diff --git a/CHANGELOG.md b/CHANGELOG.md
index 240e1aff64dc555c0316606dce19589fea02a863..352311d0910bcf0c7f60183b6f58dd7ffdcb0ed4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Documentation ###
+## [0.7.1] - 2024-03-21 ##
+
+### Fixed ###
+
+* `crawler_main` doesn't need the deprecated `debug=True` anymore to put out a
+ provenance file if the `provenance_file` parameter is provided.
+* [indiscale#129](https://gitlab.indiscale.com/caosdb/src/caosdb-crawler/-/issues/129)
+ missing packaging dependency.
+
## [0.7.0] - 2024-03-04 ##
### Added ###
diff --git a/CITATION.cff b/CITATION.cff
index de05ce11bc6667e508e3504629ba517a90642aef..abbd6b21e19c5a989c6d6d24f32d3946df070308 100644
--- a/CITATION.cff
+++ b/CITATION.cff
@@ -17,6 +17,6 @@ authors:
given-names: Alexander
orcid: https://orcid.org/0000-0003-4124-9649
title: CaosDB - Crawler
-version: 0.7.0
+version: 0.7.1
doi: 10.3390/data9020024
-date-released: 2023-03-04
\ No newline at end of file
+date-released: 2023-03-21
\ No newline at end of file
diff --git a/setup.cfg b/setup.cfg
index 1e8abb8eeee2ba4b861a71880c96d943f813c812..88898530f7b7e049e84b230bdcbd45ff5170fabf 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -1,6 +1,6 @@
[metadata]
name = caoscrawler
-version = 0.7.1
+version = 0.7.2
author = Alexander Schlemmer
author_email = alexander.schlemmer@ds.mpg.de
description = A new crawler for caosdb
@@ -19,14 +19,15 @@ package_dir =
packages = find:
python_requires = >=3.7
install_requires =
- importlib-resources
caosadvancedtools >= 0.7.0
+ importlib-resources
+ importlib_metadata;python_version<'3.8'
linkahead > 0.13.2
- yaml-header-tools >= 0.2.1
- pyyaml
odfpy #make optional
+ packaging
pandas
- importlib_metadata;python_version<'3.8'
+ pyyaml
+ yaml-header-tools >= 0.2.1
[options.packages.find]
where = src
diff --git a/src/caoscrawler/converters.py b/src/caoscrawler/converters.py
index 772f690b2ce7f8a3822d0d833f13c84cdd9d5e35..e0ca0f9bff77ba1ecc63f4d102d6d9869fb11cb0 100644
--- a/src/caoscrawler/converters.py
+++ b/src/caoscrawler/converters.py
@@ -389,8 +389,8 @@ class Converter(object, metaclass=ABCMeta):
Extract information from the structure element and store them as values in the
general store.
- Parameters:
- ------------
+ Parameters
+ ----------
values: GeneralStore
The GeneralStore to store values in.
@@ -409,8 +409,8 @@ class Converter(object, metaclass=ABCMeta):
Check if transformers are defined using the "transform" keyword.
Then apply the transformers to the variables defined in GeneralStore "values".
- Parameters:
- ------------
+ Parameters
+ ----------
values: GeneralStore
The GeneralStore to store values in.
@@ -765,6 +765,12 @@ schema_resource:
class DictElementConverter(Converter):
+ """
+**Operates on:** :py:class:`caoscrawler.structure_elements.DictElement`
+
+**Generates:** :py:class:`caoscrawler.structure_elements.StructureElement`
+ """
+
def create_children(self, generalStore: GeneralStore, element: StructureElement):
# TODO: See comment on types and inheritance
if not isinstance(element, DictElement):
@@ -1154,6 +1160,12 @@ class TableConverter(Converter):
class XLSXTableConverter(TableConverter):
+ """
+**Operates on:** :py:class:`caoscrawler.structure_elements.File`
+
+**Generates:** :py:class:`caoscrawler.structure_elements.DictElement`
+ """
+
def get_options(self):
return self._get_options([
("sheet_name", str),
diff --git a/src/caoscrawler/crawl.py b/src/caoscrawler/crawl.py
index ffd0185604f243e119f3efd136488612276a9c05..d21e6e2521578dc407e445d8220506677be84e26 100644
--- a/src/caoscrawler/crawl.py
+++ b/src/caoscrawler/crawl.py
@@ -1504,7 +1504,7 @@ def crawler_main(crawled_directory_path: str,
dry_run: bool = False,
prefix: str = "",
securityMode: SecurityMode = SecurityMode.UPDATE,
- unique_names=True,
+ unique_names: bool = True,
restricted_path: Optional[list[str]] = None,
remove_prefix: Optional[str] = None,
add_prefix: Optional[str] = None,
@@ -1520,9 +1520,9 @@ def crawler_main(crawled_directory_path: str,
identifiables_definition_file : str
filename of an identifiable definition yaml file
debug : bool
- DEPRECATED, whether or not to run in debug mode
+ DEPRECATED, use a provenance file instead.
provenance_file : str
- provenance information will be stored in a file with given filename
+ Provenance information will be stored in a file with given filename
dry_run : bool
do not commit any chnages to the server
prefix : str
@@ -1562,7 +1562,7 @@ def crawler_main(crawled_directory_path: str,
_fix_file_paths(crawled_data, add_prefix, remove_prefix)
_check_record_types(crawled_data)
- if provenance_file is not None and debug:
+ if provenance_file is not None:
crawler.save_debug_data(debug_tree=debug_tree, filename=provenance_file)
if identifiables_definition_file is not None:
diff --git a/src/caoscrawler/identifiable_adapters.py b/src/caoscrawler/identifiable_adapters.py
index 9be539fe0842e3ce24b68060fa2288cdc4c531b2..3a9b8819b2f16ae7b6b2dc4ff06d94055da14d60 100644
--- a/src/caoscrawler/identifiable_adapters.py
+++ b/src/caoscrawler/identifiable_adapters.py
@@ -90,7 +90,7 @@ Some terms:
- ``is_referenced_by`` statements
- An *identifiable* belongs to a concrete record. It consists of identifying attributes which "fill
in" the *registered identifiable*. In code, it can be represented as a Record based on the
- *registered identifiable* with all the values filled in.
