Files
adler32
aho_corasick
approx
arrayvec
ascii
backtrace
backtrace_sys
base64
bitflags
brotli2
brotli_sys
bstr
buf_redux
byteorder
bytes
cfg_if
chrono
chunked_transfer
color_quant
cookie
cookie_store
crc32fast
crossbeam_deque
crossbeam_epoch
crossbeam_queue
crossbeam_utils
csv
csv_core
csv_user_import
deflate
diesel
associations
connection
expression
expression_methods
macros
migration
mysql
query_builder
query_dsl
query_source
sql_types
type_impls
types
diesel_derives
diesel_migrations
dirs
dotenv
dtoa
either
encoding_rs
error_chain
failure
failure_derive
filetime
flate2
fnv
foreign_types
foreign_types_shared
futures
futures_cpupool
gif
google_signin
gzip_header
h2
http
http_body
httparse
hyper
hyper_rustls
hyper_tls
idna
image
indexmap
inflate
iovec
itoa
jpeg_decoder
language_tags
lazy_static
libc
lock_api
log
lzw
matches
memchr
memoffset
migrations_internals
migrations_macros
mime
mime_guess
miniz_oxide
mio
multipart
mysqlclient_sys
native_tls
net2
nodrop
num_cpus
num_derive
num_integer
num_iter
num_rational
num_traits
openssl
openssl_probe
openssl_sys
ordered_float
owning_ref
parking_lot
parking_lot_core
percent_encoding
phf
phf_shared
png
proc_macro2
publicsuffix
quick_error
quote
r2d2
rand
rand_chacha
rand_core
rand_hc
rand_isaac
rand_jitter
rand_os
rand_pcg
rand_xorshift
rayon
rayon_core
regex
regex_automata
regex_syntax
remove_dir_all
reqwest
ring
rouille
rustc_demangle
rustls
rusttype
ryu
safemem
scheduled_thread_pool
scoped_threadpool
scopeguard
sct
serde
serde_derive
serde_json
serde_urlencoded
sha1
simplelog
siphasher
slab
smallvec
stable_deref_trait
stb_truetype
string
syn
synom
synstructure
tempdir
term
thread_local
threadpool
tiff
time
tiny_http
tokio
tokio_buf
tokio_current_thread
tokio_executor
tokio_io
tokio_reactor
tokio_sync
tokio_tcp
tokio_threadpool
tokio_timer
traitobject
try_from
try_lock
twoway
typeable
unicase
unicode_bidi
unicode_normalization
unicode_xid
untrusted
url
uuid
want
webdev_lib
webpki
webpki_roots
  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
// Copyright 2015-2016 Mozilla Foundation. See the COPYRIGHT
// file at the top-level directory of this distribution.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

use super::*;
use data::*;
use handles::*;
use variant::*;
// Rust 1.14.0 requires the following despite the asterisk above.
use super::in_inclusive_range32;

pub struct Big5Decoder {
    lead: Option<u8>,
}

impl Big5Decoder {
    pub fn new() -> VariantDecoder {
        VariantDecoder::Big5(Big5Decoder { lead: None })
    }

    pub fn in_neutral_state(&self) -> bool {
        self.lead.is_none()
    }

    fn plus_one_if_lead(&self, byte_length: usize) -> Option<usize> {
        byte_length.checked_add(match self.lead {
            None => 0,
            Some(_) => 1,
        })
    }

    pub fn max_utf16_buffer_length(&self, byte_length: usize) -> Option<usize> {
        // If there is a lead but the next byte isn't a valid trail, an
        // error is generated for the lead (+1). Then another iteration checks
        // space, which needs +1 to account for the possibility of astral
        // output or combining pair.
        checked_add(1, self.plus_one_if_lead(byte_length))
    }

    pub fn max_utf8_buffer_length_without_replacement(&self, byte_length: usize) -> Option<usize> {
        // No need to account for REPLACEMENT CHARACTERS.
        // Cases:
        // ASCII: 1 to 1
        // Valid pair: 2 to 2, 2 to 3 or 2 to 4, i.e. worst case 2 to 4
        // lead set and first byte is trail: 1 to 4 worst case
        //
        // When checking for space for the last byte:
        // no lead: the last byte must be ASCII (or fatal error): 1 to 1
        // lead set: space for 4 bytes was already checked when reading the
        // lead, hence the last lead and the last trail together are worst
        // case 2 to 4.
        //
        // If lead set and the input is a single trail byte, the worst-case
        // output is 4, so we need to add one before multiplying if lead is
        // set.
        //
        // Finally, add two so that if input is non-zero, the output is at
        // least 4.
        checked_add(2, checked_mul(2, self.plus_one_if_lead(byte_length)))
    }

