[refactor] streamline crate structure, update dependencies, and integrate CLI functionalities
This commit is contained in:
@@ -2,23 +2,25 @@
|
||||
name = "polyscribe-cli"
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
license = "MIT"
|
||||
|
||||
[[bin]]
|
||||
name = "polyscribe"
|
||||
path = "src/main.rs"
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.98"
|
||||
clap = { version = "4.5.43", features = ["derive"] }
|
||||
clap_complete = "4.5.28"
|
||||
clap_mangen = "0.2"
|
||||
anyhow = "1.0.99"
|
||||
clap = { version = "4.5.44", features = ["derive"] }
|
||||
clap_complete = "4.5.57"
|
||||
clap_mangen = "0.2.29"
|
||||
directories = "5.0.1"
|
||||
indicatif = "0.17.11"
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = "1.0.142"
|
||||
toml = "0.8"
|
||||
chrono = { version = "0.4", features = ["clock"] }
|
||||
cliclack = "0.3"
|
||||
indicatif = "0.17"
|
||||
polyscribe = { path = "../polyscribe-core" }
|
||||
tokio = { version = "1.47.1", features = ["rt-multi-thread", "macros", "process", "fs"] }
|
||||
tracing = "0.1"
|
||||
tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
|
||||
which = "6.0.3"
|
||||
|
||||
polyscribe-core = { path = "../polyscribe-core" }
|
||||
polyscribe-host = { path = "../polyscribe-host" }
|
||||
polyscribe-protocol = { path = "../polyscribe-protocol" }
|
||||
|
||||
[features]
|
||||
# Optional GPU-specific flags can be forwarded down to core/host if needed
|
||||
default = []
|
||||
|
||||
119
crates/polyscribe-cli/src/cli.rs
Normal file
119
crates/polyscribe-cli/src/cli.rs
Normal file
@@ -0,0 +1,119 @@
|
||||
use clap::{Parser, Subcommand, ValueEnum};
|
||||
use std::path::PathBuf;
|
||||
|
||||
#[derive(Debug, Clone, ValueEnum)]
|
||||
pub enum GpuBackend {
|
||||
Auto,
|
||||
Cpu,
|
||||
Cuda,
|
||||
Hip,
|
||||
Vulkan,
|
||||
}
|
||||
|
||||
#[derive(Debug, Parser)]
|
||||
#[command(name = "polyscribe", version, about = "PolyScribe – local-first transcription and plugins")]
|
||||
pub struct Cli {
|
||||
/// Increase verbosity (-v, -vv)
|
||||
#[arg(short, long, action = clap::ArgAction::Count)]
|
||||
pub verbose: u8,
|
||||
|
||||
/// Quiet mode (suppresses non-error logs)
|
||||
#[arg(short, long, default_value_t = false)]
|
||||
pub quiet: bool,
|
||||
|
||||
/// Never prompt for user input (non-interactive mode)
|
||||
#[arg(long, default_value_t = false)]
|
||||
pub no_interaction: bool,
|
||||
|
||||
#[command(subcommand)]
|
||||
pub command: Commands,
|
||||
}
|
||||
|
||||
#[derive(Debug, Subcommand)]
|
||||
pub enum Commands {
|
||||
/// Transcribe audio/video files or merge existing transcripts
|
||||
Transcribe {
|
||||
/// Output file or directory (date prefix is added when directory)
|
||||
#[arg(short, long)]
|
||||
output: Option<PathBuf>,
|
||||
|
||||
/// Merge multiple inputs into one output
|
||||
#[arg(short = 'm', long, default_value_t = false)]
|
||||
merge: bool,
|
||||
|
||||
/// Write both merged and per-input outputs (requires -o dir)
|
||||
#[arg(long, default_value_t = false)]
|
||||
merge_and_separate: bool,
|
||||
|
||||
/// Language code hint, e.g. en, de
|
||||
#[arg(long)]
|
||||
language: Option<String>,
|
||||
|
||||
/// Prompt for a speaker label per input file
|
||||
#[arg(long, default_value_t = false)]
|
||||
set_speaker_names: bool,
|
||||
|
||||
/// GPU backend selection
|
||||
#[arg(long, value_enum, default_value_t = GpuBackend::Auto)]
|
||||
gpu_backend: GpuBackend,
|
||||
|
||||
/// Offload N layers to GPU (when supported)
|
||||
#[arg(long, default_value_t = 0)]
|
||||
gpu_layers: usize,
|
||||
|
||||
/// Input paths: audio/video files or JSON transcripts
|
||||
#[arg(required = true)]
|
||||
inputs: Vec<PathBuf>,
|
||||
},
|
||||
|
||||
/// Manage Whisper models
|
||||
Models {
|
||||
#[command(subcommand)]
|
||||
cmd: ModelsCmd,
|
||||
},
|
||||
|
||||
/// Discover and run plugins
|
||||
Plugins {
|
||||
#[command(subcommand)]
|
||||
cmd: PluginsCmd,
|
||||
},
|
||||
|
||||
/// Generate shell completions to stdout
|
||||
Completions {
|
||||
/// Shell to generate completions for
|
||||
#[arg(value_parser = ["bash", "zsh", "fish", "powershell", "elvish"])]
|
||||
shell: String,
|
||||
},
|
||||
|
||||
/// Generate a man page to stdout
|
||||
Man,
|
||||
}
|
||||
|
||||
#[derive(Debug, Subcommand)]
|
||||
pub enum ModelsCmd {
|
||||
/// Verify or update local models non-interactively
|
||||
Update,
|
||||
/// Interactive multi-select downloader
|
||||
Download,
|
||||
}
|
||||
|
||||
#[derive(Debug, Subcommand)]
|
||||
pub enum PluginsCmd {
|
||||
/// List installed plugins
|
||||
List,
|
||||
/// Show a plugin's capabilities (as JSON)
|
||||
Info {
|
||||
/// Plugin short name, e.g., "tubescribe"
|
||||
name: String,
|
||||
},
|
||||
/// Run a plugin command (JSON-RPC over NDJSON via stdio)
|
||||
Run {
|
||||
/// Plugin short name
|
||||
name: String,
|
||||
/// Command name in plugin's API
|
||||
command: String,
|
||||
/// JSON payload string
|
||||
#[arg(long)]
|
||||
json: Option<String>,
|
||||
},
|
||||
}
|
||||
@@ -1,536 +1,153 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025 <COPYRIGHT HOLDER>. All rights reserved.
|
||||
mod cli;
|
||||
|
||||
use std::fs::{File, create_dir_all};
|
||||
use std::io::{self, Read, Write};
|
||||
use std::path::{Path, PathBuf};
|
||||
use anyhow::{anyhow, Context, Result};
|
||||
use clap::{Parser, CommandFactory};
|
||||
use cli::{Cli, Commands, GpuBackend, ModelsCmd, PluginsCmd};
|
||||
use polyscribe_core::{config::ConfigService, ui::progress::ProgressReporter};
|
||||
use polyscribe_host::PluginManager;
|
||||
use tokio::io::AsyncWriteExt;
|
||||
use tracing::{error, info};
|
||||
use tracing_subscriber::EnvFilter;
|
||||
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use clap::{Parser, Subcommand, ValueEnum, CommandFactory};
|
||||
use clap_complete::Shell;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use polyscribe::{OutputEntry, date_prefix, normalize_lang_code, render_srt};
|
||||
use polyscribe_host as host;
|
||||
|
||||
#[derive(Subcommand, Debug, Clone)]
|
||||
enum PluginsCmd {
|
||||
/// List available plugins
|
||||
List,
|
||||
/// Show plugin capabilities
|
||||
Info { name: String },
|
||||
/// Run a plugin command with a JSON payload
|
||||
Run {
|
||||
name: String,
|
||||
command: String,
|
||||
/// JSON payload string passed to the plugin as request.params
|
||||
#[arg(long = "json")]
|
||||
json: String,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Subcommand, Debug, Clone)]
|
||||
enum Command {
|
||||
Completions { #[arg(value_enum)] shell: Shell },
|
||||
Man,
|
||||
Plugins { #[command(subcommand)] cmd: PluginsCmd },
|
||||
}
|
||||
|
||||
#[derive(ValueEnum, Debug, Clone, Copy)]
|
||||
#[value(rename_all = "kebab-case")]
|
||||
enum GpuBackendCli {
|
||||
Auto,
|
||||
Cpu,
|
||||
Cuda,
|
||||
Hip,
|
||||
Vulkan,
|
||||
}
|
||||
|
||||
#[derive(Parser, Debug)]
|
||||
#[command(
|
||||
name = "PolyScribe",
|
||||
bin_name = "polyscribe",
|
||||
version,
|
||||
about = "Merge JSON transcripts or transcribe audio using native whisper"
|
||||
)]
|
||||
struct Args {
|
||||
/// Increase verbosity (-v, -vv). Repeat to increase.
|
||||
/// Debug logs appear with -v; very verbose with -vv. Logs go to stderr.
|
||||
#[arg(short = 'v', long = "verbose", action = clap::ArgAction::Count, global = true)]
|
||||
verbose: u8,
|
||||
|
||||
/// Quiet mode: suppress non-error logging on stderr (overrides -v)
|
||||
/// Does not suppress interactive prompts or stdout output.
|
||||
#[arg(short = 'q', long = "quiet", global = true)]
|
||||
quiet: bool,
|
||||
|
||||
/// Non-interactive mode: never prompt; use defaults instead.
|
||||
#[arg(long = "no-interaction", global = true)]
|
||||
no_interaction: bool,
|
||||
|
||||
/// Disable interactive progress indicators (bars/spinners)
|
||||
#[arg(long = "no-progress", global = true)]
|
||||
no_progress: bool,
|
||||
|
||||
/// Optional subcommands (completions, man, plugins)
|
||||
#[command(subcommand)]
|
||||
cmd: Option<Command>,
|
||||
|
||||
/// Input .json transcript files or audio files to merge/transcribe
|
||||
inputs: Vec<String>,
|
||||
|
||||
/// Output file path base or directory (date prefix added).
|
||||
/// In merge mode: base path.
|
||||
/// In separate mode: directory.
|
||||
/// If omitted: prints JSON to stdout for merge mode; separate mode requires directory for multiple inputs.
