Implementation of UTF-8 ranges

New constructor 'lpeg.utfR(from, to)' creates a pattern that matches
UTF-8 byte sequences representing code points in the range [from, to].

1 files changed, 5 insertions, 0 deletions

diff --git a/lpvm.h b/lpvm.h
index 576429f..9fde967 100644
--- a/lpvm.h
+++ b/lpvm.h
@@ -17,6 +17,7 @@ typedef enum Opcode {
   ITestChar,  /* if char != aux, jump to 'offset' */
   ITestSet,  /* if char not in buff, jump to 'offset' */
   ISpan,  /* read a span of chars in buff */
+  IUTFR,  /* if codepoint not in range [offset, utf_to], fail */
   IBehind,  /* walk back 'aux' characters (fail if not possible) */
   IRet,  /* return from a rule */
   IEnd,  /* end of pattern */
@@ -50,6 +51,10 @@ typedef union Instruction {
 } Instruction;
 
 
+/* extract 24-bit value from an instruction */
+#define utf_to(inst)    (((inst)->i.key << 8) | (inst)->i.aux)
+
+
 void printpatt (Instruction *p, int n);
 const char *match (lua_State *L, const char *o, const char *s, const char *e,
                    Instruction *op, Capture *capture, int ptop);