ogc-na 0.3.55__py3-none-any.whl → 0.3.57__py3-none-any.whl

ogc/na/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.3.55'
-__version_tuple__ = version_tuple = (0, 3, 55)
+__version__ = version = '0.3.57'
+__version_tuple__ = version_tuple = (0, 3, 57)

ogc/na/annotate_schema.py

@@ -123,6 +123,7 @@ import json
 import logging
 import re
 import sys
+from collections import deque
 from operator import attrgetter
 from pathlib import Path
 from typing import Any, AnyStr, Callable, Sequence, Iterable
@@ -177,6 +178,7 @@ class ReferencedSchema:
     chain: list = dataclasses.field(default_factory=list)
     ref: str | Path = None
     is_json: bool = False
+    anchors: dict[str, Any] = dataclasses.field(default_factory=dict)
 
 
 @dataclasses.dataclass
@@ -192,8 +194,27 @@ class SchemaResolver:
         self._schema_cache: dict[str | Path, Any] = {}
 
     @staticmethod
-    def _get_branch(schema: dict, ref: str):
-        return jsonpointer.resolve_pointer(schema, re.sub('^#', '', ref))
+    def _get_branch(schema: dict, ref: str, anchors: dict[str, Any] = None):
+        ref = re.sub('^#', '', ref)
+        if anchors and ref in anchors:
+            return anchors[ref]
+        return jsonpointer.resolve_pointer(schema, ref)
+
+    @staticmethod
+    def _find_anchors(schema: dict) -> dict[str, Any]:
+        anchors = {}
+
+        pending = deque((schema,))
+        while pending:
+            current = pending.popleft()
+            if isinstance(current, dict):
+                if '$anchor' in current:
+                    anchors[current['$anchor']] = current
+                pending.extend(current.values())
+            elif isinstance(current, list):
+                pending.extend(current)
+
+        return anchors
 
     def load_contents(self, s: str | Path) -> tuple[dict, bool]:
         """
@@ -252,11 +273,13 @@ class SchemaResolver:
                     raise ValueError('Local ref provided without an anchor: ' + ref)
                 return ReferencedSchema(location=from_schema.location,
                                         fragment=ref[1:],
-                                        subschema=SchemaResolver._get_branch(from_schema.full_contents, ref),
+                                        subschema=SchemaResolver._get_branch(from_schema.full_contents, ref,
+                                                                             from_schema.anchors),
                                         full_contents=from_schema.full_contents,
                                         chain=chain,
                                         ref=ref,
-                                        is_json=from_schema.is_json)
+                                        is_json=from_schema.is_json,
+                                        anchors=from_schema.anchors)
 
             if force_contents:
                 is_json = False
@@ -269,20 +292,23 @@ class SchemaResolver:
                     contents = force_contents
             else:
                 contents, is_json = self.load_contents(schema_source)
+            anchors = SchemaResolver._find_anchors(contents)
             if fragment:
                 return ReferencedSchema(location=schema_source, fragment=fragment,
-                                        subschema=SchemaResolver._get_branch(contents, fragment),
+                                        subschema=SchemaResolver._get_branch(contents, fragment, anchors),
                                         full_contents=contents,
                                         chain=chain,
                                         ref=ref,
-                                        is_json=is_json)
+                                        is_json=is_json,
+                                        anchors=anchors)
             else:
                 return ReferencedSchema(location=schema_source,
                                         subschema=contents,
                                         full_contents=contents,
                                         chain=chain,
                                         ref=ref,
-                                        is_json=is_json)
+                                        is_json=is_json,
+                                        anchors=anchors)
         except Exception as e:
             f = f" from {from_schema.location}" if from_schema else ''
             raise IOError(f"Error resolving reference {ref}{f}") from e
@@ -522,7 +548,7 @@ class SchemaAnnotator:
                         if vocab and ':' not in prop_ctx and prop_ctx not in JSON_LD_KEYWORDS:
                             prop_ctx = f"{vocab}{prop_ctx}"
                         return {'@id': prop_ctx}
-                    elif '@id' not in prop_ctx and not vocab:
+                    elif '@id' not in prop_ctx and '@reverse' not in prop_ctx and not vocab:
                         raise ValueError(f'Missing @id for property {prop} in context {json.dumps(ctx, indent=2)}')
                     else:
                         result = {k: v for k, v in prop_ctx.items() if k in JSON_LD_KEYWORDS}
@@ -751,10 +777,11 @@ class ContextBuilder:
                             self._missed_properties[full_property_path_str] = False
                         prop_context['@' + term[len(ANNOTATION_PREFIX):]] = term_val
 
