sdc-gdr2fhir 4.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,201 @@
1
+ Apache License
2
+ Version 2.0, January 2004
3
+ http://www.apache.org/licenses/
4
+
5
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+ 1. Definitions.
8
+
9
+ "License" shall mean the terms and conditions for use, reproduction,
10
+ and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+ "Licensor" shall mean the copyright owner or entity authorized by
13
+ the copyright owner that is granting the License.
14
+
15
+ "Legal Entity" shall mean the union of the acting entity and all
16
+ other entities that control, are controlled by, or are under common
17
+ control with that entity. For the purposes of this definition,
18
+ "control" means (i) the power, direct or indirect, to cause the
19
+ direction or management of such entity, whether by contract or
20
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+ outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+ "You" (or "Your") shall mean an individual or Legal Entity
24
+ exercising permissions granted by this License.
25
+
26
+ "Source" form shall mean the preferred form for making modifications,
27
+ including but not limited to software source code, documentation
28
+ source, and configuration files.
29
+
30
+ "Object" form shall mean any form resulting from mechanical
31
+ transformation or translation of a Source form, including but
32
+ not limited to compiled object code, generated documentation,
33
+ and conversions to other media types.
34
+
35
+ "Work" shall mean the work of authorship, whether in Source or
36
+ Object form, made available under the License, as indicated by a
37
+ copyright notice that is included in or attached to the work
38
+ (an example is provided in the Appendix below).
39
+
40
+ "Derivative Works" shall mean any work, whether in Source or Object
41
+ form, that is based on (or derived from) the Work and for which the
42
+ editorial revisions, annotations, elaborations, or other modifications
43
+ represent, as a whole, an original work of authorship. For the purposes
44
+ of this License, Derivative Works shall not include works that remain
45
+ separable from, or merely link (or bind by name) to the interfaces of,
46
+ the Work and Derivative Works thereof.
47
+
48
+ "Contribution" shall mean any work of authorship, including
49
+ the original version of the Work and any modifications or additions
50
+ to that Work or Derivative Works thereof, that is intentionally
51
+ submitted to Licensor for inclusion in the Work by the copyright owner
52
+ or by an individual or Legal Entity authorized to submit on behalf of
53
+ the copyright owner. For the purposes of this definition, "submitted"
54
+ means any form of electronic, verbal, or written communication sent
55
+ to the Licensor or its representatives, including but not limited to
56
+ communication on electronic mailing lists, source code control systems,
57
+ and issue tracking systems that are managed by, or on behalf of, the
58
+ Licensor for the purpose of discussing and improving the Work, but
59
+ excluding communication that is conspicuously marked or otherwise
60
+ designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+ "Contributor" shall mean Licensor and any individual or Legal Entity
63
+ on behalf of whom a Contribution has been received by Licensor and
64
+ subsequently incorporated within the Work.
65
+
66
+ 2. Grant of Copyright License. Subject to the terms and conditions of
67
+ this License, each Contributor hereby grants to You a perpetual,
68
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+ copyright license to reproduce, prepare Derivative Works of,
70
+ publicly display, publicly perform, sublicense, and distribute the
71
+ Work and such Derivative Works in Source or Object form.
72
+
73
+ 3. Grant of Patent License. Subject to the terms and conditions of
74
+ this License, each Contributor hereby grants to You a perpetual,
75
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+ (except as stated in this section) patent license to make, have made,
77
+ use, offer to sell, sell, import, and otherwise transfer the Work,
78
+ where such license applies only to those patent claims licensable
79
+ by such Contributor that are necessarily infringed by their
80
+ Contribution(s) alone or by combination of their Contribution(s)
81
+ with the Work to which such Contribution(s) was submitted. If You
82
+ institute patent litigation against any entity (including a
83
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+ or a Contribution incorporated within the Work constitutes direct
85
+ or contributory patent infringement, then any patent licenses
86
+ granted to You under this License for that Work shall terminate
87
+ as of the date such litigation is filed.
