vdi2770-validate 0.1.0__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.
Files changed (126) hide show
  1. vdi2770_validate-0.1.0/.github/dco.yml +2 -0
  2. vdi2770_validate-0.1.0/.github/workflows/ci.yml +36 -0
  3. vdi2770_validate-0.1.0/.github/workflows/release.yml +54 -0
  4. vdi2770_validate-0.1.0/CHANGELOG.md +29 -0
  5. vdi2770_validate-0.1.0/CONTRIBUTING.md +53 -0
  6. vdi2770_validate-0.1.0/LICENSE +202 -0
  7. vdi2770_validate-0.1.0/MANIFEST.in +11 -0
  8. vdi2770_validate-0.1.0/Makefile +34 -0
  9. vdi2770_validate-0.1.0/NOTICE +45 -0
  10. vdi2770_validate-0.1.0/PKG-INFO +119 -0
  11. vdi2770_validate-0.1.0/README.md +96 -0
  12. vdi2770_validate-0.1.0/SECURITY.md +30 -0
  13. vdi2770_validate-0.1.0/THIRD_PARTY.md +121 -0
  14. vdi2770_validate-0.1.0/corpus/MANIFEST.json +207 -0
  15. vdi2770_validate-0.1.0/corpus/NOTICE +29 -0
  16. vdi2770_validate-0.1.0/corpus/examples/.gitignore +1 -0
  17. vdi2770_validate-0.1.0/corpus/examples/Invalid1.pdf +0 -0
  18. vdi2770_validate-0.1.0/corpus/examples/Invalid2.pdf +0 -0
  19. vdi2770_validate-0.1.0/corpus/examples/InvalidName.xml +58 -0
  20. vdi2770_validate-0.1.0/corpus/examples/InvalidXMLName.zip +0 -0
  21. vdi2770_validate-0.1.0/corpus/examples/PDFA1b_File.pdf +0 -0
  22. vdi2770_validate-0.1.0/corpus/examples/PDFA2b_File.pdf +0 -0
  23. vdi2770_validate-0.1.0/corpus/examples/PDFA3b_File.pdf +0 -0
  24. vdi2770_validate-0.1.0/corpus/examples/VDI2770_Main.xml +58 -0
  25. vdi2770_validate-0.1.0/corpus/examples/Valid.pdf +0 -0
  26. vdi2770_validate-0.1.0/corpus/examples/container/certificate-pdfa-a.zip +0 -0
  27. vdi2770_validate-0.1.0/corpus/examples/container/certificate-pdfa-b.zip +0 -0
  28. vdi2770_validate-0.1.0/corpus/examples/container/document-invalid-pdfa-b.zip +0 -0
  29. vdi2770_validate-0.1.0/corpus/examples/container/documentationcontainer.zip +0 -0
  30. vdi2770_validate-0.1.0/corpus/examples/container/documentcontainer-invalid.zip +0 -0
  31. vdi2770_validate-0.1.0/corpus/examples/container/documentcontainer.zip +0 -0
  32. vdi2770_validate-0.1.0/corpus/examples/container/missingdocuments.zip +0 -0
  33. vdi2770_validate-0.1.0/corpus/examples/container/morethanonepdfcontainer.zip +0 -0
  34. vdi2770_validate-0.1.0/corpus/examples/container/objectreferences.zip +0 -0
  35. vdi2770_validate-0.1.0/corpus/examples/container/vdi2770_demo.zip +0 -0
  36. vdi2770_validate-0.1.0/corpus/examples/container/vdi2770_excel.zip +0 -0
  37. vdi2770_validate-0.1.0/corpus/examples/demo_invalid_doc_type_names.zip +0 -0
  38. vdi2770_validate-0.1.0/corpus/examples/demo_vdi.zip +0 -0
  39. vdi2770_validate-0.1.0/corpus/examples/empty.zip +0 -0
  40. vdi2770_validate-0.1.0/corpus/examples/folders/456-29201/VDI2770_Metadata.xml +63 -0
  41. vdi2770_validate-0.1.0/corpus/examples/folders/456-29201/demo.pdf +0 -0
  42. vdi2770_validate-0.1.0/corpus/examples/folders/456-29201/demo.xlsx +0 -0