-                if isinstance(prop_context.get('@id'), str):
-                    self.visited_properties[full_property_path_str] = prop_context['@id']
+                if isinstance(prop_context.get('@id'), str) or isinstance(prop_context.get('@reverse'), str):
+                    prop_id_value = prop_context.get('@id', prop_context.get('@reverse'))
+                    self.visited_properties[full_property_path_str] = prop_id_value
                     self._missed_properties[full_property_path_str] = False
-                    if prop_context['@id'] in ('@nest', '@graph'):
+                    if prop_id_value in ('@nest', '@graph'):
                         merge_contexts(onto_context, process_subschema(prop_val, from_schema, full_property_path))
                     else:
                         merge_contexts(prop_context['@context'],

ogc/na/input_filters/xlsx.py

@@ -0,0 +1,87 @@
+"""
+Excel (XLSX) Input filter for ingest_json.
+
+Processes Excel XLSX files with [openpyxl](https://openpyxl.readthedocs.io/en/stable/).
+
+Configuration values:
+
+* `worksheet` (default: `None`): The name of the worksheet to process. If `None`, the default one will be used.
+* `rows` (default: `dict`): type of elements in the result list:
+    * `dict`: elements will be dictionaries, with the keys taken from the `header-row`.
+    * `list`: each resulting row will be an array values.
+* `header-row` (default: `0`): if `rows` is `dict`, the (0-based) index of the header row. All rows before the
+    header row will be skipped.
+* `skip-rows` (default: `0`): number of rows to skip at the beginning of the file (apart from the header and pre-header
+    ones if `rows` is `dict`).
+* `skip-empty-rows` (default: `True`): whether to omit empty rows (i.e., those with no values) from the result.
+"""
+from __future__ import annotations
+
+from datetime import datetime
+from io import BytesIO
+from typing import Any
+from openpyxl import load_workbook
+from openpyxl.cell import Cell
+
+from ogc.na import util
+
+DEFAULT_CONF = {
+    'worksheet': None,
+    'rows': 'dict',
+    'header-row': 0,
+    'skip-rows': 0,
+    'skip-empty-rows': True,
+}
+
+
+def _cell_to_json(c: Cell) -> str | float | int | None:
+    if isinstance(c.value, datetime):
+        return c.value.isoformat()
+    return c.value
+
+
+def apply_filter(content: bytes, conf: dict[str, Any] | None) -> tuple[dict[str, Any] | list, dict[str, Any] | None]:
+    conf = util.deep_update(DEFAULT_CONF, conf) if conf else DEFAULT_CONF
+
+    metadata = {
+        'filter': {
+            'conf': conf,
+        },
+    }
+
+    wb = load_workbook(filename=BytesIO(content), read_only=True)
+    if conf['worksheet']:
+        ws = wb[conf['worksheet']]
+    else:
+        ws = wb.worksheets[0]
+    rows = ws.rows
+    metadata['worksheet'] = ws.title
+
+    headers = None
+    if conf['rows'] == 'dict':
+        header_row = max(conf['header-row'], 0)
+        # Skip to header row
+        for i in range(header_row):
+            next(rows, None)
+        headers = next(rows, [])
+        if not headers:
+            return [], None
+        else:
+            headers = [_cell_to_json(c) for c in headers]
+        metadata['headers'] = headers
+
+    for i in range(conf['skip-rows']):
+        next(rows, None)
+
+    result = []
+    for row in rows:
+        row_values = [_cell_to_json(c) for c in row]
+        if conf['skip-empty-rows'] and not any(c is not None for c in row_values):
+            # skip empty rows
+            continue
+        if conf['rows'] == 'list':
+            result.append(row_values)
+        else:
+            result.append(dict(zip(headers, row_values)))
+
+    return result, metadata

{ogc_na-0.3.55.dist-info → ogc_na-0.3.57.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: ogc_na
-Version: 0.3.55
+Version: 0.3.57
 Summary: OGC Naming Authority tools
 Author-email: Rob Atkinson <ratkinson@ogc.org>, Piotr Zaborowski <pzaborowski@ogc.org>, Alejandro Villar <avillar@ogc.org>
 Project-URL: Homepage, https://github.com/opengeospatial/ogc-na-tools/
@@ -13,33 +13,34 @@ Classifier: Topic :: Utilities
 Classifier: Topic :: Software Development :: Libraries
 Requires-Python: >=3.7
 Description-Content-Type: text/markdown
-Requires-Dist: pyshacl >=0.19
-Requires-Dist: rdflib >=6.3.0
+Requires-Dist: pyshacl>=0.19
+Requires-Dist: rdflib>=6.3.0
 Requires-Dist: html5lib
 Requires-Dist: jq
 Requires-Dist: jsonpath-ng
 Requires-Dist: PyYAML
 Requires-Dist: wcmatch
-Requires-Dist: requests >=2.30
+Requires-Dist: requests>=2.30
 Requires-Dist: jsonschema
-Requires-Dist: GitPython >=3.1.32
+Requires-Dist: GitPython>=3.1.32
 Requires-Dist: rfc3987
 Requires-Dist: requests-cache
 Requires-Dist: xmltodict
-Requires-Dist: jsonpointer ~=2.4
+Requires-Dist: jsonpointer~=2.4
+Requires-Dist: openpyxl~=3.1.5
 Requires-Dist: setuptools
 Provides-Extra: dev
-Requires-Dist: mkdocs >=1.4.2 ; extra == 'dev'
-Requires-Dist: mkdocs-autorefs ; extra == 'dev'
-Requires-Dist: mkdocs-gen-files ; extra == 'dev'
-Requires-Dist: mkdocs-literate-nav ; extra == 'dev'
-Requires-Dist: mkdocs-material ; extra == 'dev'
-Requires-Dist: mkdocs-material-extensions ; extra == 'dev'
-Requires-Dist: mkdocs-pymdownx-material-extras ; extra == 'dev'
-Requires-Dist: mkdocs-section-index ; extra == 'dev'
-Requires-Dist: mkdocstrings ; extra == 'dev'
-Requires-Dist: mkdocstrings-python ; extra == 'dev'
-Requires-Dist: mkdocs-markdownextradata-plugin ; extra == 'dev'
+Requires-Dist: mkdocs>=1.4.2; extra == "dev"
+Requires-Dist: mkdocs-autorefs; extra == "dev"
+Requires-Dist: mkdocs-gen-files; extra == "dev"
+Requires-Dist: mkdocs-literate-nav; extra == "dev"
+Requires-Dist: mkdocs-material; extra == "dev"
+Requires-Dist: mkdocs-material-extensions; extra == "dev"
+Requires-Dist: mkdocs-pymdownx-material-extras; extra == "dev"
+Requires-Dist: mkdocs-section-index; extra == "dev"
+Requires-Dist: mkdocstrings; extra == "dev"
+Requires-Dist: mkdocstrings-python; extra == "dev"
+Requires-Dist: mkdocs-markdownextradata-plugin; extra == "dev"
 
