Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
CaosDB Crawler
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
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
Code review analytics
Issue analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
GitLab community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
caosdb
Software
CaosDB Crawler
Commits
2468d10d
Commit
2468d10d
authored
Nov 17, 2021
by
Alexander Schlemmer
Browse files
Options
Downloads
Patches
Plain Diff
values are updated correctly now in general store
parent
26e44dc8
No related branches found
No related tags found
1 merge request
!53
Release 0.1
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
src/newcrawler/crawl.py
+29
-12
29 additions, 12 deletions
src/newcrawler/crawl.py
tests/test_tool.py
+1
-1
1 addition, 1 deletion
tests/test_tool.py
with
30 additions
and
13 deletions
src/newcrawler/crawl.py
+
29
−
12
View file @
2468d10d
...
...
@@ -61,6 +61,7 @@ example, a regular expresion could be used to get a date from a file name.
import
sys
import
os
import
yaml
import
re
import
argparse
from
abc
import
abstractmethod
from
argparse
import
RawTextHelpFormatter
...
...
@@ -92,14 +93,28 @@ class Store(object):
def
__init__
(
self
):
self
.
storage
=
dict
()
def
__getitem__
(
self
,
key
):
return
self
.
storage
[
key
]
def
update
(
self
,
other
):
self
.
storage
.
update
(
other
)
def
create_scoped_copy
(
self
):
pass
s_copy
=
Store
()
s_copy
.
storage
=
dict
(
self
.
storage
)
return
s_copy
class
GeneralStore
(
Store
):
pass
def
create_scoped_copy
(
self
):
s_copy
=
GeneralStore
()
s_copy
.
storage
=
dict
(
self
.
storage
)
return
s_copy
class
RecordStore
(
Store
):
pass
def
create_scoped_copy
(
self
):
s_copy
=
RecordStore
()
s_copy
.
storage
=
dict
(
self
.
storage
)
return
s_copy
class
Converter
(
object
):
...
...
@@ -260,7 +275,8 @@ class DirectoryConverter(Converter):
def
create_values
(
self
,
values
:
GeneralStore
,
element
:
StructureElement
):
pass
m
=
re
.
match
(
self
.
definition
[
"
match
"
],
element
.
name
)
values
.
update
(
m
.
groupdict
())
def
create_children
(
self
,
generalStore
:
GeneralStore
,
element
:
StructureElement
):
...
...
@@ -275,12 +291,14 @@ class DirectoryConverter(Converter):
pass
def
typecheck
(
self
,
element
:
StructureElement
):
return
isinstance
(
element
,
File
)
return
isinstance
(
element
,
Directory
)
def
match
(
self
,
element
:
StructureElement
):
pass
m
=
re
.
match
(
self
.
definition
[
"
match
"
],
element
.
name
)
return
m
is
not
None
def
create_children_from_directory
(
self
,
element
:
Directory
):
@staticmethod
def
create_children_from_directory
(
element
:
Directory
):
"""
Creates a list of files (of type File) and directories (of type Directory) for a
given directory. No recursion.
...
...
@@ -344,7 +362,7 @@ class Crawler(object):
crawler_definition
=
yaml
.
load
(
f
,
Loader
=
yaml
.
SafeLoader
)
self
.
start_crawling
(
Directory
(
os
.
path
.
basename
(
dirname
),
os
.
path
.
dirname
(
dirname
)
),
dirname
),
crawler_definition
)
...
...
@@ -365,9 +383,8 @@ class Crawler(object):
self
.
converters
.
append
(
Converter
.
converter_factory
(
value
,
key
))
self
.
crawl
([
item
],
self
.
converters
,
[],
self
.
generalStore
,
self
.
recordStore
)
self
.
crawl
(
DirectoryConverter
.
create_children_from_directory
(
item
),
self
.
converters
,
[],
self
.
generalStore
,
self
.
recordStore
)
def
crawl
(
self
,
items
:
list
[
StructureElement
],
...
...
...
...
This diff is collapsed.
Click to expand it.
tests/test_tool.py
+
1
−
1
View file @
2468d10d
...
...
@@ -11,4 +11,4 @@ def test_crawler():
crawler
=
Crawler
([])
crawler
.
crawl_directory
(
join
(
dirname
(
__file__
),
"
test_directories/examples_article
"
),
join
(
dirname
(
__file__
),
"
scifolder_cfood.yml
"
))
assert
True
assert
crawler
.
generalStore
[
"
date
"
]
==
"
test
"
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