  43. vdi2770_validate-0.1.0/corpus/examples/folders/AB393/VDI2770_Metadata.xml +67 -0
  44. vdi2770_validate-0.1.0/corpus/examples/folders/AB393/demo.docx +0 -0
  45. vdi2770_validate-0.1.0/corpus/examples/folders/AB393/demo.pdf +0 -0
  46. vdi2770_validate-0.1.0/corpus/examples/folders/VDI2770_Main.pdf +0 -0
  47. vdi2770_validate-0.1.0/corpus/examples/folders/VDI2770_Main.xml +58 -0
  48. vdi2770_validate-0.1.0/corpus/examples/issues/issue16container.zip +0 -0
  49. vdi2770_validate-0.1.0/corpus/examples/missing_Maindocument.zip +0 -0
  50. vdi2770_validate-0.1.0/corpus/examples/missing_Metadata.zip +0 -0
  51. vdi2770_validate-0.1.0/corpus/examples/missingdocuments/VDI2770_Main.pdf +0 -0
  52. vdi2770_validate-0.1.0/corpus/examples/missingdocuments/VDI2770_Main.xml +57 -0
  53. vdi2770_validate-0.1.0/corpus/examples/missingdocuments/folders.zip +0 -0
  54. vdi2770_validate-0.1.0/corpus/examples/pdf/encrypted.pdf +0 -0
  55. vdi2770_validate-0.1.0/corpus/examples/pdf/password.pdf +0 -0
  56. vdi2770_validate-0.1.0/corpus/examples/pdf/scan.pdf +0 -0
  57. vdi2770_validate-0.1.0/corpus/examples/statistics.csv +14 -0
  58. vdi2770_validate-0.1.0/corpus/examples/xml/Datasheet.xml +83 -0
  59. vdi2770_validate-0.1.0/corpus/examples/xml/Invalid1.xml +90 -0
  60. vdi2770_validate-0.1.0/corpus/examples/xml/Invalid2.xml +83 -0
  61. vdi2770_validate-0.1.0/corpus/examples/xml/InvalidEmpty.xml +55 -0
  62. vdi2770_validate-0.1.0/corpus/examples/xml/Maindocument.xml +116 -0
  63. vdi2770_validate-0.1.0/corpus/examples/xml/MissingXmlNs.xml +81 -0
  64. vdi2770_validate-0.1.0/corpus/examples/xml/validation.xml +102 -0
  65. vdi2770_validate-0.1.0/docs/divergences.md +136 -0
  66. vdi2770_validate-0.1.0/docs/findings.md +133 -0
  67. vdi2770_validate-0.1.0/docs/licensing.md +51 -0
  68. vdi2770_validate-0.1.0/docs/rule-coverage.json +42 -0
  69. vdi2770_validate-0.1.0/docs/scope.md +65 -0
  70. vdi2770_validate-0.1.0/pyproject.toml +59 -0
  71. vdi2770_validate-0.1.0/setup.cfg +4 -0
  72. vdi2770_validate-0.1.0/src/vdi2770_validate/__init__.py +2 -0
  73. vdi2770_validate-0.1.0/src/vdi2770_validate/__main__.py +5 -0
  74. vdi2770_validate-0.1.0/src/vdi2770_validate/catalog.py +77 -0
  75. vdi2770_validate-0.1.0/src/vdi2770_validate/cli.py +82 -0
  76. vdi2770_validate-0.1.0/src/vdi2770_validate/data/VDI2770_Schema_2019-08-23.xsd +287 -0
  77. vdi2770_validate-0.1.0/src/vdi2770_validate/data/document-classes.json +206 -0
  78. vdi2770_validate-0.1.0/src/vdi2770_validate/data/rules.json +468 -0
  79. vdi2770_validate-0.1.0/src/vdi2770_validate/domain.py +110 -0
  80. vdi2770_validate-0.1.0/src/vdi2770_validate/model.py +124 -0
  81. vdi2770_validate-0.1.0/src/vdi2770_validate/readers/__init__.py +0 -0
  82. vdi2770_validate-0.1.0/src/vdi2770_validate/readers/pdfread.py +88 -0
  83. vdi2770_validate-0.1.0/src/vdi2770_validate/readers/xmlread.py +111 -0
