char string[1];
};
+struct regnode_lstring { /* Constructed this way to keep the string aligned. */
+ U8 flags;
+ U8 type;
+ U16 next_off;
+ U32 str_len; /* Only 18 bits allowed before would overflow 'next_off' */
+ char string[1];
+};
+
+struct regnode_anyofhs { /* Constructed this way to keep the string aligned. */
+ U8 str_len;
+ U8 type;
+ U16 next_off;
+ U32 arg1; /* set by set_ANYOF_arg() */
+ char string[1];
+};
+
/* Argument bearing node - workhorse,
arg1 is often for the data field */
struct regnode_1 {
U16 arg2;
};
-/* This give the number of code points that can be in the bitmap of an ANYOF
- * node. The shift number must currently be one of: 8..12. It can't be less
- * than 8 (256) because some code relies on it being at least that. Above 12
- * (4096), and you start running into warnings that some data structure widths
- * have been exceeded, though the test suite as of this writing still passes
- * for up through 16, which is as high as anyone would ever want to go,
- * encompassing all of the Unicode BMP, and thus including all the economically
- * important world scripts. At 12 most of them are: including Arabic,
- * Cyrillic, Greek, Hebrew, Indian subcontinent, Latin, and Thai; but not Han,
- * Japanese, nor Korean. (The regarglen structure in regnodes.h is a U8, and
- * the trie types TRIEC and AHOCORASICKC are larger than U8 for shift values
- * above 12.) Be sure to benchmark before changing, as larger sizes do
- * significantly slow down the test suite */
-#define NUM_ANYOF_CODE_POINTS (1 << 8)
-
#define ANYOF_BITMAP_SIZE (NUM_ANYOF_CODE_POINTS / 8) /* 8 bits/Byte */
/* Note that these form structs which are supersets of the next smaller one, by
#define FLAGS(p) ((p)->flags) /* Caution: Doesn't apply to all \
regnode types. For some, it's the \
character set of the regnode */
+#define STR_LENs(p) (__ASSERT_(OP(p) != LEXACT && OP(p) != LEXACT_REQ8) \
+ ((struct regnode_string *)p)->str_len)
+#define STRINGs(p) (__ASSERT_(OP(p) != LEXACT && OP(p) != LEXACT_REQ8) \
+ ((struct regnode_string *)p)->string)
+#define OPERANDs(p) STRINGs(p)
+
+/* Long strings. Currently limited to length 18 bits, which handles a 262000
+ * byte string. The limiting factor is the 16 bit 'next_off' field, which
+ * points to the next regnode, so the furthest away it can be is 2**16. On
+ * most architectures, regnodes are 2**2 bytes long, so that yields 2**18
+ * bytes. Should a longer string be desired, we could increase it to 26 bits
+ * fairly easily, by changing this node to have longj type which causes the ARG
+ * field to be used for the link to the next regnode (although code would have
+ * to be changed to account for this), and then use a combination of the flags
+ * and next_off fields for the length. To get 34 bit length, also change the
+ * node to be an ARG2L, using the second 32 bit field for the length, and not
+ * using the flags nor next_off fields at all. One could have an llstring node
+ * and even an lllstring type. */
+#define STR_LENl(p) (__ASSERT_(OP(p) == LEXACT || OP(p) == LEXACT_REQ8) \
+ (((struct regnode_lstring *)p)->str_len))
+#define STRINGl(p) (__ASSERT_(OP(p) == LEXACT || OP(p) == LEXACT_REQ8) \
+ (((struct regnode_lstring *)p)->string))
+#define OPERANDl(p) STRINGl(p)
+
+#define STR_LEN(p) ((OP(p) == LEXACT || OP(p) == LEXACT_REQ8) \
+ ? STR_LENl(p) : STR_LENs(p))
+#define STRING(p) ((OP(p) == LEXACT || OP(p) == LEXACT_REQ8) \
+ ? STRINGl(p) : STRINGs(p))
#define OPERAND(p) STRING(p)
-#define STR_LEN(p) (((struct regnode_string *)p)->str_len)
-#define STRING(p) (((struct regnode_string *)p)->string)
+/* The number of (smallest) regnode equivalents that a string of length l bytes
+ * occupies */
#define STR_SZ(l) (((l) + sizeof(regnode) - 1) / sizeof(regnode))
-#define NODE_SZ_STR(p) (STR_SZ(STR_LEN(p))+1)
+
+/* The number of (smallest) regnode equivalents that the EXACTISH node 'p'
+ * occupies */
+#define NODE_SZ_STR(p) (STR_SZ(STR_LEN(p)) + 1 + regarglen[(p)->type])
+
#define setSTR_LEN(p,v) \
- ((struct regnode_string *)(p))->str_len = (v);
+ STMT_START{ \
+ if (OP(p) == LEXACT || OP(p) == LEXACT_REQ8) \
+ ((struct regnode_lstring *)(p))->str_len = (v); \
+ else \
+ ((struct regnode_string *)(p))->str_len = (v); \
+ } STMT_END
+
+#define ANYOFR_BASE_BITS 20
+#define ANYOFRbase(p) (ARG(p) & ((1 << ANYOFR_BASE_BITS) - 1))
+#define ANYOFRdelta(p) (ARG(p) >> ANYOFR_BASE_BITS)
#undef NODE_ALIGN
#undef ARG_LOC
#define NODE_STEP_REGNODE 1 /* sizeof(regnode)/sizeof(regnode) */
#define EXTRA_STEP_2ARGS EXTRA_SIZE(struct regnode_2)
-#define NODE_STEP_B 4
-
#define NEXTOPER(p) ((p) + NODE_STEP_REGNODE)
#define PREVOPER(p) ((p) - NODE_STEP_REGNODE)
* 2) A subset of item 1) is if all possible code points outside the bitmap
* match. This is a common occurrence when the class is complemented,
* like /[^ij]/. Therefore a bit is reserved to indicate this,
- * rather than having a more expensive inversion list created,
+ * rather than having an inversion list created,
* ANYOF_MATCHES_ALL_ABOVE_BITMAP.
* 3) Under /d rules, it can happen that code points that are in the upper
* latin1 range (\x80-\xFF or their equivalents on EBCDIC platforms) match
# define UCHARAT(p) ((int)*(p)&CHARMASK)
#endif
+/* Number of regnode equivalents that 'guy' occupies beyond the size of the
+ * smallest regnode. */
#define EXTRA_SIZE(guy) ((sizeof(guy)-1)/sizeof(struct regnode))
#define REG_ZERO_LEN_SEEN 0x00000001
WB_BOUND
} bound_type;
-/* This unpacks the FLAGS field of ANYOFHx nodes. The value it contains
+/* This unpacks the FLAGS field of ANYOF[HR]x nodes. The value it contains
* gives the strict lower bound for the UTF-8 start byte of any code point
* matchable by the node, and a loose upper bound as well.
*