Files
addr2line
adler
ahash
aho_corasick
ansi_term
anyhow
arc_swap
arrayref
arrayvec
ascii
assert_matches
async_stream
async_stream_impl
async_trait
atty
auto_enums
auto_enums_core
auto_enums_derive
backoff
backtrace
base32
base64
bincode
bip39
bitflags
bitvec
blake3
block_buffer
block_padding
borsh
borsh_derive
borsh_derive_internal
borsh_schema_derive_internal
bs58
bstr
bv
byte_slice_cast
byte_unit
bytecount
byteorder
bytes
bzip2
bzip2_sys
cargo_build_bpf
cargo_metadata
cargo_platform
cargo_test_bpf
cast
cc
cfg_if
chrono
chrono_humanize
clap
colored
combine
console
const_fn
constant_time_eq
core_affinity
cpufeatures
crc32fast
criterion_stats
crossbeam_channel
crossbeam_deque
crossbeam_epoch
crossbeam_queue
crossbeam_utils
crunchy
crypto_mac
csv
csv_core
ctrlc
curve25519_dalek
dashmap
derivative
derive_more
derive_utils
dialoguer
digest
dir_diff
dirs_next
dirs_sys_next
dlopen
dlopen_derive
doc_comment
dtoa
ed25519
ed25519_dalek
either
encoding_rs
enum_iterator
enum_iterator_derive
env_logger
ethabi
ethbloom
ethereum
ethereum_types
evm
evm_bridge
evm_core
evm_gasometer
evm_rpc
evm_runtime
evm_state
evm_utils
failure
failure_derive
fake_simd
fast_math
fd_lock
filetime
fixed_hash
flate2
fnv
foreign_types
foreign_types_shared
form_urlencoded
fs_extra
futures
futures_channel
futures_core
futures_executor
futures_io
futures_macro
futures_sink
futures_task
futures_util
async_await
future
io
lock
sink
stream
task
gag
generic_array
gethostname
getrandom
gimli
globset
goauth
goblin
h2
half
hash256_std_hasher
hash32
hash_db
hashbrown
heck
hex
hidapi
histogram
hmac
hmac_drbg
http
http_body
httparse
httpdate
humantime
hyper
hyper_rustls
hyper_tls
idna
ieee754
impl_codec
impl_rlp
impl_serde
indexed
indexmap
indicatif
inflector
cases
camelcase
case
classcase
kebabcase
pascalcase
screamingsnakecase
sentencecase
snakecase
tablecase
titlecase
traincase
numbers
deordinalize
ordinalize
string
constants
deconstantize
demodulize
pluralize
singularize
suffix
foreignkey
input_buffer
instant
iovec
ipnet
itertools
itoa
jemalloc_ctl
jemalloc_sys
jemallocator
jobserver
jsonrpc_client_transports
jsonrpc_core
jsonrpc_core_client
jsonrpc_derive
jsonrpc_http_server
jsonrpc_pubsub
jsonrpc_server_utils
jsonrpc_ws_server
keccak
keccak_hash
keccak_hasher
kernel32
lazy_static
lazycell
libc
libloading
librocksdb_sys
linked_hash_map
lock_api
log
lru
matches
maybe_uninit
memchr
memmap2
memoffset
mime
mime_guess
miniz_oxide
mio
mio_extras
miow
native_tls
net2
nix
num_cpus
num_derive
num_enum
num_enum_derive
num_integer
num_traits
number_prefix
object
once_cell
opaque_debug
openssl
openssl_probe
openssl_sys
ouroboros
ouroboros_macro
parity_scale_codec
parity_scale_codec_derive
parity_ws
parking_lot
parking_lot_core
paste
paste_impl
paw
paw_attributes
paw_raw
pbkdf2
percent_encoding
pest
pickledb
pin_project
pin_project_lite
pin_utils
plain
ppv_lite86
pretty_hex
primitive_types
proc_macro2
proc_macro_crate
proc_macro_error
proc_macro_error_attr
proc_macro_hack
proc_macro_nested
prost
prost_derive
prost_types
quote
radium
rand
rand_chacha
rand_core
rand_isaac
raptorq
rayon
rayon_core
reed_solomon_erasure
regex
regex_automata
regex_syntax
remove_dir_all
reqwest
retain_mut
ring
ripemd160
rlp
rlp_derive
rocksdb
rpassword
rustc_demangle
rustc_hash
rustc_hex
rustls
rustversion
ryu
same_file
scopeguard