    pub fn max_utf8_buffer_length(&self, byte_length: usize) -> Option<usize> {
        // If there is a lead but the next byte isn't a valid trail, an
        // error is generated for the lead (+(1*3)). Then another iteration
        // checks space, which needs +3 to account for the possibility of astral
        // output or combining pair. In between start and end, the worst case
        // is that every byte is bad: *3.
        checked_add(3, checked_mul(3, self.plus_one_if_lead(byte_length)))
    }

    ascii_compatible_two_byte_decoder_functions!(
        {
            // If lead is between 0x81 and 0xFE, inclusive,
            // subtract offset 0x81.
            let non_ascii_minus_offset =
                non_ascii.wrapping_sub(0x81);
            if non_ascii_minus_offset > (0xFE - 0x81) {
                return (DecoderResult::Malformed(1, 0),
                        source.consumed(),
                        handle.written());
            }
            non_ascii_minus_offset
        },
        {
            // If trail is between 0x40 and 0x7E, inclusive,
            // subtract offset 0x40. Else if trail is
            // between 0xA1 and 0xFE, inclusive, subtract
            // offset 0x62.
            // TODO: Find out which range is more probable.
            let mut trail_minus_offset =
                byte.wrapping_sub(0x40);
            if trail_minus_offset > (0x7E - 0x40) {
                let trail_minus_range_start =
                    byte.wrapping_sub(0xA1);
                if trail_minus_range_start >
                   (0xFE - 0xA1) {
                    if byte < 0x80 {
                        return (DecoderResult::Malformed(1, 0),
                                unread_handle_trail.unread(),
                                handle.written());
                    }
                    return (DecoderResult::Malformed(2, 0),
                            unread_handle_trail.consumed(),
                            handle.written());
                }
                trail_minus_offset = byte - 0x62;
            }
            let pointer = lead_minus_offset as usize *
                          157usize +
                          trail_minus_offset as usize;
            let rebased_pointer = pointer.wrapping_sub(942);
            let low_bits = big5_low_bits(rebased_pointer);
            if low_bits == 0 {
                match pointer {
                    1133 => {
                        handle.write_big5_combination(0x00CAu16,
                                                      0x0304u16)
                    }
                    1135 => {
                        handle.write_big5_combination(0x00CAu16,
                                                      0x030Cu16)
                    }
                    1164 => {
                        handle.write_big5_combination(0x00EAu16,
                                                      0x0304u16)
                    }
                    1166 => {
                        handle.write_big5_combination(0x00EAu16,
                                                      0x030Cu16)
                    }
                    _ => {
                        if byte < 0x80 {
                            return (DecoderResult::Malformed(1, 0),
                                    unread_handle_trail.unread(),
                                    handle.written());
                        }
                        return (DecoderResult::Malformed(2, 0),
                                unread_handle_trail.consumed(),
                                handle.written());
                    }
                }
            } else if big5_is_astral(rebased_pointer) {
                handle.write_astral(u32::from(low_bits) |
                                    0x20000u32)
            } else {
                handle.write_bmp_excl_ascii(low_bits)
            }
        },
        self,
        non_ascii,
        byte,
        lead_minus_offset,
        unread_handle_trail,
        source,
        handle,
        'outermost,
        copy_ascii_from_check_space_astral,
        check_space_astral,
        false);
}

pub struct Big5Encoder;

impl Big5Encoder {
    pub fn new(encoding: &'static Encoding) -> Encoder {
        Encoder::new(encoding, VariantEncoder::Big5(Big5Encoder))
    }

    pub fn max_buffer_length_from_utf16_without_replacement(
        &self,
        u16_length: usize,
    ) -> Option<usize> {
        // Astral: 2 to 2
        // ASCII: 1 to 1
        // Other: 1 to 2
        u16_length.checked_mul(2)
    }

