wt_blk 0.3.1

Parser and unpacker for the BLK file format
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
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133

use std::{io::Read, isize, iter::once, ops::Add, sync::Arc};

use color_eyre::{eyre::ContextCompat, Report};
use itertools::Itertools;
use zstd::Decoder;

use crate::blk::{blk_string::BlkString, leb128::uleb128_offset};

/// A name map is a collection of shared strings across an entire VROMF file
/// Its usually in the top-level directory and called `nm` or in the binary vromf : `0xff 0x3f nm` (prefixed with a pair of seemingly random bytes)
#[derive(Clone, Debug)]
pub struct NameMap {
	pub binary: Vec<u8>,
	pub parsed: Arc<Vec<BlkString>>,
}

impl NameMap {
	pub fn idx_parsed(&self, idx: usize) -> Option<&BlkString> {
		self.parsed.get(idx)
	}

	pub fn from_encoded_file(file: &[u8]) -> Result<Self, Report> {
		let decoded = Self::decode_nm_file(file)?;

		let names = Self::parse_slim_nm(&decoded)?;

		Ok(Self {
			parsed: Arc::new(names),
			binary: decoded,
		})
	}

	pub fn decode_nm_file(file: &[u8]) -> Result<Vec<u8>, Report> {
		let _names_digest = &file.get(0..8).context(format!(
			"File out of bounds for range 0..8, found len: {}",
			file.len()
		))?;
		let _dict_digest = &file[8..40];
		let mut zstd_stream = &file[40..];
		let mut decoder = Decoder::new(&mut zstd_stream)?;
		let mut out = Vec::with_capacity(file.len());
		let _ = decoder.read_to_end(&mut out)?;
		Ok(out)
	}

	pub fn parse_name_section(file: &[u8]) -> Vec<BlkString> {
		once(-1_isize)
			.chain(memchr::memchr_iter(b'\0', file).map(|u| u as isize))
			.tuple_windows::<(isize, isize)>()
			.map(|(start, end)| {
				BlkString::from_lossy(&file[(start.add(1) as usize)..(end as usize)])
			})
			.collect()
	}

	pub fn parse_slim_nm(name_map: &[u8]) -> color_eyre::Result<Vec<BlkString>> {
		let mut nm_ptr = 0;

		let names_count = uleb128_offset(&name_map[nm_ptr..], &mut nm_ptr)?;

		let names_data_size = uleb128_offset(&name_map[nm_ptr..], &mut nm_ptr)?;

		let names = NameMap::parse_name_section(&name_map[nm_ptr..(nm_ptr + names_data_size)]);

		if names_count != names.len() {
			panic!("Should be equal"); // TODO: Change to result when fn signature allows for it
		}

		Ok(names)
	}
}

#[cfg(test)]
mod test {
	use std::fs;

	use crate::blk::{leb128::uleb128, name_map::NameMap};

	#[test]
	fn test_any_stream() {
		let decoded = NameMap::parse_name_section("a\0b\0c\0".as_bytes());
		assert_eq!(
			vec!["a", "b", "c"],
			decoded
				.iter()
				.map(|x| x.to_string())
				.collect::<Vec<String>>()
		)
	}

	#[test]
	fn test_nm_file() {
		let file = fs::read("./samples/nm").unwrap();
		let decoded = NameMap::decode_nm_file(&file).unwrap();
		assert_eq!(&fs::read("./samples/names").unwrap(), &decoded)
	}

	#[test]
	fn nm_parity() {
		let nm = fs::read("../wt_blk/samples/rendist/nm").unwrap();
		let nm = NameMap::decode_nm_file(&nm).unwrap();

		let mut nm_ptr = 0;

		let (offset, _names_count) = uleb128(&nm[nm_ptr..]).unwrap();
		nm_ptr += offset;

		let (offset, names_data_size) = uleb128(&nm[nm_ptr..]).unwrap();
		nm_ptr += offset;

		let _old = {
			let mut buff = vec![];
			let mut names = vec![];
			for val in &nm[nm_ptr..(nm_ptr + names_data_size)] {
				if *val == 0 {
					if let Ok(good) = String::from_utf8(buff.clone()) {
						names.push(good);
					} else {
						println!("{:?}", String::from_utf8_lossy(&buff));
					}
					buff.clear();
				} else {
					buff.push(*val);
				}
			}
			names
		};
		// let new = {
		// 	nm[nm_ptr..(nm_ptr + names_data_size)].split(|b| *b == 0).map(|bs| String::from_utf8_lossy(bs).to_string()).collect::<Vec<_>>()
		// };
		// assert_eq!(old, new);
	}
}