circuitpython/lib/re1.5/charclass.c
Damien George 64193c7de9 lib/re1.5: Add support for named classes in class sets.
Total code size change of this and previous commit:

   bare-arm:    +0 +0.000%
minimal x86:    +0 +0.000%
   unix x64:   +32 +0.004% standard
      stm32:   +24 +0.006% PYBV10
     cc3200:   +16 +0.009%
    esp8266:   +20 +0.003% GENERIC
      esp32:   +44 +0.003% GENERIC[incl +8(data)]
     mimxrt:   +32 +0.009% TEENSY40
 renesas-ra:   +24 +0.004% RA6M2_EK
        nrf:    +0 +0.000% pca10040
        rp2:   +24 +0.005% PICO
       samd:   +32 +0.012% ADAFRUIT_ITSYBITSY_M4_EXPRESS

Addresses issue #7920.

Signed-off-by: Damien George <damien@micropython.org>
2023-01-18 09:15:32 +11:00

42 lines
1.1 KiB
C

#include "re1.5.h"
int _re1_5_classmatch(const char *pc, const char *sp)
{
// pc points to "cnt" byte after opcode
int is_positive = (pc[-1] == Class);
int cnt = *pc++;
while (cnt--) {
if (*pc == RE15_CLASS_NAMED_CLASS_INDICATOR) {
if (_re1_5_namedclassmatch(pc + 1, sp)) {
return is_positive;
}
} else {
if (*sp >= *pc && *sp <= pc[1]) {
return is_positive;
}
}
pc += 2;
}
return !is_positive;
}
int _re1_5_namedclassmatch(const char *pc, const char *sp)
{
// pc points to name of class
int off = (*pc >> 5) & 1;
if ((*pc | 0x20) == 'd') {
if (!(*sp >= '0' && *sp <= '9')) {
off ^= 1;
}
} else if ((*pc | 0x20) == 's') {
if (!(*sp == ' ' || (*sp >= '\t' && *sp <= '\r'))) {
off ^= 1;
}
} else { // w
if (!((*sp >= 'A' && *sp <= 'Z') || (*sp >= 'a' && *sp <= 'z') || (*sp >= '0' && *sp <= '9') || *sp == '_')) {
off ^= 1;
}
}
return off;
}