|
||||
#[arg(short, long, value_name = "FILE")]
|
||||
output: Option<String>,
|
||||
|
||||
/// Merge all inputs into a single output; if not set, each input is written as a separate output
|
||||
#[arg(short = 'm', long = "merge")]
|
||||
merge: bool,
|
||||
|
||||
/// Merge and also write separate outputs per input; requires -o OUTPUT_DIR
|
||||
#[arg(long = "merge-and-separate")]
|
||||
merge_and_separate: bool,
|
||||
|
||||
/// Prompt for speaker names per input file
|
||||
#[arg(long = "set-speaker-names")]
|
||||
set_speaker_names: bool,
|
||||
|
||||
/// Language code to use for transcription (e.g., en, de). No auto-detection.
|
||||
#[arg(short, long, value_name = "LANG")]
|
||||
language: Option<String>,
|
||||
|
||||
/// Launch interactive model downloader (list HF models, multi-select and download)
|
||||
#[arg(long)]
|
||||
download_models: bool,
|
||||
|
||||
/// Update local Whisper models by comparing hashes/sizes with remote manifest
|
||||
#[arg(long)]
|
||||
update_models: bool,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputRoot {
|
||||
#[serde(default)]
|
||||
segments: Vec<InputSegment>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct InputSegment {
|
||||
start: f64,
|
||||
end: f64,
|
||||
text: String,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize)]
|
||||
struct OutputRoot {
|
||||
items: Vec<OutputEntry>,
|
||||
}
|
||||
|
||||
fn is_json_file(path: &Path) -> bool {
|
||||
matches!(path.extension().and_then(|s| s.to_str()).map(|s| s.to_lowercase()), Some(ext) if ext == "json")
|
||||
}
|
||||
|
||||
fn is_audio_file(path: &Path) -> bool {
|
||||
if let Some(ext) = path.extension().and_then(|s| s.to_str()).map(|s| s.to_lowercase()) {
|
||||
let exts = [
|
||||
"mp3", "wav", "m4a", "mp4", "aac", "flac", "ogg", "wma", "webm", "mkv", "mov", "avi",
|
||||
"m4b", "3gp", "opus", "aiff", "alac",
|
||||
];
|
||||
return exts.contains(&ext.as_str());
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
fn validate_input_path(path: &Path) -> anyhow::Result<()> {
|
||||
let display = path.display();
|
||||
if !path.exists() {
|
||||
return Err(anyhow!("Input not found: {}", display));
|
||||
}
|
||||
let metadata = std::fs::metadata(path).with_context(|| format!("Failed to stat input: {}", display))?;
|
||||
if metadata.is_dir() {
|
||||
return Err(anyhow!("Input is a directory (expected a file): {}", display));
|
||||
}
|
||||
std::fs::File::open(path)
|
||||
.with_context(|| format!("Failed to open input file: {}", display))
|
||||
.map(|_| ())
|
||||
}
|
||||
|
||||
fn sanitize_speaker_name(raw: &str) -> String {
|
||||
if let Some((prefix, rest)) = raw.split_once('-') {
|
||||
if !prefix.is_empty() && prefix.chars().all(|c| c.is_ascii_digit()) {
|
||||
return rest.to_string();
|
||||
fn init_tracing(quiet: bool, verbose: u8) {
|
||||
let level = if quiet {
|
||||
"error"
|
||||
} else {
|
||||
match verbose {
|
||||
0 => "info",
|
||||
1 => "debug",
|
||||
_ => "trace",
|
||||
}
|
||||
}
|
||||
raw.to_string()
|
||||
};
|
||||
|
||||
let filter = EnvFilter::try_from_default_env().unwrap_or_else(|_| EnvFilter::new(level));
|
||||
tracing_subscriber::fmt()
|
||||
.with_env_filter(filter)
|
||||
.with_target(false)
|
||||
.with_level(true)
|
||||
.compact()
|
||||
.init();
|
||||
}
|
||||
|
||||
fn prompt_speaker_name_for_path(
|
||||
_path: &Path,
|
||||
default_name: &str,
|
||||
enabled: bool,
|
||||
) -> String {
|
||||
if !enabled || polyscribe::is_no_interaction() {
|
||||
return sanitize_speaker_name(default_name);
|
||||
}
|
||||
// TODO implement cliclack for this
|
||||
let mut input_line = String::new();
|
||||
match std::io::stdin().read_line(&mut input_line) {
|
||||
Ok(_) => {
|
||||
let trimmed = input_line.trim();
|
||||
if trimmed.is_empty() {
|
||||
sanitize_speaker_name(default_name)
|
||||
} else {
|
||||
sanitize_speaker_name(trimmed)
|
||||
#[tokio::main]
|
||||
async fn main() -> Result<()> {
|
||||
let args = Cli::parse();
|
||||
|
||||
init_tracing(args.quiet, args.verbose);
|
||||
|
||||
let _cfg = ConfigService::load_or_default().context("loading configuration")?;
|
||||
|
||||
match args.command {
|
||||
Commands::Transcribe {
|
||||
output: _output,
|
||||
merge: _merge,
|
||||
merge_and_separate: _merge_and_separate,
|
||||
language: _language,
|
||||
set_speaker_names: _set_speaker_names,
|
||||
gpu_backend,
|
||||
gpu_layers,
|
||||
inputs,
|
||||
} => {
|
||||
info!("starting transcription workflow");
|
||||
let mut progress = ProgressReporter::new(args.no_interaction);
|
||||
|
||||
progress.step("Validating inputs");
|
||||
if inputs.is_empty() {
|
||||
return Err(anyhow!("no inputs provided"));
|
||||
}
|
||||
}
|
||||
Err(_) => sanitize_speaker_name(default_name),
|
||||
}
|
||||
}
|
||||
|
||||
fn handle_plugins(cmd: PluginsCmd) -> Result<()> {
|
||||
match cmd {
|
||||
PluginsCmd::List => {
|
||||
let list = host::discover()?;
|
||||
for p in list {
|
||||
println!("{}\t{}", p.name, p.path.display());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
PluginsCmd::Info { name } => {
|
||||
let p = host::find_plugin_by_name(&name)?;
|
||||
let caps = host::capabilities(&p.path)?;
|
||||
println!("{}", serde_json::to_string_pretty(&caps)?);
|
||||
Ok(())
|
||||
}
|
||||
PluginsCmd::Run { name, command, json } => {
|
||||
let p = host::find_plugin_by_name(&name)?;
|
||||
let params: serde_json::Value = serde_json::from_str(&json).context("--json payload must be valid JSON")?;
|
||||
let mut last_pct = 0u8;
|
||||
let result = host::run_method(&p.path, &command, params, |prog| {
|
||||
// Render minimal progress
|
||||
let stage = prog.stage.as_deref().unwrap_or("");
|
||||
let msg = prog.message.as_deref().unwrap_or("");
|
||||
if prog.pct != last_pct {
|
||||
let _ = cliclack::log::info(format!("[{}%] {} {}", prog.pct, stage, msg).trim());
|
||||
last_pct = prog.pct;
|
||||
progress.step("Selecting backend and preparing model");
|
||||
match gpu_backend {
|
||||
GpuBackend::Auto => {}
|
||||
GpuBackend::Cpu => {}
|
||||
GpuBackend::Cuda => {
|
||||
let _ = gpu_layers;
|
||||
}
|
||||
})?;
|
||||
println!("{}", serde_json::to_string_pretty(&result)?);
|
||||
GpuBackend::Hip => {}
|
||||
GpuBackend::Vulkan => {}
|
||||
}
|
||||
|
||||
progress.finish_with_message("Transcription completed (stub)");
|
||||
Ok(())
|
||||
}
|
||||
|
||||
Commands::Models { cmd } => {
|
||||
match cmd {
|
||||
ModelsCmd::Update => {
|
||||
info!("verifying/updating local models");
|
||||
println!("Models updated (stub).");
|
||||
}
|
||||
ModelsCmd::Download => {
|
||||
info!("interactive model selection and download");
|
||||
println!("Model download complete (stub).");
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
Commands::Plugins { cmd } => {
|
||||
let pm = PluginManager::default();
|
||||
|
||||
match cmd {
|
||||
PluginsCmd::List => {
|
||||
let list = pm.list().context("discovering plugins")?;
|
||||
for item in list {
|
||||
println!("{}", item.name);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
PluginsCmd::Info { name } => {
|
||||
let info = pm.info(&name).with_context(|| format!("getting info for {}", name))?;
|
||||
println!("{}", serde_json::to_string_pretty(&info)?);
|
||||
Ok(())
|
||||
}
|
||||
PluginsCmd::Run { name, command, json } => {
|
||||
let payload = json.unwrap_or_else(|| "{}".to_string());
|
||||
let mut child = pm
|
||||
.spawn(&name, &command)
|
||||
.with_context(|| format!("spawning plugin {name} {command}"))?;
|
||||
|
||||
if let Some(mut stdin) = child.stdin.take() {
|
||||
stdin
|
||||
.write_all(payload.as_bytes())
|
||||
.await
|
||||
.context("writing JSON payload to plugin stdin")?;
|
||||
}
|
||||
|
||||
let status = pm.forward_stdio(&mut child).await?;
|
||||
if !status.success() {
|
||||
error!("plugin returned non-zero exit code: {}", status);
|
||||
return Err(anyhow!("plugin failed"));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Commands::Completions { shell } => {
|
||||
use clap_complete::{generate, shells};
|
||||
use std::io;
|
||||
|
||||
let mut cmd = Cli::command();
|
||||
let name = cmd.get_name().to_string();
|
||||
|
||||
match shell.as_str() {
|
||||
"bash" => generate(shells::Bash, &mut cmd, name, &mut io::stdout()),
|
||||
"zsh" => generate(shells::Zsh, &mut cmd, name, &mut io::stdout()),
|
||||
"fish" => generate(shells::Fish, &mut cmd, name, &mut io::stdout()),
|
||||
"powershell" => generate(shells::PowerShell, &mut cmd, name, &mut io::stdout()),
|
||||
"elvish" => generate(shells::Elvish, &mut cmd, name, &mut io::stdout()),
|
||||
_ => return Err(anyhow!("unsupported shell: {shell}")),
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
Commands::Man => {
|
||||
use clap_mangen::Man;
|
||||
let cmd = Cli::command();
|
||||
let man = Man::new(cmd);
|
||||
man.render(&mut std::io::stdout())?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn main() -> Result<()> {
|
||||
let args = Args::parse();
|
||||
|
||||
// Initialize runtime flags for the library
|
||||
polyscribe::set_verbose(args.verbose);
|
||||
polyscribe::set_quiet(args.quiet);
|
||||
polyscribe::set_no_interaction(args.no_interaction);
|
||||
polyscribe::set_no_progress(args.no_progress);
|
||||
|
||||
// Handle subcommands
|
||||
if let Some(cmd) = &args.cmd {
|
||||
match cmd.clone() {
|
||||
Command::Completions { shell } => {
|
||||
let mut cmd = Args::command();
|
||||
let bin_name = cmd.get_name().to_string();
|
||||
clap_complete::generate(shell, &mut cmd, bin_name, &mut io::stdout());
|
||||
return Ok(());
|
||||
}
|
||||
Command::Man => {
|
||||
let cmd = Args::command();
|
||||
let man = clap_mangen::Man::new(cmd);
|
||||
let mut man_bytes = Vec::new();
|
||||
man.render(&mut man_bytes)?;
|
||||
io::stdout().write_all(&man_bytes)?;
|
||||
return Ok(());
|
||||
}
|
||||
Command::Plugins { cmd } => {
|
||||
return handle_plugins(cmd);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Optional model management actions
|
||||
if args.download_models {
|
||||
if let Err(err) = polyscribe::models::run_interactive_model_downloader() {
|
||||
polyscribe::elog!("Model downloader failed: {:#}", err);
|
||||
}
|
||||
if args.inputs.is_empty() {
|
||||
return Ok(())
|
||||
}
|
||||
}
|
||||
if args.update_models {
|
||||
if let Err(err) = polyscribe::models::update_local_models() {
|
||||
polyscribe::elog!("Model update failed: {:#}", err);
|
||||
return Err(err);
|
||||
}
|
||||
if args.inputs.is_empty() {
|
||||
return Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
// Process inputs
|
||||
let mut inputs = args.inputs;
|
||||
if inputs.is_empty() {
|
||||
return Err(anyhow!("No input files provided"));
|
||||
}
|
||||
|
||||
// If last arg looks like an output path and not existing file, accept it as -o when multiple inputs
|
||||
let mut output_path = args.output;
|
||||
if output_path.is_none() && inputs.len() >= 2 {
|
||||
if let Some(candidate_output) = inputs.last().cloned() {
|
||||
if !Path::new(&candidate_output).exists() {
|
||||
inputs.pop();
|
||||
output_path = Some(candidate_output);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Validate inputs; allow JSON and audio. For audio, require --language.