scroll
scroll_derive
sct
secp256k1
secp256k1_sys
semver
semver_parser
serde
serde_bytes
serde_cbor
serde_derive
serde_json
serde_urlencoded
serde_yaml
sha1
sha2
sha3
signal_hook
signal_hook_registry
signature
simpl
simple_logger
slab
smallvec
smpl_jwt
snafu
snafu_derive
socket2
solana_account_decoder
solana_accounts_bench
solana_banking_bench
solana_banks_client
solana_banks_interface
solana_banks_server
solana_bench_exchange
solana_bench_streamer
solana_bench_tps
solana_bench_tps_evm
solana_bpf_loader_program
solana_budget_program
solana_clap_utils
solana_cli
solana_cli_config
solana_cli_output
solana_client
solana_config_program
solana_core
solana_crate_features
solana_csv_to_validator_infos
solana_dos
solana_download_utils
solana_evm_loader_program
solana_exchange_program
solana_failure_program
solana_faucet
solana_frozen_abi
solana_frozen_abi_macro
solana_genesis
solana_ip_address
solana_ip_address_server
solana_ledger
solana_ledger_tool
solana_ledger_udev
solana_local_cluster
solana_log_analyzer
solana_logger
solana_measure
solana_merkle_root_bench
solana_merkle_tree
solana_metrics
solana_net_shaper
solana_net_utils
solana_noop_program
solana_notifier
solana_ownable
solana_perf
solana_poh_bench
solana_program
solana_program_test
solana_ramp_tps
solana_rayon_threadlimit
solana_rbpf
solana_remote_wallet
solana_runtime
solana_sdk
solana_sdk_macro
solana_secp256k1_program
solana_sleep_program
solana_stake_accounts
solana_stake_monitor
solana_stake_o_matic
solana_stake_program
solana_storage_bigtable
solana_storage_proto
solana_store_tool
solana_streamer
solana_sys_tuner
solana_tokens
solana_transaction_status
solana_upload_perf
solana_version
solana_vest_program
solana_vote_program
solana_watchtower
spin
spl_associated_token_account
spl_memo
spl_token
stable_deref_trait
standback
static_assertions
strsim
structopt
structopt_derive
subtle
symlink
syn
synstructure
sysctl
tar
tarpc
tarpc_plugins
tempfile
termcolor
terminal_size
textwrap
thiserror
thiserror_impl
thread_scoped
time
time_macros
time_macros_impl
tiny_keccak
tinyvec
tinyvec_macros
tokio
fs
future
io
loom
macros
net
park
process
runtime
signal
stream
sync
task
time
util
tokio_codec
tokio_executor
tokio_fs
tokio_io
tokio_reactor
tokio_rustls
tokio_serde
tokio_sync
tokio_tcp
tokio_threadpool
tokio_tls
tokio_util
toml
tonic
tower
tower_balance
tower_buffer
tower_discover
tower_layer
tower_limit
tower_load
tower_load_shed
tower_make
tower_ready_cache
tower_retry
tower_service
tower_timeout
tower_util
tracing
tracing_attributes
tracing_core
tracing_futures
trees
triedb
triehash
try_lock
tungstenite
typenum
ucd_trie
uint
unicase
unicode_bidi
unicode_normalization
unicode_segmentation
unicode_width
unicode_xid
unix_socket
unreachable
untrusted
url
users
utf8
utf8_width
vec_map
velas
velas_account_program
velas_faucet
velas_genesis
velas_gossip
velas_install
velas_install_init
velas_keygen
velas_test_validator
velas_validator
void
walkdir
want
webpki
webpki_roots
websocket
websocket_base
winapi
ws2_32
xattr
yaml_rust
zeroize
zeroize_derive
zstd
zstd_safe
zstd_sys
  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
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
use std::cmp::Ordering;
use std::collections::HashMap;
use std::fmt;
use std::mem;
use std::ops::Deref;
use std::slice;
use std::sync::Arc;

