StrIdx 0.1.3 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 52d40e64a5ace0231828bdbbe6fd94475ab5986d0c1fb7e35e0ce18463a97ae0
-  data.tar.gz: e1cdcc2ed9f377b2acb049a9fb6de22f24acdbd6e3552748b1307342c10b6cf7
+  metadata.gz: 6d559876ad4cbf26be66db682e45701f80359d9b4752fdc61042c665f62c3000
+  data.tar.gz: 6c0aa9cce9cea114ada2d1dfb08a833f2d338a3d9815c2a5dc32ceb15186bfe7
 SHA512:
-  metadata.gz: f3c27923a568fe5916c17e91766066362a965abf9568b21a4daa269cd16a8a4778248ae935b26502aa482aad4807908d401989e7ebfb88d1fbdb011b0c240b60
-  data.tar.gz: f94dda8d71931c18ae3dc6b58204edda7ffd649bc7452a74fdba4929d6092183e99bf99d7b3632be5bafccfd0be7a877f5513c8c3e72e814dcca08bd79a9b217
+  metadata.gz: 6f9bf0a17ee3541b0dfc2e296bbb78dcb2c86c821427ffff5b1d6a86b7f1a7df53d428e5fc447a148c561177a495c0a9013cf1ebe18fd074fbc478bf7ad81fec
+  data.tar.gz: 0cdead8fab1925979337d5fa5ee890c42c654006db3aed2274e7a0e4a41cc50e157a346b28cbb2f5ce2dee35876010d503602932addcf06f5409a75b8cb5c81c

data/CMakeLists.txt

@@ -0,0 +1,27 @@
+cmake_minimum_required(VERSION 3.14)
+
+project(my_project)
+# https://github.com/google/googletest/issues/4000
+include(FetchContent)
+FetchContent_Declare(
+  googletest
+  URL https://github.com/google/googletest/archive/58d77fa8070e8cec2dc1ed015d66b454c8d78850.zip # release-1.12.1
+)
+
+set(gtest_force_shared_crt ON CACHE BOOL "" FORCE)
+FetchContent_MakeAvailable(googletest)
+
+enable_testing()
+
+add_executable(
+  stridx_test
+  unittest.cpp
+)
+target_link_libraries(
+  stridx_test
+  GTest::gtest_main
+)
+
+include(GoogleTest)
+gtest_discover_tests(stridx_test)
+

data/Gemfile

@@ -0,0 +1,5 @@
+source "https://rubygems.org"
+
+gemspec
+
+

data/Makefile

@@ -1,6 +1,7 @@
 all: demo
 
 demo: *.hpp *.cpp Makefile
+	#g++  -Wall -O0 -g -lstdc++ demo.cpp -o demo
 	g++  -Wall -O3 -lstdc++ demo.cpp -o demo
 	
 clean: 

data/README.md

@@ -5,8 +5,14 @@ The fuzziness means that candidate filepaths do not need to include exact match
 
 The library can be applied for UTF-8 data also, although there is a small bias in scoring for multibyte characters.
 
+1. [String similarity calculation](#stringsim)
+2. [Interfaces](#interfaces)
+    1. [Command line](#comm)
+    2. [Ruby](#ruby)
+    3. [C++](#cpp)
 
-## String similarity calculation
+
+## String similarity calculation <a name="stringsim"/>
 
 Once the index has been created, the contents can be searched to find the best matching strings. 
 
@@ -37,9 +43,54 @@ and candidate is "./drivers/char/hw_random/nomadik-rng.c", then scores are calcu
     score = score1/(11*11)*0.97 + score1/(11*38)*0.03 = 0.342944
 ```
 
-# Ruby interface
+# Interfaces
+
+## Commandline <a name="comm"/>
+Install instructions (for Ubuntu Linux):
+```
+apt update
+apt install ruby ruby-dev build-essential
+gem install StrIdx
+```
+
+Start indexing server (on background):
+```
+stridx.rb start -- ~/Documents/ ~/Pictures/
+```
+
+Add bash keybindings (Ctrl-t):
+```
+eval "$(stridx.rb bash)"
+
+```
+
+To autostart server, add following line to .bashrc:
+```
+[ ! -f ~/.stridx/sock ] && stridx.rb start -- ~/Documents/ ~/Pictures/
+```
+
+
+Search by pressing <kbd>ctrl</kbd>+<kbd>t</kbd>.  Keys: <kbd>up</kbd>, <kbd>down</kbd>, select with <kbd>enter</kbd>
+
+![screencast](https://github.com/SamiSieranoja/stridx/assets/46612258/b2fd4fa2-37ad-4423-bd5f-d54b24ff6df5)
+
+
+Stop server:
+```
+stridx.rb stop
+```
+In case stop doesn't work, try: `kill $(pgrep -f runserver.rb | tail -n 1)`
+
+Start indexing server (on foreground, to debug):
+```
+stridx.rb run -- ~/Documents/ ~/Pictures/
+```
+
+
+## Ruby
 Install:
 ```
+apt install ruby ruby-dev build-essential
 gem install StrIdx
 ```
 
@@ -114,7 +165,7 @@ Search time: 0.0488 seconds
 ```
 
