exness-data-preprocess 1.2.1__tar.gz → 2.0.0__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.
Files changed (140) hide show
  1. exness_data_preprocess-2.0.0/.github/workflows/ci.yml +25 -0
  2. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.mise.toml +20 -12
  3. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/CHANGELOG.md +30 -0
  4. exness_data_preprocess-2.0.0/CLAUDE.md +152 -0
  5. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/PKG-INFO +141 -85
  6. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/README.md +138 -81
  7. exness_data_preprocess-2.0.0/docs/adr/2025-12-11-duckdb-removal-clickhouse.md +236 -0
  8. exness_data_preprocess-2.0.0/docs/design/2025-12-11-duckdb-removal-clickhouse/spec.md +399 -0
  9. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/baseline-sep2024/02_volatility_model_simple.py +1 -1
  10. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase1_data_validation.py +1 -1
  11. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/visualization/generate_interactive_dashboard.py +1 -0
  12. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/visualization/generate_lightweight_dashboard.py +1 -0
  13. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/gap_detection_implementation_example.py +5 -5
  14. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/pyproject.toml +6 -8
  15. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/scripts/generate_dbeaver_config.py +2 -6
  16. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/__init__.py +21 -15
  17. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_client.py +5 -1
  18. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_gap_detector.py +2 -6
  19. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_manager.py +8 -13
  20. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_ohlc_generator.py +29 -9
  21. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_query_engine.py +3 -5
  22. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/config.py +6 -9
  23. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/models.py +59 -62
  24. exness_data_preprocess-2.0.0/src/exness_data_preprocess/processor.py +582 -0
  25. exness_data_preprocess-2.0.0/tests/conftest.py +79 -0
  26. exness_data_preprocess-2.0.0/tests/test_basic.py +57 -0
  27. exness_data_preprocess-2.0.0/tests/test_functional_regression.py +136 -0
  28. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/tests/test_models.py +55 -62
  29. exness_data_preprocess-2.0.0/tests/test_processor_pydantic.py +217 -0
  30. exness_data_preprocess-1.2.1/.github/workflows/ci.yml +0 -50
  31. exness_data_preprocess-1.2.1/CLAUDE.md +0 -150
  32. exness_data_preprocess-1.2.1/src/exness_data_preprocess/database_manager.py +0 -208
  33. exness_data_preprocess-1.2.1/src/exness_data_preprocess/gap_detector.py +0 -133
  34. exness_data_preprocess-1.2.1/src/exness_data_preprocess/ohlc_generator.py +0 -265
  35. exness_data_preprocess-1.2.1/src/exness_data_preprocess/processor.py +0 -764
  36. exness_data_preprocess-1.2.1/src/exness_data_preprocess/query_engine.py +0 -290
  37. exness_data_preprocess-1.2.1/src/exness_data_preprocess/schema.py +0 -323
  38. exness_data_preprocess-1.2.1/tests/conftest.py +0 -83
  39. exness_data_preprocess-1.2.1/tests/test_basic.py +0 -31
  40. exness_data_preprocess-1.2.1/tests/test_functional_regression.py +0 -327
  41. exness_data_preprocess-1.2.1/tests/test_processor_pydantic.py +0 -223
  42. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.cz.toml +0 -0
  43. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.github/workflows/pre-commit-autoupdate.yml +0 -0
  44. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.github/workflows/publish.yml +0 -0
  45. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.gitignore +0 -0
  46. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.pre-commit-config.yaml +0 -0
  47. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/.releaserc.yml +0 -0
  48. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/CONTRIBUTING.md +0 -0
  49. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/LICENSE +0 -0
  50. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/Makefile +0 -0
  51. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/cliff-release-notes.toml +0 -0
  52. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/cliff.toml +0 -0
  53. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/DATABASE_SCHEMA.md +0 -0
