24 * time.Hour)) {
t.Fatal("zero-timeout caption expired")
}
@@ -65,7 +67,7 @@ func TestViewStateZeroTimeoutDoesNotExpire(t *testing.T) {
func TestViewStateFinalMarkupFadesAndEscapesText(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Final, Text: "<hello & goodbye>"}, now, 3*time.Second)
state.Apply(captions.Event{Kind: captions.Final, Text: "<hello & goodbye>"}, now, 3*time.Second, testLineCharacters)
if got := state.FinalMarkup(now, 3*time.Second); got != `<span foreground="#FFFFFF">&lt;hello &amp; goodbye&gt;</span>` {
t.Fatalf("new line markup = %q", got)
@@ -74,3 +76,54 @@ func TestViewStateFinalMarkupFadesAndEscapesText(t *testing.T) {
t.Fatalf("old line markup = %q", got)
}
}
func TestSplitCaptionTextUsesSentencesAndWordBoundaries(t *testing.T) {
got := splitCaptionText("Hello there. This sentence should wrap cleanly at words.", 18)
want := []string{"Hello there.", "This sentence", "should wrap", "cleanly at words."}
if len(got) != len(want) {
t.Fatalf("chunks = %#v, want %#v", got, want)
}
for i := range want {
if got[i] != want[i] {
t.Fatalf("chunks = %#v, want %#v", got, want)
}
}
}
func TestProvisionalCaptionKeepsOnlyLatestDigestibleChunks(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Provisional, Text: "One. Two. Three. Four."}, now, 3*time.Second, testLineCharacters)
if state.Provisional != "Two.\nThree.\nFour." {
t.Fatalf("provisional text = %q", state.Provisional)
}
}
func TestReadingLifetimeGrowsWithWordCount(t *testing.T) {
text := "one two three four five six seven eight nine ten eleven twelve"
if got := readingLifetime(text, 3*time.Second); got != 4*time.Second {
t.Fatalf("reading lifetime = %s, want 4s", got)
}
if got := readingLifetime("short caption", 3*time.Second); got != 3*time.Second {
t.Fatalf("short reading lifetime = %s, want 3s", got)
}
}
func TestFinalizedChunksExpireInReadingOrder(t *testing.T) {
now := time.Unix(100, 0)
var state viewState
state.Apply(captions.Event{Kind: captions.Final, Text: "First sentence. Second sentence."}, now, 3*time.Second, testLineCharacters)
if len(state.Finals) != 2 {
t.Fatalf("final chunks = %#v", state.Finals)
}
if state.Finals[0].ExpiresAt != now.Add(3*time.Second) {
t.Fatalf("first expiry = %s", state.Finals[0].ExpiresAt)
}
if state.Finals[1].ExpiresAt != now.Add(6*time.Second) {
t.Fatalf("second expiry = %s", state.Finals[1].ExpiresAt)
}
if !state.ExpireFinal(now.Add(3*time.Second)) || state.FinalText() != "Second sentence." {
t.Fatalf("unexpected state after first reading window: %#v", state)
}
}