datoon 1.7.2__tar.gz → 1.7.4__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 (127) hide show
  1. {datoon-1.7.2 → datoon-1.7.4}/CHANGELOG.md +14 -0
  2. {datoon-1.7.2 → datoon-1.7.4}/PKG-INFO +1 -1
  3. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/_version.py +3 -3
  4. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/converter.py +11 -2
  5. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/xml.py +16 -1
  6. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/PKG-INFO +1 -1
  7. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/scm_version.json +2 -2
  8. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_converter_policy.py +7 -0
  9. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_readers.py +20 -0
  10. {datoon-1.7.2 → datoon-1.7.4}/.agents/plugins/marketplace.json +0 -0
  11. {datoon-1.7.2 → datoon-1.7.4}/.claude-plugin/marketplace.json +0 -0
  12. {datoon-1.7.2 → datoon-1.7.4}/.claude-plugin/plugin.json +0 -0
  13. {datoon-1.7.2 → datoon-1.7.4}/.editorconfig +0 -0
  14. {datoon-1.7.2 → datoon-1.7.4}/.gitattributes +0 -0
  15. {datoon-1.7.2 → datoon-1.7.4}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
  16. {datoon-1.7.2 → datoon-1.7.4}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
  17. {datoon-1.7.2 → datoon-1.7.4}/.github/dependabot.yml +0 -0
  18. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/package-installer-smoke.yml +0 -0
  19. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/pages.yml +0 -0
  20. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/pre-commit.yml +0 -0
  21. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/publish-mcp.yml +0 -0
  22. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/publish.yml +0 -0
  23. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/release.yml +0 -0
  24. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/tests.yml +0 -0
  25. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/validate-artifacts.yml +0 -0
  26. {datoon-1.7.2 → datoon-1.7.4}/.github/workflows/workflow-lint.yml +0 -0
  27. {datoon-1.7.2 → datoon-1.7.4}/.gitignore +0 -0
  28. {datoon-1.7.2 → datoon-1.7.4}/.pre-commit-config.yaml +0 -0
  29. {datoon-1.7.2 → datoon-1.7.4}/.releaserc.yaml +0 -0
  30. {datoon-1.7.2 → datoon-1.7.4}/CLAUDE.md +0 -0
  31. {datoon-1.7.2 → datoon-1.7.4}/CONTRIBUTING.md +0 -0
  32. {datoon-1.7.2 → datoon-1.7.4}/INSTALL.md +0 -0
  33. {datoon-1.7.2 → datoon-1.7.4}/LICENSE +0 -0
  34. {datoon-1.7.2 → datoon-1.7.4}/MARKETPLACES.md +0 -0
  35. {datoon-1.7.2 → datoon-1.7.4}/README.md +0 -0
  36. {datoon-1.7.2 → datoon-1.7.4}/SECURITY.md +0 -0
  37. {datoon-1.7.2 → datoon-1.7.4}/SKILL.md +0 -0
  38. {datoon-1.7.2 → datoon-1.7.4}/assets/datoon-banner.svg +0 -0
  39. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/REPORT.md +0 -0
  40. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/agent_results.json +0 -0
  41. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/expected_answers.json +0 -0
  42. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/generate_payloads.py +0 -0
  43. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/1_large.json +0 -0
  44. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/1_medium.json +0 -0
  45. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/1_small.json +0 -0
  46. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/2_large.json +0 -0
  47. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/2_medium.json +0 -0
  48. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/2_small.json +0 -0
  49. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/3_large.json +0 -0
  50. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/3_medium.json +0 -0
  51. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/payloads/3_small.json +0 -0
  52. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/1_large.report.json +0 -0
  53. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/1_medium.report.json +0 -0
  54. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/1_small.report.json +0 -0
  55. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/2_large.report.json +0 -0
  56. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/2_medium.report.json +0 -0
  57. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/2_small.report.json +0 -0
  58. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/3_large.report.json +0 -0
  59. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/3_medium.report.json +0 -0
  60. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/reports/3_small.report.json +0 -0
  61. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/scored_agent_results.json +0 -0
  62. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/1_large.toon +0 -0
  63. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/1_medium.toon +0 -0
  64. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/1_small.toon +0 -0
  65. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/2_large.toon +0 -0
  66. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/2_medium.toon +0 -0
  67. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/2_small.toon +0 -0
