diff --git a/CHANGELOG.md b/CHANGELOG.md
index 7df6439d5ee38b236a0731cf5ca09b82c7fcf002..ae54ee305c850655b6132b45fc6980aa9ad14d2a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -18,6 +18,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
the correct loading behavior of that file.
### Deprecated ###
+- The command line argument '--prefix' and the 'prefix' argument of
+ `crawler_main` is depricated. Use the new argument "--remove-prefix".
### Removed ###
diff --git a/integrationtests/test_data/extroot/realworld_example/dataset_cfoods.yml b/integrationtests/test_data/extroot/realworld_example/dataset_cfoods.yml
index 7a64d708667182b80b739812e5fdf3369fc5b462..e149c0ccc0008a20d96ee782a853d345d541f3ab 100644
--- a/integrationtests/test_data/extroot/realworld_example/dataset_cfoods.yml
+++ b/integrationtests/test_data/extroot/realworld_example/dataset_cfoods.yml
@@ -31,6 +31,11 @@ Data:
type: JSONFile
match: .dataspace.json
validate: schema/dataspace.schema.json
+ records:
+ JSONFile:
+ role: File
+ path: $dataspace_json
+ file: $dataspace_json
subtree:
jsondict:
type: DictElement
diff --git a/integrationtests/test_data/extroot/realworld_example/schema/dataspace.schema.json b/integrationtests/test_data/extroot/realworld_example/schema/dataspace.schema.json
index 01653bfa821e0a0acbb5a481bfd458e2ed784fb9..c6376ee44d248ce5ea9e24e34bd245255e888e39 100644
--- a/integrationtests/test_data/extroot/realworld_example/schema/dataspace.schema.json
+++ b/integrationtests/test_data/extroot/realworld_example/schema/dataspace.schema.json
@@ -9,6 +9,7 @@
"minimum": 20000
},
"archived": { "type": "boolean" },
+ "JSONFile": { "type": "string" },
"url": {
"type": "string",
"description": "link to folder on file system (CaosDB or cloud folder)"
diff --git a/integrationtests/test_realworld_example.py b/integrationtests/test_realworld_example.py
index 4158ed22278ef5c871a22d45885e58fbfa84ea3b..5542596e2751a5de8a34a9e19628266e8c753ad3 100644
--- a/integrationtests/test_realworld_example.py
+++ b/integrationtests/test_realworld_example.py
@@ -35,6 +35,7 @@ from caoscrawler.identifiable_adapters import CaosDBIdentifiableAdapter
from caoscrawler.structure_elements import Directory
import pytest
from caosadvancedtools.models.parser import parse_model_from_json_schema, parse_model_from_yaml
+from caosadvancedtools.loadFiles import loadpath
import sys
@@ -52,6 +53,17 @@ def rfp(*pathcomponents):
DATADIR = rfp("test_data", "extroot", "realworld_example")
+@pytest.fixture
+def addfiles():
+ loadpath(path='/opt/caosdb/mnt/extroot/',
+ include=None,
+ exclude=None,
+ prefix="",
+ dryrun=False,
+ forceAllowSymlinks=True,
+ )
+
+
@pytest.fixture
def usemodel():
# First load dataspace data model
@@ -85,22 +97,18 @@ def create_identifiable_adapter():
return ident
-def test_dataset(clear_database, usemodel):
- ident = create_identifiable_adapter()
- crawler = Crawler(identifiableAdapter=ident)
- crawler_definition = crawler.load_definition(
- os.path.join(DATADIR, "dataset_cfoods.yml"))
- # print(json.dumps(crawler_definition, indent=3))
- # Load and register converter packages:
- converter_registry = crawler.load_converters(crawler_definition)
- # print("DictIntegerElement" in converter_registry)
-
- records = crawler.start_crawling(
- Directory("data", os.path.join(DATADIR, 'data')),
- crawler_definition,
- converter_registry
+def test_dataset(clear_database, usemodel, addfiles):
+ identifiable_path = os.path.join(DATADIR, "identifiables.yml")
+ crawler_definition_path = os.path.join(DATADIR, "dataset_cfoods.yml")
+ crawler_main(
+ os.path.join(DATADIR, 'data'),
+ crawler_definition_path,
+ identifiable_path,
+ True,
+ os.path.join(DATADIR, "provenance.yml"),
+ False,
+ add_prefix="/data"
)
- crawler.synchronize()
dataspace = db.execute_query("FIND RECORD Dataspace WITH name=35 AND dataspace_id=20002 AND "
"archived=FALSE AND url='https://datacloud.de/index.php/f/7679'"
@@ -120,12 +128,11 @@ def test_dataset(clear_database, usemodel):
assert db.execute_query(f"FIND Event WITH latitude=53", unique=True)
-def test_event_update(clear_database, usemodel):
+def test_event_update(clear_database, usemodel, addfiles):
identifiable_path = os.path.join(DATADIR, "identifiables.yml")
crawler_definition_path = os.path.join(DATADIR, "dataset_cfoods.yml")
- # TODO(fspreck): Use crawler_main
crawler_main(
os.path.join(DATADIR, 'data'),
crawler_definition_path,
@@ -133,7 +140,7 @@ def test_event_update(clear_database, usemodel):
True,
os.path.join(DATADIR, "provenance.yml"),
False,
- ""
+ add_prefix="/data"
)
old_dataset_rec = db.execute_query(
diff --git a/integrationtests/test_use_case_simple_presentation.py b/integrationtests/test_use_case_simple_presentation.py
index 91c523be90a4d0117a7cc54217cae0b911511957..ff2f2a43c5f4f923202218f5cd4eb89b82db04a7 100644