use input::Char;
use literal::LiteralSearcher;

/// `InstPtr` represents the index of an instruction in a regex program.
pub type InstPtr = usize;

/// Program is a sequence of instructions and various facts about thos
/// instructions.
#[derive(Clone)]
pub struct Program {
    /// A sequence of instructions that represents an NFA.
    pub insts: Vec<Inst>,
    /// Pointers to each Match instruction in the sequence.
    ///
    /// This is always length 1 unless this program represents a regex set.
    pub matches: Vec<InstPtr>,
    /// The ordered sequence of all capture groups extracted from the AST.
    /// Unnamed groups are `None`.
    pub captures: Vec<Option<String>>,
    /// Pointers to all named capture groups into `captures`.
    pub capture_name_idx: Arc<HashMap<String, usize>>,
    /// A pointer to the start instruction. This can vary depending on how
    /// the program was compiled. For example, programs for use with the DFA
    /// engine have a `.*?` inserted at the beginning of unanchored regular
    /// expressions. The actual starting point of the program is after the
    /// `.*?`.
    pub start: InstPtr,
    /// A set of equivalence classes for discriminating bytes in the compiled
    /// program.
    pub byte_classes: Vec<u8>,
    /// When true, this program can only match valid UTF-8.
    pub only_utf8: bool,
    /// When true, this program uses byte range instructions instead of Unicode
    /// range instructions.
    pub is_bytes: bool,
    /// When true, the program is compiled for DFA matching. For example, this
    /// implies `is_bytes` and also inserts a preceding `.*?` for unanchored
    /// regexes.
    pub is_dfa: bool,
    /// When true, the program matches text in reverse (for use only in the
    /// DFA).
    pub is_reverse: bool,
    /// Whether the regex must match from the start of the input.
    pub is_anchored_start: bool,
    /// Whether the regex must match at the end of the input.
    pub is_anchored_end: bool,
    /// Whether this program contains a Unicode word boundary instruction.
    pub has_unicode_word_boundary: bool,
    /// A possibly empty machine for very quickly matching prefix literals.
    pub prefixes: LiteralSearcher,
    /// A limit on the size of the cache that the DFA is allowed to use while
    /// matching.
    ///
    /// The cache limit specifies approximately how much space we're willing to
    /// give to the state cache. Once the state cache exceeds the size, it is
    /// wiped and all states must be re-computed.
    ///
    /// Note that this value does not impact correctness. It can be set to 0
    /// and the DFA will run just fine. (It will only ever store exactly one
    /// state in the cache, and will likely run very slowly, but it will work.)
    ///
    /// Also note that this limit is *per thread of execution*. That is,
    /// if the same regex is used to search text across multiple threads
    /// simultaneously, then the DFA cache is not shared. Instead, copies are
    /// made.
    pub dfa_size_limit: usize,
}

impl Program {
    /// Creates an empty instruction sequence. Fields are given default
    /// values.
    pub fn new() -> Self {
        Program {
            insts: vec![],
            matches: vec![],
            captures: vec![],
            capture_name_idx: Arc::new(HashMap::new()),
            start: 0,
            byte_classes: vec![0; 256],
            only_utf8: true,
            is_bytes: false,
            is_dfa: false,
            is_reverse: false,
            is_anchored_start: false,
            is_anchored_end: false,
            has_unicode_word_boundary: false,
            prefixes: LiteralSearcher::empty(),
            dfa_size_limit: 2 * (1 << 20),
        }
    }

    /// If pc is an index to a no-op instruction (like Save), then return the
    /// next pc that is not a no-op instruction.
    pub fn skip(&self, mut pc: usize) -> usize {
        loop {
            match self[pc] {
                Inst::Save(ref i) => pc = i.goto,
                _ => return pc,
            }
        }
    }

    /// Return true if and only if an execution engine at instruction `pc` will
    /// always lead to a match.
    pub fn leads_to_match(&self, pc: usize) -> bool {
        if self.matches.len() > 1 {
            // If we have a regex set, then we have more than one ending
            // state, so leading to one of those states is generally
            // meaningless.
            return false;
        }
        match self[self.skip(pc)] {
            Inst::Match(_) => true,
            _ => false,
        }
    }

    /// Returns true if the current configuration demands that an implicit
    /// `.*?` be prepended to the instruction sequence.
    pub fn needs_dotstar(&self) -> bool {
        self.is_dfa && !self.is_reverse && !self.is_anchored_start
    }

    /// Returns true if this program uses Byte instructions instead of
    /// Char/Range instructions.
    pub fn uses_bytes(&self) -> bool {
        self.is_bytes || self.is_dfa
    }

    /// Returns true if this program exclusively matches valid UTF-8 bytes.
    ///
    /// That is, if an invalid UTF-8 byte is seen, then no match is possible.
    pub fn only_utf8(&self) -> bool {
        self.only_utf8
    }