+ *registered identifiable* with all the values filled in.
- An *identified record* is the result of retrieving a record from the database, based on the
*identifiable* (and its values).
diff --git a/src/caoscrawler/scanner.py b/src/caoscrawler/scanner.py
index 5d92401a50d3e4aa9cc258e792be41df18ef3976..9d1f538732858ff2fbf949d45c359ebb16fe3480 100644
--- a/src/caoscrawler/scanner.py
+++ b/src/caoscrawler/scanner.py
@@ -25,7 +25,9 @@
#
"""
-This is the scanner, the original "_crawl" function from crawl.py.
+This is the scanner.
+
+This was where formerly the ``_crawl(...)`` function from ``crawl.py`` was located.
This is just the functionality that extracts data from the file system.
"""
@@ -257,31 +259,31 @@ def scanner(items: list[StructureElement],
restricted_path: Optional[list[str]] = None,
crawled_data: Optional[list[db.Record]] = None,
debug_tree: Optional[DebugTree] = None,
- registered_transformer_functions: Optional[dict] = None):
+ registered_transformer_functions: Optional[dict] = None) -> list[db.Record]:
"""Crawl a list of StructureElements and apply any matching converters.
- Formerly known as "_crawl".
+ Formerly known as ``_crawl(...)``.
Parameters
----------
- items:
+ items: list[StructureElement]
structure_elements (e.g. files and folders on one level on the hierarchy)
- converters:
+ converters: list[Converter]
locally defined converters for treating structure elements. A locally
defined converter could be one that is only valid for a specific subtree
of the originally cralwed StructureElement structure.
- general_store, record_store:
+ general_store, record_store: GeneralStore, RecordStore, optional
This recursion of the crawl function should only operate on copies of
the global stores of the Crawler object.
- restricted_path : list of strings, optional
+ restricted_path : list[str], optional
traverse the data tree only along the given path. For example, when a
- directory contains files a, b and c and b is given as restricted_path, a
- and c will be ignroed by the crawler. When the end of the given path is
+ directory contains files a, b and c, and b is given as ``restricted_path``, a
+ and c will be ignored 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
+ provided by ``restricted_path`` should be the name of the StructureElement
at this level, i.e. denoting the respective element in the items
argument.
@@ -292,7 +294,8 @@ def scanner(items: list[StructureElement],
Each function is a dictionary:
- - The key is the name of the function to be looked up in the dictionary of registered transformer functions.
+ - The key is the name of the function to be looked up in the dictionary of registered
+ transformer functions.
- The value is the function which needs to be of the form:
def func(in_value: Any, in_parameters: dict) -> Any:
pass
@@ -457,7 +460,8 @@ def scan_structure_elements(items: Union[list[StructureElement], StructureElemen
converter_registry: dict,
restricted_path: Optional[list[str]] = None,
debug_tree: Optional[DebugTree] = None,
- registered_transformer_functions: Optional[dict] = None):
+ registered_transformer_functions: Optional[dict] = None) -> (
+ list[db.Record]):
"""
Start point of the crawler recursion.
@@ -471,14 +475,14 @@ def scan_structure_elements(items: Union[list[StructureElement], StructureElemen
crawler_definition : dict
A dictionary representing the crawler definition, possibly from a yaml
file.
- restricted_path: optional, list of strings
+ restricted_path: list[str], optional
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' formore details.
+ of 'scanner' for more details.
Returns
-------
- crawled_data : list
+ crawled_data : list[db.Record]
the final list with the target state of Records.
"""
diff --git a/src/caoscrawler/structure_elements.py b/src/caoscrawler/structure_elements.py
index 952f29d012f8373062ed9dfe8a830bd18c4b0baa..ff070626ebfdd580c16bbbf2dc30ab330dc162f0 100644
--- a/src/caoscrawler/structure_elements.py
+++ b/src/caoscrawler/structure_elements.py
@@ -28,9 +28,16 @@ import warnings
class StructureElement(object):
- """ base class for elements in the hierarchical data structure """
+ """Base class for elements in the hierarchical data structure.
- def __init__(self, name):
+Parameters
+----------
+
+name: str
+ The name of the StructureElement. May be used for pattern matching by CFood rules.
+ """
+
+ def __init__(self, name: str):
# Used to store usage information for debugging:
self.metadata: tDict[str, set[str]] = {
"usage": set()
@@ -46,6 +53,18 @@ class StructureElement(object):
class FileSystemStructureElement(StructureElement):
+ """StructureElement representing an element of a file system, like a directory or a simple file.
+
+Parameters
+----------
+
+name: str
+ The name of the StructureElement. May be used for pattern matching by CFood rules.
+
+path: str
+ The path to the file or directory.
+ """
+
def __init__(self, name: str, path: str):
super().__init__(name)
self.path = path
@@ -65,6 +84,7 @@ class Directory(FileSystemStructureElement):
class File(FileSystemStructureElement):
+ """StrutureElement representing a file."""
pass
diff --git a/src/doc/concepts.rst b/src/doc/concepts.rst
index 32176b9edb895074021b3ed4eabe270ad48ae632..7100bcd1790edb3e040a1a90663a32a09b7c8eaf 100644
--- a/src/doc/concepts.rst
+++ b/src/doc/concepts.rst
@@ -1,18 +1,17 @@
Concepts
-))))))))
+========
-The CaosDB Crawler can handle any kind of hierarchical data structure. The typical use case is
+The CaosDB Crawler can handle any kind of hierarchical data structure. The typical use case is a
directory tree that is traversed. We use the following terms/concepts to describe how the CaosDB
Crawler works.
