Skip to content

Helpers

ListLookup

Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
@dataclass
class ListLookup:
    _lookup: dict[str, dict[str, str]]
    _prop_to_list_name: dict[str, str]
    _label_language: str

    @staticmethod
    def create_new(project_json_path: str | Path, language_of_label: str, default_ontology: str) -> ListLookup:
        """
        Creates a list lookup based on list labels in a specified language and returning list node names.
        Works for all lists in a project.json

        Args:
            project_json_path: path to a JSON project file (a.k.a. ontology)
            language_of_label: label language used for the list
            default_ontology: ontology prefix which is defined as default in the XML file

        Returns:
            `ListLookup` for a project

        Examples:
            ```python
            list_lookup = xmllib.ListLookup.create_new(
                project_json_path="project.json",
                language_of_label="en",
                default_ontology="default-onto",
            )
            ```
        """
        with open(project_json_path, encoding="utf-8") as f:
            json_file = json.load(f)
        label_to_list_node_lookup = _get_label_to_node_all_lists(json_file["project"]["lists"], language_of_label)
        prop_to_list_mapper = _get_property_to_list_name_mapping(json_file["project"]["ontologies"], default_ontology)
        return ListLookup(
            _lookup=label_to_list_node_lookup,
            _prop_to_list_name=prop_to_list_mapper,
            _label_language=language_of_label,
        )

    def get_node_via_list_name(self, list_name: str, node_label: str) -> str:
        """
        Returns the list node name based on a label.
        The language of the label was specified when creating the `ListLookup`.

        Args:
            list_name: name of the list
            node_label: label of the node

        Returns:
            node name

        Examples:
            ```python
            node_name = list_lookup.get_node_via_list_name(
                list_name="list1",
                node_label="Label 1"  # or: "label 1" (capitalisation is not relevant)
            )
            # node_name == "node1"
            ```
        """
        if not (list_lookup := self._lookup.get(list_name)):
            msg = f"Entered list name '{list_name}' was not found."
            warnings.warn(DspToolsUserWarning(msg))
            return ""
        if not (found_node := list_lookup.get(node_label)):
            msg = (
                f"'{node_label}' was not recognised as label of the list '{list_name}'. "
                f"This ListLookup is configured for '{self._label_language}' labels."
            )
            warnings.warn(DspToolsUserWarning(msg))
            return ""
        return found_node

    def get_list_name_and_node_via_property(self, prop_name: str, node_label: str) -> tuple[str, str]:
        """
        Returns the list name and the node name based on a property that is used with the list and the label of a node.
        The language of the label was specified when creating the `ListLookup`.
        The list name needs to be referenced in the XML file.

        Args:
            prop_name: name of the list
            node_label: label of the node

        Returns:
            list name and node name

        Examples:
            ```python
            list_name, node_name = list_lookup.get_list_name_and_node_via_property(
                prop_name=":hasList",  # or: "default-onto:hasList"
                node_label="label 1"
            )
            # list_name == "list1"
            # node_name == "node1"
            ```
        """
        if not (list_name := self.get_list_name_via_property(prop_name)):
            return "", ""
        return list_name, self.get_node_via_list_name(list_name, node_label)

    def get_list_name_via_property(self, prop_name: str) -> str:
        """
        Returns the list name as specified in the ontology for a property.
        The list name needs to be referenced in the XML file.

        Args:
            prop_name: name of the property

        Returns:
            Name of the list

        Examples:
            ```python
            list_name = list_lookup.get_list_name_via_property(
                prop_name=":hasList",  # or: "default-onto:hasList"
            )
            # list_name == "list1"
            ```
        """
        if not (list_name := self._prop_to_list_name.get(prop_name)):
            msg = f"Entered property '{prop_name}' was not found."
            warnings.warn(DspToolsUserWarning(msg))
            return ""
        return list_name

create_new

Creates a list lookup based on list labels in a specified language and returning list node names. Works for all lists in a project.json

Parameters:

Name Type Description Default
project_json_path str | Path

path to a JSON project file (a.k.a. ontology)

required
language_of_label str

label language used for the list

required
default_ontology str

ontology prefix which is defined as default in the XML file

required

Returns:

Type Description
ListLookup

ListLookup for a project

Examples:

list_lookup = xmllib.ListLookup.create_new(
    project_json_path="project.json",
    language_of_label="en",
    default_ontology="default-onto",
)
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
@staticmethod
def create_new(project_json_path: str | Path, language_of_label: str, default_ontology: str) -> ListLookup:
    """
    Creates a list lookup based on list labels in a specified language and returning list node names.
    Works for all lists in a project.json

    Args:
        project_json_path: path to a JSON project file (a.k.a. ontology)
        language_of_label: label language used for the list
        default_ontology: ontology prefix which is defined as default in the XML file

    Returns:
        `ListLookup` for a project

    Examples:
        ```python
        list_lookup = xmllib.ListLookup.create_new(
            project_json_path="project.json",
            language_of_label="en",
            default_ontology="default-onto",
        )
        ```
    """
    with open(project_json_path, encoding="utf-8") as f:
        json_file = json.load(f)
    label_to_list_node_lookup = _get_label_to_node_all_lists(json_file["project"]["lists"], language_of_label)
    prop_to_list_mapper = _get_property_to_list_name_mapping(json_file["project"]["ontologies"], default_ontology)
    return ListLookup(
        _lookup=label_to_list_node_lookup,
        _prop_to_list_name=prop_to_list_mapper,
        _label_language=language_of_label,
    )

get_node_via_list_name

Returns the list node name based on a label. The language of the label was specified when creating the ListLookup.