|
||||
for input_arg in &inputs {
|
||||
let path_ref = Path::new(input_arg);
|
||||
validate_input_path(path_ref)?;
|
||||
if !(is_json_file(path_ref) || is_audio_file(path_ref)) {
|
||||
return Err(anyhow!(
|
||||
"Unsupported input type (expected .json transcript or audio media): {}",
|
||||
path_ref.display()
|
||||
));
|
||||
}
|
||||
if is_audio_file(path_ref) && args.language.is_none() {
|
||||
return Err(anyhow!("Please specify --language (e.g., --language en). Language detection was removed."));
|
||||
}
|
||||
}
|
||||
|
||||
// Derive speakers (prompt if requested)
|
||||
let speakers: Vec<String> = inputs
|
||||
.iter()
|
||||
.map(|input_path| {
|
||||
let path = Path::new(input_path);
|
||||
let default_speaker = sanitize_speaker_name(
|
||||
path.file_stem().and_then(|s| s.to_str()).unwrap_or("speaker"),
|
||||
);
|
||||
prompt_speaker_name_for_path(path, &default_speaker, args.set_speaker_names)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// MERGE-AND-SEPARATE mode
|
||||
if args.merge_and_separate {
|
||||
polyscribe::dlog!(1, "Mode: merge-and-separate; output_dir={:?}", output_path);
|
||||
let out_dir = match output_path.as_ref() {
|
||||
Some(p) => PathBuf::from(p),
|
||||
None => return Err(anyhow!("--merge-and-separate requires -o OUTPUT_DIR")),
|
||||
};
|
||||
if !out_dir.as_os_str().is_empty() {
|
||||
create_dir_all(&out_dir).with_context(|| {
|
||||
format!("Failed to create output directory: {}", out_dir.display())
|
||||
})?;
|
||||
}
|
||||
|
||||
let mut merged_entries: Vec<OutputEntry> = Vec::new();
|
||||
for (idx, input_path) in inputs.iter().enumerate() {
|
||||
let path = Path::new(input_path);
|
||||
let speaker = speakers[idx].clone();
|
||||
// Decide based on input type (JSON transcript vs audio to transcribe)
|
||||
// TODO remove duplicate
|
||||
let mut entries: Vec<OutputEntry> = if is_json_file(path) {
|
||||
let mut buf = String::new();
|
||||
File::open(path)
|
||||
.with_context(|| format!("Failed to open: {input_path}"))?
|
||||
.read_to_string(&mut buf)
|
||||
.with_context(|| format!("Failed to read: {input_path}"))?;
|
||||
let root: InputRoot = serde_json::from_str(&buf)
|
||||
.with_context(|| format!("Invalid JSON transcript parsed from {input_path}"))?;
|
||||
root
|
||||
.segments
|
||||
.into_iter()
|
||||
.map(|seg| OutputEntry { id: 0, speaker: speaker.clone(), start: seg.start, end: seg.end, text: seg.text })
|
||||
.collect()
|
||||
} else {
|
||||
let lang_norm: Option<String> = args.language.as_deref().and_then(|s| normalize_lang_code(s));
|
||||
let selected_backend = polyscribe::backend::select_backend(polyscribe::backend::BackendKind::Auto, args.verbose > 0)?;
|
||||
selected_backend.backend.transcribe(path, &speaker, lang_norm.as_deref(), None, None)?
|
||||
};
|
||||
// Sort and id per-file
|
||||
// TODO remove duplicate
|
||||
entries.sort_by(|a, b| a.start.partial_cmp(&b.start).unwrap_or(std::cmp::Ordering::Equal)
|
||||
.then(a.end.partial_cmp(&b.end).unwrap_or(std::cmp::Ordering::Equal)));
|
||||
for (i, entry) in entries.iter_mut().enumerate() { entry.id = i as u64; }
|
||||
// Write per-file outputs
|
||||
let stem = path.file_stem().and_then(|s| s.to_str()).unwrap_or("output");
|
||||
let date = date_prefix();
|
||||
let base_name = format!("{date}_{stem}");
|
||||
let json_path = out_dir.join(format!("{}.json", &base_name));
|
||||
let toml_path = out_dir.join(format!("{}.toml", &base_name));
|
||||
let srt_path = out_dir.join(format!("{}.srt", &base_name));
|
||||
|
||||
let output_bundle = OutputRoot { items: entries.clone() };
|
||||
let mut json_file = File::create(&json_path).with_context(|| format!("Failed to create output file: {}", json_path.display()))?;
|
||||
serde_json::to_writer_pretty(&mut json_file, &output_bundle)?; writeln!(&mut json_file)?;
|
||||
let toml_str = toml::to_string_pretty(&output_bundle)?;
|
||||
let mut toml_file = File::create(&toml_path).with_context(|| format!("Failed to create output file: {}", toml_path.display()))?;
|
||||
toml_file.write_all(toml_str.as_bytes())?; if !toml_str.ends_with('\n') { writeln!(&mut toml_file)?; }
|
||||
let srt_str = render_srt(&output_bundle.items);
|
||||
let mut srt_file = File::create(&srt_path).with_context(|| format!("Failed to create output file: {}", srt_path.display()))?;
|
||||
srt_file.write_all(srt_str.as_bytes())?;
|
||||
|
||||
merged_entries.extend(output_bundle.items.into_iter());
|
||||
}
|
||||
// Write merged outputs into out_dir
|
||||
// TODO remove duplicate
|
||||
merged_entries.sort_by(|a, b| a.start.partial_cmp(&b.start).unwrap_or(std::cmp::Ordering::Equal)
|
||||
.then(a.end.partial_cmp(&b.end).unwrap_or(std::cmp::Ordering::Equal)));
|
||||
for (index, entry) in merged_entries.iter_mut().enumerate() { entry.id = index as u64; }
|
||||
let merged_output = OutputRoot { items: merged_entries };
|
||||
let date = date_prefix();
|
||||
let merged_base = format!("{date}_merged");
|
||||
let merged_json_path = out_dir.join(format!("{}.json", &merged_base));
|
||||
let merged_toml_path = out_dir.join(format!("{}.toml", &merged_base));
|
||||
let merged_srt_path = out_dir.join(format!("{}.srt", &merged_base));
|
||||
let mut merged_json_file = File::create(&merged_json_path).with_context(|| format!("Failed to create output file: {}", merged_json_path.display()))?;
|
||||
serde_json::to_writer_pretty(&mut merged_json_file, &merged_output)?; writeln!(&mut merged_json_file)?;
|
||||
let merged_toml_str = toml::to_string_pretty(&merged_output)?;
|
||||
let mut merged_toml_file = File::create(&merged_toml_path).with_context(|| format!("Failed to create output file: {}", merged_toml_path.display()))?;
|
||||
merged_toml_file.write_all(merged_toml_str.as_bytes())?; if !merged_toml_str.ends_with('\n') { writeln!(&mut merged_toml_file)?; }
|
||||
let merged_srt_str = render_srt(&merged_output.items);
|
||||
let mut merged_srt_file = File::create(&merged_srt_path).with_context(|| format!("Failed to create output file: {}", merged_srt_path.display()))?;
|
||||
merged_srt_file.write_all(merged_srt_str.as_bytes())?;
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
// MERGE mode
|
||||
if args.merge {
|
||||
polyscribe::dlog!(1, "Mode: merge; output_base={:?}", output_path);
|
||||
let mut entries: Vec<OutputEntry> = Vec::new();
|
||||
for (index, input_path) in inputs.iter().enumerate() {
|
||||
let path = Path::new(input_path);
|
||||
let speaker = speakers[index].clone();
|
||||
if is_json_file(path) {
|
||||
let mut buf = String::new();
|
||||
File::open(path)
|
||||
.with_context(|| format!("Failed to open: {}", input_path))?
