zebra/.lychee.toml at main · ZcashFoundation/zebra · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
# Lychee link checker configuration for Zebra
# https://github.com/lycheeverse/lychee

# Exclude patterns
exclude = [
    # GitHub compare links (often temporary)
    "^https://github.com/.*/compare/",
    # Local development URLs
    "^https?://localhost",
    "^https?://127\\.0\\.0\\.1",
    "^https?://0\\.0\\.0\\.0",
    # Local file references
    "^file://",
    # Placeholder URLs
    "^https?://example\\.com",
    # Rate-limited or auth-required
    "^https://crates\\.io/crates/",
    # Arti GitLab rejects automated link checks
    "^https://gitlab\\.torproject\\.org/tpo/core/arti/-/blob/main/CONTRIBUTING\\.md",
    # GitHub pages requiring authentication
    "^https://github.com/.*/settings",
    "^https://github.com/organizations/.*/settings",
    # GitHub old run IDs (change frequently)
    "^https://github.com/.*/runs/",
    # Template placeholder URLs (0000)
    "^https://github.com/.*/issues/0000",
    "^https://github.com/.*/pull/0000",
    # Mergify dashboard (requires auth)
    "^https://dashboard.mergify.com/",
    # IACR eprint server returns 403 to automated link checkers
    "^https://eprint\\.iacr\\.org/",

    # Dead upstream links in historical audit document (zebra-dependencies-for-audit.md)
    "^https://github.com/iqlusioninc/abscissa/tree/develop",
    "^https://github.com/servo/bincode/releases/tag/v1\\.3\\.3",
]

# Exclude paths
exclude_path = [
    "node_modules",
    "target",
    ".git",
    "book/mermaid.min.js",
    "zebra-rpc/qa/rpc-tests",
    "supply-chain",
    # CHANGELOG contains historical references to deprecated URLs
    "CHANGELOG.md",
]

# Accept these HTTP status codes as valid
accept = ["200", "204", "206", "301", "302", "307", "308", "429"]

# Timeout for requests (seconds)
timeout = 30

# Skip checking private/internal IP addresses
exclude_private = true
exclude_loopback = true

# Cache results to avoid repeated checks
cache = true

# Maximum age of cached results
max_cache_age = "7d"

# Maximum concurrent requests
max_concurrency = 8

# User agent string
user_agent = "lychee/0.14 (Zebra link checker; https://github.com/ZcashFoundation/zebra)"

# Skip checking mail addresses
include_mail = false

# Retry configuration
max_retries = 3
retry_wait_time = 10