diff --git a/CHANGELOG.md b/CHANGELOG.md
index dd57c15751ceb8238be36debb92791f4871ce249..354024f9be37fc102f035a5d6562b6d522aaa915 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -23,6 +23,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
variables to `int`, `float`, `str` and `bool`.
- Transformer function definition in the cfood support variable
substitutions now.
+- `crawler_main` and `scanner.scan_directory` now support list of
+ directories to be crawled, too. Note that giving a list of
+ directories is currently incompatible with
+ `securityMode=SecurityMode.RETRIEVE` or
+ `securityMode=SecurityMode.INSERT` since the functionality to
+ authoriye pending inserts or updates doesn't support path lists yet
+ and will raise a NotImplementedError for now.
- `match_newer_than_file` option for `DirectoryConverter`: A reference
file containing (only) an ISO-formatted datetime string can be
specified here. Directories with this option won't match if all
diff --git a/integrationtests/test_crawler_main.py b/integrationtests/test_crawler_main.py
new file mode 100644
index 0000000000000000000000000000000000000000..a2eebf4f04e195754eaf71dc5e829b6a77a4cc4b
--- /dev/null
+++ b/integrationtests/test_crawler_main.py
@@ -0,0 +1,95 @@
+# This file is a part of the LinkAhead Project.
+#
+# Copyright (C) 2024 Indiscale GmbH <info@indiscale.com>
+# 2024 Florian Spreckelsen <f.spreckelsen@indiscale.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as
+# published by the Free Software Foundation, either version 3 of the
+# License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU Affero General Public License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with this program. If not, see <https://www.gnu.org/licenses/>.
+#
+
+import logging
+import tempfile
+
+from pathlib import Path
+
+import linkahead as db
+
+from caoscrawler import crawl
+from caoscrawler.crawl import (crawler_main, SecurityMode)
+from linkahead.utils.register_tests import clear_database, set_test_key
+
+set_test_key("10b128cf8a1372f30aa3697466bb55e76974e0c16a599bb44ace88f19c8f61e2")
+
+INTTESTDIR = Path(__file__).parent
+
+
+def test_list_of_paths(clear_database, monkeypatch):
+
+ # Mock the status record
+ dummy_status = {
+ "n_calls": 0
+ }
+
+ def _mock_update_status_record(run_id, n_inserts, n_updates, status):
+ print("Update mocked status")
+ dummy_status["run_id"] = run_id
+ dummy_status["n_inserts"] = n_inserts
+ dummy_status["n_updates"] = n_updates
+ dummy_status["status"] = status
+ dummy_status["n_calls"] += 1
+ monkeypatch.setattr(crawl, "_update_status_record", _mock_update_status_record)
+
+ # mock SSS environment
+ monkeypatch.setenv("SHARED_DIR", tempfile.gettempdir())
+
+ # We need only one dummy RT
+ rt = db.RecordType(name="TestType").insert()
+ basepath = INTTESTDIR / "test_data" / "crawler_main_with_list_of_dirs"
+ dirlist = [basepath / "dir1", basepath / "dir2"]
+ crawler_main(
+ dirlist,
+ cfood_file_name=basepath / "cfood.yml",
+ identifiables_definition_file=basepath / "identifiable.yml"
+ )
+ recs = db.execute_query("FIND TestType")
+ assert len(recs) == 2
+ assert "Test1" in [r.name for r in recs]
+ assert "Test2" in [r.name for r in recs]
+
+ assert dummy_status["n_inserts"] == 2
+ assert dummy_status["n_updates"] == 0
+ assert dummy_status["status"] == "OK"
+ assert dummy_status["n_calls"] == 1
+
+
+def test_not_implemented_list_with_authorization(caplog, clear_database):
+
+ rt = db.RecordType(name="TestType").insert()
+ basepath = INTTESTDIR / "test_data" / "crawler_main_with_list_of_dirs"
+ dirlist = [basepath / "dir1", basepath / "dir2"]
+
+ # This is not implemented yet, so check log for correct error.
