Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
E
ece459-w23-a2
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Patrick Lam
ece459-w23-a2
Commits
c749a8c4
Commit
c749a8c4
authored
2 years ago
by
Patrick Lam
Browse files
Options
Downloads
Patches
Plain Diff
restore wrapping backwards, dunno why I removed it
parent
abf74caa
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
src/main.rs
+1
-1
1 addition, 1 deletion
src/main.rs
src/packages/parser.rs
+43
-16
43 additions, 16 deletions
src/packages/parser.rs
with
44 additions
and
17 deletions
src/main.rs
+
1
−
1
View file @
c749a8c4
...
...
@@ -23,7 +23,7 @@ struct Args {
fn
test_derive_2grams_from_trigram
()
{
let
twograms_oracle
=
vec!
[(
"one^two"
),
(
"two^three"
)];
let
twograms
=
derive_2grams
(
"one^two^three"
);
let
twograms
=
derive_2grams
_from_trigram
(
"one^two^three"
);
assert_eq!
(
twograms_oracle
,
twograms
);
}
...
...
This diff is collapsed.
Click to expand it.
src/packages/parser.rs
+
43
−
16
View file @
c749a8c4
...
...
@@ -102,8 +102,8 @@ fn test_token_splitter() {
assert_eq!
(
split_line
,
vec!
[
"check"
,
"pass;"
,
"user"
,
"unknown"
]);
}
// processes line, a
ssum
ing t
hat prev1 and prev2 were the last tokens on the previous
line, and returns the first 2 tokens on this line
fn
process_dictionary_builder_line
(
line
:
String
,
lookahead_line
:
Option
<
String
>
,
regexp
:
&
Regex
,
regexps
:
&
Vec
<
Regex
>
,
dbl
:
&
mut
HashMap
<
String
,
i32
>
,
trpl
:
&
mut
HashMap
<
String
,
i32
>
,
all_token_list
:
&
mut
Vec
<
String
>
)
{
// processes line, a
dd
ing t
o the end of line the first two tokens from lookahead_
line, and returns the first 2 tokens on this line
fn
process_dictionary_builder_line
(
line
:
String
,
lookahead_line
:
Option
<
String
>
,
regexp
:
&
Regex
,
regexps
:
&
Vec
<
Regex
>
,
dbl
:
&
mut
HashMap
<
String
,
i32
>
,
trpl
:
&
mut
HashMap
<
String
,
i32
>
,
all_token_list
:
&
mut
Vec
<
String
>
,
prev1
:
Option
<
String
>
,
prev2
:
Option
<
String
>
)
->
(
Option
<
String
>
,
Option
<
String
>
)
{
let
(
next1
,
next2
)
=
match
lookahead_line
{
None
=>
(
None
,
None
),
Some
(
ll
)
=>
{
...
...
@@ -118,13 +118,28 @@ fn process_dictionary_builder_line(line: String, lookahead_line: Option<String>,
let
mut
tokens
=
token_splitter
(
line
,
&
regexp
,
&
regexps
);
if
tokens
.is_empty
()
{
return
;
return
(
None
,
None
)
;
}
tokens
.iter
()
.for_each
(|
t
|
if
!
all_token_list
.contains
(
t
)
{
all_token_list
.push
(
t
.clone
())
}
);
let
mut
tokens2
=
match
next1
{
// keep this for later when we'll return it
let
last1
=
match
tokens
.len
()
{
0
=>
None
,
n
=>
Some
(
tokens
[
n
-
1
]
.clone
())
};
let
last2
=
match
tokens
.len
()
{
0
=>
None
,
1
=>
None
,
n
=>
Some
(
tokens
[
n
-
2
]
.clone
())
};
let
mut
tokens2_
=
match
prev1
{
None
=>
tokens
,
Some
(
x
)
=>
{
tokens
.push
(
x
);
tokens
}
Some
(
x
)
=>
{
let
mut
t
=
vec!