Parameters:

Name Type Description Default
list_name str

name of the list

required
node_label str

label of the node

required

Returns:

Type Description
str

node name

Examples:

node_name = list_lookup.get_node_via_list_name(
    list_name="list1",
    node_label="Label 1"  # or: "label 1" (capitalisation is not relevant)
)
# node_name == "node1"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
def get_node_via_list_name(self, list_name: str, node_label: str) -> str:
    """
    Returns the list node name based on a label.
    The language of the label was specified when creating the `ListLookup`.

    Args:
        list_name: name of the list
        node_label: label of the node

    Returns:
        node name

    Examples:
        ```python
        node_name = list_lookup.get_node_via_list_name(
            list_name="list1",
            node_label="Label 1"  # or: "label 1" (capitalisation is not relevant)
        )
        # node_name == "node1"
        ```
    """
    if not (list_lookup := self._lookup.get(list_name)):
        msg = f"Entered list name '{list_name}' was not found."
        warnings.warn(DspToolsUserWarning(msg))
        return ""
    if not (found_node := list_lookup.get(node_label)):
        msg = (
            f"'{node_label}' was not recognised as label of the list '{list_name}'. "
            f"This ListLookup is configured for '{self._label_language}' labels."
        )
        warnings.warn(DspToolsUserWarning(msg))
        return ""
    return found_node

get_list_name_and_node_via_property

Returns the list name and the node name based on a property that is used with the list and the label of a node. The language of the label was specified when creating the ListLookup. The list name needs to be referenced in the XML file.

Parameters:

Name Type Description Default
prop_name str

name of the list

required
node_label str

label of the node

required

Returns:

Type Description
tuple[str, str]

list name and node name

Examples:

list_name, node_name = list_lookup.get_list_name_and_node_via_property(
    prop_name=":hasList",  # or: "default-onto:hasList"
    node_label="label 1"
)
# list_name == "list1"
# node_name == "node1"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
def get_list_name_and_node_via_property(self, prop_name: str, node_label: str) -> tuple[str, str]:
    """
    Returns the list name and the node name based on a property that is used with the list and the label of a node.
    The language of the label was specified when creating the `ListLookup`.
    The list name needs to be referenced in the XML file.

    Args:
        prop_name: name of the list
        node_label: label of the node

    Returns:
        list name and node name

    Examples:
        ```python
        list_name, node_name = list_lookup.get_list_name_and_node_via_property(
            prop_name=":hasList",  # or: "default-onto:hasList"
            node_label="label 1"
        )
        # list_name == "list1"
        # node_name == "node1"
        ```
    """
    if not (list_name := self.get_list_name_via_property(prop_name)):
        return "", ""
    return list_name, self.get_node_via_list_name(list_name, node_label)

get_list_name_via_property

Returns the list name as specified in the ontology for a property. The list name needs to be referenced in the XML file.

Parameters:

Name Type Description Default
prop_name str

name of the property

required

Returns:

Type Description
str

Name of the list

Examples:

list_name = list_lookup.get_list_name_via_property(
    prop_name=":hasList",  # or: "default-onto:hasList"
)
# list_name == "list1"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
def get_list_name_via_property(self, prop_name: str) -> str:
    """
    Returns the list name as specified in the ontology for a property.
    The list name needs to be referenced in the XML file.

    Args:
        prop_name: name of the property

    Returns:
        Name of the list

    Examples:
        ```python
        list_name = list_lookup.get_list_name_via_property(
            prop_name=":hasList",  # or: "default-onto:hasList"
        )
        # list_name == "list1"
        ```
    """
    if not (list_name := self._prop_to_list_name.get(prop_name)):
        msg = f"Entered property '{prop_name}' was not found."
        warnings.warn(DspToolsUserWarning(msg))
        return ""
    return list_name

create_footnote_string

Takes the text for a footnote, and returns a string with the correct formatting. You can use this if you want to add the footnote to a string. Currently, the newline replacement options are restricted to LINEBREAK and NONE. The reserved characters <, > and & will be escaped temporarily, but they will be correctly displayed in DSP-APP.

Attention
  • The text in the footnote may be richtext, i.e. contain XML tags.
  • Not all tags supported in ordinary richtext are currently implemented.
  • The allowed tags are:
    • <br> (break line)
    • <strong> (bold)
    • <em> (italic)
    • <u> (underline)
    • <strike> (strike through)
    • <a href="URI"> (link to a URI)
    • <a class="salsah-link" href="Knora IRI"> (link to a resource)

Parameters:

Name Type Description Default
footnote_text str

Text for the footnote

required
newline_replacement_option NewlineReplacement

options to replace newlines

LINEBREAK

Returns:

Type Description
str

The footnote as a string

Examples:

result = xmllib.create_footnote_string("Text")
# result == '<footnote content="Text"/>'
result = xmllib.create_footnote_string("Text\nSecond Line")
# result == '<footnote content="Text&lt;br/&gt;Second Line"/>'
result = xmllib.create_footnote_string("Already escaped &lt;&gt;")
# already escaped characters will not be escaped again
# result == '<footnote content="Already escaped &lt;&gt;"/>'
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
def create_footnote_string(
    footnote_text: str, newline_replacement_option: NewlineReplacement = NewlineReplacement.LINEBREAK
) -> str:
    """
    Takes the text for a footnote, and returns a string with the correct formatting.
    You can use this if you want to add the footnote to a string.
    Currently, the newline replacement options are restricted to `LINEBREAK` and `NONE`.
    The reserved characters `<`, `>` and `&` will be escaped temporarily,
    but they will be correctly displayed in DSP-APP.

