From 4ebaa31250589212a0cd1ef30bb4c8e7480d35ed Mon Sep 17 00:00:00 2001 From: Kieran Date: Sun, 29 Sep 2024 14:47:24 +0100 Subject: [PATCH] Init --- .gitignore | 2 + Cargo.lock | 534 ++++++++++++++++++++++++++++++++++++++++++++++++++ Cargo.toml | 13 ++ src/cursor.rs | 70 +++++++ src/event.rs | 12 ++ src/main.rs | 37 ++++ 6 files changed, 668 insertions(+) create mode 100644 .gitignore create mode 100644 Cargo.lock create mode 100644 Cargo.toml create mode 100644 src/cursor.rs create mode 100644 src/event.rs create mode 100644 src/main.rs diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..f6c313c --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/target +/data \ No newline at end of file diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..343e75a --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,534 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 3 + +[[package]] +name = "addr2line" +version = "0.24.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f5fb1d8e4442bd405fdfd1dacb42792696b0cf9cb15882e5d097b742a676d375" +dependencies = [ + "gimli", +] + +[[package]] +name = "adler2" +version = "2.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627" + +[[package]] +name = "anstream" +version = "0.6.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "64e15c1ab1f89faffbf04a634d5e1962e9074f2741eef6d97f3c4e322426d526" +dependencies = [ + "anstyle", + "anstyle-parse", + "anstyle-query", + "anstyle-wincon", + "colorchoice", + "is_terminal_polyfill", + "utf8parse", +] + +[[package]] +name = "anstyle" +version = "1.0.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bec1de6f59aedf83baf9ff929c98f2ad654b97c9510f4e70cf6f661d49fd5b1" + +[[package]] +name = "anstyle-parse" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eb47de1e80c2b463c735db5b217a0ddc39d612e7ac9e2e96a5aed1f57616c1cb" +dependencies = [ + "utf8parse", +] + +[[package]] +name = "anstyle-query" +version = "1.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6d36fc52c7f6c869915e99412912f22093507da8d9e942ceaf66fe4b7c14422a" +dependencies = [ + "windows-sys", +] + +[[package]] +name = "anstyle-wincon" +version = "3.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5bf74e1b6e971609db8ca7a9ce79fd5768ab6ae46441c572e46cf596f59e57f8" +dependencies = [ + "anstyle", + "windows-sys", +] + +[[package]] +name = "anyhow" +version = "1.0.89" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "86fdf8605db99b54d3cd748a44c6d04df638eb5dafb219b135d0149bd0db01f6" + +[[package]] +name = "async-compression" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fec134f64e2bc57411226dfc4e52dec859ddfc7e711fc5e07b612584f000e4aa" +dependencies = [ + "bzip2", + "flate2", + "futures-core", + "memchr", + "pin-project-lite", + "tokio", + "zstd", + "zstd-safe", +] + +[[package]] +name = "backtrace" +version = "0.3.74" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a" +dependencies = [ + "addr2line", + "cfg-if", + "libc", + "miniz_oxide", + "object", + "rustc-demangle", + "windows-targets", +] + +[[package]] +name = "bytes" +version = "1.7.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "428d9aa8fbc0670b7b8d6030a7fadd0f86151cae55e4dbbece15f3780a3dfaf3" + +[[package]] +name = "bzip2" +version = "0.4.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bdb116a6ef3f6c3698828873ad02c3014b3c85cadb88496095628e3ef1e347f8" +dependencies = [ + "bzip2-sys", + "libc", +] + +[[package]] +name = "bzip2-sys" +version = "0.1.11+1.0.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "736a955f3fa7875102d57c82b8cac37ec45224a07fd32d58f9f7a186b6cd4cdc" +dependencies = [ + "cc", + "libc", + "pkg-config", +] + +[[package]] +name = "cc" +version = "1.1.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07b1695e2c7e8fc85310cde85aeaab7e3097f593c91d209d3f9df76c928100f0" +dependencies = [ + "jobserver", + "libc", + "shlex", +] + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "clap" +version = "4.5.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b0956a43b323ac1afaffc053ed5c4b7c1f1800bacd1683c353aabbb752515dd3" +dependencies = [ + "clap_builder", + "clap_derive", +] + +[[package]] +name = "clap_builder" +version = "4.5.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4d72166dd41634086d5803a47eb71ae740e61d84709c36f3c34110173db3961b" +dependencies = [ + "anstream", + "anstyle", + "clap_lex", + "strsim", +] + +[[package]] +name = "clap_derive" +version = "4.5.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4ac6a0c7b1a9e9a5186361f67dfa1b88213572f427fb9ab038efb2bd8c582dab" +dependencies = [ + "heck", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "clap_lex" +version = "0.7.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1462739cb27611015575c0c11df5df7601141071f07518d56fcc1be504cbec97" + +[[package]] +name = "colorchoice" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3fd119d74b830634cea2a0f58bbd0d54540518a14397557951e79340abc28c0" + +[[package]] +name = "crc32fast" +version = "1.