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
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
caosdb
Software
CaosDB Crawler
Commits
1a3fc544
Commit
1a3fc544
authored
4 months ago
by
Florian Spreckelsen
Browse files
Options
Downloads
Patches
Plain Diff
FIX: Add unit tests and fix for
https://gitlab.com/linkahead/linkahead-crawler/-/issues/112
parent
3c836b10
No related branches found
No related tags found
2 merge requests
!217
TST: Make NamedTemporaryFiles Windows-compatible
,
!216
TST: Make NamedTemporaryFiles Windows-compatible
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
src/caoscrawler/converters/converters.py
+4
-1
4 additions, 1 deletion
src/caoscrawler/converters/converters.py
unittests/test_issues.py
+80
-4
80 additions, 4 deletions
unittests/test_issues.py
with
84 additions
and
5 deletions
src/caoscrawler/converters/converters.py
+
4
−
1
View file @
1a3fc544
...
@@ -1327,7 +1327,10 @@ out:
...
@@ -1327,7 +1327,10 @@ out:
m1
=
{}
m1
=
{}
if
"
match_value
"
in
definition
:
if
"
match_value
"
in
definition
:
m2
=
re
.
match
(
definition
[
"
match_value
"
],
str
(
value
),
re
.
DOTALL
)
# None values will be interpreted as empty strings for the
# matcher.
m_value
=
str
(
value
)
if
(
value
is
not
None
and
not
pd
.
isna
(
value
))
else
""
m2
=
re
.
match
(
definition
[
"
match_value
"
],
m_value
,
re
.
DOTALL
)
if
m2
is
None
:
if
m2
is
None
:
return
None
return
None
else
:
else
:
...
...
This diff is collapsed.
Click to expand it.
unittests/test_issues.py
+
80
−
4
View file @
1a3fc544
...
@@ -20,14 +20,44 @@
...
@@ -20,14 +20,44 @@
# along with this program. If not, see <https://www.gnu.org/licenses/>.
# along with this program. If not, see <https://www.gnu.org/licenses/>.
#
#
from
pytes
t
import
mark
impor
t
import
lib
from
caoscrawler.converters
import
CrawlerTemplate
,
replace_variables
from
pathlib
import
Path
from
pytest
import
fixture
,
mark
from
caoscrawler.converters
import
(
CrawlerTemplate
,
replace_variables
,
TextElementConverter
)
from
caoscrawler.crawl
import
Crawler
from
caoscrawler.crawl
import
Crawler
from
caoscrawler.scanner
import
(
create_converter_registry
,
from
caoscrawler.scanner
import
(
create_converter_registry
,
scan_directory
,
scan_structure_elements
)
scan_structure_elements
)
from
caoscrawler.stores
import
GeneralStore
from
caoscrawler.stores
import
GeneralStore
from
caoscrawler.structure_elements
import
DictElement
from
caoscrawler.structure_elements
import
DictElement
,
TextElement
UNITTESTDIR
=
Path
(
__file__
).
parent
@fixture
def
converter_registry
():
converter_registry
:
dict
[
str
,
dict
[
str
,
str
]]
=
{
"
TextElement
"
:
{
"
converter
"
:
"
TextElementConverter
"
,
"
package
"
:
"
caoscrawler.converters
"
},
"
Directory
"
:
{
"
converter
"
:
"
DirectoryConverter
"
,
"
package
"
:
"
caoscrawler.converters
"
},
"
CSVTableConverter
"
:
{
"
converter
"
:
"
CSVTableConverter
"
,
"
package
"
:
"
caoscrawler.converters
"
},
"
Datetime
"
:
{
"
converter
"
:
"
DatetimeElementConverter
"
,
"
package
"
:
"
caoscrawler.converters
"
}
}
for
key
,
value
in
converter_registry
.
items
():
module
=
importlib
.
import_module
(
value
[
"
package
"
])
value
[
"
class
"
]
=
getattr
(
module
,
value
[
"
converter
"
])
return
converter_registry
def
test_issue_10
():
def
test_issue_10
():
...
@@ -148,3 +178,49 @@ def test_issue_93():
...
@@ -148,3 +178,49 @@ def test_issue_93():
propvalue_template
=
CrawlerTemplate
(
propvalue
)
propvalue_template
=
CrawlerTemplate
(
propvalue
)
assert
(
propvalue_template
.
safe_substitute
(
**
values
.
get_storage
())
assert
(
propvalue_template
.
safe_substitute
(
**
values
.
get_storage
())
==
f
"
some text before >> This is
{
exp
}
<< some text after
"
)
==
f
"
some text before >> This is
{
exp
}
<< some text after
"
)
def
test_issue_112
(
converter_registry
):
"""
Test that empty table cells are not matched in case of
``match_value:
"
.+
"
``.
See https://gitlab.com/linkahead/linkahead-crawler/-/issues/112.
"""
tec
=
TextElementConverter
(
name
=
"
TestTextConverter
"
,
definition
=
{
"
match_name
"
:
"
.*
"
,
"
match_value
"
:
"
(?P<content>.+)
"
},
converter_registry
=
converter_registry
)
empty
=
TextElement
(
name
=
"
empty
"
,
value
=
''
)
assert
tec
.
match
(
empty
)
is
None
empty_none
=
TextElement
(
name
=
"
empty
"
,
value
=
None
)
assert
tec
.
match
(
empty_none
)
is
None
non_empty
=
TextElement
(
name
=
"
empty
"
,
value
=
'
'
)
matches
=
tec
.
match
(
non_empty
)
assert
"
content
"
in
matches
assert
matches
[
"
content
"
]
==
'
'
# Cfood definition for CSV example file
records
=
scan_directory
(
UNITTESTDIR
/
"
test_directories
"
/
"
examples_tables
"
/
"
ExperimentalData
"
,
UNITTESTDIR
/
"
test_directories
"
/
"
examples_tables
"
/
"
crawler_for_issue_112.yml
"
)
assert
records
for
rec
in
records
:
print
(
rec
.
name
)
assert
len
(
rec
.
parents
.
filter_by_identity
(
name
=
"
Event
"
))
>
0
assert
rec
.
name
in
[
"
event_a
"
,
"
event_b
"
,
"
event_c
"
]
if
rec
.
name
==
"
event_a
"
:
assert
rec
.
get_property
(
"
event_time
"
)
is
not
None
assert
rec
.
get_property
(
"
event_time
"
).
value
==
"
2025-02-06
"
elif
rec
.
name
==
"
event_b
"
:
# This should not have matched
assert
rec
.
get_property
(
"
event_time
"
)
is
None
if
rec
.
name
==
"
event_c
"
:
assert
rec
.
get_property
(
"
event_time
"
)
is
not
None
assert
rec
.
get_property
(
"
event_time
"
).
value
==
"
2025-02-06T09:00:00
"
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