  68. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/3_large.toon +0 -0
  69. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/3_medium.toon +0 -0
  70. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/agent_skill_eval/toon/3_small.toon +0 -0
  71. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/payloads.json +0 -0
  72. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/results/.gitkeep +0 -0
  73. {datoon-1.7.2 → datoon-1.7.4}/benchmarks/run.py +0 -0
  74. {datoon-1.7.2 → datoon-1.7.4}/datoon/SKILL.md +0 -0
  75. {datoon-1.7.2 → datoon-1.7.4}/datoon.skill +0 -0
  76. {datoon-1.7.2 → datoon-1.7.4}/docs/.nojekyll +0 -0
  77. {datoon-1.7.2 → datoon-1.7.4}/docs/app.js +0 -0
  78. {datoon-1.7.2 → datoon-1.7.4}/docs/assets/datoon-banner.svg +0 -0
  79. {datoon-1.7.2 → datoon-1.7.4}/docs/index.html +0 -0
  80. {datoon-1.7.2 → datoon-1.7.4}/docs/styles.css +0 -0
  81. {datoon-1.7.2 → datoon-1.7.4}/glama.json +0 -0
  82. {datoon-1.7.2 → datoon-1.7.4}/install.sh +0 -0
  83. {datoon-1.7.2 → datoon-1.7.4}/plugins/datoon/.codex-plugin/plugin.json +0 -0
  84. {datoon-1.7.2 → datoon-1.7.4}/plugins/datoon/skills/datoon/SKILL.md +0 -0
  85. {datoon-1.7.2 → datoon-1.7.4}/pyproject.toml +0 -0
  86. {datoon-1.7.2 → datoon-1.7.4}/scripts/ab_skill_benchmark.py +0 -0
  87. {datoon-1.7.2 → datoon-1.7.4}/scripts/install.py +0 -0
  88. {datoon-1.7.2 → datoon-1.7.4}/scripts/summarize_agent_skill_eval.py +0 -0
  89. {datoon-1.7.2 → datoon-1.7.4}/scripts/validate_plugin_metadata.py +0 -0
  90. {datoon-1.7.2 → datoon-1.7.4}/scripts/validate_skill_sync.py +0 -0
  91. {datoon-1.7.2 → datoon-1.7.4}/server.json +0 -0
  92. {datoon-1.7.2 → datoon-1.7.4}/setup.cfg +0 -0
  93. {datoon-1.7.2 → datoon-1.7.4}/setup.sh +0 -0
  94. {datoon-1.7.2 → datoon-1.7.4}/skills/datoon/README.md +0 -0
  95. {datoon-1.7.2 → datoon-1.7.4}/skills/datoon/SKILL.md +0 -0
  96. {datoon-1.7.2 → datoon-1.7.4}/smithery.yaml +0 -0
  97. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/__init__.py +0 -0
  98. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/analyzer.py +0 -0
  99. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/cli.py +0 -0
  100. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/mcp_server.py +0 -0
  101. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/models.py +0 -0
  102. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/py.typed +0 -0
  103. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/__init__.py +0 -0
  104. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/_coerce.py +0 -0
  105. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/_tabular.py +0 -0
  106. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/columnar.py +0 -0
  107. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/csv.py +0 -0
  108. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/excel.py +0 -0
  109. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/jsonl.py +0 -0
  110. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/numbers.py +0 -0
  111. {datoon-1.7.2 → datoon-1.7.4}/src/datoon/readers/yaml.py +0 -0
  112. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/SOURCES.txt +0 -0
  113. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/dependency_links.txt +0 -0
  114. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/entry_points.txt +0 -0
  115. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/requires.txt +0 -0
  116. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/scm_file_list.json +0 -0
  117. {datoon-1.7.2 → datoon-1.7.4}/src/datoon.egg-info/top_level.txt +0 -0
  118. {datoon-1.7.2 → datoon-1.7.4}/tests/fixtures/users.expected.toon +0 -0
  119. {datoon-1.7.2 → datoon-1.7.4}/tests/fixtures/users.json +0 -0
  120. {datoon-1.7.2 → datoon-1.7.4}/tests/integration/test_toon_cli_integration.py +0 -0
  121. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_analyzer.py +0 -0
  122. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_cli.py +0 -0
  123. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_installer.py +0 -0
  124. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_mcp_server.py +0 -0
  125. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_models.py +0 -0
  126. {datoon-1.7.2 → datoon-1.7.4}/tests/unit/test_tabular_rows.py +0 -0
  127. {datoon-1.7.2 → datoon-1.7.4}/uv.lock +0 -0
@@ -1,3 +1,17 @@
1
+ ## [1.7.4](https://github.com/andrii-su/datoon/compare/v1.7.3...v1.7.4) (2026-07-07)
2
+
3
+
4
+ ### Bug Fixes
5
+
6
+ * **xml:** refuse DTD/DOCTYPE to block entity-expansion DoS ([#38](https://github.com/andrii-su/datoon/issues/38)) ([ef6a35e](https://github.com/andrii-su/datoon/commit/ef6a35e624176aab0a648794715c2d99411421d7))
7
+
8
+ ## [1.7.3](https://github.com/andrii-su/datoon/compare/v1.7.2...v1.7.3) (2026-07-07)
9
+
10
+
11
+ ### Bug Fixes
12
+
13
+ * **converter:** reject non-finite JSON constants instead of passing them through ([#37](https://github.com/andrii-su/datoon/issues/37)) ([ed73b53](https://github.com/andrii-su/datoon/commit/ed73b53922ac9b72a906e565303043d27f7ae686))
14
+
1
15
  ## [1.7.2](https://github.com/andrii-su/datoon/compare/v1.7.1...v1.7.2) (2026-07-07)
2
16
 