|
||||
.read_to_string(&mut buf)
|
||||
.with_context(|| format!("Failed to read: {}", input_path))?;
|
||||
let root: InputRoot = serde_json::from_str(&buf)
|
||||
.with_context(|| format!("Invalid JSON transcript parsed from {}", input_path))?;
|
||||
for seg in root.segments {
|
||||
entries.push(OutputEntry { id: 0, speaker: speaker.clone(), start: seg.start, end: seg.end, text: seg.text });
|
||||
}
|
||||
} else {
|
||||
let lang_norm: Option<String> = args.language.as_deref().and_then(|s| normalize_lang_code(s));
|
||||
let selected_backend = polyscribe::backend::select_backend(polyscribe::backend::BackendKind::Auto, args.verbose > 0)?;
|
||||
let mut new_entries = selected_backend.backend.transcribe(path, &speaker, lang_norm.as_deref(), None, None)?;
|
||||
entries.append(&mut new_entries);
|
||||
}
|
||||
}
|
||||
// TODO remove duplicate
|
||||
entries.sort_by(|a, b| a.start.partial_cmp(&b.start).unwrap_or(std::cmp::Ordering::Equal)
|
||||
.then(a.end.partial_cmp(&b.end).unwrap_or(std::cmp::Ordering::Equal)));
|
||||
for (i, entry) in entries.iter_mut().enumerate() { entry.id = i as u64; }
|
||||
let output_bundle = OutputRoot { items: entries };
|
||||
|
||||
if let Some(path) = output_path {
|
||||
let base_path = Path::new(&path);
|
||||
let parent_opt = base_path.parent();
|
||||
if let Some(parent) = parent_opt {
|
||||
if !parent.as_os_str().is_empty() {
|
||||
create_dir_all(parent).with_context(|| {
|
||||
format!("Failed to create parent directory for output: {}", parent.display())
|
||||
})?;
|
||||
}
|
||||
}
|
||||
let stem = base_path.file_stem().and_then(|s| s.to_str()).unwrap_or("output");
|
||||
let date = date_prefix();
|
||||
let base_name = format!("{}_{}", date, stem);
|
||||
let dir = parent_opt.unwrap_or(Path::new(""));
|
||||
let json_path = dir.join(format!("{}.json", &base_name));
|
||||
let toml_path = dir.join(format!("{}.toml", &base_name));
|
||||
let srt_path = dir.join(format!("{}.srt", &base_name));
|
||||
|
||||
let mut json_file = File::create(&json_path).with_context(|| format!("Failed to create output file: {}", json_path.display()))?;
|
||||
serde_json::to_writer_pretty(&mut json_file, &output_bundle)?; writeln!(&mut json_file)?;
|
||||
let toml_str = toml::to_string_pretty(&output_bundle)?;
|
||||
let mut toml_file = File::create(&toml_path).with_context(|| format!("Failed to create output file: {}", toml_path.display()))?;
|
||||
toml_file.write_all(toml_str.as_bytes())?; if !toml_str.ends_with('\n') { writeln!(&mut toml_file)?; }
|
||||
let srt_str = render_srt(&output_bundle.items);
|
||||
let mut srt_file = File::create(&srt_path).with_context(|| format!("Failed to create output file: {}", srt_path.display()))?;
|
||||
srt_file.write_all(srt_str.as_bytes())?;
|
||||
} else {
|
||||
let stdout = io::stdout();
|
||||
let mut handle = stdout.lock();
|
||||
serde_json::to_writer_pretty(&mut handle, &output_bundle)?; writeln!(&mut handle)?;
|
||||
}
|
||||
return Ok(());
|
||||
}
|
||||
|
||||
// SEPARATE (default)
|
||||
polyscribe::dlog!(1, "Mode: separate; output_dir={:?}", output_path);
|
||||
if output_path.is_none() && inputs.len() > 1 {
|
||||
return Err(anyhow!("Multiple inputs without --merge require -o OUTPUT_DIR to write separate files"));
|
||||
}
|
||||
let out_dir: Option<PathBuf> = output_path.as_ref().map(PathBuf::from);
|
||||
if let Some(dir) = &out_dir {
|
||||
if !dir.as_os_str().is_empty() {
|
||||
create_dir_all(dir).with_context(|| format!("Failed to create output directory: {}", dir.display()))?;
|
||||
}
|
||||
}
|
||||
|
||||
for (index, input_path) in inputs.iter().enumerate() {
|
||||
let path = Path::new(input_path);
|
||||
let speaker = speakers[index].clone();
|
||||
// TODO remove duplicate
|
||||
let mut entries: Vec<OutputEntry> = if is_json_file(path) {
|
||||
let mut buf = String::new();
|
||||
File::open(path)
|
||||
.with_context(|| format!("Failed to open: {input_path}"))?
|
||||
.read_to_string(&mut buf)
|
||||
.with_context(|| format!("Failed to read: {input_path}"))?;
|
||||
let root: InputRoot = serde_json::from_str(&buf)
|
||||
.with_context(|| format!("Invalid JSON transcript parsed from {input_path}"))?;
|
||||
root
|
||||
.segments
|
||||
.into_iter()
|
||||
.map(|seg| OutputEntry { id: 0, speaker: speaker.clone(), start: seg.start, end: seg.end, text: seg.text })
|
||||
.collect()
|
||||
} else {
|
||||
let lang_norm: Option<String> = args.language.as_deref().and_then(|s| normalize_lang_code(s));
|
||||
let selected_backend = polyscribe::backend::select_backend(polyscribe::backend::BackendKind::Auto, args.verbose > 0)?;
|
||||
selected_backend.backend.transcribe(path, &speaker, lang_norm.as_deref(), None, None)?
|
||||
};
|
||||
// TODO remove duplicate
|
||||
entries.sort_by(|a, b| a.start.partial_cmp(&b.start).unwrap_or(std::cmp::Ordering::Equal)
|
||||
.then(a.end.partial_cmp(&b.end).unwrap_or(std::cmp::Ordering::Equal)));
|
||||
for (i, entry) in entries.iter_mut().enumerate() { entry.id = i as u64; }
|
||||
|
||||
let stem = path.file_stem().and_then(|s| s.to_str()).unwrap_or("output");
|
||||
let date = date_prefix();
|
||||
let base_name = format!("{date}_{stem}");
|
||||
if let Some(dir) = &out_dir {
|
||||
let json_path = dir.join(format!("{}.json", &base_name));
|
||||
let toml_path = dir.join(format!("{}.toml", &base_name));
|
||||
let srt_path = dir.join(format!("{}.srt", &base_name));
|
||||
let output_bundle = OutputRoot { items: entries };
|
||||
let mut json_file = File::create(&json_path).with_context(|| format!("Failed to create output file: {}", json_path.display()))?;
|
||||
serde_json::to_writer_pretty(&mut json_file, &output_bundle)?; writeln!(&mut json_file)?;
|
||||
let toml_str = toml::to_string_pretty(&output_bundle)?;
|
||||
let mut toml_file = File::create(&toml_path).with_context(|| format!("Failed to create output file: {}", toml_path.display()))?;
|
||||
toml_file.write_all(toml_str.as_bytes())?; if !toml_str.ends_with('\n') { writeln!(&mut toml_file)?; }
|
||||
let srt_str = render_srt(&output_bundle.items);
|
||||
let mut srt_file = File::create(&srt_path).with_context(|| format!("Failed to create output file: {}", srt_path.display()))?;
|
||||
srt_file.write_all(srt_str.as_bytes())?;
|
||||
} else {
|
||||
// In separate mode with single input and no output dir, print JSON to stdout
|
||||
let stdout = io::stdout();
|
||||
let mut handle = stdout.lock();
|
||||
let output_bundle = OutputRoot { items: entries };
|
||||
serde_json::to_writer_pretty(&mut handle, &output_bundle)?; writeln!(&mut handle)?;
|
||||
}
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
@@ -3,8 +3,9 @@
|
||||
|
||||
use std::process::Command;
|
||||
|
||||
fn bin() -> &'static str {
|
||||
env!("CARGO_BIN_EXE_polyscribe")
|
||||
fn bin() -> String {
|
||||
std::env::var("CARGO_BIN_EXE_polyscribe")
|
||||
.unwrap_or_else(|_| "polyscribe".to_string())
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -1,32 +1,16 @@
|
||||
[package]
|
||||
name = "polyscribe"
|
||||
name = "polyscribe-core"
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
license = "MIT"
|
||||
|
||||
[features]
|
||||
# Default: CPU only; no GPU features enabled
|
||||
default = []
|
||||
# GPU backends map to whisper-rs features or FFI stub for Vulkan
|
||||
gpu-cuda = ["whisper-rs/cuda"]
|
||||
gpu-hip = ["whisper-rs/hipblas"]
|
||||
gpu-vulkan = []
|
||||
# explicit CPU fallback feature (no effect at build time, used for clarity)
|
||||
cpu-fallback = []
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.98"
|
||||
anyhow = "1.0.99"
|
||||
thiserror = "1.0.69"
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = "1.0.142"
|
||||
toml = "0.8"
|
||||
chrono = { version = "0.4", features = ["clock"] }
|
||||
sha2 = "0.10"
|
||||
whisper-rs = { git = "https://github.com/tazz4843/whisper-rs" }
|
||||
libc = "0.2"
|
||||
cliclack = "0.3"
|
||||
indicatif = "0.17"
|
||||
thiserror = "1"
|
||||
directories = "5"
|
||||
|
||||
[build-dependencies]
|
||||
# no special build deps
|
||||
toml = "0.8.23"
|
||||
directories = "5.0.1"
|
||||
chrono = "0.4.41"
|
||||
libc = "0.2.175"
|
||||
whisper-rs = "0.14.3"
|
||||
indicatif = "0.17.11"
|
||||
|
||||
@@ -1,149 +1,108 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Simple ConfigService with XDG/system/workspace merge and atomic writes
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use directories::BaseDirs;
|
||||
use crate::prelude::*;
|
||||
use directories::ProjectDirs;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use std::env;
|
||||
use std::fs;
|
||||
use std::io::Write;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::{fs, path::PathBuf};
|
||||
|
||||
/// Generic configuration represented as TOML table
|
||||
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
|
||||
pub struct Config(pub toml::value::Table);
|
||||
const ENV_PREFIX: &str = "POLYSCRIBE";
|
||||
|
||||
impl Config {
|
||||
/// Get a mutable reference to a top-level table under the given key, creating
|
||||
/// an empty table if it does not exist yet.