88
+
89
+ 4. Redistribution. You may reproduce and distribute copies of the
90
+ Work or Derivative Works thereof in any medium, with or without
91
+ modifications, and in Source or Object form, provided that You
92
+ meet the following conditions:
93
+
94
+ (a) You must give any other recipients of the Work or
95
+ Derivative Works a copy of this License; and
96
+
97
+ (b) You must cause any modified files to carry prominent notices
98
+ stating that You changed the files; and
99
+
100
+ (c) You must retain, in the Source form of any Derivative Works
101
+ that You distribute, all copyright, patent, trademark, and
102
+ attribution notices from the Source form of the Work,
103
+ excluding those notices that do not pertain to any part of
104
+ the Derivative Works; and
105
+
106
+ (d) If the Work includes a "NOTICE" text file as part of its
107
+ distribution, then any Derivative Works that You distribute must
108
+ include a readable copy of the attribution notices contained
109
+ within such NOTICE file, excluding those notices that do not
110
+ pertain to any part of the Derivative Works, in at least one
111
+ of the following places: within a NOTICE text file distributed
112
+ as part of the Derivative Works; within the Source form or
113
+ documentation, if provided along with the Derivative Works; or,
114
+ within a display generated by the Derivative Works, if and
115
+ wherever such third-party notices normally appear. The contents
116
+ of the NOTICE file are for informational purposes only and
117
+ do not modify the License. You may add Your own attribution
118
+ notices within Derivative Works that You distribute, alongside
119
+ or as an addendum to the NOTICE text from the Work, provided
120
+ that such additional attribution notices cannot be construed
121
+ as modifying the License.
122
+
123
+ You may add Your own copyright statement to Your modifications and
124
+ may provide additional or different license terms and conditions
125
+ for use, reproduction, or distribution of Your modifications, or
126
+ for any such Derivative Works as a whole, provided Your use,
127
+ reproduction, and distribution of the Work otherwise complies with
128
+ the conditions stated in this License.
129
+
130
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
131
+ any Contribution intentionally submitted for inclusion in the Work
132
+ by You to the Licensor shall be under the terms and conditions of
133
+ this License, without any additional terms or conditions.
134
+ Notwithstanding the above, nothing herein shall supersede or modify
135
+ the terms of any separate license agreement you may have executed
136
+ with Licensor regarding such Contributions.
137
+
138
+ 6. Trademarks. This License does not grant permission to use the trade
139
+ names, trademarks, service marks, or product names of the Licensor,
140
+ except as required for reasonable and customary use in describing the
141
+ origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+ 7. Disclaimer of Warranty. Unless required by applicable law or
144
+ agreed to in writing, Licensor provides the Work (and each
145
+ Contributor provides its Contributions) on an "AS IS" BASIS,
146
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+ implied, including, without limitation, any warranties or conditions
148
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+ PARTICULAR PURPOSE. You are solely responsible for determining the
150
+ appropriateness of using or redistributing the Work and assume any
151
+ risks associated with Your exercise of permissions under this License.
152
+
153
+ 8. Limitation of Liability. In no event and under no legal theory,
154
+ whether in tort (including negligence), contract, or otherwise,
155
+ unless required by applicable law (such as deliberate and grossly
156
+ negligent acts) or agreed to in writing, shall any Contributor be
157
+ liable to You for damages, including any direct, indirect, special,
158
+ incidental, or consequential damages of any character arising as a
159
+ result of this License or out of the use or inability to use the
160
+ Work (including but not limited to damages for loss of goodwill,
161
+ work stoppage, computer failure or malfunction, or any and all
162
+ other commercial damages or losses), even if such Contributor
163
+ has been advised of the possibility of such damages.
164
+
165
+ 9. Accepting Warranty or Additional Liability. While redistributing
166
+ the Work or Derivative Works thereof, You may choose to offer,
167
+ and charge a fee for, acceptance of support, warranty, indemnity,
168
+ or other liability obligations and/or rights consistent with this
169
+ License. However, in accepting such obligations, You may act only
170
+ on Your own behalf and on Your sole responsibility, not on behalf
171
+ of any other Contributor, and only if You agree to indemnify,
172
+ defend, and hold each Contributor harmless for any liability
173
+ incurred by, or claims asserted against, such Contributor by reason
174
+ of your accepting any such warranty or additional liability.
175
+
176
+ END OF TERMS AND CONDITIONS
177
+
178
+ APPENDIX: How to apply the Apache License to your work.
179
+
180
+ To apply the Apache License to your work, attach the following
181
+ boilerplate notice, with the fields enclosed by brackets "[]"
182
+ replaced with your own identifying information. (Don't include
183
+ the brackets!) The text should be enclosed in the appropriate
184
+ comment syntax for the file format. We also recommend that a
185
+ file or class name and description of purpose be included on the
186
+ same "printed page" as the copyright notice for easier
187
+ identification within third-party archives.
