vdi2770 0.1.0__tar.gz

vdi2770-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Wooyong Lee (dev365code)
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

vdi2770-0.1.0/MANIFEST.in

@@ -0,0 +1,5 @@
+# setuptools ships the package source by default and nothing else. The tests
+# are the reason to trust the package, so they travel with it.
+include LICENSE README.md
+recursive-include tests *.py
+recursive-include src *.py py.typed

vdi2770-0.1.0/PKG-INFO

@@ -0,0 +1,128 @@
+Metadata-Version: 2.4
+Name: vdi2770
+Version: 0.1.0
+Summary: Read a VDI 2770 handover-documentation container safely — no dependencies, no disk, no network
+Author: Wooyong Lee
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/dev365code/vdi2770-validate/tree/main/packages/vdi2770
+Project-URL: Source, https://github.com/dev365code/vdi2770-validate
+Project-URL: Issues, https://github.com/dev365code/vdi2770-validate/issues
+Keywords: vdi2770,technical documentation,handover documentation,industry 4.0,zip
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Manufacturing
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Text Processing :: Markup :: XML
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: pytest==8.3.4; extra == "dev"
+Requires-Dist: ruff==0.16.3; extra == "dev"
+Dynamic: license-file
+
+# vdi2770
+
+Read a VDI 2770 handover-documentation container and get back a typed model —
+without extracting anything to disk, without opening a socket, and without any
+dependencies.
+
+```bash
+pip install vdi2770
+```
+
+```python
+import vdi2770
+
+box = vdi2770.read_container_file("handover.zip")
+for c in box.walk():
+    if c.metadata_bytes is None:
+        continue
+    doc = vdi2770.build_document(vdi2770.parse_xml(c.metadata_bytes), c.where)
+    print(c.path, doc.ids, [k.class_id for k in doc.classifications])
+```
+
+```
+handover.zip ('DOC-2024-0001',) ['03-01']
+handover.zip!/pumps.zip ('DOC-2024-0002',) ['02-04']
+```
+
+## It decides nothing
+
+There is no `is_valid()` here, on purpose. Whether a container is *correct* is a
+question about VDI 2770, and the answer depends on which supplement your customer
+sent you. This library tells you what is in the file and where it is written; the
+opinion is yours to supply.
+
+If you want an opinion supplied for you, [`vdi2770-validate`](https://pypi.org/project/vdi2770-validate/)
+is this library plus a rule set, as a command-line tool.
+
+## Three properties, each tested rather than promised
+
+**Nothing is extracted to disk.** Members are decompressed into memory under a
+budget and dropped. There is no temporary directory to clean up and no path
+traversal to get wrong, because no path is ever joined.
+
+**Nothing is fetched.** No socket is opened for any input, ever — including XML
+that asks for one. An entity declaration is refused outright rather than
+resolved-but-locally, so there is no parser setting to get wrong later.
+
+**A refusal is reported, not raised.** A member that blows a budget becomes a
+`Defect` on the container and the read continues, so one hostile file inside a
+supplier archive does not cost you the other four hundred.
+
+## What comes back
+
+`read_container(data, name)` returns a `Container`:
+
+| | |
+|---|---|
+| `path` | `handover.zip!/pumps.zip` — the JAR convention, so it stays greppable |
+| `kind` | `DOCUMENTATION`, `DOCUMENT`, `UNKNOWN`, or `UNREADABLE` |
+| `members`, `file_names` | what is in the archive, after the budget filter |
+| `metadata_bytes`, `metadata_name` | the metadata that was found, if any |
+| `children`, `walk()` | inner containers, opened to three levels |
+| `defects` | what the reader could not do, and why |
+| `rejected` | members present in the archive but refused, and why |
+| `near_misses` | `vdi2770_metadata.xml` in an archive that has no metadata — the name is case-sensitive, and silence about that is unkind |
+| `duplicate_names` | a ZIP may carry the same name twice; readers disagree about which one wins |
+
+`build_document(node, where)` returns a `Document` whose every node carries a
+`Location` with the line and column it was written at, which is the reason this
+package parses XML itself instead of handing you an `ElementTree`.
+
+`read_pdf(data)` returns four facts and no verdict: `is_pdf`, `header`,
+`encrypted`, and `pdfa_claim` — the last being what the file's own metadata
+*claims*, such as `"2b"`. Nothing here verifies that claim. Verifying PDF/A takes
+a PDF/A validator, and this is not one.
+
+### Defect kinds
+
+`not-a-zip`, `too-many-members`, `unsafe-member-name`, `member-too-large`,
+`suspicious-compression`, `archive-too-large`, `metadata-too-large`,
+`metadata-unreadable`, `member-unreadable`, `nesting-too-deep`.
+
+These strings are part of the public surface; a test in this package fails if the
+code grows a kind that this list does not name.
+
+## Supported
+
+Python 3.9 and up. The budgets — member count, member size, total size,
+compression ratio, metadata size, nesting depth — are module constants in
+`vdi2770.zipread`, so you can read them, and they are deliberately not
+arguments, so a caller cannot turn them off by accident.
+
+## Unofficial
+
+Not affiliated with, endorsed by, or connected to VDI, the Digital Data Chain
+Consortium, or IDTA. VDI 2770 is a guideline published by the Verein Deutscher
+Ingenieure; this is an independent reader for the container format it describes,
+written without access to the guideline text, which is sold rather than
+published. What that means for what this library can and cannot claim is spelled
+out in the [validator's scope note](https://github.com/dev365code/vdi2770-validate/blob/main/docs/scope.md).
+
+Apache-2.0.

