code-digest 0.5.0

High-performance CLI tool to convert codebases to Markdown for LLM context
Documentation 
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
78
79
80
81
82
83
84
85

# Comprehensive configuration example
# Shows all available options

[defaults]
max_tokens = 200000
progress = true
verbose = true
quiet = false

[ignore]
patterns = [
    "*.log",
    "*.tmp",
    "*.cache",
    ".git/",
    "vendor/",
    "node_modules/",
    "target/debug/",
]
use_gitignore = true

# Detailed priority configuration
[[priorities]]
pattern = "src/main.rs"
weight = 150  # Entry point gets highest priority

[[priorities]]
pattern = "src/lib.rs"
weight = 140

[[priorities]]
pattern = "src/api/**/*.rs"
weight = 120  # API definitions are important

[[priorities]]
pattern = "src/core/**/*.rs"
weight = 110

[[priorities]]
pattern = "src/**/*.rs"
weight = 100  # Other source files

[[priorities]]
pattern = "Cargo.toml"
weight = 90

[[priorities]]
pattern = "**/*.md"
weight = 70

[[priorities]]
pattern = "tests/**/*.rs"
weight = 50  # Tests are lower priority

[[priorities]]
pattern = "benches/**/*.rs"
weight = 40

[[priorities]]
pattern = "examples/**/*"
weight = 30  # Examples are lowest priority

[output]
include_tree = true
syntax_highlighting = true
max_line_length = 120  # Wrap long lines
file_header_template = """
================================================================================
## File: {path}
================================================================================
"""

[performance]
threads = 8  # Use 8 threads
max_file_size = 5242880  # 5MB limit per file
chunk_size = 131072  # 128KB chunks

[tokenizer]
model = "cl100k_base"  # GPT-3.5/4 tokenizer
cache_enabled = true

[logging]
level = "debug"  # trace, debug, info, warn, error
file = "code-digest.log"
stderr = true