188
+
189
+ Copyright [yyyy] [name of copyright owner]
190
+
191
+ Licensed under the Apache License, Version 2.0 (the "License");
192
+ you may not use this file except in compliance with the License.
193
+ You may obtain a copy of the License at
194
+
195
+ http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+ Unless required by applicable law or agreed to in writing, software
198
+ distributed under the License is distributed on an "AS IS" BASIS,
199
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+ See the License for the specific language governing permissions and
201
+ limitations under the License.
@@ -0,0 +1,16 @@
1
+ Copyright 2026 Axius SDC, Inc.
2
+
3
+ Licensed under the Apache License, Version 2.0.
4
+
5
+ src/sdc_gdr2fhir/schemas/fhir.schema.json is the JSON schema published with HL7 FHIR Release 4 (4.0.1),
6
+ http://hl7.org/fhir/R4/fhir.schema.json.zip, unmodified. The FHIR specification is © HL7 and licensed under Creative
7
+ Commons "No Rights Reserved" (CC0); HL7®, HEALTH LEVEL SEVEN®, FHIR® and the FHIR® flame logo are trademarks owned by
8
+ Health Level Seven International, registered with the United States Patent and Trademark Office. This package does
9
+ not claim that HL7 or any of its members endorses it.
10
+
11
+ The package ships no terminology content. LOINC, SNOMED CT, ICD-10-CM and NCI Thesaurus codes appear in its output, its
12
+ mapping files and its tests only as the published models bind them and the records carry them.
13
+
14
+ The test fixtures under samples/ are the published packages of the NHANES Participant and NHANES Medication models of
15
+ the FAIR Data Demo (https://github.com/SemanticDataCharter/FAIR_Data_Demo, Apache 2.0) and a seeded sample of 200
16
+ records of each, generated by that project from the CDC's NHANES 2017-2018 public release.
@@ -0,0 +1,139 @@
1
+ Metadata-Version: 2.4
2
+ Name: sdc-gdr2fhir
3
+ Version: 4.0.0
4
+ Summary: Governed Data Records as HL7 FHIR R4 Bundles, through sdc-mapper: one mapping file per model, every value reported, Exceptional Values preserved.
5
+ Author: Axius SDC, Inc.
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Repository, https://github.com/SemanticDataCharter/sdc-gdr2fhir
8
+ Keywords: sdc,semantic data charter,governed data record,fhir,hl7,r4,mapping,null flavor
9
+ Classifier: Programming Language :: Python :: 3
10
+ Requires-Python: >=3.12
11
+ Description-Content-Type: text/markdown
12
+ License-File: LICENSE
13
+ License-File: NOTICE
14
+ Requires-Dist: sdc-mapper<5,>=4.2
15
+ Requires-Dist: jsonschema>=4.20
16
+ Provides-Extra: dev
17
+ Requires-Dist: pytest>=8.0; extra == "dev"
18
+ Requires-Dist: pyyaml>=6.0; extra == "dev"
19
+ Requires-Dist: lxml>=5.0; extra == "dev"
20
+ Dynamic: license-file
21
+
22
+ # sdc-gdr2fhir
23
+
24
+ Governed Data Records as HL7 FHIR R4 Bundles. A target mapper for
25
+ [sdc-mapper](https://github.com/SemanticDataCharter/sdc-mapper): the core validates the record, resolves every value
26
+ against its model and reports each one; this package says which FHIR resource and element each value goes in and
27
+ writes the Bundle. Outbound only. Apache 2.0.
28
+
29
+ **Status:** 4.0.0 in development. Models so far, from the FAIR Data Demo:
30
+
31
+ | Model | ct_id | Resources | Rules |
32
+ |---|---|---|---|
33
+ | NHANES Participant | `xy8upneajsb8vdcmnve01g6g` | Patient, Observation, QuestionnaireResponse | 112 |
34
+ | NHANES Medication | `epbdfmvxc3gbh5f66hhb3o2m` | Patient, MedicationStatement, QuestionnaireResponse | 18 |
35
+
36
+ ## Use
37
+
38
+ ```python
39
+ from sdc_mapper import Engine, load_mapping
40
+ from sdc_gdr2fhir import FHIRMapper, mapping_path
41
+
42
+ result = Engine().map_record(xml, FHIRMapper(), load_mapping(mapping_path("xy8upneajsb8vdcmnve01g6g")))
43
+ result.files["Bundle.json"] # a FHIR R4 Bundle of type collection
44
+ result.report # every value: lookup, declared or not representable; every Exceptional Value
45
+ ```
46
+
47
+ Through sdc-mapper's CLI and MCP server the mapper is the target `fhir`.