    Attention:
        - The text in the footnote may be richtext, i.e. contain XML tags.
        - Not all tags supported in ordinary richtext are currently implemented.
        - The allowed tags are:
            - `<br>` (break line)
            - `<strong>` (bold)
            - `<em>` (italic)
            - `<u>` (underline)
            - `<strike>` (strike through)
            - `<a href="URI">` (link to a URI)
            - `<a class="salsah-link" href="Knora IRI">` (link to a resource)

    Args:
        footnote_text: Text for the footnote
        newline_replacement_option: options to replace newlines

    Raises:
        InputError: If the text is empty, or if a newline replacement which is not implemented is entered

    Returns:
        The footnote as a string

    Examples:
        ```python
        result = xmllib.create_footnote_string("Text")
        # result == '<footnote content="Text"/>'
        ```

        ```python
        result = xmllib.create_footnote_string("Text\\nSecond Line")
        # result == '<footnote content="Text&lt;br/&gt;Second Line"/>'
        ```

        ```python
        result = xmllib.create_footnote_string("Already escaped &lt;&gt;")
        # already escaped characters will not be escaped again
        # result == '<footnote content="Already escaped &lt;&gt;"/>'
        ```
    """
    text_tag = create_footnote_element(footnote_text, newline_replacement_option)
    return etree.tostring(text_tag, encoding="unicode")

create_footnote_element

Takes the text for a footnote, and returns an etree.Element. You can use this if you are working with lxml. Currently, the newline replacement options are restricted to LINEBREAK and NONE.

Attention
  • The text in the footnote may be richtext, i.e. contain XML tags.
  • Not all tags supported in ordinary richtext are currently implemented.
  • The allowed tags are:
    • <br> (break line)
    • <strong> (bold)
    • <em> (italic)
    • <u> (underline)
    • <strike> (strike through)
    • <a href="URI"> (link to a URI)
    • <a class="salsah-link" href="Knora IRI"> (link to a resource)

Parameters:

Name Type Description Default
footnote_text str

Text for the footnote

required
newline_replacement_option NewlineReplacement

options to replace newlines

LINEBREAK

Returns:

Type Description
_Element

The footnote as a string

Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
def create_footnote_element(
    footnote_text: str, newline_replacement_option: NewlineReplacement = NewlineReplacement.LINEBREAK
) -> etree._Element:
    """
    Takes the text for a footnote, and returns an `etree.Element`.
    You can use this if you are working with `lxml`.
    Currently, the newline replacement options are restricted to `LINEBREAK` and `NONE`.

    Attention:
        - The text in the footnote may be richtext, i.e. contain XML tags.
        - Not all tags supported in ordinary richtext are currently implemented.
        - The allowed tags are:
            - `<br>` (break line)
            - `<strong>` (bold)
            - `<em>` (italic)
            - `<u>` (underline)
            - `<strike>` (strike through)
            - `<a href="URI">` (link to a URI)
            - `<a class="salsah-link" href="Knora IRI">` (link to a resource)

    Args:
        footnote_text: Text for the footnote
        newline_replacement_option: options to replace newlines

    Raises:
        InputError: If the text is empty, or if a newline replacement which is not implemented is entered

    Returns:
        The footnote as a string
    """
    if newline_replacement_option not in {NewlineReplacement.LINEBREAK, NewlineReplacement.NONE}:
        raise InputError("Currently the only supported newline replacement is linebreak (<br/>) or None.")
    if not is_nonempty_value_internal(footnote_text):
        raise InputError("The input value is empty.")
    footnote_text = replace_newlines_with_tags(str(footnote_text), newline_replacement_option)
    unescaped_text = unescape_reserved_xml_chars(footnote_text)
    return etree.Element("footnote", attrib={"content": unescaped_text})

Creates a standoff link to a resource.

Parameters:

Name Type Description Default
resource_id str

ID of the resource that is linked

required
displayed_text str

text to display for the embedded link

required

Returns:

Type Description
str

A standoff link in string form.

Examples:

result = xmllib.create_standoff_link_to_resource("resource_id", "Text")
# result == '<a class="salsah-link" href="IRI:resource_id:IRI">Text</a>'
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
def create_standoff_link_to_resource(resource_id: str, displayed_text: str) -> str:
    """
    Creates a standoff link to a resource.

    Args:
        resource_id: ID of the resource that is linked
        displayed_text: text to display for the embedded link

    Returns:
        A standoff link in string form.

