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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * libxas: Extendable Assembler Library
 * Copyright (C) 2022 Amy Parker <apark0006@student.cerritos.edu>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write to the Free Software Foundation, Inc.,
 * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA or visit
 * the GNU Project at <https://gnu.org/licenses>. The GNU General Public
 * License version 2 is available at, for your convenience,
 * <https://gnu.org/licenses/old-licenses/gpl-2.0.html>.
 */

// TODO: box analysis
// how much should be stored in boxes... returning huge structs from functions
// isn't always the best idea, we might want to consider boxes (+ saves stack space)

// TODO: trait analysis
// figure out what needs to be implemented, and should be implemented
// and what should be removed and/or manually implemented for efficiency

// VecDeque is used for overall compatibility
// and to lower binary size. However, we don't use double-ended
// functionality - usage is purely FIFO
// TODO: analyze if there is a better solution
use std::collections::VecDeque;

// TODO: custom error support
// for now, we just use std::num::ParseIntError which is disgusting
// what's annoying is having to map to any existing error type

// TODO: manual implementation of Debug, Display for parsed structs

/// Instruction which has been parsed by a Parser.
/// Holds the instruction name as a string, and a vector of the arguments.
#[derive(Clone, Debug)]
pub struct ParsedInstruction {
    /// Holds a string representing the name of the instruction.
    pub instr: String,
    /// Holds a string representing the arguments of the instruction.
    pub args: Option<Vec<String>>,
}

#[derive(Clone, Debug)]
pub struct ParsedMacro {
    pub mcr: String,
    pub args: Option<Vec<String>>,
}

#[derive(Clone, Debug)]
pub enum ParsedOperation {
    Instruction(ParsedInstruction),
    Macro(ParsedMacro),
}

/// Structure holding a queue of parsed and to-be parsed entries.
/// Uses implemented methods for construction and interaction.
// TODO: document q-d meaning cross-project
pub struct Parser {
    /// Internally accessed queue of strings to be parsed.
    /// Each string represents exactly one line.
    q: VecDeque<String>,
    /// Internally accessed queue of instructions.
    /// Passed later to the lexer.
    d: VecDeque<ParsedOperation>,
}

impl std::str::FromStr for Parser {
    // TODO FIXME better error type
    type Err = std::num::ParseIntError;

    fn from_str(s: &str) -> Result<Self, Self::Err> {
        // TODO: explicitly list type of split
        // TODO: consider putting directly in the Ok()
        let split = s.lines();
        Ok(Parser {
            q: VecDeque::from_iter(split.map(|s| s.to_string())),
            d: VecDeque::new(),
        })
    }
}

// TODO: more ways to import lines (iterators, files, etc)
// no need to worry about stdin - that's client-side

// TODO: optimize, this is terribly inefficient
// TODO: if keeping do-it-self, consider box or array of width 2
fn single_split(s: &str) -> (String, String) {
    let mut flag: bool = true;
    let mut res: (String, String) = (String::new(), String::new());
    for c in s.chars() {
        if flag {
            if !c.is_whitespace() {
                res.0.push(c);
            } else {
                flag = false;
                res.1.push(c);
            }
        } else {
            res.1.push(c);
        }
    }
    res
}

impl Parser {
    pub fn pop_vdq(&mut self) -> VecDeque<ParsedOperation> {
        std::mem::replace(&mut self.d, VecDeque::new())
    }

    pub fn peek_queued(&self) -> Option<&String> {
        self.q.front()
    }

    fn pop_queued(&mut self) -> Option<String> {
        self.q.pop_front()
    }

    // TODO: find more efficient method
    pub fn drop_queued(&mut self) -> () {
        // discard value
        self.pop_queued();
    }

    pub fn peek_parsed(&self) -> Option<&ParsedOperation> {
        self.d.front()
    }

    pub fn pop_parsed(&mut self) -> Option<ParsedOperation> {
        self.d.pop_front()
    }

    pub fn parse_all(&mut self) -> () {
        while self.parse_line() {}
    }

    pub fn parse_line(&mut self) -> bool {
        let mut a: String = match self.pop_queued() {
            Some(s) => s,
            None => return false,
        };
        let mut b = a.trim_end().chars();
        if b.next_back() == Some(':') {
            self.d.push_back(ParsedOperation::Macro(ParsedMacro {
                mcr: "label".to_string(),
                args: Some(vec![b.collect::<String>()]),
            }));
            return true;
        } else {
            drop(b);
        }
        a = split_comments(a.trim_start());
        // skip empty lines
        if a == "" {
            return true;
        }
        let b: (String, String) = single_split(&a);
        let mut ar: Vec<String> = vec![];
        if b.1.trim_start() != "" {
            for n in acs_from_str(&b.1) {
                ar.push(n.trim().to_string());
            }
        }
        let oar: Option<Vec<String>> = {
            if ar.len() != 0 {
                Some(ar)
            } else {
                None
            }
        };
        // Current implementations guarantee that there will always be one character
        // If single_split's implementation changes, change this
        // unwrap() is safe - no possible error/panic - because of this
        if b.0.chars().nth(0).unwrap() != '.' {
            self.d
                .push_back(ParsedOperation::Instruction(ParsedInstruction {
                    instr: b.0,
                    args: oar,
                }));
        } else {
            // TODO: put iterator type here
            let mut ns: std::str::Chars = b.0.chars();
            ns.next();
            self.d.push_back(ParsedOperation::Macro(ParsedMacro {
                mcr: ns.collect::<String>(),
                args: oar,
            }));
        }

        true
    }
}

// Proper comma splitting algorithm
// Splits on commas as long as they aren't in parentheses
// TODO NOTE move into some sort of utilities file/external library, could be useful elsewhere... maybe an "arsu" crate with various utilities?
// NOTE should this be made pub?
// FIXME this needs major changes and updates, optimizations, etc
struct ArgCommaSplitter<'a> {
    p: bool,
    c: core::iter::Peekable<std::str::Bytes<'a>>,
}

// TODO optimize
impl Iterator for ArgCommaSplitter<'_> {
    type Item = String;

    fn next(&mut self) -> Option<Self::Item> {
        if let None = self.c.peek() {
            return None;
        }
        let mut pool: Vec<u8> = Vec::new();
        loop {
            // based on there being absolutely no nested parentheses
            // if nested parentheses are supported, check self.p beforehand NOTE
            match self.c.next() {
                // is match actually the best choice here due to code dup?
                // NOTE TODO code dup
                Some(b'(') => {
                    self.p = true;
                    pool.push(b'(');
                }
                Some(b')') => {
                    self.p = false;
                    pool.push(b')');
                }
                Some(b',') => {
                    if !self.p {
                        return Some(String::from_utf8(pool).unwrap());
                    } else {
                        pool.push(b',');
                    }
                }
                // NOTE TODO code dup
                None => return Some(String::from_utf8(pool).unwrap()),
                Some(v) => pool.push(v),
            }
        }
    }
}

// TODO: make project FromStr trait, maybe in utilities?
fn acs_from_str(s: &str) -> impl Iterator<Item = String> + '_ {
    ArgCommaSplitter {
        p: false,
        c: s.bytes().peekable(),
    }
}

fn split_comments(s: &str) -> String {
    s.split("//")
        .next()
        .unwrap()
        .split(';')
        .next()
        .unwrap()
        .to_string()
}