Skip to content

XMLRoot

Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
 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
 76
 77
 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
115
116
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
148
149
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
181
182
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
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
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
@dataclass
class XMLRoot:
    shortcode: str
    default_ontology: str
    resources: list[AnyResource] = field(default_factory=list)
    apply_default_resource_authorship: tuple[str, ...] | ResourceAuthorshipDefault | None = None
    _res_id_to_type_lookup: dict[str, list[str]] = field(default_factory=dict)

    @staticmethod
    def create_new(
        shortcode: str,
        default_ontology: str,
        apply_default_resource_authorship: list[str] | ResourceAuthorshipDefault | None = None,
    ) -> XMLRoot:
        """
        Create a new XML root, for one file.

        Args:
            shortcode: project shortcode
            default_ontology: name of the default ontology
            apply_default_resource_authorship: optional default authorship for the resource records,
                applied to every resource that does not set its own authorship with `Resource.create_new`.
                Provide either a list of author names, or `xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT`
                to apply the project's `default_data_authorship` which is resolved against the server
                during the `xmlupload`.
                This is distinct from the project's `default_data_authorship`: setting it here actually
                writes the authorship onto the resources, whereas the project field is only a default
                that is never applied to uploaded data on its own.

        Returns:
            Instance of `XMLRoot`

        Examples:
            ```python
            root = xmllib.XMLRoot.create_new(
                shortcode="0000",
                default_ontology="onto"
            )
            ```

            ```python
            # apply a literal default authorship to all resources without their own
            root = xmllib.XMLRoot.create_new(
                shortcode="0000",
                default_ontology="onto",
                apply_default_resource_authorship=["Daisy Duck"],
            )
            ```

            ```python
            # apply the project's `default_data_authorship`, resolved at xmlupload
            root = xmllib.XMLRoot.create_new(
                shortcode="0000",
                default_ontology="onto",
                apply_default_resource_authorship=xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT,
            )
            ```
        """
        default_authorship = check_and_fix_default_resource_authorship_input(apply_default_resource_authorship)
        return XMLRoot(
            shortcode=shortcode,
            default_ontology=default_ontology,
            apply_default_resource_authorship=default_authorship,
        )

    def add_resource(self, resource: AnyResource) -> XMLRoot:
        """
        Add one resource to the root.

        Args:
            resource: any one of:
                    `Resource`,
                    `RegionResource`,
                    `LinkResource`,
                    `VideoSegmentResource`,
                    `AudioSegmentResource`

        Returns:
            The original XMLRoot, with the added resource

        Warning:
            If the ID of the new resource is already used.

        Examples:
            ```python
            resource = xmllib.Resource.create_new(
                res_id="ID", restype=":ResourceType", label="label"
            )

            root = root.add_resource(resource)
            ```
        """
        if isinstance(resource, Resource):
            res_type = resource.restype
        else:
            res_type = resource.__class__.__name__
        if types_used := self._res_id_to_type_lookup.get(resource.res_id):
            existing_types = [f"'{x}'" for x in types_used]
            msg = (
                f"The ID for this resource of type '{res_type}' "
                f"is already used by resource(s) of the following type(s): {', '.join(existing_types)}."
            )
            info_msg = MessageInfo(
                message=msg,
                resource_id=resource.res_id,
                field="Resource ID",
            )
            emit_xmllib_input_warning(info_msg)
            self._res_id_to_type_lookup[resource.res_id].append(res_type)
        else:
            self._res_id_to_type_lookup[resource.res_id] = [res_type]
        self.resources.append(resource)
        return self

    def add_resource_multiple(self, resources: Collection[AnyResource]) -> XMLRoot:
        """
        Add a list of resources to the root.

        Args:
            resources: a list of:
                    `Resource`,
                    `RegionResource`,
                    `LinkResource`,
                    `VideoSegmentResource`,
                    `AudioSegmentResource`
                    The types of the resources may be mixed.

        Returns:
            The original XMLRoot, with the added resource

        Warning:
            If the ID of the new resource is already used.

        Examples:
            ```python
            resource_1 = xmllib.Resource.create_new(
                res_id="ID_1", restype=":ResourceType", label="label 1"
            )
            resource_2 = xmllib.Resource.create_new(
                res_id="ID_2", restype=":ResourceType", label="label 2"
            )

            root = root.add_resource_multiple([resource_1, resource_2])
            ```
        """
        for res in resources:
            self.add_resource(res)
        return self

    def add_resource_optional(self, resource: AnyResource | None) -> XMLRoot:
        """
        If the resource is not None, add it to the XMLRoot, otherwise return the XMLRoot unchanged.

