Regular Expressions 101

Save & Share

Flavor

  • PCRE2 (PHP >=7.3)
  • PCRE (PHP <7.3)
  • ECMAScript (JavaScript)
  • Python
  • Golang
  • Java 8
  • .NET 7.0 (C#)
  • Rust
  • Regex Flavor Guide

Function

  • Match
  • Substitution
  • List
  • Unit Tests

Tools

Sponsors
There are currently no sponsors. Become a sponsor today!
An explanation of your regex will be automatically generated as you type.
Detailed match information will be displayed here automatically.
  • All Tokens
  • Common Tokens
  • General Tokens
  • Anchors
  • Meta Sequences
  • Quantifiers
  • Group Constructs
  • Character Classes
  • Flags/Modifiers
  • Substitution
  • A single character of: a, b or c
    [abc]
  • A character except: a, b or c
    [^abc]
  • A character in the range: a-z
    [a-z]
  • A character not in the range: a-z
    [^a-z]
  • A character in the range: a-z or A-Z
    [a-zA-Z]
  • Any single character
    .
  • Alternate - match either a or b
    a|b
  • Any whitespace character
    \s
  • Any non-whitespace character
    \S
  • Any digit
    \d
  • Any non-digit
    \D
  • Any word character
    \w
  • Any non-word character
    \W
  • Non-capturing group
    (?:...)
  • Capturing group
    (...)
  • Zero or one of a
    a?
  • Zero or more of a
    a*
  • One or more of a
    a+
  • Exactly 3 of a
    a{3}
  • 3 or more of a
    a{3,}
  • Between 3 and 6 of a
    a{3,6}
  • Start of string
    ^
  • End of string
    $
  • A word boundary
    \b
  • Non-word boundary
    \B

Regular Expression
No Match

/
/
g

Test String

Code Generator

Language

Generated Code

# coding=utf8 # the above tag defines encoding for this document and is for Python 2.x compatibility import re regex = r"(\/)(\*)(.|\n)*?\2\1|(\/\/.*)" test_str = ("#include<stdio.h>\n" "#include<stdlib.h>\n" "typedef struct Node\n" "{\n" " int data;\n" " struct Node *next;\n" " struct Node *prev;\n" "}node;\n" "void insert(node *pointer, int data)\n" "{\n" " /* Iterate through the list till we encounter the last node.*/\n" " while(pointer->next!=NULL)\n" " {\n" " pointer = pointer -> next;\n" " }\n" " /* Allocate memory for the new node and put data in it.*/\n" " pointer->next = (node *)malloc(sizeof(node));\n" " (pointer->next)->prev = pointer;\n" " pointer = pointer->next;\n" " pointer->data = data;\n" " pointer->next = NULL;\n" "}\n" "int find(node *pointer, int key)\n" "{\n" " pointer = pointer -> next; //First node is dummy node.\n" " /* Iterate through the entire linked list and search for the key. */\n" " while(pointer!=NULL)\n" " {\n" " if(pointer->data == key) //key is found.\n" " {\n" " return 1;\n" " }\n" " pointer = pointer -> next;//Search in the next node.\n" " }\n" " /*Key is not found */\n" " return 0;\n" "}\n" "void delete(node *pointer, int data)\n" "{\n" " /* Go to the node for which the node next to it has to be deleted */\n" " while(pointer->next!=NULL && (pointer->next)->data != data)\n" " {\n" " pointer = pointer -> next;\n" " }\n" " if(pointer->next==NULL)\n" " {\n" " printf(\"Element %d is not present in the list\\n\",data);\n" " return;\n" " }\n" " /* Now pointer points to a node and the node next to it has to be removed */\n" " node *temp;\n" " temp = pointer -> next;\n" " /*temp points to the node which has to be removed*/\n" " pointer->next = temp->next;\n" " temp->prev = pointer;\n" " /*We removed the node which is next to the pointer (which is also temp) */\n" " free(temp);\n" " /* Beacuse we deleted the node, we no longer require the memory used for it .\n" " free() will deallocate the memory.\n" " */\n" " return;\n" "}\n" "void print(node *pointer)\n" "{\n" " if(pointer==NULL)\n" " {\n" " return;\n" " }\n" " printf(\"%d \",pointer->data);\n" " print(pointer->next);\n" "}\n" "int main()\n" "{\n" " /* start always points to the first node of the linked list.\n" " temp is used to point to the last node of the linked list.*/\n" " node *start,*temp;\n" " start = (node *)malloc(sizeof(node));\n" " temp = start;\n" " temp -> next = NULL;\n" " temp -> prev = NULL;\n" " /* Here in this code, we take the first node as a dummy node.\n" " The first node does not contain data, but it used because to avoid handling special cases\n" " in insert and delete functions.\n" " */\n" " printf(\"1. Insert\\n\");\n" " printf(\"2. Delete\\n\");\n" " printf(\"3. Print\\n\");\n" " printf(\"4. Find\\n\");\n" " while(1)\n" " {\n" " int query;\n" " scanf(\"%d\",&query);\n" " if(query==1)\n" " {\n" " int data;\n" " scanf(\"%d\",&data);\n" " insert(start,data);\n" " }\n" " else if(query==2)\n" " {\n" " int data;\n" " scanf(\"%d\",&data);\n" " delete(start,data);\n" " }\n" " else if(query==3)\n" " {\n" " printf(\"The list is \");\n" " print(start->next);\n" " printf(\"\\n\");\n" " }\n" " else if(query==4)\n" " {\n" " int data;\n" " scanf(\"%d\",&data);\n" " int status = find(start,data);\n" " if(status)\n" " {\n" " printf(\"Element Found\\n\");\n" " }\n" " else\n" " {\n" " printf(\"Element Not Found\\n\");\n\n" " }\n" " }\n" " }\n\n\n" "}") matches = re.finditer(regex, test_str) for matchNum, match in enumerate(matches, start=1): print ("Match {matchNum} was found at {start}-{end}: {match}".format(matchNum = matchNum, start = match.start(), end = match.end(), match = match.group())) for groupNum in range(0, len(match.groups())): groupNum = groupNum + 1 print ("Group {groupNum} found at {start}-{end}: {group}".format(groupNum = groupNum, start = match.start(groupNum), end = match.end(groupNum), group = match.group(groupNum))) # Note: for Python 2.7 compatibility, use ur"" to prefix the regex and u"" to prefix the test string and substitution.

Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Python, please visit: https://docs.python.org/3/library/re.html