    /// Return the approximate heap usage of this instruction sequence in
    /// bytes.
    pub fn approximate_size(&self) -> usize {
        // The only instruction that uses heap space is Ranges (for
        // Unicode codepoint programs) to store non-overlapping codepoint
        // ranges. To keep this operation constant time, we ignore them.
        (self.len() * mem::size_of::<Inst>())
            + (self.matches.len() * mem::size_of::<InstPtr>())
            + (self.captures.len() * mem::size_of::<Option<String>>())
            + (self.capture_name_idx.len()
                * (mem::size_of::<String>() + mem::size_of::<usize>()))
            + (self.byte_classes.len() * mem::size_of::<u8>())
            + self.prefixes.approximate_size()
    }
}

impl Deref for Program {
    type Target = [Inst];

    #[cfg_attr(feature = "perf-inline", inline(always))]
    fn deref(&self) -> &Self::Target {
        &*self.insts
    }
}

impl fmt::Debug for Program {
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        use self::Inst::*;

        fn with_goto(cur: usize, goto: usize, fmtd: String) -> String {
            if goto == cur + 1 {
                fmtd
            } else {
                format!("{} (goto: {})", fmtd, goto)
            }
        }

        fn visible_byte(b: u8) -> String {
            use std::ascii::escape_default;
            let escaped = escape_default(b).collect::<Vec<u8>>();
            String::from_utf8_lossy(&escaped).into_owned()
        }

        for (pc, inst) in self.iter().enumerate() {
            match *inst {
                Match(slot) => write!(f, "{:04} Match({:?})", pc, slot)?,
                Save(ref inst) => {
                    let s = format!("{:04} Save({})", pc, inst.slot);
                    write!(f, "{}", with_goto(pc, inst.goto, s))?;
                }
                Split(ref inst) => {
                    write!(
                        f,
                        "{:04} Split({}, {})",
                        pc, inst.goto1, inst.goto2
                    )?;
                }
                EmptyLook(ref inst) => {
                    let s = format!("{:?}", inst.look);
                    write!(f, "{:04} {}", pc, with_goto(pc, inst.goto, s))?;
                }
                Char(ref inst) => {
                    let s = format!("{:?}", inst.c);
                    write!(f, "{:04} {}", pc, with_goto(pc, inst.goto, s))?;
                }
                Ranges(ref inst) => {
                    let ranges = inst
                        .ranges
                        .iter()
                        .map(|r| format!("{:?}-{:?}", r.0, r.1))
                        .collect::<Vec<String>>()
                        .join(", ");
                    write!(
                        f,
                        "{:04} {}",
                        pc,
                        with_goto(pc, inst.goto, ranges)
                    )?;
                }
                Bytes(ref inst) => {
                    let s = format!(
                        "Bytes({}, {})",
                        visible_byte(inst.start),
                        visible_byte(inst.end)
                    );
                    write!(f, "{:04} {}", pc, with_goto(pc, inst.goto, s))?;
                }
            }
            if pc == self.start {
                write!(f, " (start)")?;
            }
            write!(f, "\n")?;
        }
        Ok(())
    }
}

impl<'a> IntoIterator for &'a Program {
    type Item = &'a Inst;
    type IntoIter = slice::Iter<'a, Inst>;
    fn into_iter(self) -> Self::IntoIter {
        self.iter()
    }
}

/// Inst is an instruction code in a Regex program.
///
/// Regrettably, a regex program either contains Unicode codepoint
/// instructions (Char and Ranges) or it contains byte instructions (Bytes).
/// A regex program can never contain both.
///
/// It would be worth investigating splitting this into two distinct types and
/// then figuring out how to make the matching engines polymorphic over those
/// types without sacrificing performance.
///
/// Other than the benefit of moving invariants into the type system, another
/// benefit is the decreased size. If we remove the `Char` and `Ranges`
/// instructions from the `Inst` enum, then its size shrinks from 40 bytes to
/// 24 bytes. (This is because of the removal of a `Vec` in the `Ranges`
/// variant.) Given that byte based machines are typically much bigger than
/// their Unicode analogues (because they can decode UTF-8 directly), this ends
/// up being a pretty significant savings.
#[derive(Clone, Debug)]
pub enum Inst {
    /// Match indicates that the program has reached a match state.
    ///
    /// The number in the match corresponds to the Nth logical regular
    /// expression in this program. This index is always 0 for normal regex
    /// programs. Values greater than 0 appear when compiling regex sets, and
    /// each match instruction gets its own unique value. The value corresponds
    /// to the Nth regex in the set.
    Match(usize),
    /// Save causes the program to save the current location of the input in
    /// the slot indicated by InstSave.
    Save(InstSave),
    /// Split causes the program to diverge to one of two paths in the
    /// program, preferring goto1 in InstSplit.
    Split(InstSplit),
    /// EmptyLook represents a zero-width assertion in a regex program. A
    /// zero-width assertion does not consume any of the input text.
    EmptyLook(InstEmptyLook),
    /// Char requires the regex program to match the character in InstChar at
    /// the current position in the input.
    Char(InstChar),
    /// Ranges requires the regex program to match the character at the current
    /// position in the input with one of the ranges specified in InstRanges.
    Ranges(InstRanges),
    /// Bytes is like Ranges, except it expresses a single byte range. It is
    /// used in conjunction with Split instructions to implement multi-byte
    /// character classes.
    Bytes(InstBytes),
}