+ ret = crawler_main(
+ dirlist,
+ cfood_file_name=basepath / "cfood.yml",
+ identifiables_definition_file=basepath / "identifiable.yml",
+ securityMode=SecurityMode.RETRIEVE
+ )
+ # crawler_main hides the error, but has a non-zero return code and
+ # errors in the log:
+ assert ret != 0
+ err_tuples = [t for t in caplog.record_tuples if t[1] == logging.ERROR]
+ assert len(err_tuples) == 1
+ assert "currently implemented only for single paths, not for lists of paths" in err_tuples[0][2]
+ # No inserts after the errors
+ assert len(db.execute_query("FIND TestType")) == 0
diff --git a/integrationtests/test_data/crawler_main_with_list_of_dirs/cfood.yml b/integrationtests/test_data/crawler_main_with_list_of_dirs/cfood.yml
new file mode 100644
index 0000000000000000000000000000000000000000..c7f22ce07e9b401915aefde3bf7e3a78d92e2bd6
--- /dev/null
+++ b/integrationtests/test_data/crawler_main_with_list_of_dirs/cfood.yml
@@ -0,0 +1,10 @@
+---
+metadata:
+ crawler-version: 0.10.2
+---
+BaseDirElement:
+ type: Directory
+ match: ^dir(?P<dir_number>[0-9]+)$$
+ records:
+ TestType:
+ name: Test$dir_number
diff --git a/integrationtests/test_data/crawler_main_with_list_of_dirs/dir1/.gitkeep b/integrationtests/test_data/crawler_main_with_list_of_dirs/dir1/.gitkeep
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/integrationtests/test_data/crawler_main_with_list_of_dirs/dir2/.gitkeep b/integrationtests/test_data/crawler_main_with_list_of_dirs/dir2/.gitkeep
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/integrationtests/test_data/crawler_main_with_list_of_dirs/identifiable.yml b/integrationtests/test_data/crawler_main_with_list_of_dirs/identifiable.yml
new file mode 100644
index 0000000000000000000000000000000000000000..6d608cece0ae7c2aa6461fb56025a8ac8e4faf6f
--- /dev/null
+++ b/integrationtests/test_data/crawler_main_with_list_of_dirs/identifiable.yml
@@ -0,0 +1,2 @@
+TestType:
+ - name
diff --git a/integrationtests/test_issues.py b/integrationtests/test_issues.py
index cb1e2e0925dd85b9f6cadf2b56b22aface4bb468..c699e0ab84a0d928c1f84a1b421d97e1b2d848b6 100644
--- a/integrationtests/test_issues.py
+++ b/integrationtests/test_issues.py
@@ -1,4 +1,4 @@
-# This file is a part of the CaosDB Project.
+# This file is a part of the LinkAhead Project.
#
# Copyright (C) 2022 Indiscale GmbH <info@indiscale.com>
# 2022 Florian Spreckelsen <f.spreckelsen@indiscale.com>
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index a79e4434ee8f58fd1cc2646ced85c0d02d3fb66b..a939b2ff8240295b08c23cdf505005ebdf318d32 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -621,7 +621,7 @@ one with the entities that need to be updated and the other with entities to be
crawled_data: Optional[list[db.Record]] = None,
no_insert_RTs: Optional[list[str]] = None,
no_update_RTs: Optional[list[str]] = None,
- path_for_authorized_run: Optional[str] = "",
+ path_for_authorized_run: Optional[Union[str, list[str]]] = "",
):
"""
This function applies several stages:
@@ -643,7 +643,7 @@ one with the entities that need to be updated and the other with entities to be
no_update_RTs : list[str], optional
list of RecordType names. Records that have one of those RecordTypes
as parent will not be updated
- path_for_authorized_run : str, optional
+ path_for_authorized_run : str or list[str], optional
only used if there are changes that need authorization before being
applied. The form for rerunning the crawler with the authorization
of these changes will be generated with this path. See
@@ -661,6 +661,12 @@ one with the entities that need to be updated and the other with entities to be
"use for example the Scanner to create this data."))
crawled_data = self.crawled_data
+ if isinstance(path_for_authorized_run, list) and self.securityMode != SecurityMode.UPDATE:
+ raise NotImplementedError(
+ "Authorization of inserts and updates is currently implemented only "
+ "for single paths, not for lists of paths."
+ )
+
to_be_inserted, to_be_updated = self._split_into_inserts_and_updates(
SyncGraph(crawled_data, self.identifiableAdapter))
@@ -1004,7 +1010,7 @@ def _store_dry_run_data(ins, upd):
"update": updates}))
-def crawler_main(crawled_directory_path: str,
+def crawler_main(crawled_directory_path: Union[str, list[str]],
cfood_file_name: str,
identifiables_definition_file: Optional[str] = None,
debug: bool = False,
@@ -1022,8 +1028,8 @@ def crawler_main(crawled_directory_path: str,
Parameters
----------
- crawled_directory_path : str
- path to be crawled
+ crawled_directory_path : str or list[str]
+ path(s) to be crawled
cfood_file_name : str
filename of the cfood to be used
identifiables_definition_file : str
@@ -1115,42 +1121,28 @@ def crawler_main(crawled_directory_path: str,
crawler.run_id)
_update_status_record(crawler.run_id, len(inserts), len(updates), status="OK")
return 0
- except ForbiddenTransaction as err:
- logger.debug(traceback.format_exc())
- logger.error(err)
- _update_status_record(crawler.run_id, 0, 0, status="FAILED")
- return 1
- except ConverterValidationError as err:
- logger.debug(traceback.format_exc())
