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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
//! This module contains the Character Inclusion Domain (CI).
//!
//! This domain considers the characters of a string and distinguishes
//! between two scenarios which are stored in different HashSets.
//! - The first set contains characters that are certainly contained in
//! the string.
//! - The second set contains characters that may be in the string.
//!
//! This distinction is made when two CI domains merge.
//! Furthermore, the CI domain does not preserve information about the order of characters.
//! The *Top* value of the CI domain stands for an empty set of certainly
//! contained characters and the whole alphabet of allowed characters for the possibly contained characters.
//!
//! The following presents an example which shows how the CI domain works:
//! 1. When a string is assigned to the CI domain its unique characters are stored in both
//! sets. e.g. "Hello, World!" => ({H,e,l,o,',',' ',W,o,r,d}, {H,e,l,o,',',' ',W,o,r,d})
//! 2. When two strings are concatenated, the union of the two sets of the two domains is taken.
//! e.g. "Hello, " + "World" => ({H,e,l,o,',',' '} v {W,o,r,d}, {H,e,l,o,',',' '} v {W,o,r,d})
//! 3. When two domains are merged, the intersection of the certain sets and the union of possible sets are taken.
//! e.g. ({H,e,l,o,',',' '}, {H,e,l,o,',',' '}) v ({W,o,r,l,d}, {W,o,r,l,d}) => ({l,o}, {H,e,l,o,',',' ',W,o,r,d})
use std::{collections::BTreeSet, fmt};
use crate::prelude::*;
use std::fmt::Debug;
use super::{AbstractDomain, DomainInsertion, HasTop};
/// The `CharacterInclusionDomain` is a abstract domain describing the characters a string certainly has
/// and the characters a string may have.
///
/// The value comprises of a set of certainly contained characters and a set of possibly contained characters
/// while the *Top* value does not get any data. However, the *Top* value stands for an empty set of certainly
/// contained characters and the whole alphabet of allowed characters for the possibly contained characters.
#[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
pub enum CharacterInclusionDomain {
/// The *Top* value stands for an empty set of certainly contained characters and
/// the whole alphabet of allowed characters for the possibly contained characters.
Top,
/// The set of certainly contained characters and a set of possibly contained characters
Value((CharacterSet, CharacterSet)),
}
impl CharacterInclusionDomain {
/// Unwraps the values from the Character Inclusion Domain
pub fn unwrap_value(&self) -> (CharacterSet, CharacterSet) {
match self {
CharacterInclusionDomain::Value(value) => value.clone(),
_ => panic!("Unexpected Character Inclusion type."),
}
}
}
impl DomainInsertion for CharacterInclusionDomain {
/// Append string domain as part of a concatenation. (different to merge)
fn append_string_domain(&self, string_domain: &Self) -> CharacterInclusionDomain {
match self {
CharacterInclusionDomain::Value((self_certain, self_possible)) => match string_domain {
CharacterInclusionDomain::Value((other_certain, other_possible)) => {
CharacterInclusionDomain::Value((
self_certain.union(other_certain.clone()),
self_possible.union(other_possible.clone()),
))
}
CharacterInclusionDomain::Top => {
CharacterInclusionDomain::Value((self_certain.clone(), CharacterSet::Top))
}
},
CharacterInclusionDomain::Top => match string_domain {
CharacterInclusionDomain::Value((other_certain, _)) => {
CharacterInclusionDomain::Value((other_certain.clone(), CharacterSet::Top))
}
CharacterInclusionDomain::Top => CharacterInclusionDomain::Top,
},
}
}
/// Create a string domain that approximates float values.
fn create_float_value_domain() -> Self {
let float_character_set: BTreeSet<char> = vec![
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '.', '-', 'a', 'i', 'n', 'f', 'e',
'E',
]
.into_iter()
.collect();
CharacterInclusionDomain::Value((
CharacterSet::Value(vec![].into_iter().collect()),
CharacterSet::Value(float_character_set),
))
}
/// Create a string domain that approximates char values.
fn create_char_domain() -> Self {
CharacterInclusionDomain::Top
}
/// Create a string domain that approximates integer values.
fn create_integer_domain() -> Self {
let integer_character_set: BTreeSet<char> =
vec!['0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '-']
.into_iter()
.collect();
CharacterInclusionDomain::Value((
CharacterSet::Value(vec![].into_iter().collect()),
CharacterSet::Value(integer_character_set),
))
}
/// Create a string domain that approximates pointer values.
fn create_pointer_value_domain() -> Self {
CharacterInclusionDomain::Top
}
/// Creates a top value of the domain.
fn create_top_value_domain() -> Self {
CharacterInclusionDomain::Top
}
/// Create a string domain that represents an empty string.
fn create_empty_string_domain() -> Self {
CharacterInclusionDomain::from("".to_string())
}
}
impl From<String> for CharacterInclusionDomain {
fn from(string: String) -> Self {
let characters: BTreeSet<char> = string.chars().collect();
CharacterInclusionDomain::Value((
CharacterSet::Value(characters.clone()),
CharacterSet::Value(characters),
))
}
}
impl AbstractDomain for CharacterInclusionDomain {
/// Merge two values; Takes the intersection of the certainly contained characters
/// and the union of the possibly contained characters.