[
x
];
t
.append
(
&
mut
tokens
);
t
}
};
let
mut
tokens2
=
match
next1
{
None
=>
tokens2_
,
Some
(
x
)
=>
{
tokens2_
.push
(
x
);
tokens2_
}
};
for
doubles
in
tokens2
.windows
(
2
)
{
...
...
@@ -136,9 +151,13 @@ fn process_dictionary_builder_line(line: String, lookahead_line: Option<String>,
}
}
let
tokens3
=
match
next
2
{
let
mut
tokens3
_
=
match
prev
2
{
None
=>
tokens2
,
Some
(
x
)
=>
{
tokens2
.push
(
x
);
tokens2
}
Some
(
x
)
=>
{
let
mut
t
=
vec!
[
x
];
t
.append
(
&
mut
tokens2
);
t
}
};
let
tokens3
=
match
next2
{
None
=>
tokens3_
,
Some
(
x
)
=>
{
tokens3_
.push
(
x
);
tokens3_
}
};
for
triples
in
tokens3
.windows
(
3
)
{
let
triple_tmp
=
format!
(
"{}^{}^{}"
,
triples
[
0
],
triples
[
1
],
triples
[
2
]);
...
...
@@ -148,6 +167,7 @@ fn process_dictionary_builder_line(line: String, lookahead_line: Option<String>,
trpl
.insert
(
triple_tmp
,
1
);
}
}
return
(
last1
,
last2
);
}
fn
dictionary_builder
(
raw_fn
:
String
,
format
:
String
,
regexps
:
Vec
<
Regex
>
)
->
(
HashMap
<
String
,
i32
>
,
HashMap
<
String
,
i32
>
,
Vec
<
String
>
)
{
...
...
@@ -156,6 +176,8 @@ fn dictionary_builder(raw_fn: String, format: String, regexps: Vec<Regex>) -> (H
let
mut
all_token_list
=
vec!
[];
let
regex
=
regex_generator
(
format
);
let
mut
prev1
=
None
;
let
mut
prev2
=
None
;
if
let
Ok
(
lines
)
=
read_lines
(
raw_fn
)
{
let
mut
lp
=
lines
.peekable
();
loop
{
...
...
@@ -164,9 +186,9 @@ fn dictionary_builder(raw_fn: String, format: String, regexps: Vec<Regex>) -> (H
Some
(
Ok
(
ip
))
=>
match
lp
.peek
()
{
None
=>
process_dictionary_builder_line
(
ip
,
None
,
&
regex
,
&
regexps
,
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
),
(
prev1
,
prev2
)
=
process_dictionary_builder_line
(
ip
,
None
,
&
regex
,
&
regexps
,
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
,
prev1
,
prev2
),
Some
(
Ok
(
next_line
))
=>
process_dictionary_builder_line
(
ip
,
Some
(
next_line
.clone
()),
&
regex
,
&
regexps
,
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
),
(
prev1
,
prev2
)
=
process_dictionary_builder_line
(
ip
,
Some
(
next_line
.clone
()),
&
regex
,
&
regexps
,
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
,
prev1
,
prev2
),
Some
(
Err
(
_
))
=>
{}
// meh, some weirdly-encoded line, throw it out
}
Some
(
Err
(
_
))
=>
{}
// meh, some weirdly-encoded line, throw it out
...
...
@@ -183,7 +205,8 @@ fn test_dictionary_builder_process_line_lookahead_is_none() {
let
mut
dbl
=
HashMap
::
new
();
let
mut
trpl
=
HashMap
::
new
();
let
mut
all_token_list
=
vec!
[];
process_dictionary_builder_line
(
line
,
None
,
&
re
,
&
linux_censored_regexps
(),
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
);
let
(
last1
,
last2
)
=
process_dictionary_builder_line
(
line
,
None
,
&
re
,
&
linux_censored_regexps
(),
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
,
None
,
None
);
assert_eq!
((
last1
,
last2
),
(
Some
(
"unknown"
.to_string
()),
Some
(
"user"
.to_string
())));
let
mut
dbl_oracle
=
HashMap
::
new
();
dbl_oracle
.insert
(
"user^unknown"
.to_string
(),
1
);
...
