Add a cache for the cli to store property labels

master
Raymon Zutekouw 3 weeks ago
parent 8937c5677f
commit 9c6f71f32d
Signed by: raymon
GPG Key ID: 0E62222846283925
  1. 67
      Cargo.lock
  2. 1
      Cargo.toml
  3. 88
      src/main.rs

67
Cargo.lock generated

@ -360,6 +360,27 @@ dependencies = [
"subtle",
]
[[package]]
name = "dirs-next"
version = "2.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b98cf8ebf19c3d1b223e151f99a4f9f0690dca41414773390fc824184ac833e1"
dependencies = [
"cfg-if",
"dirs-sys-next",
]
[[package]]
name = "dirs-sys-next"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4ebda144c4fe02d1f7ea1a7d9641b6fc6b580adcfa024ae48797ecdeb6825b4d"
dependencies = [
"libc",
"redox_users",
"winapi",
]
[[package]]
name = "displaydoc"
version = "0.2.5"
@ -989,6 +1010,16 @@ version = "0.2.174"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
[[package]]
name = "libredox"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "391290121bad3d37fbddad76d8f5d1c1c314cfc646d143d7e07a3086ddff0ce3"
dependencies = [
"bitflags 2.9.1",
"libc",
]
[[package]]
name = "linux-raw-sys"
version = "0.9.4"
@ -1245,7 +1276,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1db05f56d34358a8b1066f67cbb203ee3e7ed2ba674a6263a1d5ec6db2204323"
dependencies = [
"memchr",
"thiserror",
"thiserror 2.0.12",
"ucd-trie",
]
@ -1427,6 +1458,17 @@ dependencies = [
"bitflags 2.9.1",
]
[[package]]
name = "redox_users"
version = "0.4.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ba009ff324d1fc1b900bd1fdb31564febe58a8ccc8a6fdbb93b543d33b13ca43"
dependencies = [
"getrandom 0.2.16",
"libredox",
"thiserror 1.0.69",
]
[[package]]
name = "regex"
version = "1.11.1"
@ -1877,13 +1919,33 @@ dependencies = [
"unicode-width",
]
[[package]]
name = "thiserror"
version = "1.0.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
dependencies = [
"thiserror-impl 1.0.69",
]
[[package]]
name = "thiserror"
version = "2.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "567b8a2dae586314f7be2a752ec7474332959c6460e02bde30d702a66d488708"
dependencies = [
"thiserror-impl",
"thiserror-impl 2.0.12",
]
[[package]]
name = "thiserror-impl"
version = "1.0.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.104",
]
[[package]]
@ -2327,6 +2389,7 @@ name = "wikipedia-infobox-analyzer"
version = "0.1.0"
dependencies = [
"ascii_table",
"dirs-next",
"itertools",
"mediawiki",
"regex",

@ -17,6 +17,7 @@ categories = ["command-line-utilities"]
[dependencies]
regex = "1.11.1"
ascii_table = "4.0.7"
dirs-next = "2.0.0"
itertools = "0.14.0"
mediawiki = "0.3.1"
reqwest = { version = "0.12", features = ["blocking"] }

@ -1,6 +1,12 @@
use structopt::StructOpt;
use wikipedia_infobox_analyzer::wikipedia_infobox_analyzer::*;
use dirs_next::cache_dir;
use std::collections::HashMap;
use std::fs;
use std::io;
use std::path::PathBuf;
use structopt::StructOpt;
#[derive(StructOpt)]
struct Cli {
#[structopt(default_value = "Earth", long = "title")]
@ -11,10 +17,88 @@ struct Cli {
infobox_template_file: std::path::PathBuf,
}
#[derive(Debug)]
struct StorageDisk {
base_path: PathBuf,
}
impl StorageDisk {
fn new(app_name: &str) -> Self {
// Get OS-specific cache directory, otherwise use a fallback location
let mut path = match cache_dir() {
Some(path) => path,
None => PathBuf::from("./.cache"),
};
path.push(app_name);
fs::create_dir_all(&path)
.unwrap_or_else(|_| panic!("Failed to create storage directory: {path:?}"));
StorageDisk { base_path: path }
}
#[allow(dead_code)]
fn delete(&self) -> std::io::Result<()> {
fs::remove_dir_all(&self.base_path)
}
fn store_data(&self, filename: String, data: String) -> std::io::Result<()> {
let file_path = self.base_path.join(filename);
fs::write(file_path, data)
}
fn read_data(&self, filename: String) -> std::io::Result<String> {
let file_path = self.base_path.join(filename);
fs::read_to_string(file_path)
}
}
struct Cache {
file_name: String,
storage: StorageDisk,
property_labels: HashMap<String, String>,
}
impl Cache {
fn new(file_name: String, storage: StorageDisk) -> std::io::Result<Self> {
let mut property_labels: HashMap<String, String> = HashMap::new();
match storage.read_data(file_name.clone()) {
Ok(raw_data) => {
property_labels = serde_json::from_str(&raw_data)?;
}
Err(err) if err.kind() == io::ErrorKind::NotFound => {
println!("No cache found, populating the program cache with wikidata...");
property_labels = HashMap::new();
property_labels.insert("P31".to_string(), "instance of".to_string());
let data = serde_json::to_string(&property_labels)?;
storage.store_data(file_name.clone(), data)?;
println!("Cache populated from wikidata")
}
Err(err) => {
println!("Unknown error occurred, exiting gracefully");
return Err(err);
}
}
Ok(Cache {
file_name,
storage,
property_labels,
})
}
}
fn main() -> Result<(), Box<dyn std::error::Error>> {
let args = Cli::from_args();
// Initialize cache and storage
let storage = StorageDisk::new("wikipedia-infobox-analyzer");
let cache = Cache::new("property_labels.cache".to_string(), storage);
// Input to the program
let args = Cli::from_args();
let title = args.wikipedia_article_title;
let language = args.wikipedia_language_code;
let template = std::fs::read_to_string(&args.infobox_template_file)?;

Loading…
Cancel
Save