- logger.error(err)
- _update_status_record(crawler.run_id, 0, 0, status="FAILED")
- return 1
- except ImpossibleMergeError as err:
- logger.debug(traceback.format_exc())
- logger.error(
- "Encountered conflicting information when creating Records from the crawled "
- f"data:\n\n{err}"
- )
- _update_status_record(crawler.run_id, 0, 0, status="FAILED")
- return 1
- except TransactionError as err:
- logger.debug(traceback.format_exc())
- logger.error(err)
- logger.error("Transaction error details:")
- for suberr in err.errors:
- logger.error("---")
- logger.error(suberr.msg)
- logger.error(suberr.entity)
- return 1
except Exception as err:
logger.debug(traceback.format_exc())
logger.error(err)
-
- if "SHARED_DIR" in os.environ:
- # pylint: disable=E0601
- domain = get_config_setting("public_host_url")
- logger.error("Unexpected Error: Please tell your administrator about this and provide "
- f"the following path.\n{get_shared_resource_link(domain, debuglog_public)}")
+ # Special treatment for known error types
+ if isinstance(err, ImpossibleMergeError):
+ logger.error(
+ "Encountered conflicting information when creating Records from the crawled "
+ f"data:\n\n{err}"
+ )
+ elif isinstance(err, TransactionError):
+ logger.error("Transaction error details:")
+ for suberr in err.errors:
+ logger.error("---")
+ logger.error(suberr.msg)
+ logger.error(suberr.entity)
+ # Unkown errors get a special message
+ elif not isinstance(err, (ConverterValidationError, ForbiddenTransaction)):
+ if "SHARED_DIR" in os.environ:
+ # pylint: disable=E0601
+ domain = get_config_setting("public_host_url")
+ logger.error("Unexpected Error: Please tell your administrator about this and provide "
+ f"the following path.\n{get_shared_resource_link(domain, debuglog_public)}")
_update_status_record(crawler.run_id, 0, 0, status="FAILED")
return 1
@@ -1174,6 +1166,7 @@ def parse_args():
"This file will only be generated if this option is set.")
parser.add_argument("--debug", required=False, action="store_true",
help="Path name of the cfood yaml file to be used.")
+ # TODO allow to provide multiple directories to be crawled on the commandline
parser.add_argument("crawled_directory_path",
help="The subtree of files below the given path will "
"be considered. Use '/' for everything.")
diff --git a/src/caoscrawler/scanner.py b/src/caoscrawler/scanner.py
index 89bd1c04411665bf4832d6bccce69bbe1b11cad1..af1f4173e95827606a02979ddd6d7fcd9f133271 100644
--- a/src/caoscrawler/scanner.py
+++ b/src/caoscrawler/scanner.py
@@ -421,7 +421,7 @@ def scanner(items: list[StructureElement],
# --------------------------------------------------------------------------------
-def scan_directory(dirname: str, crawler_definition_path: str,
+def scan_directory(dirname: Union[str, list[str]], crawler_definition_path: str,
restricted_path: Optional[list[str]] = None,
debug_tree: Optional[DebugTree] = None):
""" Crawl a single directory.
@@ -434,10 +434,12 @@ def scan_directory(dirname: str, crawler_definition_path: str,
Parameters
----------
+ dirname: str or list[str]
+ directory or list of directories to be scanned
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. See docstring of 'scanner' for
- more details.
+ Traverse the data tree only along the given path. When the end
+ of the given path is reached, traverse the full tree as
+ normal. See docstring of 'scanner' for more details.
Returns
-------
@@ -455,26 +457,31 @@ def scan_directory(dirname: str, crawler_definition_path: str,
if not dirname:
raise ValueError(
"You have to provide a non-empty path for crawling.")
- dir_structure_name = os.path.basename(dirname)
-
- # TODO: needs to be covered somewhere else
- crawled_directory = dirname
- if not dir_structure_name and dirname.endswith('/'):
- if dirname == '/':
- # Crawling the entire file system
- dir_structure_name = "root"
- else:
- # dirname had a trailing '/'
- dir_structure_name = os.path.basename(dirname[:-1])
-
- return scan_structure_elements(Directory(dir_structure_name,
- dirname),
- crawler_definition,
- converter_registry,
- restricted_path=restricted_path,
- debug_tree=debug_tree,
- registered_transformer_functions=registered_transformer_functions
- )
+ if not isinstance(dirname, list):
+ dirname = [dirname]
+ dir_element_list = []
+ for dname in dirname:
+ dir_structure_name = os.path.basename(dname)
+
+ # TODO: needs to be covered somewhere else
+ crawled_directory = dname
+ if not dir_structure_name and dname.endswith(os.path.sep):
+ if dname == os.path.sep:
+ # Crawling the entire file system
+ dir_structure_name = "root"
+ else:
+ # dirname had a trailing '/'
+ dir_structure_name = os.path.basename(dname[:-1])
+ dir_element_list.append(Directory(dir_structure_name, dname))
+
+ return scan_structure_elements(
+ dir_element_list,
+ crawler_definition,
+ converter_registry,
+ restricted_path=restricted_path,
+ debug_tree=debug_tree,
+ registered_transformer_functions=registered_transformer_functions
+ )
def scan_structure_elements(items: Union[list[StructureElement], StructureElement],