    pub fn max_buffer_length_from_utf8_without_replacement(
        &self,
        byte_length: usize,
    ) -> Option<usize> {
        // Astral: 4 to 2
        // Upper BMP: 3 to 2
        // Lower BMP: 2 to 2
        // ASCII: 1 to 1
        byte_length.checked_add(1)
    }

    ascii_compatible_encoder_functions!(
        {
            // For simplicity, unified ideographs
            // in the pointer range 11206...11212 are handled
            // as Level 1 Hanzi.
            if let Some((lead, trail)) = big5_level1_hanzi_encode(bmp) {
                handle.write_two(lead, trail)
            } else {
                let pointer = if let Some(pointer) = big5_box_encode(bmp) {
                    pointer
                } else if let Some(pointer) = big5_other_encode(bmp) {
                    pointer
                } else {
                    return (
                        EncoderResult::unmappable_from_bmp(bmp),
                        source.consumed(),
                        handle.written(),
                    );
                };
                let lead = pointer / 157 + 0x81;
                let remainder = pointer % 157;
                let trail = if remainder < 0x3F {
                    remainder + 0x40
                } else {
                    remainder + 0x62
                };
                handle.write_two(lead as u8, trail as u8)
            }
        },
        {
            if in_inclusive_range32(astral as u32, 0x2008A, 0x2F8A6) {
                if let Some(rebased_pointer) = big5_astral_encode(astral as u16) {
                    // big5_astral_encode returns rebased pointer,
                    // so adding 0x87 instead of 0x81.
                    let lead = rebased_pointer / 157 + 0x87;
                    let remainder = rebased_pointer % 157;
                    let trail = if remainder < 0x3F {
                        remainder + 0x40
                    } else {
                        remainder + 0x62
                    };
                    handle.write_two(lead as u8, trail as u8)
                } else {
                    return (
                        EncoderResult::Unmappable(astral),
                        source.consumed(),
                        handle.written(),
                    );
                }
            } else {
                return (
                    EncoderResult::Unmappable(astral),
                    source.consumed(),
                    handle.written(),
                );
            }
        },
        bmp,
        astral,
        self,
        source,
        handle,
        copy_ascii_to_check_space_two,
        check_space_two,
        false
    );
}

// Any copyright to the test code below this comment is dedicated to the
// Public Domain. http://creativecommons.org/publicdomain/zero/1.0/

#[cfg(test)]
mod tests {
    use super::super::testing::*;
    use super::super::*;

    fn decode_big5(bytes: &[u8], expect: &str) {
        decode(BIG5, bytes, expect);
    }

    fn encode_big5(string: &str, expect: &[u8]) {
        encode(BIG5, string, expect);
    }

    #[test]
    fn test_big5_decode() {
        // Empty
        decode_big5(b"", &"");

        // ASCII
        decode_big5(&[0x61u8, 0x62u8], &"\u{0061}\u{0062}");

        // Edge cases
        decode_big5(&[0x87u8, 0x40u8], &"\u{43F0}");
        decode_big5(&[0xFEu8, 0xFEu8], &"\u{79D4}");
        decode_big5(&[0xFEu8, 0xFDu8], &"\u{2910D}");
        decode_big5(&[0x88u8, 0x62u8], &"\u{00CA}\u{0304}");
        decode_big5(&[0x88u8, 0x64u8], &"\u{00CA}\u{030C}");
        decode_big5(&[0x88u8, 0x66u8], &"\u{00CA}");
        decode_big5(&[0x88u8, 0xA3u8], &"\u{00EA}\u{0304}");
        decode_big5(&[0x88u8, 0xA5u8], &"\u{00EA}\u{030C}");
        decode_big5(&[0x88u8, 0xA7u8], &"\u{00EA}");
        decode_big5(&[0x99u8, 0xD4u8], &"\u{8991}");
        decode_big5(&[0x99u8, 0xD5u8], &"\u{27967}");
        decode_big5(&[0x99u8, 0xD6u8], &"\u{8A29}");