 
-# C++ API
+## C++ <a name="cpp"/>
 See demo.cpp
 ```cpp
 #include "stridx.hpp"

data/demo.cpp

@@ -1,4 +1,6 @@
 
+#include <sys/resource.h>
+
 #include <condition_variable>
 #include <functional>
 #include <iostream>
@@ -46,7 +48,11 @@ int main() {
   std::string fn_filePaths = "flist.txt";
   std::vector<std::string> v_filePaths = readLinesFromFile(fn_filePaths);
 
-	// Launch indexing to be run on background
+  // int* a = new int[10];
+  // delete(a);
+  // delete(a);
+
+  // Launch indexing to be run on background
   cout << "File paths: " << v_filePaths.size() << std::endl;
   cout << "Start indexing in the background" << std::endl;
   auto start = std::chrono::high_resolution_clock::now();
@@ -60,22 +66,33 @@ int main() {
   std::chrono::duration<double, std::milli> duration_launch = idx_time_launch - start;
   cout << "Indexing launch time (seconds): " << duration_launch.count() / 1000 << "\n";
 
-	// Wait until indexing has finished
+  // Wait until indexing has finished
   idx.waitUntilDone();
 
   auto idx_time = std::chrono::high_resolution_clock::now();
   std::chrono::duration<double, std::milli> duration = idx_time - start;
   cout << "Indexing finished time for " << v_filePaths.size()
        << " file paths (seconds): " << duration.count() / 1000 << "\n";
+       
+       
+  cout << "DEBUG" << std::endl;
+	// idx.cm.debug();
+  cout << "END DEBUG" << std::endl;
 
   // Find matching filepaths from the index for the query string "rngnomadriv"
   start = std::chrono::high_resolution_clock::now();
-  std::string query = "rngnomadriv";
+  // std::string query = "rngnomadriv";
+  std::string query = "irqbypass.c";
   for (int i = 0; i < 99; i++) {
-    const vector<pair<float, int>> &results = idx.findSimilar(query, 2);
+    // const vector<pair<float, int>> &results = idx.findSimilar(query, 2);
+    const vector<pair<float, int>> &results = idx.findSim(query);
   }
 
-  const vector<pair<float, int>> &results = idx.findSimilar(query, 2);
+
+  // idx.findSim(query);
+
+  // const vector<pair<float, int>> &results = idx.findSimilar(query, 2);
+  const vector<pair<float, int>> &results = idx.findSim(query);
   auto search_time = std::chrono::high_resolution_clock::now();
   duration = search_time - start;
   cout << "Search time for 100 queries (seconds): " << duration.count() / 1000 << "\n";
@@ -91,6 +108,20 @@ int main() {
     }
   }
 
+    // std::cout << "Size of MyClass: " << sizeof(StrIdx::CharMap) << " bytes" << std::endl;
+    // std::cout << "Size of CharMap3: " << sizeof(StrIdx::CharMap3) << " bytes" << std::endl;
+    std::cout << "Size of CharNode: " << sizeof(StrIdx::CharNode) << " bytes" << std::endl;
+    std::cout << "Size of int: " << sizeof(int) << " bytes" << std::endl;
+
+  struct rusage usage;
+  getrusage(RUSAGE_SELF, &usage);
+  std::cout << "Maximum resident set size: " << usage.ru_maxrss << " kilobytes" << std::endl;
+  std::cout << "Integral shared memory size: " << usage.ru_ixrss << " kilobytes" << std::endl;
+  std::cout << "Integral unshared data size: " << usage.ru_idrss << " kilobytes" << std::endl;
+  std::cout << "Integral unshared stack size: " << usage.ru_isrss << " kilobytes" << std::endl;
+  
+  
+
   return 0;
 }
 

data/exe/stridx.rb

@@ -0,0 +1,21 @@
+#!/usr/bin/env ruby
+require 'fileutils'
+
+$:.unshift File.dirname(__FILE__) + "/.."
+
+if ARGV[0] == "tty"
+  require "stridx-tty.rb"
+  StrIdxTTY.run
+elsif ARGV[0] == "bash"
+  puts %q/
+  bind -m emacs-standard '"\er": redraw-current-line';
+  bind -m emacs-standard '"\C-t": " \C-b\C-k \C-u`stridx.rb tty`\e\C-e\er\C-a\C-y\C-h\C-e\e \C-y\ey\C-x\C-x\C-f"'
+/
+else
+  require "daemons"
+  
+  pid_dir_path = File.expand_path("~/.config/stridx/")
+  FileUtils.mkdir_p(pid_dir_path)
+  Daemons.run(File.dirname(__FILE__) + "/../runserver.rb", 
+  {:dir_mode => :normal, :dir => pid_dir_path })
+end