--- a/integrationtests/test_use_case_simple_presentation.py
+++ b/integrationtests/test_use_case_simple_presentation.py
@@ -63,7 +63,7 @@ def test_complete_crawler(
True,
os.path.join(DATADIR, "provenance.yml"),
False,
- "/use_case_simple_presentation")
+ remove_prefix="/use_case_simple_presentation")
res = db.execute_query("FIND Record Experiment")
assert len(res) == 1
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index fe6c63ff7af86a76fd6649323c96b8977b9fcc2f..60face1706dabbe40b78026d637154f5c97e13c4 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -1229,7 +1229,9 @@ def crawler_main(crawled_directory_path: str,
prefix: str = "",
securityMode: SecurityMode = SecurityMode.UPDATE,
unique_names=True,
- restricted_path: Optional[list[str]] = None
+ restricted_path: Optional[list[str]] = None,
+ remove_prefix: Optional[str] = None,
+ add_prefix: Optional[str] = None,
):
"""
@@ -1248,7 +1250,7 @@ def crawler_main(crawled_directory_path: str,
dry_run : bool
do not commit any chnages to the server
prefix : str
- remove the given prefix from file paths
+ DEPRICATED, remove the given prefix from file paths
securityMode : int
securityMode of Crawler
unique_names : bool
@@ -1256,6 +1258,10 @@ def crawler_main(crawled_directory_path: str,
restricted_path: optional, list of strings
Traverse the data tree only along the given path. When the end of the given path
is reached, traverse the full tree as normal.
+ remove_prefix : Optional[str]
+ remove the given prefix from file paths
+ add_prefix : Optional[str]
+ add the given prefix to file paths
Returns
-------
@@ -1272,11 +1278,17 @@ def crawler_main(crawled_directory_path: str,
crawler.save_debug_data(provenance_file)
if identifiables_definition_file is not None:
-
ident = CaosDBIdentifiableAdapter()
ident.load_from_yaml_definition(identifiables_definition_file)
crawler.identifiableAdapter = ident
+ if prefix != "":
+ warnings.warn(DeprecationWarning("The prefix argument is derpicated. Please use "
+ "remove_prefix."))
+ if remove_prefix is not None:
+ raise ValueError("Please do not supply prefix argument. Only remove_prefix")
+ remove_prefix = prefix
+
if dry_run:
ins, upd = crawler.synchronize(commit_changes=False)
inserts = [str(i) for i in ins]
@@ -1291,11 +1303,14 @@ def crawler_main(crawled_directory_path: str,
if isinstance(elem, db.File):
# correct the file path:
# elem.file = os.path.join(args.path, elem.file)
- if prefix is None:
- raise RuntimeError(
- "No prefix set. Prefix must be set if files are used.")
- if elem.path.startswith(prefix):
- elem.path = elem.path[len(prefix):]
+ if remove_prefix:
+ if elem.path.startswith(remove_prefix):
+ elem.path = elem.path[len(remove_prefix):]
+ else:
+ raise RuntimeError("Prefix shall be removed from file path but the path "
+ "does not start with the prefix")
+ if add_prefix:
+ elem.path = add_prefix + elem.path
elem.file = None
# TODO: as long as the new file backend is not finished
# we are using the loadFiles function to insert symlinks.
@@ -1363,8 +1378,12 @@ def parse_args():
parser.add_argument("-u", "--unique-names",
help="Insert or updates entities even if name conflicts exist.")
parser.add_argument("-p", "--prefix",
- help="Remove the given prefix from the paths "
+ help="DEPRICATED. Remove the given prefix from the paths "
"of all file objects.")
+ parser.add_argument("--remove-prefix",
+ help="Remove the given prefix from the paths of all file objects.")
+ parser.add_argument("--add-prefix",
+ help="Add the given prefix to the paths of all file objects.")
return parser.parse_args()
@@ -1384,6 +1403,10 @@ def main():
conlogger = logging.getLogger("connection")
conlogger.setLevel(level=logging.ERROR)
+ if args.prefix:
+ print("Please use '--remove-prefix' option instead of '--prefix' or '-p'.")
+ return -1
+
# logging config for local execution
logger.addHandler(logging.StreamHandler(sys.stdout))
if args.debug:
@@ -1406,12 +1429,13 @@ def main():
debug=args.debug,
provenance_file=args.provenance,
dry_run=args.dry_run,
- prefix=args.prefix,
securityMode={"retrieve": SecurityMode.RETRIEVE,
"insert": SecurityMode.INSERT,
"update": SecurityMode.UPDATE}[args.security_mode],
unique_names=args.unique_names,
- restricted_path=restricted_path
+ restricted_path=restricted_path,
+ remove_prefix=args.remove_prefix,
+ add_prefix=args.add_prefix,
))
diff --git a/unittests/test_tool.py b/unittests/test_tool.py
index 23b35f2dc9228eeda9137945198c49c19bf5c474..735c33125fcf024d1cb4bd9b83ad222ce66ba2d0 100755
--- a/unittests/test_tool.py
+++ b/unittests/test_tool.py
@@ -792,8 +792,7 @@ def test_validation_error_print(caplog):
os.path.join(DATADIR, "identifiables.yml"),
True,
None,
- False,
- "/use_case_simple_presentation")
+ False)
assert "Couldn't validate" in caplog.text
caplog.clear()