  84. vdi2770_validate-0.1.0/src/vdi2770_validate/readers/xsdvalidate.py +73 -0
  85. vdi2770_validate-0.1.0/src/vdi2770_validate/readers/zipread.py +224 -0
  86. vdi2770_validate-0.1.0/src/vdi2770_validate/report.py +63 -0
  87. vdi2770_validate-0.1.0/src/vdi2770_validate/resources.py +19 -0
  88. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/__init__.py +5 -0
  89. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/container.py +71 -0
  90. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/files.py +48 -0
  91. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/metadata.py +98 -0
  92. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/pdf.py +35 -0
  93. vdi2770_validate-0.1.0/src/vdi2770_validate/rules/schema.py +28 -0
  94. vdi2770_validate-0.1.0/src/vdi2770_validate/runner.py +79 -0
  95. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/PKG-INFO +119 -0
  96. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/SOURCES.txt +124 -0
  97. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/dependency_links.txt +1 -0
  98. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/entry_points.txt +2 -0
  99. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/requires.txt +5 -0
  100. vdi2770_validate-0.1.0/src/vdi2770_validate.egg-info/top_level.txt +1 -0
  101. vdi2770_validate-0.1.0/tests/conftest.py +10 -0
  102. vdi2770_validate-0.1.0/tests/data/oracle-messages.json +245 -0
  103. vdi2770_validate-0.1.0/tests/test_amplification.py +64 -0
  104. vdi2770_validate-0.1.0/tests/test_catalogue.py +113 -0
  105. vdi2770_validate-0.1.0/tests/test_ci_parity.py +94 -0
  106. vdi2770_validate-0.1.0/tests/test_cli.py +98 -0
  107. vdi2770_validate-0.1.0/tests/test_defences.py +171 -0
  108. vdi2770_validate-0.1.0/tests/test_determinism.py +29 -0
  109. vdi2770_validate-0.1.0/tests/test_evasion.py +139 -0
  110. vdi2770_validate-0.1.0/tests/test_layering.py +49 -0
  111. vdi2770_validate-0.1.0/tests/test_licensing.py +84 -0
  112. vdi2770_validate-0.1.0/tests/test_model.py +35 -0
  113. vdi2770_validate-0.1.0/tests/test_no_false_positives_on_the_reference_corpus.py +34 -0
  114. vdi2770_validate-0.1.0/tests/test_offline.py +48 -0
  115. vdi2770_validate-0.1.0/tests/test_pdf_precision.py +69 -0
  116. vdi2770_validate-0.1.0/tests/test_promises.py +94 -0
  117. vdi2770_validate-0.1.0/tests/test_readers.py +104 -0
  118. vdi2770_validate-0.1.0/tests/test_readme_sample.py +32 -0
  119. vdi2770_validate-0.1.0/tests/test_rule_pairs.py +58 -0
  120. vdi2770_validate-0.1.0/tests/test_tool_limits_are_not_verdicts.py +55 -0
  121. vdi2770_validate-0.1.0/tests/test_version_is_one_number.py +56 -0
  122. vdi2770_validate-0.1.0/tests/tools_shim.py +13 -0
  123. vdi2770_validate-0.1.0/tools/check_sdist.py +47 -0
  124. vdi2770_validate-0.1.0/tools/make_fixtures.py +233 -0
  125. vdi2770_validate-0.1.0/tools/rule_coverage.py +108 -0
