pdf-font 1.0.0-beta.3

PDF font handling: CFF/Type1 parsing, CMap parsing, and PostScript scanning.
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
134
135
136
137

use super::stream::Stream;
use alloc::vec;
use alloc::vec::Vec;
use log::error;

pub(crate) fn decrypt(data: &[u8], use_decryption: bool) -> Option<Vec<u8>> {
    let mut stream = Stream::new(data);
    stream.skip_whitespaces();

    let mut b00 = None;
    let mut r: u32 = 55665;

    let mut decrypt = |b: u8| decrypt_byte(b, &mut r, use_decryption);

    for _ in 0..1000 {
        let c = stream.read_byte()?;
        if !is_white_space_after_token_eexec(c) {
            b00 = Some(c);
            break;
        }
    }

    let Some(b00) = b00 else {
        error!("b00 was None");

        return None;
    };

    let mut b = [0_u8; 4];
    b[0] = b00;

    for byte in b.iter_mut().skip(1) {
        let c = stream.read_byte()?;
        *byte = c;
    }

    let mut is_bin = false;

    for byte in &b {
        if !byte.is_ascii_hexdigit() {
            is_bin = true;
        }
    }

    if is_bin {
        let mut out = vec![];

        for byte in &b {
            decrypt(*byte);
        }

        for b in stream.tail()? {
            out.push(decrypt(*b));
        }

        Some(out)
    } else {
        let mut out = vec![];

        // Decrypt the first 4 hex chars (2 bytes) as garbage bytes
        let b0 = hex_to_byte(b[0] as char, b[1] as char)?;
        let b1 = hex_to_byte(b[2] as char, b[3] as char)?;
        decrypt(b0);
        decrypt(b1);

        let mut hex_chars = vec![];
        for b in stream.tail()? {
            if b.is_ascii_hexdigit() {
                hex_chars.push(*b as char);
            } else if !is_whitespace(*b) {
                break;
            }
        }

        let mut i = 0;
        while i + 1 < hex_chars.len() {
            if let Some(byte) = hex_to_byte(hex_chars[i], hex_chars[i + 1]) {
                if i < 4 {
                    decrypt(byte);
                } else {
                    out.push(decrypt(byte));
                }
                i += 2;
            } else {
                error!("failed to convert hex chars to byte");
                return None;
            }
        }

        // Handle odd number of hex digits (pad with '0')
        if i < hex_chars.len()
            && let Some(byte) = hex_to_byte(hex_chars[i], '0')
        {
            if i >= 4 {
                out.push(decrypt(byte));
            } else {
                decrypt(byte);
            }
        }

        Some(out)
    }
}

pub(crate) fn decrypt_byte(cipher: u8, r: &mut u32, use_decryption: bool) -> u8 {
    let cipher = cipher as u32;
    if use_decryption {
        let plain = cipher ^ (*r >> 8);
        *r = ((cipher + *r).wrapping_mul(52845) + 22719) & 0xFFFF;
        (plain & 0xFF) as u8
    } else {
        (cipher & 0xFF) as u8
    }
}

fn is_white_space_after_token_eexec(c: u8) -> bool {
    matches!(c, b' ' | b'\t' | b'\n' | b'\r')
}

fn is_whitespace(c: u8) -> bool {
    matches!(c, b' ' | b'\t' | b'\n' | b'\r' | b'\0' | b'\x0C')
}

fn hex_to_byte(c1: char, c2: char) -> Option<u8> {
    let h1 = hex_to_dec(c1)?;
    let h2 = hex_to_dec(c2)?;
    Some((h1 << 4) | h2)
}

fn hex_to_dec(hex: char) -> Option<u8> {
    match hex {
        '0'..='9' => Some((hex as u8) - b'0'),
        'A'..='F' => Some((hex as u8) - b'A' + 10),
        'a'..='f' => Some((hex as u8) - b'a' + 10),
        _ => None,
    }
}