3
17
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datoon
3
- Version: 1.7.2
3
+ Version: 1.7.4
4
4
  Summary: Smart structured-data-to-TOON gateway with pragmatic auto-gating for LLM prompts.
5
5
  Author-email: Andrii Suruhov <andrii.suruhov@gmail.com>
6
6
  License: MIT License
@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
18
18
  commit_id: str | None
19
19
  __commit_id__: str | None
20
20
 
21
- __version__ = version = '1.7.2'
22
- __version_tuple__ = version_tuple = (1, 7, 2)
21
+ __version__ = version = '1.7.4'
22
+ __version_tuple__ = version_tuple = (1, 7, 4)
23
23
 
24
- __commit_id__ = commit_id = 'ga011eb92d'
24
+ __commit_id__ = commit_id = 'g9c1017702'
@@ -23,14 +23,23 @@ class DatoonError(RuntimeError):
23
23
  """Raised when datoon cannot process the payload safely."""
24
24
 
25
25
 
26
+ def _reject_non_finite(constant: str) -> Any:
27
+ """Reject Infinity/-Infinity/NaN, which are invalid JSON and break serialization."""
28
+ raise DatoonError(
29
+ f"Input contains non-finite constant '{constant}', which is not valid JSON."
30
+ )
31
+
32
+
26
33
  def _normalize_json(raw_text: str) -> tuple[Any, str]:
27
34
  """Parse and re-serialize JSON into a deterministic compact representation."""
28
35
  try:
29
- parsed = json.loads(raw_text)
36
+ parsed = json.loads(raw_text, parse_constant=_reject_non_finite)
30
37
  except json.JSONDecodeError as exc:
31
38
  raise DatoonError(f"Invalid JSON input: {exc.msg} (pos={exc.pos}).") from exc
32
39
 
33
- normalized = json.dumps(parsed, ensure_ascii=False, separators=(",", ":"))
40
+ normalized = json.dumps(
41
+ parsed, ensure_ascii=False, separators=(",", ":"), allow_nan=False
42
+ )
34
43
  return parsed, normalized
35
44
 
36
45
 
@@ -1,15 +1,30 @@
1
- """XML reader using stdlib xml.etree.ElementTree."""
1
+ """XML reader using stdlib xml.etree.ElementTree.
2
+
3
+ The stdlib parser rejects external entities but expands internal ones, so a DTD
4
+ can smuggle a billion-laughs DoS. datoon may process untrusted payloads, so DTDs
5
+ are refused outright. ``<!DOCTYPE`` is a fixed XML token (no internal
6
+ whitespace), so a literal scan reliably catches every declaration expat would
7
+ process.
8
+ """
2
9
 