  54. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/EXNESS_DATA_SOURCES.md +0 -0
  55. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/MODULE_ARCHITECTURE.md +0 -0
  56. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/PRIORITY3_CLEANUP_PLAN.yaml +0 -0
  57. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/README.md +0 -0
  58. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/REPOSITORY_REFACTORING_PLAN.yaml +0 -0
  59. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/RESEARCH_PATTERNS.md +0 -0
  60. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/TRADING_HOURS_RESEARCH.md +0 -0
  61. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/UNIFIED_DUCKDB_PLAN_v2.md +0 -0
  62. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/2025-12-09-codebase-pruning.md +0 -0
  63. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/2025-12-09-exness-clickhouse-migration.md +0 -0
  64. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/2025-12-10-clickhouse-e2e-validation-pipeline.md +0 -0
  65. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/2025-12-10-clickhouse-pydantic-config.md +0 -0
  66. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/diagrams/2025-12-10-clickhouse-pydantic-config-after.dot +0 -0
  67. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/diagrams/2025-12-10-clickhouse-pydantic-config-arch.dot +0 -0
  68. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/adr/diagrams/2025-12-10-clickhouse-pydantic-config-before.dot +0 -0
  69. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/archive/PHASE4_DRY_RUN_CONFIG_PLAN.yaml +0 -0
  70. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/archive/PHASE7_v1.5.0_REFACTORING_PLAN.md +0 -0
  71. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/archive/PHASE7_v1.6.0_REFACTORING_PROGRESS.md +0 -0
  72. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/archive/PYDANTIC_REFACTORING_PLAN_v0.2.0_COMPLETE.md +0 -0
  73. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/archive/PYDANTIC_REFACTORING_STATUS_v0.2.0_COMPLETE.md +0 -0
  74. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/design/2025-12-09-codebase-pruning/spec.md +0 -0
  75. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/design/2025-12-09-exness-clickhouse-migration/spec.md +0 -0
  76. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/design/2025-12-10-clickhouse-e2e-validation-pipeline/spec.md +0 -0
  77. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/design/2025-12-10-clickhouse-pydantic-config/spec.md +0 -0
  78. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/optimization/OPTIMIZATION_OPPORTUNITIES_2025-10-18.md +0 -0
  79. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/phases/PHASE2_SESSION_VECTORIZATION_PLAN.yaml +0 -0
  80. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/phases/PHASE3_SQL_GAP_DETECTION_PLAN.yaml +0 -0
  81. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/releases/RELEASE_NOTES.md +0 -0
  82. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/releases/RELEASE_NOTES_SHORT.md +0 -0
  83. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/HYBRID_SESSION_DETECTION_ANALYSIS.md +0 -0
  84. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/compression-benchmarks/README.md +0 -0
  85. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/compression-benchmarks/test_all_compression_methods.py +0 -0
  86. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/compression-benchmarks/test_delta_encoding_properly.py +0 -0
  87. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/compression-benchmarks/test_parquet_compression_methods.py +0 -0
  88. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/01-methodology.md +0 -0
  89. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/02-mode-truncated-analysis.md +0 -0
  90. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/03-hurdle-model-analysis.md +0 -0
  91. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/04-temporal-patterns.md +0 -0
  92. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/05-final-recommendations.md +0 -0
  93. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/README.md +0 -0
  94. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/scripts/reproduction_guide.md +0 -0
  95. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/hurdle-model/hurdle_decomposition.png +0 -0