48
+
49
+ ## The target
50
+
51
+ **HL7 FHIR Release 4 (4.0.1)**, JSON. The specification is © HL7 and licensed under Creative Commons "No Rights
52
+ Reserved" (CC0); its terms allow redistribution and implementation-related products, so long as no one claims HL7's
53
+ endorsement and no altered specification is published as FHIR. HL7® and FHIR® are HL7's trademarks. This package
54
+ carries the FHIR R4 JSON schema unmodified (see `NOTICE`) and ships no terminology: LOINC, SNOMED CT, ICD-10-CM and NCI
55
+ Thesaurus codes appear only as the models bind them and the records carry them.
56
+
57
+ Every Bundle this package writes is valid against the FHIR R4 JSON schema, resource by resource and as a Bundle, or is
58
+ not written. The schema checks structure, types, required members and code patterns; it does not check FHIR's
59
+ invariants or terminology bindings. `tests/` runs the HL7 FHIR validator (`validator_cli.jar`) too, where Java and the
60
+ validator are installed (`FHIR_VALIDATOR_JAR`); it has not been run for this version.
61
+
62
+ ## Where values go
63
+
64
+ Each record is one Bundle of type `collection`, identified by the record's instance id
65
+ (`https://semanticdatacharter.com/ns/sdc4/instance`). Entry ids and `urn:uuid` fullUrls are derived from the instance
66
+ id, so the same record gives the same bytes.
67
+
68
+ - **Patient**: the respondent sequence number as an identifier, and the administrative gender.
69
+ - **Observation**: each blood pressure reading (the vital signs blood pressure panel, LOINC 85354-9, with systolic and
70
+ diastolic as components, body site and status), the heart rate and each laboratory result, with the LOINC code the
71
+ model binds and UCUM units; smoking status, with the model's LOINC code and the answer's LOINC answer code; each
72
+ chronic condition indicator, with the SNOMED CT concept the model names as its subject and the Yes or No answer's
73
+ LOINC answer code. A condition indicator is the answer to "has a doctor ever told you", so it is an Observation of
74
+ the answer, not a Condition.
75
+ - **MedicationStatement**: the NHANES generic drug code and name, the ICD-10-CM reasons, and the status from "taken in
76
+ the past month" (Yes is active, No not-taken).
77
+ - **QuestionnaireResponse**: every other survey answer, an item each, linkId the component's identifier and text its
78
+ label; a Coding where the model binds each of the answer's values to its own code, else the answer as recorded.
79
+
80
+ **Lookup or declared.** Where the model binds the code FHIR needs (a laboratory result's LOINC code, a condition's
81
+ SNOMED CT subject, an answer's LOINC answer code, an administrative gender, an observation status), the code written
82
+ is the model's own and the value is a **lookup**; `tools/build_mapping.py` copies those bindings from the model into
83
+ the mapping file, and the mapper checks at run time that the code it writes is one the model binds. Which resource and
84
+ element a value goes in is **declared**, one mapping file per model.
85
+
86
+ For the 200 sample records of each model:
87
+
88
+ | Model | lookup | declared | not representable |
89
+ |---|---|---|---|
90
+ | NHANES Participant | 9,093 (65.8% of the data values) | 4,733 | 5,400 (provenance and audit) |
91
+ | NHANES Medication | 0 | 1,591 (100% of the data values) | 5,400 (provenance and audit) |
92
+
93
+ The medication model binds its ICD-10-CM and drug code components to their code systems, not each value to a code,
94
+ so its codes are written as the record holds them: declared.
95
+
96
+ ## Exceptional Values: every one preserved
97
+
98
+ FHIR is the target that can say what an Exceptional Value says. Where the data-absent-reason code system
99
+ (`http://terminology.hl7.org/CodeSystem/data-absent-reason`) has the concept, an Observation's (or component's) value
100
+ is replaced by `dataAbsentReason`, and any other element carries the data-absent-reason extension. The null flavors
101
+ data-absent-reason has no concept for are written exactly from v3 NullFlavor
102
+ (`http://terminology.hl7.org/CodeSystem/v3-NullFlavor`), as the `iso21090-nullFlavor` extension on the element or a v3
103
+ NullFlavor coding of `dataAbsentReason` (whose binding is extensible). v3 NullFlavor has no Asked and Refused;
104
+ data-absent-reason does.