        Args:
            resource: any one of:
                    `Resource`,
                    `RegionResource`,
                    `LinkResource`,
                    `VideoSegmentResource`,
                    `AudioSegmentResource`

        Returns:
            The original XMLRoot, with the added value if it was not empty. Else the unchanged original XMLRoot.

        Warning:
            If the ID of the new resource is already used.

        Examples:
            ```python
            resource = xmllib.Resource.create_new(
                res_id="ID", restype=":ResourceType", label="label"
            )

            root = root.add_resource_optional(resource)
            ```

            ```python
            root = root.add_resource_optional(None)
            ```
        """
        if resource:
            self.add_resource(resource)
        return self

    def write_file(self, filepath: str | Path, default_permissions: Permissions | None = None) -> None:
        """
        Write the finished XML to a file.

        Args:
            filepath: where to save the file
            default_permissions: This parameter is deprecated and has no effect.
                Default permissions can be set in the JSON project file.

        Warning:
            if the XML is not valid according to the schema

        Examples:
            ```python
            root.write_file("xml_file_name.xml")
            ```
        """

        if default_permissions:
            msg = (
                "You added a default permission. This has no effect. This functionality is deprecated, "
                "because project wide default permissions are set in the JSON project file. "
                "This parameter will be removed soon."
            )
            warnings.warn(DspToolsFutureWarning(msg))

        root = self.serialise()

        # The logging is only configured when using the CLI entry point.
        # If this is not disabled, then the statements will also be printed out on the terminal.
        logger.disable("dsp_tools")
        validate_root_emit_user_message(root, Path(filepath).parent)

        etree.indent(root, space="    ")
        xml_string = etree.tostring(
            root,
            encoding="unicode",
            pretty_print=True,
            doctype='<?xml version="1.0" encoding="UTF-8"?>',
        )
        with open(filepath, "w", encoding="utf-8") as f:
            f.write(xml_string)
            print(f"The XML file was successfully saved to {filepath}.")
        if file_path := os.getenv("XMLLIB_WARNINGS_CSV_SAVEPATH"):
            df = pd.read_csv(file_path)
            if len(df) > 0:
                msg = f"{len(df)} warnings occurred, please consult '{file_path}' for details."
                print(BOLD_RED, msg, RESET_TO_DEFAULT)
            else:
                msg = "No warnings occurred during the runtime."
                print(BOLD_GREEN, msg, RESET_TO_DEFAULT)

    def serialise(self) -> etree._Element:
        """
        Create an `lxml.etree._Element` with the information in the root.
        If you wish to create a file, we recommend using the `write_file` method instead.

        Returns:
            The `XMLRoot` serialised as XML
        """
        root = self._make_root()
        root.extend(self._get_permissions())
        literal_default = self._literal_default_authorship()
        author_lookup = _make_authorship_lookup(self.resources, literal_default)
        authorship = _serialise_authorship(author_lookup.lookup)
        root.extend(authorship)
        serialised_resources = serialise_resources(self.resources, author_lookup, literal_default)
        root.extend(serialised_resources)
        return root

    def _literal_default_authorship(self) -> tuple[str, ...] | None:
        if isinstance(self.apply_default_resource_authorship, tuple):
            return self.apply_default_resource_authorship
        return None

    def _get_permissions(self) -> list[etree._Element]:
        contains_old_permissions, contains_new_permissions = self._find_permission_types()
        if contains_old_permissions:
            msg = (
                "Your data contains old permissions. Please migrate to the new ones:\n"
                " - Permissions.OPEN            -> use Permissions.PUBLIC instead\n"
                " - Permissions.RESTRICTED      -> use Permissions.PRIVATE instead\n"
                " - Permissions.RESTRICTED_VIEW -> use Permissions.LIMITED_VIEW instead\n"
            )
            warnings.warn(msg, category=DspToolsFutureWarning)
        return XMLPermissions().serialise(contains_old_permissions, contains_new_permissions)

