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
/*
* Copyright 2021 ZXing authors
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
use unicode_segmentation::UnicodeSegmentation;
use super::{CharacterSet, Eci};
use once_cell::sync::Lazy;
// static ENCODERS: Lazy<Vec<CharacterSet>> = Lazy::new(|| {
// let mut enc_vec = Vec::new();
// for name in NAMES {
// if let Some(enc) = CharacterSet::get_character_set_by_name(name) {
// enc_vec.push(enc);
// }
// }
// enc_vec
// });
// const NAMES: [&str; 20] = [
// "IBM437",
// "ISO-8859-2",
// "ISO-8859-3",
// "ISO-8859-4",
// "ISO-8859-5",
// "ISO-8859-6",
// "ISO-8859-7",
// "ISO-8859-8",
// "ISO-8859-9",
// "ISO-8859-10",
// "ISO-8859-11",
// "ISO-8859-13",
// "ISO-8859-14",
// "ISO-8859-15",
// "ISO-8859-16",
// "windows-1250",
// "windows-1251",
// "windows-1252",
// "windows-1256",
// "Shift_JIS",
// ];
static ENCODERS: Lazy<Vec<CharacterSet>> = Lazy::new(|| {
vec![
CharacterSet::Cp437,
CharacterSet::ISO8859_2,
CharacterSet::ISO8859_3,
CharacterSet::ISO8859_4,
CharacterSet::ISO8859_5,
// CharacterSet::ISO8859_6,
CharacterSet::ISO8859_7,
// CharacterSet::ISO8859_8,
CharacterSet::ISO8859_9,
// CharacterSet::ISO8859_10,
// CharacterSet::ISO8859_11,
// CharacterSet::ISO8859_13,
// CharacterSet::ISO8859_14,
CharacterSet::ISO8859_15,
CharacterSet::ISO8859_16,
CharacterSet::Shift_JIS,
CharacterSet::Cp1250,
CharacterSet::Cp1251,
CharacterSet::Cp1252,
CharacterSet::Cp1256,
]
});
/**
* Set of CharsetEncoders for a given input string
*
* Invariants:
* - The list contains only encoders from CharacterSetECI (list is shorter then the list of encoders available on
* the platform for which ECI values are defined).
* - The list contains encoders at least one encoder for every character in the input.
* - The first encoder in the list is always the ISO-8859-1 encoder even of no character in the input can be encoded
* by it.
* - If the input contains a character that is not in ISO-8859-1 then the last two entries in the list will be the
* UTF-8 encoder and the UTF-16BE encoder.
*
* @author Alex Geller
*/
#[derive(Clone)]
pub struct ECIEncoderSet {
encoders: Vec<CharacterSet>,
priorityEncoderIndex: Option<usize>,
}
impl ECIEncoderSet {
/**
* Constructs an encoder set
*
* @param stringToEncode the string that needs to be encoded
* @param priorityCharset The preferred {@link Charset} or null.
* @param fnc1 fnc1 denotes the character in the input that represents the FNC1 character or -1 for a non-GS1 bar
* code. When specified, it is considered an error to pass it as argument to the methods canEncode() or encode().
*/
pub fn new(
stringToEncodeMain: &str,
priorityCharset: Option<CharacterSet>,
fnc1: Option<&str>,
) -> Self {
// List of encoders that potentially encode characters not in ISO-8859-1 in one byte.
