Files
adler32
backtrace
backtrace_sys
base64
bigtable
bitflags
byteorder
bytes
cfg_if
cookie
cookie_store
crc32fast
crossbeam_deque
crossbeam_epoch
crossbeam_queue
crossbeam_utils
curl
curl_sys
dtoa
either
encoding_rs
error_chain
failure
failure_derive
flate2
fnv
foreign_types
foreign_types_shared
futures
futures_cpupool
goauth
h2
http
http_body
httparse
hyper
hyper_tls
idna
indexmap
iovec
itoa
lazy_static
libc
libz_sys
lock_api
log
matches
maybe_uninit
memoffset
mime
mime_guess
miniz_oxide
mio
native_tls
net2
num_cpus
num_traits
openssl
openssl_probe
openssl_sys
parking_lot
parking_lot_core
percent_encoding
proc_macro2
protobuf
protobuf_json
publicsuffix
quote
rand
rand_chacha
rand_core
rand_hc
rand_isaac
rand_jitter
rand_os
rand_pcg
rand_xorshift
regex
regex_syntax
reqwest
rustc_demangle
rustc_serialize
ryu
scopeguard
serde
serde_codegen_internals
serde_derive
serde_json
serde_urlencoded
slab
smallvec
smpl_jwt
socket2
string
syn
synom
synstructure
time
tokio
tokio_buf
tokio_current_thread
tokio_executor
tokio_io
tokio_reactor
tokio_sync
tokio_tcp
tokio_threadpool
tokio_timer
try_from
try_lock
unicase
unicode_bidi
unicode_normalization
unicode_xid
url
uuid
want
  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
use std::str;

use find_byte::find_byte;

use re_bytes;
use re_unicode;

pub fn expand_str(
    caps: &re_unicode::Captures,
    mut replacement: &str,
    dst: &mut String,
) {
    while !replacement.is_empty() {
        match find_byte(b'$', replacement.as_bytes()) {
            None => break,
            Some(i) => {
                dst.push_str(&replacement[..i]);
                replacement = &replacement[i..];
            }
        }
        if replacement.as_bytes().get(1).map_or(false, |&b| b == b'$') {
            dst.push_str("$");
            replacement = &replacement[2..];
            continue;
        }
        debug_assert!(!replacement.is_empty());
        let cap_ref = match find_cap_ref(replacement) {
            Some(cap_ref) => cap_ref,
            None => {
                dst.push_str("$");
                replacement = &replacement[1..];
                continue;
            }
        };
        replacement = &replacement[cap_ref.end..];
        match cap_ref.cap {
            Ref::Number(i) => {
                dst.push_str(caps.get(i).map(|m| m.as_str()).unwrap_or(""));
            }
            Ref::Named(name) => {
                dst.push_str(
                    caps.name(name).map(|m| m.as_str()).unwrap_or(""),
                );
            }
        }
    }
    dst.push_str(replacement);
}

pub fn expand_bytes(
    caps: &re_bytes::Captures,
    mut replacement: &[u8],
    dst: &mut Vec<u8>,
) {
    while !replacement.is_empty() {
        match find_byte(b'$', replacement) {
            None => break,
            Some(i) => {
                dst.extend(&replacement[..i]);
                replacement = &replacement[i..];
            }
        }
        if replacement.get(1).map_or(false, |&b| b == b'$') {
            dst.push(b'$');
            replacement = &replacement[2..];
            continue;
        }
        debug_assert!(!replacement.is_empty());
        let cap_ref = match find_cap_ref(replacement) {
            Some(cap_ref) => cap_ref,
            None => {
                dst.push(b'$');
                replacement = &replacement[1..];
                continue;
            }
        };
        replacement = &replacement[cap_ref.end..];
        match cap_ref.cap {
            Ref::Number(i) => {
                dst.extend(caps.get(i).map(|m| m.as_bytes()).unwrap_or(b""));
            }
            Ref::Named(name) => {
                dst.extend(
                    caps.name(name).map(|m| m.as_bytes()).unwrap_or(b""),
                );
            }
        }
    }
    dst.extend(replacement);
}