  96. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/mode-truncated/cv_mode_comparison.png +0 -0
  97. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/mode-truncated/distribution_overlay.png +0 -0
  98. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/mode-truncated/signal_quality_comparison.png +0 -0
  99. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/mode-truncated/variance_decomposition.png +0 -0
  100. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/temporal/concentration_curve.png +0 -0
  101. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-spread-analysis/visualizations/temporal/percentile_analysis.png +0 -0
  102. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/01-methodology.md +0 -0
  103. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/02-baseline-sep2024.md +0 -0
  104. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/03-multiperiod-validation.md +0 -0
  105. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/04-discoveries-and-plan-evolution.md +0 -0
  106. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/README.md +0 -0
  107. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/findings/baseline-sep2024-comprehensive-summary.md +0 -0
  108. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/findings/phase2-mean-reversion-report.md +0 -0
  109. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/findings/phase3-volatility-model-report.md +0 -0
  110. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/findings/phase4-5-statistical-tests-survivorship-report.md +0 -0
  111. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/baseline-sep2024/01_mean_reversion_analysis.py +0 -0
  112. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/baseline-sep2024/03_liquidity_crisis_detection.py +0 -0
  113. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/baseline-sep2024/04_regime_detection_analysis.py +0 -0
  114. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase2_mean_reversion.py +0 -0
  115. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase3_volatility_model.py +0 -0
  116. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase4_statistical_tests.py +0 -0
  117. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase5_survivorship_bias.py +0 -0
  118. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase5_survivorship_bias_v1.0.1.py +0 -0
  119. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase6a_interval_analysis.py +0 -0
  120. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase6b_price_clustering.py +0 -0
  121. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/multiperiod-validation/phase6c_combined_pattern.py +0 -0
  122. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/reproduction_guide.md +0 -0
  123. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/visualization/diagnostic_burst_decay.py +0 -0
  124. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/research/eurusd-zero-spread-deviations/scripts/visualization/prepare_visualization_data.py +0 -0
  125. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/setup/GITHUB_PYPI_SETUP.md +0 -0
  126. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/validation/E2E_VALIDATION_RESULTS_v1.6.0.md +0 -0
  127. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/validation/SPIKE_TEST_RESULTS_PHASE1_2025-10-18.md +0 -0
  128. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/docs/validation/SPIKE_TEST_RESULTS_PHASE2_2025-10-18.md +0 -0
  129. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/examples/basic_usage.py +0 -0
  130. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/examples/batch_processing.py +0 -0
  131. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/package-lock.json +0 -0
  132. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/package.json +0 -0
  133. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/clickhouse_base.py +0 -0
  134. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/downloader.py +0 -0
  135. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/exchanges.py +0 -0
  136. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/session_detector.py +0 -0
  137. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/src/exness_data_preprocess/tick_loader.py +0 -0
  138. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/tests/README.md +0 -0
  139. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/tests/__init__.py +0 -0