|
||||
pub fn get_table_mut(&mut self, key: &str) -> &mut toml::value::Table {
|
||||
let needs_init = !matches!(self.0.get(key), Some(toml::Value::Table(_)));
|
||||
if needs_init {
|
||||
self.0.insert(key.to_string(), toml::Value::Table(Default::default()));
|
||||
}
|
||||
match self.0.get_mut(key) {
|
||||
Some(toml::Value::Table(t)) => t,
|
||||
_ => unreachable!(),
|
||||
/// Configuration for the Polyscribe application
|
||||
///
|
||||
/// Contains paths to models and plugins directories that can be customized
|
||||
/// through configuration files or environment variables.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Config {
|
||||
/// Directory path where ML models are stored
|
||||
pub models_dir: Option<PathBuf>,
|
||||
/// Directory path where plugins are stored
|
||||
pub plugins_dir: Option<PathBuf>,
|
||||
}
|
||||
|
||||
impl Default for Config {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
models_dir: None,
|
||||
plugins_dir: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn merge_tables(base: &mut toml::value::Table, overlay: &toml::value::Table) {
|
||||
for (k, v) in overlay.iter() {
|
||||
match (base.get_mut(k), v) {
|
||||
(Some(toml::Value::Table(bsub)), toml::Value::Table(osub)) => {
|
||||
merge_tables(bsub, osub);
|
||||
}
|
||||
_ => {
|
||||
base.insert(k.clone(), v.clone());
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn read_toml(path: &Path) -> Result<toml::value::Table> {
|
||||
let s = fs::read_to_string(path).with_context(|| format!("Failed to read config: {}", path.display()))?;
|
||||
let v: toml::Value = toml::from_str(&s).with_context(|| format!("Invalid TOML in {}", path.display()))?;
|
||||
Ok(v.as_table().cloned().unwrap_or_default())
|
||||
}
|
||||
|
||||
fn write_toml_atomic(path: &Path, tbl: &toml::value::Table) -> Result<()> {
|
||||
if let Some(parent) = path.parent() {
|
||||
fs::create_dir_all(parent).with_context(|| format!("Failed to create config dir: {}", parent.display()))?;
|
||||
}
|
||||
let tmp = path.with_extension("tmp");
|
||||
let mut f = fs::File::create(&tmp).with_context(|| format!("Failed to create temp file: {}", tmp.display()))?;
|
||||
let s = toml::to_string_pretty(&toml::Value::Table(tbl.clone()))?;
|
||||
f.write_all(s.as_bytes())?;
|
||||
if !s.ends_with('\n') { f.write_all(b"\n")?; }
|
||||
drop(f);
|
||||
fs::rename(&tmp, path).with_context(|| format!("Failed to atomically replace config: {}", path.display()))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn system_config_path() -> PathBuf {
|
||||
if cfg!(unix) { PathBuf::from("/etc").join("polyscribe").join("config.toml") } else { default_user_config_path() }
|
||||
}
|
||||
|
||||
fn default_user_config_path() -> PathBuf {
|
||||
if let Some(base) = BaseDirs::new() {
|
||||
return PathBuf::from(base.config_dir()).join("polyscribe").join("config.toml");
|
||||
}
|
||||
PathBuf::from(".polyscribe").join("config.toml")
|
||||
}
|
||||
|
||||
fn workspace_config_path() -> PathBuf {
|
||||
PathBuf::from(".polyscribe").join("config.toml")
|
||||
}
|
||||
|
||||
/// Service responsible for loading and saving PolyScribe configuration
|
||||
#[derive(Debug, Default, Clone)]
|
||||
/// Service for managing Polyscribe configuration
|
||||
///
|
||||
/// Provides functionality to load, save, and access configuration settings
|
||||
/// from disk or environment variables.
|
||||
pub struct ConfigService;
|
||||
|
||||
impl ConfigService {
|
||||
/// Load configuration, merging system < user < workspace < env overrides.
|
||||
pub fn load(&self) -> Result<Config> {
|
||||
let mut accum = toml::value::Table::default();
|
||||
let sys = system_config_path();
|
||||
if sys.exists() {
|
||||
merge_tables(&mut accum, &read_toml(&sys)?);
|
||||
}
|
||||
let user = default_user_config_path();
|
||||
if user.exists() {
|
||||
merge_tables(&mut accum, &read_toml(&user)?);
|
||||
}
|
||||
let ws = workspace_config_path();
|
||||
if ws.exists() {
|
||||
merge_tables(&mut accum, &read_toml(&ws)?);
|
||||
}
|
||||
// Env overrides: POLYSCRIBE__SECTION__KEY=value
|
||||
let mut env_over = toml::value::Table::default();
|
||||
for (k, v) in env::vars() {
|
||||
if let Some(rest) = k.strip_prefix("POLYSCRIBE__") {
|
||||
let parts: Vec<&str> = rest.split("__").collect();
|
||||
if parts.is_empty() { continue; }
|
||||
let val: toml::Value = toml::Value::String(v);
|
||||
// Build nested tables
|
||||
let mut current = &mut env_over;
|
||||
for (i, part) in parts.iter().enumerate() {
|
||||
if i == parts.len() - 1 {
|
||||
current.insert(part.to_lowercase(), val.clone());
|
||||
} else {
|
||||
current = current.entry(part.to_lowercase()).or_insert_with(|| toml::Value::Table(Default::default()))
|
||||
.as_table_mut().expect("table");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
merge_tables(&mut accum, &env_over);
|
||||
Ok(Config(accum))
|
||||
/// Loads configuration from disk or returns default values if not found
|
||||
///
|
||||
/// This function attempts to read the configuration file from disk. If the file
|
||||
/// doesn't exist or can't be parsed, it falls back to default values.
|
||||
/// Environment variable overrides are then applied to the configuration.
|
||||
pub fn load_or_default() -> Result<Config> {
|
||||
let mut cfg = Self::read_disk().unwrap_or_default();
|
||||
Self::apply_env_overrides(&mut cfg)?;
|
||||
Ok(cfg)
|
||||
}
|
||||
|
||||
/// Ensure user config exists with sensible defaults, return loaded config
|
||||
pub fn ensure_user_config(&self) -> Result<Config> {
|
||||
let path = default_user_config_path();
|
||||
if !path.exists() {
|
||||
let mut defaults = toml::value::Table::default();
|
||||
defaults.insert("ui".into(), toml::Value::Table({
|
||||
let mut t = toml::value::Table::default();
|
||||
t.insert("theme".into(), toml::Value::String("auto".into()));
|
||||
t
|
||||
}));
|
||||
write_toml_atomic(&path, &defaults)?;
|
||||
/// Saves the configuration to disk
|
||||
///
|
||||
/// This function serializes the configuration to TOML format and writes it
|
||||
/// to the standard configuration directory for the application.
|
||||
/// Returns an error if writing fails or if project directories cannot be determined.
|
||||
pub fn save(cfg: &Config) -> Result<()> {
|
||||
let Some(dirs) = Self::dirs() else {
|
||||
return Err(Error::Other("unable to get project dirs".into()));
|
||||
};
|
||||
let cfg_dir = dirs.config_dir();
|
||||
fs::create_dir_all(cfg_dir)?;
|
||||
let path = cfg_dir.join("config.toml");
|
||||
let s = toml::to_string_pretty(cfg)?;
|
||||
fs::write(path, s)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn read_disk() -> Option<Config> {
|
||||
let dirs = Self::dirs()?;
|
||||
let path = dirs.config_dir().join("config.toml");
|
||||
let s = fs::read_to_string(path).ok()?;
|
||||
toml::from_str(&s).ok()
|
||||
}
|
||||
|
||||
fn apply_env_overrides(cfg: &mut Config) -> Result<()> {
|
||||
// POLYSCRIBE__SECTION__KEY format reserved for future nested config.
|
||||
if let Ok(v) = std::env::var(format!("{ENV_PREFIX}_MODELS_DIR")) {
|
||||
cfg.models_dir = Some(PathBuf::from(v));
|
||||
}
|
||||
self.load()
|
||||
if let Ok(v) = std::env::var(format!("{ENV_PREFIX}_PLUGINS_DIR")) {
|
||||
cfg.plugins_dir = Some(PathBuf::from(v));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Save to user config atomically, merging over existing user file.
|
||||
pub fn save_user(&self, new_values: &toml::value::Table) -> Result<()> {
|
||||
let path = default_user_config_path();
|
||||
let mut base = if path.exists() { read_toml(&path)? } else { Default::default() };
|
||||
merge_tables(&mut base, new_values);
|
||||
write_toml_atomic(&path, &base)
|
||||
/// Returns the standard project directories for the application
|
||||
///
|
||||
/// This function creates a ProjectDirs instance with the appropriate
|
||||
/// organization and application names for Polyscribe.
|
||||
/// Returns None if the project directories cannot be determined.
|
||||
pub fn dirs() -> Option<ProjectDirs> {
|
||||
ProjectDirs::from("dev", "polyscribe", "polyscribe")
|
||||
}
|
||||
|
||||
/// Paths used for debugging/information
|
||||
pub fn paths(&self) -> (PathBuf, PathBuf, PathBuf) {
|
||||
(system_config_path(), default_user_config_path(), workspace_config_path())
|
||||
/// Returns the default directory path for storing ML models
|
||||
///
|
||||
/// This function determines the standard data directory for the application
|
||||
/// and appends a 'models' subdirectory to it.
|
||||
/// Returns None if the project directories cannot be determined.
|
||||
pub fn default_models_dir() -> Option<PathBuf> {
|
||||
Self::dirs().map(|d| d.data_dir().join("models"))
|
||||
}
|
||||
|
||||
/// Returns the default directory path for storing plugins
|
||||
///
|
||||
/// This function determines the standard data directory for the application
|
||||
/// and appends a 'plugins' subdirectory to it.
