01_reModule.py

#!/usr/bin/env python
# coding: utf-8

# ================================================================
# EXECUTIVE SUMMARY : re module** for working with regular expressions
# ================================================================
# This script demonstrates Python's **re module** for working with regular expressions.

# The re module in Python is a built-in library for working with regular expressions (regex). Regular expressions are sequences of characters that define search patterns, enabling tasks such as text searching, extraction, and manipulation. 


# Purpose:
# - To showcase how regex can be used for text searching, replacement, and pattern matching.
# - To provide recruiter-friendly explanations of regex syntax and its practical applications.

# Why it matters:
# - Regular expressions are essential for text processing tasks such as cleaning data,
#   validating inputs, and extracting information.
# - Recruiters value candidates who can explain both the *how* and the *why* of regex usage.

# Techniques highlighted:
# - `re.sub()` for substitution.
# - `re.search()` for pattern matching.
# - Regex metacharacters: `\d`, `\D`, `\w`, `\W`, `\s`, `\S`, `^`, `$`, `[ ]`, `[^ ]`.

"""re.sub(pattern, repl, string, count=0, flags=0):

pattern: The regular expression to match.

repl: The replacement string.

string: The input string.

count: Optional; the maximum number of replacements to make. Default is 0, which means all occurrences are replaced.

flags: Optional; flags to modify the behavior of the regex.

"""

# ================================================================


# ==== Step 1: Import re Module ====
import re


# ==== Step 2: Basic Substitution ====
sentence = 'Hi, I am sachin'
new_sen = re.sub(r'sachin', 'rahul', sentence)
print(new_sen)
# Explanation:
# - `re.sub(pattern, repl, string)` replaces occurrences of `pattern` with `repl`.
# - Here, "sachin" is replaced with "rahul".


# ==== Step 3: Case-Insensitive Replacement ====
Ignor = re.sub(r'sachin', 'Ajinkya', sentence, flags=re.IGNORECASE)
print(Ignor)
# Explanation:
# - `flags=re.IGNORECASE` makes the match case-insensitive.


# ==== Step 4: Digit Replacement ====
info = 'Sachin is from Nagpur have 2 bikes and 4 bicycle'
print(info)

new_info = re.sub(r'\d', '#', info)
print(new_info)
# Explanation:
# - `\d` matches any digit (0–9).
# - All digits are replaced with "#".

new_info1 = re.sub(r'\D', '#', info)
print(new_info1)
# - `\D` matches any non-digit character.

new_info2 = re.sub(r'[0-9]', '*', info)
print(new_info2)
# - `[0-9]` explicitly matches digits.


# ==== Step 5: Word and Non-Word Characters ====
new_info3 = re.sub(r'\w', '#', info)
print(new_info3)
# - `\w` matches word characters (letters, digits, underscores).
#  function replaces each word character (\w) with the character #.
# \w: Matches word characters (letters, digits, and underscores).
# Using \w is useful when you want to replace all alphanumeric characters and underscores in a string.



new_info4 = re.sub(r'\W', '#', info)
print(new_info4)
# - `\W` matches non-word characters (spaces, punctuation).


# ==== Step 6: Whitespace and Non-Whitespace ====
new_info5 = re.sub(r'\s', '#', info)
print(new_info5)

# - `\s` matches whitespace characters.
# r'\s': This is a regular expression pattern that matches any whitespace character, including spaces, tabs, newlines, etc.
# Each matched whitespace character is replaced with the specified replacement string, which is # in this case.


new_info6 = re.sub(r'\S', '#', info)
print(new_info6)
# - `\S` matches non-whitespace characters.
# r'\S': This is a regular expression pattern that matches any non-space character.
# The \S pattern matches any single non-space character in the string.
# Non-space characters include letters, numbers, punctuation, and special characters.


# ==== Step 7: Character Classes ====
new_info7 = re.sub(r'[a-z]', '#', info)
print(new_info7)
# - `[a-z]` matches lowercase letters.

new_info8 = re.sub(r'[a-zA-Z]', '#', info)
print(new_info8)
# - `[a-zA-Z]` matches both lowercase and uppercase letters.

new_info9 = re.sub(r'[a-zA-Z0-9]', '#', info)
print(new_info9)
# - `[a-zA-Z0-9]` matches alphanumeric characters.


# ==== Step 8: Specific Character Matching ====
new_sen = re.sub(r'[rw]', '#', info)
print(new_sen)
# - `[rw]` matches "r" or "w".

new_sen1 = re.sub(r'[^rw]', '#', info)
print(new_sen1)
# - `[^rw]` matches any character except "r" or "w".


# ==== Step 9: Searching Patterns ====
new_sen2 = re.search(r'from', info)
print(new_sen2)
# - `re.search()` finds the first occurrence of "from".


# ==== Step 10: Empty String Matching ====
unique = ""
sen_unique = re.search(r'.*', unique)
print(sen_unique)
# - `.*` matches zero or more characters (including empty string).


sen_unique1 = re.search(r'.+', unique)
print(sen_unique1)
# - `.+` requires at least one character (fails on empty string).
# The .+ pattern matches one or more characters. 
# This means it cannot match an empty string.


# ==== Step 11: Anchors (^ and $) ====
sen_search = re.search(r'^r', info)
print(sen_search)
# - `^r` matches "r" at the start of the string.

sen_search1 = re.search(r'^S', info)
print(sen_search1)
# - `^S` matches "S" at the start of the string.
# r'^S': This is a regular expression pattern that matches the character "r" only if it is at the beginning of the string.
# The ^ symbol indicates the start of the string.



sen_search2 = re.search(r'2$', info)
print(sen_search2)
# - `2$` matches "2" at the end of the string.
# r'2$': This is a regular expression pattern that matches the digit "2" only if it is at the end of the string. 
# The $ symbol indicates the end of the string.



sen_search3 = re.search(r'bicycle$', info)
print(sen_search3)
# - `bicycle$` matches "bicycle" at the end of the string.
# r'bicycle$': This is a regular expression pattern that matches the word "bicycle" only if it is at the end of the string. 
# The $ symbol indicates the end of the string.


# ==== Step 12: Advanced Substitution ====
Info2 = "Hello, I am sachin $ 30 years old and have 2 dogs."

sen_search4 = re.sub(r'sachin', 'Ashwin', Info2)
print(sen_search4)
# - Replace "sachin" with "Ashwin".

print(re.sub(r'^', '#', Info2))
# - Adds "#" at the start of the string.
# re.sub(r'\^', '#', info2) does nothing if there are no caret characters in the string


sen_search5 = re.sub(r'\$', '#', Info2)
print(sen_search5)
#  Each matched dollar sign is replaced with the specified replacement string, which is # in this case.


# ================================================================
# FINAL SUMMARY
# ================================================================

# - We explored Python's `re` module for regex operations.
# - Key functions: `re.sub()` for substitution, `re.search()` for pattern matching.
# - Regex patterns demonstrated:
#   * `\d`, `\D` → digits vs non-digits
#   * `\w`, `\W` → word vs non-word characters
#   * `\s`, `\S` → whitespace vs non-whitespace
#   * `[ ]`, `[^ ]` → character classes and negation
#   * `^`, `$` → anchors for start/end of string
# - Practical applications: text cleaning, anonymization, validation, and extraction.

# ================================================================