discover/grub2: improve handling of word & delimiter tokens

Currently, the delimiter token handling is a little fragile: we try to
ignore non-inter-word delimiters in the lexer with a selective set of
regexes on the possible delimiter characters.

This means we don't need to handle potential delimiters in every grammar
rule, but there are other situations (not regex-able) where we may see
delimters, and this will cause a parse error.

Instead of relying on the regex behaviour, we have an 'inter_word' flag,
which is set when we see the first word token, and cleared when we see
an end-of-line token. We only emit TOKEN_DELIM when this flag is set.

This means that we only get the delim tokens when they're required -
when we're looking for word separators (becuase WORD DELIM WORD is
distinct from WORD WORD - eg "linux /vmlinux" and "x$var").

We add a few new tests for the "menuentry" and "if" syntax, with
different delimiter configurations.

Signed-off-by: Jeremy Kerr <jk@ozlabs.org>

1 files changed, 40 insertions, 0 deletions

diff --git a/test/parser/test-grub2-if-formats.c b/test/parser/test-grub2-if-formats.c
new file mode 100644
index 0000000..cbf1afb
--- /dev/null
+++ b/test/parser/test-grub2-if-formats.c
@@ -0,0 +1,40 @@
+
+#include "parser-test.h"
+
+#if 0 /* PARSER_EMBEDDED_CONFIG */
+if true;then t1=1;fi
+if true ;then t2=2;fi
+if true;then t3=3 ;fi
+if true;then t4=4; ;fi
+if true
+then t5=5
+fi
+if true
+then t6=6;
+fi
+if true
+ then t7=7
+fi
+if true
+then t8=8; fi
+if true
+then
+t9=9
+
+fi
+
+menuentry $t1$t2$t3$t4$t5$t6$t7$t8$t9 {linux /vmlinux}
+#endif
+
+void run_test(struct parser_test *test)
+{
+	struct discover_boot_option *opt;
+
+	test_read_conf_embedded(test, "/grub2/grub.cfg");
+
+	test_run_parser(test, "grub2");
+
+	check_boot_option_count(test->ctx, 1);
+	opt = get_boot_option(test->ctx, 0);
+	check_name(opt, "123456789");
+}