|
||||
/// Returns None if the project directories cannot be determined.
|
||||
pub fn default_plugins_dir() -> Option<PathBuf> {
|
||||
Self::dirs().map(|d| d.data_dir().join("plugins"))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,39 +1,39 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
|
||||
use thiserror::Error;
|
||||
|
||||
/// The common error type for the polyscribe core crate.
|
||||
/// Add more domain-specific variants as needed.
|
||||
#[derive(Debug, Error)]
|
||||
/// Error types for the polyscribe-core crate.
|
||||
///
|
||||
/// This enum represents various error conditions that can occur during
|
||||
/// operations in this crate, including I/O errors, serialization/deserialization
|
||||
/// errors, and environment variable access errors.
|
||||
pub enum Error {
|
||||
/// Wrapper for any boxed dynamic error. Useful as a temporary catch-all.
|
||||
#[error("anyhow error: {0}")]
|
||||
Anyhow(#[from] anyhow::Error),
|
||||
|
||||
/// IO-related error.
|
||||
#[error("io error: {0}")]
|
||||
#[error("I/O error: {0}")]
|
||||
/// Represents an I/O error that occurred during file or stream operations
|
||||
Io(#[from] std::io::Error),
|
||||
|
||||
/// UTF-8 conversion error.
|
||||
#[error("utf8 error: {0}")]
|
||||
Utf8(#[from] std::string::FromUtf8Error),
|
||||
#[error("serde error: {0}")]
|
||||
/// Represents a JSON serialization or deserialization error
|
||||
Serde(#[from] serde_json::Error),
|
||||
|
||||
#[error("toml error: {0}")]
|
||||
/// Represents a TOML deserialization error
|
||||
Toml(#[from] toml::de::Error),
|
||||
|
||||
#[error("toml ser error: {0}")]
|
||||
/// Represents a TOML serialization error
|
||||
TomlSer(#[from] toml::ser::Error),
|
||||
|
||||
/// Environment variable error.
|
||||
#[error("env var error: {0}")]
|
||||
Var(#[from] std::env::VarError),
|
||||
/// Represents an error that occurred during environment variable access
|
||||
EnvVar(#[from] std::env::VarError),
|
||||
|
||||
/// TOML de serialization error.
|
||||
#[error("toml de error: {0}")]
|
||||
TomlDe(#[from] toml::de::Error),
|
||||
|
||||
/// Configuration parsing error.
|
||||
#[error("configuration error: {0}")]
|
||||
Config(String),
|
||||
|
||||
/// Placeholder for not-yet-implemented backends or features.
|
||||
#[error("unimplemented: {0}")]
|
||||
Unimplemented(&'static str),
|
||||
#[error("other: {0}")]
|
||||
/// Represents a general error condition with a custom message
|
||||
Other(String),
|
||||
}
|
||||
|
||||
/// Convenient result alias for the polyscribe core crate.
|
||||
pub type Result<T> = std::result::Result<T, Error>;
|
||||
impl From<anyhow::Error> for Error {
|
||||
fn from(e: anyhow::Error) -> Self {
|
||||
Error::Other(e.to_string())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -192,20 +192,17 @@ macro_rules! qlog {
|
||||
($($arg:tt)*) => {{ $crate::ilog!($($arg)*); }}
|
||||
}
|
||||
|
||||
/// Re-export backend module (GPU/CPU selection and transcription).
|
||||
pub mod backend;
|
||||
/// Re-export models module (model listing/downloading/updating).
|
||||
pub mod models;
|
||||
/// Configuration service (XDG + atomic writes)
|
||||
/// Configuration handling for PolyScribe
|
||||
pub mod config;
|
||||
/// UI helpers
|
||||
// Use the file-backed ui.rs module, which also declares its own `progress` submodule.
|
||||
pub mod ui;
|
||||
/// Error types for the crate.
|
||||
/// Error definitions for the PolyScribe library
|
||||
pub mod error;
|
||||
pub use error::Error;
|
||||
pub mod prelude;
|
||||
|
||||
pub use error::{Error, Result as OtherResult};
|
||||
|
||||
/// Transcript entry for a single segment.
|
||||
#[derive(Debug, serde::Serialize, Clone)]
|
||||
pub struct OutputEntry {
|
||||
|
||||
@@ -88,9 +88,10 @@ pub fn run_interactive_model_downloader() -> Result<()> {
|
||||
}
|
||||
|
||||
let answer = ui::prompt_input("Your selection", Some("1"))?;
|
||||
let selection_raw = match answer {
|
||||
Some(s) => s.trim().to_string(),
|
||||
None => "1".to_string(),
|
||||
let selection_raw = if answer.trim().is_empty() {
|
||||
"1".to_string()
|
||||
} else {
|
||||
answer.trim().to_string()
|
||||
};
|
||||
let selection = if selection_raw.is_empty() { "1" } else { &selection_raw };
|
||||
|
||||
|
||||
@@ -4,10 +4,13 @@
|
||||
|
||||
pub use crate::backend::*;
|
||||
pub use crate::config::*;
|
||||
pub use crate::error::{Error, Result};
|
||||
pub use crate::error::Error;
|
||||
pub use crate::models::*;
|
||||
|
||||
// If you frequently use UI helpers across binaries/tests, export them too.
|
||||
// Keep this lean to avoid pulling UI everywhere unintentionally.
|
||||
#[allow(unused_imports)]
|
||||
pub use crate::ui::*;
|
||||
|
||||
/// A convenient alias for `std::result::Result` with the error type defaulting to [`Error`].
|
||||
pub type Result<T, E = Error> = std::result::Result<T, E>;
|
||||
|
||||
@@ -1,87 +1,64 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2025 <COPYRIGHT HOLDER>. All rights reserved.
|
||||
|
||||
//! Centralized UI helpers (TTY-aware, quiet/verbose-aware)
|
||||
//! Minimal UI helpers used across the core crate.
|
||||
//! This keeps interactive bits centralized and easy to stub in tests.
|
||||
|
||||
use std::io;
|
||||
/// Progress indicators and reporting tools for displaying task completion.
|
||||
pub mod progress;
|
||||
|
||||
/// Startup intro/banner (suppressed when quiet).
|
||||
pub fn intro(msg: impl AsRef<str>) {
|
||||
let _ = cliclack::intro(msg.as_ref());
|
||||
}
|
||||
use std::io::{self, Write};
|
||||
|
||||
/// Final outro/summary printed below any progress indicators (suppressed when quiet).
|
||||
pub fn outro(msg: impl AsRef<str>) {
|
||||
let _ = cliclack::outro(msg.as_ref());
|
||||
}
|
||||
|
||||
/// Info message (TTY-aware; suppressed by --quiet is handled by outer callers if needed)
|
||||
/// Print an informational line to stderr (suppressed when quiet mode is enabled by callers).
|
||||
pub fn info(msg: impl AsRef<str>) {
|
||||
let _ = cliclack::log::info(msg.as_ref());
|
||||
eprintln!("{}", msg.as_ref());
|
||||
}
|
||||
|
||||
/// Print a warning (always printed).
|
||||
/// Print a warning line to stderr.
|
||||
pub fn warn(msg: impl AsRef<str>) {
|
||||
// cliclack provides a warning-level log utility
|
||||
let _ = cliclack::log::warning(msg.as_ref());
|
||||
eprintln!("WARNING: {}", msg.as_ref());
|
||||
}
|
||||
|
||||
/// Print an error (always printed).
|
||||
/// Print an error line to stderr.
|
||||
pub fn error(msg: impl AsRef<str>) {
|
||||
let _ = cliclack::log::error(msg.as_ref());
|
||||
eprintln!("ERROR: {}", msg.as_ref());
|
||||
}
|
||||
|
||||
/// Print a line above any progress bars (maps to cliclack log; synchronized).
|
||||
pub fn println_above_bars(msg: impl AsRef<str>) {
|
||||
if crate::is_quiet() { return; }
|
||||
// cliclack logs are synchronized with its spinners/bars
|
||||
let _ = cliclack::log::info(msg.as_ref());
|
||||
/// Print a short intro header (non-fancy).
|
||||
pub fn intro(title: impl AsRef<str>) {
|
||||
eprintln!("== {} ==", title.as_ref());
|
||||
}
|
||||
|
||||
/// Input prompt with a question: returns Ok(None) if non-interactive or canceled
|
||||
pub fn prompt_input(question: impl AsRef<str>, default: Option<&str>) -> anyhow::Result<Option<String>> {
|
||||
if crate::is_no_interaction() || !crate::stdin_is_tty() {
|
||||
return Ok(None);
|
||||
}
|
||||
let mut p = cliclack::input(question.as_ref());
|
||||
if let Some(d) = default {
|
||||
// Use default_input when available in 0.3.x
|
||||
p = p.default_input(d);
|
||||
}
|
||||
match p.interact() {
|
||||
Ok(s) => Ok(Some(s)),
|
||||
Err(_) => Ok(None),
|
||||
}
|
||||
/// Print a short outro footer (non-fancy).
|
||||
pub fn outro(msg: impl AsRef<str>) {
|
||||
eprintln!("{}", msg.as_ref());
|
||||
}
|
||||
|
||||
/// Confirmation prompt; returns Ok(None) if non-interactive or canceled
|
||||
pub fn prompt_confirm(question: impl AsRef<str>, default_yes: bool) -> anyhow::Result<Option<bool>> {
|
||||
if crate::is_no_interaction() || !crate::stdin_is_tty() {
|
||||
return Ok(None);
|
||||
}
|
||||
let res = cliclack::confirm(question.as_ref())
|
||||
.initial_value(default_yes)
|
||||
.interact();
|
||||
match res {
|
||||
Ok(v) => Ok(Some(v)),
|
||||
Err(_) => Ok(None),
|
||||
}
|
||||
/// Print a line that should appear above any progress indicators (plain for now).
|
||||
pub fn println_above_bars(line: impl AsRef<str>) {
|
||||
eprintln!("{}", line.as_ref());
|
||||
}
|
||||
|
||||
/// Prompt the user (TTY-aware via cliclack) and read a line from stdin. Returns the raw line with trailing newline removed.
|
||||
pub fn prompt_line(prompt: &str) -> io::Result<String> {
|
||||
// Route prompt through cliclack to keep consistent styling and avoid direct eprint!/println!
