From 99a4f6360bf96de61fc0ff403ae2b0807ec8052d Mon Sep 17 00:00:00 2001
From: Kaz Kylheku <kaz@kylheku.com>
Date: Wed, 22 Nov 2023 13:35:55 -0800
Subject: glob: suppress consecutive duplicates; fix memleak.

* glob.c (glob_wrap): When converting the glob array to the
returned list, suppress consecutive duplicates. This has to be
done separately for each call to glob or super_glob, so we now
interleave the production of the output list with the glob
calls.  It has to be done separately because there can be
duplicates between different patterns. E.g. if (glob "?")
matches one path then (glob '("?" "?")) must return two copies
of it. Furthermore, the brace expansion implementation in
glob* produces multiple glob calls and appends their results.
Duplicates inside a single super_glob call result when there
are multiple ** (double star) patterns present, which are
matched by the same path in more than one way. If the results
are sorted, then the duplicates appear consecutively and we
will squash them. Also, a memory leak is fixed here: we
must free(pat_u8) unconditionally, before testing for the
early exit situation.
---
 glob.c            | 33 ++++++++++++++++++++++-----------
 tests/018/glob.tl |  2 +-
 2 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/glob.c b/glob.c
index a2642c92..932af58d 100644
--- a/glob.c
+++ b/glob.c
@@ -82,6 +82,8 @@ val glob_wrap(val pattern, val flags, val errfun)
   int (*globfn)(const char *, int,
                 int (*) (const char *, int),
                 glob_t *) = if3((c_flags & GLOB_XSTAR) != 0, super_glob, glob);
+  size_t i = 0;
+  list_collect_decl (out, ptail);
 
   if (s_errfunc)
     uw_throwf(error_s, lit("~a: glob cannot be re-entered from "
@@ -98,8 +100,16 @@ val glob_wrap(val pattern, val flags, val errfun)
 
   if (stringp(pattern)) {
     char *pat_u8 = utf8_dup_to(c_str(pattern, self));
+    const char *prev = "";
     (void) globfn(pat_u8, c_flags, s_errfunc ? errfunc_thunk : 0, &gl);
     free(pat_u8);
+    for (; i < gl.gl_pathc; i++) {
+      const char *path = gl.gl_pathv[i];
+      if (prev == path || strcmp(prev, path) == 0)
+        continue;
+      ptail = list_collect (ptail, string_utf8(path));
+      prev = path;
+    }
   } else {
     seq_iter_t iter;
     val elem;
@@ -107,11 +117,20 @@ val glob_wrap(val pattern, val flags, val errfun)
 
     while (seq_get(&iter, &elem)) {
       char *pat_u8 = utf8_dup_to(c_str(elem, self));
+      const char *prev = "";
       (void) globfn(pat_u8, c_flags, s_errfunc ? errfunc_thunk : 0, &gl);
+      free(pat_u8);
       if (s_exit_point)
         break;
       c_flags |= GLOB_APPEND;
-      free(pat_u8);
+
+      for (; i < gl.gl_pathc; i++) {
+        const char *path = gl.gl_pathv[i];
+        if (prev == path || strcmp(prev, path) == 0)
+          continue;
+        ptail = list_collect (ptail, string_utf8(path));
+        prev = path;
+      }
     }
   }
 
@@ -124,16 +143,8 @@ val glob_wrap(val pattern, val flags, val errfun)
     uw_continue(ep);
   }
 
-  {
-    size_t i;
-    list_collect_decl (out, ptail);
-
-    for (i = 0; i < gl.gl_pathc; i++)
-      ptail = list_collect (ptail, string_utf8(gl.gl_pathv[i]));
-
-    globfree(&gl);
-    return out;
-  }
+  globfree(&gl);
+  return out;
 }
 
 static const char *super_glob_find_inner(const char *pattern)
diff --git a/tests/018/glob.tl b/tests/018/glob.tl
index f28ec480..438e4c65 100644
--- a/tests/018/glob.tl
+++ b/tests/018/glob.tl
@@ -112,7 +112,7 @@
   (glob* "**/{3,4,5}*/**" glob-xnobrace)
   nil
   (len (glob* "**/proc/**/**"))
-  547)
+  366)
 
 (if (neq (os-symbol) :solaris)
   (test
-- 
cgit v1.2.3