Structure Elements
++++++++++++++++++
-This hierarchical structure is assumed to be consituted of a tree of
-StructureElements. The tree is created on the fly by so called Converters which
-are defined in a yaml file. The tree of StructureElements is a model
-of the existing data (For example could a tree of Python file objects
-(StructureElements) represent a file tree that exists on some file server).
+The crawled hierarchical structure is represented by a tree of *StructureElements*. This tree is
+generated on the fly by so called Converters which are defined in a yaml file (usually called
+``cfood.yml``). This generated tree of StructureElements is a model of the existing data. For
+example a tree of Python *file objects* (StructureElements) could correspond to a file system tree.
Relevant sources in:
@@ -23,29 +22,28 @@ Relevant sources in:
Converters
++++++++++
-Converters treat StructureElements and thereby create the StructureElement that
-are the children of the treated StructureElement. Converters therefore create
-the above named tree. The definition of a Converter also contains what
-Converters shall be used to treat the generated child-StructureElements. The
-definition is therefore a tree itself.
-
-See :std:doc:`converters<converters>` for details.
+Converters treat a StructureElement and during this process create a number of new
+StructureElements: the children of the initially treated StructureElement. Thus by treatment of
+existing StructureElements, Converters create a tree of StructureElements.
+.. image:: img/converter.png
+ :height: 170
+See :std:doc:`converters<converters>` for details.
Relevant sources in:
-- ``src/converters.py``
+- ``src/converters.py``
Identifiables
+++++++++++++
-An Identifiable of a Record is like the fingerprint of a Record.
+An *Identifiable* of a Record is like the fingerprint of a Record.
-The identifiable contains the information that is used by the CaosDB Crawler to identify Records.
-For example, in order to check whether a Record exits in the CaosDB Server, the CaosDB Crawler creates a query
-using the information contained in the Identifiable.
+The Identifiable contains the information that is used by the CaosDB Crawler to identify Records.
+For example, the CaosDB Crawler may create a query using the information contained in the
+Identifiable in order to check whether a Record exists in the CaosDB Server.
Suppose a certain experiment is at most done once per day, then the identifiable could
consist of the RecordType "SomeExperiment" (as a parent) and the Property "date" with the respective value.
@@ -100,7 +98,9 @@ The Crawler
+++++++++++
The crawler can be considered the main program doing the synchronization in basically two steps:
+
#. Based on a yaml-specification scan the file system (or other sources) and create a set of CaosDB Entities that are supposed to be inserted or updated in a CaosDB instance.
+
#. Compare the current state of the CaosDB instance with the set of CaosDB Entities created in step 1, taking into account the :ref:`registered identifiables<Identifiables>`. Insert or update entites accordingly.
Relevant sources in:
diff --git a/src/doc/conf.py b/src/doc/conf.py
index ac5fc7f5d95c2399f4402121ba9445bc0dbc6aaa..3cce99d03728d229c848ba6374d15de9fe73ec7b 100644
--- a/src/doc/conf.py
+++ b/src/doc/conf.py
@@ -33,10 +33,10 @@ copyright = '2024, IndiScale'
author = 'Alexander Schlemmer'
# The short X.Y version
-version = '0.7.1'
+version = '0.7.2'
# The full version, including alpha/beta/rc tags
# release = '0.5.2-rc2'
-release = '0.7.1-dev'
+release = '0.7.2-dev'
# -- General configuration ---------------------------------------------------
diff --git a/src/doc/converters.rst b/src/doc/converters.rst
index 44988fbd497cdb57023b5a696f83d55e7eb5113a..9b28c9a61eec4d9707b9640720b9c6a44a8fe25e 100644
--- a/src/doc/converters.rst
+++ b/src/doc/converters.rst
@@ -1,18 +1,23 @@
Converters
))))))))))
-Converters treat StructureElements and thereby create the StructureElement that
-are the children of the treated StructureElement. Converters therefore create
-the tree of structure elements. The definition of a Converter also contains what
-Converters shall be used to treat the generated child-StructureElements. The
-definition is therefore a tree itself.
-
-Each StructureElement in the tree has a set of data values, i.e a dictionary of
-key value pairs.
-Some of those values are set due to the kind of StructureElement. For example,
-a file could have the file name as such a key value pair: 'filename': <sth>.
+Converters treat a StructureElement and during this process create a number of new
+StructureElements: the children of the initially treated StructureElement. Thus by treatment of
+existing StructureElements, Converters create a tree of StructureElements.
+
+.. image:: img/converter.png
+ :height: 170
+
+The ``cfood.yml`` definition also describes which
+Converters shall be used to treat the generated child StructureElements. The
+definition therefore itself also defines a tree.
+
+Each StructureElement in the tree has a set of properties, organized as
+key-value pairs.
+Some of those properties are specified by the type of StructureElement. For example,
+a file could have the file name as property: ``'filename': myfile.dat``.
Converters may define additional functions that create further values. For
-example, a regular expresion could be used to get a date from a file name.
+example, a regular expression could be used to get a date from a file name.
A converter is defined via a yml file or part of it. The definition states
@@ -20,7 +25,7 @@ what kind of StructureElement it treats (typically one).
Also, it defines how children of the current StructureElement are
created and what Converters shall be used to treat those.
-The yaml definition looks like the following:
+The yaml definition may look like this:
TODO: outdated, see cfood-schema.yml
@@ -53,8 +58,9 @@ to generate records (see :py:meth:`~caoscrawler.converters.Converter.create_reco
**records** is a dict of definitions that define the semantic structure
(see details below).
-Subtree contains a list of Converter defnitions that look like the one
-described here.
+**subtree** makes the yaml recursive: It contains a list of new Converter
+definitions, which work on the StructureElements that are returned by the
+current Converter.