105
+
106
+ | ISO 21090 | Written as | Class |
107
+ |---|---|---|
108
+ | UNK | data-absent-reason `unknown` | preserved |
109
+ | ASKU | data-absent-reason `asked-unknown` | preserved |
110
+ | NAV | data-absent-reason `temp-unknown` | preserved |
111
+ | NASK | data-absent-reason `not-asked` | preserved |
112
+ | ASKR | data-absent-reason `asked-declined` | preserved |
113
+ | MSK | data-absent-reason `masked` | preserved |
114
+ | NA | data-absent-reason `not-applicable` | preserved |
115
+ | NINF | data-absent-reason `negative-infinity` | preserved |
116
+ | PINF | data-absent-reason `positive-infinity` | preserved |
117
+ | NI, INV, DER, OTH, UNC, QS, TRC | v3 NullFlavor, the same code | preserved |
118
+
119
+ A mapping file cannot change this table.
120
+
121
+ ## What FHIR cannot hold here
122
+
123
+ - **The record's provenance and audit.** FHIR's Provenance and AuditEvent require a recorded instant with a time
124
+ zone, and the FAIR Data Demo records' times carry none; the PROV and audit values are reported as not representable,
125
+ with that reason.
126
+ - **Times without a time zone.** FHIR's dateTime requires a time zone with a time; an observation's date and time is
127
+ written as its date.
128
+ - Validity windows and recording times (act, vtb, vte, tr), and the definitions each component is bound to beyond the
129
+ codes written.
130
+
131
+ ## Tests
132
+
133
+ ```
134
+ pip install -e ".[dev]"
135
+ python -m pytest
136
+ ```
137
+
138
+ Every sample record is mapped and each resource validated against the FHIR R4 JSON schema; Bundles are byte-stable;
139
+ lookups, Exceptional Values and refused mappings are exercised.
@@ -0,0 +1,118 @@
1
+ # sdc-gdr2fhir
2
+
3
+ Governed Data Records as HL7 FHIR R4 Bundles. A target mapper for
4
+ [sdc-mapper](https://github.com/SemanticDataCharter/sdc-mapper): the core validates the record, resolves every value
5
+ against its model and reports each one; this package says which FHIR resource and element each value goes in and
6
+ writes the Bundle. Outbound only. Apache 2.0.
7
+
8
+ **Status:** 4.0.0 in development. Models so far, from the FAIR Data Demo:
9
+
10
+ | Model | ct_id | Resources | Rules |
11
+ |---|---|---|---|
12
+ | NHANES Participant | `xy8upneajsb8vdcmnve01g6g` | Patient, Observation, QuestionnaireResponse | 112 |
13
+ | NHANES Medication | `epbdfmvxc3gbh5f66hhb3o2m` | Patient, MedicationStatement, QuestionnaireResponse | 18 |
14
+
15
+ ## Use
16
+
17
+ ```python
18
+ from sdc_mapper import Engine, load_mapping
19
+ from sdc_gdr2fhir import FHIRMapper, mapping_path
20
+
21
+ result = Engine().map_record(xml, FHIRMapper(), load_mapping(mapping_path("xy8upneajsb8vdcmnve01g6g")))
22
+ result.files["Bundle.json"] # a FHIR R4 Bundle of type collection
23
+ result.report # every value: lookup, declared or not representable; every Exceptional Value
24
+ ```
25
+
26
+ Through sdc-mapper's CLI and MCP server the mapper is the target `fhir`.
27
+
28
+ ## The target
29
+
30
+ **HL7 FHIR Release 4 (4.0.1)**, JSON. The specification is © HL7 and licensed under Creative Commons "No Rights
31
+ Reserved" (CC0); its terms allow redistribution and implementation-related products, so long as no one claims HL7's
32
+ endorsement and no altered specification is published as FHIR. HL7® and FHIR® are HL7's trademarks. This package
33
+ carries the FHIR R4 JSON schema unmodified (see `NOTICE`) and ships no terminology: LOINC, SNOMED CT, ICD-10-CM and NCI
34
+ Thesaurus codes appear only as the models bind them and the records carry them.
