| 968 | |
| 969 | @dataclasses.dataclass |
| 970 | class UcdRecord: |
| 971 | # 15 fields from UnicodeData.txt . See: |
| 972 | # https://www.unicode.org/reports/tr44/#UnicodeData.txt |
| 973 | codepoint: str |
| 974 | name: str |
| 975 | general_category: str |
| 976 | canonical_combining_class: str |
| 977 | bidi_class: str |
| 978 | decomposition_type: str |
| 979 | decomposition_mapping: str |
| 980 | numeric_type: str |
| 981 | numeric_value: str |
| 982 | bidi_mirrored: str |
| 983 | unicode_1_name: str # obsolete |
| 984 | iso_comment: str # obsolete |
| 985 | simple_uppercase_mapping: str |
| 986 | simple_lowercase_mapping: str |
| 987 | simple_titlecase_mapping: str |
| 988 | |
| 989 | # https://www.unicode.org/reports/tr44/#EastAsianWidth.txt |
| 990 | east_asian_width: Optional[str] |
| 991 | |
| 992 | # Binary properties, as a set of those that are true. |
| 993 | # Taken from multiple files: |
| 994 | # https://www.unicode.org/reports/tr44/#DerivedCoreProperties.txt |
| 995 | # https://www.unicode.org/reports/tr44/#LineBreak.txt |
| 996 | binary_properties: Set[str] |
| 997 | |
| 998 | # The Quick_Check properties related to normalization: |
| 999 | # https://www.unicode.org/reports/tr44/#Decompositions_and_Normalization |
| 1000 | # We store them as a bitmask. |
| 1001 | quick_check: int |
| 1002 | |
| 1003 | # The Indic_Conjunct_Break property from DerivedCoreProperties.txt. See: |
| 1004 | # https://www.unicode.org/reports/tr44/#DerivedCoreProperties.txt |
| 1005 | incb: str |
| 1006 | |
| 1007 | |
| 1008 | def from_row(row: List[str]) -> UcdRecord: |
no outgoing calls
no test coverage detected
searching dependent graphs…