better arg parsing and passing

Cargo.lock

@@ -384,6 +384,14 @@ name = "glob"
 version = "0.2.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 
+[[package]]
+name = "heck"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "unicode-segmentation 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
 [[package]]
 name = "humantime"
 version = "1.2.0"
@@ -888,6 +896,7 @@ dependencies = [
  "serde 1.0.92 (registry+https://github.com/rust-lang/crates.io-index)",
  "serde_json 1.0.39 (registry+https://github.com/rust-lang/crates.io-index)",
  "size_format 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
+ "structopt 0.2.17 (registry+https://github.com/rust-lang/crates.io-index)",
  "tar 0.4.26 (registry+https://github.com/rust-lang/crates.io-index)",
  "tree_magic_fork 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
  "xz2 0.1.6 (registry+https://github.com/rust-lang/crates.io-index)",
@@ -1017,6 +1026,26 @@ name = "strsim"
 version = "0.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 
+[[package]]
+name = "structopt"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "clap 2.33.0 (registry+https://github.com/rust-lang/crates.io-index)",
+ "structopt-derive 0.2.17 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "structopt-derive"
+version = "0.2.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "heck 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)",
+ "proc-macro2 0.4.30 (registry+https://github.com/rust-lang/crates.io-index)",
+ "quote 0.6.12 (registry+https://github.com/rust-lang/crates.io-index)",
+ "syn 0.15.34 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
 [[package]]
 name = "syn"
 version = "0.15.34"
@@ -1132,6 +1161,11 @@ dependencies = [
  "smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)",
 ]
 
+[[package]]
+name = "unicode-segmentation"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
 [[package]]
 name = "unicode-width"
 version = "0.1.5"
@@ -1311,6 +1345,7 @@ dependencies = [
 "checksum fuchsia-cprng 0.1.1 (registry+https://github.com/rust-lang/crates.io-index)" = "a06f77d526c1a601b7c4cdd98f54b5eaabffc14d5f2f0296febdc7f357c6d3ba"
 "checksum generic-array 0.12.0 (registry+https://github.com/rust-lang/crates.io-index)" = "3c0f28c2f5bfb5960175af447a2da7c18900693738343dc896ffbcabd9839592"
 "checksum glob 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "8be18de09a56b60ed0edf84bc9df007e30040691af7acd1c41874faac5895bfb"
+"checksum heck 0.3.1 (registry+https://github.com/rust-lang/crates.io-index)" = "20564e78d53d2bb135c343b3f47714a56af2061f1c928fdb541dc7b9fdd94205"
 "checksum humantime 1.2.0 (registry+https://github.com/rust-lang/crates.io-index)" = "3ca7e5f2e110db35f93b837c81797f3714500b81d517bf20c431b16d3ca4f114"
 "checksum idna 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "38f09e0f0b1fb55fdee1f17470ad800da77af5186a1a76c026b679358b7e844e"
 "checksum itoa 0.4.4 (registry+https://github.com/rust-lang/crates.io-index)" = "501266b7edd0174f8530248f87f99c88fbe60ca4ef3dd486835b8d8d53136f7f"
@@ -1385,6 +1420,8 @@ dependencies = [
 "checksum size_format 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6ed5f6ab2122c6dec69dca18c72fa4590a27e581ad20d44960fe74c032a0b23b"
 "checksum smallvec 0.6.9 (registry+https://github.com/rust-lang/crates.io-index)" = "c4488ae950c49d403731982257768f48fada354a5203fe81f9bb6f43ca9002be"
 "checksum strsim 0.8.0 (registry+https://github.com/rust-lang/crates.io-index)" = "8ea5119cdb4c55b55d432abb513a0429384878c15dde60cc77b1c99de1a95a6a"
+"checksum structopt 0.2.17 (registry+https://github.com/rust-lang/crates.io-index)" = "c767a8971f53d7324583085deee2e230903be09e52fb27df9af94c5cb2b43c31"
+"checksum structopt-derive 0.2.17 (registry+https://github.com/rust-lang/crates.io-index)" = "c57a30c87454ced2186f62f940e981746e8cbbe026d52090c8c4352b636f8235"
 "checksum syn 0.15.34 (registry+https://github.com/rust-lang/crates.io-index)" = "a1393e4a97a19c01e900df2aec855a29f71cf02c402e2f443b8d2747c25c5dbe"
 "checksum synstructure 0.10.2 (registry+https://github.com/rust-lang/crates.io-index)" = "02353edf96d6e4dc81aea2d8490a7e9db177bf8acb0e951c24940bf866cb313f"
 "checksum tar 0.4.26 (registry+https://github.com/rust-lang/crates.io-index)" = "b3196bfbffbba3e57481b6ea32249fbaf590396a52505a2615adbb79d9d826d3"
@@ -1398,6 +1435,7 @@ dependencies = [
 "checksum ucd-util 0.1.3 (registry+https://github.com/rust-lang/crates.io-index)" = "535c204ee4d8434478593480b8f86ab45ec9aae0e83c568ca81abf0fd0e88f86"
 "checksum unicode-bidi 0.3.4 (registry+https://github.com/rust-lang/crates.io-index)" = "49f2bd0c6468a8230e1db229cff8029217cf623c767ea5d60bfbd42729ea54d5"
 "checksum unicode-normalization 0.1.8 (registry+https://github.com/rust-lang/crates.io-index)" = "141339a08b982d942be2ca06ff8b076563cbe223d1befd5450716790d44e2426"
+"checksum unicode-segmentation 1.3.0 (registry+https://github.com/rust-lang/crates.io-index)" = "1967f4cdfc355b37fd76d2a954fb2ed3871034eb4f26d60537d88795cfc332a9"
 "checksum unicode-width 0.1.5 (registry+https://github.com/rust-lang/crates.io-index)" = "882386231c45df4700b275c7ff55b6f3698780a650026380e72dabe76fa46526"
 "checksum unicode-xid 0.1.0 (registry+https://github.com/rust-lang/crates.io-index)" = "fc72304796d0818e357ead4e000d19c9c174ab23dc11093ac919054d20a6a7fc"
 "checksum url 1.7.2 (registry+https://github.com/rust-lang/crates.io-index)" = "dd4e7c0d531266369519a4aa4f399d748bd37043b00bde1e4ff1f60a120b355a"