    Raises:
        InputError: if the resource ID or the displayed text are empty

    Examples:
        ```python
        result = xmllib.create_standoff_link_to_resource("resource_id", "Text")
        # result == '<a class="salsah-link" href="IRI:resource_id:IRI">Text</a>'
        ```
    """
    if not all([is_nonempty_value_internal(resource_id), is_nonempty_value_internal(displayed_text)]):
        raise InputError(
            (
                f"The entered resource ID and displayed text may not be empty. "
                f"Your input: resource_id '{resource_id}' / displayed_text '{displayed_text}'"
            )
        )
    attribs = {"class": "salsah-link", "href": f"IRI:{resource_id}:IRI"}
    ele = etree.Element("a", attrib=attribs)
    ele.text = displayed_text
    return etree.tostring(ele, encoding="unicode")

Creates a standoff link to a URI.

Parameters:

Name Type Description Default
uri str

the target URI that should be linked to

required
displayed_text str

text to display for the embedded link

required

Returns:

Type Description
str

A standoff link in string form.

Examples:

result = xmllib.create_standoff_link_to_uri("https://www.dasch.swiss/", "This is DaSCH")
# result == '<a href="https://www.dasch.swiss/">This is DaSCH</a>'
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
def create_standoff_link_to_uri(uri: str, displayed_text: str) -> str:
    """
    Creates a standoff link to a URI.

    Args:
        uri: the target URI that should be linked to
        displayed_text: text to display for the embedded link

    Returns:
        A standoff link in string form.

    Raises:
        InputError: if the URI or the displayed text are empty

    Examples:
        ```python
        result = xmllib.create_standoff_link_to_uri("https://www.dasch.swiss/", "This is DaSCH")
        # result == '<a href="https://www.dasch.swiss/">This is DaSCH</a>'
        ```
    """
    if not all([is_nonempty_value_internal(uri), is_nonempty_value_internal(displayed_text)]):
        raise InputError(
            (
                f"The entered URI and displayed text may not be empty. "
                f"Your input: uri '{uri}' / displayed_text '{displayed_text}'"
            )
        )
    attribs = {"href": uri}
    ele = etree.Element("a", attrib=attribs)
    ele.text = displayed_text
    return etree.tostring(ele, encoding="unicode")

create_label_to_name_list_node_mapping

Often, data sources contain list values named after the "label" of the JSON project list node, instead of the "name" which is needed for the dsp-tools xmlupload. To create a correct XML, you need a dictionary that maps the "labels" to their correct "names".

Parameters:

Name Type Description Default
project_json_path str

path to a JSON project file (a.k.a. ontology)

required
list_name str

name of a list in the JSON project

required
language_of_label str

which language of the label to choose

required

Returns:

Type Description
dict[str, str]

a dictionary of the form {label: name}

Examples:

"lists": [
    {
        "name": "listName",
        "labels": {
            "en": "List",
            "de": "Liste"
        },
        "comments": { ... },
        "nodes": [
            {
                "name": "n1",
                "labels": {
                    "en": "Node 1",
                    "de": "Knoten 1"
                }
            },
            {
                "name": "n2",
                "labels": {
                    "en": "Node 2",
                    "de": "Knoten 2"
                }
            }
        ]
    }
]
result = xmllib.create_label_to_name_list_node_mapping(
    project_json_path="project.json",
    list_name="listName",
    language_of_label="de",
)
# result == {"Knoten 1": "n1", "knoten 1": "n1", "Knoten 2": "n2", "knoten 2": "n2"}
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
def create_label_to_name_list_node_mapping(
    project_json_path: str,
    list_name: str,
    language_of_label: str,
) -> dict[str, str]:
    """
    Often, data sources contain list values named after the "label" of the JSON project list node, instead of the "name"
    which is needed for the `dsp-tools xmlupload`.
    To create a correct XML, you need a dictionary that maps the "labels" to their correct "names".

    Args:
        project_json_path: path to a JSON project file (a.k.a. ontology)
        list_name: name of a list in the JSON project
        language_of_label: which language of the label to choose

    Returns:
        a dictionary of the form {label: name}

    Examples:
        ```json
        "lists": [
            {
                "name": "listName",
                "labels": {
                    "en": "List",
                    "de": "Liste"
                },
                "comments": { ... },
                "nodes": [
                    {
                        "name": "n1",
                        "labels": {
                            "en": "Node 1",
                            "de": "Knoten 1"
                        }
                    },
                    {
                        "name": "n2",
                        "labels": {
                            "en": "Node 2",
                            "de": "Knoten 2"
                        }
                    }
                ]
            }
        ]
        ```

        ```python
        result = xmllib.create_label_to_name_list_node_mapping(
            project_json_path="project.json",
            list_name="listName",
            language_of_label="de",
        )
        # result == {"Knoten 1": "n1", "knoten 1": "n1", "Knoten 2": "n2", "knoten 2": "n2"}
        ```
    """
    with open(project_json_path, encoding="utf-8") as f:
        json_file = json.load(f)
    return _get_label_to_node_one_list(json_file["project"]["lists"], list_name, language_of_label)

get_list_nodes_from_string_via_list_name

Takes a string containing list labels, the separator by which they can be split, a property name and the list lookup. Resolves the labels and returns the list name to be referenced in the XML file and a list of node names. If the string is empty, it returns an empty list.

Parameters:

Name Type Description Default
string_with_list_labels str

the string containing the labels

required
label_separator str

separator in the string that contains the labels

required
list_name str

name of the list

required
list_lookup ListLookup

ListLookup of the project

required

Returns:

Type Description
list[str]

The name of the list and a list of node names.