Transform Functions
+++++++++++++++++++
@@ -108,6 +114,9 @@ them to the cfood definition (see :doc:`CFood Documentation<cfood>`).
Standard Converters
+++++++++++++++++++
+These are the standard converters that exist in a default installation. For writing and applying
+*custom converters*, see :ref:`below <Custom Converters>`.
+
Directory Converter
===================
The Directory Converter creates StructureElements for each File and Directory
@@ -126,11 +135,14 @@ children elements according to the structure of the header.
DictElement Converter
=====================
+
+DictElement → StructureElement
+
Creates a child StructureElement for each key in the dictionary.
Typical Subtree converters
--------------------------
-The following StructureElement are typically created:
+The following StructureElement types are typically created by the DictElement converter:
- BooleanElement
- FloatElement
@@ -155,12 +167,12 @@ behavior can be adjusted with the fields `accept_text`, `accept_int`,
The following denotes what kind of StructureElements are accepted by default
(they are defined in `src/caoscrawler/converters.py`):
-- DictBooleanElementConverter: bool, int
-- DictFloatElementConverter: int, float
-- DictTextElementConverter: text, bool, int, float
-- DictIntegerElementConverter: int
-- DictListElementConverter: list
-- DictDictElementConverter: dict
+- BooleanElementConverter: bool, int
+- FloatElementConverter: int, float
+- TextElementConverter: text, bool, int, float
+- IntegerElementConverter: int
+- ListElementConverter: list
+- DictElementConverter: dict
YAMLFileConverter
=================
@@ -180,11 +192,13 @@ JSONFileConverter
TableConverter
==============
+Table → DictElement
+
A generic converter (abstract) for files containing tables.
-Currently, there are two specialized implementations for xlsx-files and csv-files.
+Currently, there are two specialized implementations for XLSX files and CSV files.
-All table converters generate a subtree that can be converted with DictDictElementConverters:
-For each row in the table a DictDictElement (structure element) is generated. The key of the
+All table converters generate a subtree of dicts, which in turn can be converted with DictElementConverters:
+For each row in the table the TableConverter generates a DictElement (structure element). The key of the
element is the row number. The value of the element is a dict containing the mapping of
column names to values of the respective cell.
@@ -193,21 +207,21 @@ Example:
.. code-block:: yaml
subtree:
- TABLE:
+ TABLE: # Any name for the table as a whole
type: CSVTableConverter
match: ^test_table.csv$
records:
(...) # Records edited for the whole table file
subtree:
- ROW:
- type: DictDictElement
+ ROW: # Any name for a data row in the table
+ type: DictElement
match_name: .*
match_value: .*
records:
(...) # Records edited for each row
subtree:
- COLUMN:
- type: DictFloatElement
+ COLUMN: # Any name for a specific type of column in the table
+ type: FloatElement
match_name: measurement # Name of the column in the table file
match_value: (?P<column_value).*)
records:
@@ -217,9 +231,13 @@ Example:
XLSXTableConverter
==================
+XLSX File → DictElement
+
CSVTableConverter
=================
+CSV File → DictElement
+
Further converters
++++++++++++++++++
@@ -322,11 +340,15 @@ file in a text property, the name of which can be configured with the
Custom Converters
+++++++++++++++++
-It was previously mentioned that it is possible to create custom converters.
+As mentioned before it is possible to create custom converters.
These custom converters can be used to integrate arbitrary data extraction and ETL capabilities
-into the caosdb-crawler and make these extensions available to any yaml specification.
+into the LinkAhead crawler and make these extensions available to any yaml specification.
+
+Tell the crawler about a custom converter
+=========================================
-The basic syntax for adding a custom converter to a yaml cfood definition file is:
+To use a custom crawler, it must be defined in the ``Converters`` section of the CFood yaml file.
+The basic syntax for adding a custom converter to a definition file is:
.. code-block:: yaml
@@ -335,7 +357,7 @@ The basic syntax for adding a custom converter to a yaml cfood definition file i
package: <python>.<module>.<name>
converter: <PythonClassName>
-The Converters-section can be either put into the first or second document of the cfood yaml file.
+The Converters section can be either put into the first or the second document of the cfood yaml file.
It can be also part of a single-document yaml cfood file. Please refer to :doc:`the cfood documentation<cfood>` for more details.
Details:
@@ -344,9 +366,16 @@ Details:
- **<python>.<module>.<name>**: The name of the module where the converter class resides.
- **<PythonClassName>**: Within this specified module there must be a class inheriting from base class :py:class:`caoscrawler.converters.Converter`.
+Implementing a custom converter
+===============================
+
+Converters inherit from the :py:class:`~caoscrawler.converters.Converter` class.
+
The following methods are abstract and need to be overwritten by your custom converter to make it work:
-- :py:meth:`~caoscrawler.converters.Converter.create_children`
+:py:meth:`~caoscrawler.converters.Converter.create_children`:
+ Return a list of child StructureElement objects.
+
- :py:meth:`~caoscrawler.converters.Converter.match`
- :py:meth:`~caoscrawler.converters.Converter.typecheck`
diff --git a/src/doc/getting_started/furtherreading.rst b/src/doc/getting_started/furtherreading.rst
new file mode 100644
index 0000000000000000000000000000000000000000..eb600416c1fce3857d28fc2e856ceabebb3a8bb7
--- /dev/null
+++ b/src/doc/getting_started/furtherreading.rst
@@ -0,0 +1,8 @@
+Further reading
+===============
+
+- A simple `documented example <https://gitlab.com/caosdb/documented-crawler-example>`_ which
+ demonstrates the crawler usage.