Cargo.toml

@@ -1,7 +1,7 @@
 
 [package]
 name = "rga"
-description = "ripgrep but also search in PDFs, E-Books, Office documents, etc, and also in archives"
+description = "ripgrep but search in PDFs, E-Books, Office documents, etc, and also in archives"
 license = "AGPL-3.0-or-later"
 version = "0.4.0"
 repository = "https://github.com/phiresky/rga"
@@ -39,3 +39,4 @@ encoding_rs = "0.8.17"
 encoding_rs_io = "0.1.6"
 rusqlite = { version = "0.18.0", features=["vtab"] } # "bundled"
 size_format = "1.0.2"
+structopt = "0.2.17"

README.md

@@ -10,3 +10,10 @@ similar:
 # considerations
 
 -   matching on mime (magic bytes) instead of filename
+
+# Development
+
+To enable debug logging:
+
+export RUST_LOG=rga=debug
+export RUST_BACKTRACE=1

src/args.rs

@@ -0,0 +1,64 @@
+use clap::{crate_version, App, Arg};
+use failure::Fallible;
+use log::*;
+use serde::{Deserialize, Serialize};
+use std::ffi::OsStr;
+use std::ffi::OsString;
+use std::iter::IntoIterator;
+use std::process::Command;
+use structopt::StructOpt;
+fn is_default<T: Default + PartialEq>(t: &T) -> bool {
+    t == &T::default()
+}
+
+#[derive(StructOpt, Debug, Deserialize, Serialize)]
+#[structopt(rename_all = "kebab-case")]
+pub struct RgaOptions {
+    #[serde(default, skip_serializing_if = "is_default")]
+    #[structopt(long, help = "Disable caching of results")]
+    pub no_cache: bool,
+
+    #[serde(default, skip_serializing_if = "is_default")]
+    #[structopt(
+        long,
+        require_equals = true,
+        require_delimiter = true,
+        help = "Change which adapters to use and in which priority order (descending)"
+    )]
+    pub adapters: Vec<String>,
+
+    #[serde(skip)]
+    #[structopt(long, help = "Show help for ripgrep itself")]
+    pub rg_help: bool,
+
+    #[serde(skip)]
+    #[structopt(long, help = "Show version of ripgrep itself")]
+    pub rg_version: bool,
+
+    #[serde(skip)]
+    #[structopt(long, help = "List all known adapters")]
+    pub list_adapters: bool,
+}
+
+static RGA_CONFIG: &str = "RGA_CONFIG";
+
+pub fn parse_args<I>(args: I) -> Fallible<RgaOptions>
+where
+    I: IntoIterator,
+    I::Item: Into<OsString> + Clone,
+{
+    match std::env::var(RGA_CONFIG) {
+        Ok(val) => {
+            error!("Loading args from env {}={}", RGA_CONFIG, val);
+            Ok(serde_json::from_str(&val)?)
+        }
+        Err(_) => {
+            let matches = RgaOptions::from_iter(args);
+            let serialized_config = serde_json::to_string(&matches)?;
+            std::env::set_var(RGA_CONFIG, &serialized_config);
+            debug!("{}={}", RGA_CONFIG, serialized_config);
+
+            Ok(matches)
+        }
+    }
+}