|
||||
let _ = cliclack::log::info(prompt);
|
||||
let mut s = String::new();
|
||||
io::stdin().read_line(&mut s)?;
|
||||
Ok(s)
|
||||
}
|
||||
/// Prompt for input on stdin. Returns default if provided and user enters empty string.
|
||||
/// In non-interactive workflows, callers should skip prompt based on their flags.
|
||||
pub fn prompt_input(prompt: &str, default: Option<&str>) -> io::Result<String> {
|
||||
let mut stdout = io::stdout();
|
||||
match default {
|
||||
Some(def) => {
|
||||
write!(stdout, "{} [{}]: ", prompt, def)?;
|
||||
}
|
||||
None => {
|
||||
write!(stdout, "{}: ", prompt)?;
|
||||
}
|
||||
}
|
||||
stdout.flush()?;
|
||||
|
||||
/// TTY-aware progress UI built on `indicatif` for per-file and aggregate progress bars.
|
||||
///
|
||||
/// This small helper encapsulates a `MultiProgress` with one aggregate (total) bar and
|
||||
/// one per-file bar. It is intentionally minimal to keep integration lightweight.
|
||||
pub mod progress {
|
||||
// The submodule is defined in a separate file for clarity.
|
||||
include!("ui/progress.rs");
|
||||
let mut buf = String::new();
|
||||
io::stdin().read_line(&mut buf)?;
|
||||
let trimmed = buf.trim();
|
||||
if trimmed.is_empty() {
|
||||
Ok(default.unwrap_or_default().to_string())
|
||||
} else {
|
||||
Ok(trimmed.to_string())
|
||||
}
|
||||
}
|
||||
|
||||
@@ -79,3 +79,47 @@ impl ProgressManager {
|
||||
if let Some(total) = &self.total { total.set_position(self.completed as u64); }
|
||||
}
|
||||
}
|
||||
|
||||
/// A simple reporter for displaying progress messages in the terminal.
|
||||
/// Provides different output formatting based on whether the environment is interactive or not.
|
||||
#[derive(Debug)]
|
||||
pub struct ProgressReporter {
|
||||
non_interactive: bool,
|
||||
}
|
||||
|
||||
impl ProgressReporter {
|
||||
/// Creates a new progress reporter.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `non_interactive` - Whether the output should be formatted for non-interactive environments.
|
||||
pub fn new(non_interactive: bool) -> Self {
|
||||
Self { non_interactive }
|
||||
}
|
||||
|
||||
/// Displays a progress step message.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `message` - The message to display for this progress step.
|
||||
pub fn step(&mut self, message: &str) {
|
||||
if self.non_interactive {
|
||||
eprintln!("[..] {message}");
|
||||
} else {
|
||||
eprintln!("• {message}");
|
||||
}
|
||||
}
|
||||
|
||||
/// Displays a completion message.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `message` - The message to display when a task is completed.
|
||||
pub fn finish_with_message(&mut self, message: &str) {
|
||||
if self.non_interactive {
|
||||
eprintln!("[ok] {message}");
|
||||
} else {
|
||||
eprintln!("✓ {message}");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2,16 +2,10 @@
|
||||
name = "polyscribe-host"
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
license = "MIT"
|
||||
|
||||
[dependencies]
|
||||
anyhow = "1.0.98"
|
||||
thiserror = "1"
|
||||
anyhow = "1.0.99"
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = "1.0.142"
|
||||
tokio = { version = "1", features = ["full"] }
|
||||
which = "6"
|
||||
cliclack = "0.3"
|
||||
directories = "5"
|
||||
polyscribe = { path = "../polyscribe-core" }
|
||||
polyscribe-protocol = { path = "../polyscribe-protocol" }
|
||||
tokio = { version = "1.47.1", features = ["rt-multi-thread", "process", "io-util"] }
|
||||
which = "6.0.3"
|
||||
|
||||
@@ -1,168 +1,118 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
|
||||
use anyhow::{anyhow, Context, Result};
|
||||
use cliclack as ui; // reuse for minimal logging
|
||||
use directories::BaseDirs;
|
||||
use serde_json::Value;
|
||||
use std::collections::BTreeMap;
|
||||
use std::ffi::OsStr;
|
||||
use std::fs;
|
||||
use std::io::{BufRead, BufReader, Write};
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::process::{Command, Stdio};
|
||||
|
||||
use polyscribe_protocol as psp;
|
||||
use anyhow::{Context, Result};
|
||||
use serde::Deserialize;
|
||||
use std::{
|
||||
env,
|
||||
fs,
|
||||
os::unix::fs::PermissionsExt,
|
||||
path::Path,
|
||||
};
|
||||
use tokio::{
|
||||
io::{AsyncBufReadExt, BufReader},
|
||||
process::{Child as TokioChild, Command},
|
||||
};
|
||||
use std::process::Stdio;
|
||||
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct Plugin {
|
||||
pub struct PluginInfo {
|
||||
pub name: String,
|
||||
pub path: PathBuf,
|
||||
pub path: String,
|
||||
}
|
||||
|
||||
/// Discover plugins on PATH and in the user's data dir (XDG) under polyscribe/plugins.
|
||||
pub fn discover() -> Result<Vec<Plugin>> {
|
||||
let mut found: BTreeMap<String, PathBuf> = BTreeMap::new();
|
||||
#[derive(Debug, Default)]
|
||||
pub struct PluginManager;
|
||||
|
||||
// Scan PATH directories
|
||||
if let Some(path_var) = std::env::var_os("PATH") {
|
||||
for dir in std::env::split_paths(&path_var) {
|
||||
if dir.as_os_str().is_empty() { continue; }
|
||||
if let Ok(rd) = fs::read_dir(&dir) {
|
||||
for ent in rd.flatten() {
|
||||
let p = ent.path();
|
||||
if !is_executable(&p) { continue; }
|
||||
if let Some(fname) = p.file_name().and_then(OsStr::to_str) {
|
||||
if let Some(name) = fname.strip_prefix("polyscribe-plugin-") {
|
||||
found.entry(name.to_string()).or_insert(p);
|
||||
impl PluginManager {
|
||||
pub fn list(&self) -> Result<Vec<PluginInfo>> {
|
||||
let mut plugins = Vec::new();
|
||||
|
||||
// Scan PATH entries for executables starting with "polyscribe-plugin-"
|
||||
if let Ok(path) = env::var("PATH") {
|
||||
for dir in env::split_paths(&path) {
|
||||
if let Ok(read_dir) = fs::read_dir(&dir) {
|
||||
for entry in read_dir.flatten() {
|
||||
let path = entry.path();
|
||||
if let Some(fname) = path.file_name().and_then(|s| s.to_str()) {
|
||||
if fname.starts_with("polyscribe-plugin-") && is_executable(&path) {
|
||||
let name = fname.trim_start_matches("polyscribe-plugin-").to_string();
|
||||
plugins.push(PluginInfo {
|
||||
name,
|
||||
path: path.to_string_lossy().to_string(),
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TODO: also scan XDG data plugins dir for symlinks/binaries
|
||||
Ok(plugins)
|
||||
}
|
||||
|
||||
// Scan user data dir
|
||||
if let Some(base) = BaseDirs::new() {
|
||||
let user_plugins = PathBuf::from(base.data_dir()).join("polyscribe").join("plugins");
|
||||
if let Ok(rd) = fs::read_dir(&user_plugins) {
|
||||
for ent in rd.flatten() {
|
||||
let p = ent.path();
|
||||
if !is_executable(&p) { continue; }
|
||||
if let Some(fname) = p.file_name().and_then(OsStr::to_str) {
|
||||
let name = fname.strip_prefix("polyscribe-plugin-")
|
||||
.map(|s| s.to_string())
|
||||
.or_else(|| Some(fname.to_string()))
|
||||
.unwrap();
|
||||
found.entry(name).or_insert(p);
|
||||
}
|
||||
pub fn info(&self, name: &str) -> Result<serde_json::Value> {
|
||||
let bin = self.resolve(name)?;
|
||||
let out = std::process::Command::new(&bin)
|
||||
.arg("info")
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(Stdio::inherit())
|
||||
.spawn()
|
||||
.context("spawning plugin info")?
|
||||
.wait_with_output()
|
||||
.context("waiting for plugin info")?;
|
||||
|
||||
let val: serde_json::Value =
|
||||
serde_json::from_slice(&out.stdout).context("parsing plugin info JSON")?;
|
||||
Ok(val)
|
||||
}
|
||||
|
||||
pub fn spawn(&self, name: &str, command: &str) -> Result<TokioChild> {
|
||||
let bin = self.resolve(name)?;
|
||||
let mut cmd = Command::new(&bin);
|
||||
cmd.arg("run")
|
||||
.arg(command)
|
||||
.stdin(Stdio::piped())
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(Stdio::inherit());
|
||||
let child = cmd.spawn().context("spawning plugin run")?;
|
||||
Ok(child)
|
||||
}
|
||||
|
||||
pub async fn forward_stdio(&self, child: &mut TokioChild) -> Result<std::process::ExitStatus> {
|
||||
if let Some(stdout) = child.stdout.take() {
|
||||
let mut reader = BufReader::new(stdout).lines();
|
||||
while let Some(line) = reader.next_line().await? {
|
||||
println!("{line}");
|
||||
}
|
||||
}
|
||||
Ok(child.wait().await?)
|
||||
}
|
||||
|
||||
Ok(found
|
||||
.into_iter()
|
||||
.map(|(name, path)| Plugin { name, path })
|
||||
.collect())
|
||||
fn resolve(&self, name: &str) -> Result<String> {
|
||||
let bin = format!("polyscribe-plugin-{name}");
|
||||
let path = which::which(&bin).with_context(|| format!("plugin not found in PATH: {bin}"))?;
|
||||
Ok(path.to_string_lossy().to_string())
|
||||
}
|
||||
}
|
||||
|
||||
fn is_executable(p: &Path) -> bool {
|
||||
if !p.is_file() { return false; }
|
||||
fn is_executable(path: &Path) -> bool {
|
||||
if !path.is_file() {
|
||||
return false;
|
||||
}
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
if let Ok(md) = fs::metadata(p) {
|
||||
let mode = md.permissions().mode();
|
||||
return (mode & 0o111) != 0;
|
||||
}
|
||||
false
|
||||
}
|
||||
#[cfg(not(unix))]
|
||||
{
|
||||
// On Windows, consider .exe, .bat, .cmd
|
||||
matches!(p.extension().and_then(|s| s.to_str()).map(|s| s.to_lowercase()), Some(ext) if matches!(ext.as_str(), "exe"|"bat"|"cmd"))
|
||||
}
|
||||
}
|
||||
|
||||
/// Query plugin capabilities by invoking `--capabilities`.