  126. vdi2770_validate-0.1.0/tools/vendor_corpus.py +94 -0
@@ -0,0 +1,2 @@
1
+ require:
2
+ members: false
@@ -0,0 +1,36 @@
1
+ name: check
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+ pull_request:
7
+
8
+ jobs:
9
+ check:
10
+ runs-on: ubuntu-latest
11
+ strategy:
12
+ matrix:
13
+ python-version: ["3.9", "3.12"]
14
+ steps:
15
+ - uses: actions/checkout@v4
16
+ - uses: actions/setup-python@v5
17
+ with:
18
+ python-version: ${{ matrix.python-version }}
19
+ - name: Install
20
+ run: |
21
+ python -m pip install --upgrade pip
22
+ python -m pip install -e ".[dev]"
23
+ - name: Lint
24
+ run: python -m ruff check src tests tools
25
+ - name: Build fixtures
26
+ run: python tools/make_fixtures.py
27
+ - name: Test
28
+ run: python -m pytest
29
+ - name: Corpus is unchanged
30
+ run: python tools/vendor_corpus.py --check
31
+ - name: Firing coverage
32
+ run: python tools/rule_coverage.py --check
33
+ - name: The sdist can run its own tests
34
+ run: |
35
+ python -m pip install build
36
+ python tools/check_sdist.py
@@ -0,0 +1,54 @@
1
+ name: release
2
+
3
+ # One package in this repository, so one environment. The collision that bit the
4
+ # sibling project was two packages sharing a (repo, workflow, environment) tuple;
5
+ # splitting further here would be ceremony, not safety.
6
+
7
+ on:
8
+ push:
9
+ tags: ["v*"]
10
+
11
+ jobs:
12
+ build:
13
+ runs-on: ubuntu-latest
14
+ steps:
15
+ - uses: actions/checkout@v4
16
+ - uses: actions/setup-python@v5
17
+ with:
18
+ python-version: "3.12"
19
+ - name: Install
20
+ run: |
21
+ python -m pip install --upgrade pip build
22
+ python -m pip install -e ".[dev]"
23
+ - name: The gate must pass on the tagged tree
24
+ run: |
25
+ python -m ruff check src tests tools
26
+ python tools/make_fixtures.py
27
+ python -m pytest
28
+ python tools/vendor_corpus.py --check
29
+ python tools/rule_coverage.py --check
30
+ python tools/check_sdist.py
31
+ - name: The tag must be the version
32
+ run: |
33
+ tag="${GITHUB_REF_NAME#v}"
34
+ pkg=$(python -c "import sys; sys.path.insert(0,'src'); import vdi2770_validate as v; print(v.__version__)")
35
+ test "$tag" = "$pkg" || { echo "tag $tag != package $pkg"; exit 1; }
36
+ - name: Build
37
+ run: python -m build
38
+ - uses: actions/upload-artifact@v4
39
+ with:
40
+ name: dist
41
+ path: dist/
42
+
43
+ publish:
44
+ needs: build
45
+ runs-on: ubuntu-latest
46
+ environment: pypi
47
+ permissions:
48
+ id-token: write # Trusted Publishing; no API token is stored anywhere
49
+ steps:
50
+ - uses: actions/download-artifact@v4
51
+ with:
52
+ name: dist
53
+ path: dist/
54
+ - uses: pypa/gh-action-pypi-publish@release/v1
@@ -0,0 +1,29 @@
1
+ # Changelog
2
+
3
+ ## 0.1.0 — 2026-08-24
4
+
5
+ First release. It reads a VDI 2770 container and tells you what is wrong with
6
+ it, offline, with a remedy on every finding.