Examples:

string_with_list_labels = "Label 1; Label 2"
nodes = xmllib.get_list_nodes_from_string_via_list_name(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    list_name="list1",
    list_lookup=list_lookup,
)
# nodes == ["node1", "node2"]
string_with_list_labels = ""
nodes = xmllib.get_list_nodes_from_string_via_list_name(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    list_name="list1",
    list_lookup=list_lookup,
)
# nodes == []
string_with_list_labels = pd.NA
nodes = xmllib.get_list_nodes_from_string_via_list_name(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    list_name="list1",
    list_lookup=list_lookup,
)
# nodes == []
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
def get_list_nodes_from_string_via_list_name(
    string_with_list_labels: str, label_separator: str, list_name: str, list_lookup: ListLookup
) -> list[str]:
    """
    Takes a string containing list labels, the separator by which they can be split,
    a property name and the list lookup.
    Resolves the labels and returns the list name to be referenced in the XML file and a list of node names.
    If the string is empty, it returns an empty list.

    Args:
        string_with_list_labels: the string containing the labels
        label_separator: separator in the string that contains the labels
        list_name: name of the list
        list_lookup: `ListLookup` of the project

    Returns:
        The name of the list and a list of node names.

    Examples:
        ```python
        string_with_list_labels = "Label 1; Label 2"
        nodes = xmllib.get_list_nodes_from_string_via_list_name(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            list_name="list1",
            list_lookup=list_lookup,
        )
        # nodes == ["node1", "node2"]
        ```

        ```python
        string_with_list_labels = ""
        nodes = xmllib.get_list_nodes_from_string_via_list_name(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            list_name="list1",
            list_lookup=list_lookup,
        )
        # nodes == []
        ```

        ```python
        string_with_list_labels = pd.NA
        nodes = xmllib.get_list_nodes_from_string_via_list_name(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            list_name="list1",
            list_lookup=list_lookup,
        )
        # nodes == []
        ```
    """
    if not is_nonempty_value_internal(string_with_list_labels):
        return []
    labels_list = create_list_from_string(string_with_list_labels, label_separator)
    nodes_list = [list_lookup.get_node_via_list_name(list_name, label) for label in labels_list]
    return nodes_list

get_list_nodes_from_string_via_property

Takes a string containing list labels, the separator by which they can be split, a property name and the list lookup. Resolves the labels and returns the list name to be referenced in the XML file and a list of node names. If the string is empty, it returns an empty list.

Parameters:

Name Type Description Default
string_with_list_labels str

the string containing the labels

required
label_separator str

separator in the string that contains the labels

required
property_name str

name of the property

required
list_lookup ListLookup

ListLookup of the project

required

Returns:

Type Description
tuple[str, list[str]]

The name of the list and a list of node names.

Examples:

string_with_list_labels = "Label 1; Label 2"
list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    property_name=":hasList",
    list_lookup=list_lookup,
)
# list_name == "list1"
# nodes == ["node1", "node2"]
string_with_list_labels = ""
list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    property_name=":hasList",
    list_lookup=list_lookup,
)
# list_name == ""
# nodes == []
string_with_list_labels = pd.NA
list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
    string_with_list_labels=string_with_list_labels,
    label_separator=";",
    property_name=":hasList",
    list_lookup=list_lookup,
)
# list_name == ""
# nodes == []
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
def get_list_nodes_from_string_via_property(
    string_with_list_labels: str, label_separator: str, property_name: str, list_lookup: ListLookup
) -> tuple[str, list[str]]:
    """
    Takes a string containing list labels, the separator by which they can be split,
    a property name and the list lookup.
    Resolves the labels and returns the list name to be referenced in the XML file and a list of node names.
    If the string is empty, it returns an empty list.

    Args:
        string_with_list_labels: the string containing the labels
        label_separator: separator in the string that contains the labels
        property_name: name of the property
        list_lookup: `ListLookup` of the project

    Returns:
        The name of the list and a list of node names.

    Examples:
        ```python
        string_with_list_labels = "Label 1; Label 2"
        list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            property_name=":hasList",
            list_lookup=list_lookup,
        )
        # list_name == "list1"
        # nodes == ["node1", "node2"]
        ```

        ```python
        string_with_list_labels = ""
        list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            property_name=":hasList",
            list_lookup=list_lookup,
        )
        # list_name == ""
        # nodes == []
        ```

        ```python
        string_with_list_labels = pd.NA
        list_name, nodes = xmllib.get_list_nodes_from_string_via_property(
            string_with_list_labels=string_with_list_labels,
            label_separator=";",
            property_name=":hasList",
            list_lookup=list_lookup,
        )
        # list_name == ""
        # nodes == []
        ```
    """
    if not is_nonempty_value_internal(string_with_list_labels):
        return "", []
    labels_list = create_list_from_string(string_with_list_labels, label_separator)
    list_name = ""
    nodes = []
    for lbl in labels_list:
        list_name, node_name = list_lookup.get_list_name_and_node_via_property(property_name, lbl)
        nodes.append(node_name)
    return list_name, nodes

escape_reserved_xml_characters

From richtext strings (encoding="xml"), escape the reserved characters <, > and &, but only if they are not part of a standard standoff tag or escape sequence.

See the documentation for the standard standoff tags allowed by DSP-API, which will not be escaped.

