Add rust-based nginx log parsing implementation

reporting/rust/Cargo.lock

+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "aho-corasick"
+version = "0.7.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc936419f96fa211c1b9166887b38e5e40b19958e5b895be7c1f93adec7071ac"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "android_system_properties"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
+
+[[package]]
+name = "bumpalo"
+version = "3.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d261e256854913907f67ed06efbc3338dfe6179796deefc1ff763fc1aee5535"
+
+[[package]]
+name = "cc"
+version = "1.0.79"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "50d30906286121d95be3d479533b458f87493b30a4b5f79a607db8f5d11aa91f"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "chrono"
+version = "0.4.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "16b0a3d9ed01224b22057780a37bb8c5dbfe1be8ba48678e7bf57ec4b385411f"
+dependencies = [
+ "iana-time-zone",
+ "js-sys",
+ "num-integer",
+ "num-traits",
+ "time",
+ "wasm-bindgen",
+ "winapi",
+]
+
+[[package]]
+name = "codespan-reporting"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3538270d33cc669650c4b093848450d380def10c331d38c768e34cac80576e6e"
+dependencies = [
+ "termcolor",
+ "unicode-width",
+]
+
+[[package]]
+name = "core-foundation-sys"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5827cebf4670468b8772dd191856768aedcb1b0278a04f989f7766351917b9dc"
+
+[[package]]
+name = "cxx"
+version = "1.0.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86d3488e7665a7a483b57e25bdd90d0aeb2bc7608c8d0346acf2ad3f1caf1d62"
+dependencies = [
+ "cc",
+ "cxxbridge-flags",
+ "cxxbridge-macro",
+ "link-cplusplus",
+]
+
+[[package]]
+name = "cxx-build"
+version = "1.0.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48fcaf066a053a41a81dfb14d57d99738b767febb8b735c3016e469fac5da690"
+dependencies = [
+ "cc",
+ "codespan-reporting",
+ "once_cell",
+ "proc-macro2",
+ "quote",
+ "scratch",
+ "syn",
+]
+
+[[package]]
+name = "cxxbridge-flags"
+version = "1.0.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a2ef98b8b717a829ca5603af80e1f9e2e48013ab227b68ef37872ef84ee479bf"
+
+[[package]]
+name = "cxxbridge-macro"
+version = "1.0.91"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "086c685979a698443656e5cf7856c95c642295a38599f12fb1ff76fb28d19892"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "iana-time-zone"
+version = "0.1.53"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "64c122667b287044802d6ce17ee2ddf13207ed924c712de9a66a5814d5b64765"
+dependencies = [
+ "android_system_properties",
+ "core-foundation-sys",
+ "iana-time-zone-haiku",
+ "js-sys",
+ "wasm-bindgen",
+ "winapi",
+]
+
+[[package]]
+name = "iana-time-zone-haiku"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0703ae284fc167426161c2e3f1da3ea71d94b21bedbcc9494e92b28e334e3dca"
+dependencies = [
+ "cxx",
+ "cxx-build",
+]
+
+[[package]]
+name = "js-sys"
+version = "0.3.61"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "445dde2150c55e483f3d8416706b97ec8e8237c307e5b7b4b8dd15e6af2a0730"
+dependencies = [
+ "wasm-bindgen",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.139"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79"
+
+[[package]]
+name = "link-cplusplus"
+version = "1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ecd207c9c713c34f95a097a5b029ac2ce6010530c7b49d7fea24d977dede04f5"
+dependencies = [
+ "cc",
+]
+
+[[package]]
+name = "log"
+version = "0.4.17"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "abb12e687cfb44aa40f41fc3978ef76448f9b6038cad6aef4259d3c095a2382e"
+dependencies = [
+ "cfg-if",
+]
+
+[[package]]
+name = "memchr"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
+
+[[package]]
+name = "nginx-parser"
+version = "0.1.0"
+dependencies = [
+ "chrono",
+ "regex",
+]
+
+[[package]]
+name = "num-integer"
+version = "0.1.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "225d3389fb3509a24c93f5c29eb6bde2586b98d9f016636dff58d7c6f7569cd9"
+dependencies = [
+ "autocfg",
+ "num-traits",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "578ede34cf02f8924ab9447f50c28075b4d3e5b269972345e7e0372b38c6cdcd"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.17.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7e5500299e16ebb147ae15a00a942af264cf3688f47923b8fc2cd5858f23ad3"
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.51"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d727cae5b39d21da60fa540906919ad737832fe0b1c165da3a34d6548c849d6"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "regex"
+version = "1.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48aaa5748ba571fb95cd2c85c09f629215d3a6ece942baa100950af03a34f733"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.6.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
+
+[[package]]
+name = "scratch"
+version = "1.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddccb15bcce173023b3fedd9436f882a0739b8dfb45e4f6b6002bee5929f61b2"
+
+[[package]]
+name = "syn"
+version = "1.0.107"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f4064b5b16e03ae50984a5a8ed5d4f8803e6bc1fd170a3cda91a1be4b18e3f5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "termcolor"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "be55cf8942feac5c765c2c993422806843c9a9a45d4d5c407ad6dd2ea95eb9b6"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "time"
+version = "0.1.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b797afad3f312d1c66a56d11d0316f916356d11bd158fbc6ca6389ff6bf805a"
+dependencies = [
+ "libc",
+ "wasi",
+ "winapi",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "84a22b9f218b40614adcb3f4ff08b703773ad44fa9423e4e0d346d5db86e4ebc"
+
+[[package]]
+name = "unicode-width"
+version = "0.1.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b"
+
+[[package]]
+name = "wasi"
+version = "0.10.0+wasi-snapshot-preview1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a143597ca7c7793eff794def352d41792a93c481eb1042423ff7ff72ba2c31f"
+
+[[package]]
+name = "wasm-bindgen"
+version = "0.2.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "31f8dcbc21f30d9b8f2ea926ecb58f6b91192c17e9d33594b3df58b2007ca53b"
+dependencies = [
+ "cfg-if",
+ "wasm-bindgen-macro",
+]
+
+[[package]]
+name = "wasm-bindgen-backend"
+version = "0.2.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "95ce90fd5bcc06af55a641a86428ee4229e44e07033963a2290a8e241607ccb9"
+dependencies = [
+ "bumpalo",
+ "log",
+ "once_cell",
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-macro"
+version = "0.2.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c21f77c0bedc37fd5dc21f897894a5ca01e7bb159884559461862ae90c0b4c5"
+dependencies = [
+ "quote",
+ "wasm-bindgen-macro-support",
+]
+
+[[package]]
+name = "wasm-bindgen-macro-support"
+version = "0.2.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2aff81306fcac3c7515ad4e177f521b5c9a15f2b08f4e32d823066102f35a5f6"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+ "wasm-bindgen-backend",
+ "wasm-bindgen-shared",
+]
+
+[[package]]
+name = "wasm-bindgen-shared"
+version = "0.2.84"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0046fef7e28c3804e5e38bfa31ea2a0f73905319b677e57ebe37e49358989b5d"
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-util"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