  140. {exness_data_preprocess-1.2.1 → exness_data_preprocess-2.0.0}/tests/test_types.py +0 -0
@@ -0,0 +1,25 @@
1
+ name: CI
2
+
3
+ on:
4
+ push:
5
+ branches: [main]
6
+ pull_request:
7
+ branches: [main]
8
+
9
+ jobs:
10
+ pre-commit:
11
+ name: Pre-commit hooks
12
+ runs-on: ubuntu-latest
13
+ steps:
14
+ - uses: actions/checkout@v4
15
+
16
+ - uses: actions/setup-python@v5
17
+ with:
18
+ python-version: '3.12'
19
+
20
+ - name: Run pre-commit hooks
21
+ uses: pre-commit/action@v3.0.1
22
+
23
+ # NOTE: Tests removed per local-first testing standard
24
+ # See: ~/.claude/CLAUDE.md - "NO unit testing in GitHub Actions"
25
+ # Run tests locally with: mise run validate
@@ -35,8 +35,9 @@ python = "3.11"
35
35
 
36
36
  [tasks.validate]
37
37
  description = "Run full E2E validation pipeline"
38
- # ADR: /docs/adr/2025-12-10-clickhouse-e2e-validation-pipeline.md
38
+ # ADR: /docs/adr/2025-12-11-duckdb-removal-clickhouse.md
39
39
  depends = [
40
+ "clickhouse:ensure", # Fail fast if ClickHouse not running
40
41
  "validate:imports",
41
42
  "validate:lint",
42
43
  "validate:typecheck",
@@ -44,24 +45,36 @@ depends = [
44
45
  "validate:build",
45
46
  "validate:install",
46
47
  "validate:mixin",
48
+ "validate:clickhouse", # ClickHouse E2E validation
47
49
  ]
48
50
  run = '''
49
51
  echo ""
50
52
  echo "=============================================="
51
53
  echo "✅ ALL VALIDATIONS PASSED"
52
54
  echo "=============================================="
53
- echo ""
54
- echo "💡 To run ClickHouse validation (requires ClickHouse running):"
55
- echo " mise run clickhouse:start"
56
- echo " mise run validate:clickhouse"
57
55
  '''
58
56
 
59
57
  # -----------------------------------------------------------------------------
60
58
  # Individual Validation Tasks
61
59
  # -----------------------------------------------------------------------------
62
60
 
61
+ [tasks."clickhouse:ensure"]
62
+ description = "Ensure ClickHouse is running (fail fast)"
63
+ # ADR: /docs/adr/2025-12-11-duckdb-removal-clickhouse.md
64
+ run = '''
65
+ #!/usr/bin/env bash
66
+ set -e
67
+ if ! nc -z localhost 8123 2>/dev/null; then
68
+ echo "ERROR: ClickHouse not running on port 8123" >&2
69
+ echo "Start with: mise run clickhouse:start" >&2
70
+ exit 1
71
+ fi
72
+ echo "✅ ClickHouse connection verified"
73
+ '''
74
+
63
75
  [tasks."validate:imports"]
64
76
  description = "Validate all module imports (catch circular imports, missing deps)"
77
+ # ADR: /docs/adr/2025-12-11-duckdb-removal-clickhouse.md - DuckDB modules removed
65
78
  run = '''
66
79
  #!/usr/bin/env bash
67
80
  set -e
@@ -95,7 +108,7 @@ from exness_data_preprocess import (
95
108
  print('✅ All public exports importable')
96
109
  " || { echo "❌ Public exports import failed"; exit 1; }
97
110
 
98
- # Test all internal modules
111
+ # Test all internal modules (ClickHouse-only, DuckDB modules removed)
99
112
  uv run python -c "
100
113
  modules = [
101
114
  'exness_data_preprocess.clickhouse_base',
@@ -105,15 +118,10 @@ modules = [
105
118
  'exness_data_preprocess.clickhouse_ohlc_generator',
106
119
  'exness_data_preprocess.clickhouse_query_engine',
107
120
  'exness_data_preprocess.config',
108
- 'exness_data_preprocess.database_manager',
109
121
  'exness_data_preprocess.downloader',
110
122
  'exness_data_preprocess.exchanges',
111
- 'exness_data_preprocess.gap_detector',
112
123
  'exness_data_preprocess.models',
113
- 'exness_data_preprocess.ohlc_generator',
114
124
  'exness_data_preprocess.processor',
115
- 'exness_data_preprocess.query_engine',
116
- 'exness_data_preprocess.schema',
117
125
  'exness_data_preprocess.session_detector',
118
126
  'exness_data_preprocess.tick_loader',
119
127
  ]
@@ -121,7 +129,7 @@ import importlib
121
129
  for mod in modules:
122
130
  importlib.import_module(mod)
123
131
  print(f' ✓ {mod}')
124
- print('✅ All 18 modules importable')
132
+ print('✅ All 13 modules importable')
125
133
  "
126
134
  echo "✅ Import validation passed"
127
135
  '''
@@ -1,3 +1,33 @@
1
+ # [2.0.0](https://github.com/terrylica/exness-data-preprocess/compare/v1.2.1...v2.0.0) (2025-12-27)
2
+
3
+
4
+ * feat!: migrate to ClickHouse-only backend, remove DuckDB ([7fd83bc](https://github.com/terrylica/exness-data-preprocess/commit/7fd83bc5720b2f5997a661ef8060757abd602a81))
5
+
6
+
7
+ ### BREAKING CHANGES
8
+
9
+ * This release removes DuckDB and makes ClickHouse the sole storage backend.