+- Some useful examples can be found in the `integration tests
+ <https://gitlab.com/caosdb/caosdb-crawler/-/tree/main/integrationtests>`_ (and to a certain extent
+ in the unit tests).
diff --git a/src/doc/getting_started/index.rst b/src/doc/getting_started/index.rst
index 490c705f2feb9eeedc399e8c1d91e28abcd7fd12..86b34d069391b146d15599228067df2e9e41d642 100644
--- a/src/doc/getting_started/index.rst
+++ b/src/doc/getting_started/index.rst
@@ -10,6 +10,7 @@ Getting Started
prerequisites
helloworld
optionalfeatures
+ furtherreading
This section will help you get going! From the first installation steps to the first simple crawl.
diff --git a/src/doc/img/converter.png b/src/doc/img/converter.png
new file mode 100644
index 0000000000000000000000000000000000000000..c11517a32ceb164510a7731ff0516d19db71801a
Binary files /dev/null and b/src/doc/img/converter.png differ
diff --git a/src/doc/img/converter.svg b/src/doc/img/converter.svg
new file mode 100644
index 0000000000000000000000000000000000000000..af32ff69cdd6c25805f929458556310b3ee34f41
--- /dev/null
+++ b/src/doc/img/converter.svg
@@ -0,0 +1,442 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+ xmlns:dc="http://purl.org/dc/elements/1.1/"
+ xmlns:cc="http://creativecommons.org/ns#"
+ xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+ xmlns:svg="http://www.w3.org/2000/svg"
+ xmlns="http://www.w3.org/2000/svg"
+ xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+ xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+ width="72.854424mm"
+ height="33.470383mm"
+ viewBox="0 0 72.854423 33.470383"
+ version="1.1"
+ id="svg13434"
+ inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
+ sodipodi:docname="converter.svg"
+ inkscape:export-filename="/home/daniel/indiscale/software/linkahead/caosdb-crawler/src/doc/img/converter.png"
+ inkscape:export-xdpi="299.83078"
+ inkscape:export-ydpi="299.83078">
+ <defs
+ id="defs13428">
+ <marker
+ style="overflow:visible;"
+ id="marker1559"
+ refX="0.0"
+ refY="0.0"
+ orient="auto"
+ inkscape:stockid="Arrow2Mend"
+ inkscape:isstock="true">
+ <path
+ transform="scale(0.6) rotate(180) translate(0,0)"
+ d="M 8.7185878,4.0337352 L -2.2072895,0.016013256 L 8.7185884,-4.0017078 C 6.9730900,-1.6296469 6.9831476,1.6157441 8.7185878,4.0337352 z "
+ style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round;stroke:#000000;stroke-opacity:1;fill:#000000;fill-opacity:1"
+ id="path1557" />
+ </marker>
+ <marker
+ style="overflow:visible"
+ id="marker1266"
+ refX="0"
+ refY="0"
+ orient="auto"
+ inkscape:stockid="Arrow2Mend"
+ inkscape:isstock="true">
+ <path
+ transform="scale(-0.6)"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0.625;stroke-linejoin:round;stroke-opacity:1"
+ id="path1264" />
+ </marker>
+ <marker
+ style="overflow:visible"
+ id="marker1218"
+ refX="0"
+ refY="0"
+ orient="auto"
+ inkscape:stockid="Arrow2Mend"
+ inkscape:isstock="true"
+ inkscape:collect="always">
+ <path
+ transform="scale(-0.6)"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0.625;stroke-linejoin:round;stroke-opacity:1"
+ id="path1216" />
+ </marker>
+ <marker
+ style="overflow:visible"
+ id="Arrow2Mend"
+ refX="0"
+ refY="0"
+ orient="auto"
+ inkscape:stockid="Arrow2Mend"
+ inkscape:isstock="true"
+ inkscape:collect="always">
+ <path
+ transform="scale(-0.6)"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0.625;stroke-linejoin:round;stroke-opacity:1"
+ id="path909" />
+ </marker>
+ <marker
+ style="overflow:visible"
+ id="Arrow1Lend"
+ refX="0"
+ refY="0"
+ orient="auto"
+ inkscape:stockid="Arrow1Lend"
+ inkscape:isstock="true">
+ <path
+ transform="matrix(-0.8,0,0,-0.8,-10,0)"
+ style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:1pt;stroke-opacity:1"
+ d="M 0,0 5,-5 -12.5,0 5,5 Z"
+ id="path885" />
+ </marker>
+ <marker
+ style="overflow:visible"
+ id="marker1559-2"
+ refX="0"
+ refY="0"
+ orient="auto"
+ inkscape:stockid="Arrow2Mend"
+ inkscape:isstock="true">
+ <path
+ transform="scale(-0.6)"
+ d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+ style="fill:#000000;fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0.625;stroke-linejoin:round;stroke-opacity:1"
+ id="path1557-9" />
+ </marker>
+ </defs>
+ <sodipodi:namedview
+ id="base"
+ pagecolor="#ffffff"
+ bordercolor="#666666"
+ borderopacity="1.0"
+ inkscape:pageopacity="0.0"
+ inkscape:pageshadow="2"
+ inkscape:zoom="2.8"
+ inkscape:cx="120.68286"
+ inkscape:cy="23.831081"
+ inkscape:document-units="mm"
+ inkscape:current-layer="g1411"
+ inkscape:document-rotation="0"
+ showgrid="false"
+ inkscape:snap-global="false"
+ inkscape:window-width="1920"
+ inkscape:window-height="1135"
+ inkscape:window-x="0"
+ inkscape:window-y="0"
+ inkscape:window-maximized="1"
+ lock-margins="true"
+ fit-margin-top="2"
+ fit-margin-left="2"
+ fit-margin-right="2"
+ fit-margin-bottom="2" />
+ <metadata
+ id="metadata13431">
+ <rdf:RDF>
+ <cc:Work
+ rdf:about="">
+ <dc:format>image/svg+xml</dc:format>
+ <dc:type
+ rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+ <dc:title></dc:title>
+ </cc:Work>
+ </rdf:RDF>
+ </metadata>
+ <g
