| Subject: | Data::SExpression#read can not parse several strings. |
Description:
Data::SExpression#read can not parse following cases.
* empty string in list.
q{("" "")}
* newline in a string.
"a\nb"
Steps to Reproduce:
Show quoted text
> perl -MData::SExpression -e "Data::SExpression->new->read(q
{(\"\" \"\")})"
Parse error near: '")' at lib/Data/SExpression/Parser.yp line 105.
Show quoted text > perl -MData::SExpression -e "Data::SExpression->new->read(qq
{\"a\nb\"})"
Parse error near: '"a
b' at lib/Data/SExpression/Parser.yp line 105.
Product:
Data-SExpressoin-0.3
Perl version:
This is perl, v5.8.8 built for MSWin32-x86-multi-thread
(ActivePerl 5.8.8.817)
Operating System vendor and version:
Microsoft Windows XP Professional SP2
Attachments:
patch.txt will fix the problem.
Thanks.
| Subject: | patch.txt |
diff -r -u Data-SExpression-0.3/lib/Data/SExpression/Parser.yp Data-SExpression-0.3.fix/lib/Data/SExpression/Parser.yp
--- Data-SExpression-0.3/lib/Data/SExpression/Parser.yp 2006-08-01 11:30:57.000000000 +0900
+++ Data-SExpression-0.3.fix/lib/Data/SExpression/Parser.yp 2006-11-27 22:33:46.031250000 +0900
@@ -86,7 +86,7 @@
/\G ($symbol_char ($symbol_char | \d )*)/gcx
and return ('SYMBOL', $1);
- /\G " (.*? [^\\]) "/gcx || /\G ""/gcx
+ /\G " ([^"\\]* (?: \\. [^"\\]*)*) "/gcx
and return ('STRING', $1 || "");
/\G ([().])/gcx
diff -r -u Data-SExpression-0.3/t/01-lexer.t Data-SExpression-0.3.fix/t/01-lexer.t
--- Data-SExpression-0.3/t/01-lexer.t 2006-08-01 11:36:55.000000000 +0900
+++ Data-SExpression-0.3.fix/t/01-lexer.t 2006-11-27 22:33:46.031250000 +0900
@@ -57,3 +57,51 @@
[[SYMBOL => 'a'],
[q{.} => q{.}],
[SYMBOL => 'b']]);
+
+is_deeply(tokenize(q{""}),
+ [[STRING => '']]);
+
+is_deeply(tokenize(q{("")}),
+ [['(' => '('],
+ [STRING => ''],
+ [')' => ')']]);
+
+is_deeply(tokenize(q{("") ("")}),
+ [['(' => '('],
+ [STRING => ''],
+ [')' => ')'],
+ ['(' => '('],
+ [STRING => ''],
+ [')' => ')']]);
+
+is_deeply(tokenize(q{("") (" ")}),
+ [['(' => '('],
+ [STRING => ''],
+ [')' => ')'],
+ ['(' => '('],
+ [STRING => ' '],
+ [')' => ')']]);
+
+is_deeply(tokenize(q{("a") ("b")}),
+ [['(' => '('],
+ [STRING => 'a'],
+ [')' => ')'],
+ ['(' => '('],
+ [STRING => 'b'],
+ [')' => ')']]);
+
+
+is_deeply(tokenize(qq{"\n"}),
+ [[STRING => "\n"]]);
+
+is_deeply(tokenize(qq{"aa\n"}),
+ [[STRING => "aa\n"]]);
+
+is_deeply(tokenize(qq{"\nbb"}),
+ [[STRING => "\nbb"]]);
+
+is_deeply(tokenize(qq{"aa\nbb"}),
+ [[STRING => "aa\nbb"]]);
+
+is_deeply(tokenize(qq{"aa\nbb\ncc\ndd\n"}),
+ [[STRING => "aa\nbb\ncc\ndd\n"]]);
diff -r -u Data-SExpression-0.3/t/02-scalars.t Data-SExpression-0.3.fix/t/02-scalars.t
--- Data-SExpression-0.3/t/02-scalars.t 2006-07-30 11:11:14.000000000 +0900
+++ Data-SExpression-0.3.fix/t/02-scalars.t 2006-11-27 22:33:46.031250000 +0900
@@ -8,7 +8,7 @@
=cut
-use Test::More tests => 11;
+use Test::More tests => 15;
use Symbol;
use Data::SExpression;
@@ -30,3 +30,21 @@
7
}), 7, "Skipped comment");
is(scalar $ds->read('+'), qualify_to_ref('+'), "Read '+' symbol");
+is(scalar $ds->read(q{
+"foo
+bar
+"
+}), "foo\nbar\n", "LF is OK");
+is(scalar $ds->read(q{
+"
+
+"
+}), "\n\n", "LF is OK (2)");
+is(scalar $ds->read(q{
+";; not comment"
+}), ";; not comment", "comment in string OK");
+is(scalar $ds->read(q{
+"
+; not comment
+"
+}), "\n; not comment\n", "comment in string OK (2)");
diff -r -u Data-SExpression-0.3/t/03-lists.t Data-SExpression-0.3.fix/t/03-lists.t
--- Data-SExpression-0.3/t/03-lists.t 2006-07-30 11:11:14.000000000 +0900
+++ Data-SExpression-0.3.fix/t/03-lists.t 2006-11-27 22:33:46.031250000 +0900
@@ -8,7 +8,7 @@
=cut
-use Test::More tests => 5;
+use Test::More tests => 7;
use Test::Deep;
use Symbol;
@@ -59,6 +59,22 @@
cdr => undef)))),
"Read a tree");
+cmp_deeply(
+ scalar $ds->read(qq{("")}),
+ methods(
+ car => "",
+ cdr => undef),
+ "Read an empty string");
+
+cmp_deeply(
+ scalar $ds->read(qq{("" "")}),
+ methods(
+ car => "",
+ cdr => methods(
+ car => "",
+ cdr => undef)),
+ "Read an empty strings");
+
no warnings 'once'; #For the symbol globs
cmp_deeply(