diff --git a/src/newcrawler.egg-info/PKG-INFO b/src/newcrawler.egg-info/PKG-INFO
new file mode 100644
index 0000000000000000000000000000000000000000..4c6e7241e76b3c419a59d21f9a43666dd76a1fab
--- /dev/null
+++ b/src/newcrawler.egg-info/PKG-INFO
@@ -0,0 +1,61 @@
+Metadata-Version: 2.1
+Name: newcrawler
+Version: 0.1
+Summary: A new crawler for caosdb
+Home-page: UNKNOWN
+Author: Alexander Schlemmer
+Author-email: alexander.schlemmer@ds.mpg.de
+License: UNKNOWN
+Platform: UNKNOWN
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: AGPLv3
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+# newcrawler
+
+A new crawler for CaosDB.
+
+
+This package has yaml-header-tools as a dependency:
+https://gitlab.com/salexan/yaml-header-tools
+
+
+
+This python package can be installed using `pip`, e.g.:
+```bash
+pip install --user .
+```
+
+# Usage
+
+work in progress
+
+# Running the tests
+
+After installation of the package run (within the project folder):
+
+```bash
+pytest
+```
+
+
+# Contributers
+
+The original authors of this package are:
+
+- Alexander Schlemmer
+- Henrik tom Wörden
+- Florian Spreckelsen
+
+# License
+
+Copyright (C) 2021 Research Group Biomedical Physics, Max Planck Institute for
+Dynamics and Self-Organization Göttingen.
+
+All files in this repository are licensed under a [GNU Affero General Public
+License](LICENCE) (version 3 or later).
+
+
diff --git a/src/newcrawler.egg-info/SOURCES.txt b/src/newcrawler.egg-info/SOURCES.txt
new file mode 100644
index 0000000000000000000000000000000000000000..4b7fb6aba468a63d558145b360bb2eb50e239bfd
--- /dev/null
+++ b/src/newcrawler.egg-info/SOURCES.txt
@@ -0,0 +1,11 @@
+LICENSE
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+src/newcrawler/__init__.py
+src/newcrawler/crawl.py
+src/newcrawler.egg-info/PKG-INFO
+src/newcrawler.egg-info/SOURCES.txt
+src/newcrawler.egg-info/dependency_links.txt
+src/newcrawler.egg-info/top_level.txt
\ No newline at end of file
diff --git a/src/newcrawler.egg-info/dependency_links.txt b/src/newcrawler.egg-info/dependency_links.txt
new file mode 100644
index 0000000000000000000000000000000000000000..8b137891791fe96927ad78e64b0aad7bded08bdc
--- /dev/null
+++ b/src/newcrawler.egg-info/dependency_links.txt
@@ -0,0 +1 @@
+
diff --git a/src/newcrawler.egg-info/top_level.txt b/src/newcrawler.egg-info/top_level.txt
new file mode 100644
index 0000000000000000000000000000000000000000..db6194c54d7e8b2645c547662714ef69d22c9afa
--- /dev/null
+++ b/src/newcrawler.egg-info/top_level.txt
@@ -0,0 +1 @@
+newcrawler
diff --git a/src/newcrawler/crawl.py b/src/newcrawler/crawl.py
index f441a1a0dea6cfa1ba8134e1d2a3cd6272078503..5c02ed922d6d404d6a9794d7f53ddc45819d11a0 100755
--- a/src/newcrawler/crawl.py
+++ b/src/newcrawler/crawl.py
@@ -99,6 +99,25 @@ def get_subnode_with_defaults(node: dict,
return subnode
+def match_complete(node: dict):
+ """Determine whether the match is complete.
+
+ This function checks whether all nodes and subnodes have a value.
+
+ Parameters
+ ----------
+ node : The node to check.
+
+ Returns
+ -------
+ True if the match is complete and False otherwise.
+ """
+ if "value" not in node:
+ return False
+ if "children" in node:
+ return all([match_complete(element) for element in node["children"]])
+ return True
+
def crawl_cfood(dirname: str,
cfood: str):
"""
@@ -115,25 +134,25 @@ def crawl_cfood(dirname: str,
if len(root_node) != 1:
raise ValueError("Only a single cfood root is allowed.")
current_node = get_subnode_with_defaults(root_node, list(root_node.keys())[0])
+ current_dir = dirname
# Strategy: keep a list of currently matching candidates...
- for currentpath, dirs, files in os.walk(dirname):
- # for current nodes of type dir look in the list of dirs for matches
- # dir is the default
- if current_node["type"] == "dir":
- for dirname in dirs:
- match = match_file_object(current_node, dirname)
- if match is not None:
- print(json.dumps(match, indent=2))
- elif current_node["type"] == "file":
- for filename in files:
- match = match_file_object(current_node, dirname)
- if match is not None:
- print(match)
- else:
- # work in progress
- pass
+ matches = []
+ for element in os.listdir(current_dir):
+ path = os.path.join(dirname, element)
+
+
+ if current_node["type"] == "dir" and os.path.isdir(path):
+ match = match_file_object(current_node, dirname)
+ if match is not None:
+ matches.append((path, match))
+ elif current_node["tpye"] == "file" and not os.path.isdir(path):
+ match = match_file_object(current_node, dirname)
+ if match is not None:
+ matches.append((path, match))
+
+
def crawl(dirname: str,
diff --git a/tests/test_functions.py b/tests/test_functions.py
new file mode 100644
index 0000000000000000000000000000000000000000..a33f0d2182474e960fa42c2343db533c3d21d41f
--- /dev/null
+++ b/tests/test_functions.py
@@ -0,0 +1,34 @@
+#!/bin/python
+# Tests for main functions of crawler
+# A. Schlemmer, 07/2021
+
+from newcrawler import match_complete
+
+def test_match_complete():
+ node = {"name": "bla"}
+ assert match_complete(node) == False
+
+ node = {"name": "bla",
+ "children": [{
+ "name": "test",
+ "value": 234}, {
+ "name": "test",
+ "value": 234}]}
+ assert match_complete(node) == False
+
+ node = {"name": "bla",
+ "value": "ok",
+ "children": [{
+ "name": "test",
+ "value": 234}, {
+ "name": "test",
+ "value": 234}]}
+ assert match_complete(node) == True
+
+ node = {"name": "bla",
+ "value": "ok",
+ "children": [{
+ "name": "test"}, {
+ "name": "test",
+ "value": 234}]}
+ assert match_complete(node) == False
diff --git a/tests/test_tool.py b/tests/test_tool.py
index 28add00bedb342e6625b7d3fd426682eadc87151..3ba782c3b651dea57c84e9531a48f32a076074ad 100755
--- a/tests/test_tool.py
+++ b/tests/test_tool.py
@@ -7,8 +7,6 @@ from newcrawler import crawl
from os.path import join, dirname
def test_examples_article():
- m = crawl(join(dirname(__file__), "test_directories/examples_article"))
- assert len(m) == 14
-
- for r in m:
- assert len(r[2]) == 0
+ m = crawl(join(dirname(__file__), "test_directories/examples_article"),
+ [join(dirname(__file__), "scifolder_cfood.yml")])
+ assert True