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
07ae221f
Commit
07ae221f
authored
3 years ago
by
Henrik tom Wörden
Browse files
Options
Downloads
Patches
Plain Diff
TST: add unittest
parent
78524fe7
No related branches found
No related tags found
2 merge requests
!53
Release 0.1
,
!9
ENH: introduce JSON converter
Changes
3
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
src/newcrawler/converters.py
+7
-5
7 additions, 5 deletions
src/newcrawler/converters.py
src/newcrawler/structure_elements.py
+6
-0
6 additions, 0 deletions
src/newcrawler/structure_elements.py
unittests/test_converters.py
+58
-3
58 additions, 3 deletions
unittests/test_converters.py
with
71 additions
and
8 deletions
src/newcrawler/converters.py
+
7
−
5
View file @
07ae221f
...
...
@@ -26,10 +26,11 @@
import
os
import
re
import
caosdb
as
db
import
json
from
.utils
import
has_parent
from
.stores
import
GeneralStore
,
RecordStore
from
.structure_elements
import
(
StructureElement
,
Directory
,
File
,
TextElement
,
DictTextElement
,
DictListElement
)
TextElement
,
DictTextElement
,
DictElement
,
DictListElement
)
from
typing
import
Optional
,
Union
from
abc
import
abstractmethod
import
yaml_header_tools
...
...
@@ -397,17 +398,18 @@ class JSONFileConverter(Converter):
# DictXXXElements for numbers, booleans, enums, ...
if
type
(
entry
)
==
list
:
children
.
append
(
DictListElement
(
name
,
entry
))
elif
type
(
entry
)
==
str
ing
:
elif
type
(
entry
)
==
str
:
children
.
append
(
DictTextElement
(
name
,
entry
))
else
:
raise
RuntimeError
(
f
"
JSON entry
{
name
}
has incompatible type.
"
)
children
.
append
(
DictElement
(
name
,
entry
))
print
(
f
"
JSON entry
{
name
}
has incompatible type.
"
)
# raise RuntimeError(f"JSON entry {name} has incompatible type.")
return
children
class
DictTextElementConverter
(
Converter
):
def
create_children
(
self
,
generalStore
:
GeneralStore
,
element
:
StructureElement
):
def
create_children
(
self
,
generalStore
:
GeneralStore
,
element
:
StructureElement
):
return
[]
def
typecheck
(
self
,
element
:
StructureElement
):
...
...
This diff is collapsed.
Click to expand it.
src/newcrawler/structure_elements.py
+
6
−
0
View file @
07ae221f
...
...
@@ -60,6 +60,12 @@ class File(FileSystemStructureElement):
pass
class
DictElement
(
StructureElement
):
def
__init__
(
self
,
name
:
str
,
value
:
str
):
super
().
__init__
(
name
)
self
.
value
=
value
class
DictTextElement
(
StructureElement
):
def
__init__
(
self
,
name
:
str
,
value
:
str
):
super
().
__init__
(
name
)
...
...
This diff is collapsed.
Click to expand it.
unittests/test_converters.py
+
58
−
3
View file @
07ae221f
...
...
@@ -29,15 +29,16 @@ test the converters module
from
newcrawler.converters
import
Converter
from
newcrawler.stores
import
GeneralStore
from
newcrawler.converters
import
MarkdownFileConverter
from
newcrawler.converters
import
MarkdownFileConverter
,
JSONFileConverter
from
newcrawler.structure_elements
import
Directory
from
newcrawler.structure_elements
import
File
,
DictTextElement
,
DictListElement
from
newcrawler.structure_elements
import
File
,
DictTextElement
,
DictListElement
,
DictElement
from
test_tool
import
rfp
import
pytest
import
importlib
@pytest.fixture
def
converter_registry
():
converter_registry
:
dict
[
str
,
dict
[
str
,
str
]]
=
{
...
...
@@ -55,7 +56,10 @@ def converter_registry():
"
package
"
:
"
newcrawler.converters
"
},
"
TextElement
"
:
{
"
converter
"
:
"
TextElementConverter
"
,
"
package
"
:
"
newcrawler.converters
"
}
"
package
"
:
"
newcrawler.converters
"
},
"
JSONFile
"
:
{
"
converter
"
:
"
JSONFileConverter
"
,
"
package
"
:
"
newcrawler.converters
"
},
}
for
key
,
value
in
converter_registry
.
items
():
...
...
@@ -158,3 +162,54 @@ def test_markdown_converter(converter_registry):
assert
children
[
0
].
__class__
==
DictListElement
assert
children
[
0
].
name
==
"
responsible
"
assert
children
[
0
].
value
.
__class__
==
list
def
test_json_converter
(
converter_registry
):
test_json
=
File
(
"
testjson.json
"
,
rfp
(
"
test_directories
"
,
"
single_file_test_data
"
,
"
testjson.json
"
))
converter
=
JSONFileConverter
(
definition
=
{
"
match
"
:
"
(.*)
"
},
name
=
"
TestJSONFileConverter
"
,
converter_registry
=
converter_registry
)
m
=
converter
.
match
(
test_json
)
assert
m
is
not
None
assert
len
(
m
)
==
0
children
=
converter
.
create_children
(
None
,
test_json
)
assert
len
(
children
)
==
8
assert
children
[
0
].
__class__
==
DictTextElement
assert
children
[
0
].
name
==
"
name
"
assert
children
[
0
].
value
.
__class__
==
str
assert
children
[
0
].
value
==
"
DEMO
"
assert
children
[
1
].
__class__
==
DictElement
assert
children
[
1
].
name
==
"
id
"
assert
children
[
1
].
value
.
__class__
==
int
assert
children
[
1
].
value
==
10002
assert
children
[
2
].
__class__
==
DictElement
assert
children
[
2
].
name
==
"
archived
"
assert
children
[
2
].
value
.
__class__
==
bool
assert
children
[
3
].
__class__
==
DictElement
assert
children
[
3
].
name
==
"
coordinator
"
assert
children
[
3
].
value
.
__class__
==
dict
assert
children
[
4
].
__class__
==
DictTextElement
assert
children
[
4
].
name
==
"
start_date
"
assert
children
[
4
].
value
.
__class__
==
str
assert
children
[
5
].
__class__
==
DictListElement
assert
children
[
5
].
name
==
"
candidates
"
assert
children
[
5
].
value
.
__class__
==
list
assert
children
[
5
].
value
==
[
"
Mouse
"
,
"
Penguine
"
]
assert
children
[
6
].
__class__
==
DictElement
assert
children
[
6
].
name
==
"
rvalue
"
assert
children
[
6
].
value
.
__class__
==
float
assert
children
[
7
].
__class__
==
DictTextElement
assert
children
[
7
].
name
==
"
url
"
assert
children
[
7
].
value
.
__class__
==
str
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