Add read_logs.rb scripts

3 files changed, 85 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
index 22f011b..e10b85f 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,2 +1,3 @@
 /dist-newstyle/
 /config.toml
+/log/
diff --git a/README.md b/README.md
index 2e256cb..e5b8459 100644
--- a/README.md
+++ b/README.md
@@ -25,4 +25,29 @@ and in another session:
 curl localhost:8082
 ```
 
+## read\_logs.rb
+
+read\_logs.rb looks in the `log/` directory for files ending with `.log`,
+`.log.1`, `.log.2.gz`, `.log.3.gz` and so forth. It filters out lines starting
+with a timestamp, `yyyy-mm-ddThh:mm:ss`, followed by random characters and a
+custom string provided as the only command line parameter. Finally
+it outputs all matched content after the provided string along with the date.
+
+The log files are read in the order based on the number in the filename.
+
+For example calling the script as
+
+```sh
+./bin/read_logs.rb 'doctrine.INFO:'
+```
+
+on a log file containing
+`[2025-02-04T19:51:49.356093+01:00] doctrine.INFO: Disconnecting [] []`
+
+will print:
+
+```
+2025-02-04 (Disconnecting [])
+```
+
 ## tea-cleaner
diff --git a/bin/read_logs.rb b/bin/read_logs.rb
new file mode 100755
index 0000000..76627bc
--- /dev/null
+++ b/bin/read_logs.rb
@@ -0,0 +1,59 @@
+#!/usr/bin/env ruby
+
+require 'date'
+require 'zlib'
+require 'pathname'
+
+class Visit
+  attr_accessor :page, :date
+
+  def initialize(match_data)
+    @date = Date.iso8601 match_data[1]
+    @page = match_data[2].strip
+  end
+end
+
+def numeric_extension(filename)
+  if filename.extname == '.gz'
+    filename.sub_ext('').extname[1..-1].to_i
+  elsif filename.extname == '.log'
+    0
+  else
+    filename.extname[1..-1].to_i
+  end
+end
+
+entries = Dir.new('log')
+  .entries
+  .reject { |entry| entry.start_with? '.' }
+  .map { |entry| Pathname.new entry }
+  .sort { |a, b| numeric_extension(b) <=> numeric_extension(a) }
+
+def read_lines(stream)
+  if ARGV.length > 0
+    regex = /([0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2}).+#{ARGV[0]}(.+) /
+  else
+    regex = /([0-9]{4}-[0-9]{2}-[0-9]{2}T[0-9]{2}:[0-9]{2}:[0-9]{2})(.+) /
+  end
+
+  stream
+    .map { |line| line.match regex }
+    .reject { |line| line.nil? }
+    .map { |match_data| Visit.new match_data }
+end
+
+lines_in_all_files = entries.flat_map do |log|
+  log_path = Pathname.new('log') + log
+
+  if log_path.extname == '.gz'
+    File.open log_path.to_s do |file|
+      read_lines Zlib::GzipReader.new(file).readlines
+    end
+  else
+    read_lines File.readlines(log_path.to_s)
+  end
+end
+
+lines_in_all_files.each do |visit|
+  puts "#{visit.date.strftime} (#{visit.page})"
+end