+ Fixed the uber scanner test yet again (this time wrt
NULL characters embedded in the token strings).
+ Added a number of sniffing tests. The rules returned
by the parser appear to sniff properly now.

Incidentally, our sniffer supports conjunctions, i.e the rule

1.0 ('abc') [9] ('xyz')

is equivalent to the rule

1.0 ('abc______xyz' & 0xFFF000000FFF)

This is different than the R5 sniffer, which doesn't reject
rules like the former, but appears to ignore all expressions
in the rule except for the first, i.e. it would treat the first
rule as

1.0 ('abc')

The only problem I can see with this is if someone for
some reason wrote such a rule with multiple expressions
for use with the R5 sniffer. It would likely work differently
with ours. I'm going to search my MIME database and see
if any such rules exist. If so, it'll be easy to switch to the
R5 way of doing things.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@663 a95241bf-73f2-0310-859d-f6bbb57e9c96

Used to be ParserTest.*
+ Added some scanner tests
+ Parser tests still do very little testing
+ The "1e-25 ('ABCD')" test, which apparently fails with
R5's CheckSnifferRule(), has been commented out, as our
version accepts it and I can't currently figure out why it
would be an invalid sniffer rule.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@602 a95241bf-73f2-0310-859d-f6bbb57e9c96

+ Fixed the uber scanner test yet again (this time wrt
NULL characters embedded in the token strings).
+ Added a number of sniffing tests. The rules returned
by the parser appear to sniff properly now.

Incidentally, our sniffer supports conjunctions, i.e the rule

1.0 ('abc') [9] ('xyz')

is equivalent to the rule

1.0 ('abc______xyz' & 0xFFF000000FFF)

This is different than the R5 sniffer, which doesn't reject
rules like the former, but appears to ignore all expressions
in the rule except for the first, i.e. it would treat the first
rule as

1.0 ('abc')

The only problem I can see with this is if someone for
some reason wrote such a rule with multiple expressions
for use with the R5 sniffer. It would likely work differently
with ours. I'm going to search my MIME database and see
if any such rules exist. If so, it'll be easy to switch to the
R5 way of doing things.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@663 a95241bf-73f2-0310-859d-f6bbb57e9c96

Used to be ParserTest.*
+ Added some scanner tests
+ Parser tests still do very little testing
+ The "1e-25 ('ABCD')" test, which apparently fails with
R5's CheckSnifferRule(), has been commented out, as our
version accepts it and I can't currently figure out why it
would be an invalid sniffer rule.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@602 a95241bf-73f2-0310-859d-f6bbb57e9c96