/// `CaptureRef` represents a reference to a capture group inside some text.
/// The reference is either a capture group name or a number.
///
/// It is also tagged with the position in the text following the
/// capture reference.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
struct CaptureRef<'a> {
    cap: Ref<'a>,
    end: usize,
}

/// A reference to a capture group in some text.
///
/// e.g., `$2`, `$foo`, `${foo}`.
#[derive(Clone, Copy, Debug, Eq, PartialEq)]
enum Ref<'a> {
    Named(&'a str),
    Number(usize),
}

impl<'a> From<&'a str> for Ref<'a> {
    fn from(x: &'a str) -> Ref<'a> {
        Ref::Named(x)
    }
}

impl From<usize> for Ref<'static> {
    fn from(x: usize) -> Ref<'static> {
        Ref::Number(x)
    }
}

/// Parses a possible reference to a capture group name in the given text,
/// starting at the beginning of `replacement`.
///
/// If no such valid reference could be found, None is returned.
fn find_cap_ref<T: ?Sized + AsRef<[u8]>>(
    replacement: &T,
) -> Option<CaptureRef> {
    let mut i = 0;
    let rep: &[u8] = replacement.as_ref();
    if rep.len() <= 1 || rep[0] != b'$' {
        return None;
    }
    let mut brace = false;
    i += 1;
    if rep[i] == b'{' {
        brace = true;
        i += 1;
    }
    let mut cap_end = i;
    while rep.get(cap_end).map_or(false, is_valid_cap_letter) {
        cap_end += 1;
    }
    if cap_end == i {
        return None;
    }
    // We just verified that the range 0..cap_end is valid ASCII, so it must
    // therefore be valid UTF-8. If we really cared, we could avoid this UTF-8
    // check with either unsafe or by parsing the number straight from &[u8].
    let cap =
        str::from_utf8(&rep[i..cap_end]).expect("valid UTF-8 capture name");
    if brace {
        if !rep.get(cap_end).map_or(false, |&b| b == b'}') {
            return None;
        }
        cap_end += 1;
    }
    Some(CaptureRef {
        cap: match cap.parse::<u32>() {
            Ok(i) => Ref::Number(i as usize),
            Err(_) => Ref::Named(cap),
        },
        end: cap_end,
    })
}

/// Returns true if and only if the given byte is allowed in a capture name.
fn is_valid_cap_letter(b: &u8) -> bool {
    match *b {
        b'0'..=b'9' | b'a'..=b'z' | b'A'..=b'Z' | b'_' => true,
        _ => false,
    }
}

#[cfg(test)]
mod tests {
    use super::{find_cap_ref, CaptureRef};

    macro_rules! find {
        ($name:ident, $text:expr) => {
            #[test]
            fn $name() {
                assert_eq!(None, find_cap_ref($text));
            }
        };
        ($name:ident, $text:expr, $capref:expr) => {
            #[test]
            fn $name() {
                assert_eq!(Some($capref), find_cap_ref($text));
            }
        };
    }

    macro_rules! c {
        ($name_or_number:expr, $pos:expr) => {
            CaptureRef { cap: $name_or_number.into(), end: $pos }
        };
    }

    find!(find_cap_ref1, "$foo", c!("foo", 4));
    find!(find_cap_ref2, "${foo}", c!("foo", 6));
    find!(find_cap_ref3, "$0", c!(0, 2));
    find!(find_cap_ref4, "$5", c!(5, 2));
    find!(find_cap_ref5, "$10", c!(10, 3));
    // see https://github.com/rust-lang/regex/pull/585 for more on characters following numbers
    find!(find_cap_ref6, "$42a", c!("42a", 4));
    find!(find_cap_ref7, "${42}a", c!(42, 5));
    find!(find_cap_ref8, "${42");
    find!(find_cap_ref9, "${42 ");
    find!(find_cap_ref10, " $0 ");
    find!(find_cap_ref11, "$");
    find!(find_cap_ref12, " ");
    find!(find_cap_ref13, "");
    find!(find_cap_ref14, "$1-$2", c!(1, 2));
    find!(find_cap_ref15, "$1_$2", c!("1_", 3));
    find!(find_cap_ref16, "$x-$y", c!("x", 2));
    find!(find_cap_ref17, "$x_$y", c!("x_", 3));
}