Vendor import of bwk's 14-March-2003 release.

7 files changed, 99 insertions, 26 deletions

diff --git a/contrib/one-true-awk/FIXES b/contrib/one-true-awk/FIXES
index 76b2553..bf9381b 100644
--- a/contrib/one-true-awk/FIXES
+++ b/contrib/one-true-awk/FIXES
@@ -25,6 +25,21 @@ THIS SOFTWARE.
 This file lists all bug fixes, changes, etc., made since the AWK book
 was sent to the printers in August, 1987.
 
+Mar 14, 2003:
+	the internationalization changes, somewhat modified, are now
+	reinstated.  in theory awk will now do character comparisons
+	and case conversions in national language, but "." will always
+	be the decimal point separator on input and output regardless
+	of national language.  isblank(){} has an #ifndef.
+
+	this no longer compiles on windows: LC_MESSAGES isn't defined
+	in vc6++.
+
+	fixed subtle behavior in field and record splitting: if FS is
+	a single character and RS is not empty, \n is NOT a separator.
+	this tortuous reading is found in the awk book; behavior now
+	matches gawk and mawk.
+
 Dec 13, 2002:
 	for the moment, the internationalization changes of nov 29 are
 	rolled back -- programs like x = 1.2 don't work in some locales,
diff --git a/contrib/one-true-awk/README b/contrib/one-true-awk/README
index 8fbf30b..166840f 100644
--- a/contrib/one-true-awk/README
+++ b/contrib/one-true-awk/README
@@ -72,8 +72,14 @@ This also compiles with Visual C++ on all flavors of Windows,
 *if* you provide versions of popen and pclose.  The file
 missing95.c contains versions that can be used to get started
 with, though the underlying support has mysterious properties,
-the symptom of which can be truncated pipe output.  Beware.
-The file makefile.win gives hints on how to proceed.
+the symptom of which can be truncated pipe output.  Beware.  The
+file makefile.win gives hints on how to proceed; if you run
+vcvars32.bat, it will set up necessary paths and parameters so
+you can subsequently run nmake -f makefile.win.  Beware also that
+when running on Windows under command.com, various quoting
+conventions are different from Unix systems: single quotes won't
+work around arguments, and various characters like % are
+interpreted within double quotes.
 
 This compiles without change on Macintosh OS X using gcc and
 the standard developer tools.
diff --git a/contrib/one-true-awk/b.c b/contrib/one-true-awk/b.c
index aa2ad15..df3aaa9 100644
--- a/contrib/one-true-awk/b.c
+++ b/contrib/one-true-awk/b.c
@@ -282,9 +282,24 @@ int quoted(char **pp)	/* pick up next thing after a \\ */
 	return c;
 }
 
+static int collate_range_cmp(int a, int b)
+{
+	int r;
+	static char s[2][2];
+
+	if ((uschar)a == (uschar)b)
+		return 0;
+	s[0][0] = a;
+	s[1][0] = b;
+	if ((r = strcoll(s[0], s[1])) == 0)
+		r = (uschar)a - (uschar)b;
+	return r;
+}
+
 char *cclenter(const char *argp)	/* add a character class */
 {
 	int i, c, c2;
+	int j;
 	uschar *p = (uschar *) argp;
 	uschar *op, *bp;
 	static uschar *buf = 0;
@@ -303,15 +318,18 @@ char *cclenter(const char *argp)	/* add a character class */
 				c2 = *p++;
 				if (c2 == '\\')
 					c2 = quoted((char **) &p);
-				if (c > c2) {	/* empty; ignore */
+				if (collate_range_cmp(c, c2) > 0) {	/* empty; ignore */
 					bp--;
 					i--;
 					continue;
 				}
-				while (c < c2) {
+				for (j = 0; j < NCHARS; j++) {
+					if ((collate_range_cmp(c, j) > 0) ||
+					    collate_range_cmp(j, c2) > 0)
+						continue;
 					if (!adjbuf((char **) &buf, &bufsz, bp-buf+2, 100, (char **) &bp, 0))
 						FATAL("out of space for character class [%.10s...] 2", p);
-					*bp++ = ++c;
+					*bp++ = j;
 					i++;
 				}
 				continue;
@@ -695,23 +713,39 @@ Node *unary(Node *np)
  * relex(), the expanded character class (prior to range expansion)
  * must be less than twice the size of their full name.
  */
+
+/* Because isblank doesn't show up in any of the header files on any
+ * system i use, it's defined here.  if some other locale has a richer
+ * definition of "blank", define HAS_ISBLANK and provide your own
+ * version.
+ */
+
+#ifndef HAS_ISBLANK
+
+int isblank(int c)
+{
+	return c==' ' || c=='\t';
+}
+
+#endif
+
 struct charclass {
 	const char *cc_name;
 	int cc_namelen;
-	const char *cc_expand;
+	int (*cc_func)(int);
 } charclasses[] = {
-	{ "alnum",	5,	"0-9A-Za-z" },
-	{ "alpha",	5,	"A-Za-z" },
-	{ "blank",	5,	" \t" },
-	{ "cntrl",	5,	"\000-\037\177" },
-	{ "digit",	5,	"0-9" },
-	{ "graph",	5,	"\041-\176" },
-	{ "lower",	5,	"a-z" },
-	{ "print",	5,	" \041-\176" },
-	{ "punct",	5,	"\041-\057\072-\100\133-\140\173-\176" },
-	{ "space",	5,	" \f\n\r\t\v" },
-	{ "upper",	5,	"A-Z" },
-	{ "xdigit",	6,	"0-9A-Fa-f" },
+	{ "alnum",	5,	isalnum },
+	{ "alpha",	5,	isalpha },
+	{ "blank",	5,	isblank },
+	{ "cntrl",	5,	iscntrl },
+	{ "digit",	5,	isdigit },
+	{ "graph",	5,	isgraph },
+	{ "lower",	5,	islower },
+	{ "print",	5,	isprint },
+	{ "punct",	5,	ispunct },
+	{ "space",	5,	isspace },
+	{ "upper",	5,	isupper },
+	{ "xdigit",	6,	isxdigit },
 	{ NULL,		0,	NULL },
 };
 