35
+
36
+ Every Bundle this package writes is valid against the FHIR R4 JSON schema, resource by resource and as a Bundle, or is
37
+ not written. The schema checks structure, types, required members and code patterns; it does not check FHIR's
38
+ invariants or terminology bindings. `tests/` runs the HL7 FHIR validator (`validator_cli.jar`) too, where Java and the
39
+ validator are installed (`FHIR_VALIDATOR_JAR`); it has not been run for this version.
40
+
41
+ ## Where values go
42
+
43
+ Each record is one Bundle of type `collection`, identified by the record's instance id
44
+ (`https://semanticdatacharter.com/ns/sdc4/instance`). Entry ids and `urn:uuid` fullUrls are derived from the instance
45
+ id, so the same record gives the same bytes.
46
+
47
+ - **Patient**: the respondent sequence number as an identifier, and the administrative gender.
48
+ - **Observation**: each blood pressure reading (the vital signs blood pressure panel, LOINC 85354-9, with systolic and
49
+ diastolic as components, body site and status), the heart rate and each laboratory result, with the LOINC code the
50
+ model binds and UCUM units; smoking status, with the model's LOINC code and the answer's LOINC answer code; each
51
+ chronic condition indicator, with the SNOMED CT concept the model names as its subject and the Yes or No answer's
52
+ LOINC answer code. A condition indicator is the answer to "has a doctor ever told you", so it is an Observation of
53
+ the answer, not a Condition.
54
+ - **MedicationStatement**: the NHANES generic drug code and name, the ICD-10-CM reasons, and the status from "taken in
55
+ the past month" (Yes is active, No not-taken).
56
+ - **QuestionnaireResponse**: every other survey answer, an item each, linkId the component's identifier and text its
57
+ label; a Coding where the model binds each of the answer's values to its own code, else the answer as recorded.
58
+
59
+ **Lookup or declared.** Where the model binds the code FHIR needs (a laboratory result's LOINC code, a condition's
60
+ SNOMED CT subject, an answer's LOINC answer code, an administrative gender, an observation status), the code written
61
+ is the model's own and the value is a **lookup**; `tools/build_mapping.py` copies those bindings from the model into
62
+ the mapping file, and the mapper checks at run time that the code it writes is one the model binds. Which resource and
63
+ element a value goes in is **declared**, one mapping file per model.
64
+
65
+ For the 200 sample records of each model:
66
+
67
+ | Model | lookup | declared | not representable |
68
+ |---|---|---|---|
69
+ | NHANES Participant | 9,093 (65.8% of the data values) | 4,733 | 5,400 (provenance and audit) |
70
+ | NHANES Medication | 0 | 1,591 (100% of the data values) | 5,400 (provenance and audit) |
71
+
72
+ The medication model binds its ICD-10-CM and drug code components to their code systems, not each value to a code,
73
+ so its codes are written as the record holds them: declared.
74
+
75
+ ## Exceptional Values: every one preserved
76
+
77
+ FHIR is the target that can say what an Exceptional Value says. Where the data-absent-reason code system
78
+ (`http://terminology.hl7.org/CodeSystem/data-absent-reason`) has the concept, an Observation's (or component's) value
79
+ is replaced by `dataAbsentReason`, and any other element carries the data-absent-reason extension. The null flavors
80
+ data-absent-reason has no concept for are written exactly from v3 NullFlavor
81
+ (`http://terminology.hl7.org/CodeSystem/v3-NullFlavor`), as the `iso21090-nullFlavor` extension on the element or a v3
82
+ NullFlavor coding of `dataAbsentReason` (whose binding is extensible). v3 NullFlavor has no Asked and Refused;
83
+ data-absent-reason does.
84
+
85
+ | ISO 21090 | Written as | Class |
86
+ |---|---|---|
87
+ | UNK | data-absent-reason `unknown` | preserved |
88
+ | ASKU | data-absent-reason `asked-unknown` | preserved |
89
+ | NAV | data-absent-reason `temp-unknown` | preserved |
90
+ | NASK | data-absent-reason `not-asked` | preserved |
91
+ | ASKR | data-absent-reason `asked-declined` | preserved |
92
+ | MSK | data-absent-reason `masked` | preserved |
93
+ | NA | data-absent-reason `not-applicable` | preserved |
94
+ | NINF | data-absent-reason `negative-infinity` | preserved |
95
+ | PINF | data-absent-reason `positive-infinity` | preserved |
96
+ | NI, INV, DER, OTH, UNC, QS, TRC | v3 NullFlavor, the same code | preserved |
97
+
98
+ A mapping file cannot change this table.