let mut encoders: Vec<CharacterSet>;
let mut priorityEncoderIndexValue = None;
let mut neededEncoders: Vec<CharacterSet> = Vec::new();
let stringToEncode = stringToEncodeMain.graphemes(true).collect::<Vec<&str>>();
//we always need the ISO-8859-1 encoder. It is the default encoding
neededEncoders.push(CharacterSet::ISO8859_1);
let mut needUnicodeEncoder = if let Some(pc) = priorityCharset {
//pc.name().starts_with("UTF") || pc.name().starts_with("utf")
pc == CharacterSet::UTF8 || pc == CharacterSet::UTF16BE
} else {
false
};
//Walk over the input string and see if all characters can be encoded with the list of encoders
for i in 0..stringToEncode.len() {
// for (int i = 0; i < stringToEncode.length(); i++) {
let mut canEncode = false;
for encoder in &neededEncoders {
// for (CharsetEncoder encoder : neededEncoders) {
let c = stringToEncode.get(i).unwrap();
if (fnc1.is_some() && c == fnc1.as_ref().unwrap()) || encoder.encode(c).is_ok() {
canEncode = true;
break;
}
}
if !canEncode {
//for the character at position i we don't yet have an encoder in the list
for i_encoder in 0..ENCODERS.len() {
// for encoder in ENCODERS {
let encoder = ENCODERS.get(i_encoder).unwrap();
// for (CharsetEncoder encoder : ENCODERS) {
if encoder.encode(stringToEncode.get(i).unwrap()).is_ok() {
//Good, we found an encoder that can encode the character. We add him to the list and continue scanning
//the input
neededEncoders.push(*encoder);
canEncode = true;
break;
}
}
}
if !canEncode {
//The character is not encodeable by any of the single byte encoders so we remember that we will need a
//Unicode encoder.
needUnicodeEncoder = true;
}
}
if neededEncoders.len() == 1 && !needUnicodeEncoder {
//the entire input can be encoded by the ISO-8859-1 encoder
encoders = vec![CharacterSet::ISO8859_1];
} else {
// we need more than one single byte encoder or we need a Unicode encoder.
// In this case we append a UTF-8 and UTF-16 encoder to the list
// encoders = [] new CharsetEncoder[neededEncoders.size() + 2];
encoders = Vec::new();
// let index = 0;
for encoder in neededEncoders {
// for (CharsetEncoder encoder : neededEncoders) {
//encoders[index++] = encoder;
encoders.push(encoder);
}
encoders.push(CharacterSet::UTF8);
encoders.push(CharacterSet::UTF16BE);
}
//Compute priorityEncoderIndex by looking up priorityCharset in encoders
// if priorityCharset != null {
if priorityCharset.is_some() {
// for i in 0..encoders.len() {
for (i, encoder) in encoders.iter().enumerate() {
// for (int i = 0; i < encoders.length; i++) {
// if priorityCharset.as_ref().unwrap().name() == encoder.name() {
if priorityCharset.as_ref().unwrap() == encoder {
priorityEncoderIndexValue = Some(i);
break;
}
}
}
// }
//invariants
assert_eq!(encoders[0], CharacterSet::ISO8859_1);
Self {
encoders,
priorityEncoderIndex: priorityEncoderIndexValue,
}
}
pub fn len(&self) -> usize {
self.encoders.len()
}
pub fn is_empty(&self) -> bool {
self.encoders.is_empty()
}
pub fn getCharsetName(&self, index: usize) -> Option<&'static str> {
if index < self.len() {
Some(self.encoders[index].get_charset_name())
} else {
None
}
}
pub fn getCharset(&self, index: usize) -> Option<CharacterSet> {
if index < self.len() {
Some(self.encoders[index])
} else {
None
}
}
pub fn get_eci(&self, encoderIndex: usize) -> Eci {
self.encoders[encoderIndex].into()
// CharacterSetECI::getValue(
// &CharacterSetECI::getCharacterSetECI(self.encoders[encoderIndex]).unwrap(),
// )
}
/*
* returns -1 if no priority charset was defined
*/
pub fn getPriorityEncoderIndex(&self) -> Option<usize> {
self.priorityEncoderIndex
}
pub fn canEncode(&self, c: &str, encoderIndex: usize) -> Option<bool> {
if encoderIndex < self.len() {
let encoder = self.encoders[encoderIndex];
let enc_data = encoder.encode(c);
Some(enc_data.is_ok())
} else {
None
}
}
pub fn encode_char(&self, c: &str, encoderIndex: usize) -> Option<Vec<u8>> {
if encoderIndex < self.len() {
let encoder = self.encoders[encoderIndex];
let enc_data = encoder.encode(c);
enc_data.ok()
// assert!(enc_data.is_ok());
// enc_data.unwrap()
} else {
None
}
}
pub fn encode_string(&self, s: &str, encoderIndex: usize) -> Option<Vec<u8>> {
if encoderIndex < self.len() {
let encoder = self.encoders[encoderIndex];
encoder.encode(s).ok()
} else {
None
}
}
}