    def _find_permission_types(self) -> tuple[bool, bool]:
        contains_old_permissions = False
        contains_new_permissions = False
        for res in self.resources:
            if self._is_old(res.permissions):
                contains_old_permissions = True
            elif self._is_new(res.permissions):
                contains_new_permissions = True
            for val in res.values:
                if self._is_old(val.permissions):
                    contains_old_permissions = True
                elif self._is_new(val.permissions):
                    contains_new_permissions = True
            if isinstance(res, Resource):
                if res.file_value:
                    if self._is_old(res.file_value.metadata.permissions):
                        contains_old_permissions = True
                    elif self._is_new(res.file_value.metadata.permissions):
                        contains_new_permissions = True
            if contains_old_permissions and contains_new_permissions:
                # no need to continue, the end result won't change any more
                return True, True
        return contains_old_permissions, contains_new_permissions

    def _is_old(self, perm: Permissions) -> bool:
        return perm in [Permissions.OPEN, Permissions.RESTRICTED_VIEW, Permissions.RESTRICTED]

    def _is_new(self, perm: Permissions) -> bool:
        return perm in [Permissions.PUBLIC, Permissions.LIMITED_VIEW, Permissions.PRIVATE]

    def _make_root(self) -> etree._Element:
        schema_url = (
            "https://raw.githubusercontent.com/dasch-swiss/dsp-tools/main/src/dsp_tools/resources/schema/data.xsd"
        )
        schema_location_key = str(etree.QName("http://www.w3.org/2001/XMLSchema-instance", "schemaLocation"))
        schema_location_value = f"https://dasch.swiss/schema {schema_url}"
        attrib = {
            schema_location_key: schema_location_value,
            "shortcode": self.shortcode,
            "default-ontology": self.default_ontology,
        }
        if self.apply_default_resource_authorship is ResourceAuthorshipDefault.PROJECT_DEFAULT:
            attrib["use-project-default-resource-authorship"] = "true"
        return etree.Element(
            f"{DASCH_SCHEMA}knora",
            attrib=attrib,
            nsmap=XML_NAMESPACE_MAP,
        )

create_new

Create a new XML root, for one file.

Parameters:

Name Type Description Default
shortcode str

project shortcode

 required
default_ontology str

name of the default ontology

 required
apply_default_resource_authorship list[str] | ResourceAuthorshipDefault | None

optional default authorship for the resource records, applied to every resource that does not set its own authorship with Resource.create_new. Provide either a list of author names, or xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT to apply the project's default_data_authorship which is resolved against the server during the xmlupload. This is distinct from the project's default_data_authorship: setting it here actually writes the authorship onto the resources, whereas the project field is only a default that is never applied to uploaded data on its own.

 None

Returns:

Type Description
XMLRoot

Instance of XMLRoot

Examples:

root = xmllib.XMLRoot.create_new(
    shortcode="0000",
    default_ontology="onto"
)

# apply a literal default authorship to all resources without their own
root = xmllib.XMLRoot.create_new(
    shortcode="0000",
    default_ontology="onto",
    apply_default_resource_authorship=["Daisy Duck"],
)

# apply the project's `default_data_authorship`, resolved at xmlupload
root = xmllib.XMLRoot.create_new(
    shortcode="0000",
    default_ontology="onto",
    apply_default_resource_authorship=xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT,
)
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
 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
 76
 77
 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
@staticmethod
def create_new(
    shortcode: str,
    default_ontology: str,
    apply_default_resource_authorship: list[str] | ResourceAuthorshipDefault | None = None,
) -> XMLRoot:
    """
    Create a new XML root, for one file.

    Args:
        shortcode: project shortcode
        default_ontology: name of the default ontology
        apply_default_resource_authorship: optional default authorship for the resource records,
            applied to every resource that does not set its own authorship with `Resource.create_new`.
            Provide either a list of author names, or `xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT`
            to apply the project's `default_data_authorship` which is resolved against the server
            during the `xmlupload`.
            This is distinct from the project's `default_data_authorship`: setting it here actually
            writes the authorship onto the resources, whereas the project field is only a default
            that is never applied to uploaded data on its own.