vdi2770-0.1.0/README.md

@@ -0,0 +1,101 @@
+# vdi2770
+
+Read a VDI 2770 handover-documentation container and get back a typed model —
+without extracting anything to disk, without opening a socket, and without any
+dependencies.
+
+```bash
+pip install vdi2770
+```
+
+```python
+import vdi2770
+
+box = vdi2770.read_container_file("handover.zip")
+for c in box.walk():
+    if c.metadata_bytes is None:
+        continue
+    doc = vdi2770.build_document(vdi2770.parse_xml(c.metadata_bytes), c.where)
+    print(c.path, doc.ids, [k.class_id for k in doc.classifications])
+```
+
+```
+handover.zip ('DOC-2024-0001',) ['03-01']
+handover.zip!/pumps.zip ('DOC-2024-0002',) ['02-04']
+```
+
+## It decides nothing
+
+There is no `is_valid()` here, on purpose. Whether a container is *correct* is a
+question about VDI 2770, and the answer depends on which supplement your customer
+sent you. This library tells you what is in the file and where it is written; the
+opinion is yours to supply.
+
+If you want an opinion supplied for you, [`vdi2770-validate`](https://pypi.org/project/vdi2770-validate/)
+is this library plus a rule set, as a command-line tool.
+
+## Three properties, each tested rather than promised
+
+**Nothing is extracted to disk.** Members are decompressed into memory under a
+budget and dropped. There is no temporary directory to clean up and no path
+traversal to get wrong, because no path is ever joined.
+
+**Nothing is fetched.** No socket is opened for any input, ever — including XML
+that asks for one. An entity declaration is refused outright rather than
+resolved-but-locally, so there is no parser setting to get wrong later.
+
+**A refusal is reported, not raised.** A member that blows a budget becomes a
+`Defect` on the container and the read continues, so one hostile file inside a
+supplier archive does not cost you the other four hundred.
+
+## What comes back
+
+`read_container(data, name)` returns a `Container`:
+
+| | |
+|---|---|
+| `path` | `handover.zip!/pumps.zip` — the JAR convention, so it stays greppable |
+| `kind` | `DOCUMENTATION`, `DOCUMENT`, `UNKNOWN`, or `UNREADABLE` |
+| `members`, `file_names` | what is in the archive, after the budget filter |
+| `metadata_bytes`, `metadata_name` | the metadata that was found, if any |
+| `children`, `walk()` | inner containers, opened to three levels |
+| `defects` | what the reader could not do, and why |
+| `rejected` | members present in the archive but refused, and why |
+| `near_misses` | `vdi2770_metadata.xml` in an archive that has no metadata — the name is case-sensitive, and silence about that is unkind |
+| `duplicate_names` | a ZIP may carry the same name twice; readers disagree about which one wins |
+
+`build_document(node, where)` returns a `Document` whose every node carries a
+`Location` with the line and column it was written at, which is the reason this
+package parses XML itself instead of handing you an `ElementTree`.
+
+`read_pdf(data)` returns four facts and no verdict: `is_pdf`, `header`,
+`encrypted`, and `pdfa_claim` — the last being what the file's own metadata
+*claims*, such as `"2b"`. Nothing here verifies that claim. Verifying PDF/A takes
+a PDF/A validator, and this is not one.
+
+### Defect kinds
+
+`not-a-zip`, `too-many-members`, `unsafe-member-name`, `member-too-large`,
+`suspicious-compression`, `archive-too-large`, `metadata-too-large`,
+`metadata-unreadable`, `member-unreadable`, `nesting-too-deep`.
+
+These strings are part of the public surface; a test in this package fails if the
+code grows a kind that this list does not name.
+
+## Supported
+
+Python 3.9 and up. The budgets — member count, member size, total size,
+compression ratio, metadata size, nesting depth — are module constants in
+`vdi2770.zipread`, so you can read them, and they are deliberately not
+arguments, so a caller cannot turn them off by accident.
+
+## Unofficial
+
+Not affiliated with, endorsed by, or connected to VDI, the Digital Data Chain
+Consortium, or IDTA. VDI 2770 is a guideline published by the Verein Deutscher
+Ingenieure; this is an independent reader for the container format it describes,
+written without access to the guideline text, which is sold rather than
+published. What that means for what this library can and cannot claim is spelled
+out in the [validator's scope note](https://github.com/dev365code/vdi2770-validate/blob/main/docs/scope.md).
+
+Apache-2.0.

