From 9029b5304bdd14acbca715c14f5c878e25f7aa0c Mon Sep 17 00:00:00 2001
From: Daniel Hornung <d.hornung@indiscale.com>
Date: Mon, 31 May 2021 16:42:29 +0200
Subject: [PATCH] DOC: Updated documentation a bit.
---
README_SETUP.md | 2 +-
integrationtests/crawl.py | 2 +-
.../extroot/{.cerate_dir => .create_dir} | 0
src/doc/crawler.rst | 14 +++++++++-----
4 files changed, 11 insertions(+), 7 deletions(-)
rename integrationtests/extroot/{.cerate_dir => .create_dir} (100%)
diff --git a/README_SETUP.md b/README_SETUP.md
index 9b7b27ec..19f05163 100644
--- a/README_SETUP.md
+++ b/README_SETUP.md
@@ -34,7 +34,7 @@ For testing:
3. Start an empty (!) CaosDB instance (with the mounted extroot). The
database will be cleared during testing, so it's important to use
an empty instance.
-4. Run `test.sh`.
+4. Run `test.sh`. Note that this may modify content of the `integrationtest/extroot/` directory.
## Code Formatting
`autopep8 -i -r ./`
diff --git a/integrationtests/crawl.py b/integrationtests/crawl.py
index bf72b5f7..65600016 100755
--- a/integrationtests/crawl.py
+++ b/integrationtests/crawl.py
@@ -43,7 +43,7 @@ except ModuleNotFoundError:
return argparse.ArgumentParser()
def print_success(text):
- print("Success: "+text)
+ print("Success: " + text)
def get_parser():
diff --git a/integrationtests/extroot/.cerate_dir b/integrationtests/extroot/.create_dir
similarity index 100%
rename from integrationtests/extroot/.cerate_dir
rename to integrationtests/extroot/.create_dir
diff --git a/src/doc/crawler.rst b/src/doc/crawler.rst
index 7c95dad9..391c5458 100644
--- a/src/doc/crawler.rst
+++ b/src/doc/crawler.rst
@@ -75,7 +75,7 @@ The crawler can be executed directly via a python script (usually called
``crawl.py``). The script prints the progress and reports potential
problems. The exact behavior depends on your setup. However, you can
have a look at the example in the
-`tests <https://gitlab.com/caosdb/caosdb-advanced-user-tools/-/blob/main/integrationtests/full_test/crawl.py>`__.
+`tests <https://gitlab.indiscale.com/caosdb/src/caosdb-advanced-user-tools/-/blob/main/integrationtests/crawl.py>`__.
.. Note:: The crawler depends on the CaosDB Python client, so make sure to install :doc:`pycaosdb
<caosdb-pylib:getting_started>`.
@@ -86,14 +86,18 @@ Typically, an invocation looks like:
.. code:: python
- python3 crawl.py "/TestData/"
+ python3 crawl.py /someplace/
-In this case ``/TestData/`` identifies the path to be crawled **within
-the CaosDB file system**. You can browse the CaosDB file system by
+.. Note:: For trying this out with the above mentioned example crawler from the integration tests,
+ make sure that the ``extroot`` directory in the ``integrationtests`` folder is used as
+ CaosDB's extroot directory,and call the crawler with ``python3 crawl.py /``.
+
+In this case ``/someplace/`` identifies the path to be crawled **within
+CaosDB's file system**. You can browse the CaosDB file system by
opening the WebUI of your CaosDB instance and clicking on “File Systemâ€.
In the backend, ``crawl.py`` starts a CQL query
-``FIND File WHICH IS STORED AT /TestData/**`` and crawls the resulting
+``FIND File WHICH IS STORED AT /someplace/**`` and crawls the resulting
files according to your customized ``CFoods``.
Crawling may consist of two distinct steps: 1. Insertion of files (use
--
GitLab