Compute collation fallback supplement from CLDR #4720
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Manishearth
previously approved these changes
Mar 22, 2024
Manishearth
reviewed
Mar 22, 2024
| @@ -4948,7 +4948,7 @@ displaynames/variants@1, th, 3709B, ed1d48e400b1c35c | |||
| displaynames/variants@1, tr, 1094B, f75a0ab8f0d0bc98 | |||
| fallback/likelysubtags@1, und, 1963B, ea452a518b2defb6 | |||
| fallback/parents@1, und, 2553B, 8f3b5fb7bff27d97 | |||
| fallback/supplement/co@1, und, 70B, 71e01f2099eca417 | |||
| fallback/supplement/co@1, und, 246B, 78151ac4e67429c5 | |||
There was a problem hiding this comment.
is that size increase expected?
There was a problem hiding this comment.
yes if you look at the json it adds a handful of parent relationships
Manishearth
previously approved these changes
Mar 22, 2024
robertbastian
commented
Mar 22, 2024
| @@ -457,8 +457,7 @@ mod tests { | |||
| requires_data: true, | |||
| extension_key: None, | |||
| fallback_supplement: Some(LocaleFallbackSupplement::Collation), | |||
| // TODO(#1964): add "zh" as a target. | |||
| expected_language_chain: &["yue-HK", "yue", "zh-Hant"], | |||
| expected_language_chain: &["yue-HK", "yue", "zh-Hant", "zh"], | |||
Manishearth
approved these changes
Mar 22, 2024
robertbastian
commented
Mar 22, 2024
| static VALUES: [&<icu::collator::provider::CollationReorderingV1Marker as icu_provider::DataMarker>::Yokeable; 50usize] = [&AM, &AR, &AS, &AZ, &BE, &BE, &AS, &AZ, &BE, &CHR, &EL, &AR, &GU, &HE, &HI, &AZ, &HY, &JA, &KA, &BE, &KM, &KN, &KO, &HI, &KU, &BE, &LO, &BE, &ML, &MN, &HI, &MY, &NE, &OR, &PA, &AR, &BE, &SI, &BE, &AZ, &TA, &TE, &TH, &AR, &BE, &AR, &ZH, &ZH_U_CO_STROKE, &ZH_U_CO_STROKE, &ZH_U_CO_STROKE]; | ||
| static KEYS: [&str; 50usize] = ["am", "ar", "as", "az", "be", "bg", "bn", "bs", "bs-Cyrl", "chr", "el", "fa", "gu", "he", "hi", "hr", "hy", "ja", "ka", "kk", "km", "kn", "ko", "kok", "ku", "ky", "lo", "mk", "ml", "mn", "mr", "my", "ne", "or", "pa", "ps", "ru", "si", "sr", "sr-Latn", "ta", "te", "th", "ug", "uk", "ur", "zh", "zh-u-co-stroke", "zh-u-co-unihan", "zh-u-co-zhuyin"]; | ||
| static YUE_U_CO_STROKE: <icu::collator::provider::CollationReorderingV1Marker as icu_provider::DataMarker>::Yokeable = icu::collator::provider::CollationReorderingV1 { min_high_no_reorder: 4261412864u32, reorder_table: unsafe { zerovec::ZeroVec::from_bytes_unchecked(b"\0\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0B\x0C\r\x0E\x0F\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1A\x1B\x1C\x1D\x1E\x1F !\"#$%&'(\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF\xC0\xC1\xC2\xC3\xC4\xC5\xC6\xC7\xC8\xC9\xCA\xCB\xCC\xCD\xCE\xCF\xD0\xD1\xD2\xD3\xD4\xD5\xD6\xD7\xD8\xD9\xDA\xDB\xDC\xDD\xDE\xDD\xDE\xDF\xE0\xE1\xE2\xE3\xE4\xE5\xE6\xE7\xE8\xE9\xEA\xEB\xEC\xED\xEE\xEF\xF0\xF1\xF2\xF3\xF4\xF5\xF6\xF7\0\xF9\xFA'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7F\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xFE\xFF") }, reorder_ranges: unsafe { zerovec::ZeroVec::from_bytes_unchecked(b",\0v{}\0\0~\xA9\xFF\0\xFE") } }; | ||
| static VALUES: [&<icu::collator::provider::CollationReorderingV1Marker as icu_provider::DataMarker>::Yokeable; 56usize] = [&AM, &AR, &AS, &AZ, &BE, &BE, &AS, &AZ, &BE, &CHR, &EL, &AR, &GU, &HE, &HI, &AZ, &HY, &JA, &KA, &BE, &KM, &KN, &KO, &HI, &KU, &BE, &LO, &BE, &ML, &MN, &HI, &MY, &NE, &OR, &PA, &AR, &BE, &SI, &BE, &AZ, &TA, &TE, &TH, &AR, &BE, &AR, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &ZH, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE, &YUE_U_CO_STROKE]; |
There was a problem hiding this comment.
Hmm, I think this is most likely because unicode_extension_defaults is not being used anywhere, so all of these would inherit zh == pinyin if allowed to fall back.
sffc
approved these changes
Mar 26, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#1964