+ inkscape:label="Ebene 1"
+ inkscape:groupmode="layer"
+ id="layer1"
+ transform="translate(-8.1569115,-36.221295)">
+ <g
+ id="g1411"
+ transform="translate(32.258972,-4.0381556)">
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ d="m 26.22787,46.991961 -0.04324,7.85981"
+ id="path870"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ d="m 27.268191,47.234524 6.5917,7.093847"
+ id="path872"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ d="M 17.211264,56.167197 12.543075,64.49543"
+ id="path874"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ d="m 19.403188,56.222309 1.865426,8.356695"
+ id="path876"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.265;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#Arrow2Mend);paint-order:markers fill stroke;stop-color:#000000"
+ d="m 34.590338,55.360048 c 1.051358,-1.820435 1.974353,-2.426981 3.317324,-2.31217 0.956924,0.08181 1.647835,1.289889 2.049783,2.024833"
+ id="path880"
+ sodipodi:nodetypes="cac" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ d="m 25.076267,47.179412 -6.5917,7.093847"
+ id="path14001"
+ sodipodi:nodetypes="cc" />
+ <rect
+ style="opacity:1;fill:#25e325;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="rect13997"
+ width="4.4276514"
+ height="3.9112766"
+ x="23.986937"
+ y="44.075451" />
+ <rect
+ style="opacity:1;fill:#ff8cff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="rect13999"
+ width="4.4276514"
+ height="3.9112766"
+ x="15.955473"
+ y="53.282654" />
+ <path
+ sodipodi:type="star"
+ style="opacity:1;fill:#ff8cff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14003"
+ sodipodi:sides="3"
+ sodipodi:cx="26.161613"
+ sodipodi:cy="55.658291"
+ sodipodi:r1="2.7924292"
+ sodipodi:r2="1.3962145"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ d="m 28.579928,57.054505 -4.836629,0 2.418314,-4.188643 z"
+ inkscape:transform-center-y="-0.69810795" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:0.264583;stroke-miterlimit:4;stroke-dasharray:0.529166, 0.529166;stroke-dashoffset:0;paint-order:markers fill stroke;stop-color:#000000"
+ d="M 11.791704,65.225482 9.0065326,70.566411"
+ id="path1467"
+ sodipodi:nodetypes="cc" />
+ <path
+ style="fill:none;stroke:#000000;stroke-width:0.264583;stroke-miterlimit:4;stroke-dasharray:0.529166, 0.529166;stroke-dashoffset:0;paint-order:markers fill stroke;stop-color:#000000"
+ d="m 13.983628,65.280594 1.865426,5.369391"
+ id="path1469"
+ sodipodi:nodetypes="cc" />
+ <circle
+ style="opacity:1;fill:#6abfff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14861"
+ cx="12.714239"
+ cy="65.343147"
+ r="2.3446827" />
+ <path
+ sodipodi:type="star"
+ style="opacity:1;fill:#ff8cff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14863"
+ sodipodi:sides="3"
+ sodipodi:cx="33.771244"
+ sodipodi:cy="55.658291"
+ sodipodi:r1="2.7924292"
+ sodipodi:r2="1.3962145"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ d="m 36.189559,57.054505 -4.83663,0 2.418315,-4.188643 z"
+ inkscape:transform-center-y="-0.69810795" />
+ <path
+ sodipodi:type="star"
+ style="font-variation-settings:normal;opacity:1;vector-effect:none;fill:#6abfff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000;stop-opacity:1"
+ id="path14865"
+ sodipodi:sides="3"
+ sodipodi:cx="31.079979"
+ sodipodi:cy="69.469734"
+ sodipodi:r1="2.7924292"
+ sodipodi:r2="1.3962145"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ d="m 33.498294,70.865949 -4.83663,0 2.418315,-4.188644 z"
+ inkscape:transform-center-y="-0.69810795" />
+ <circle
+ style="font-variation-settings:normal;opacity:1;vector-effect:none;fill:#6abfff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000;stop-opacity:1"
+ id="circle14867"
+ cx="21.223957"
+ cy="65.343147"
+ r="2.3446827" />
+ <rect
+ style="font-variation-settings:normal;opacity:1;vector-effect:none;fill:#6abfff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000;stop-opacity:1"
+ id="rect14869"
+ width="4.4276514"
+ height="3.9112766"
+ x="36.216988"
+ y="66.749847" />
+ <path
+ id="path82"
+ inkscape:connector-curvature="0"
+ d="m 41.515562,54.871846 -0.417806,1.20398 -1.168202,0.279888 -0.960641,-0.870246 -1.138707,0.832408 0.537693,1.179427 -0.621192,1.02818 -1.273991,0.03274 -0.218785,1.407938 1.203979,0.417805 0.279889,1.168202 -0.870245,0.960643 0.832407,1.138704 1.179427,-0.537691 1.028181,0.621191 0.03274,1.273992 1.407938,0.218785 0.417806,-1.20398 1.168202,-0.279888 0.96064,0.870244 1.138706,-0.832406 -0.537691,-1.179427 0.621192,-1.028182 1.273992,-0.03274 0.218784,-1.407938 -1.20398,-0.417805 -0.279888,-1.168203 0.870246,-0.96064 -0.83241,-1.138707 -1.179425,0.537693 -1.028181,-0.621192 -0.03274,-1.273992 z"
+ style="fill:#d0dbf5;fill-opacity:1;stroke:#0f2d59;stroke-width:0.284967;stroke-linecap:round;stroke-linejoin:round"
+ sodipodi:nodetypes="ccccccccccccccccccccccccccccccccc" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.265;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#marker1218);paint-order:markers fill stroke;stop-color:#000000"
+ d="m 36.505382,61.212129 c -1.732593,0.460546 -2.239587,0.94846 -3.054171,1.805942 -0.855057,0.900086 -1.291029,1.914968 -1.728787,3.298907"