7
+
8
+ What 0.1.0 means here: the 33 rules it has are gated — each was killed in turn to
9
+ confirm the suite notices, 22 have a minimal violating/conforming fixture pair,
10
+ and the rest are exercised by the reference project's own examples, which no
11
+ structural rule is allowed to fire on. What it does *not* mean is broad coverage
12
+ of VDI 2770. The scope is small and written down in docs/scope.md, and the
13
+ refusals there are the honest part.
14
+
15
+ - Reads VDI 2770 document and documentation containers without extracting them.
16
+ - 32 rules across five layers — container shape, schema conformance, declared
17
+ files versus actual members, metadata model, and PDF claims — each with a
18
+ remedy sentence and each traceable to the schema VDI publishes free, to a
19
+ freely published table, to container mechanics, or to a stated judgement of
20
+ our own.
21
+ - Document classification matched on class id and German name. The two freely
22
+ published sources disagree on five of twelve English names, so an English name
23
+ never decides a verdict here; it produces a note showing both renderings.
24
+ - Reports what a PDF *claims* about PDF/A. Does not verify the claim, and says so
25
+ on every line where it matters.
26
+ - Gates: fixture pairs, firing coverage, import layering, offline, determinism,
27
+ CI/local parity, the declared Python floor, licence notices, remedy text not
28
+ copied from the reference, no structural rule firing on an upstream example,
29
+ and the README sample being output the tool really produces.
@@ -0,0 +1,53 @@
1
+ # Contributing
2
+
3
+ ## The Developer Certificate of Origin
4
+
5
+ Every commit carries a `Signed-off-by` line — `git commit -s`. That is a
6
+ [certificate of origin](https://developercertificate.org/), not a transfer of
7
+ rights; you keep the copyright in what you write.
8
+
9
+ ## Before you open a pull request
10
+
11
+ ```bash
12
+ python -m pip install -e ".[dev]"
13
+ make check
14
+ ```
15
+
16
+ `make check` is the whole gate: lint, build the fixtures, tests, the corpus is
17
+ unchanged, and every rule still fires. CI runs exactly those commands — a test asserts that, because
18
+ "the same command" is not the same thing as "the same environment".
19
+
20
+ ## Three rules of the road
21
+
22
+ Each exists because ignoring it would break something specific.
23
+
24
+ 1. **A new rule is a row in `rules.json` plus a function.** The row carries where
25
+ the requirement comes from, and a remedy sentence saying what the user should
26
+ *do*. A finding that only restates the problem is half a finding.
27
+
28
+ 2. **A new rule needs a fixture pair.** One container that violates it, one that
29
+ does not, differing in as little as possible — add the violating one to
30
+ `tools/make_fixtures.py`. A rule that has never been seen to fire has never
31
+ been tested, and `make check` will say so.
32
+
33
+ 3. **Rules may not import a parser.** `tests/test_layering.py` fails if a module
34
+ under `rules/` imports `zipfile` or an XML library. (Rules do import the
35
+ readers' reserved file names — that exemption is written into the test.)
36
+ Rules read the model; how the document was spelled is not their business.
37
+
38
+ ## Where the requirement came from matters
39
+
40
+ `rules.json` gives every rule an `obligation`: `schema` (the XSD VDI publishes
41
+ free), `table` (a freely published table), `container` (mechanics anyone can
42
+ observe), or `ours` — and `ours` must carry a `whyOurs` sentence.
43
+
44
+ **The VDI 2770 guideline text is sold by DIN Media and is not used here.** Do not
45
+ quote or paraphrase it, even from memory, and do not copy message text from other
46
+ implementations into a remedy — a test checks for that. See
47
+ [docs/licensing.md](docs/licensing.md).
48
+
49
+ ## Reporting something without writing code
50
+
51
+ An issue with a container that is judged wrongly — in either direction — is one
52
+ of the most useful things you can send. Strip anything confidential first; a
53
+ minimal archive that still reproduces is ideal.