3
10
  from __future__ import annotations
4
11
 
12
+ import re
5
13
  import xml.etree.ElementTree as ET
6
14
  from typing import Any
7
15
 
8
16
  from datoon.readers._coerce import coerce_scalar as _coerce
9
17
 
18
+ _DOCTYPE_RE = re.compile(r"<!DOCTYPE", re.IGNORECASE)
19
+
10
20
 
11
21
  def read_xml(text: str) -> list[dict[str, Any]]:
12
22
  """Parse XML into a list of row dicts from the dominant repeated child element."""
23
+ if _DOCTYPE_RE.search(text):
24
+ raise ValueError(
25
+ "XML with a DOCTYPE/DTD is not allowed (entity-expansion risk)."
26
+ )
27
+
13
28
  try:
14
29
  root = ET.fromstring(text)
15
30
  except ET.ParseError as exc:
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datoon
3
- Version: 1.7.2
3
+ Version: 1.7.4
4
4
  Summary: Smart structured-data-to-TOON gateway with pragmatic auto-gating for LLM prompts.
5
5
  Author-email: Andrii Suruhov <andrii.suruhov@gmail.com>
6
6
  License: MIT License
@@ -1,7 +1,7 @@
1
1
  {
2
- "tag": "1.7.2",
2
+ "tag": "1.7.4",
3
3
  "distance": 0,
4
- "node": "ga011eb92d6c550e4d87db4ebdd3b5efe9cb4f533",
4
+ "node": "g9c10177027b097628e6bb075bb54501482175b78",
5
5
  "dirty": false,
6
6
  "branch": "HEAD",
7
7
  "node_date": "2026-07-07"
@@ -28,6 +28,13 @@ def test_convert_json_for_llm_rejects_invalid_json() -> None:
28
28
  convert_json_for_llm("{bad json", ConversionConfig())
29
29
 
30
30
 
31
+ @pytest.mark.parametrize("literal", ["Infinity", "-Infinity", "NaN"])
32
+ def test_convert_json_for_llm_rejects_non_finite_constants(literal: str) -> None:
33
+ """Non-finite constants are invalid JSON per spec and must fail loudly."""
34
+ with pytest.raises(DatoonError, match="non-finite"):
35
+ convert_json_for_llm(f'{{"x": {literal}}}', ConversionConfig())
36
+
37
+
31
38
  def test_policy_skips_non_uniform_arrays(monkeypatch: pytest.MonkeyPatch) -> None:
32
39
  """Non-uniform arrays should skip conversion before CLI invocation."""
33
40
  called = {"value": False}
@@ -250,6 +250,26 @@ def test_read_xml_rejects_non_finite() -> None:
250
250
  assert rows[1]["v"] == "nan"
251
251
 
252
252
 
253
+ def test_read_xml_rejects_dtd_billion_laughs() -> None:
254
+ # Internal entity expansion (billion laughs) is a DoS vector; DTDs are refused.
255
+ payload = (
256
+ '<!DOCTYPE lolz [<!ENTITY lol "lol">'
257
+ '<!ENTITY lol2 "&lol;&lol;&lol;">]>'
258
+ "<rows><r>&lol2;</r></rows>"
259
+ )
260
+ with pytest.raises(ValueError, match="DOCTYPE"):
261
+ read_xml(payload)
262
+
263
+
264
+ def test_read_xml_rejects_external_entity_dtd() -> None:
265
+ payload = (
266
+ '<!DOCTYPE foo [<!ENTITY xxe SYSTEM "file:///etc/passwd">]>'
267
+ "<rows><r>&xxe;</r></rows>"
268
+ )
269
+ with pytest.raises(ValueError, match="DOCTYPE"):
270
+ read_xml(payload)
271
+
272
+
253
273
  def test_read_xml_invalid_raises() -> None:
254
274
  with pytest.raises(ValueError, match="Invalid XML"):
255
275
  read_xml("<not closed>")
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes
File without changes