shithub: trueawk

Info  •  Files  •  Log  •  Branches

Start on rewrite of fnematch.

--- a/b.c

+++ b/b.c

@@ -80,7 +80,9 @@

 fa	*fatab[NFA];

 int	nfatab	= 0;	/* entries in fatab */

+extern int u8_nextlen(const char *s);

+

 /* utf-8 mechanism:

    For most of Awk, utf-8 strings just "work", since they look like

@@ -754,36 +756,61 @@

 	return (0);

 }

-static int getrune(FILE *fp, char **pbuf, int *pbufsize, int quantum,

-		   int *curpos, int *lastpos)

+

+#define MAX_UTF_BYTES	4	// UTF-8 is up to 4 bytes long

+

+// Read one rune at a time from the given FILE*. Return both

+// the bytes and the actual rune.

+

+struct runedata {

+	int rune;

+	size_t len;

+	char bytes[6];

+};

+

+struct runedata getrune(FILE *fp)

 {

-	int c = 0;

-	char *buf = *pbuf;

-	static const int max_bytes = 4;	// max multiple bytes in UTF-8 is 4

-	int i, rune;

-	uschar private_buf[max_bytes + 1];

+	struct runedata result;

+	int c, next;

-	for (i = 0; i <= max_bytes; i++) {

-		if (++*curpos == *lastpos) {

-			if (*lastpos == *pbufsize)

-				if (!adjbuf((char **) pbuf, pbufsize, *pbufsize+1, quantum, 0, "getrune"))

-					FATAL("stream '%.30s...' too long", buf);

-			buf[(*lastpos)++] = (c = getc(fp)) != EOF ? c : 0;

-			private_buf[i] = c;

-		}

-		if (c == 0 || c < 128 ||  (c >> 6) == 4) { // 10xxxxxx starts a new character

-			ungetc(c, fp);

-			private_buf[i] = 0;

+	memset(&result, 0, sizeof(result));

+

+	c = getc(fp);

+	if (c == EOF)

+		return result;	// result.rune == 0 --> EOF

+	else if (c < 128) {

+		result.bytes[0] = c;

+		result.len = 1;

+		result.rune = c;

+

+		return result;

+	}

+

+	// need to get bytes and fill things in

+	result.bytes[0] = c;

+	result.len = 1;

+

+	next = 1;

+	for (int i = 1; i < MAX_UTF_BYTES; i++) {

+		c = getc(fp);

+		if (c == EOF)

 			break;

-		}

+		result.bytes[next++] = c;

+		result.len++;

 	}

-	u8_rune(& rune, private_buf);

+	// put back any extra input bytes

+	int actual_len = u8_nextlen(result.bytes);

+	while (result.len > actual_len) {

+		ungetc(result.bytes[--result.len], fp);

+	}

-	return rune;

+	result.bytes[result.len] = '\0';

+	(void) u8_rune(& result.rune, (uschar *) result.bytes);

+

+	return result;

 }

-

 /*

  * NAME

  *     fnematch

@@ -803,8 +830,8 @@

 {

 	char *buf = *pbuf;

 	int bufsize = *pbufsize;

-	int c, i, j, k, ns, s;

-	int rune;

+	int i, j, k, ns, s;

+	struct runedata r;

 	s = pfa->initstat;

 	patlen = 0;

@@ -813,8 +840,8 @@

 	 * All indices relative to buf.

 	 * i <= j <= k <= bufsize

 	 *

-	 * i: origin of active substring

-	 * j: current character

+	 * i: origin of active substring (first byte of first character)

+	 * j: current character		(last byte of current character)

 	 * k: destination of next getc()

 	 */

 	i = -1, k = 0;

@@ -821,30 +848,26 @@

         do {

 		j = i++;

 		do {

-			if (++j == k) {

-				if (k == bufsize)

+			r = getrune(f);

+			if ((++j + r.len) >= k) {

+				if (k >= bufsize)

 					if (!adjbuf((char **) &buf, &bufsize, bufsize+1, quantum, 0, "fnematch"))

 						FATAL("stream '%.30s...' too long", buf);

-				buf[k++] = (c = getc(f)) != EOF ? c : 0;

 			}

-			c = (uschar)buf[j];

-			if (c < 128)

-				rune = c;

-			else {

-				j--;

-				k--;

-				ungetc(c, f);

-				rune = getrune(f, &buf, &bufsize, quantum, &j, &k);

-			}

+			memcpy(buf + k, r.bytes, r.len);

+			j += r.len - 1;	// incremented next time around the loop

+			k += r.len;

+			if (r.len > 1)

+				i += r.len - 1;	// also

-			if ((ns = get_gototab(pfa, s, rune)) != 0)

+			if ((ns = get_gototab(pfa, s, r.rune)) != 0)

 				s = ns;

 			else

-				s = cgoto(pfa, s, rune);

+				s = cgoto(pfa, s, r.rune);

 			if (pfa->out[s]) {	/* final state */

 				patlen = j - i + 1;

-				if (c == 0)	/* don't count $ */

+				if (r.rune == 0)	/* don't count $ */

 					patlen--;

 			}

 		} while (buf[j] && s != 1);

@@ -869,8 +892,9 @@

 		 * terminate the buffer.

 		 */

 		do

-			if (buf[--k] && ungetc(buf[k], f) == EOF)

-				FATAL("unable to ungetc '%c'", buf[k]);

+			for (int ii = r.len; ii > 0; ii--)

+				if (buf[--k] && ungetc(buf[k], f) == EOF)

+					FATAL("unable to ungetc '%c'", buf[k]);

 		while (k > i + patlen);

 		buf[k] = '\0';

 		return true;

--- a/makefile

+++ b/makefile

@@ -23,9 +23,9 @@

 # ****************************************************************/

 CFLAGS = -fsanitize=address -O1 -g -fno-omit-frame-pointer -fno-optimize-sibling-calls

-CFLAGS = -g

-CFLAGS =

-CFLAGS = -O2

+CFLAGS = -g3

+#CFLAGS =

+#CFLAGS = -O2

 # compiler options

 #CC = gcc -Wall -g -Wwrite-strings

-- 

⑨