Adding a command to search for a pattern in a file/standard input

pysh.py

@@ -3,6 +3,7 @@
 import os
 import subprocess
 from utils.commands_list import *
+from utils.boyer_moore_algorithm import BoyerMooreAlgorithm
 import calendar
 import getpass
 import shutil
@@ -627,6 +628,24 @@ def do_diff(self, *args):
  else:
  print("pysh: diff: incorrect usage: try 'diff [FILE1] [FILE2]'")
 
+ def do_grep(self, *args):
+ commands = args[0].split()
+ self.save_history("grep " + " ".join(commands))
+ pattern = BoyerMooreAlgorithm(commands[0])
+
+ if '-f' in commands:
+ if os.path.exists(os.getcwd() + '/' + commands[commands.index('-f') - 1]):
+ with open(commands[commands.index('-f') - 1], 'r') as file:
+ line_number = 1
+ for line in file:
+ pattern.find_pattern(line.split(' '), True, line_number)
+ line_number += 1
+ else:
+ print("pysh: grep: {}: No such file or directory".format(commands[commands.index('-f') - 1]))
+
+ else:
+ pattern.find_pattern(commands[1:])
+
  def do_chmod(self, *args):
  gen_args = args[0].split()
 
@@ -788,6 +807,9 @@ def help_kill(self):
  def help_diff(self):
  print(commands_list_manual['diff'])
 
+ def help_grep(self):
+ print(commands_list_manual['grep'])
+
  def help_chmod(self):
  print(commands_list_manual['chmod'])
 

utils/boyer_moore_algorithm.py

@@ -0,0 +1,65 @@
+from colorama import Fore
+
+NO_OF_CHARS = 256
+
+class BoyerMooreAlgorithm():
+ def __init__(self, pattern):
+ self.pattern = pattern
+ self.shift_table = [-1] * NO_OF_CHARS
+
+ # Fill the actual value of last occurrence
+ for char in range(len(pattern)):
+ self.shift_table[ord(pattern[char])] = char;
+
+ def find_pattern(self, source, file = False, line_number = 0):
+ source = " ".join(source)
+ pattern_length = len(self.pattern)
+ result = []
+ source_index = 0
+ while(source_index <= len(source) - pattern_length):
+ j = pattern_length - 1
+
+ '''
+ Keep reducing index j of pattern while
+ characters of pattern and text are matching
+ at this shift source_index
+ '''
+ while j >= 0 and self.pattern[j] == source[source_index+j]:
+ j -= 1
+
+ '''
+ If the pattern is present at current shift,
+ then index j will become -1 after the above loop
+ '''
+ if j < 0:
+ result.append(source_index)
+ ''' 
+ Shift the pattern so that the next character in text
+ aligns with the last occurrence of it in pattern.
+ The condition source_index + pattern_length < len(source) is necessary for the case when
+ pattern occurs at the end of text
+ '''
+ source_index += (pattern_length - self.shift_table[ord(source[source_index + pattern_length])] 
+ if source_index + pattern_length < len(source) else 1)
+ else:
+ '''
+ Shift the pattern so that the bad character in source text
+ aligns with the last occurrence of it in pattern. The
+ max function is used to make sure that we get a positive
+ shift. We may get a negative shift if the last occurrence
+ of bad character in pattern is on the right side of the
+ current character.
+ '''
+ source_index += max(1, j - self.shift_table[ord(source[source_index+j])])
+
+ if file and result != []:
+ print(f"Line {line_number}: ", end = '')
+
+ previos_index = 0
+ for index in result:
+ print(source[previos_index:index], end="")
+ print(Fore.CYAN + source[index:index + len(self.pattern)] + Fore.RESET, end = "")
+ previos_index = index + len(self.pattern)
+
+ if result != []:
+ print('\n')

utils/commands_list.py

@@ -1,8 +1,7 @@
 commands_list = ['lf', 'ldir', 'pwd', 'cd', 'manual', 'mkdir',
  'calendar', 'calc', 'whoami', 'echo', 'rm',
  'cat', 'cp', 'mv', 'date', 'file', 'history',
- 'head', 'tail', 'touch', 'wc', 'ip', 'host', 'arch', 'ps', 'wget', 'kill', 'diff',
- 'chmod']
+ 'head', 'tail', 'touch', 'wc', 'ip', 'host', 'arch', 'ps', 'wget', 'kill', 'diff', 'chmod', 'grep']
 
 commands_list_manual = {
  'exit': "Exits the shell where it is currently running. \nusage: 'exit'",
@@ -36,5 +35,6 @@
  'wget': "Network downloader - download files from internet. \nusage: 'wget [URL]'",
  'kill': "Terminate an unresponsive program. \nusage: 'kill [PID]'",
  'diff': "Compares files line by line. \nusage: 'diff [FILE1] [FILE2]'",
+ 'grep': "Utility for searching plain-text data sets for lines that match a regular expression. \nusage: 'grep [expression] [data-set] -f' {if the data-set is a file}\nusage: 'grep [expression] [data-set]' {if the data-set is an input string}",
  'chmod': "Changes access permissions and the special mode flags of file system objects. \nusage: 'chmod [PERMISSIONS] [FILES]...'"
 }