wordsplit: fix ws trimming and return_delim option

* src/wordsplit.c (_WSNF_DELIM): New node flag
(wsnode_flagstr): Print 'd' for that flag.
(expvar): Don't set WRDSF_WS when expanding variable
value.  This fixes, e.g., expansion of a$x if x begins with
a whitespace.
(wsnode_nullelim): A _WSNF_DELIM node breaks join chain.
(wordsplit_trimws): Don't affect nodes within join chains.
(scan_word): Set _WSNF_DELIM for returned delimiters.
* tests/wordsplit.at (TESTWSP): 8th argument - prologue
shell code.  Use it to unset environment variables in
env/getenv tests.
Test ws elimination with return_delims set.

1 files changed, 23 insertions, 8 deletions

diff --git a/src/wordsplit.c b/src/wordsplit.c
index 29547f6..4715547 100644
--- a/src/wordsplit.c
+++ b/src/wordsplit.c
@@ -307,6 +307,7 @@ alloc_space (struct wordsplit *wsp, size_t count)
 #define _WSNF_NOEXPAND 0x08     /* text is not subject to expansion */
 #define _WSNF_JOIN     0x10     /* node must be joined with the next node */
 #define _WSNF_SEXP     0x20     /* is a sed expression */
+#define _WSNF_DELIM    0x40     /* node is a delimiter */
 
 #define _WSNF_EMPTYOK  0x0100   /* special flag indicating that
                                    wordsplit_add_segm must add the
@@ -331,7 +332,7 @@ struct wordsplit_node
 static const char *
 wsnode_flagstr (int flags)
 {
-  static char retbuf[6];
+  static char retbuf[7];
   char *p = retbuf;
 
   if (flags & _WSNF_WORD)
@@ -356,6 +357,10 @@ wsnode_flagstr (int flags)
     *p++ = 's';
   else
     *p++ = '-';
+  if (flags & _WSNF_DELIM)
+    *p++ = 'd';
+  else
+    *p++ = '-';
   *p = 0;
   return retbuf;
 }
@@ -1148,7 +1153,7 @@ expvar (struct wordsplit *wsp, const char *str, size_t len,
           
           rc = _wsplt_subsplit (wsp, &ws, value, strlen (value),
                                 WRDSF_NOVAR | WRDSF_NOCMD |
-                                WRDSF_WS | WRDSF_QUOTE);
+                                WRDSF_QUOTE);
           free (value);
           if (rc)
             {
@@ -1268,6 +1273,8 @@ wsnode_nullelim (struct wordsplit *wsp)
   for (p = wsp->ws_head; p;)
     {
       struct wordsplit_node *next = p->next;
+      if (p->flags & _WSNF_DELIM && p->prev)
+        p->prev->flags &= ~_WSNF_JOIN;
       if (p->flags & _WSNF_NULL)
         {
           wsnode_remove (wsp, p);
@@ -1446,14 +1453,21 @@ wordsplit_trimws (struct wordsplit *wsp)
     {
       size_t n;
 
+      if (!(p->flags & _WSNF_QUOTE))
+        {
+          /* Skip leading whitespace: */
+          for (n = p->v.segm.beg; n < p->v.segm.end && ISWS (wsp->ws_input[n]);
+               n++)
+            ;
+          p->v.segm.beg = n;
+        }
+      
+      while (p->next && (p->flags & _WSNF_JOIN))
+        p = p->next;
+      
       if (p->flags & _WSNF_QUOTE)
         continue;
-
-      /* Skip leading whitespace: */
-      for (n = p->v.segm.beg; n < p->v.segm.end && ISWS (wsp->ws_input[n]);
-           n++)
-        ;
-      p->v.segm.beg = n;
+      
       /* Trim trailing whitespace */
       for (n = p->v.segm.end;
            n > p->v.segm.beg && ISWS (wsp->ws_input[n - 1]); n--);
@@ -1835,6 +1849,7 @@ scan_word (struct wordsplit *wsp, size_t start)
   else if (wsp->ws_flags & WRDSF_RETURN_DELIMS)
     {
       i++;
+      flags |= _WSNF_DELIM;
     }
   else if (!(wsp->ws_flags & WRDSF_SQUEEZE_DELIMS))
     flags |= _WSNF_EMPTYOK;