        // Edge cases surrounded with ASCII
        decode_big5(
            &[0x61u8, 0x87u8, 0x40u8, 0x62u8],
            &"\u{0061}\u{43F0}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0xFEu8, 0xFEu8, 0x62u8],
            &"\u{0061}\u{79D4}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0xFEu8, 0xFDu8, 0x62u8],
            &"\u{0061}\u{2910D}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0x62u8, 0x62u8],
            &"\u{0061}\u{00CA}\u{0304}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0x64u8, 0x62u8],
            &"\u{0061}\u{00CA}\u{030C}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0x66u8, 0x62u8],
            &"\u{0061}\u{00CA}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0xA3u8, 0x62u8],
            &"\u{0061}\u{00EA}\u{0304}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0xA5u8, 0x62u8],
            &"\u{0061}\u{00EA}\u{030C}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x88u8, 0xA7u8, 0x62u8],
            &"\u{0061}\u{00EA}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x99u8, 0xD4u8, 0x62u8],
            &"\u{0061}\u{8991}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x99u8, 0xD5u8, 0x62u8],
            &"\u{0061}\u{27967}\u{0062}",
        );
        decode_big5(
            &[0x61u8, 0x99u8, 0xD6u8, 0x62u8],
            &"\u{0061}\u{8A29}\u{0062}",
        );

        // Bad sequences
        decode_big5(&[0x80u8, 0x61u8], &"\u{FFFD}\u{0061}");
        decode_big5(&[0xFFu8, 0x61u8], &"\u{FFFD}\u{0061}");
        decode_big5(&[0xFEu8, 0x39u8], &"\u{FFFD}\u{0039}");
        decode_big5(&[0x87u8, 0x66u8], &"\u{FFFD}\u{0066}");
        decode_big5(&[0x81u8, 0x40u8], &"\u{FFFD}\u{0040}");
        decode_big5(&[0x61u8, 0x81u8], &"\u{0061}\u{FFFD}");
    }

    #[test]
    fn test_big5_encode() {
        // Empty
        encode_big5("", b"");

        // ASCII
        encode_big5("\u{0061}\u{0062}", b"\x61\x62");

        // Edge cases
        encode_big5("\u{9EA6}\u{0061}", b"&#40614;\x61");
        encode_big5("\u{2626B}\u{0061}", b"&#156267;\x61");
        encode_big5("\u{3000}", b"\xA1\x40");
        encode_big5("\u{20AC}", b"\xA3\xE1");
        encode_big5("\u{4E00}", b"\xA4\x40");
        encode_big5("\u{27607}", b"\xC8\xA4");
        encode_big5("\u{FFE2}", b"\xC8\xCD");
        encode_big5("\u{79D4}", b"\xFE\xFE");

        // Not in index
        encode_big5("\u{2603}\u{0061}", b"&#9731;\x61");

        // duplicate low bits
        encode_big5("\u{203B5}", b"\xFD\x6A");
        encode_big5("\u{25605}", b"\xFE\x46");

        // prefer last
        encode_big5("\u{2550}", b"\xF9\xF9");
    }

    #[test]
    fn test_big5_decode_all() {
        let input = include_bytes!("test_data/big5_in.txt");
        let expectation = include_str!("test_data/big5_in_ref.txt");
        let (cow, had_errors) = BIG5.decode_without_bom_handling(input);
        assert!(had_errors, "Should have had errors.");
        assert_eq!(&cow[..], expectation);
    }

    #[test]
    fn test_big5_encode_all() {
        let input = include_str!("test_data/big5_out.txt");
        let expectation = include_bytes!("test_data/big5_out_ref.txt");
        let (cow, encoding, had_errors) = BIG5.encode(input);
        assert!(!had_errors, "Should not have had errors.");
        assert_eq!(encoding, BIG5);
        assert_eq!(&cow[..], &expectation[..]);
    }

    #[test]
    fn test_big5_encode_from_two_low_surrogates() {
        let expectation = b"&#65533;&#65533;";
        let mut output = [0u8; 40];
        let mut encoder = BIG5.new_encoder();
        let (result, read, written, had_errors) =
            encoder.encode_from_utf16(&[0xDC00u16, 0xDEDEu16], &mut output[..], true);
        assert_eq!(result, CoderResult::InputEmpty);
        assert_eq!(read, 2);
        assert_eq!(written, expectation.len());
        assert!(had_errors);
        assert_eq!(&output[..written], expectation);
    }
}