Parameters:

Name Type Description Default
text str

the richtext string to be escaped

required

Returns:

Type Description
str

The escaped richtext string

Examples:

result = xmllib.escape_reserved_xml_characters("Text <unknownTag>")
# result == "Text &lt;unknownTag&gt;"
result = xmllib.escape_reserved_xml_characters("Text <br/> text after")
# result == "Text <br/> text after"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
def escape_reserved_xml_characters(text: str) -> str:
    """
    From richtext strings (encoding="xml"), escape the reserved characters `<`, `>` and `&`,
    but only if they are not part of a standard standoff tag or escape sequence.

    [See the documentation for the standard standoff tags allowed by DSP-API,
    which will not be escaped.](https://docs.dasch.swiss/latest/DSP-API/03-endpoints/api-v2/text/standard-standoff/)

    Args:
        text: the richtext string to be escaped

    Returns:
        The escaped richtext string

    Examples:
        ```python
        result = xmllib.escape_reserved_xml_characters("Text <unknownTag>")
        # result == "Text &lt;unknownTag&gt;"
        ```

        ```python
        result = xmllib.escape_reserved_xml_characters("Text <br/> text after")
        # result == "Text <br/> text after"
        ```
    """
    allowed_tags_regex = "|".join(KNOWN_XML_TAGS)
    lookahead = rf"(?!/?({allowed_tags_regex})/?>)"
    illegal_lt = rf"<{lookahead}"
    lookbehind = rf"(?<!</?({allowed_tags_regex})/?)"
    illegal_gt = rf"{lookbehind}>"
    illegal_amp = r"&(?![#a-zA-Z0-9]+;)"
    text = regex.sub(illegal_lt, "&lt;", text)
    text = regex.sub(illegal_gt, "&gt;", text)
    text = regex.sub(illegal_amp, "&amp;", text)
    return text

find_date_in_string

Checks if a string contains a date value (single date, or date range), and returns the first found date as DSP-formatted string. Once a date/date range has been found, subsequent dates/date ranges are ignored. Returns None if no date was found. See XML documentation for details.

Notes
  • If no era or calendar is given, dates are interpreted in the Common Era and the Gregorian calendar.
  • Standalone numbers from 000-2999, in 3/4-digit form, are interpreted as years CE.
  • If a number (with any number of digits) is followed by CE, C.E., AD, A.D., it is interpreted as years CE.
  • If a number (with any number of digits) is followed by BCE, BC, B.C., B.C.E., av. J.-C., it is interpreted as years BCE.
  • Dates written with slashes are always interpreted in a European manner: 5/11/2021 is the 5th of November.
  • In the European notation, 2-digit years are expanded to 4 digits, with the current year as watershed:
    • 30.4.24 -> 30.04.2024
    • 30.4.50 -> 30.04.1950
Currently supported date formats
  • 0476-09-04 -> GREGORIAN:CE:0476-09-04:CE:0476-09-04
  • 0476_09_04 -> GREGORIAN:CE:0476-09-04:CE:0476-09-04
  • 30.4.2021 -> GREGORIAN:CE:2021-04-30:CE:2021-04-30
  • 30.4.21 -> GREGORIAN:CE:2021-04-30:CE:2021-04-30
  • 5/11/2021 -> GREGORIAN:CE:2021-11-05:CE:2021-11-05
  • Jan 26, 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
  • 26 Jan 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
  • 26 January 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
    1. Jan. 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
    1. Januar 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
  • 28.2.-1.12.1515 -> GREGORIAN:CE:1515-02-28:CE:1515-12-01
  • 25.-26.2.0800 -> GREGORIAN:CE:0800-02-25:CE:0800-02-26
  • 1.9.2022-3.1.2024 -> GREGORIAN:CE:2022-09-01:CE:2024-01-03
  • 1848 -> GREGORIAN:CE:1848:CE:1848
  • 1849/1850 -> GREGORIAN:CE:1849:CE:1850
  • 1849/50 -> GREGORIAN:CE:1849:CE:1850
  • 1845-50 -> GREGORIAN:CE:1845:CE:1850
  • 840-50 -> GREGORIAN:CE:840:CE:850
  • 840-1 -> GREGORIAN:CE:840:CE:841
  • 9 BC / 9 B.C. / 9 B.C.E. / 9 BCE -> GREGORIAN:BC:9:BC:9
  • 20 BCE - 50 CE -> GREGORIAN:BC:20:CE:50
  • 1000-900 av. J.-C. -> GREGORIAN:BC:1000:BC:900
  • 45 av. J.-C. -> GREGORIAN:BC:45:BC:45

Parameters:

Name Type Description Default
string str

string to check

required

Returns:

Type Description
str | None

DSP-formatted date string, or None

Examples:

result = xmllib.find_date_in_string("1849/1850")
# result == "GREGORIAN:CE:1849:CE:1850"
result = xmllib.find_date_in_string("not a valid date")
# result == None
result = xmllib.find_date_in_string("first date: 2024. Second is ignored: 2025.")
# result == "GREGORIAN:CE:2024:CE:2024"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
def find_date_in_string(string: str) -> str | None:
    """
    Checks if a string contains a date value (single date, or date range),
    and returns the first found date as DSP-formatted string.
    Once a date/date range has been found, subsequent dates/date ranges are ignored.
    Returns None if no date was found.
    [See XML documentation for details](https://docs.dasch.swiss/latest/DSP-TOOLS/file-formats/xml-data-file/#date).