reporting/rust/Cargo.toml

+[package]
+name = "nginx-parser"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+chrono = "0.4.23"
+regex = "1.7.1"

reporting/rust/src/main.rs

+use chrono::DateTime;
+use regex::Regex;
+use std::collections::HashMap;
+use std::io::{self, BufRead};
+
+fn main() {
+    // TODO: argument parsing
+
+    let file_download_regex =
+        Regex::new(r"GET /records/(\w+\-\w+)/files/(.*?)(\?download=1|\s)").unwrap();
+    let export_regex = Regex::new(r"GET /records/(\w+\-\w+)/export/").unwrap();
+    let landing_page_regex = Regex::new(r"GET /records/(\w+\-\w+)\s").unwrap();
+    let timestamp_regex =
+        Regex::new(r"\[(\d{2}/\w{3}/\d{4}:\d{2}:\d{2}:\d{2}\s+.?\d{0,4})\]").unwrap();
+
+    let mut record_views = HashMap::new();
+    let mut file_downloads = HashMap::new();
+    let mut record_exports = HashMap::new();
+
+    for line in io::stdin().lock().lines() {
+        let line = line.unwrap();
+
+        // check the line for a timestamp and parse it
+        // TODO: capture begin & end timestamps
+        // TODO: `continue` if the parsed timestamp is before the supplied one
+        let timestamp;
+        if timestamp_regex.is_match(&line) {
+            let capture = timestamp_regex.captures(&line).unwrap();
+            timestamp = DateTime::parse_from_str(&capture[1], "%d/%b/%Y:%H:%M:%S %z").unwrap();
+        } else {
+            continue;
+        }
+
+        // check which kind of request it was & for which record
+        if landing_page_regex.is_match(&line) {
+            let cap = landing_page_regex.captures(&line).unwrap();
+            let recid = &cap[1];
+
+            let entry = record_views.entry(String::from(recid)).or_insert(0);
+            *entry += 1;
+
+        } else if file_download_regex.is_match(&line) {
+            let cap = file_download_regex.captures(&line).unwrap();
+            let recid = &cap[1];
+            let file = &cap[2];
+
+            let entry = file_downloads
+                .entry((String::from(recid), String::from(file)))
+                .or_insert(0);
+            *entry += 1;
+
+        } else if export_regex.is_match(&line) {
+            let cap = export_regex.captures(&line).unwrap();
+            let recid = &cap[1];
+
+            let entry = record_exports.entry(String::from(recid)).or_insert(0);
+            *entry += 1;
+        }
+    }
+
+    // TODO: sort & pretty-print the results
+    println!("record views: {:?}", record_views);
+    println!("file downloads: {:?}", file_downloads);
+    println!("record exports: {:?}", record_exports);
+}