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright 2026 Wooyong Lee (dev365code)
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,11 @@
1
+ # The sdist must be able to run its own tests, or a downstream packager building
2
+ # from it gets a green build that never ran the gate. This is the same class of
3
+ # error as a check that reads a path outside the repository: "the gate exists"
4
+ # and "the gate runs" differ only in someone else's environment.
5
+ include LICENSE NOTICE THIRD_PARTY.md CHANGELOG.md CONTRIBUTING.md SECURITY.md Makefile
6
+ recursive-include tests *.py *.json
7
+ recursive-include tools *.py
8
+ recursive-include corpus *
9
+ recursive-include docs *.md *.json
10
+ recursive-include .github *.yml
11
+ prune tests/fixtures
@@ -0,0 +1,34 @@
1
+ # One entry point. CI runs exactly these targets — tests/test_ci_parity.py proves it.
2
+ PYTHON ?= python3
3
+ RUFF_VERSION := 0.16.3
4
+ PYTEST_VERSION := 8.3.4
5
+ XMLSCHEMA_VERSION := 4.2.0
6
+
7
+ .PHONY: check lint test fixtures corpus coverage-check sdist-runs-its-own-tests clean
8
+
9
+ check: lint fixtures test corpus coverage-check
10
+
11
+ lint:
12
+ $(PYTHON) -m ruff check src tests tools
13
+
14
+ test:
15
+ $(PYTHON) -m pytest
16
+
17
+ # Fixtures are generated, never committed: the generator is the source of truth.
18
+ fixtures:
19
+ $(PYTHON) tools/make_fixtures.py
20
+
21
+ corpus:
22
+ $(PYTHON) tools/vendor_corpus.py --check
23
+
24
+ coverage-check:
25
+ $(PYTHON) tools/rule_coverage.py --check
26
+
27
+ # A downstream packager builds from the sdist. If the sdist cannot run the gate,
28
+ # they get a green build that checked nothing — the same shape as a gate that
29
+ # reads a path outside the repository.
30
+ sdist-runs-its-own-tests:
31
+ $(PYTHON) tools/check_sdist.py
32
+
33
+ clean:
34
+ rm -rf .pytest_cache .ruff_cache build dist tests/fixtures **/__pycache__
@@ -0,0 +1,45 @@
1
+ vdi2770-validate
2
+ Copyright 2026 Wooyong Lee
3
+
4
+ This product includes software developed by Wooyong Lee.
5
+ Licensed under the Apache License, Version 2.0.
6
+
7
+ --------------------------------------------------------------------------
8
+ Third-party material bundled with this project
9
+ --------------------------------------------------------------------------
10
+
11
+ 1. VDI 2770 XML schema — src/vdi2770_validate/data/VDI2770_Schema_2019-08-23.xsd
12
+
13
+ Published free of charge by VDI (Verein Deutscher Ingenieure) on the
14
+ VDI 2770 guideline programme page. Redistributed verbatim, unmodified.
15
+ Retrieved 2026-08-21 from
16
+ https://www.vdi.de/fileadmin/pages/vdi_de/redakteure/richtlinien/dateien/vdi2770/VDI_2770_1_de_Deklaration_des_XML-Schemas_-_Declaration_of_the_XML_model.xsd
17
+ The download page states no licence or terms of use. The file is treated
18
+ as VDI's work and is redistributed unchanged. See docs/licensing.md.
19
+
20
+ 2. VDI 2770 document class table — src/vdi2770_validate/data/document-classes.json
21
+
22
+ Table 1 of IDTA 02004 "Handover Documentation", Version 2.0.1 (November 2025),
23
+ Industrial Digital Twin Association e.V., published in
24
+ github.com/admin-shell-io/submodel-templates under CC BY 4.0.
25
+ Modified: the twelve rows were extracted and reformatted as JSON.