+ id="path1214"
+ sodipodi:nodetypes="cac" />
+ <path
+ style="opacity:1;fill:none;stroke:#000000;stroke-width:0.265;stroke-miterlimit:4;stroke-dasharray:none;marker-end:url(#marker1266);paint-order:markers fill stroke;stop-color:#000000"
+ d="m 39.119283,63.680684 c -0.561579,0.349977 -1.171361,1.831472 -1.388934,2.468193"
+ id="path1262"
+ sodipodi:nodetypes="cc" />
+ <g
+ id="g1624-1"
+ transform="translate(-24.776227,-7.0250037)">
+ <path
+ sodipodi:type="star"
+ style="font-variation-settings:normal;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.113934;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14865-5-2"
+ sodipodi:sides="3"
+ sodipodi:cx="66.174721"
+ sodipodi:cy="64.759911"
+ sodipodi:r1="1.2024668"
+ sodipodi:r2="0.60123342"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ inkscape:transform-center-y="-0.30061479"
+ inkscape:transform-center-x="2.0589357e-06"
+ d="m 67.216088,65.361144 -2.082734,0 1.041367,-1.8037 z" />
+ <path
+ style="font-variation-settings:normal;opacity:1;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.15;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;marker-end:url(#marker1559-2);paint-order:markers fill stroke;stop-color:#000000;stop-opacity:1"
+ d="M 66.173282,65.809672 V 67.26045"
+ id="path1555-0" />
+ <g
+ id="g1807"
+ transform="translate(0.32991862)">
+ <rect
+ style="font-variation-settings:normal;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.113934;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="rect14869-6-7"
+ width="1.906621"
+ height="1.6842613"
+ x="66.594307"
+ y="67.911743" />
+ <path
+ sodipodi:type="star"
+ style="font-variation-settings:normal;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.113934;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="path1803"
+ sodipodi:sides="3"
+ sodipodi:cx="64.271751"
+ sodipodi:cy="69.082977"
+ sodipodi:r1="1.2024668"
+ sodipodi:r2="0.60123342"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ inkscape:transform-center-y="-0.30061479"
+ inkscape:transform-center-x="2.0589357e-06"
+ d="m 65.313118,69.684211 -2.082733,0 1.041366,-1.803701 z" />
+ </g>
+ </g>
+ </g>
+ <g
+ id="g1374"
+ transform="translate(-49.214304,-4.5219647)">
+ <circle
+ style="font-variation-settings:normal;vector-effect:none;fill:#6abfff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="circle14867-5"
+ cx="61.878521"
+ cy="49.767113"
+ r="2.3446827" />
+ <text
+ xml:space="preserve"
+ style="font-style:normal;font-weight:normal;font-size:3.52778px;line-height:1.25;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.125046"
+ x="59.173122"
+ y="60.298515"
+ id="text14855"><tspan
+ sodipodi:role="line"
+ id="tspan14853"
+ x="59.173122"
+ y="60.298515"
+ style="font-size:3.52778px;stroke-width:0.125046">Converter</tspan></text>
+ <text
+ xml:space="preserve"
+ style="font-style:normal;font-weight:normal;font-size:3.52778px;line-height:1.25;font-family:sans-serif;letter-spacing:0px;word-spacing:0px;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.125046"
+ x="59.173122"
+ y="45.423546"
+ id="text14859"><tspan
+ sodipodi:role="line"
+ id="tspan14857"
+ x="59.173122"
+ y="45.423546"
+ style="font-size:3.52778px;stroke-width:0.125046">StructureElement</tspan></text>
+ <rect
+ style="fill:#25e325;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="rect13997-6"
+ width="4.4276514"
+ height="3.9112766"
+ x="65.556091"
+ y="47.811474" />
+ <path
+ sodipodi:type="star"
+ style="fill:#ff8cff;fill-opacity:1;stroke:#000000;stroke-width:0.264583;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14003-7"
+ sodipodi:sides="3"
+ sodipodi:cx="73.831802"
+ sodipodi:cy="50.531364"
+ sodipodi:r1="2.7924292"
+ sodipodi:r2="1.3962145"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ inkscape:transform-center-y="-0.69810795"
+ d="m 76.250117,51.927579 -4.836629,0 2.418314,-4.188644 z" />
+ <g
+ id="g1649">
+ <path
+ id="path82-3"
+ inkscape:connector-curvature="0"
+ d="m 66.342602,61.715213 -0.417806,1.20398 -1.168202,0.279888 -0.960641,-0.870246 -1.138707,0.832408 0.537693,1.179427 -0.621192,1.02818 -1.273991,0.03274 -0.218785,1.407938 1.203979,0.417805 0.279889,1.168202 -0.870245,0.960643 0.832407,1.138704 1.179427,-0.537691 1.028181,0.621191 0.03274,1.273992 1.407938,0.218785 0.417806,-1.20398 1.168202,-0.279888 0.96064,0.870244 1.138706,-0.832406 -0.537691,-1.179427 0.621192,-1.028182 1.273992,-0.03274 0.218784,-1.407938 -1.20398,-0.417805 -0.279888,-1.168203 0.870246,-0.96064 -0.83241,-1.138707 -1.179425,0.537693 -1.028181,-0.621192 -0.03274,-1.273992 z"
+ style="fill:#d0dbf5;fill-opacity:1;stroke:#0f2d59;stroke-width:0.284967;stroke-linecap:round;stroke-linejoin:round"
+ sodipodi:nodetypes="ccccccccccccccccccccccccccccccccc" />
+ <g
+ id="g1624"
+ transform="translate(-0.23034383)">
+ <path
+ sodipodi:type="star"
+ style="font-variation-settings:normal;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.113934;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="path14865-5"
+ sodipodi:sides="3"
