Re: [9front] [PATCH] awk: add %q format for quoted strings (see quote(2))

[ori@eigenstate.org]

Quoth ori@eigenstate.org:
> Quoth james palmer <james@biobuf.link>:
> > this one comes in handy for building bulk rename scripts.
> > patch for git/import attached.
> > 
> > - james
> > 
> 
> I think it makes sense to add this, though I'm
> not sure how much we want to diverge from upstream.
> 
> Ape would get this by accident, but it's a superset
> of what posix needs.
> 
> going the other way would also be neat:
> 
> 	ls -l | awk -Q {print $NF}
> 

Here's a proof of concept -- though, I don't like how it
totally ignores FS.

diff fb2e0a1987b33083e3e08fa0659f99534c56d6aa uncommitted
--- a/sys/src/cmd/awk/awk.h
+++ b/sys/src/cmd/awk/awk.h
@@ -49,6 +49,7 @@
 extern int	donefld;	/* 1 if record broken into fields */
 extern int	donerec;	/* 1 if record is valid (no fld has changed */
 extern char	inputFS[];	/* FS at time of input, for field splitting */
+extern int	quotefld;	/* if we use quotes instead of FS for splitting */
 
 extern int	dbg;
 
--- a/sys/src/cmd/awk/lib.c
+++ b/sys/src/cmd/awk/lib.c
@@ -38,6 +38,7 @@
 
 Cell	**fldtab;	/* pointers to Cells */
 char	inputFS[100] = " ";
+int	quotefld;
 
 #define	MAXFLD	200
 int	nfields	= MAXFLD;	/* last allocated slot for $i */
@@ -242,7 +243,49 @@
 	   dprint( ("command line set %s to |%s|\n", s, p) );
 }
 
+char *unquoted(char *t, char **et)
+{
+	int quoting;
+	char *h, *s;
 
+	quoting = 0;
+	/* unquoting only shrinks s */
+	while (*t == ' ' || *t == '\t' || *t == '\n')
+		t++;
+	s = strdup(t);
+	h = s;
+	if (s == nil)
+		FATAL("out of space in tostring on %s", s);
+	while(*t!='\0'){
+		if(!quoting && (*t == ' ' || *t == '\t' || *t == '\n'))
+			break;
+		if(*t != '\''){
+			*s++ = *t++;
+			continue;
+		}
+		/* *t is a quote */
+		if(!quoting){
+			quoting = 1;
+			t++;
+			continue;
+		}
+		/* quoting and we're on a quote */
+		if(t[1] != '\''){
+			/* end of quoted section; absorb closing quote */
+			t++;
+			quoting = 0;
+			continue;
+		}
+		/* doubled quote; fold one quote into two */
+		t++;
+		*s++ = *t++;
+
+	}
+	*s = 0;
+	*et = t;
+	return h;
+}	
+
 void fldbld(void)	/* create fields from current record */
 {
 	/* this relies on having fields[] the same length as $0 */
@@ -265,7 +308,21 @@
 	}
 	fr = fields;
 	i = 0;	/* number of fields accumulated here */
-	if (strlen(inputFS) > 1) {	/* it's a regular expression */
+	if (quotefld){				/* it's quoted text */
+		for (i = 0; ; ) {
+			while (*r == ' ' || *r == '\t' || *r == '\n')
+				r++;
+			if (*r == 0)
+				break;
+			i++;
+			if (i > nfields)
+				growfldtab(i);
+			if (freeable(fldtab[i]))
+				xfree(fldtab[i]->sval);
+			fldtab[i]->sval = unquoted(r, &r);
+			fldtab[i]->tval = FLD | STR;
+		}
+	}else if (strlen(inputFS) > 1) {	/* it's a regular expression */
 		i = refldbld(r, inputFS);
 	} else if (*inputFS == ' ') {	/* default whitespace */
 		for (i = 0; ; ) {
--- a/sys/src/cmd/awk/main.c
+++ b/sys/src/cmd/awk/main.c
@@ -51,7 +51,7 @@
 
 void main(int argc, char *argv[])
 {
-	char *fs = nil, *marg;
+	char *fs = nil, qs = 0, *marg;
 	int temp;
 
 	setfcr(getfcr() & ~FPINVAL);
@@ -103,6 +103,9 @@
 			if (fs == nil || *fs == '\0')
 				WARNING("field separator FS is empty");
 			break;
+		case 'Q':
+			qs = 1;
+			break;
 		case 'v':	/* -v a=1 to be done NOW.  one -v for each */
 			if (argv[1][2] == '\0' && --argc > 1 && isclvar((++argv)[1]))
 				setclvar(argv[1]);
@@ -158,6 +161,8 @@
 	   dprint( ("argc=%d, argv[0]=%s\n", argc, argv[0]) );
 	arginit(argc, argv);
 	yyparse();
+	if (qs)
+		quotefld = 1;
 	if (fs)
 		*FS = qstring(fs, '\0');
 	   dprint( ("exitstatus=%s\n", exitstatus) );