From 54120e1b3351a4b6adb8c3f8fc98a60cb0ad3836 Mon Sep 17 00:00:00 2001
From: chylex <contact@chylex.com>
Date: Fri, 13 Jan 2023 16:26:03 +0100
Subject: [PATCH] Add access log parser
---
src/log_parser.rs | 58 +++++++++++++++++++++++++++++++++++++++++++++++
src/main.rs | 5 ++--
2 files changed, 61 insertions(+), 2 deletions(-)
create mode 100644 src/log_parser.rs
diff --git a/src/log_parser.rs b/src/log_parser.rs
new file mode 100644
index 0000000..0e860ac
--- /dev/null
+++ b/src/log_parser.rs
@@ -0,0 +1,58 @@
+use std::fmt::{Display, Error, Formatter};
+
+pub struct AccessLogLineParts<'a> {
+ pub time: &'a str,
+ pub remote_host: &'a str,
+ pub request: &'a str,
+ pub response_status: &'a str,
+ pub response_bytes: &'a str,
+ pub response_time_ms: &'a str,
+ pub referer: &'a str,
+ pub user_agent: &'a str,
+}
+
+impl Display for AccessLogLineParts<'_> {
+ fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error> {
+ write!(f, "[{}] {} \"{}\" {} {} {} \"{}\" \"{}\"", self.time, self.remote_host, self.request, self.response_status, self.response_bytes, self.response_time_ms, self.referer, self.user_agent)
+ }
+}
+
+impl<'a> AccessLogLineParts<'a> {
+ pub fn parse(line: &'a str) -> Result<AccessLogLineParts<'a>, ParseError> {
+ let (time, line) = extract_between_chars(line, '[', ']').ok_or(ParseError::TimeBracketsNotFound)?;
+ let (remote_host, line) = next_space_delimited_part(line).ok_or(ParseError::RemoteHostNotFound)?;
+ let (request, line) = extract_between_chars(line.trim_start_matches(' '), '"', '"').ok_or(ParseError::RequestNotFound)?;
+ let (response_status, line) = next_space_delimited_part(line).ok_or(ParseError::ResponseStatusNotFound)?;
+ let (response_bytes, line) = next_space_delimited_part(line).ok_or(ParseError::ResponseBytesNotFound)?;
+ let (response_time_ms, line) = next_space_delimited_part(line).ok_or(ParseError::ResponseTimeNotFound)?;
+ let (referer, line) = extract_between_chars(line.trim_start_matches(' '), '"', '"').ok_or(ParseError::RefererNotFound)?;
+ let (user_agent, _) = extract_between_chars(line.trim_start_matches(' '), '"', '"').ok_or(ParseError::UserAgentNotFound)?;
+ Ok(AccessLogLineParts { time, remote_host, request, response_status, response_bytes, response_time_ms, referer, user_agent })
+ }
+}
+
+fn next_space_delimited_part(str: &str) -> Option<(&str, &str)> {
+ return str.trim_start_matches(' ').split_once(' ')
+}
+
+fn extract_between_chars(str: &str, left_side: char, right_side: char) -> Option<(&str, &str)> {
+ let str = str.trim_start_matches(' ');
+ let next_char = str.chars().next()?;
+ return if next_char == left_side {
+ str.get(1..)?.split_once(right_side)
+ } else {
+ None
+ };
+}
+
+#[derive(Debug, Copy, Clone)]
+pub enum ParseError {
+ TimeBracketsNotFound,
+ RemoteHostNotFound,
+ RequestNotFound,
+ ResponseStatusNotFound,
+ ResponseBytesNotFound,
+ ResponseTimeNotFound,
+ RefererNotFound,
+ UserAgentNotFound,
+}
diff --git a/src/main.rs b/src/main.rs
index 1b769e0..ba10a8c 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -10,9 +10,10 @@ use crate::log_file_pattern::{LogFilePath, parse_log_file_pattern_from_env};
use crate::log_watcher::watch_logs_task;
use crate::web_server::{create_web_server, run_web_server};
-mod log_file_pattern;
-mod log_watcher;
mod apache_metrics;
+mod log_file_pattern;
+mod log_parser;
+mod log_watcher;
mod web_server;
const ACCESS_LOG_FILE_PATTERN: &'static str = "ACCESS_LOG_FILE_PATTERN";