c语言正则表达式检索文件名,正则表达式查找所有的搜索关键词匹配
我会推荐一个工具，如gplex/gppg,GOLD，ANTLR来做这种工作，特别是因为你会评估解析结果。
如果你坚持使用.NET RegEx，我建议你看看使用Balancing Group Definitions。
如果你想要一些更容易处理的事情，那么我会考虑编写一个简单的Recursive Descent Parser将输入分解为语法树，然后对其进行评估。维基百科有一个用C语言编写的体面样本(没有指针，所以很容易转换为.net)，我也在下面复制它。
均衡组样品
using System;
using System.Text.RegularExpressions;
class Example
{
public static void Main()
{
string pattern = "[<>]*" +
"(" +
"((?'Open']*)+" +
"((?'Close-Open'>)[^<>]*)+" +
")*" +
"(?(Open)(?!))$";
string input = ">";
Match m = Regex.Match(input, pattern);
if (m.Success == true)
{
Console.WriteLine("Input: "{0}" \nMatch: "{1}"", input, m);
int grpCtr = 0;
foreach (Group grp in m.Groups)
{
Console.WriteLine(" Group {0}: {1}", grpCtr, grp.Value);
grpCtr++;
int capCtr = 0;
foreach (Capture cap in grp.Captures)
{
Console.WriteLine(" Capture {0}: {1}", capCtr, cap.Value);
capCtr++;
}
}
}
else
{
Console.WriteLine("Match failed.");
}
}
}
// The example displays the following output:
// Input: ">"
// Match: ">"
// Group 0: >
// Capture 0: >
// Group 1: >
// Capture 0:
// Capture 1: >
// Group 2:
// Capture 0:
// Capture 1:
// Capture 2:
// Group 3: >
// Capture 0: >
// Capture 1: >
// Capture 2: >
// Group 4:
// Group 5: mno
// Capture 0: abc
// Capture 1: xyz
// Capture 2: mno
递归下降解析器样品(来自Wikipedia)
typedef enum {ident, number, lparen, rparen, times, slash, plus,
minus, eql, neq, lss, leq, gtr, geq, callsym, beginsym, semicolon,
endsym, ifsym, whilesym, becomes, thensym, dosym, constsym, comma,
varsym, procsym, period, oddsym} Symbol;
Symbol sym;
void getsym(void);
void error(const char msg[]);
void expression(void);
int accept(Symbol s) {
if (sym == s) {
getsym();
return 1;
}
return 0;
}
int expect(Symbol s) {
if (accept(s))
return 1;
error("expect: unexpected symbol");
return 0;
}
void factor(void) {
if (accept(ident)) {
;
} else if (accept(number)) {
;
} else if (accept(lparen)) {
expression();
expect(rparen);
} else {
error("factor: syntax error");
getsym();
}
}
void term(void) {
factor();
while (sym == times || sym == slash) {
getsym();
factor();
}
}
void expression(void) {
if (sym == plus || sym == minus)
getsym();
term();
while (sym == plus || sym == minus) {
getsym();
term();
}
}
void condition(void) {
if (accept(oddsym)) {
expression();
} else {
expression();
if (sym == eql || sym == neq || sym == lss || sym == leq || sym == gtr || sym == geq) {
getsym();
expression();
} else {
error("condition: invalid operator");
getsym();
}
}
}
void statement(void) {
if (accept(ident)) {
expect(becomes);
expression();
} else if (accept(callsym)) {
expect(ident);
} else if (accept(beginsym)) {
do {
statement();
} while (accept(semicolon));
expect(endsym);
} else if (accept(ifsym)) {
condition();
expect(thensym);
statement();
} else if (accept(whilesym)) {
condition();
expect(dosym);
statement();
} else {
error("statement: syntax error");
getsym();
}
}
void block(void) {
if (accept(constsym)) {
do {
expect(ident);
expect(eql);
expect(number);
} while (accept(comma));
expect(semicolon);
}
if (accept(varsym)) {
do {
expect(ident);
} while (accept(comma));
expect(semicolon);
}
while (accept(procsym)) {
expect(ident);
expect(semicolon);
block();
expect(semicolon);
}
statement();
}
void program(void) {
getsym();
block();
expect(period);
}