    Notes:
        - If no era or calendar is given, dates are interpreted in the Common Era and the Gregorian calendar.
        - Standalone numbers from 000-2999, in 3/4-digit form, are interpreted as years CE.
        - If a number (with any number of digits) is followed by CE, C.E., AD, A.D., it is interpreted as years CE.
        - If a number (with any number of digits) is followed by BCE, BC, B.C., B.C.E., av. J.-C.,
          it is interpreted as years BCE.
        - Dates written with slashes are always interpreted in a European manner: 5/11/2021 is the 5th of November.
        - In the European notation, 2-digit years are expanded to 4 digits, with the current year as watershed:
            - 30.4.24 -> 30.04.2024
            - 30.4.50 -> 30.04.1950

    Currently supported date formats:
        - 0476-09-04 -> GREGORIAN:CE:0476-09-04:CE:0476-09-04
        - 0476_09_04 -> GREGORIAN:CE:0476-09-04:CE:0476-09-04
        - 30.4.2021 -> GREGORIAN:CE:2021-04-30:CE:2021-04-30
        - 30.4.21 -> GREGORIAN:CE:2021-04-30:CE:2021-04-30
        - 5/11/2021 -> GREGORIAN:CE:2021-11-05:CE:2021-11-05
        - Jan 26, 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
        - 26 Jan 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
        - 26 January 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
        - 26. Jan. 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
        - 26. Januar 1993 -> GREGORIAN:CE:1993-01-26:CE:1993-01-26
        - 28.2.-1.12.1515 -> GREGORIAN:CE:1515-02-28:CE:1515-12-01
        - 25.-26.2.0800 -> GREGORIAN:CE:0800-02-25:CE:0800-02-26
        - 1.9.2022-3.1.2024 -> GREGORIAN:CE:2022-09-01:CE:2024-01-03
        - 1848 -> GREGORIAN:CE:1848:CE:1848
        - 1849/1850 -> GREGORIAN:CE:1849:CE:1850
        - 1849/50 -> GREGORIAN:CE:1849:CE:1850
        - 1845-50 -> GREGORIAN:CE:1845:CE:1850
        - 840-50 -> GREGORIAN:CE:840:CE:850
        - 840-1 -> GREGORIAN:CE:840:CE:841
        - 9 BC / 9 B.C. / 9 B.C.E. / 9 BCE -> GREGORIAN:BC:9:BC:9
        - 20 BCE - 50 CE -> GREGORIAN:BC:20:CE:50
        - 1000-900 av. J.-C. -> GREGORIAN:BC:1000:BC:900
        - 45 av. J.-C. -> GREGORIAN:BC:45:BC:45

    Args:
        string: string to check

    Returns:
        DSP-formatted date string, or None

    Examples:
        ```python
        result = xmllib.find_date_in_string("1849/1850")
        # result == "GREGORIAN:CE:1849:CE:1850"
        ```

        ```python
        result = xmllib.find_date_in_string("not a valid date")
        # result == None
        ```

        ```python
        result = xmllib.find_date_in_string("first date: 2024. Second is ignored: 2025.")
        # result == "GREGORIAN:CE:2024:CE:2024"
        ```
    """

    # sanitise input, just in case that the method was called on an empty or N/A cell
    if not is_nonempty_value_internal(string):
        return None
    try:
        return _find_date_in_string_raising(string)
    except ValueError:
        return None

make_xsd_compatible_id

An xsd:ID may not contain all types of special characters, and it must start with a letter or underscore. Replace illegal characters with _, and prepend a leading _ if necessary.

The string must contain at least one Unicode letter (matching the regex \p{L}), _, !, ?, or number, but must not be None, <NA>, N/A, or -.

Parameters:

Name Type Description Default
input_value str | float | int

input value

required

Returns:

Type Description
str

An xsd ID compatible string based on the input value

Examples:

result = xmllib.make_xsd_compatible_id("0_Universität_Basel")
# result == "_0_Universit_t_Basel"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
def make_xsd_compatible_id(input_value: str | float | int) -> str:
    """
    An xsd:ID may not contain all types of special characters,
    and it must start with a letter or underscore.
    Replace illegal characters with `_`, and prepend a leading `_` if necessary.

    The string must contain at least one Unicode letter (matching the regex ``\\p{L}``),
    `_`, `!`, `?`, or number, but must not be `None`, `<NA>`, `N/A`, or `-`.

    Args:
        input_value: input value

    Raises:
        InputError: if the input cannot be transformed to an xsd:ID

    Returns:
        An xsd ID compatible string based on the input value

    Examples:
        ```python
        result = xmllib.make_xsd_compatible_id("0_Universität_Basel")
        # result == "_0_Universit_t_Basel"
        ```
    """
    if not is_nonempty_value_internal(input_value):
        raise InputError(f"The input '{input_value}' cannot be transformed to an xsd:ID")
    # if the start of string is neither letter nor underscore, add an underscore
    res = regex.sub(r"^(?=[^A-Za-z_])", "_", str(input_value))
    # replace all illegal characters by underscore
    res = regex.sub(r"[^\w_\-.]", "_", res, flags=regex.ASCII)
    return res

make_xsd_compatible_id_with_uuid

An xsd:ID may not contain all types of special characters, and it must start with a letter or underscore. Replace illegal characters with _, and prepend a leading _ if necessary. Additionally, add a UUID at the end. The UUID will be different each time the function is called.

