Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
E
eecs398-search
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
Model registry
Operate
Environments
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
vcday
eecs398-search
Commits
e18149f5
Commit
e18149f5
authored
7 years ago
by
vcday
Browse files
Options
Downloads
Patches
Plain Diff
validate url b4 push
parent
06bbce9d
No related branches found
No related tags found
No related merge requests found
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
parser/Parser.cpp
+69
-3
69 additions, 3 deletions
parser/Parser.cpp
parser/Parser.h
+7
-0
7 additions, 0 deletions
parser/Parser.h
with
76 additions
and
3 deletions
parser/Parser.cpp
+
69
−
3
View file @
e18149f5
...
...
@@ -58,14 +58,18 @@ void Parser::parse ( string html, ParsedUrl currentUrl, Tokenizer *tokenizer )
string
url
=
extract_url
(
line
);
if
(
url
!=
""
)
{
if
(
isLocal
(
url
)
)
if
(
isLocal
(
url
)
)
{
string
completeUrl
=
""
;
completeUrl
.
assign
(
currentUrl
.
CompleteUrl
);
url
=
completeUrl
+
url
;
}
urlFrontier
->
Push
(
url
);
cout
<<
url
<<
endl
;
if
(
isValid
(
url
)
)
{
// TODO ParsedUrl with anchor text
urlFrontier
->
Push
(
url
);
cout
<<
url
<<
endl
;
}
}
// check if line is title
else
...
...
@@ -148,4 +152,66 @@ string Parser::extract_title ( string & word )
bool
Parser
::
isLocal
(
string
url
)
{
return
(
*
url
.
begin
(
)
==
'/'
);
}
/**
* Returns false if the link is an invalid type
*
* @param url
* @return
*/
bool
Parser
::
isValid
(
string
url
)
{
auto
begPtr
=
url
.
begin
(
);
auto
endPtr
=
begPtr
+
url
.
size
(
)
-
1
;
unsigned
long
size
=
url
.
size
(
);
auto
html
=
findPrev
(
".html"
,
endPtr
,
begPtr
+
size
-
6
);
if
(
*
html
!=
'\0'
)
{
return
true
;
}
// png
if
(
*
findPrev
(
".png"
,
endPtr
,
begPtr
+
size
-
5
)
!=
'\0'
)
{
return
false
;
}
//jpg
if
(
*
findPrev
(
".jpg"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
//jpeg
if
(
*
findPrev
(
".jpeg"
,
endPtr
,
begPtr
+
size
-
6
)
)
{
return
false
;
}
//css
if
(
*
findPrev
(
".css"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
//gif
if
(
*
findPrev
(
".gif"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
//pdf
if
(
*
findPrev
(
".pdf"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
//wav
if
(
*
findPrev
(
".wav"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
//mp3
if
(
*
findPrev
(
".mp3"
,
endPtr
,
begPtr
+
size
-
5
)
)
{
return
false
;
}
return
true
;
}
\ No newline at end of file
This diff is collapsed.
Click to expand it.
parser/Parser.h
+
7
−
0
View file @
e18149f5
...
...
@@ -70,5 +70,12 @@ private:
*/
bool
isLocal
(
string
url
);
/**
* Returns true is url is valid
*
* @param url
* @return
*/
bool
isValid
(
string
url
);
};
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