10
+
11
+ API Changes:
12
+ - `duckdb_path` → `database` (str, ClickHouse database name)
13
+ - `duckdb_size_mb` → `storage_bytes` (int, bytes not MB)
14
+ - `database_exists` → removed
15
+ - `base_dir` constructor parameter → removed
16
+
17
+ Schema Changes:
18
+ - OHLC schema reduced from 30 to 26 columns (removed 4 normalized metrics)
19
+
20
+ Deleted Files (~1,219 lines):
21
+ - database_manager.py (209 lines)
22
+ - gap_detector.py (134 lines)
23
+ - ohlc_generator.py (266 lines)
24
+ - query_engine.py (291 lines)
25
+ - schema.py (324 lines)
26
+
27
+ Requires: ClickHouse running on localhost:8123
28
+
29
+ ADR: docs/adr/2025-12-11-duckdb-removal-clickhouse.md
30
+
1
31
  ## [1.2.1](https://github.com/terrylica/exness-data-preprocess/compare/v1.2.0...v1.2.1) (2025-12-11)
2
32
 
3
33
 
@@ -0,0 +1,152 @@
1
+ # CLAUDE.md
2
+
3
+ This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
4
+
5
+ **Package**: `exness-data-preprocess` — Forex tick data preprocessing with ClickHouse backend
6
+
7
+ **Version**: See [`pyproject.toml`](pyproject.toml) line 3 (SSoT via semantic-release)
8
+
9
+ **Quick Start**: [`README.md`](README.md) — Installation, API reference, usage examples
10
+
11
+ ---
12
+
13
+ ## Documentation Hub (Progressive Disclosure)
14
+
15
+ ### Essential Links
16
+
17
+ | Topic | SSoT Document | Purpose |
18
+ | ---------------- | ------------------------------------------------------------------------------------------------------ | ---------------------------- |
19
+ | **User Guide** | [`README.md`](README.md) | Installation, API, examples |
20
+ | **Architecture** | [`docs/adr/2025-12-11-duckdb-removal-clickhouse.md`](docs/adr/2025-12-11-duckdb-removal-clickhouse.md) | ClickHouse-only decision |
21
+ | **Schema** | [`docs/DATABASE_SCHEMA.md`](docs/DATABASE_SCHEMA.md) | 26-column OHLC specification |
22
+ | **Modules** | [`docs/MODULE_ARCHITECTURE.md`](docs/MODULE_ARCHITECTURE.md) | 13 modules with SLOs |
23
+ | **Data Sources** | [`docs/EXNESS_DATA_SOURCES.md`](docs/EXNESS_DATA_SOURCES.md) | Exness tick data variants |
24
+ | **Tasks** | [`.mise.toml`](.mise.toml) | Validation, ClickHouse tasks |
25
+ | **Contributing** | [`CONTRIBUTING.md`](CONTRIBUTING.md) | Development guidelines |
26
+
27
+ ### Deep Dives (On-Demand)
28
+
29
+ | Topic | Location | When to Read |
30
+ | ------------------ | -------------------------------------- | ------------------------- |
31
+ | ADRs | [`docs/adr/`](docs/adr/) | Architecture decisions |
32
+ | Design Specs | [`docs/design/`](docs/design/) | Implementation blueprints |
33
+ | Validation Results | [`docs/validation/`](docs/validation/) | Spike test proofs |
34
+
35
+ ---
36
+
37
+ ## Architecture Overview (v2.0.0)
38
+
39
+ ### ClickHouse-Only Backend
40
+
41
+ **ADR**: [`docs/adr/2025-12-11-duckdb-removal-clickhouse.md`](docs/adr/2025-12-11-duckdb-removal-clickhouse.md)
42
+
43
+ | Feature | Description |
44
+ | --------------- | ------------------------------------------------ |
45
+ | **Database** | `exness` (single database for all instruments) |
46
+ | **Tables** | `raw_spread_ticks`, `standard_ticks`, `ohlc_1m` |
47
+ | **Engine** | ReplacingMergeTree (deduplication at merge time) |
48
+ | **Connection** | localhost:8123 (local) or cloud via env vars |
49
+ | **Entry Point** | `ExnessDataProcessor` |
50
+
51
+ ### Module Structure (13 Modules)
52
+
53
+ **ClickHouse Backend (7 modules)**:
54
+
55
+ - `processor.py` — Main orchestrator with ClickHouse backend
56
+ - `clickhouse_manager.py` — Schema management, data loading
57
+ - `clickhouse_gap_detector.py` — Gap detection for incremental updates
58
+ - `clickhouse_query_engine.py` — Query with pagination
59
+ - `clickhouse_ohlc_generator.py` — OHLC generation
60
+ - `clickhouse_client.py` — Connection factory with error handling
61
+ - `clickhouse_base.py` — Shared mixin for client lifecycle
62
+
63
+ **Shared (6 modules)**:
64
+
65
+ - `downloader.py` — HTTP download operations
66
+ - `tick_loader.py` — CSV parsing
67
+ - `session_detector.py` — Holiday/session detection (vectorized)
68
+ - `config.py` — Configuration management
69
+ - `models.py` — Pydantic models (UpdateResult, CoverageInfo, etc.)