26
+ https://creativecommons.org/licenses/by/4.0/
27
+
28
+ 3. Reference message catalogue — tests/data/oracle-messages.json
29
+
30
+ The English validation messages of the same reference implementation,
31
+ reproduced so the licensing gate in tests/test_catalogue.py can check that no
32
+ remedy text in this project was copied from them. Test data only; nothing in
33
+ the shipped package reads it.
34
+ MIT License, Copyright (C) 2021 Johannes Schmidt.
35
+
36
+ 4. Conformance corpus — corpus/
37
+
38
+ Copied from github.com/DigitalDataChainConsortium/vdi2770 (examples/),
39
+ MIT License, Copyright (C) 2021 Johannes Schmidt. See corpus/NOTICE.
40
+
41
+ The text of the VDI 2770 guideline itself (VDI 2770 Blatt 1:2020-04) is sold
42
+ by DIN Media and is NOT included, quoted, or paraphrased anywhere in this
43
+ project. See docs/licensing.md.
44
+
45
+ Full provenance, licence texts and modification statements: THIRD_PARTY.md
@@ -0,0 +1,119 @@
1
+ Metadata-Version: 2.4
2
+ Name: vdi2770-validate
3
+ Version: 0.1.0
4
+ Summary: Offline conformance checker for VDI 2770 containers — every finding comes with a remedy
5
+ Author: Wooyong Lee
6
+ License: Apache-2.0
7
+ Keywords: vdi2770,technical documentation,conformance,validation,industry 4.0
8
+ Classifier: Development Status :: 3 - Alpha
9
+ Classifier: Intended Audience :: Manufacturing
10
+ Classifier: License :: OSI Approved :: Apache Software License
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Topic :: Software Development :: Quality Assurance
13
+ Requires-Python: >=3.9
14
+ Description-Content-Type: text/markdown
15
+ License-File: LICENSE
16
+ License-File: NOTICE
17
+ License-File: THIRD_PARTY.md
18
+ Requires-Dist: xmlschema==4.2.0
19
+ Provides-Extra: dev
20
+ Requires-Dist: pytest==8.3.4; extra == "dev"
21
+ Requires-Dist: ruff==0.16.3; extra == "dev"
22
+ Dynamic: license-file
23
+
24
+ # vdi2770-validate
25
+
26
+ Point it at a VDI 2770 container and it tells you, offline, whether the archive is
27
+ one — and if something is wrong, what to do about it.
28
+
29
+ VDI 2770 is how manufacturers hand over technical documentation in the process
30
+ industry: PDFs bundled into ZIP "document containers" with an XML metadata file,
31
+ those bundled into a "documentation container". Operators in the process industry
32
+ increasingly ask for it in purchase orders, and a container rejected on intake holds
33
+ up a delivery. The reference implementation is a Java library and web service; this
34
+ is a small offline CLI you can drop into a CI job.
35
+
36
+ **Unofficial.** Not affiliated with VDI, the Digital Data Chain Consortium, or IDTA.
37
+ Names are used descriptively.
38
+
39
+ ```
40
+ $ vdi2770-validate check corpus/examples/missingdocuments/folders.zip
41
+ error F1 A file named in the metadata is not in the container
42
+ at folders.zip!/VDI2770_Main.xml:56:2
43
+ 'VDI2770_Main.pdf' is declared but not in the archive
44
+ -> Add the missing file to the container, or remove its DigitalFile entry from the metadata. The two must agree.
45
+ error Z7 The documentation container has no VDI2770_Main.pdf
46
+ at folders.zip
47
+ -> Add the main document as VDI2770_Main.pdf at the root of the documentation container, next to VDI2770_Main.xml.
48
+ warn F2 A file in the container is not named in the metadata
49
+ at folders.zip!/456-29201/VDI2770_Metadata.xml
50
+ -> Declare the file as a DigitalFile in the metadata, or remove it from the container. An undeclared file is invisible to the recipient's system.