 # ogc-na-tools
 

{ogc_na-0.3.55.dist-info → ogc_na-0.3.57.dist-info}/RECORD

@@ -1,6 +1,6 @@
 ogc/na/__init__.py,sha256=uzcNiJ3uKFNJ1HBfKxIwgAy2HMUFsLAe5RkrUg8ncac,464
-ogc/na/_version.py,sha256=vA6gPTjPSdC1gxj6eZa79wc5Se9JVwdnhpHXCsZkLbU,413
-ogc/na/annotate_schema.py,sha256=cjKZPKNOEUSghcQH9qCOiE2-Evr0VFyYMN2NkUMz5wo,42647
+ogc/na/_version.py,sha256=KqIVwYBdIdahVzuj89W2dfY5Y-ewSsfE6L9PQnp8tPw,413
+ogc/na/annotate_schema.py,sha256=YtxL9pOeeVk9CubvnByUMh7nZUJYZCDQ60hXEvtiR6g,43869
 ogc/na/domain_config.py,sha256=ORzITa1rTrD1MQdpWYrIVW5SwSa9lJd3hnyHIxNgiIU,13947
 ogc/na/download.py,sha256=2afrLyl4WsAlxkCgXsl47fs9mNKfDmhVpeT2iwNSoq0,3354
 ogc/na/exceptions.py,sha256=cwvnq79ih90T9lfwJww0zOx_QwuICaUvlo3Mc8m8ouA,85
@@ -14,8 +14,9 @@ ogc/na/util.py,sha256=Ztju3g1YuguUDbk4n2RJfCrl_IIzNAj7linfy24T6VA,12067
 ogc/na/validation.py,sha256=5xjHH55NZKM8HtUk8XgVzm8W5ZlZY00u_qsWfXK_8dM,3732
 ogc/na/input_filters/__init__.py,sha256=AhE7n_yECwxFKwOM3Jc0ft96TtF5i_Z-fHrS4HYOjaE,1179
 ogc/na/input_filters/csv.py,sha256=nFfB1XQF_QApcGGzMqEvzD_b3pBtCtsfUECsZ9UGE6s,2616
+ogc/na/input_filters/xlsx.py,sha256=X9EpFgC9WwHQD8iUJRGdaDYfgiLKjXPdhTVhDmNPAQ0,2730
 ogc/na/input_filters/xml.py,sha256=9qYjp_w5JLInFM48zB15IYH9eTafjp1Aqd_8kfuW3aA,2074
-ogc_na-0.3.55.dist-info/METADATA,sha256=FPql5ZiyEyfGR0_tSciYAakCV0BkLfWdHJMmzPZaJME,3829
-ogc_na-0.3.55.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-ogc_na-0.3.55.dist-info/top_level.txt,sha256=Kvy3KhzcIhNPT4_nZuJCmS946ptRr_MDyU4IIhZJhCY,4
-ogc_na-0.3.55.dist-info/RECORD,,
+ogc_na-0.3.57.dist-info/METADATA,sha256=dcn9t_MBayKk9qKGfH5an7jKwcCpmK8QtDovmc5Ljmw,3843
+ogc_na-0.3.57.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ogc_na-0.3.57.dist-info/top_level.txt,sha256=Kvy3KhzcIhNPT4_nZuJCmS946ptRr_MDyU4IIhZJhCY,4
+ogc_na-0.3.57.dist-info/RECORD,,

{ogc_na-0.3.55.dist-info → ogc_na-0.3.57.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any