src/bin/rga-preproc.rs

@@ -1,10 +1,17 @@
-use failure::{format_err, Error};
+use clap::{crate_version, App, Arg};
+
+use failure::{format_err, Error, Fallible};
+use log::*;
 use rga::adapters::*;
 use rga::preproc::*;
 use std::env;
 use std::fs::File;
 use std::io::BufReader;
-fn main() -> Result<(), Error> {
+fn main() -> Fallible<()> {
+    env_logger::init();
+    let empty: Vec<std::ffi::OsString> = vec![];
+    let args = rga::args::parse_args(empty)?;
+    //clap::App::new("rga-preproc").arg(Arg::from_usage())
     let path = {
         let filepath = std::env::args_os()
             .skip(1)
@@ -16,9 +23,10 @@ fn main() -> Result<(), Error> {
 
     let i = File::open(&path)?;
     let mut o = std::io::stdout();
-    let cache = match env::var("RGA_NO_CACHE") {
+    let cache = if args.no_cache {
-        Ok(ref s) if s.len() > 0 => None,
+        None
-        Ok(_) | Err(_) => Some(rga::preproc_cache::open()?),
+    } else {
+        Some(rga::preproc_cache::open()?)
     };
     let ai = AdaptInfo {
         inp: &mut BufReader::new(i),

src/bin/rga.rs

@@ -3,24 +3,18 @@ use failure::Fallible;
 use log::*;
 use rga::adapters::spawning::map_exe_error;
 use rga::adapters::*;
+use rga::args::*;
+use serde::{Deserialize, Serialize};
 use std::ffi::OsString;
 use std::process::Command;
+use structopt::StructOpt;
+
+fn split_args() -> Fallible<(RgaOptions, Vec<OsString>)> {
+    let mut app = RgaOptions::clap();
 
-fn main() -> Fallible<()> {
-    env_logger::init();
-    let mut app = App::new(env!("CARGO_PKG_NAME"))
-        .version(crate_version!())
-        .about(env!("CARGO_PKG_DESCRIPTION"))
-        // .setting(clap::AppSettings::ArgRequiredElseHelp)
-        .arg(Arg::from_usage(
-            "--list-adapters 'Lists all known adapters'",
-        ))
-        .arg(Arg::from_usage("--adapters=[commaseparated] 'Change which adapters to use and in which priority order (descending)'").require_equals(true))
-        .arg(Arg::from_usage("--no-cache 'Disable caching of results'"))
-        .arg(Arg::from_usage("--rg-help 'Show help for ripgrep itself'"))
-        .arg(Arg::from_usage("--rg-version 'Show version of ripgrep itself'"));
     app.p.create_help_and_version();
     let mut firstarg = true;
+    // debug!("{:#?}", app.p.flags);
     let (our_args, mut passthrough_args): (Vec<OsString>, Vec<OsString>) = std::env::args_os()
         .partition(|os_arg| {
             if firstarg {
@@ -45,7 +39,7 @@ fn main() -> Fallible<()> {
                 for opt in app.p.opts() {
                     // only parse --x=... for now
                     if let Some(l) = opt.s.long {
-                        if arg.starts_with(&format!("--{}-", l)) {
+                        if arg.starts_with(&format!("--{}=", l)) {
                             return true;
                         }
                     }
@@ -54,18 +48,24 @@ fn main() -> Fallible<()> {
             false
         });
     debug!("our_args: {:?}", our_args);
-    let matches = app.get_matches_from(our_args);
+    let matches = parse_args(our_args)?;
-    if matches.is_present("rg-help") {
+    if matches.rg_help {
         passthrough_args.insert(0, "--help".into());
     }
-    if matches.is_present("rg-version") {
+    if matches.rg_version {
         passthrough_args.insert(0, "--version".into());
     }
     debug!("passthrough_args: {:?}", passthrough_args);
+    Ok((matches, passthrough_args))
+}
 
+fn main() -> Fallible<()> {
+    env_logger::init();
+
+    let (args, passthrough_args) = split_args()?;
     let adapters = get_adapters();
 
-    if matches.is_present("list-adapters") {
+    if args.list_adapters {
         println!("Adapters:");
         for adapter in adapters {
             let meta = adapter.metadata();

src/lib.rs

@@ -1,6 +1,7 @@
 #![warn(clippy::all)]
 
 pub mod adapters;
+pub mod args;
 mod caching_writer;
 pub mod preproc;
 pub mod preproc_cache;