    Returns:
        Instance of `XMLRoot`

    Examples:
        ```python
        root = xmllib.XMLRoot.create_new(
            shortcode="0000",
            default_ontology="onto"
        )
        ```

        ```python
        # apply a literal default authorship to all resources without their own
        root = xmllib.XMLRoot.create_new(
            shortcode="0000",
            default_ontology="onto",
            apply_default_resource_authorship=["Daisy Duck"],
        )
        ```

        ```python
        # apply the project's `default_data_authorship`, resolved at xmlupload
        root = xmllib.XMLRoot.create_new(
            shortcode="0000",
            default_ontology="onto",
            apply_default_resource_authorship=xmllib.ResourceAuthorshipDefault.PROJECT_DEFAULT,
        )
        ```
    """
    default_authorship = check_and_fix_default_resource_authorship_input(apply_default_resource_authorship)
    return XMLRoot(
        shortcode=shortcode,
        default_ontology=default_ontology,
        apply_default_resource_authorship=default_authorship,
    )

add_resource

Add one resource to the root.

Parameters:

Name Type Description Default
resource AnyResource

any one of: Resource, RegionResource, LinkResource, VideoSegmentResource, AudioSegmentResource

 required

Returns:

Type Description
XMLRoot

The original XMLRoot, with the added resource
Warning

If the ID of the new resource is already used.

Examples:

resource = xmllib.Resource.create_new(
    res_id="ID", restype=":ResourceType", label="label"
)

root = root.add_resource(resource)
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
108
109
110
111
112
113
114
115
116
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
148
149
150
151
152
153
154
155
def add_resource(self, resource: AnyResource) -> XMLRoot:
    """
    Add one resource to the root.

    Args:
        resource: any one of:
                `Resource`,
                `RegionResource`,
                `LinkResource`,
                `VideoSegmentResource`,
                `AudioSegmentResource`

    Returns:
        The original XMLRoot, with the added resource

    Warning:
        If the ID of the new resource is already used.

    Examples:
        ```python
        resource = xmllib.Resource.create_new(
            res_id="ID", restype=":ResourceType", label="label"
        )

        root = root.add_resource(resource)
        ```
    """
    if isinstance(resource, Resource):
        res_type = resource.restype
    else:
        res_type = resource.__class__.__name__
    if types_used := self._res_id_to_type_lookup.get(resource.res_id):
        existing_types = [f"'{x}'" for x in types_used]
        msg = (
            f"The ID for this resource of type '{res_type}' "
            f"is already used by resource(s) of the following type(s): {', '.join(existing_types)}."
        )
        info_msg = MessageInfo(
            message=msg,
            resource_id=resource.res_id,
            field="Resource ID",
        )
        emit_xmllib_input_warning(info_msg)
        self._res_id_to_type_lookup[resource.res_id].append(res_type)
    else:
        self._res_id_to_type_lookup[resource.res_id] = [res_type]
    self.resources.append(resource)
    return self

add_resource_multiple

Add a list of resources to the root.

Parameters:

Name Type Description Default
resources Collection[AnyResource]

a list of: Resource, RegionResource, LinkResource, VideoSegmentResource, AudioSegmentResource The types of the resources may be mixed.

 required

Returns:

Type Description
XMLRoot

The original XMLRoot, with the added resource
Warning

If the ID of the new resource is already used.

Examples:

resource_1 = xmllib.Resource.create_new(
    res_id="ID_1", restype=":ResourceType", label="label 1"
)
resource_2 = xmllib.Resource.create_new(
    res_id="ID_2", restype=":ResourceType", label="label 2"
)

root = root.add_resource_multiple([resource_1, resource_2])
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
def add_resource_multiple(self, resources: Collection[AnyResource]) -> XMLRoot:
    """
    Add a list of resources to the root.

    Args:
        resources: a list of:
                `Resource`,
                `RegionResource`,
                `LinkResource`,
                `VideoSegmentResource`,
                `AudioSegmentResource`
                The types of the resources may be mixed.

    Returns:
        The original XMLRoot, with the added resource

    Warning:
        If the ID of the new resource is already used.

    Examples:
        ```python
        resource_1 = xmllib.Resource.create_new(
            res_id="ID_1", restype=":ResourceType", label="label 1"
        )
        resource_2 = xmllib.Resource.create_new(
            res_id="ID_2", restype=":ResourceType", label="label 2"
        )

        root = root.add_resource_multiple([resource_1, resource_2])
        ```
    """
    for res in resources:
        self.add_resource(res)
    return self

add_resource_optional

If the resource is not None, add it to the XMLRoot, otherwise return the XMLRoot unchanged.