70
+ - `exchanges.py` — Exchange calendar integration
71
+
72
+ **Deleted in v2.0.0**:
73
+
74
+ - ~~`database_manager.py`~~ — DuckDB database operations
75
+ - ~~`gap_detector.py`~~ — DuckDB gap detection
76
+ - ~~`ohlc_generator.py`~~ — DuckDB OHLC generation
77
+ - ~~`query_engine.py`~~ — DuckDB query operations
78
+ - ~~`schema.py`~~ — DuckDB SQL schema definitions
79
+
80
+ ---
81
+
82
+ ## Development Commands
83
+
84
+ ### Quick Reference
85
+
86
+ ```bash
87
+ # Setup
88
+ uv sync --dev
89
+
90
+ # Testing (45 tests)
91
+ uv run pytest # All tests
92
+ mise run validate # Full E2E validation (requires ClickHouse)
93
+
94
+ # Linting
95
+ uv run ruff check --fix src/ tests/
96
+
97
+ # ClickHouse (required for full validation)
98
+ mise run clickhouse:start # Start local server
99
+ mise run clickhouse:status # Check connection
100
+ mise run clickhouse:ensure # Fail fast if not running
101
+
102
+ # Build & Publish
103
+ uv build
104
+ ```
105
+
106
+ ### mise Tasks
107
+
108
+ All validation and tooling tasks are defined in [`.mise.toml`](.mise.toml):
109
+
110
+ | Task | Description |
111
+ | ------------------------------ | --------------------------------------- |
112
+ | `mise run validate` | Full E2E pipeline (requires ClickHouse) |
113
+ | `mise run clickhouse:ensure` | Fail fast if ClickHouse not running |
114
+ | `mise run clickhouse:start` | Start mise-installed ClickHouse |
115
+ | `mise run validate:clickhouse` | ClickHouse E2E tests |
116
+
117
+ ---
118
+
119
+ ## Key Changes in v2.0.0
120
+
121
+ ### Breaking Changes
122
+
123
+ | v1.x (DuckDB) | v2.0.0 (ClickHouse) |
124
+ | ----------------- | ------------------------------- |
125
+ | `duckdb_path` | `database` (str) |
126
+ | `duckdb_size_mb` | `storage_bytes` (int) |
127
+ | `database_exists` | removed |
128
+ | `base_dir` param | removed (ClickHouse manages) |
129
+ | 30-column OHLC | 26-column OHLC (4 cols removed) |
130
+
131
+ ### Removed Files
132
+
133
+ ```
134
+ src/exness_data_preprocess/database_manager.py (209 lines)
135
+ src/exness_data_preprocess/gap_detector.py (134 lines)
136
+ src/exness_data_preprocess/ohlc_generator.py (266 lines)
137
+ src/exness_data_preprocess/query_engine.py (291 lines)
138
+ src/exness_data_preprocess/schema.py (324 lines)
139
+ ```
140
+
141
+ **Total: ~1,224 lines deleted**
142
+
143
+ ---
144
+
145
+ ## References
146
+
147
+ - **Exness Data**: <https://ticks.ex2archive.com/>
148
+ - **ClickHouse**: <https://clickhouse.com/>
149
+
150
+ ---
151
+
152
+ **Last Updated**: 2025-12-11