51
+ warn F2 A file in the container is not named in the metadata
52
+ at folders.zip!/456-29201/demo.pdf
53
+ -> Declare the file as a DigitalFile in the metadata, or remove it from the container. An undeclared file is invisible to the recipient's system.
54
+ warn F2 A file in the container is not named in the metadata
55
+ at folders.zip!/456-29201/demo.xlsx
56
+ -> Declare the file as a DigitalFile in the metadata, or remove it from the container. An undeclared file is invisible to the recipient's system.
57
+ warn F2 A file in the container is not named in the metadata
58
+
59
+ … 6 more warnings of the same kind
60
+ ```
61
+
62
+ That is real output on a container that ships with this repository, so the same command works after cloning.
63
+
64
+ ## What it will not tell you
65
+
66
+ **Whether a PDF really is PDF/A.** That needs a full PDF/A validator such as
67
+ veraPDF. This tool reports what a file *claims*, which catches the common failure:
68
+ files that never claimed at all. It says so on every line where it matters, and the
69
+ JSON output carries `"pdfaVerified": false` on every path. The rest of the refusals
70
+ are in [docs/scope.md](docs/scope.md).
71
+
72
+ ## How it is built
73
+
74
+ - **Offline by design.** No network at runtime, proven by a test that makes sockets
75
+ raise. Nothing is extracted to disk; a supplier archive does not get to pick a
76
+ path on your filesystem or expand an XML entity.
77
+ - **Rules are data.** [`rules.json`](src/vdi2770_validate/data/rules.json) — each
78
+ rule carries where its requirement comes from, a remedy sentence, and — where the
79
+ reference implementation checks the same thing — the message keys it uses.
80
+ - **22 of 32 rules have a minimal fixture pair** — a container that violates the rule
81
+ and a conforming one differing in as little as a single member. The rest are exercised
82
+ by the vendored corpus. A rule that fires nowhere fails the build.
83
+ - **Rules cannot reach the parser.** A test fails if a rule module imports `zipfile`
84
+ or an XML library, so a rule cannot accidentally check how a document was spelled
85
+ instead of what it says. Rules may name the readers' reserved file names, nothing more.
86
+
87
+ ## The classification table, and a disagreement
88
+
89
+ VDI 2770 defines twelve document classes. Two sources publish that table for free —
90
+ IDTA 02004 v2.0.1 Table 1, and the MIT reference implementation. Both renderings of
91
+ every name are stored, so you can check rather than trust: **they agree on all twelve
92
+ German names and disagree on five English ones** (02-03, 02-04, 03-01, 03-04,
93
+ 04-01). So matching here is keyed on the class id and the German name, and an
94
+ English name never fails a document — it produces a note that shows both renderings.
95
+
96
+ ```
97
+ $ vdi2770-validate classes
98
+ 02-03 Bauteile Assemblies [sources disagree]
99
+ IDTA 02004: 'Assemblies' reference impl: 'Components'
100
+ ```
101
+
102
+ Details in [docs/divergences.md](docs/divergences.md).
103
+
104
+ ## Licensing
105
+
106
+ Apache-2.0. The VDI 2770 guideline text is sold by DIN Media and was **not** read,
107
+ quoted, or paraphrased. Every rule names its source in `rules.json` instead: the schema
108
+ VDI publishes free, a freely published table, ZIP and XML mechanics, the MIT reference
109
+ implementation (observed there, not verified against the standard), or a judgement of
110
+ our own that has to explain itself.
111
+ See [docs/licensing.md](docs/licensing.md) and [NOTICE](NOTICE).
112
+
113
+ Contributions take a `Signed-off-by` line (DCO).
114
+
115
+ ## Related
116
+
117
+ [iirds-validate](https://github.com/dev365code/iirds-validate) — the same idea for
118
+ iiRDS. [standards-watch](https://github.com/dev365code/standards-watch) — a daily
119
+ watch on these standards.