reg-meta 0.9.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,95 @@
1
+ # Python
2
+ __pycache__/
3
+ *.py[cod]
4
+ *.egg-info/
5
+ dist/
6
+ # Root-anchored: only the repo-root packaging dir, NOT the real
7
+ # `reg_monabundle/src/reg_monabundle/build/` source package (the bundle
8
+ # amalgamator). `__pycache__/` above still ignores byte-code anywhere.
9
+ /build/
10
+
11
+ # Environments
12
+ .venv/
13
+ .env
14
+ .envrc
15
+
16
+ # Tools
17
+ .ruff_cache/
18
+ .pytest_cache/
19
+ .mypy_cache/
20
+ node_modules/
21
+
22
+ # IDE
23
+ .idea/
24
+ .vscode/
25
+ *.swp
26
+
27
+ # OS
28
+ .DS_Store
29
+ Thumbs.db
30
+
31
+ # Project
32
+ .tmp/
33
+
34
+ # Input data (SCB CSVs, Socialstyrelsen metadata, source PDFs — not committed).
35
+ # Listed per-subdirectory so the maintainer-curated classifications/ folder
36
+ # can stay tracked without an exclude/re-include dance (git doesn't traverse
37
+ # into a parent dir that's been ignored at the directory level).
38
+ reg_meta_build/input_data/*
39
+ !reg_meta_build/input_data/classifications/
40
+ # Under classifications/ only the normalized CSVs (+ manifest.json) are tracked.
41
+ # The raw SOS source workbooks the fetch script downloads are not — they
42
+ # regenerate from scripts/fetch_sos_classifications.py.
43
+ reg_meta_build/input_data/classifications/sos/*.xls
44
+ reg_meta_build/input_data/classifications/sos/*.xlsx
45
+ # landskoder.csv is fetched but deliberately not seeded (see
46
+ # reg_meta_build/CLASSIFICATIONS.md); a bare fetch run regenerates it —
47
+ # keep it out of status noise.
48
+ reg_meta_build/input_data/classifications/sos/landskoder.csv
49
+
50
+ # mock-data-wizard generated output
51
+ mock_data/
52
+ mock_output/
53
+ mdw_runner.py
54
+ mdw_step1_discovery.json
55
+ mdw_step2_config.json
56
+ mdw_step3_stats.json
57
+ extract_stats*.R
58
+
59
+ # mock-data-wizard runtime artifacts (transient — fcntl sidecar, run logs)
60
+ .mock_data_config.lock
61
+ mdw_log_*.txt
62
+
63
+ # Local test workspaces (real user data, not part of the toolkit)
64
+ /covid-education-immigrants-test/
65
+
66
+ # Personal exploration scripts (not part of the toolkit's curated scripts/)
67
+ scripts/sample_*.py
68
+
69
+ # MONA probe artefacts -- can contain workspace metadata (paths,
70
+ # hostnames, DSNs); inspect before sharing. The findings that matter
71
+ # live in mock_data_wizard/DESIGN.md.
72
+ mdw_probe_*.log
73
+ mdw_python_probe_*.log
74
+ mdw_py_probe_*.csv
75
+ mdw_upload_probe_*.txt
76
+
77
+ # reg_meta database (built from SCB exports, not committed)
78
+ *.db
79
+
80
+ # SCB source PDFs (binary, copyrighted, not committed)
81
+ *.pdf
82
+
83
+ # Marker raw output (regenerable from PDFs + parser)
84
+ reg_meta_build/docs/_raw/
85
+
86
+ # Archive (concluded investigations, ad-hoc scripts, internal notes)
87
+ archive/
88
+ *.har
89
+
90
+ # Claude Code harness state (transient locks, per-user settings, worktree shims).
91
+ # `.claude/skills/` is intentionally tracked for shared skills, so ignore the
92
+ # transient pieces individually rather than blanket-ignoring `.claude/`.
93
+ .claude/scheduled_tasks.lock
94
+ .claude/worktrees/
95
+ .claude/settings.local.json