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
90620c94
Commit
90620c94
authored
2 years ago
by
Alexander Schlemmer
Browse files
Options
Downloads
Patches
Plain Diff
MAIN: refactored scan_structure_elements and scan_directory functions
parent
31a6b372
Branches
Branches containing commit
Tags
Tags containing commit
2 merge requests
!108
Release 0.5.0
,
!104
Create a new scanner module and move functions from crawl module there
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
src/caoscrawler/scanner.py
+20
-25
20 additions, 25 deletions
src/caoscrawler/scanner.py
with
20 additions
and
25 deletions
src/caoscrawler/scanner.py
+
20
−
25
View file @
90620c94
...
...
@@ -164,6 +164,8 @@ def create_converter_registry(definition: dict):
- module is the name of the module to be imported which must be installed
- class is the converter class to load and associate with this converter entry
Formerly known as
"
load_converters
"
.
all other info for the converter needs to be included in the converter plugin
directory:
schema.yml file
...
...
@@ -337,10 +339,12 @@ def _crawl(self,
# --------------------------------------------------------------------------------
def
crawl
_directory
(
dirname
:
str
,
crawler_definition_path
:
str
,
def
scan
_directory
(
dirname
:
str
,
crawler_definition_path
:
str
,
restricted_path
:
Optional
[
list
[
str
]]
=
None
):
"""
Crawl a single directory.
Formerly known as
"
crawl_directory
"
.
Convenience function that starts the crawler (calls start_crawling)
with a single directory as the StructureElement.
...
...
@@ -351,7 +355,7 @@ def crawl_directory(dirname: str, crawler_definition_path: str,
crawler_definition
=
load_definition
(
crawler_definition_path
)
# Load and register converter packages:
converter_registry
=
load
_converter
s
(
crawler_definition
)
converter_registry
=
create
_converter
_registry
(
crawler_definition
)
if
not
dirname
:
raise
ValueError
(
...
...
@@ -366,21 +370,22 @@ def crawl_directory(dirname: str, crawler_definition_path: str,
# dirname had a trailing '/'
dir_structure_name
=
os
.
path
.
basename
(
dirname
[:
-
1
])
start_crawling
(
Directory
(
dir_structure_name
,
return
scan_structure_elements
(
Directory
(
dir_structure_name
,
dirname
),
crawler_definition
,
converter_registry
,
restricted_path
=
restricted_path
)
restricted_path
=
restricted_path
)
def
s
tart_crawling
(
items
:
Union
[
list
[
StructureElement
],
StructureElement
],
def
s
can_structure_elements
(
items
:
Union
[
list
[
StructureElement
],
StructureElement
],
crawler_definition
:
dict
,
converter_registry
:
dict
,
restricted_path
:
Optional
[
list
[
str
]]
=
None
):
"""
Start point of the crawler recursion.
Formerly known as
"
start_crawling
"
.
Parameters
----------
items: list
...
...
@@ -400,27 +405,17 @@ def start_crawling(items: Union[list[StructureElement], StructureElement],
"""
# This function builds the tree of converters out of the crawler definition.
if
self
.
generalStore
is
None
:
raise
RuntimeError
(
"
Should not happen.
"
)
if
not
isinstance
(
items
,
list
):
items
=
[
items
]
self
.
run_id
=
uuid
.
uuid1
()
local_
converters
=
Crawler
.
initialize_converters
(
crawler_definition
,
converter_registry
)
converters
=
initialize_converters
(
crawler_definition
,
converter_registry
)
# This recursive crawling procedure generates the update list:
self
.
crawled_data
:
list
[
db
.
Record
]
=
[]
self
.
_crawl
(
return
_crawl
(
items
=
items
,
local_converters
=
local_
converters
,
local_converters
=
converters
,
generalStore
=
self
.
generalStore
,
recordStore
=
self
.
recordStore
,
structure_elements_path
=
[],
converters_path
=
[],
restricted_path
=
restricted_path
)
if
self
.
debug
:
self
.
debug_converters
=
local_converters
return
self
.
crawled_data
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