The string must contain at least one Unicode letter (matching the regex \p{L}), _, !, ?, or number, but must not be None, <NA>, N/A, or -.

Parameters:

Name Type Description Default
input_value str | float | int

input value

required

Returns:

Type Description
str

an xsd ID based on the input value, with a UUID attached.

Examples:

result = xmllib.make_xsd_compatible_id_with_uuid("Universität_Basel")
# result == "Universit_t_Basel_88f5cd0b-f333-4174-9030-65900b17773d"
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
def make_xsd_compatible_id_with_uuid(input_value: str | float | int) -> str:
    """
    An xsd:ID may not contain all types of special characters,
    and it must start with a letter or underscore.
    Replace illegal characters with `_`, and prepend a leading `_` if necessary.
    Additionally, add a UUID at the end.
    The UUID will be different each time the function is called.

    The string must contain at least one Unicode letter (matching the regex ``\\p{L}``),
    `_`, `!`, `?`, or number, but must not be `None`, `<NA>`, `N/A`, or `-`.

    Args:
        input_value: input value

    Raises:
        InputError: if the input cannot be transformed to an xsd:ID

    Returns:
        an xsd ID based on the input value, with a UUID attached.

    Examples:
        ```python
        result = xmllib.make_xsd_compatible_id_with_uuid("Universität_Basel")
        # result == "Universit_t_Basel_88f5cd0b-f333-4174-9030-65900b17773d"
        ```
    """
    res = make_xsd_compatible_id(input_value)
    _uuid = uuid.uuid4()
    res = f"{res}_{_uuid}"
    return res

create_list_from_string

Creates a list from a string. Trailing and leading whitespaces are removed from the list items.

Parameters:

Name Type Description Default
string str

input string

required
separator str

The character that separates the different values in the string. For example, a comma or newline.

required

Returns:

Type Description
list[str]

The list that results from splitting the input string. If the original string is empty or consists only of whitespace characters, the resulting list will be empty.

Examples:

result = xmllib.create_non_empty_list_from_string(" One/  Two\n/", "/")
# result == ["One", "Two"]
result = xmllib.create_list_from_string("   \n    ", "\n")
# result == []
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
def create_list_from_string(string: str, separator: str) -> list[str]:
    """
    Creates a list from a string.
    Trailing and leading whitespaces are removed from the list items.

    Args:
        string: input string
        separator: The character that separates the different values in the string.
            For example, a comma or newline.

    Returns:
        The list that results from splitting the input string.
            If the original string is empty or consists only of whitespace characters, the resulting list will be empty.

    Raises:
        InputError: If the input value is not a string.

    Examples:
        ```python
        result = xmllib.create_non_empty_list_from_string(" One/  Two\\n/", "/")
        # result == ["One", "Two"]
        ```

        ```python
        result = xmllib.create_list_from_string("   \\n    ", "\\n")
        # result == []
        ```
    """
    if not isinstance(string, str):
        raise InputError(f"The input for this function must be a string. Your input is a {type(string).__name__}.")
    return [strpd for x in string.split(separator) if (strpd := x.strip())]

create_non_empty_list_from_string

Creates a list from a string. Trailing and leading whitespaces are removed from the list items.

If the resulting list is empty it will raise an InputError.

Parameters:

Name Type Description Default
string str

input string

required
separator str

The character that separates the different values in the string. For example, a comma or newline.

required
resource_id str | None

If the ID of the resource is provided, a better error message can be composed

None
prop_name str | None

If the name of the property is provided, a better error message can be composed

None

Returns:

Type Description
list[str]

The list that results from splitting the input string.

Examples:

result = xmllib.create_non_empty_list_from_string("One\nTwo   ", "\n")
# result == ["One", "Two"]
result = xmllib.create_non_empty_list_from_string("   \n/    ", "/")
# raises InputError
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/helpers.py
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
def create_non_empty_list_from_string(
    string: str, separator: str, resource_id: str | None = None, prop_name: str | None = None
) -> list[str]:
    """
    Creates a list from a string.
    Trailing and leading whitespaces are removed from the list items.

    If the resulting list is empty it will raise an `InputError`.

    Args:
        string: input string
        separator: The character that separates the different values in the string.
            For example, a comma or newline.
        resource_id: If the ID of the resource is provided, a better error message can be composed
        prop_name: If the name of the property is provided, a better error message can be composed

    Returns:
        The list that results from splitting the input string.

    Raises:
        InputError: If the resulting list is empty.

    Examples:
        ```python
        result = xmllib.create_non_empty_list_from_string("One\\nTwo   ", "\\n")
        # result == ["One", "Two"]
        ```

        ```python
        result = xmllib.create_non_empty_list_from_string("   \\n/    ", "/")
        # raises InputError
        ```
    """
    lst = create_list_from_string(string, separator)
    if len(lst) == 0:
        msg = "The input for this function must result in a non-empty list. Your input"
        details = []
        if resource_id:
            details.append(f"resource with the ID '{resource_id}'")
        if prop_name:
            details.append(f"property '{prop_name}'")
        details_msg = "for the " + " and ".join(details) + " " if details else ""
        msg += " " + details_msg + "results in an empty list."
        raise InputError(msg)
    return lst