|
||||
pub fn capabilities(plugin_path: &Path) -> Result<psp::Capabilities> {
|
||||
let out = Command::new(plugin_path)
|
||||
.arg("--capabilities")
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(Stdio::null())
|
||||
.output()
|
||||
.with_context(|| format!("Failed to execute plugin: {}", plugin_path.display()))?;
|
||||
if !out.status.success() {
|
||||
return Err(anyhow!("Plugin --capabilities failed: {}", plugin_path.display()));
|
||||
}
|
||||
let s = String::from_utf8(out.stdout).context("capabilities stdout not utf-8")?;
|
||||
let caps: psp::Capabilities = serde_json::from_str(s.trim()).context("invalid capabilities JSON")?;
|
||||
Ok(caps)
|
||||
}
|
||||
|
||||
/// Run a single method via `--serve`, writing one JSON-RPC request and streaming until result.
|
||||
pub fn run_method<F>(plugin_path: &Path, method: &str, params: Value, mut on_progress: F) -> Result<Value>
|
||||
where
|
||||
F: FnMut(psp::Progress),
|
||||
{
|
||||
let mut child = Command::new(plugin_path)
|
||||
.arg("--serve")
|
||||
.stdin(Stdio::piped())
|
||||
.stdout(Stdio::piped())
|
||||
.stderr(Stdio::null())
|
||||
.spawn()
|
||||
.with_context(|| format!("Failed to spawn plugin: {}", plugin_path.display()))?;
|
||||
|
||||
let mut stdin = child.stdin.take().ok_or_else(|| anyhow!("failed to open plugin stdin"))?;
|
||||
let stdout = child.stdout.take().ok_or_else(|| anyhow!("failed to open plugin stdout"))?;
|
||||
|
||||
// Send request line
|
||||
let req = psp::JsonRpcRequest { jsonrpc: "2.0".into(), id: "1".into(), method: method.to_string(), params: Some(params) };
|
||||
let line = serde_json::to_string(&req)? + "\n";
|
||||
stdin.write_all(line.as_bytes())?;
|
||||
stdin.flush()?;
|
||||
|
||||
// Read response lines
|
||||
let reader = BufReader::new(stdout);
|
||||
for line in reader.lines() {
|
||||
let line = line?;
|
||||
if line.trim().is_empty() { continue; }
|
||||
// Try parse StreamItem; if that fails, try parse JsonRpcResponse directly
|
||||
if let Ok(item) = serde_json::from_str::<psp::StreamItem>(&line) {
|
||||
match item {
|
||||
psp::StreamItem::Progress(p) => {
|
||||
on_progress(p);
|
||||
}
|
||||
psp::StreamItem::Result(resp) => {
|
||||
match resp.outcome {
|
||||
psp::JsonRpcOutcome::Ok { result } => return Ok(result),
|
||||
psp::JsonRpcOutcome::Err { error } => return Err(anyhow!("{} ({})", error.message, error.code)),
|
||||
}
|
||||
}
|
||||
}
|
||||
} else if let Ok(resp) = serde_json::from_str::<psp::JsonRpcResponse>(&line) {
|
||||
match resp.outcome {
|
||||
psp::JsonRpcOutcome::Ok { result } => return Ok(result),
|
||||
psp::JsonRpcOutcome::Err { error } => return Err(anyhow!("{} ({})", error.message, error.code)),
|
||||
}
|
||||
} else {
|
||||
let _ = ui::log::warning(format!("Unrecognized plugin output: {}", line));
|
||||
if let Ok(meta) = fs::metadata(path) {
|
||||
let mode = meta.permissions().mode();
|
||||
// if any execute bit is set
|
||||
return mode & 0o111 != 0;
|
||||
}
|
||||
}
|
||||
|
||||
// If we exited loop without returning, wait for child
|
||||
let status = child.wait()?;
|
||||
if status.success() {
|
||||
Err(anyhow!("Plugin terminated without sending a result"))
|
||||
} else {
|
||||
Err(anyhow!("Plugin exited with status: {:?}", status))
|
||||
}
|
||||
// Fallback for non-unix (treat files as candidates)
|
||||
true
|
||||
}
|
||||
|
||||
/// Helper: find a plugin by name using discovery
|
||||
pub fn find_plugin_by_name(name: &str) -> Result<Plugin> {
|
||||
let plugins = discover()?;
|
||||
plugins
|
||||
.into_iter()
|
||||
.find(|p| p.name == name)
|
||||
.ok_or_else(|| anyhow!("Plugin '{}' not found", name))
|
||||
#[allow(dead_code)]
|
||||
#[derive(Debug, Deserialize)]
|
||||
struct Capability {
|
||||
command: String,
|
||||
summary: String,
|
||||
}
|
||||
|
||||
@@ -2,9 +2,7 @@
|
||||
name = "polyscribe-protocol"
|
||||
version = "0.1.0"
|
||||
edition = "2024"
|
||||
license = "MIT"
|
||||
|
||||
[dependencies]
|
||||
serde = { version = "1.0.219", features = ["derive"] }
|
||||
serde_json = "1.0.142"
|
||||
thiserror = "1"
|
||||
|
||||
@@ -1,90 +1,60 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// PolyScribe Protocol (PSP/1): JSON-RPC 2.0 over NDJSON on stdio
|
||||
|
||||
use serde::{Deserialize, Serialize};
|
||||
use serde_json::Value;
|
||||
|
||||
/// Plugin capabilities as reported by `--capabilities`.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Capabilities {
|
||||
pub name: String,
|
||||
pub version: String,
|
||||
/// Protocol identifier (e.g., "psp/1")
|
||||
pub protocol: String,
|
||||
/// Role (e.g., pipeline, tool, generator)
|
||||
pub role: String,
|
||||
/// Supported command names
|
||||
pub commands: Vec<String>,
|
||||
}
|
||||
|
||||
/// Generic JSON-RPC 2.0 request for PSP/1
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct JsonRpcRequest {
|
||||
pub jsonrpc: String, // "2.0"
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct Request {
|
||||
pub id: String,
|
||||
pub method: String,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub params: Option<serde_json::Value>,
|
||||
pub params: Option<Value>,
|
||||
}
|
||||
|
||||
/// Error object for JSON-RPC 2.0
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct JsonRpcError {
|
||||
pub code: i64,
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct Response {
|
||||
pub id: String,
|
||||
pub result: Option<Value>,
|
||||
pub error: Option<ErrorObj>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
pub struct ErrorObj {
|
||||
pub code: i32,
|
||||
pub message: String,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
pub data: Option<serde_json::Value>,
|
||||
pub data: Option<Value>,
|
||||
}
|
||||
|
||||
/// Generic JSON-RPC 2.0 response for PSP/1
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "lowercase")]
|
||||
pub enum StreamItem {
|
||||
/// Progress notification (out-of-band in stream, not a JSON-RPC response)
|
||||
Progress(Progress),
|
||||
/// A proper JSON-RPC response with a result
|
||||
Result(JsonRpcResponse),
|
||||
#[derive(Debug, Serialize, Deserialize)]
|
||||
#[serde(tag = "event", content = "data")]
|
||||
pub enum ProgressEvent {
|
||||
Started,
|
||||
Message(String),
|
||||
Percent(f32),
|
||||
Finished,
|
||||
}
|
||||
|
||||
/// JSON-RPC 2.0 Response envelope containing either result or error.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct JsonRpcResponse {
|
||||
pub jsonrpc: String, // "2.0"
|
||||
pub id: String,
|
||||
#[serde(flatten)]
|
||||
pub outcome: JsonRpcOutcome,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
#[serde(untagged)]
|
||||
pub enum JsonRpcOutcome {
|
||||
Ok { result: serde_json::Value },
|
||||
Err { error: JsonRpcError },
|
||||
}
|
||||
|
||||
/// Progress event structure for PSP/1 streaming
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct Progress {
|
||||
/// 0..=100
|
||||
pub pct: u8,
|
||||
/// Short phase name
|
||||
pub stage: Option<String>,
|
||||
/// Human-friendly detail
|
||||
pub message: Option<String>,
|
||||
}
|
||||
|
||||
/// Convenience helpers to build items
|
||||
impl StreamItem {
|
||||
pub fn progress(pct: u8, stage: impl Into<Option<String>>, message: impl Into<Option<String>>) -> Self {
|
||||
StreamItem::Progress(Progress { pct, stage: stage.into(), message: message.into() })
|
||||
}
|
||||
pub fn ok(id: impl Into<String>, result: serde_json::Value) -> Self {
|
||||
StreamItem::Result(JsonRpcResponse { jsonrpc: "2.0".into(), id: id.into(), outcome: JsonRpcOutcome::Ok { result } })
|
||||
}
|
||||
pub fn err(id: impl Into<String>, code: i64, message: impl Into<String>, data: Option<serde_json::Value>) -> Self {
|
||||
StreamItem::Result(JsonRpcResponse {
|
||||
jsonrpc: "2.0".into(),
|
||||
impl Response {
|
||||
pub fn ok(id: impl Into<String>, result: Value) -> Self {
|
||||
Self {
|
||||
id: id.into(),
|
||||
outcome: JsonRpcOutcome::Err { error: JsonRpcError { code, message: message.into(), data } },
|
||||
})
|
||||
result: Some(result),
|
||||
error: None,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn err(
|
||||
id: impl Into<String>,
|
||||
code: i32,
|
||||
message: impl Into<String>,
|
||||
data: Option<Value>,
|
||||
) -> Self {
|
||||
Self {
|
||||
id: id.into(),
|
||||
result: None,
|
||||
error: Some(ErrorObj {
|
||||
code,
|
||||
message: message.into(),
|
||||
data,
|
||||
}),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user