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
138
139
140
141
142
143
144
145
146

// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//    http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

use super::AssemblyError;

// ===================================================================
// Token
// ===================================================================

#[derive(Debug,PartialEq)]
pub enum Token<'a> {
    EOF, // End-Of-File (not EVM Object Format)
    Section(&'a str),
    Hex(&'a str),
    Identifier(&'a str),
    Label(&'a str)
}

impl<'a> Token<'a> {
    // Return the "length" of a token.  That is, the number of
    // characters it represents.
    pub fn len(&self) -> usize {
        match self {
            Token::EOF => 0,
            Token::Section(s) => s.len() + 1,
            Token::Hex(s) => s.len(),
            Token::Identifier(s) => s.len(),
            Token::Label(s) => s.len() + 1
        }
    }
}

// ===================================================================
// Lexer
// ===================================================================

/// A very simple lexer
pub struct Lexer<'a> {
    input: &'a str,
    chars: Vec<char>,
    index: usize
}

impl<'a> Lexer<'a> {
    pub fn new(input: &'a str) -> Self {
        // FIXME: this could be made more efficient by using an
        // iterator instead of allocating a new vector.
        let chars : Vec<char> = input.chars().collect();
        //
        Self{input, chars, index: 0}
    }

    pub fn lookahead(&self) -> Result<Token<'a>,AssemblyError> {
        // Skip any whitespace
        let start = self.skip_whitespace(self.index);
        // Sanity check for end-of-file
        if start >= self.chars.len() {
            Ok(Token::EOF)
        } else {
            // Determine what kind of token we have.
            match self.chars[start] {
                '.' => self.scan_section_header(start),
                '0'..='9' => self.scan_hex_literal(start),
                'a'..='z'|'A'..='Z'|'_' => self.scan_id_or_label(start),
                _ => Err(AssemblyError::UnexpectedCharacter(start))
            }
        }
    }

    pub fn next(&mut self) -> Result<Token<'a>,AssemblyError> {
        // Skip any whitespace
        self.index = self.skip_whitespace(self.index);
        // Determine next token
        let tok = self.lookahead()?;
        // Account for next token
        self.index += tok.len();
        //
        Ok(tok)
    }

    fn scan_hex_literal(&self, start: usize) -> Result<Token<'a>,AssemblyError> {
        // Sanity check literal starts with "0x"
        if self.chars[start..].starts_with(&['0','x']) {
            // Scan all digits of this hex literal
            let end = skip(&self.chars,start + 2,|c| c.is_ascii_alphanumeric());
            // Construct token
            Ok(Token::Hex(&self.input[start..end]))
        } else {
            Err(AssemblyError::InvalidHexString(start))
        }
    }

    fn scan_id_or_label(&self, start: usize) -> Result<Token<'a>,AssemblyError> {
        // Scan all characters of this identifier or label
        let end = skip(&self.chars,start,|c| c.is_ascii_alphanumeric());
        // Distinguish label versus identifier.
        if end < self.chars.len() && self.chars[end] == ':' {
            Ok(Token::Label(&self.input[start..end]))
        } else {
            Ok(Token::Identifier(&self.input[start..end]))
        }
    }

    fn scan_section_header(&self, mut start: usize) -> Result<Token<'a>,AssemblyError> {
        // Move passed "."
        start = start + 1;
        // Scan all characters of this identifier or label
        let end = skip(&self.chars,start,|c| c.is_ascii_alphabetic());
        // Done
        Ok(Token::Section(&self.input[start..end]))
    }

    fn skip_whitespace(&self, mut index: usize) -> usize {
        index = skip(&self.chars, index, |c| c.is_ascii_whitespace());
        // Check for a comment
        if self.chars[index..].starts_with(&[';']) {
            // Skip to newline
            index = skip(&self.chars, index, |c| c != '\n');
            // Recursive call to handle trainling whitespace
            self.skip_whitespace(index)
        } else {
            index
        }
    }
}

/// Skip over any characters matching a given predicate.
fn skip<P>(input: &[char], index: usize, pred: P) -> usize
where P: Fn(char) -> bool {
    let mut i = index;
    // Continue matching
    while i < input.len() && pred(input[i]) {
        i = i + 1;
    }
    // Done
    i
}