From 0a20600533ef845a25404bc249c56555c16b1d2b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Henrik=20tom=20W=C3=B6rden?= <h.tomwoerden@indiscale.com>
Date: Thu, 2 Feb 2023 10:23:14 +0100
Subject: [PATCH] DOC: enhance docstrings
---
src/caoscrawler/crawl.py | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index 3d844ad5..0273acef 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -427,7 +427,9 @@ class Crawler(object):
Convenience function that starts the crawler (calls start_crawling)
with a single directory as the StructureElement.
- restricted_path: see start_crawling
+ restricted_path: optional, list of string
+ Traverse the data tree only along the given path. When the end of the given path
+ is reached, traverse the full tree as normal.
"""
crawler_definition = self.load_definition(crawler_definition_path)
@@ -1193,9 +1195,12 @@ ____________________\n""".format(i + 1, len(pending_changes)) + str(el[3]))
generalStore and recordStore: This recursion of the crawl function should only operate on
copies of the global stores of the Crawler object.
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; The given path contains only the untreated levels, i.e. the first
- element is considered at this level.
+ path. For example, when a directory contains files a, b and c and b is
+ given in restricted_path, a and c will be ignroed by the crawler.
+ When the end of the given path is reached, traverse the full tree as
+ normal. The first element of the list provided by restricted_path should
+ be the name of the StructureElement at this level, i.e. denoting the
+ respective element in the items argument.
"""
# This path_found variable stores wether the path given by restricted_path was found in the
# data tree
@@ -1312,8 +1317,9 @@ def crawler_main(crawled_directory_path: str,
securityMode of Crawler
unique_names : bool
whether or not to update or insert entities inspite of name conflicts
- restricted_path : optional, list of str
- see start_crawling
+ restricted_path: optional, list of string
+ Traverse the data tree only along the given path. When the end of the given path
+ is reached, traverse the full tree as normal.
Returns
-------
--
GitLab