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "flate2" +version = "1.0.34" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a1b589b4dc103969ad3cf85c950899926ec64300a1a46d76c03a6072957036f0" +dependencies = [ + "crc32fast", + "miniz_oxide", +] + +[[package]] +name = "futures-core" +version = "0.3.30" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dfc6580bb841c5a68e9ef15c77ccc837b40a7504914d52e47b8b0e9bbda25a1d" + +[[package]] +name = "gimli" +version = "0.31.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32085ea23f3234fc7846555e85283ba4de91e21016dc0455a16286d87a292d64" + +[[package]] +name = "heck" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" + +[[package]] +name = "hex" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70" + +[[package]] +name = "is_terminal_polyfill" +version = "1.70.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf" + +[[package]] +name = "itoa" +version = "1.0.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" + +[[package]] +name = "jobserver" +version = "0.1.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "48d1dbcbbeb6a7fec7e059840aa538bd62aaccf972c7346c4d9d2059312853d0" +dependencies = [ + "libc", +] + +[[package]] +name = "libc" +version = "0.2.159" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "561d97a539a36e26a9a5fad1ea11a3039a67714694aaa379433e580854bc3dc5" + +[[package]] +name = "memchr" +version = "2.7.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" + +[[package]] +name = "miniz_oxide" +version = "0.8.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e2d80299ef12ff69b16a84bb182e3b9df68b5a91574d3d4fa6e41b65deec4df1" +dependencies = [ + "adler2", +] + +[[package]] +name = "nostr_stat" +version = "0.1.0" +dependencies = [ + "anyhow", + "async-compression", + "clap", + "hex", + "serde", + "serde_json", + "tokio", +] + +[[package]] +name = "object" +version = "0.36.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "084f1a5821ac4c651660a94a7153d27ac9d8a53736203f58b31945ded098070a" +dependencies = [ + "memchr", +] + +[[package]] +name = "pin-project-lite" +version = "0.2.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bda66fc9667c18cb2758a2ac84d1167245054bcf85d5d1aaa6923f45801bdd02" + +[[package]] +name = "pkg-config" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "953ec861398dccce10c670dfeaf3ec4911ca479e9c02154b3a215178c5f566f2" + +[[package]] +name = "proc-macro2" +version = "1.0.86" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.37" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "rustc-demangle" +version = "0.1.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "719b953e2095829ee67db738b3bfa9fa368c94900df327b3f07fe6e794d2fe1f" + +[[package]] +name = "ryu" +version = "1.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f3cb5ba0dc43242ce17de99c180e96db90b235b8a9fdc9543c96d2209116bd9f" + +[[package]] +name = "serde" +version = "1.0.210" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8e3592472072e6e22e0a54d5904d9febf8508f65fb8552499a1abc7d1078c3a" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.210" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "243902eda00fad750862fc144cea25caca5e20d615af0a81bee94ca738f1df1f" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "serde_json" +version = "1.0.128" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ff5456707a1de34e7e37f2a6fd3d3f808c318259cbd01ab6377795054b483d8" +dependencies = [ + "itoa", + "memchr", + "ryu", + "serde", +] + +[[package]] +name = "shlex" +version = "1.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64" + +[[package]] +name = "strsim" +version = "0.11.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f" + +[[package]] +name = "syn" +version = "2.0.79" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "89132cd0bf050864e1d38dc3bbc07a0eb8e7530af26344d3d2bbbef83499f590" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "tokio" +version = "1.40.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e2b070231665d27ad9ec9b8df639893f46727666c6767db40317fbe920a5d998" +dependencies = [ + "backtrace", + "bytes", + "pin-project-lite", + "tokio-macros", +] + +[[package]] +name = "tokio-macros" +version = "2.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "693d596312e88961bc67d7f1f97af8a70227d9f90c31bba5806eec004978d752" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "unicode-ident" +version = "1.0.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e91b56cd4cadaeb79bbf1a5645f6b4f8dc5bde8834ad5894a8db35fda9efa1fe" + +[[package]] +name = "utf8parse" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821" + +[[package]] +name = "windows-sys" +version = "0.52.