/// Returns *Top* if either Domain represents it.
fn merge(&self, other: &Self) -> Self {
if self.is_top() || other.is_top() {
Self::Top
} else if self == other {
self.clone()
} else {
let (self_certain, self_possible) = self.unwrap_value();
let (other_certain, other_possible) = other.unwrap_value();
Self::Value((
self_certain.intersection(other_certain),
self_possible.union(other_possible),
))
}
}
/// Check if the value is *Top*.
fn is_top(&self) -> bool {
matches!(self, Self::Top)
}
}
impl HasTop for CharacterInclusionDomain {
/// Return a *Top* value
fn top(&self) -> Self {
CharacterInclusionDomain::Top
}
}
impl fmt::Display for CharacterInclusionDomain {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
CharacterInclusionDomain::Top => write!(f, "Top"),
CharacterInclusionDomain::Value((certain_set, possible_set)) => {
write!(f, "Certain: {certain_set}, Possible: {possible_set}")
}
}
}
}
/// A domain that represents character sets.
#[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
pub enum CharacterSet {
/// The *Top* value represents a character set of all allowed characters.
Top,
/// Represents a real subset of all allowed characters.
Value(BTreeSet<char>),
}
impl CharacterSet {
/// Unwraps the values from the CharacterSet
pub fn unwrap_value(&self) -> BTreeSet<char> {
match self {
CharacterSet::Value(value) => value.clone(),
_ => panic!("Unexpected CharacterSet type."),
}
}
/// Takes the intersection of two character sets.
/// None of the sets should be *Top* since otherwise
/// the whole CharacterInclusionDomain would be *Top*
/// which is checked beforehand.
pub fn intersection(&self, other: Self) -> Self {
if self.is_top() || other.is_top() {
panic!("Unexpected Top Value for CharacterSet intersection.")
}
CharacterSet::Value(
self.unwrap_value()
.intersection(&other.unwrap_value())
.cloned()
.collect(),
)
}
/// Takes the union of two character sets.
/// If either of them is *Top* the union is *Top*.
/// Otherwise the standard set union is taken.
pub fn union(&self, other: Self) -> Self {
if self.is_top() || other.is_top() {
return CharacterSet::Top;
}
CharacterSet::Value(
self.unwrap_value()
.union(&other.unwrap_value())
.cloned()
.collect(),
)
}
/// Check if the value is *Top*.
fn is_top(&self) -> bool {
matches!(self, Self::Top)
}
}
impl HasTop for CharacterSet {
/// Return a *Top* value
fn top(&self) -> Self {
CharacterSet::Top
}
}
impl fmt::Display for CharacterSet {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
match self {
CharacterSet::Top => write!(f, "Top"),
CharacterSet::Value(char_set) => {
write!(f, "{char_set:?}")
}
}
}
}
#[cfg(test)]
pub mod tests {
use super::*;
impl CharacterInclusionDomain {
pub fn ci(concrete: &str) -> CharacterInclusionDomain {
let abstract_set = CharacterSet::Value(concrete.chars().into_iter().collect());
CharacterInclusionDomain::Value((abstract_set.clone(), abstract_set.clone()))
}
}
#[test]
fn merging() {
let first = CharacterInclusionDomain::ci("abc");
let second = CharacterInclusionDomain::ci("def");
let third = CharacterInclusionDomain::ci("dabc");
let possible_set = CharacterSet::Value("abcdef".chars().into_iter().collect());
let certain_set = CharacterSet::Value("d".chars().into_iter().collect());
assert_eq!(
first.merge(&second),
CharacterInclusionDomain::Value((
CharacterSet::Value(BTreeSet::new()),
possible_set.clone()
))
);
assert_eq!(
third.merge(&second),
CharacterInclusionDomain::Value((certain_set, possible_set))
);
assert_eq!(
first.merge(&CharacterInclusionDomain::Top),
CharacterInclusionDomain::Top
);
assert_eq!(
CharacterInclusionDomain::Top.merge(&CharacterInclusionDomain::Top),
CharacterInclusionDomain::Top
);
}
}