99
+
100
+ ## What FHIR cannot hold here
101
+
102
+ - **The record's provenance and audit.** FHIR's Provenance and AuditEvent require a recorded instant with a time
103
+ zone, and the FAIR Data Demo records' times carry none; the PROV and audit values are reported as not representable,
104
+ with that reason.
105
+ - **Times without a time zone.** FHIR's dateTime requires a time zone with a time; an observation's date and time is
106
+ written as its date.
107
+ - Validity windows and recording times (act, vtb, vte, tr), and the definitions each component is bound to beyond the
108
+ codes written.
109
+
110
+ ## Tests
111
+
112
+ ```
113
+ pip install -e ".[dev]"
114
+ python -m pytest
115
+ ```
116
+
117
+ Every sample record is mapped and each resource validated against the FHIR R4 JSON schema; Bundles are byte-stable;
118
+ lookups, Exceptional Values and refused mappings are exercised.
@@ -0,0 +1,40 @@
1
+ [build-system]
2
+ requires = ["setuptools>=77"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "sdc-gdr2fhir"
7
+ version = "4.0.0"
8
+ description = "Governed Data Records as HL7 FHIR R4 Bundles, through sdc-mapper: one mapping file per model, every value reported, Exceptional Values preserved."
9
+ readme = "README.md"
10
+ requires-python = ">=3.12"
11
+ license = "Apache-2.0"
12
+ license-files = ["LICENSE", "NOTICE"]
13
+ authors = [{ name = "Axius SDC, Inc." }]
14
+ keywords = ["sdc", "semantic data charter", "governed data record", "fhir", "hl7", "r4", "mapping", "null flavor"]
15
+ classifiers = [
16
+ "Programming Language :: Python :: 3",
17
+ ]
18
+ dependencies = [
19
+ "sdc-mapper>=4.2,<5", # placements, '=name' joins, declared cluster order (4.2.0)
20
+ "jsonschema>=4.20", # the FHIR R4 JSON schema (draft-06)
21
+ ]
22
+
23
+ [project.optional-dependencies]
24
+ dev = ["pytest>=8.0", "pyyaml>=6.0", "lxml>=5.0"]
25
+
26
+ [project.entry-points."sdc_mapper.targets"]
27
+ fhir = "sdc_gdr2fhir:FHIRMapper"
28
+
29
+ [project.urls]
30
+ Repository = "https://github.com/SemanticDataCharter/sdc-gdr2fhir"
31
+
32
+ [tool.setuptools.packages.find]
33
+ where = ["src"]
34
+
35
+ [tool.setuptools.package-data]
36
+ sdc_gdr2fhir = ["mappings/*.yaml", "schemas/*.json"]
37
+
38
+ [tool.pytest.ini_options]
39
+ testpaths = ["tests"]
40
+ markers = ["validator: needs Java and the HL7 FHIR validator jar"]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,26 @@
1
+ """sdc-gdr2fhir: Governed Data Records as HL7 FHIR R4 Bundles, through sdc-mapper.
2
+
3
+ from sdc_mapper import Engine, load_mapping
4
+ from sdc_gdr2fhir import FHIRMapper, mapping_path
5
+ result = Engine().map_record(xml, FHIRMapper(), load_mapping(mapping_path("xy8upneajsb8vdcmnve01g6g")))
6
+
7
+ One mapping file per model, in `mappings/`. Registered with sdc-mapper as the target `fhir`.
8
+ """
9
+ from pathlib import Path
10
+
11
+ __version__ = "4.0.0"
12
+
13
+ MAPPINGS = Path(__file__).with_name("mappings")
14
+
15
+
16
+ def mapping_path(ct_id: str) -> Path:
17
+ """The mapping file this package publishes for a model, by the model's identifier."""
18
+ found = sorted(MAPPINGS.glob(f"*-{ct_id}.yaml"))
19
+ if not found:
20
+ raise FileNotFoundError(f"sdc-gdr2fhir has no mapping for model {ct_id}")
21
+ return found[-1]
22
+
23
+
24
+ from .mapper import FHIRMapper # noqa: E402
25
+
26
+ __all__ = ["FHIRMapper", "mapping_path", "MAPPINGS", "__version__"]
@@ -0,0 +1,70 @@
1
+ """Codes as FHIR writes them: an IRI the model binds a value to, as a (system, code) pair FHIR's Coding takes.
