Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
C
crawl
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Service Desk
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
ale
crawl
Commits
7c1b1f70
Commit
7c1b1f70
authored
10 years ago
by
ale
Browse files
Options
Downloads
Patches
Plain Diff
add a prefix iterator to gobDb
parent
c31b2d91
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
crawler.go
+24
-4
24 additions, 4 deletions
crawler.go
with
24 additions
and
4 deletions
crawler.go
+
24
−
4
View file @
7c1b1f70
...
...
@@ -50,6 +50,25 @@ func (db *gobDB) GetObj(ro *levigo.ReadOptions, key []byte, obj interface{}) err
return
nil
}
func
(
db
*
gobDB
)
NewPrefixIterator
(
ro
*
levigo
.
ReadOptions
,
prefix
[]
byte
)
*
gobIterator
{
i
:=
db
.
NewIterator
(
ro
)
i
.
Seek
(
prefix
)
return
&
gobIterator
{
Iterator
:
i
,
prefix
:
prefix
}
}
type
gobIterator
struct
{
*
levigo
.
Iterator
prefix
[]
byte
}
func
(
i
*
gobIterator
)
Valid
()
bool
{
return
i
.
Iterator
.
Valid
()
&&
bytes
.
HasPrefix
(
i
.
Key
(),
i
.
prefix
)
}
func
(
i
*
gobIterator
)
Value
(
obj
interface
{})
error
{
return
gob
.
NewDecoder
(
bytes
.
NewBuffer
(
i
.
Iterator
.
Value
()))
.
Decode
(
obj
)
}
type
URLInfo
struct
{
URL
string
StatusCode
int
...
...
@@ -77,7 +96,7 @@ func (f HandlerFunc) Handle(db *Crawler, u string, depth int, resp *http.Respons
return
f
(
db
,
u
,
depth
,
resp
,
err
)
}
// UrlDb is the database of crawls (either pending or done).
// UrlDb is the database of crawl
ed URL
s (either pending or done).
type
Crawler
struct
{
db
*
gobDB
seeds
[]
*
url
.
URL
...
...
@@ -113,6 +132,7 @@ func (c *Crawler) Enqueue(u *url.URL, depth int) {
}
}
// Protect the read-modify-update below with a mutex.
c
.
enqueueMx
.
Lock
()
defer
c
.
enqueueMx
.
Unlock
()
...
...
@@ -151,10 +171,10 @@ func (c *Crawler) process() <-chan QueuePair {
ro
:=
levigo
.
NewReadOptions
()
ro
.
SetSnapshot
(
s
)
iter
:=
c
.
db
.
NewIterator
(
ro
)
for
iter
.
Seek
(
queuePrefix
);
iter
.
Valid
()
&&
bytes
.
HasPrefix
(
iter
.
Key
(),
queuePrefix
);
iter
.
Next
()
{
iter
:=
c
.
db
.
New
Prefix
Iterator
(
ro
,
queuePrefix
)
for
;
iter
.
Valid
(
);
iter
.
Next
()
{
var
p
QueuePair
if
err
:=
gob
.
NewDecoder
(
bytes
.
NewBuffer
(
iter
.
Value
()))
.
Decod
e
(
&
p
);
err
!=
nil
{
if
err
:=
iter
.
Valu
e
(
&
p
);
err
!=
nil
{
continue
}
ch
<-
p
...
...
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