@@ -724,7 +758,7 @@ int relex(void)		/* lexical analyzer for reparse */
 	static int bufsz = 100;
 	uschar *bp;
 	struct charclass *cc;
-	const uschar *p;
+	int i;
 
 	switch (c = *prestr++) {
 	case '|': return OR;
@@ -773,8 +807,14 @@ int relex(void)		/* lexical analyzer for reparse */
 				if (cc->cc_name != NULL && prestr[1 + cc->cc_namelen] == ':' &&
 				    prestr[2 + cc->cc_namelen] == ']') {
 					prestr += cc->cc_namelen + 3;
-					for (p = (const uschar *) cc->cc_expand; *p; p++)
-						*bp++ = *p;
+					for (i = 0; i < NCHARS; i++) {
+						if (!adjbuf((char **) &buf, &bufsz, bp-buf+1, 100, (char **) &bp, 0))
+						    FATAL("out of space for reg expr %.10s...", lastre);
+						if (cc->cc_func(i)) {
+							*bp++ = i;
+							n++;
+						}
+					}
 				} else
 					*bp++ = c;
 			} else if (c == '\0') {
diff --git a/contrib/one-true-awk/lib.c b/contrib/one-true-awk/lib.c
index 630bbce..9e64247 100644
--- a/contrib/one-true-awk/lib.c
+++ b/contrib/one-true-awk/lib.c
@@ -308,6 +308,13 @@ void fldbld(void)	/* create fields from current record */
 		}
 		*fr = 0;
 	} else if (*r != 0) {	/* if 0, it's a null field */
+		/* subtlecase : if length(FS) == 1 && length(RS > 0)
+		 * \n is NOT a field separator (cf awk book 61,84).
+		 * this variable is tested in the inner while loop.
+		 */
+		int rtest = '\n';  /* normal case */
+		if (strlen(*RS) > 0)
+			rtest = '\0';
 		for (;;) {
 			i++;
 			if (i > nfields)
@@ -316,7 +323,7 @@ void fldbld(void)	/* create fields from current record */
 				xfree(fldtab[i]->sval);
 			fldtab[i]->sval = fr;
 			fldtab[i]->tval = FLD | STR | DONTFREE;
-			while (*r != sep && *r != '\n' && *r != '\0')	/* \n is always a separator */
+			while (*r != sep && *r != rtest && *r != '\0')	/* \n is always a separator */
 				*fr++ = *r++;
 			*fr++ = 0;
 			if (*r++ == 0)
diff --git a/contrib/one-true-awk/main.c b/contrib/one-true-awk/main.c
index b0d2807..df855dd 100644
--- a/contrib/one-true-awk/main.c
+++ b/contrib/one-true-awk/main.c
@@ -22,11 +22,12 @@ ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
 THIS SOFTWARE.
 ****************************************************************/
 
-const char	*version = "version 20021213";
+const char	*version = "version 20030314";
 
 #define DEBUG
 #include <stdio.h>
 #include <ctype.h>
+#include <locale.h>
 #include <stdlib.h>
 #include <string.h>
 #include <signal.h>
@@ -54,6 +55,10 @@ int main(int argc, char *argv[])
 {
 	const char *fs = NULL;
 
+	setlocale(LC_ALL, "");
+	setlocale(LC_COLLATE, "");
+	setlocale(LC_CTYPE, "");
+	setlocale(LC_MESSAGES, "");
 	cmdname = argv[0];
 	if (argc == 1) {
 		fprintf(stderr, "Usage: %s [-f programfile | 'program'] [-Ffieldsep] [-v var=value] [files]\n", cmdname);
diff --git a/contrib/one-true-awk/makefile b/contrib/one-true-awk/makefile
index b0222c2..2de732a 100644
--- a/contrib/one-true-awk/makefile
+++ b/contrib/one-true-awk/makefile
@@ -45,7 +45,7 @@ LISTING = awk.h proto.h awkgram.y lex.c b.c main.c maketab.c parse.c \
 	lib.c run.c tran.c missing95.c
 
 SHIP = README FIXES $(SOURCE) ytab[ch].bak makefile makefile.win \
-	buildwin.bat mac.code awk.1
+	vcvars32.bat buildwin.bat mac.code awk.1
 
 a.out:	ytab.o $(OFILES)
 	$(CC) $(CFLAGS) ytab.o $(OFILES) $(ALLOC)  -lm
diff --git a/contrib/one-true-awk/run.c b/contrib/one-true-awk/run.c
index 64722bd..617ac7d 100644
--- a/contrib/one-true-awk/run.c
+++ b/contrib/one-true-awk/run.c
@@ -1509,11 +1509,11 @@ Cell *bltin(Node **a, int n)	/* builtin functions. a[0] is type, a[1] is arg lis
 		if (t == FTOUPPER) {
 			for (p = buf; *p; p++)
 				if (islower((uschar) *p))
-					*p = toupper(*p);
+					*p = toupper((uschar)*p);
 		} else {
 			for (p = buf; *p; p++)
 				if (isupper((uschar) *p))
-					*p = tolower(*p);
+					*p = tolower((uschar)*p);
 		}
 		tempfree(x);
 		x = gettemp();