Make File::Glob::csh_glob consisent wrt '"\

File::Glob::csh_glob, which is the routine implementing Perl’s own
glob function, is not consistent in its treatment of quotation marks
and backslashes.  It differs depending on whether there are white-
space characters in the pattern both preceded and followed by non-
whitespace.

Without whitespace, quotation marks are treated literally and back-
slashes are treated as escapes that cause metacharacters to be treated
literally.  So

    <"foo*">

looks for files with literal quotation marks in their name.

With whitespace, quotation marks are treated as word delimiters, so

    <"foo copy*">

will find file names matching /^foo copy/.  Backslash escapes are pro-
cessed twice, so one has to write

    glob '\\\** .\\\**'

to find files beginning with a literal ‘*’ or ‘.*’.  But simply

    glob '\**'

to find files beginning with ‘*’.  (Note that <> is a double-quotish
operator, so in <> those would have to be quadruple and double back-
slashes, respectively.)

There are two problems with the code:

1) Text::Parsewords is only used when there is whitespace present.  It
   should be used also for quotation marks, too, if they exist.
2) Text::Parsewords should not be removing backslash escapes.
3) Actually, there’s a third.  A final escaped space should also go
   through Text::ParseWords, instead of being stripped.

This commit fixes both things.

diff --git a/ext/File-Glob/Glob.pm b/ext/File-Glob/Glob.pm
index af17cff..30263d9 100644 (file)
--- a/ext/File-Glob/Glob.pm
+++ b/ext/File-Glob/Glob.pm
@@ -36,7 +36,7 @@ use feature 'switch';
 
 @EXPORT_OK   = (@{$EXPORT_TAGS{'glob'}}, 'csh_glob');
 
-$VERSION = '1.13';
+$VERSION = '1.14';
 
 sub import {
     require Exporter;
@@ -84,14 +84,19 @@ sub csh_glob {
 
     # extract patterns
     $pat =~ s/^\s+//;  # Protect against empty elements in
-    $pat =~ s/\s+$//;  # things like < *.c> and <*.c >.
-                       # These alone shouldn't trigger ParseWords.
-    if ($pat =~ /\s/) {
+                       # things like < *.c>, which alone
+                       # shouldn't trigger ParseWords.  Patterns
+                       # with a trailing space must be passed
+                       # to ParseWords, in case it is escaped,
+                       # as in <\ >.
+    if ($pat =~ /[\s"']/) {
         # XXX this is needed for compatibility with the csh
        # implementation in Perl.  Need to support a flag
        # to disable this behavior.
        require Text::ParseWords;
-       @pat = Text::ParseWords::parse_line('\s+',0,$pat);
+       for (@pat = Text::ParseWords::parse_line('\s+',1,$pat)) {
+           s/^['"]// and chop;
+       }
     }
 
     # assume global context if not provided one

diff --git a/ext/File-Glob/t/basic.t b/ext/File-Glob/t/basic.t
index c40b1d5..bdf0d94 100644 (file)
--- a/ext/File-Glob/t/basic.t
+++ b/ext/File-Glob/t/basic.t
@@ -10,7 +10,7 @@ BEGIN {
     }
 }
 use strict;
-use Test::More tests => 18;
+use Test::More tests => 23;
 BEGIN {use_ok('File::Glob', ':glob')};
 use Cwd ();
 
@@ -233,3 +233,12 @@ pass("Don't panic");
 # This used to segfault.
 my $i = bsd_glob('*', GLOB_ALTDIRFUNC);
 is(&File::Glob::GLOB_ERROR, 0, "Successfuly ignored unsupported flag");
+
+package frimpy; # get away from the glob override, so we can test csh_glob,
+use Test::More;  # which is perl's default
+
+is +(glob "a'b'")[0], (<a'b' c>)[0], "a'b' with and without spaces";
+is +(<a"b">)[0], (<a"b" c>)[0], 'a"b" with and without spaces';
+is <\\*>, '*', 'backslashes without spaces';
+is_deeply [sort <\\* .\\*>], [sort qw<* .*>], 'backslashes with spaces';
+is <\\ >, ' ', 'final escaped space';