Parameters:

Name Type Description Default
resource AnyResource | None

any one of: Resource, RegionResource, LinkResource, VideoSegmentResource, AudioSegmentResource

 required

Returns:

Type Description
XMLRoot

The original XMLRoot, with the added value if it was not empty. Else the unchanged original XMLRoot.
Warning

If the ID of the new resource is already used.

Examples:

resource = xmllib.Resource.create_new(
    res_id="ID", restype=":ResourceType", label="label"
)

root = root.add_resource_optional(resource)

root = root.add_resource_optional(None)
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
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
def add_resource_optional(self, resource: AnyResource | None) -> XMLRoot:
    """
    If the resource is not None, add it to the XMLRoot, otherwise return the XMLRoot unchanged.

    Args:
        resource: any one of:
                `Resource`,
                `RegionResource`,
                `LinkResource`,
                `VideoSegmentResource`,
                `AudioSegmentResource`

    Returns:
        The original XMLRoot, with the added value if it was not empty. Else the unchanged original XMLRoot.

    Warning:
        If the ID of the new resource is already used.

    Examples:
        ```python
        resource = xmllib.Resource.create_new(
            res_id="ID", restype=":ResourceType", label="label"
        )

        root = root.add_resource_optional(resource)
        ```

        ```python
        root = root.add_resource_optional(None)
        ```
    """
    if resource:
        self.add_resource(resource)
    return self

write_file

Write the finished XML to a file.

Parameters:

Name Type Description Default
filepath str | Path

where to save the file

 required
default_permissions Permissions | None

This parameter is deprecated and has no effect. Default permissions can be set in the JSON project file.

 None
Warning

if the XML is not valid according to the schema

Examples:

root.write_file("xml_file_name.xml")
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
def write_file(self, filepath: str | Path, default_permissions: Permissions | None = None) -> None:
    """
    Write the finished XML to a file.

    Args:
        filepath: where to save the file
        default_permissions: This parameter is deprecated and has no effect.
            Default permissions can be set in the JSON project file.

    Warning:
        if the XML is not valid according to the schema

    Examples:
        ```python
        root.write_file("xml_file_name.xml")
        ```
    """

    if default_permissions:
        msg = (
            "You added a default permission. This has no effect. This functionality is deprecated, "
            "because project wide default permissions are set in the JSON project file. "
            "This parameter will be removed soon."
        )
        warnings.warn(DspToolsFutureWarning(msg))

    root = self.serialise()

    # The logging is only configured when using the CLI entry point.
    # If this is not disabled, then the statements will also be printed out on the terminal.
    logger.disable("dsp_tools")
    validate_root_emit_user_message(root, Path(filepath).parent)

    etree.indent(root, space="    ")
    xml_string = etree.tostring(
        root,
        encoding="unicode",
        pretty_print=True,
        doctype='<?xml version="1.0" encoding="UTF-8"?>',
    )
    with open(filepath, "w", encoding="utf-8") as f:
        f.write(xml_string)
        print(f"The XML file was successfully saved to {filepath}.")
    if file_path := os.getenv("XMLLIB_WARNINGS_CSV_SAVEPATH"):
        df = pd.read_csv(file_path)
        if len(df) > 0:
            msg = f"{len(df)} warnings occurred, please consult '{file_path}' for details."
            print(BOLD_RED, msg, RESET_TO_DEFAULT)
        else:
            msg = "No warnings occurred during the runtime."
            print(BOLD_GREEN, msg, RESET_TO_DEFAULT)

serialise

Create an lxml.etree._Element with the information in the root. If you wish to create a file, we recommend using the write_file method instead.

Returns:

Type Description
_Element

The XMLRoot serialised as XML
Source code in dsp/dsp-tools/src/dsp_tools/xmllib/models/root.py 
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
def serialise(self) -> etree._Element:
    """
    Create an `lxml.etree._Element` with the information in the root.
    If you wish to create a file, we recommend using the `write_file` method instead.

    Returns:
        The `XMLRoot` serialised as XML
    """
    root = self._make_root()
    root.extend(self._get_permissions())
    literal_default = self._literal_default_authorship()
    author_lookup = _make_authorship_lookup(self.resources, literal_default)
    authorship = _serialise_authorship(author_lookup.lookup)
    root.extend(authorship)
    serialised_resources = serialise_resources(self.resources, author_lookup, literal_default)
    root.extend(serialised_resources)
    return root