vdi2770-0.1.0/pyproject.toml

@@ -0,0 +1,48 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "vdi2770"
+version = "0.1.0"
+description = "Read a VDI 2770 handover-documentation container safely — no dependencies, no disk, no network"
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "Apache-2.0" }
+authors = [{ name = "Wooyong Lee" }]
+keywords = ["vdi2770", "technical documentation", "handover documentation", "industry 4.0", "zip"]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Manufacturing",
+  "Intended Audience :: Developers",
+  "License :: OSI Approved :: Apache Software License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Text Processing :: Markup :: XML",
+  "Typing :: Typed",
+]
+# No dependencies, and that is a feature rather than an omission. See README.
+dependencies = []
+
+[project.optional-dependencies]
+dev = ["pytest==8.3.4", "ruff==0.16.3"]
+
+[project.urls]
+Homepage = "https://github.com/dev365code/vdi2770-validate/tree/main/packages/vdi2770"
+Source = "https://github.com/dev365code/vdi2770-validate"
+Issues = "https://github.com/dev365code/vdi2770-validate/issues"
+
+[tool.setuptools]
+license-files = ["LICENSE"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+vdi2770 = ["py.typed"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-q"

vdi2770-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

vdi2770-0.1.0/src/vdi2770/__init__.py

@@ -0,0 +1,65 @@
+"""Read a VDI 2770 handover-documentation container without trusting it.
+
+    import vdi2770
+
+    box = vdi2770.read_container_file("manuals.zip")
+    for c in box.walk():
+        doc = vdi2770.build_document(vdi2770.parse_xml(c.metadata_bytes), c.at)
+        print(doc.id, [k.class_id for k in doc.classifications])
+
+Three properties this library holds to, each of them tested rather than
+promised:
+
+* **Nothing is extracted to disk.** Members are decompressed into memory
+  under a budget and dropped. There is no temporary directory to clean up
+  and no path traversal to get wrong, because no path is ever joined.
+* **Nothing is fetched.** No socket is opened, for any input, ever --
+  including XML that asks for one. Entity declarations are refused outright
+  rather than resolved-but-locally.
+* **A refusal is reported, not raised.** A member that blows a budget
+  becomes a `Defect` on the container and the read continues, so one hostile
+  file inside an archive does not cost you the other four hundred.
+
+It has **no dependencies**, and it decides nothing. Whether a container is
+*correct* is a question about VDI 2770, and this library does not answer it;
+it tells you what is in the file and where. If you want the verdict too, see
+`vdi2770-validate`, which is this library plus a rule set.
+
+Unofficial. Not affiliated with VDI, the Digital Data Chain Consortium, or
+IDTA. VDI 2770 is a guideline published by VDI; this is an independent
+reader for the container format it describes.
+"""
+from .domain import (
+    Classification,
+    Description,
+    DigitalFile,
+    Document,
+    DocumentVersion,
+)
+from .domain import build as build_document
+from .model import Defect, Location
+from .pdfread import PdfFacts
+from .pdfread import read as read_pdf
+from .xmlread import NS, Node, UnsafeXml, XmlError
+from .xmlread import parse as parse_xml
+from .zipread import (
+    MAIN_PDF,
+    MAIN_XML,
+    METADATA_XML,
+    Container,
+    Kind,
+    Member,
+    member_bytes,
+)
+from .zipread import read as read_container
+from .zipread import read_file as read_container_file
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "Classification", "Container", "Defect", "Description", "DigitalFile",
+    "Document", "DocumentVersion", "Kind", "Location", "MAIN_PDF", "MAIN_XML",
+    "METADATA_XML", "Member", "NS", "Node", "PdfFacts", "UnsafeXml", "XmlError",
+    "build_document", "member_bytes", "parse_xml", "read_container",
+    "read_container_file", "read_pdf", "__version__",
+]