+ sodipodi:cx="66.489288"
+ sodipodi:cy="64.759911"
+ sodipodi:r1="1.2024668"
+ sodipodi:r2="0.60123342"
+ sodipodi:arg1="0.52359878"
+ sodipodi:arg2="1.5707963"
+ inkscape:flatsided="true"
+ inkscape:rounded="0"
+ inkscape:randomized="0"
+ inkscape:transform-center-y="-0.30061479"
+ d="m 67.530655,65.361144 -2.082734,0 1.041367,-1.8037 z"
+ inkscape:transform-center-x="2.0589357e-06" />
+ <rect
+ style="font-variation-settings:normal;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.113934;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke;stop-color:#000000"
+ id="rect14869-6"
+ width="1.906621"
+ height="1.6842613"
+ x="65.535973"
+ y="67.911743" />
+ <path
+ style="font-variation-settings:normal;opacity:1;vector-effect:none;fill:none;fill-opacity:1;stroke:#000000;stroke-width:0.15;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;marker-end:url(#marker1559);paint-order:markers fill stroke;stop-color:#000000;stop-opacity:1"
+ d="M 66.487845,65.809672 V 67.26045"
+ id="path1555" />
+ </g>
+ </g>
+ </g>
+ </g>
+</svg>
diff --git a/src/doc/macros.rst b/src/doc/macros.rst
index 5329ca6ddde49dbef439659d4904b07ed3f2bef9..d093d9b69f5d2c14b5bfbb2fe292545fc7943ca7 100644
--- a/src/doc/macros.rst
+++ b/src/doc/macros.rst
@@ -1,7 +1,8 @@
Macros
------
-Macros highly facilitate the writing of complex :doc:`CFoods<cfood>`. Consider the following prevalent example:
+Macros highly facilitate the writing of complex :doc:`CFoods<cfood>`. Consider the following common
+example:
.. _example_files:
.. code-block:: yaml
diff --git a/src/doc/tutorials/index.rst b/src/doc/tutorials/index.rst
index b6f0fab511f3646f3ec6a7a320299e72a2c20038..2d4e8be7172f3d1ea8f5f154c4d8013891312309 100644
--- a/src/doc/tutorials/index.rst
+++ b/src/doc/tutorials/index.rst
@@ -9,4 +9,4 @@ This chapter contains a collection of tutorials.
Parameter File<parameterfile>
Scientific Data Folder<scifolder>
-
+ WIP: Single Structured File <single_file>
diff --git a/src/doc/tutorials/single_file.rst b/src/doc/tutorials/single_file.rst
new file mode 100644
index 0000000000000000000000000000000000000000..35c6c999e8ed422ac3b8caf6ae92b31d91f182c6
--- /dev/null
+++ b/src/doc/tutorials/single_file.rst
@@ -0,0 +1,129 @@
+WIP Tutorial: Single structured file
+====================================
+
+.. warning::
+
+ This tutorial is still work in progress. It may be better than nothing, but it is still
+ incomplete and probably contains serious errors.
+
+ Use at your own risk.
+
+In this tutorial, we will create a crawler that reads a single structured file, such as an XLSX
+file.
+
+Declarations
+------------
+
+``identifiables.yml``
+
+.. code-block:: yaml
+
+ Präventionsmaßnahme:
+ - Organisation
+ - titel
+ - Laufzeit
+
+
+``cfood.yml``
+
+.. code-block:: yaml
+
+ ---
+ metadata:
+ crawler-version: 0.6.1
+ ---
+
+ Präventionsmaßnahme der Organisation: # Eine Excel-Datei mit Präventionsmaßnahmen
+ type: XLSXTableConverter
+ match: ".*xlsx$" # Any xlsx file.
+ subtree:
+ Maßnahme: # Eine Zeile in der Datei
+ type: DictElement
+ match_name: .*
+ match_value: .*
+ records:
+ Präventionsmaßnahme: # Records edited for each row
+ name: ""
+ subtree:
+ MaßnahmenArt: # Spalte mit Art der Maßnahme
+ type: IntegerElement
+ match_name: Art der Maßnahme # Name of the column in the table file
+ match_value: (?P<column_value).*)
+ MaßnahmenTitel:
+ type: TextElement
+ match_name: Titel der Maßnahme # Name of the column in the table file
+ match_value: (?P<column_value).*)
+ records: # Records edited for each cell
+ Präventionsmaßnahme:
+ titel: $column_value
+
+
+Python code
+-----------
+
+
+.. code-block:: python
+
+ #!/usr/bin/env python3
+
+ # Crawler für Präventionsmaßnahme
+ #
+ # Copyright (C) 2023 IndiScale GmbH <info@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/>.
+
+ """Crawler für Präventionsmaßnahmen"""
+
+ import argparse
+
+ from caoscrawler.scanner import load_definition, create_converter_registry, scan_structure_elements
+ from caoscrawler.structure_elements import File
+
+
+ def crawl_file(filename: str, dry_run: bool = False):
+ """Read an XLSX file into a LinkAhead container.
+
+ Parameters
+ ----------
+ filename : str
+ The name of the XLSX file.
+
+ dry_run : bool
+ If True, do not modify the database.
+ """
+ definition = load_definition("cfood.yml")
+ converter_registry = create_converter_registry(definition)
+
+ records = scan_structure_elements(items=File(name="somename.xlsx", path=filename),
+ crawler_definition=definition,
+ converter_registry=converter_registry)
+ from IPython import embed
+ embed()
+
+ def _parse_arguments():
+ """Parse the arguments."""
+ parser = argparse.ArgumentParser(description='Crawler für Präventionsmaßnahme')
+ parser.add_argument('-n', '--dry-run', help="Do not modify the database.", action="store_true")
+ parser.add_argument('xlsx_file', metavar="XSLX file", help="The xlsx file to be crawled.")
+ return parser.parse_args()
+
+
+ def main():
+ """Main function."""
+ args = _parse_arguments()
+ crawl_file(args.xlsx_file, dry_run=args.dry_run)
+
+
+ if __name__ == '__main__':
+ main()