ak/rxing
1
0
Fork 0
mirror of https://github.com/starovoid/rxing.git synced 2026-07-26 04:12:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename character set and rename methods

Browse Source
This commit is contained in:
Henry Schimke
2023-03-04 11:47:39 -06:00
parent c81c6578d0
commit 15859b9f10
29 changed files with 329 additions and 363 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
src/common/string_utils.rs
View File

@@ -16,7 +16,7 @@
use crate::{DecodeHintType, DecodeHintValue, DecodingHintDictionary};
use super::CharacterSetECI;
use super::CharacterSet;
/**
* Common string-related functions.
@@ -48,7 +48,7 @@ const ASSUME_SHIFT_JIS: bool = false;
// static SHIFT_JIS: &'static str = "SJIS";
// static GB2312: &'static str = "GB2312";
pub static SHIFT_JIS_CHARSET: CharacterSetECI = CharacterSetECI::SJIS;
pub static SHIFT_JIS_CHARSET: CharacterSet = CharacterSet::SJIS;
// private static final boolean ASSUME_SHIFT_JIS =
// SHIFT_JIS_CHARSET.equals(PLATFORM_DEFAULT_ENCODING) ||
@@ -64,14 +64,14 @@ impl StringUtils {
*/
pub fn guessEncoding(bytes: &[u8], hints: &DecodingHintDictionary) -> Option<&'static str> {
let c = StringUtils::guessCharset(bytes, hints)?;
if c == CharacterSetECI::SJIS {
if c == CharacterSet::SJIS {
Some("SJIS")
} else if c == CharacterSetECI::UTF8 {
} else if c == CharacterSet::UTF8 {
Some("UTF8")
} else if c == CharacterSetECI::ISO8859_1 {
} else if c == CharacterSet::ISO8859_1 {
Some("ISO8859_1")
} else {
Some(c.getCharsetName())
Some(c.get_charset_name())
}
}
@@ -84,12 +84,12 @@ impl StringUtils {
* or the platform default encoding if
* none of these can possibly be correct
*/
pub fn guessCharset(bytes: &[u8], hints: &DecodingHintDictionary) -> Option<CharacterSetECI> {
pub fn guessCharset(bytes: &[u8], hints: &DecodingHintDictionary) -> Option<CharacterSet> {
if let Some(DecodeHintValue::CharacterSet(cs_name)) =
hints.get(&DecodeHintType::CHARACTER_SET)
{
// if let DecodeHintValue::CharacterSet(cs_name) = hint {
return CharacterSetECI::getCharacterSetECIByName(cs_name);
return CharacterSet::get_character_set_by_name(cs_name);
// }
}
// if hints.contains_key(&DecodeHintType::CHARACTER_SET) {
@@ -101,9 +101,9 @@ impl StringUtils {
&& ((bytes[0] == 0xFE && bytes[1] == 0xFF) || (bytes[0] == 0xFF && bytes[1] == 0xFE))
{
if bytes[0] == 0xFE && bytes[1] == 0xFF {
return Some(CharacterSetECI::UnicodeBigUnmarked);
return Some(CharacterSet::UnicodeBigUnmarked);
} else {
return Some(CharacterSetECI::UTF16LE);
return Some(CharacterSet::UTF16LE);
}
}
@@ -221,7 +221,7 @@ impl StringUtils {
// Easy -- if there is BOM or at least 1 valid not-single byte character (and no evidence it can't be UTF-8), done
if can_be_utf8 && (utf8bom || utf2_bytes_chars + utf3_bytes_chars + utf4_bytes_chars > 0) {
return Some(CharacterSetECI::UTF8);
return Some(CharacterSet::UTF8);
}
// Easy -- if assuming Shift_JIS or >= 3 valid consecutive not-ascii characters (and no evidence it can't be), done
if can_be_shift_jis
@@ -229,7 +229,7 @@ impl StringUtils {
|| sjis_max_katakana_word_length >= 3
|| sjis_max_double_bytes_word_length >= 3)
{
return Some(CharacterSetECI::SJIS); //encoding::label::encoding_from_whatwg_label("SJIS");
return Some(CharacterSet::SJIS); //encoding::label::encoding_from_whatwg_label("SJIS");
}
// Distinguishing Shift_JIS and ISO-8859-1 can be a little tough for short words. The crude heuristic is:
// - If we saw
@@ -240,23 +240,23 @@ impl StringUtils {
return if (sjis_max_katakana_word_length == 2 && sjis_katakana_chars == 2)
|| iso_high_other * 10 >= length
{
Some(CharacterSetECI::SJIS)
Some(CharacterSet::SJIS)
} else {
Some(CharacterSetECI::ISO8859_1)
Some(CharacterSet::ISO8859_1)
};
}
// Otherwise, try in order ISO-8859-1, Shift JIS, UTF-8 and fall back to default platform encoding
if can_be_iso88591 {
return Some(CharacterSetECI::ISO8859_1);
return Some(CharacterSet::ISO8859_1);
}
if can_be_shift_jis {
return Some(CharacterSetECI::SJIS);
return Some(CharacterSet::SJIS);
}
if can_be_utf8 {
return Some(CharacterSetECI::UTF8);
return Some(CharacterSet::UTF8);
}
// Otherwise, we take a wild guess with platform encoding
Some(CharacterSetECI::UTF8)
Some(CharacterSet::UTF8)
}
}