2
+
3
+ A model binds an enumerated value to its definition (`rdfs:isDefinedBy`) and a component to concepts (`skos:exactMatch`,
4
+ `dcterms:subject`). Where such an IRI names one concept of a code system FHIR knows, the pair below is that concept as a
5
+ FHIR Coding; an IRI that names a whole system, or a page that defines a variable rather than one answer, gives none.
6
+ """
7
+ from __future__ import annotations
8
+
9
+ import re
10
+
11
+ LOINC = "http://loinc.org"
12
+ SNOMED = "http://snomed.info/sct"
13
+ NCIT = "http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl"
14
+ UCUM = "http://unitsofmeasure.org"
15
+
16
+ _PATTERNS = [
17
+ (re.compile(r"^https?://loinc\.org/((?:LA|LP|LG)?[0-9]+-[0-9])/?$"), LOINC),
18
+ (re.compile(r"^https?://snomed\.info/id/([0-9]+)$"), SNOMED),
19
+ (re.compile(r"^https?://purl\.obolibrary\.org/obo/NCIT_(C[0-9]+)$"), NCIT),
20
+ ]
21
+ _FRAGMENT = re.compile(r"^(https?://(?:hl7\.org/fhir|terminology\.hl7\.org/CodeSystem)/[A-Za-z0-9./-]+)#([^#\s]+)$")
22
+
23
+
24
+ def coding(iri: str | None) -> tuple[str, str] | None:
25
+ """The (system, code) an IRI names, or None."""
26
+ if not iri:
27
+ return None
28
+ for pattern, system in _PATTERNS:
29
+ m = pattern.match(iri)
30
+ if m:
31
+ return system, m.group(1)
32
+ m = _FRAGMENT.match(iri)
33
+ if m:
34
+ return m.group(1), m.group(2)
35
+ return None
36
+
37
+
38
+ def bound_codes(value) -> set[str]:
39
+ """Every code the model binds a resolved value to: its enumeration value's definition, and the component's
40
+ exact matches and subjects. A target code that is one of these comes from the model: a lookup."""
41
+ iris = []
42
+ if value.code and value.code.defined_by:
43
+ iris.append(value.code.defined_by)
44
+ for predicate, targets in (value.links or {}).items():
45
+ if predicate.endswith(("#exactMatch", "/subject")):
46
+ iris.extend(targets)
47
+ return {c[1] for c in map(coding, iris) if c}
48
+
49
+
50
+ #: The Default library's unit symbols that are not already UCUM codes.
51
+ UCUM_CODES = {"mmHg": "mm[Hg]"}
52
+
53
+ #: ISO 21090 null flavors as FHIR R4 writes them. Where the data-absent-reason code system has the same concept, it is
54
+ #: written (as Observation.dataAbsentReason, or the data-absent-reason extension on any other element); every other
55
+ #: code is written exactly, from v3 NullFlavor, with the iso21090-nullFlavor extension (or as a v3 NullFlavor coding of
56
+ #: dataAbsentReason, whose binding is extensible). v3 NullFlavor has no Asked and Refused; data-absent-reason does.
57
+ DATA_ABSENT_REASON = "http://terminology.hl7.org/CodeSystem/data-absent-reason"
58
+ V3_NULL_FLAVOR = "http://terminology.hl7.org/CodeSystem/v3-NullFlavor"
59
+ DAR_EXTENSION = "http://hl7.org/fhir/StructureDefinition/data-absent-reason"
60
+ NULL_FLAVOR_EXTENSION = "http://hl7.org/fhir/StructureDefinition/iso21090-nullFlavor"
61
+ DAR = {"UNK": "unknown", "ASKU": "asked-unknown", "NAV": "temp-unknown", "NASK": "not-asked", "ASKR": "asked-declined",
62
+ "MSK": "masked", "NA": "not-applicable", "NINF": "negative-infinity", "PINF": "positive-infinity"}
63
+ V3_ONLY = ("NI", "INV", "DER", "OTH", "UNC", "QS", "TRC")
64
+
65
+
66
+ def absent(code: str) -> tuple[str, str, str]:
67
+ """(code system, code, extension url) FHIR writes for an ISO 21090 code."""
68
+ if code in DAR:
69
+ return DATA_ABSENT_REASON, DAR[code], DAR_EXTENSION
70
+ return V3_NULL_FLAVOR, code, NULL_FLAVOR_EXTENSION