...
@@ -205,10 +228,12 @@ fn test_dictionary_builder_process_line_lookahead_is_some() {
let
mut
dbl
=
HashMap
::
new
();
let
mut
trpl
=
HashMap
::
new
();
let
mut
all_token_list
=
vec!
[];
process_dictionary_builder_line
(
line
,
Some
(
next_line
),
&
re
,
&
linux_censored_regexps
(),
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
);
let
(
last1
,
last2
)
=
process_dictionary_builder_line
(
line
,
Some
(
next_line
),
&
re
,
&
linux_censored_regexps
(),
&
mut
dbl
,
&
mut
trpl
,
&
mut
all_token_list
,
Some
(
"foo"
.to_string
()),
Some
(
"bar"
.to_string
()));
assert_eq!
((
last1
,
last2
),
(
Some
(
"unknown"
.to_string
()),
Some
(
"user"
.to_string
())));
let
mut
dbl_oracle
=
HashMap
::
new
();
dbl_oracle
.insert
(
"unknown^baz"
.to_string
(),
1
);
dbl_oracle
.insert
(
"foo^check"
.to_string
(),
1
);
dbl_oracle
.insert
(
"user^unknown"
.to_string
(),
1
);
dbl_oracle
.insert
(
"pass;^user"
.to_string
(),
1
);
dbl_oracle
.insert
(
"check^pass;"
.to_string
(),
1
);
...
...
@@ -218,6 +243,8 @@ fn test_dictionary_builder_process_line_lookahead_is_some() {
trpl_oracle
.insert
(
"pass;^user^unknown"
.to_string
(),
1
);
trpl_oracle
.insert
(
"check^pass;^user"
.to_string
(),
1
);
trpl_oracle
.insert
(
"unknown^baz^bad"
.to_string
(),
1
);
trpl_oracle
.insert
(
"foo^check^pass;"
.to_string
(),
1
);
trpl_oracle
.insert
(
"bar^foo^check"
.to_string
(),
1
);
trpl_oracle
.insert
(
"user^unknown^baz"
.to_string
(),
1
);
assert_eq!
(
trpl
,
trpl_oracle
);
}
...
...
@@ -249,21 +276,21 @@ fn test_parse_raw_linux() {
double_dict_oracle
.insert
(
"rdd_42_22^locally"
.to_string
(),
1
);
double_dict_oracle
.insert
(
"rdd_42_23^locally"
.to_string
(),
1
);
double_dict_oracle
.insert
(
"rdd_42_24^locally"
.to_string
(),
1
);
double_dict_oracle
.insert
(
"locally^Found"
.to_string
(),
3
);
double_dict_oracle
.insert
(
"locally^Found"
.to_string
(),
6
);
assert_eq!
(
double_dict
,
double_dict_oracle
);
let
mut
triple_dict_oracle
=
HashMap
::
new
();
triple_dict_oracle
.insert
(
"block^rdd_42_20^locally"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"block^rdd_42_22^locally"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"block^rdd_42_23^locally"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"block^rdd_42_24^locally"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"rdd_42_20^locally^Found"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"rdd_42_22^locally^Found"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"rdd_42_23^locally^Found"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"rdd_42_20^locally^Found"
.to_string
(),
2
);
triple_dict_oracle
.insert
(
"rdd_42_22^locally^Found"
.to_string
(),
2
);
triple_dict_oracle
.insert
(
"rdd_42_23^locally^Found"
.to_string
(),
2
);
triple_dict_oracle
.insert
(
"Found^block^rdd_42_20"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"Found^block^rdd_42_22"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"Found^block^rdd_42_23"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"Found^block^rdd_42_24"
.to_string
(),
1
);
triple_dict_oracle
.insert
(
"locally^Found^block"
.to_string
(),
3
);
triple_dict_oracle
.insert
(
"locally^Found^block"
.to_string
(),
6
);
assert_eq!
(
triple_dict
,
triple_dict_oracle
);
}
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment