Cynical Software

C Regex

Basics

Any char (alpha)	char* p = "."; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Any char (digit)	char* p = "."; char* s = "2";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Any char (punct)	char* p = "."; char* s = ";";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Any char (\n)	// '.' matches anything except newline \n // but only in REG_NEWLINE mode! char* p = "."; char* s = "\n";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	false
Specific char (alpha)	char* p = "a"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Specific char (alpha)	char* p = "a"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Specific char (oct)	char* p = "\141"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Specific char (oct)	char* p = "\141"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Specific char (hex)	char* p = "\x61"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Specific char (hex)	char* p = "\x61"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false

Anchor start

Start of string	char* p = "^hello"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Start of string	char* p = "^world"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Start of line	char* p = "^world"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	true
Start of line	char* p = "^world"; char* s = "hello world";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	false
Start of word	char* p = "\\bworld"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Start of word	char* p = "\\bworld"; char* s = "helloworld";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Start of buffer	char* p = "\\`hello"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	true
Start of buffer	char* p = "\\`world"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	false

Anchor end

End of string	char* p = "world$"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
End of string	char* p = "hello$"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
End of line	char* p = "hello$"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	true
End of line	char* p = "hello$"; char* s = "hello world";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	false
End of word	char* p = "hello\\b"; char* s = "hello world";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
End of word	char* p = "hello\\b"; char* s = "helloworld";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
End of buffer	char* p = "world\\'"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	true
End of buffer	char* p = "hello\\'"; char* s = "hello\nworld";	regcomp(&r, p, REG_NEWLINE); t=(regexec(&r, s, n, m, 0)==0);	false

Repeats

Zero or more (0)	char* p = "ab"; char s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Zero or more (1)	char* p = "ab"; char s = "ab";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Zero or more (>1)	char* p = "ab"; char s = "aaaaaab";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
One or more (0)	char* p = "a+b"; char* s = "b";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
One or more (1)	char* p = "a+b"; char* s = "ab";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
One or more (>1)	char* p = "a+b"; char* s = "aaaaaab";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Zero or one (0)	char* p = "ca?b"; char* s = "cb";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Zero or one (1)	char* p = "ca?b"; char* s = "cab";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Zero or one (>1)	char* p = "ca?b"; char* s = "caab";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
N (N)	char* p = "^a{2}$"; char* s = "aa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
N (>N)	char* p = "^a{2}$"; char* s = "aaa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
N (<N)	char* p = "^a{2}$"; char* s = "a";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
N or more (N)	char* p = "^a{2,}$"; char* s = "aa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
N or more (>N)	char* p = "^a{2,}$"; char* s = "aaaaaaa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
N or more (<N)	char* p = "^a{2,}$"; char* s = "a";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
N or less (N)	char* p = "^a{,2}$"; char* s = "aa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
N or less (<N)	char* p = "^a{,2}$"; char* s = "a";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
N or less (>N)	char* p = "^a{,2}$"; char* s = "aaa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
Between N and M (N)	char* p = "^a{2,3}$"; char* s = "aa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Between N and M (M)	char* p = "^a{2,3}$"; char* s = "aaa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Between N and M (<N)	char* p = "^a{2,3}$"; char* s = "a";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
Between N and M (>M)	char* p = "^a{2,3}$"; char* s = "aaaa";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false

Alternatives

String A or B (A)	char* p = "abc\|def"; char* s = "abc";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
String A or B (B)	char* p = "abc\|def"; char* s = "def";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
String A or B (neither)	char* p = "abc\|def"; char* s = "hello";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false
Grouped A or B (A)	char* p = "abc(d\|ef)"; char* s = "abcd";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Grouped A or B (B)	char* p = "abc(d\|ef)"; char* s = "abcef";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	true
Grouped A or B (neither)	char* p = "abc(d\|ef)"; char* s = "abcf";	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0)==0);	false

Character classes

Literal (included)	char* p = "[abc]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Literal (included)	char* p = "[abc]"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Literal (excluded)	char* p = "[abc]"; char* s = "d";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Range (inside)	char* p = "[a-f]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Range (inside)	char* p = "[a-f]"; char* s = "c";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Range (outside)	char* p = "[a-f]"; char* s = "g";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Negated literal (excluded)	char* p = "[^abc]"; char* s = "d";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Negated literal (included)	char* p = "[^abc]"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Negated range (outside)	char* p = "[^c-g]"; char* s = "b";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Negated range (outside)	char* p = "[^c-g]"; char* s = "h";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Negated range (inside)	char* p = "[^c-g]"; char* s = "c";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Negated range (inside)	char* p = "[^c-g]"; char* s = "g";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false

POSIX character classes

Uppercase letters	char* p = "[[:upper:]]"; char* s = "A";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Uppercase letters	char* p = "[[:upper:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Uppercase letters	char* p = "[[:upper:]]"; char* s = "1";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Uppercase letters	char* p = "[[:upper:]]"; char* s = "-";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Lowercase letters	char* p = "[[:lower:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Lowercase letters	char* p = "[[:lower:]]"; char* s = "A";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Lowercase letters	char* p = "[[:lower:]]"; char* s = "1";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Lowercase letters	char* p = "[[:lower:]]"; char* s = "-";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
All letters	char* p = "[[:alpha:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
All letters	char* p = "[[:alpha:]]"; char* s = "A";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
All letters	char* p = "[[:alpha:]]"; char* s = "1";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
All letters	char* p = "[[:alpha:]]"; char* s = ",";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
All letters and digits	char* p = "[[:alnum:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
All letters and digits	char* p = "[[:alnum:]]"; char* s = "A";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
All letters and digits	char* p = "[[:alnum:]]"; char* s = "1";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
All letters and digits	char* p = "[[:alnum:]]"; char* s = ";";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Digits	char* p = "[[:digit:]]"; char* s = "0";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Digits	char* p = "[[:digit:]]"; char* s = "5";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Digits	char* p = "[[:digit:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Digits	char* p = "[[:digit:]]"; char* s = "B";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Digits	char* p = "[[:digit:]]"; char* s = ".";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Hexadecimal digits	char* p = "[[:xdigit:]]"; char* s = "0";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Hexadecimal digits	char* p = "[[:xdigit:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Hexadecimal digits	char* p = "[[:xdigit:]]"; char* s = "B";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Hexadecimal digits	char* p = "[[:xdigit:]]"; char* s = "g";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Punctuation	char* p = "^[[:punct:]]$"; char s = ".,;:-/@#~%${}()[]+";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Punctuation	char* p = "[[:punct:]]"; char* s = "a";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Punctuation	char* p = "[[:punct:]]"; char* s = "2";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Punctuation	char* p = "[[:punct:]]"; char* s = " ";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Whitespace	char* p = "^[[:space:]]$"; char s = " \r \n \t \t ";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Whitespace	char* p = "^[[:space:]]$"; char s = "abc";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false
Blanks	char* p = "^[[:blank:]]$"; char s = " \t \t";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	true
Blanks	char* p = "^[[:blank:]]$"; char s = "\n";	regcomp(&r, p, 0); t=(regexec(&r, s, n, m, 0)==0);	false

Capture groups

Group 1	char* p = "([0-9]+)([a-z]+)"; char* s = "123abc"; i=1; // group 1	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	123
Group 2	char* p = "([0-9]+)([a-z]+)"; char* s = "123abc"; i=2; // group 2	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	abc
Optional group 1 - matched	char* p = "([0-9]+)([a-z]+)"; char s = "123abc"; i=1; // group 1	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	123
Optional group 1 - not matched	char* p = "([0-9]+)([a-z]+)"; char s = "abc"; i=1; // group 1	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; if (strlen(g)==0) { strcpy(g,"None"); } }	None
Group 2 following optional group not matched	char* p = "([0-9]+)([a-z]+)"; char s = "abc"; i=2; // group 2	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	abc
Complete match	char* p = "([0-9]+)-([a-z]+)"; char s = "123-abc"; i=0;	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	123-abc
Nested group 1	char* p = "(([0-9]+)([a-z]+))([A-Z]+)"; char* s = "123abcDEF"; i=1;	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	123abc
Nested group 2	char* p = "(([0-9]+)([a-z]+))([A-Z]+)"; char* s = "123abcDEF"; i=2;	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	123
Nested group 3	char* p = "(([0-9]+)([a-z]+))([A-Z]+)"; char* s = "123abcDEF"; i=3;	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	abc
Nested group 4	char* p = "(([0-9]+)([a-z]+))([A-Z]+)"; char* s = "123abcDEF"; i=4;	regcomp(&r, p, REG_EXTENDED); t=(regexec(&r, s, n, m, 0) == 0); if (t) { len = m[i].rm_eo - m[i].rm_so; strncpy(g, s + m[i].rm_so, len); g[len] = '\0'; }	DEF