emil/libhl
1
3
Fork 0
Code Issues Pull Requests Releases Wiki Activity

regex2 extensions

Browse Source
This commit is contained in:
anon 2023-08-24 01:08:40 +02:00
parent 3912449f11
commit e05150f1f5
1 changed files with 114 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

129
source/regex2.hpp
View File

@ -1,4 +1,3 @@
#include <vector>
#include <assert.h> #include <assert.h>
#include <string.h> #include <string.h>
@ -52,10 +51,37 @@ bool is_quantifier(const char c){
int escape_1_to_1(const char c, char * whitelist) { int escape_1_to_1(const char c, char * whitelist) {
switch(c) { switch(c) {
case 't': { case 't': {
strcpy(whitelist, "\t"); strcat(whitelist, "\t");
} return 1; } return 1;
case 'n': { case 'n': {
strcpy(whitelist, "\n"); strcat(whitelist, "\n");
} return 1;
case 'r': {
strcat(whitelist, "\r");
} return 1;
case 'b': {
strcat(whitelist, "\b");
} return 1;
case '[': {
strcat(whitelist, "[");
} return 1;
case ']': {
strcat(whitelist, "]");
} return 1;
case '.': {
strcat(whitelist, ".");
} return 1;
case '?': {
strcat(whitelist, "?");
} return 1;
case '+': {
strcat(whitelist, "+");
} return 1;
case '*': {
strcat(whitelist, "*");
} return 1;
case '\\': {
strcat(whitelist, "\\");
} return 1; } return 1;
} }
@ -64,20 +90,90 @@ int escape_1_to_1(const char c, char * whitelist) {
int escape_1_to_N(const char c, char * whitelist) { int escape_1_to_N(const char c, char * whitelist) {
switch(c) { switch(c) {
case 'd': { case 'i': {
const char digitchars[] = "0123456789"; const char identifier_chars[] = "@0123456789_\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, digitchars); strcpy(whitelist, identifier_chars);
return sizeof(digitchars)-1; return sizeof(identifier_chars)-1;
}; };
case 'w': { case 'I': {
const char wordchars[] = "abcdefghijklmnopqrstuwxyzABCDEFGHIJKLMNOPQRSTUWXYZ"; const char identifier_chars[] = "@_\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, wordchars); strcpy(whitelist, identifier_chars);
return sizeof(wordchars)-1; return sizeof(identifier_chars)-1;
};
case 'k': {
const char keyword_chars[] = "@0123456789_\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, keyword_chars);
return sizeof(keyword_chars)-1;
};
case 'K': {
const char keyword_chars[] = "@_\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, keyword_chars);
return sizeof(keyword_chars)-1;
};
case 'f': {
const char filename_chars[] = "@0123456789/.-_+,#$%~=";
strcpy(whitelist, keyword_chars);
return sizeof(keyword_chars)-1;
};
case 'F': {
const char filename_chars[] = "@/.-_+,#$%~=";
strcpy(whitelist, keyword_chars);
return sizeof(keyword_chars)-1;
};
case 'p': {
const char printable_chars[] = "@\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, printable_chars);
return sizeof(printable_chars)-1;
};
case 'P': {
const char printable_chars[] = "@\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337";
strcpy(whitelist, printable_chars);
return sizeof(printable_chars)-1;
}; };
case 's': { case 's': {
const char blankchars[] = " \t\v\n"; const char whitespace_chars[] = " \t\v\n";
strcpy(whitelist, blankchars); strcpy(whitelist, whitespace_chars);
return sizeof(blankchars)-1; return sizeof(whitespace_chars)-1;
};
case 'd': {
const char digit_chars[] = "0123456789";
strcpy(whitelist, digit_chars);
return sizeof(digit_chars)-1;
};
case 'x': {
const char hex_chars[] = "0123456789abcdefABCDEF";
strcpy(whitelist, hex_chars);
return sizeof(hex_chars)-1;
};
case 'o': {
const char oct_chars[] = "01234567";
strcpy(whitelist, oct_chars);
return sizeof(oct_chars)-1;
};
case 'w': {
const char word_chars[] = "0123456789abcdefghijklmnopqrstuwxyzABCDEFGHIJKLMNOPQRSTUWXYZ_";
strcpy(whitelist, word_chars);
return sizeof(word_chars)-1;
};
case 'h': {
const char very_word_chars[] = "abcdefghijklmnopqrstuwxyzABCDEFGHIJKLMNOPQRSTUWXYZ_";
strcpy(whitelist, very_word_chars);
return sizeof(very_word_chars)-1;
};
case 'a': {
const char alpha_chars[] = "abcdefghijklmnopqrstuwxyzABCDEFGHIJKLMNOPQRSTUWXYZ";
strcpy(whitelist, alpha_chars);
return sizeof(alpha_chars)-1;
};
case 'l': {
const char lower_alpha_chars[] = "abcdefghijklmnopqrstuwxyz";
strcpy(whitelist, lower_alpha_chars);
return sizeof(lower_alpha_chars)-1;
};
case 'u': {
const char upper_alpha_chars[] = "ABCDEFGHIJKLMNOPQRSTUWXYZ";
strcpy(whitelist, upper_alpha_chars);
return sizeof(upper_alpha_chars)-1;
}; };
} }
@ -93,7 +189,10 @@ int compile_range(const char * const range,
for (s = range+1; *s != ']'; s++) { for (s = range+1; *s != ']'; s++) {
assert(*s != '\00' && "Unclosed range."); assert(*s != '\00' && "Unclosed range.");
char c = *s; char c = *s;
if (*(s+1) == '-') { if (escape_1_to_1(c, whitelist)
|| escape_1_to_N(c, whitelist)) {
;
} else if (*(s+1) == '-') {
char end = *(s+2); char end = *(s+2);
assert(c < end && "Endless range."); assert(c < end && "Endless range.");
for (char cc = c; cc < end+1; cc++) { for (char cc = c; cc < end+1; cc++) {