impl Inst {
    /// Returns true if and only if this is a match instruction.
    pub fn is_match(&self) -> bool {
        match *self {
            Inst::Match(_) => true,
            _ => false,
        }
    }
}

/// Representation of the Save instruction.
#[derive(Clone, Debug)]
pub struct InstSave {
    /// The next location to execute in the program.
    pub goto: InstPtr,
    /// The capture slot (there are two slots for every capture in a regex,
    /// including the zeroth capture for the entire match).
    pub slot: usize,
}

/// Representation of the Split instruction.
#[derive(Clone, Debug)]
pub struct InstSplit {
    /// The first instruction to try. A match resulting from following goto1
    /// has precedence over a match resulting from following goto2.
    pub goto1: InstPtr,
    /// The second instruction to try. A match resulting from following goto1
    /// has precedence over a match resulting from following goto2.
    pub goto2: InstPtr,
}

/// Representation of the `EmptyLook` instruction.
#[derive(Clone, Debug)]
pub struct InstEmptyLook {
    /// The next location to execute in the program if this instruction
    /// succeeds.
    pub goto: InstPtr,
    /// The type of zero-width assertion to check.
    pub look: EmptyLook,
}

/// The set of zero-width match instructions.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum EmptyLook {
    /// Start of line or input.
    StartLine,
    /// End of line or input.
    EndLine,
    /// Start of input.
    StartText,
    /// End of input.
    EndText,
    /// Word character on one side and non-word character on other.
    WordBoundary,
    /// Word character on both sides or non-word character on both sides.
    NotWordBoundary,
    /// ASCII word boundary.
    WordBoundaryAscii,
    /// Not ASCII word boundary.
    NotWordBoundaryAscii,
}

/// Representation of the Char instruction.
#[derive(Clone, Debug)]
pub struct InstChar {
    /// The next location to execute in the program if this instruction
    /// succeeds.
    pub goto: InstPtr,
    /// The character to test.
    pub c: char,
}

/// Representation of the Ranges instruction.
#[derive(Clone, Debug)]
pub struct InstRanges {
    /// The next location to execute in the program if this instruction
    /// succeeds.
    pub goto: InstPtr,
    /// The set of Unicode scalar value ranges to test.
    pub ranges: Vec<(char, char)>,
}

impl InstRanges {
    /// Tests whether the given input character matches this instruction.
    pub fn matches(&self, c: Char) -> bool {
        // This speeds up the `match_class_unicode` benchmark by checking
        // some common cases quickly without binary search. e.g., Matching
        // a Unicode class on predominantly ASCII text.
        for r in self.ranges.iter().take(4) {
            if c < r.0 {
                return false;
            }
            if c <= r.1 {
                return true;
            }
        }
        self.ranges
            .binary_search_by(|r| {
                if r.1 < c {
                    Ordering::Less
                } else if r.0 > c {
                    Ordering::Greater
                } else {
                    Ordering::Equal
                }
            })
            .is_ok()
    }

    /// Return the number of distinct characters represented by all of the
    /// ranges.
    pub fn num_chars(&self) -> usize {
        self.ranges
            .iter()
            .map(|&(s, e)| 1 + (e as u32) - (s as u32))
            .sum::<u32>() as usize
    }
}

/// Representation of the Bytes instruction.
#[derive(Clone, Debug)]
pub struct InstBytes {
    /// The next location to execute in the program if this instruction
    /// succeeds.
    pub goto: InstPtr,
    /// The start (inclusive) of this byte range.
    pub start: u8,
    /// The end (inclusive) of this byte range.
    pub end: u8,
}

impl InstBytes {
    /// Returns true if and only if the given byte is in this range.
    pub fn matches(&self, byte: u8) -> bool {
        self.start <= byte && byte <= self.end
    }
}