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d" +dependencies = [ + "windows-targets", +] + +[[package]] +name = "windows-targets" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" +dependencies = [ + "windows_aarch64_gnullvm", + "windows_aarch64_msvc", + "windows_i686_gnu", + "windows_i686_gnullvm", + "windows_i686_msvc", + "windows_x86_64_gnu", + "windows_x86_64_gnullvm", + "windows_x86_64_msvc", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" + +[[package]] +name = "windows_i686_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" + +[[package]] +name = "windows_i686_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" + +[[package]] +name = "zstd" +version = "0.13.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fcf2b778a664581e31e389454a7072dab1647606d44f7feea22cd5abb9c9f3f9" +dependencies = [ + "zstd-safe", +] + +[[package]] +name = "zstd-safe" +version = "7.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "54a3ab4db68cea366acc5c897c7b4d4d1b8994a9cd6e6f841f8964566a419059" +dependencies = [ + "zstd-sys", +] + +[[package]] +name = "zstd-sys" +version = "2.0.13+zstd.1.5.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "38ff0f21cfee8f97d94cef41359e0c89aa6113028ab0291aa8ca0038995a95aa" +dependencies = [ + "cc", + "pkg-config", +] diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..c8240eb --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,13 @@ +[package] +name = "nostr_stat" +version = "0.1.0" +edition = "2021" + +[dependencies] +anyhow = "1.0.89" +clap = { version = "4.5.18", features = ["derive"] } +serde = { version = "1.0.210", features = ["derive"] } +tokio = { version = "1.40.0", features = ["rt", "rt-multi-thread", "macros", "fs", "io-util"] } +serde_json = "1.0.128" +hex = "0.4.3" +async-compression = { version = "0.4.12", features = ["tokio", "gzip", "zstd", "bzip2"] } diff --git a/src/cursor.rs b/src/cursor.rs new file mode 100644 index 0000000..108dd18 --- /dev/null +++ b/src/cursor.rs @@ -0,0 +1,70 @@ +use crate::event::NostrEvent; +use async_compression::tokio::bufread::{BzDecoder, GzipDecoder, ZstdDecoder}; +use std::collections::HashSet; +use std::path::PathBuf; +use std::pin::Pin; +use tokio::fs::File; +use tokio::io::{AsyncBufReadExt, AsyncRead, BufReader}; + +#[derive(Ord, PartialOrd, Eq, PartialEq, Hash)] +struct EventId([u8; 32]); + +/// A director cursor over 1 or more JSON-L files +/// +/// Skips duplicate events +/// +/// Works with compressed files too +pub struct NostrCursor { + ids: HashSet, + dir: PathBuf, +} + +impl NostrCursor { + pub fn new(dir: PathBuf) -> Self { + Self { + dir, + ids: HashSet::new(), + } + } + + pub async fn walk(&mut self, mut fx: T) -> Result<(), anyhow::Error> + where + T: FnMut(&NostrEvent), + { + let mut dir_reader = tokio::fs::read_dir(&self.dir).await?; + while let Ok(Some(path)) = dir_reader.next_entry().await { + let path = path.path(); + println!("Reading: {}", path.to_str().unwrap()); + let file: Pin> = match path.extension() { + Some(ext) => { + let buf_reader = BufReader::new(File::open(path.clone()).await?); + match ext.to_str().unwrap() { + "json" => Box::pin(buf_reader), + "gz" => Box::pin(GzipDecoder::new(buf_reader)), + "zstd" => Box::pin(ZstdDecoder::new(buf_reader)), + "bz2" => Box::pin(BzDecoder::new(buf_reader)), + _ => anyhow::bail!("Unknown extension") + } + } + None => anyhow::bail!("Could not determine archive format") + }; + let mut file = BufReader::new(file); + let mut line = String::new(); + while let Ok(size) = file.read_line(&mut line).await { + if size == 0 { + break; + } + + if let Ok(event) = serde_json::from_str::(&line[..size]) { + let ev_id = EventId(hex::decode(&event.id)?.as_slice().try_into()?); + if self.ids.insert(ev_id) { + fx(&event); + } + } + line.clear(); + } + } + + Ok(()) + } +} \ No newline at end of file diff --git a/src/event.rs b/src/event.rs new file mode 100644 index 0000000..ef41892 --- /dev/null +++ b/src/event.rs @@ -0,0 +1,12 @@ +use serde::{Deserialize, Serialize}; + +#[derive(Serialize, Deserialize, Debug)] +pub struct NostrEvent { + pub id: String, + pub created_at: u64, + pub kind: u32, + pub pubkey: String, + pub sig: String, + pub content: String, + pub tags: Vec>, +} \ No newline at end of file diff --git a/src/main.rs b/src/main.rs new file mode 100644 index 0000000..f0f1a6c --- /dev/null +++ b/src/main.rs @@ -0,0 +1,37 @@ +mod event; +mod cursor; + +use std::collections::HashMap; +use std::path::PathBuf; +use clap::Parser; +use crate::cursor::NostrCursor; + +#[derive(Parser)] +#[command(about, version)] +struct Args { + #[arg(long)] + pub dir: String, +} + +#[tokio::main] +async fn main() -> Result<(), anyhow::Error> { + let args = Args::parse(); + + let dir: PathBuf = args.dir.parse()?; + println!("Reading data from: {}", dir.to_str().unwrap()); + + let mut event_dates: HashMap = HashMap::new(); + let mut cursor = NostrCursor::new(dir); + cursor.walk(|e| { + let day = e.created_at / (60 * 60 * 24); + if let Some(x) = event_dates.get_mut(&day) { + *x += 1u64; + } else { + event_dates.insert(day, 1); + } + }).await?; + for (day, count) in event_dates { + println!("{}: {}", day, count); + } + Ok(()) +}