vdi2770-0.1.0/src/vdi2770/domain.py

@@ -0,0 +1,110 @@
+"""The parsed metadata, as a model. Every node remembers where it was written.
+
+Rules read this. Rules never read the XML tree, so a rule physically cannot
+depend on how the document was spelled.
+"""
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Optional, Tuple
+
+from .model import Location
+from .xmlread import Node
+
+
+@dataclass(frozen=True)
+class Classification:
+    class_id: str
+    system: str
+    names: Tuple[Tuple[str, str], ...]   # (language, text)
+    src: Location = Location()
+
+
+@dataclass(frozen=True)
+class DigitalFile:
+    file_name: str
+    file_format: str
+    src: Location = Location()
+
+
+@dataclass(frozen=True)
+class Description:
+    language: str
+    title: str
+    src: Location = Location()
+
+
+@dataclass(frozen=True)
+class DocumentVersion:
+    version_id: str
+    languages: Tuple[str, ...]
+    descriptions: Tuple[Description, ...]
+    files: Tuple[DigitalFile, ...]
+    life_cycle_status: str
+    src: Location = Location()
+
+
+@dataclass(frozen=True)
+class Document:
+    ids: Tuple[str, ...]
+    classifications: Tuple[Classification, ...]
+    versions: Tuple[DocumentVersion, ...]
+    src: Location = Location()
+
+    @property
+    def all_files(self) -> Tuple[DigitalFile, ...]:
+        return tuple(f for v in self.versions for f in v.files)
+
+
+def _loc(base: Location, n: Node, subject: Optional[str] = None) -> Location:
+    return base.child(line=n.line, column=n.column, subject=subject)
+
+
+def build(root: Node, base: Location) -> Document:
+    ids = tuple(n.text.strip() for n in root.find_all("DocumentId"))
+
+    classifications = []
+    for c in root.find_all("DocumentClassification"):
+        names = tuple(
+            (nm.attrib.get("Language", "").strip(), nm.text.strip())
+            for nm in c.find_all("ClassName")
+        )
+        cid = c.text_of("ClassId")
+        classifications.append(Classification(
+            class_id=cid,
+            system=c.attrib.get("ClassificationSystem", "").strip(),
+            names=names,
+            src=_loc(base, c, cid or None),
+        ))
+
+    versions = []
+    for v in root.find_all("DocumentVersion"):
+        files = tuple(
+            DigitalFile(
+                # the file name is the element's text; the media type is an attribute
+                file_name=f.text.strip(),
+                file_format=f.attrib.get("FileFormat", "").strip(),
+                src=_loc(base, f, f.text.strip() or None),
+            )
+            for f in v.find_all("DigitalFile")
+        )
+        descriptions = tuple(
+            Description(
+                language=d.attrib.get("Language", "").strip(),
+                title=d.text_of("Title"),
+                src=_loc(base, d),
+            )
+            for d in v.find_all("DocumentDescription")
+        )
+        lcs = v.find("LifeCycleStatus")
+        versions.append(DocumentVersion(
+            version_id=v.text_of("DocumentVersionId"),
+            languages=tuple(n.text.strip() for n in v.find_all("Language")),
+            descriptions=descriptions,
+            files=files,
+            life_cycle_status=(lcs.attrib.get("StatusValue", "").strip() if lcs else ""),
+            src=_loc(base, v, v.text_of("DocumentVersionId") or None),
+        ))
+
+    return Document(ids=ids, classifications=tuple(classifications),
+                    versions=tuple(versions), src=_loc(base, root))